Skip to contentSkip to conversation

habanalabs: fetch pll frequency from firmware

PATCH New Oded Gabbay 2 participants 4 messages Nov 18, 2020 Char and misc drivers

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 habanalabs: fetch pll frequency from firmware

From: Alon Mizrahi <[email protected]>

Once firmware security is enabled, driver must fetch pll frequencies through the firmware message interface instead of reading the registers directly.

---
 drivers/misc/habanalabs/common/firmware_if.c  |  24 ++--
 drivers/misc/habanalabs/common/habanalabs.h   |   9 +-
 .../misc/habanalabs/common/habanalabs_ioctl.c |  22 +++
 drivers/misc/habanalabs/gaudi/gaudi.c         | 135 ++++++++++++------
 drivers/misc/habanalabs/gaudi/gaudiP.h        |   8 ++
 drivers/misc/habanalabs/goya/goya.c           |   2 +-
 .../misc/habanalabs/include/common/cpucp_if.h |  40 +++++-
 .../habanalabs/include/common/hl_boot_if.h    |   4 +
 .../include/gaudi/asic_reg/gaudi_regs.h       |  14 +-
 .../gaudi/asic_reg/psoc_hbm_pll_regs.h        | 114 ---------------
 .../gaudi/asic_reg/psoc_pci_pll_regs.h        | 114 ---------------
 include/uapi/misc/habanalabs.h                |   9 ++
 12 files changed, 199 insertions(+), 296 deletions(-)
 delete mode 100644 drivers/misc/habanalabs/include/gaudi/asic_reg/psoc_hbm_pll_regs.h
 delete mode 100644 drivers/misc/habanalabs/include/gaudi/asic_reg/psoc_pci_pll_regs.h
drivers/misc/habanalabs/common/firmware_if.c +15 -9
index 8f70d0bbe5e1..c4a8d6ca34bb 100644
@@ -279,7 +279,8 @@ int hl_fw_send_heartbeat(struct hl_device *hdev)
 	return rc;
 }
 
-int hl_fw_cpucp_info_get(struct hl_device *hdev)
+int hl_fw_cpucp_info_get(struct hl_device *hdev,
+			u32 cpu_security_boot_status_reg)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	struct cpucp_packet pkt = {};
@@ -324,6 +325,11 @@ int hl_fw_cpucp_info_get(struct hl_device *hdev)
 		goto out;
 	}
 
+	/* Read FW application security bits again */
+	if (hdev->asic_prop.fw_security_status_valid)
+		hdev->asic_prop.fw_app_security_map =
+				RREG32(cpu_security_boot_status_reg);
+
 out:
 	hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
 			sizeof(struct cpucp_info), cpucp_info_cpu_addr);
@@ -446,10 +452,8 @@ int hl_fw_cpucp_total_energy_get(struct hl_device *hdev, u64 *total_energy)
 	return rc;
 }
 
-int hl_fw_cpucp_pll_info_get(struct hl_device *hdev,
-		enum cpucp_pll_type_attributes pll_type,
-		enum cpucp_pll_reg_attributes pll_reg,
-		u32 *pll_info)
+int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, u16 pll_index,
+		u16 *pll_freq_arr)
 {
 	struct cpucp_packet pkt;
 	u64 result;
@@ -457,17 +461,19 @@ int hl_fw_cpucp_pll_info_get(struct hl_device *hdev,
 
 	memset(&pkt, 0, sizeof(pkt));
 
-	pkt.ctl = cpu_to_le32(CPUCP_PACKET_PLL_REG_GET <<
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_PLL_INFO_GET <<
 				CPUCP_PKT_CTL_OPCODE_SHIFT);
-	pkt.pll_type = __cpu_to_le16(pll_type);
-	pkt.pll_reg = __cpu_to_le16(pll_reg);
+	pkt.pll_type = __cpu_to_le16(pll_index);
 
 	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
 			HL_CPUCP_INFO_TIMEOUT_USEC, &result);
 	if (rc)
 		dev_err(hdev->dev, "Failed to read PLL info, error %d\n", rc);
 
