summaryrefslogtreecommitdiff
path: root/drivers/accel/habanalabs/gaudi2/gaudi2.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/accel/habanalabs/gaudi2/gaudi2.c')
-rw-r--r--drivers/accel/habanalabs/gaudi2/gaudi2.c487
1 files changed, 406 insertions, 81 deletions
diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index 20c4583f12b0..819660c684cf 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -66,7 +66,6 @@
#define GAUDI2_NUM_OF_TPC_INTR_CAUSE 31
#define GAUDI2_NUM_OF_DEC_ERR_CAUSE 25
#define GAUDI2_NUM_OF_MME_ERR_CAUSE 16
-#define GAUDI2_NUM_OF_MME_SBTE_ERR_CAUSE 5
#define GAUDI2_NUM_OF_MME_WAP_ERR_CAUSE 7
#define GAUDI2_NUM_OF_DMA_CORE_INTR_CAUSE 8
#define GAUDI2_NUM_OF_MMU_SPI_SEI_CAUSE 19
@@ -916,14 +915,6 @@ static const char * const guadi2_mme_error_cause[GAUDI2_NUM_OF_MME_ERR_CAUSE] =
"sbte_prtn_intr_4",
};
-static const char * const guadi2_mme_sbte_error_cause[GAUDI2_NUM_OF_MME_SBTE_ERR_CAUSE] = {
- "i0",
- "i1",
- "i2",
- "i3",
- "i4",
-};
-
static const char * const guadi2_mme_wap_error_cause[GAUDI2_NUM_OF_MME_WAP_ERR_CAUSE] = {
"WBC ERR RESP_0",
"WBC ERR RESP_1",
@@ -993,6 +984,111 @@ gaudi2_pcie_addr_dec_error_cause[GAUDI2_NUM_OF_PCIE_ADDR_DEC_ERR_CAUSE] = {
"TLP is blocked by RR"
};
+static const int gaudi2_queue_id_to_engine_id[] = {
+ [GAUDI2_QUEUE_ID_PDMA_0_0...GAUDI2_QUEUE_ID_PDMA_0_3] = GAUDI2_ENGINE_ID_PDMA_0,
+ [GAUDI2_QUEUE_ID_PDMA_1_0...GAUDI2_QUEUE_ID_PDMA_1_3] = GAUDI2_ENGINE_ID_PDMA_1,
+ [GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE0_EDMA_0_3] =
+ GAUDI2_DCORE0_ENGINE_ID_EDMA_0,
+ [GAUDI2_QUEUE_ID_DCORE0_EDMA_1_0...GAUDI2_QUEUE_ID_DCORE0_EDMA_1_3] =
+ GAUDI2_DCORE0_ENGINE_ID_EDMA_1,
+ [GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE1_EDMA_0_3] =
+ GAUDI2_DCORE1_ENGINE_ID_EDMA_0,
+ [GAUDI2_QUEUE_ID_DCORE1_EDMA_1_0...GAUDI2_QUEUE_ID_DCORE1_EDMA_1_3] =
+ GAUDI2_DCORE1_ENGINE_ID_EDMA_1,
+ [GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE2_EDMA_0_3] =
+ GAUDI2_DCORE2_ENGINE_ID_EDMA_0,
+ [GAUDI2_QUEUE_ID_DCORE2_EDMA_1_0...GAUDI2_QUEUE_ID_DCORE2_EDMA_1_3] =
+ GAUDI2_DCORE2_ENGINE_ID_EDMA_1,
+ [GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0...GAUDI2_QUEUE_ID_DCORE3_EDMA_0_3] =
+ GAUDI2_DCORE3_ENGINE_ID_EDMA_0,
+ [GAUDI2_QUEUE_ID_DCORE3_EDMA_1_0...GAUDI2_QUEUE_ID_DCORE3_EDMA_1_3] =
+ GAUDI2_DCORE3_ENGINE_ID_EDMA_1,
+ [GAUDI2_QUEUE_ID_DCORE0_MME_0_0...GAUDI2_QUEUE_ID_DCORE0_MME_0_3] =
+ GAUDI2_DCORE0_ENGINE_ID_MME,
+ [GAUDI2_QUEUE_ID_DCORE1_MME_0_0...GAUDI2_QUEUE_ID_DCORE1_MME_0_3] =
+ GAUDI2_DCORE1_ENGINE_ID_MME,
+ [GAUDI2_QUEUE_ID_DCORE2_MME_0_0...GAUDI2_QUEUE_ID_DCORE2_MME_0_3] =
+ GAUDI2_DCORE2_ENGINE_ID_MME,
+ [GAUDI2_QUEUE_ID_DCORE3_MME_0_0...GAUDI2_QUEUE_ID_DCORE3_MME_0_3] =
+ GAUDI2_DCORE3_ENGINE_ID_MME,
+ [GAUDI2_QUEUE_ID_DCORE0_TPC_0_0...GAUDI2_QUEUE_ID_DCORE0_TPC_0_3] =
+ GAUDI2_DCORE0_ENGINE_ID_TPC_0,
+ [GAUDI2_QUEUE_ID_DCORE0_TPC_1_0...GAUDI2_QUEUE_ID_DCORE0_TPC_1_3] =
+ GAUDI2_DCORE0_ENGINE_ID_TPC_1,
+ [GAUDI2_QUEUE_ID_DCORE0_TPC_2_0...GAUDI2_QUEUE_ID_DCORE0_TPC_2_3] =
+ GAUDI2_DCORE0_ENGINE_ID_TPC_2,
+ [GAUDI2_QUEUE_ID_DCORE0_TPC_3_0...GAUDI2_QUEUE_ID_DCORE0_TPC_3_3] =
+ GAUDI2_DCORE0_ENGINE_ID_TPC_3,
+ [GAUDI2_QUEUE_ID_DCORE0_TPC_4_0...GAUDI2_QUEUE_ID_DCORE0_TPC_4_3] =
+ GAUDI2_DCORE0_ENGINE_ID_TPC_4,
+ [GAUDI2_QUEUE_ID_DCORE0_TPC_5_0...GAUDI2_QUEUE_ID_DCORE0_TPC_5_3] =
+ GAUDI2_DCORE0_ENGINE_ID_TPC_5,
+ [GAUDI2_QUEUE_ID_DCORE0_TPC_6_0...GAUDI2_QUEUE_ID_DCORE0_TPC_6_3] =
+ GAUDI2_DCORE0_ENGINE_ID_TPC_6,
+ [GAUDI2_QUEUE_ID_DCORE1_TPC_0_0...GAUDI2_QUEUE_ID_DCORE1_TPC_0_3] =
+ GAUDI2_DCORE1_ENGINE_ID_TPC_0,