-	*pll_info = (u32) result;
+	pll_freq_arr[0] = FIELD_GET(CPUCP_PKT_RES_PLL_OUT0_MASK, result);
+	pll_freq_arr[1] = FIELD_GET(CPUCP_PKT_RES_PLL_OUT1_MASK, result);
+	pll_freq_arr[2] = FIELD_GET(CPUCP_PKT_RES_PLL_OUT2_MASK, result);
+	pll_freq_arr[3] = FIELD_GET(CPUCP_PKT_RES_PLL_OUT3_MASK, result);
 
 	return rc;
 }
drivers/misc/habanalabs/common/habanalabs.h +4 -5
index e1db8301ecbd..9c9c8b24c47a 100644
@@ -2191,16 +2191,15 @@ void *hl_fw_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size,
 void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
 					void *vaddr);
 int hl_fw_send_heartbeat(struct hl_device *hdev);
-int hl_fw_cpucp_info_get(struct hl_device *hdev);
+int hl_fw_cpucp_info_get(struct hl_device *hdev,
+			u32 cpu_security_boot_status_reg);
 int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size);
 int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev,
 		struct hl_info_pci_counters *counters);
 int hl_fw_cpucp_total_energy_get(struct hl_device *hdev,
 			u64 *total_energy);
-int hl_fw_cpucp_pll_info_get(struct hl_device *hdev,
-		enum cpucp_pll_type_attributes pll_type,
-		enum cpucp_pll_reg_attributes pll_reg,
-		u32 *pll_info);
+int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, u16 pll_index,
+		u16 *pll_freq_arr);
 int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
 			u32 msg_to_cpu_reg, u32 cpu_msg_status_reg,
 			u32 cpu_security_boot_status_reg, u32 boot_err0_reg,
drivers/misc/habanalabs/common/habanalabs_ioctl.c +22 -0
index ba8217fc9425..32e6af1db4e3 100644
@@ -403,6 +403,25 @@ static int total_energy_consumption_info(struct hl_fpriv *hpriv,
 		min((size_t) max_size, sizeof(total_energy))) ? -EFAULT : 0;
 }
 
+static int pll_frequency_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_pll_frequency_info freq_info = {0};
+	u32 max_size = args->return_size;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+	int rc;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	rc = hl_fw_cpucp_pll_info_get(hdev, args->pll_index, freq_info.output);
+	if (rc)
+		return rc;
+
+	return copy_to_user(out, &freq_info,
+		min((size_t) max_size, sizeof(freq_info))) ? -EFAULT : 0;
+}
+
 static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 				struct device *dev)
 {
@@ -480,6 +499,9 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 	case HL_INFO_TOTAL_ENERGY:
 		return total_energy_consumption_info(hpriv, args);
 
+	case HL_INFO_PLL_FREQUENCY:
+		return pll_frequency_info(hpriv, args);
+
 	default:
 		dev_err(dev, "Invalid request %d\n", args->op);
 		rc = -ENOTTY;
drivers/misc/habanalabs/gaudi/gaudi.c +91 -44

171 lines not on this page · raw message

drivers/misc/habanalabs/gaudi/gaudiP.h +8 -0
index 1a5e681c720d..f2d91f4fcffe 100644
@@ -14,6 +14,7 @@
 #include "../include/gaudi/gaudi_packets.h"
 #include "../include/gaudi/gaudi.h"
 #include "../include/gaudi/gaudi_async_events.h"
+#include "../include/gaudi/gaudi_fw_if.h"
 
 #define NUMBER_OF_EXT_HW_QUEUES		8
 #define NUMBER_OF_CMPLT_QUEUES		NUMBER_OF_EXT_HW_QUEUES
@@ -104,6 +105,13 @@
 #define MME_ACC_OFFSET		(mmMME1_ACC_BASE - mmMME0_ACC_BASE)
 #define SRAM_BANK_OFFSET	(mmSRAM_Y0_X1_RTR_BASE - mmSRAM_Y0_X0_RTR_BASE)
 
+#define PLL_NR_OFFSET		0
+#define PLL_NF_OFFSET		(mmPSOC_CPU_PLL_NF - mmPSOC_CPU_PLL_NR)
+#define PLL_OD_OFFSET		(mmPSOC_CPU_PLL_OD - mmPSOC_CPU_PLL_NR)
+#define PLL_DIV_FACTOR_0_OFFSET	(mmPSOC_CPU_PLL_DIV_FACTOR_0 - \
+				mmPSOC_CPU_PLL_NR)
+#define PLL_DIV_SEL_0_OFFSET	(mmPSOC_CPU_PLL_DIV_SEL_0 - mmPSOC_CPU_PLL_NR)
+
 #define NUM_OF_SOB_IN_BLOCK		\
 	(((mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_2047 - \
 	mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_0) + 4) >> 2)
drivers/misc/habanalabs/goya/goya.c +1 -1
index 342227b93778..d91f553b8595 100644
@@ -5156,7 +5156,7 @@ int goya_cpucp_info_get(struct hl_device *hdev)
 	if (!(goya->hw_cap_initialized & HW_CAP_CPU_Q))
 		return 0;
 
-	rc = hl_fw_cpucp_info_get(hdev);
+	rc = hl_fw_cpucp_info_get(hdev, mmCPU_BOOT_DEV_STS0);
 	if (rc)
 		return rc;
 
drivers/misc/habanalabs/include/common/cpucp_if.h +34 -6
index 759c068b2b7a..554f82271d5f 100644
@@ -252,10 +252,26 @@ enum pq_init_status {
  *       The packet's arguments specify the desired sensor and the field to
  *       set.
  *
- * CPUCP_PACKET_PLL_REG_GET
- *       Fetch register of PLL from the required PLL IP.
- *       The packet's arguments specify the PLL IP and the register to get.
- *       Each register is 32-bit value which is returned in result field.
+ * CPUCP_PACKET_PCIE_THROUGHPUT_GET
+ *       Get throughput of PCIe.
+ *       The packet's arguments specify the transaction direction (TX/RX).
+ *       The window measurement is 10[msec], and the return value is in KB/sec.
+ *
+ * CPUCP_PACKET_PCIE_REPLAY_CNT_GET
+ *       Replay count measures number of "replay" events, which is basicly
+ *       number of retries done by PCIe.
+ *
+ * CPUCP_PACKET_TOTAL_ENERGY_GET
+ *       Total Energy is measurement of energy from the time FW Linux
+ *       is loaded. It is calculated by multiplying the average power
+ *       by time (passed from armcp start). The units are in MilliJouls.
+ *
+ * CPUCP_PACKET_PLL_INFO_GET
+ *       Fetch frequencies of PLL from the required PLL IP.
+ *       The packet's arguments specify the device PLL type
+ *       Pll type is the PLL from device pll_index enum.
+ *       The result is composed of 4 outputs, each is 16-bit
+ *       frequency in MHz.
  *
  */
 
@@ -289,7 +305,7 @@ enum cpucp_packet_id {
 	CPUCP_PACKET_PCIE_THROUGHPUT_GET,	/* internal */
 	CPUCP_PACKET_PCIE_REPLAY_CNT_GET,	/* internal */
 	CPUCP_PACKET_TOTAL_ENERGY_GET,		/* internal */
-	CPUCP_PACKET_PLL_REG_GET,		/* internal */
+	CPUCP_PACKET_PLL_INFO_GET,		/* internal */
 };
 
 #define CPUCP_PACKET_FENCE_VAL	0xFE8CE7A5
@@ -300,6 +316,15 @@ enum cpucp_packet_id {
 #define CPUCP_PKT_CTL_OPCODE_SHIFT	16
 #define CPUCP_PKT_CTL_OPCODE_MASK	0x1FFF0000
 
+#define CPUCP_PKT_RES_PLL_OUT0_SHIFT	0
+#define CPUCP_PKT_RES_PLL_OUT0_MASK	0x000000000000FFFF
+#define CPUCP_PKT_RES_PLL_OUT1_SHIFT	16
+#define CPUCP_PKT_RES_PLL_OUT1_MASK	0x00000000FFFF0000
+#define CPUCP_PKT_RES_PLL_OUT2_SHIFT	32
+#define CPUCP_PKT_RES_PLL_OUT2_MASK	0x0000FFFF00000000
+#define CPUCP_PKT_RES_PLL_OUT3_SHIFT	48
+#define CPUCP_PKT_RES_PLL_OUT3_MASK	0xFFFF000000000000
+
 struct cpucp_packet {
 	union {
 		__le64 value;	/* For SET packets */
@@ -324,8 +349,9 @@ struct cpucp_packet {
 			__u8 pad; /* unused */
 		};
 
-		struct {/* For PLL register fetch */
+		struct {/* For PLL info fetch */
 			__le16 pll_type;
+			/* TODO pll_reg is kept temporary before removal */
 			__le16 pll_reg;
 		};
 