+ [GAUDI2_QUEUE_ID_DCORE1_TPC_1_0...GAUDI2_QUEUE_ID_DCORE1_TPC_1_3] =
+ GAUDI2_DCORE1_ENGINE_ID_TPC_1,
+ [GAUDI2_QUEUE_ID_DCORE1_TPC_2_0...GAUDI2_QUEUE_ID_DCORE1_TPC_2_3] =
+ GAUDI2_DCORE1_ENGINE_ID_TPC_2,
+ [GAUDI2_QUEUE_ID_DCORE1_TPC_3_0...GAUDI2_QUEUE_ID_DCORE1_TPC_3_3] =
+ GAUDI2_DCORE1_ENGINE_ID_TPC_3,
+ [GAUDI2_QUEUE_ID_DCORE1_TPC_4_0...GAUDI2_QUEUE_ID_DCORE1_TPC_4_3] =
+ GAUDI2_DCORE1_ENGINE_ID_TPC_4,
+ [GAUDI2_QUEUE_ID_DCORE1_TPC_5_0...GAUDI2_QUEUE_ID_DCORE1_TPC_5_3] =
+ GAUDI2_DCORE1_ENGINE_ID_TPC_5,
+ [GAUDI2_QUEUE_ID_DCORE2_TPC_0_0...GAUDI2_QUEUE_ID_DCORE2_TPC_0_3] =
+ GAUDI2_DCORE2_ENGINE_ID_TPC_0,
+ [GAUDI2_QUEUE_ID_DCORE2_TPC_1_0...GAUDI2_QUEUE_ID_DCORE2_TPC_1_3] =
+ GAUDI2_DCORE2_ENGINE_ID_TPC_1,
+ [GAUDI2_QUEUE_ID_DCORE2_TPC_2_0...GAUDI2_QUEUE_ID_DCORE2_TPC_2_3] =
+ GAUDI2_DCORE2_ENGINE_ID_TPC_2,
+ [GAUDI2_QUEUE_ID_DCORE2_TPC_3_0...GAUDI2_QUEUE_ID_DCORE2_TPC_3_3] =
+ GAUDI2_DCORE2_ENGINE_ID_TPC_3,
+ [GAUDI2_QUEUE_ID_DCORE2_TPC_4_0...GAUDI2_QUEUE_ID_DCORE2_TPC_4_3] =
+ GAUDI2_DCORE2_ENGINE_ID_TPC_4,
+ [GAUDI2_QUEUE_ID_DCORE2_TPC_5_0...GAUDI2_QUEUE_ID_DCORE2_TPC_5_3] =
+ GAUDI2_DCORE2_ENGINE_ID_TPC_5,
+ [GAUDI2_QUEUE_ID_DCORE3_TPC_0_0...GAUDI2_QUEUE_ID_DCORE3_TPC_0_3] =
+ GAUDI2_DCORE3_ENGINE_ID_TPC_0,
+ [GAUDI2_QUEUE_ID_DCORE3_TPC_1_0...GAUDI2_QUEUE_ID_DCORE3_TPC_1_3] =
+ GAUDI2_DCORE3_ENGINE_ID_TPC_1,
+ [GAUDI2_QUEUE_ID_DCORE3_TPC_2_0...GAUDI2_QUEUE_ID_DCORE3_TPC_2_3] =
+ GAUDI2_DCORE3_ENGINE_ID_TPC_2,
+ [GAUDI2_QUEUE_ID_DCORE3_TPC_3_0...GAUDI2_QUEUE_ID_DCORE3_TPC_3_3] =
+ GAUDI2_DCORE3_ENGINE_ID_TPC_3,
+ [GAUDI2_QUEUE_ID_DCORE3_TPC_4_0...GAUDI2_QUEUE_ID_DCORE3_TPC_4_3] =
+ GAUDI2_DCORE3_ENGINE_ID_TPC_4,
+ [GAUDI2_QUEUE_ID_DCORE3_TPC_5_0...GAUDI2_QUEUE_ID_DCORE3_TPC_5_3] =
+ GAUDI2_DCORE3_ENGINE_ID_TPC_5,
+ [GAUDI2_QUEUE_ID_NIC_0_0...GAUDI2_QUEUE_ID_NIC_0_3] = GAUDI2_ENGINE_ID_NIC0_0,
+ [GAUDI2_QUEUE_ID_NIC_1_0...GAUDI2_QUEUE_ID_NIC_1_3] = GAUDI2_ENGINE_ID_NIC0_1,
+ [GAUDI2_QUEUE_ID_NIC_2_0...GAUDI2_QUEUE_ID_NIC_2_3] = GAUDI2_ENGINE_ID_NIC1_0,
+ [GAUDI2_QUEUE_ID_NIC_3_0...GAUDI2_QUEUE_ID_NIC_3_3] = GAUDI2_ENGINE_ID_NIC1_1,
+ [GAUDI2_QUEUE_ID_NIC_4_0...GAUDI2_QUEUE_ID_NIC_4_3] = GAUDI2_ENGINE_ID_NIC2_0,
+ [GAUDI2_QUEUE_ID_NIC_5_0...GAUDI2_QUEUE_ID_NIC_5_3] = GAUDI2_ENGINE_ID_NIC2_1,
+ [GAUDI2_QUEUE_ID_NIC_6_0...GAUDI2_QUEUE_ID_NIC_6_3] = GAUDI2_ENGINE_ID_NIC3_0,
+ [GAUDI2_QUEUE_ID_NIC_7_0...GAUDI2_QUEUE_ID_NIC_7_3] = GAUDI2_ENGINE_ID_NIC3_1,
+ [GAUDI2_QUEUE_ID_NIC_8_0...GAUDI2_QUEUE_ID_NIC_8_3] = GAUDI2_ENGINE_ID_NIC4_0,
+ [GAUDI2_QUEUE_ID_NIC_9_0...GAUDI2_QUEUE_ID_NIC_9_3] = GAUDI2_ENGINE_ID_NIC4_1,
+ [GAUDI2_QUEUE_ID_NIC_10_0...GAUDI2_QUEUE_ID_NIC_10_3] = GAUDI2_ENGINE_ID_NIC5_0,
+ [GAUDI2_QUEUE_ID_NIC_11_0...GAUDI2_QUEUE_ID_NIC_11_3] = GAUDI2_ENGINE_ID_NIC5_1,
+ [GAUDI2_QUEUE_ID_NIC_12_0...GAUDI2_QUEUE_ID_NIC_12_3] = GAUDI2_ENGINE_ID_NIC6_0,
+ [GAUDI2_QUEUE_ID_NIC_13_0...GAUDI2_QUEUE_ID_NIC_13_3] = GAUDI2_ENGINE_ID_NIC6_1,
+ [GAUDI2_QUEUE_ID_NIC_14_0...GAUDI2_QUEUE_ID_NIC_14_3] = GAUDI2_ENGINE_ID_NIC7_0,
+ [GAUDI2_QUEUE_ID_NIC_15_0...GAUDI2_QUEUE_ID_NIC_15_3] = GAUDI2_ENGINE_ID_NIC7_1,
+ [GAUDI2_QUEUE_ID_NIC_16_0...GAUDI2_QUEUE_ID_NIC_16_3] = GAUDI2_ENGINE_ID_NIC8_0,
+ [GAUDI2_QUEUE_ID_NIC_17_0...GAUDI2_QUEUE_ID_NIC_17_3] = GAUDI2_ENGINE_ID_NIC8_1,
+ [GAUDI2_QUEUE_ID_NIC_18_0...GAUDI2_QUEUE_ID_NIC_18_3] = GAUDI2_ENGINE_ID_NIC9_0,
+ [GAUDI2_QUEUE_ID_NIC_19_0...GAUDI2_QUEUE_ID_NIC_19_3] = GAUDI2_ENGINE_ID_NIC9_1,
+ [GAUDI2_QUEUE_ID_NIC_20_0...GAUDI2_QUEUE_ID_NIC_20_3] = GAUDI2_ENGINE_ID_NIC10_0,
+ [GAUDI2_QUEUE_ID_NIC_21_0...GAUDI2_QUEUE_ID_NIC_21_3] = GAUDI2_ENGINE_ID_NIC10_1,
+ [GAUDI2_QUEUE_ID_NIC_22_0...GAUDI2_QUEUE_ID_NIC_22_3] = GAUDI2_ENGINE_ID_NIC11_0,