@@ -404,6 +430,7 @@ enum cpucp_pcie_throughput_attributes {
 	cpucp_pcie_throughput_rx
 };
 
+/* TODO temporary kept before removal */
 enum cpucp_pll_reg_attributes {
 	cpucp_pll_nr_reg,
 	cpucp_pll_nf_reg,
@@ -412,6 +439,7 @@ enum cpucp_pll_reg_attributes {
 	cpucp_pll_div_sel_reg
 };
 
+/* TODO temporary kept before removal */
 enum cpucp_pll_type_attributes {
 	cpucp_pll_cpu,
 	cpucp_pll_pci,
drivers/misc/habanalabs/include/common/hl_boot_if.h +4 -0
index 60916780df35..68ac15c53f37 100644
@@ -131,6 +131,9 @@
  *					receiving the halt-machine event.
  *					Initialized in: linux
  *
+ * CPU_BOOT_DEV_STS0_PLL_INFO_EN	FW retrieval of PLL info is enabled.
+ *					Initialized in: linux
+ *
  * CPU_BOOT_DEV_STS0_ENABLED		Device status register enabled.
  *					This is a main indication that the
  *					running FW populates the device status
@@ -150,6 +153,7 @@
 #define CPU_BOOT_DEV_STS0_SRAM_SCR_EN			(1 << 8)
 #define CPU_BOOT_DEV_STS0_DRAM_SCR_EN			(1 << 9)
 #define CPU_BOOT_DEV_STS0_FW_HARD_RST_EN		(1 << 10)
+#define CPU_BOOT_DEV_STS0_PLL_INFO_EN			(1 << 11)
 #define CPU_BOOT_DEV_STS0_ENABLED			(1 << 31)
 
 enum cpu_boot_status {
drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h +11 -3
index df21a40691e5..5bb54b34a8ae 100644
@@ -81,6 +81,7 @@
 #include "sif_rtr_ctrl_6_regs.h"
 #include "sif_rtr_ctrl_7_regs.h"
 #include "psoc_etr_regs.h"
+#include "psoc_cpu_pll_regs.h"
 
 #include "dma0_qm_masks.h"
 #include "mme0_qm_masks.h"
@@ -102,9 +103,6 @@
 
 #include "nic0_qm0_masks.h"
 
-#include "psoc_hbm_pll_regs.h"
-#include "psoc_cpu_pll_regs.h"
-
 #define GAUDI_ECC_MEM_SEL_OFFSET		0xF18
 #define GAUDI_ECC_ADDRESS_OFFSET		0xF1C
 #define GAUDI_ECC_SYNDROME_OFFSET		0xF20
@@ -307,4 +305,14 @@
 #define mmPCIE_AUX_FLR_CTRL                                          0xC07394
 #define mmPCIE_AUX_DBI                                               0xC07490
 
+#define mmPSOC_PCI_PLL_NR                                            0xC72100
+#define mmSRAM_W_PLL_NR                                              0x4C8100
+#define mmPSOC_HBM_PLL_NR                                            0xC74100
+#define mmNIC0_PLL_NR                                                0xCF9100
+#define mmDMA_W_PLL_NR                                               0x487100
+#define mmMESH_W_PLL_NR                                              0x4C7100
+#define mmPSOC_MME_PLL_NR                                            0xC71100
+#define mmPSOC_TPC_PLL_NR                                            0xC73100
+#define mmIF_W_PLL_NR                                                0x488100
+
 #endif /* ASIC_REG_GAUDI_REGS_H_ */
drivers/misc/habanalabs/include/gaudi/asic_reg/psoc_hbm_pll_regs.h deleted +0 -114

114 lines not on this page · raw message

drivers/misc/habanalabs/include/gaudi/asic_reg/psoc_pci_pll_regs.h deleted +0 -114

114 lines not on this page · raw message

include/uapi/misc/habanalabs.h +9 -0
index d9cc782aba21..96eea49f48bc 100644
@@ -295,6 +295,7 @@ enum hl_device_status {
 #define HL_INFO_CLK_THROTTLE_REASON	13
 #define HL_INFO_SYNC_MANAGER		14
 #define HL_INFO_TOTAL_ENERGY		15
+#define HL_INFO_PLL_FREQUENCY		16
 
 #define HL_INFO_VERSION_MAX_LEN	128
 #define HL_INFO_CARD_NAME_MAX_LEN	16
@@ -396,6 +397,12 @@ struct hl_info_energy {
 	__u64 total_energy_consumption;
 };
 
+#define HL_PLL_NUM_OUTPUTS 4
+
+struct hl_pll_frequency_info {
+	__u16 output[HL_PLL_NUM_OUTPUTS];
+};
+
 /**
  * struct hl_info_sync_manager - sync manager information
  * @first_available_sync_object: first available sob
@@ -465,6 +472,8 @@ struct hl_info_args {
 		 * resolution.
 		 */
 		__u32 period_ms;
+		/* PLL frequency retrieval */
+		__u32 pll_index;
 	};
 
 	__u32 pad;
Signature · 1 line
2.17.1
#1 lore raw

PATCH 1/1 habanalabs: print CS type when it is stuck

We have several types of command submissions and the user wants to know which type of command submission has not finished in time when that event occurs. This is very helpful for debug.

---
 .../habanalabs/common/command_submission.c    | 28 +++++++++++++++++--
 1 file changed, 25 insertions(+), 3 deletions(-)
drivers/misc/habanalabs/common/command_submission.c +25 -3
index 516cbaacc03e..6ca77abf7f8a 100644
@@ -418,9 +418,31 @@ static void cs_timedout(struct work_struct *work)
 
 	hdev = cs->ctx->hdev;
 
-	dev_err(hdev->dev,
-		"Command submission %llu has not finished in time!\n",
-		cs->sequence);
+	switch (cs->type) {
+	case CS_TYPE_SIGNAL:
+		dev_err(hdev->dev,
+			"Signal command submission %llu has not finished in time!\n",
+			cs->sequence);
+		break;
+
+	case CS_TYPE_WAIT:
+		dev_err(hdev->dev,
+			"Wait command submission %llu has not finished in time!\n",
+			cs->sequence);
+		break;
+
+	case CS_TYPE_COLLECTIVE_WAIT:
+		dev_err(hdev->dev,
+			"Collective Wait command submission %llu has not finished in time!\n",
+			cs->sequence);
+		break;
+
+	default:
+		dev_err(hdev->dev,
+			"Command submission %llu has not finished in time!\n",
+			cs->sequence);
+		break;
+	}
 
 	cs_put(cs);
 
Signature · 1 line
2.17.1
#3 lore raw

PATCH 1/1 habanalabs: mmu map wrapper for sizes larger than a page

In reply to Oded Gabbay

From: Ofir Bitton <[email protected]>

We introduce a new wrapper which allows us to mmu map any size to any host va_range available. In addition we remove duplicated code from various places in driver and using this new wrapper instead.
This wrapper supports mapping only contiguous physical memory blocks and will be used for mappings that are done to the driver ASID.

---
 .../misc/habanalabs/common/command_buffer.c   |  10 +-
 drivers/misc/habanalabs/common/habanalabs.h   |   7 +-
 drivers/misc/habanalabs/common/memory.c       |   6 +-
 drivers/misc/habanalabs/common/mmu.c          | 112 +++++++++++++++++-
 drivers/misc/habanalabs/gaudi/gaudi.c         |  60 ++--------
 drivers/misc/habanalabs/goya/goya.c           |  26 ++--
 6 files changed, 144 insertions(+), 77 deletions(-)
drivers/misc/habanalabs/common/command_buffer.c +5 -5
index 0c482358f350..2856bb3423ee 100644
@@ -67,9 +67,9 @@ static int cb_map_mem(struct hl_ctx *ctx, struct hl_cb *cb)
 	bus_addr = cb->bus_address;
 	offset = 0;
 	list_for_each_entry(va_block, &cb->va_block_list, node) {
-		rc = hl_mmu_map(ctx, va_block->start, bus_addr, va_block->size,
-				list_is_last(&va_block->node,
-						&cb->va_block_list));
+		rc = hl_mmu_map_page(ctx, va_block->start, bus_addr,
+				va_block->size, list_is_last(&va_block->node,
+							&cb->va_block_list));
 		if (rc) {
 			dev_err(hdev->dev, "Failed to map VA %#llx to CB\n",
 				va_block->start);
@@ -92,7 +92,7 @@ static int cb_map_mem(struct hl_ctx *ctx, struct hl_cb *cb)
 	list_for_each_entry(va_block, &cb->va_block_list, node) {
 		if (offset <= 0)
 			break;
-		hl_mmu_unmap(ctx, va_block->start, va_block->size,
+		hl_mmu_unmap_page(ctx, va_block->start, va_block->size,
 				offset <= va_block->size);
 		offset -= va_block->size;
 	}
@@ -119,7 +119,7 @@ static void cb_unmap_mem(struct hl_ctx *ctx, struct hl_cb *cb)
 	mutex_lock(&ctx->mmu_lock);
 