+ [GAUDI2_QUEUE_ID_NIC_23_0...GAUDI2_QUEUE_ID_NIC_23_3] = GAUDI2_ENGINE_ID_NIC11_1,
+ [GAUDI2_QUEUE_ID_ROT_0_0...GAUDI2_QUEUE_ID_ROT_0_3] = GAUDI2_ENGINE_ID_ROT_0,
+ [GAUDI2_QUEUE_ID_ROT_1_0...GAUDI2_QUEUE_ID_ROT_1_3] = GAUDI2_ENGINE_ID_ROT_1,
+};
+
const u32 gaudi2_qm_blocks_bases[GAUDI2_QUEUE_ID_SIZE] = {
[GAUDI2_QUEUE_ID_PDMA_0_0] = mmPDMA0_QM_BASE,
[GAUDI2_QUEUE_ID_PDMA_0_1] = mmPDMA0_QM_BASE,
@@ -2001,7 +2097,8 @@ enum razwi_event_sources {
RAZWI_PDMA,
RAZWI_NIC,
RAZWI_DEC,
- RAZWI_ROT
+ RAZWI_ROT,
+ RAZWI_ARC_FARM
};
struct hbm_mc_error_causes {
@@ -2431,7 +2528,7 @@ static int gaudi2_set_fixed_properties(struct hl_device *hdev)
prop->pcie_dbi_base_address = CFG_BASE + mmPCIE_DBI_BASE;
prop->pcie_aux_dbi_reg_addr = CFG_BASE + mmPCIE_AUX_DBI;
- strncpy(prop->cpucp_info.card_name, GAUDI2_DEFAULT_CARD_NAME, CARD_NAME_MAX_LEN);
+ strscpy_pad(prop->cpucp_info.card_name, GAUDI2_DEFAULT_CARD_NAME, CARD_NAME_MAX_LEN);
prop->mme_master_slave_mode = 1;
@@ -2884,7 +2981,8 @@ static int gaudi2_cpucp_info_get(struct hl_device *hdev)
}
if (!strlen(prop->cpucp_info.card_name))
- strncpy(prop->cpucp_info.card_name, GAUDI2_DEFAULT_CARD_NAME, CARD_NAME_MAX_LEN);
+ strscpy_pad(prop->cpucp_info.card_name, GAUDI2_DEFAULT_CARD_NAME,
+ CARD_NAME_MAX_LEN);
/* Overwrite binning masks with the actual binning values from F/W */
hdev->dram_binning = prop->cpucp_info.dram_binning_mask;
@@ -4077,6 +4175,8 @@ static const char *gaudi2_irq_name(u16 irq_number)
return "gaudi2 unexpected error";
case GAUDI2_IRQ_NUM_USER_FIRST ... GAUDI2_IRQ_NUM_USER_LAST:
return "gaudi2 user completion";
+ case GAUDI2_IRQ_NUM_EQ_ERROR:
+ return "gaudi2 eq error";
default:
return "invalid";
}
@@ -4127,9 +4227,7 @@ static int gaudi2_dec_enable_msix(struct hl_device *hdev)
rc = request_irq(irq, hl_irq_handler_dec_abnrm, 0,
gaudi2_irq_name(i), (void *) dec);
} else {
- rc = request_threaded_irq(irq, hl_irq_handler_user_interrupt,
- hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
- gaudi2_irq_name(i),
+ rc = request_irq(irq, hl_irq_user_interrupt_handler, 0, gaudi2_irq_name(i),
(void *) &hdev->user_interrupt[dec->core_id]);
}
@@ -4187,17 +4285,17 @@ static int gaudi2_enable_msix(struct hl_device *hdev)
}
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_TPC_ASSERT);
- rc = request_threaded_irq(irq, hl_irq_handler_user_interrupt,
- hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
- gaudi2_irq_name(GAUDI2_IRQ_NUM_TPC_ASSERT), &hdev->tpc_interrupt);
+ rc = request_threaded_irq(irq, NULL, hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
+ gaudi2_irq_name(GAUDI2_IRQ_NUM_TPC_ASSERT),
+ &hdev->tpc_interrupt);
if (rc) {
dev_err(hdev->dev, "Failed to request IRQ %d", irq);
goto free_dec_irq;
}
irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_UNEXPECTED_ERROR);
- rc = request_irq(irq, hl_irq_handler_user_interrupt, 0,
- gaudi2_irq_name(GAUDI2_IRQ_NUM_UNEXPECTED_ERROR),
+ rc = request_threaded_irq(irq, NULL, hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
+ gaudi2_irq_name(GAUDI2_IRQ_NUM_UNEXPECTED_ERROR),
&hdev->unexpected_error_interrupt);
if (rc) {
dev_err(hdev->dev, "Failed to request IRQ %d", irq);
@@ -4209,16 +4307,23 @@ static int gaudi2_enable_msix(struct hl_device *hdev)
i++, j++, user_irq_init_cnt++) {
irq = pci_irq_vector(hdev->pdev, i);
- rc = request_threaded_irq(irq, hl_irq_handler_user_interrupt,
- hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
- gaudi2_irq_name(i), &hdev->user_interrupt[j]);
-
+ rc = request_irq(irq, hl_irq_user_interrupt_handler, 0, gaudi2_irq_name(i),
+ &hdev->user_interrupt[j]);
if (rc) {
dev_err(hdev->dev, "Failed to request IRQ %d", irq);
goto free_user_irq;
}
}
+ irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_EQ_ERROR);
+ rc = request_threaded_irq(irq, NULL, hl_irq_eq_error_interrupt_thread_handler,
+ IRQF_ONESHOT, gaudi2_irq_name(GAUDI2_IRQ_NUM_EQ_ERROR),
+ hdev);
+ if (rc) {
+ dev_err(hdev->dev, "Failed to request IRQ %d", irq);
+ goto free_user_irq;
+ }
+
gaudi2->hw_cap_initialized |= HW_CAP_MSIX;
return 0;
@@ -4278,6 +4383,7 @@ static void gaudi2_sync_irqs(struct hl_device *hdev)
}
synchronize_irq(pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_EVENT_QUEUE));
+ synchronize_irq(pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_EQ_ERROR));
}
static void gaudi2_disable_msix(struct hl_device *hdev)
@@ -4314,6 +4420,9 @@ static void gaudi2_disable_msix(struct hl_device *hdev)
cq = &hdev->completion_queue[GAUDI2_RESERVED_CQ_CS_COMPLETION];
free_irq(irq, cq);
+ irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_EQ_ERROR);
+ free_irq(irq, hdev);
+
pci_free_irq_vectors(hdev->pdev);
gaudi2->hw_cap_initialized &= ~HW_CAP_MSIX;
@@ -4716,6 +4825,8 @@ static void gaudi2_init_firmware_preload_params(struct hl_device *hdev)
pre_fw_load->boot_err0_reg = mmCPU_BOOT_ERR0;
pre_fw_load->boot_err1_reg = mmCPU_BOOT_ERR1;
pre_fw_load->wait_for_preboot_timeout = GAUDI2_PREBOOT_REQ_TIMEOUT_USEC;
+ pre_fw_load->wait_for_preboot_extended_timeout =
+ GAUDI2_PREBOOT_EXTENDED_REQ_TIMEOUT_USEC;
}
static void gaudi2_init_firmware_loader(struct hl_device *hdev)
@@ -6157,17 +6268,14 @@ static int gaudi2_get_soft_rst_done_indication(struct hl_device *hdev, u32 poll_
static int gaudi2_execute_soft_reset(struct hl_device *hdev, bool driver_performs_reset,
u32 poll_timeout_us)
{
- struct cpu_dyn_regs *dyn_regs = &hdev->fw_loader.dynamic_loader.comm_desc.cpu_dyn_regs;
- int rc = 0;
+ int rc;
if (!driver_performs_reset) {
if (hl_is_fw_sw_ver_below(hdev, 1, 10)) {
/* set SP to indicate reset request sent to FW */
- if (dyn_regs->cpu_rst_status)
- WREG32(le32_to_cpu(dyn_regs->cpu_rst_status), CPU_RST_STATUS_NA);
- else
- WREG32(mmCPU_RST_STATUS_TO_HOST, CPU_RST_STATUS_NA);
- WREG32(le32_to_cpu(dyn_regs->gic_host_soft_rst_irq),
+ WREG32(mmCPU_RST_STATUS_TO_HOST, CPU_RST_STATUS_NA);
+
+ WREG32(mmGIC_HOST_SOFT_RST_IRQ_POLL_REG,
gaudi2_irq_map_table[GAUDI2_EVENT_CPU_SOFT_RESET].cpu_id);
/* wait for f/w response */
@@ -6623,24 +6731,6 @@ static void gaudi2_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t s
hl_fw_cpu_accessible_dma_pool_free(hdev, size, vaddr);
}
-static dma_addr_t gaudi2_dma_map_single(struct hl_device *hdev, void *addr, int len,
- enum dma_data_direction dir)
-{
- dma_addr_t dma_addr;
-
- dma_addr = dma_map_single(&hdev->pdev->dev, addr, len, dir);
- if (unlikely(dma_mapping_error(&hdev->pdev->dev, dma_addr)))
- return 0;
-
- return dma_addr;
-}
-
-static void gaudi2_dma_unmap_single(struct hl_device *hdev, dma_addr_t addr, int len,
- enum dma_data_direction dir)
-{
- dma_unmap_single(&hdev->pdev->dev, addr, len, dir);
-}
-
static int gaudi2_validate_cb_address(struct hl_device *hdev, struct hl_cs_parser *parser)
{
struct asic_fixed_properties *asic_prop = &hdev->asic_prop;
@@ -7703,11 +7793,13 @@ static inline bool is_info_event(u32 event)
switch (event) {
case GAUDI2_EVENT_CPU_CPLD_SHUTDOWN_CAUSE:
case GAUDI2_EVENT_CPU_FIX_POWER_ENV_S ... GAUDI2_EVENT_CPU_FIX_THERMAL_ENV_E:
+ case GAUDI2_EVENT_ARC_PWR_BRK_ENTRY ... GAUDI2_EVENT_ARC_PWR_RD_MODE3:
/* return in case of NIC status event - these events are received periodically and not as
* an indication to an error.