 	list_for_each_entry(va_block, &cb->va_block_list, node)
-		if (hl_mmu_unmap(ctx, va_block->start, va_block->size,
+		if (hl_mmu_unmap_page(ctx, va_block->start, va_block->size,
 				list_is_last(&va_block->node,
 						&cb->va_block_list)))
 			dev_warn_ratelimited(hdev->dev,
drivers/misc/habanalabs/common/habanalabs.h +5 -2
index 43aa8cbd8969..e1db8301ecbd 100644
@@ -2162,10 +2162,13 @@ int hl_mmu_init(struct hl_device *hdev);
 void hl_mmu_fini(struct hl_device *hdev);
 int hl_mmu_ctx_init(struct hl_ctx *ctx);
 void hl_mmu_ctx_fini(struct hl_ctx *ctx);
-int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
+int hl_mmu_map_page(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr,
 		u32 page_size, bool flush_pte);
-int hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr, u32 page_size,
+int hl_mmu_unmap_page(struct hl_ctx *ctx, u64 virt_addr, u32 page_size,
 		bool flush_pte);
+int hl_mmu_map_contiguous(struct hl_ctx *ctx, u64 virt_addr,
+					u64 phys_addr, u32 size);
+int hl_mmu_unmap_contiguous(struct hl_ctx *ctx, u64 virt_addr, u32 size);
 void hl_mmu_swap_out(struct hl_ctx *ctx);
 void hl_mmu_swap_in(struct hl_ctx *ctx);
 int hl_mmu_if_set_funcs(struct hl_device *hdev);
drivers/misc/habanalabs/common/memory.c +3 -3
index 351c9927151f..744275dd6410 100644
@@ -843,7 +843,7 @@ static int map_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
 	for (i = 0 ; i < phys_pg_pack->npages ; i++) {
 		paddr = phys_pg_pack->pages[i];
 
-		rc = hl_mmu_map(ctx, next_vaddr, paddr, page_size,
+		rc = hl_mmu_map_page(ctx, next_vaddr, paddr, page_size,
 				(i + 1) == phys_pg_pack->npages);
 		if (rc) {
 			dev_err(hdev->dev,
@@ -862,7 +862,7 @@ static int map_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
 err:
 	next_vaddr = vaddr;
 	for (i = 0 ; i < mapped_pg_cnt ; i++) {
-		if (hl_mmu_unmap(ctx, next_vaddr, page_size,
+		if (hl_mmu_unmap_page(ctx, next_vaddr, page_size,
 					(i + 1) == mapped_pg_cnt))
 			dev_warn_ratelimited(hdev->dev,
 				"failed to unmap handle %u, va: 0x%llx, pa: 0x%llx, page size: %u\n",
@@ -892,7 +892,7 @@ static void unmap_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
 	next_vaddr = vaddr;
 
 	for (i = 0 ; i < phys_pg_pack->npages ; i++, next_vaddr += page_size) {
-		if (hl_mmu_unmap(ctx, next_vaddr, page_size,
+		if (hl_mmu_unmap_page(ctx, next_vaddr, page_size,
 				       (i + 1) == phys_pg_pack->npages))
 			dev_warn_ratelimited(hdev->dev,
 			"unmap failed for vaddr: 0x%llx\n", next_vaddr);
drivers/misc/habanalabs/common/mmu.c +107 -5