*/
case GAUDI2_EVENT_CPU0_STATUS_NIC0_ENG0 ... GAUDI2_EVENT_CPU11_STATUS_NIC11_ENG1:
+ case GAUDI2_EVENT_ARC_EQ_HEARTBEAT:
return true;
default:
return false;
@@ -7739,21 +7831,34 @@ static void gaudi2_print_event(struct hl_device *hdev, u16 event_type,
static bool gaudi2_handle_ecc_event(struct hl_device *hdev, u16 event_type,
struct hl_eq_ecc_data *ecc_data)
{
- u64 ecc_address = 0, ecc_syndrom = 0;
+ u64 ecc_address = 0, ecc_syndrome = 0;
u8 memory_wrapper_idx = 0;
+ bool has_block_id = false;
+ u16 block_id;
+
+ if (!hl_is_fw_sw_ver_below(hdev, 1, 12))
+ has_block_id = true;
ecc_address = le64_to_cpu(ecc_data->ecc_address);
- ecc_syndrom = le64_to_cpu(ecc_data->ecc_syndrom);
+ ecc_syndrome = le64_to_cpu(ecc_data->ecc_syndrom);
memory_wrapper_idx = ecc_data->memory_wrapper_idx;
- gaudi2_print_event(hdev, event_type, !ecc_data->is_critical,
- "ECC error detected. address: %#llx. Syndrom: %#llx. block id %u. critical %u.",
- ecc_address, ecc_syndrom, memory_wrapper_idx, ecc_data->is_critical);
+ if (has_block_id) {
+ block_id = le16_to_cpu(ecc_data->block_id);
+ gaudi2_print_event(hdev, event_type, !ecc_data->is_critical,
+ "ECC error detected. address: %#llx. Syndrome: %#llx. wrapper id %u. block id %#x. critical %u.",
+ ecc_address, ecc_syndrome, memory_wrapper_idx, block_id,
+ ecc_data->is_critical);
+ } else {
+ gaudi2_print_event(hdev, event_type, !ecc_data->is_critical,
+ "ECC error detected. address: %#llx. Syndrome: %#llx. wrapper id %u. critical %u.",
+ ecc_address, ecc_syndrome, memory_wrapper_idx, ecc_data->is_critical);
+ }
return !!ecc_data->is_critical;
}
-static void print_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base)
+static void handle_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base, u64 event_mask)
{
u32 lo, hi, cq_ptr_size, arc_cq_ptr_size;
u64 cq_ptr, arc_cq_ptr, cp_current_inst;
@@ -7775,10 +7880,22 @@ static void print_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base)
dev_info(hdev->dev,
"LowerQM. CQ: {ptr %#llx, size %u}, ARC_CQ: {ptr %#llx, size %u}, CP: {instruction %#llx}\n",
cq_ptr, cq_ptr_size, arc_cq_ptr, arc_cq_ptr_size, cp_current_inst);
+
+ if (event_mask & HL_NOTIFIER_EVENT_UNDEFINED_OPCODE) {
+ if (arc_cq_ptr) {
+ hdev->captured_err_info.undef_opcode.cq_addr = arc_cq_ptr;
+ hdev->captured_err_info.undef_opcode.cq_size = arc_cq_ptr_size;
+ } else {
+ hdev->captured_err_info.undef_opcode.cq_addr = cq_ptr;
+ hdev->captured_err_info.undef_opcode.cq_size = cq_ptr_size;
+ }
+
+ hdev->captured_err_info.undef_opcode.stream_id = QMAN_STREAMS;
+ }
}
static int gaudi2_handle_qman_err_generic(struct hl_device *hdev, u16 event_type,
- u64 qman_base, u32 qid_base)
+ u64 qman_base, u32 qid_base, u64 *event_mask)
{
u32 i, j, glbl_sts_val, arb_err_val, num_error_causes, error_count = 0;
u64 glbl_sts_addr, arb_err_addr;
@@ -7812,8 +7929,22 @@ static int gaudi2_handle_qman_err_generic(struct hl_device *hdev, u16 event_type
error_count++;
}
- if (i == QMAN_STREAMS)
- print_lower_qman_data_on_err(hdev, qman_base);
+ if (i == QMAN_STREAMS && error_count) {
+ /* check for undefined opcode */
+ if (glbl_sts_val & PDMA0_QM_GLBL_ERR_STS_CP_UNDEF_CMD_ERR_MASK &&
+ hdev->captured_err_info.undef_opcode.write_enable) {
+ memset(&hdev->captured_err_info.undef_opcode, 0,
+ sizeof(hdev->captured_err_info.undef_opcode));
+
+ hdev->captured_err_info.undef_opcode.write_enable = false;
+ hdev->captured_err_info.undef_opcode.timestamp = ktime_get();
+ hdev->captured_err_info.undef_opcode.engine_id =
+ gaudi2_queue_id_to_engine_id[qid_base];
+ *event_mask |= HL_NOTIFIER_EVENT_UNDEFINED_OPCODE;
+ }
+
+ handle_lower_qman_data_on_err(hdev, qman_base, *event_mask);
+ }
}
arb_err_val = RREG32(arb_err_addr);
@@ -7927,6 +8058,9 @@ static enum gaudi2_engine_id gaudi2_razwi_calc_engine_id(struct hl_device *hdev,
case RAZWI_ROT:
return GAUDI2_ENGINE_ID_ROT_0 + module_idx;
+ case RAZWI_ARC_FARM:
+ return GAUDI2_ENGINE_ID_ARC_FARM;
+
default:
return GAUDI2_ENGINE_ID_SIZE;
}
@@ -8036,6 +8170,11 @@ static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
lbw_rtr_id = gaudi2_rot_initiator_lbw_rtr_id[module_idx];
sprintf(initiator_name, "ROT_%u", module_idx);
break;
+ case RAZWI_ARC_FARM:
+ lbw_rtr_id = DCORE1_RTR5;
+ hbw_rtr_id = DCORE1_RTR7;
+ sprintf(initiator_name, "ARC_FARM_%u", module_idx);
+ break;
default:
return;
}
@@ -8149,11 +8288,11 @@ static int gaudi2_psoc_razwi_get_engines(struct gaudi2_razwi_info *razwi_info, u
eng_id[num_of_eng] = razwi_info[i].eng_id;
base[num_of_eng] = razwi_info[i].rtr_ctrl;
if (!num_of_eng)
- str_size += snprintf(eng_name + str_size,
+ str_size += scnprintf(eng_name + str_size,
PSOC_RAZWI_ENG_STR_SIZE - str_size, "%s",
razwi_info[i].eng_name);
else
- str_size += snprintf(eng_name + str_size,
+ str_size += scnprintf(eng_name + str_size,
PSOC_RAZWI_ENG_STR_SIZE - str_size, " or %s",
razwi_info[i].eng_name);
num_of_eng++;
@@ -8475,7 +8614,8 @@ static int gaudi2_handle_qman_err(struct hl_device *hdev, u16 event_type, u64 *e
return 0;
}
- error_count = gaudi2_handle_qman_err_generic(hdev, event_type, qman_base, qid_base);
+ error_count = gaudi2_handle_qman_err_generic(hdev, event_type, qman_base,
+ qid_base, event_mask);
/* 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) {
@@ -8488,7 +8628,7 @@ static int gaudi2_handle_qman_err(struct hl_device *hdev, u16 event_type, u64 *e
return error_count;
}
-static int gaudi2_handle_arc_farm_sei_err(struct hl_device *hdev, u16 event_type)
+static int gaudi2_handle_arc_farm_sei_err(struct hl_device *hdev, u16 event_type, u64 *event_mask)
{
u32 i, sts_val, sts_clr_val, error_count = 0, arc_farm;
@@ -8510,6 +8650,7 @@ static int gaudi2_handle_arc_farm_sei_err(struct hl_device *hdev, u16 event_type
sts_clr_val);
}
+ gaudi2_ack_module_razwi_event_handler(hdev, RAZWI_ARC_FARM, 0, 0, event_mask);
hl_check_for_glbl_errors(hdev);
return error_count;
@@ -8649,21 +8790,16 @@ static int gaudi2_handle_mme_err(struct hl_device *hdev, u8 mme_index, u16 event
return error_count;
}
-static int gaudi2_handle_mme_sbte_err(struct hl_device *hdev, u16 event_type,
- u64 intr_cause_data)
+static int gaudi2_handle_mme_sbte_err(struct hl_device *hdev, u16 event_type)
{
- int i, error_count = 0;
-
- for (i = 0 ; i < GAUDI2_NUM_OF_MME_SBTE_ERR_CAUSE ; i++)
- if (intr_cause_data & BIT(i)) {
- gaudi2_print_event(hdev, event_type, true,
- "err cause: %s", guadi2_mme_sbte_error_cause[i]);
- error_count++;
- }
-
+ /*
+ * We have a single error cause here but the report mechanism is
+ * buggy. Hence there is no good reason to fetch the cause so we
+ * just check for glbl_errors and exit.
+ */
hl_check_for_glbl_errors(hdev);
- return error_count;
+ return GAUDI2_NA_EVENT_CAUSE;
}
static int gaudi2_handle_mme_wap_err(struct hl_device *hdev, u8 mme_index, u16 event_type,
@@ -9460,6 +9596,176 @@ static int hl_arc_event_handle(struct hl_device *hdev, u16 event_type,
}
}
+static u16 event_id_to_engine_id(struct hl_device *hdev, u16 event_type)
+{
+ enum gaudi2_block_types type = GAUDI2_BLOCK_TYPE_MAX;
+ u16 index;
+
+ switch (event_type) {
+ case GAUDI2_EVENT_TPC0_AXI_ERR_RSP ... GAUDI2_EVENT_TPC24_AXI_ERR_RSP:
+ index = event_type - GAUDI2_EVENT_TPC0_AXI_ERR_RSP;
+ type = GAUDI2_BLOCK_TYPE_TPC;
+ break;
+ case GAUDI2_EVENT_TPC0_QM ... GAUDI2_EVENT_TPC24_QM:
+ index = event_type - GAUDI2_EVENT_TPC0_QM;
+ type = GAUDI2_BLOCK_TYPE_TPC;
+ break;
+ case GAUDI2_EVENT_MME0_SBTE0_AXI_ERR_RSP ... GAUDI2_EVENT_MME0_CTRL_AXI_ERROR_RESPONSE:
+ case GAUDI2_EVENT_MME0_SPI_BASE ... GAUDI2_EVENT_MME0_WAP_SOURCE_RESULT_INVALID:
+ case GAUDI2_EVENT_MME0_QM:
+ index = 0;
+ type = GAUDI2_BLOCK_TYPE_MME;
+ break;
+ case GAUDI2_EVENT_MME1_SBTE0_AXI_ERR_RSP ... GAUDI2_EVENT_MME1_CTRL_AXI_ERROR_RESPONSE:
+ case GAUDI2_EVENT_MME1_SPI_BASE ... GAUDI2_EVENT_MME1_WAP_SOURCE_RESULT_INVALID:
+ case GAUDI2_EVENT_MME1_QM:
+ index = 1;
+ type = GAUDI2_BLOCK_TYPE_MME;
+ break;
+ case GAUDI2_EVENT_MME2_SBTE0_AXI_ERR_RSP ... GAUDI2_EVENT_MME2_CTRL_AXI_ERROR_RESPONSE:
+ case GAUDI2_EVENT_MME2_SPI_BASE ... GAUDI2_EVENT_MME2_WAP_SOURCE_RESULT_INVALID:
+ case GAUDI2_EVENT_MME2_QM:
+ index = 2;
+ type = GAUDI2_BLOCK_TYPE_MME;
+ break;
+ case GAUDI2_EVENT_MME3_SBTE0_AXI_ERR_RSP ... GAUDI2_EVENT_MME3_CTRL_AXI_ERROR_RESPONSE:
+ case GAUDI2_EVENT_MME3_SPI_BASE ... GAUDI2_EVENT_MME3_WAP_SOURCE_RESULT_INVALID:
+ case GAUDI2_EVENT_MME3_QM:
+ index = 3;
+ type = GAUDI2_BLOCK_TYPE_MME;
+ break;
+ case GAUDI2_EVENT_KDMA_CH0_AXI_ERR_RSP:
+ case GAUDI2_EVENT_KDMA_BM_SPMU:
+ case GAUDI2_EVENT_KDMA0_CORE:
+ return GAUDI2_ENGINE_ID_KDMA;
+ case GAUDI2_EVENT_PDMA_CH0_AXI_ERR_RSP:
+ case GAUDI2_EVENT_PDMA0_CORE:
+ case GAUDI2_EVENT_PDMA0_BM_SPMU:
+ case GAUDI2_EVENT_PDMA0_QM:
+ return GAUDI2_ENGINE_ID_PDMA_0;
+ case GAUDI2_EVENT_PDMA_CH1_AXI_ERR_RSP:
+ case GAUDI2_EVENT_PDMA1_CORE:
+ case GAUDI2_EVENT_PDMA1_BM_SPMU:
+ case GAUDI2_EVENT_PDMA1_QM:
+ return GAUDI2_ENGINE_ID_PDMA_1;
+ case GAUDI2_EVENT_DEC0_AXI_ERR_RSPONSE ... GAUDI2_EVENT_DEC9_AXI_ERR_RSPONSE:
+ index = event_type - GAUDI2_EVENT_DEC0_AXI_ERR_RSPONSE;
+ type = GAUDI2_BLOCK_TYPE_DEC;
+ break;
+ case GAUDI2_EVENT_DEC0_SPI ... GAUDI2_EVENT_DEC9_BMON_SPMU:
+ index = (event_type - GAUDI2_EVENT_DEC0_SPI) >> 1;
+ type = GAUDI2_BLOCK_TYPE_DEC;
+ break;
+ case GAUDI2_EVENT_NIC0_AXI_ERROR_RESPONSE ... GAUDI2_EVENT_NIC11_AXI_ERROR_RESPONSE:
+ index = event_type - GAUDI2_EVENT_NIC0_AXI_ERROR_RESPONSE;
+ return GAUDI2_ENGINE_ID_NIC0_0 + (index * 2);
+ case GAUDI2_EVENT_NIC0_QM0 ... GAUDI2_EVENT_NIC11_QM1:
+ index = event_type - GAUDI2_EVENT_NIC0_QM0;
+ return GAUDI2_ENGINE_ID_NIC0_0 + index;
+ case GAUDI2_EVENT_NIC0_BMON_SPMU ... GAUDI2_EVENT_NIC11_SW_ERROR:
+ index = event_type - GAUDI2_EVENT_NIC0_BMON_SPMU;
+ return GAUDI2_ENGINE_ID_NIC0_0 + (index * 2);
+ case GAUDI2_EVENT_TPC0_BMON_SPMU ... GAUDI2_EVENT_TPC24_KERNEL_ERR:
+ index = (event_type - GAUDI2_EVENT_TPC0_BMON_SPMU) >> 1;
+ type = GAUDI2_BLOCK_TYPE_TPC;
+ break;
+ case GAUDI2_EVENT_ROTATOR0_AXI_ERROR_RESPONSE:
+ case GAUDI2_EVENT_ROTATOR0_BMON_SPMU:
+ case GAUDI2_EVENT_ROTATOR0_ROT0_QM:
+ return GAUDI2_ENGINE_ID_ROT_0;
+ case GAUDI2_EVENT_ROTATOR1_AXI_ERROR_RESPONSE:
+ case GAUDI2_EVENT_ROTATOR1_BMON_SPMU:
+ case GAUDI2_EVENT_ROTATOR1_ROT1_QM:
+ return GAUDI2_ENGINE_ID_ROT_1;
+ case GAUDI2_EVENT_HDMA0_BM_SPMU:
+ case GAUDI2_EVENT_HDMA0_QM:
+ case GAUDI2_EVENT_HDMA0_CORE:
+ return GAUDI2_DCORE0_ENGINE_ID_EDMA_0;
+ case GAUDI2_EVENT_HDMA1_BM_SPMU:
+ case GAUDI2_EVENT_HDMA1_QM:
+ case GAUDI2_EVENT_HDMA1_CORE:
+ return GAUDI2_DCORE0_ENGINE_ID_EDMA_1;
+ case GAUDI2_EVENT_HDMA2_BM_SPMU:
+ case GAUDI2_EVENT_HDMA2_QM:
+ case GAUDI2_EVENT_HDMA2_CORE:
+ return GAUDI2_DCORE1_ENGINE_ID_EDMA_0;
+ case GAUDI2_EVENT_HDMA3_BM_SPMU:
+ case GAUDI2_EVENT_HDMA3_QM:
+ case GAUDI2_EVENT_HDMA3_CORE:
+ return GAUDI2_DCORE1_ENGINE_ID_EDMA_1;
+ case GAUDI2_EVENT_HDMA4_BM_SPMU:
+ case GAUDI2_EVENT_HDMA4_QM:
+ case GAUDI2_EVENT_HDMA4_CORE:
+ return GAUDI2_DCORE2_ENGINE_ID_EDMA_0;
+ case GAUDI2_EVENT_HDMA5_BM_SPMU:
+ case GAUDI2_EVENT_HDMA5_QM:
+ case GAUDI2_EVENT_HDMA5_CORE:
+ return GAUDI2_DCORE2_ENGINE_ID_EDMA_1;
+ case GAUDI2_EVENT_HDMA6_BM_SPMU:
+ case GAUDI2_EVENT_HDMA6_QM:
+ case GAUDI2_EVENT_HDMA6_CORE:
+ return GAUDI2_DCORE3_ENGINE_ID_EDMA_0;
+ case GAUDI2_EVENT_HDMA7_BM_SPMU:
+ case GAUDI2_EVENT_HDMA7_QM:
+ case GAUDI2_EVENT_HDMA7_CORE:
+ return GAUDI2_DCORE3_ENGINE_ID_EDMA_1;
+ default:
+ break;
+ }
+
+ switch (type) {
+ case GAUDI2_BLOCK_TYPE_TPC:
+ switch (index) {
+ case TPC_ID_DCORE0_TPC0 ... TPC_ID_DCORE0_TPC5:
+ return GAUDI2_DCORE0_ENGINE_ID_TPC_0 + index;
+ case TPC_ID_DCORE1_TPC0 ... TPC_ID_DCORE1_TPC5:
+ return GAUDI2_DCORE1_ENGINE_ID_TPC_0 + index - TPC_ID_DCORE1_TPC0;
+ case TPC_ID_DCORE2_TPC0 ... TPC_ID_DCORE2_TPC5:
+ return GAUDI2_DCORE2_ENGINE_ID_TPC_0 + index - TPC_ID_DCORE2_TPC0;
+ case TPC_ID_DCORE3_TPC0 ... TPC_ID_DCORE3_TPC5:
+ return GAUDI2_DCORE3_ENGINE_ID_TPC_0 + index - TPC_ID_DCORE3_TPC0;
+ default:
+ break;
+ }
+ break;
+ case GAUDI2_BLOCK_TYPE_MME:
+ switch (index) {
+ case MME_ID_DCORE0: return GAUDI2_DCORE0_ENGINE_ID_MME;
+ case MME_ID_DCORE1: return GAUDI2_DCORE1_ENGINE_ID_MME;
+ case MME_ID_DCORE2: return GAUDI2_DCORE2_ENGINE_ID_MME;
+ case MME_ID_DCORE3: return GAUDI2_DCORE3_ENGINE_ID_MME;
+ default:
+ break;
+ }
+ break;
+ case GAUDI2_BLOCK_TYPE_DEC:
+ switch (index) {
+ case DEC_ID_DCORE0_DEC0: return GAUDI2_DCORE0_ENGINE_ID_DEC_0;
+ case DEC_ID_DCORE0_DEC1: return GAUDI2_DCORE0_ENGINE_ID_DEC_1;
+ case DEC_ID_DCORE1_DEC0: return GAUDI2_DCORE1_ENGINE_ID_DEC_0;
+ case DEC_ID_DCORE1_DEC1: return GAUDI2_DCORE1_ENGINE_ID_DEC_1;
+ case DEC_ID_DCORE2_DEC0: return GAUDI2_DCORE2_ENGINE_ID_DEC_0;
+ case DEC_ID_DCORE2_DEC1: return GAUDI2_DCORE2_ENGINE_ID_DEC_1;
+ case DEC_ID_DCORE3_DEC0: return GAUDI2_DCORE3_ENGINE_ID_DEC_0;
+ case DEC_ID_DCORE3_DEC1: return GAUDI2_DCORE3_ENGINE_ID_DEC_1;
+ case DEC_ID_PCIE_VDEC0: return GAUDI2_PCIE_ENGINE_ID_DEC_0;
+ case DEC_ID_PCIE_VDEC1: return GAUDI2_PCIE_ENGINE_ID_DEC_1;
+ default:
+ break;
+ }
+ break;
+ default:
+ break;
+ }
+
+ return U16_MAX;
+}
+
+static void hl_eq_heartbeat_event_handle(struct hl_device *hdev)
+{
+ hdev->eq_heartbeat_received = true;
+}
+
static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry)
{
struct gaudi2_device *gaudi2 = hdev->asic_specific;
@@ -9501,7 +9807,7 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
break;
case GAUDI2_EVENT_ARC_AXI_ERROR_RESPONSE_0:
- error_count = gaudi2_handle_arc_farm_sei_err(hdev, event_type);
+ error_count = gaudi2_handle_arc_farm_sei_err(hdev, event_type, &event_mask);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
@@ -9724,8 +10030,7 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
case GAUDI2_EVENT_MME1_SBTE0_AXI_ERR_RSP ... GAUDI2_EVENT_MME1_SBTE4_AXI_ERR_RSP:
case GAUDI2_EVENT_MME2_SBTE0_AXI_ERR_RSP ... GAUDI2_EVENT_MME2_SBTE4_AXI_ERR_RSP:
case GAUDI2_EVENT_MME3_SBTE0_AXI_ERR_RSP ... GAUDI2_EVENT_MME3_SBTE4_AXI_ERR_RSP:
- error_count = gaudi2_handle_mme_sbte_err(hdev, event_type,
- le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
+ error_count = gaudi2_handle_mme_sbte_err(hdev, event_type);
event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
break;
case GAUDI2_EVENT_VM0_ALARM_A ... GAUDI2_EVENT_VM3_ALARM_B:
@@ -9875,6 +10180,21 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
is_critical = true;
break;
+ case GAUDI2_EVENT_ARC_PWR_BRK_ENTRY:
+ case GAUDI2_EVENT_ARC_PWR_BRK_EXT:
+ case GAUDI2_EVENT_ARC_PWR_RD_MODE0:
+ case GAUDI2_EVENT_ARC_PWR_RD_MODE1:
+ case GAUDI2_EVENT_ARC_PWR_RD_MODE2:
+ case GAUDI2_EVENT_ARC_PWR_RD_MODE3:
+ error_count = GAUDI2_NA_EVENT_CAUSE;
+ dev_info_ratelimited(hdev->dev, "%s event received\n",
+ gaudi2_irq_map_table[event_type].name);
+ break;
+
+ case GAUDI2_EVENT_ARC_EQ_HEARTBEAT:
+ hl_eq_heartbeat_event_handle(hdev);
+ error_count = GAUDI2_NA_EVENT_CAUSE;
+ break;
default:
if (gaudi2_irq_map_table[event_type].valid) {
dev_err_ratelimited(hdev->dev, "Cannot find handler for event %d\n",
@@ -9883,6 +10203,9 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
}
}
+ if (event_mask & HL_NOTIFIER_EVENT_USER_ENGINE_ERR)
+ hl_capture_engine_err(hdev, event_id_to_engine_id(hdev, event_type), error_count);
+
/* Make sure to dump an error in case no error cause was printed so far.
* Note that although we have counted the errors, we use this number as
* a boolean.
@@ -10523,6 +10846,9 @@ static int gaudi2_ctx_init(struct hl_ctx *ctx)
{
int rc;
+ if (ctx->asid == HL_KERNEL_ASID_ID)
+ return 0;
+
rc = gaudi2_mmu_prepare(ctx->hdev, ctx->asid);
if (rc)
return rc;
@@ -11014,6 +11340,7 @@ static int gaudi2_ack_mmu_page_fault_or_access_error(struct hl_device *hdev, u64
static void gaudi2_get_msi_info(__le32 *table)
{
table[CPUCP_EVENT_QUEUE_MSI_TYPE] = cpu_to_le32(GAUDI2_EVENT_QUEUE_MSIX_IDX);
+ table[CPUCP_EVENT_QUEUE_ERR_MSI_TYPE] = cpu_to_le32(GAUDI2_IRQ_NUM_EQ_ERROR);
}
static int gaudi2_map_pll_idx_to_fw_idx(u32 pll_idx)
@@ -11170,11 +11497,9 @@ static const struct hl_asic_funcs gaudi2_funcs = {
.asic_dma_pool_free = gaudi2_dma_pool_free,
.cpu_accessible_dma_pool_alloc = gaudi2_cpu_accessible_dma_pool_alloc,
.cpu_accessible_dma_pool_free = gaudi2_cpu_accessible_dma_pool_free,
- .asic_dma_unmap_single = gaudi2_dma_unmap_single,
- .asic_dma_map_single = gaudi2_dma_map_single,
- .hl_dma_unmap_sgtable = hl_dma_unmap_sgtable,
+ .dma_unmap_sgtable = hl_asic_dma_unmap_sgtable,
.cs_parser = gaudi2_cs_parser,
- .asic_dma_map_sgtable = hl_dma_map_sgtable,
+ .dma_map_sgtable = hl_asic_dma_map_sgtable,
.add_end_of_cb_packets = NULL,
.update_eq_ci = gaudi2_update_eq_ci,
.context_switch = gaudi2_context_switch,