142 lines not on this page · raw message

drivers/misc/habanalabs/gaudi/gaudi.c +9 -51

96 lines not on this page · raw message

drivers/misc/habanalabs/goya/goya.c +15 -11
index 55d174d3cac8..342227b93778 100644
@@ -4906,9 +4906,10 @@ static int goya_mmu_add_mappings_for_device_cpu(struct hl_device *hdev)
 		return 0;
 
 	for (off = 0 ; off < CPU_FW_IMAGE_SIZE ; off += PAGE_SIZE_2MB) {
-		rc = hl_mmu_map(hdev->kernel_ctx, prop->dram_base_address + off,
-				prop->dram_base_address + off, PAGE_SIZE_2MB,
-				(off + PAGE_SIZE_2MB) == CPU_FW_IMAGE_SIZE);
+		rc = hl_mmu_map_page(hdev->kernel_ctx,
+			prop->dram_base_address + off,
+			prop->dram_base_address + off, PAGE_SIZE_2MB,
+			(off + PAGE_SIZE_2MB) == CPU_FW_IMAGE_SIZE);
 		if (rc) {
 			dev_err(hdev->dev, "Map failed for address 0x%llx\n",
 				prop->dram_base_address + off);
@@ -4917,8 +4918,10 @@ static int goya_mmu_add_mappings_for_device_cpu(struct hl_device *hdev)
 	}
 
 	if (!(hdev->cpu_accessible_dma_address & (PAGE_SIZE_2MB - 1))) {
-		rc = hl_mmu_map(hdev->kernel_ctx, VA_CPU_ACCESSIBLE_MEM_ADDR,
-			hdev->cpu_accessible_dma_address, PAGE_SIZE_2MB, true);
+		rc = hl_mmu_map_page(hdev->kernel_ctx,
+			VA_CPU_ACCESSIBLE_MEM_ADDR,
+			hdev->cpu_accessible_dma_address,
+			PAGE_SIZE_2MB, true);
 
 		if (rc) {
 			dev_err(hdev->dev,
@@ -4928,7 +4931,7 @@ static int goya_mmu_add_mappings_for_device_cpu(struct hl_device *hdev)
 		}
 	} else {
 		for (cpu_off = 0 ; cpu_off < SZ_2M ; cpu_off += PAGE_SIZE_4KB) {
-			rc = hl_mmu_map(hdev->kernel_ctx,
+			rc = hl_mmu_map_page(hdev->kernel_ctx,
 				VA_CPU_ACCESSIBLE_MEM_ADDR + cpu_off,
 				hdev->cpu_accessible_dma_address + cpu_off,
 				PAGE_SIZE_4KB, true);
@@ -4955,7 +4958,7 @@ static int goya_mmu_add_mappings_for_device_cpu(struct hl_device *hdev)
 
 unmap_cpu:
 	for (; cpu_off >= 0 ; cpu_off -= PAGE_SIZE_4KB)
-		if (hl_mmu_unmap(hdev->kernel_ctx,
+		if (hl_mmu_unmap_page(hdev->kernel_ctx,
 				VA_CPU_ACCESSIBLE_MEM_ADDR + cpu_off,
 				PAGE_SIZE_4KB, true))
 			dev_warn_ratelimited(hdev->dev,
@@ -4963,7 +4966,7 @@ static int goya_mmu_add_mappings_for_device_cpu(struct hl_device *hdev)
 				VA_CPU_ACCESSIBLE_MEM_ADDR + cpu_off);
 unmap:
 	for (; off >= 0 ; off -= PAGE_SIZE_2MB)
-		if (hl_mmu_unmap(hdev->kernel_ctx,
+		if (hl_mmu_unmap_page(hdev->kernel_ctx,
 				prop->dram_base_address + off, PAGE_SIZE_2MB,
 				true))
 			dev_warn_ratelimited(hdev->dev,
@@ -4989,13 +4992,14 @@ void goya_mmu_remove_device_cpu_mappings(struct hl_device *hdev)
 	WREG32(mmCPU_IF_AWUSER_OVR_EN, 0);
 
 	if (!(hdev->cpu_accessible_dma_address & (PAGE_SIZE_2MB - 1))) {
-		if (hl_mmu_unmap(hdev->kernel_ctx, VA_CPU_ACCESSIBLE_MEM_ADDR,
+		if (hl_mmu_unmap_page(hdev->kernel_ctx,
+				VA_CPU_ACCESSIBLE_MEM_ADDR,
 				PAGE_SIZE_2MB, true))
 			dev_warn(hdev->dev,
 				"Failed to unmap CPU accessible memory\n");
 	} else {
 		for (cpu_off = 0 ; cpu_off < SZ_2M ; cpu_off += PAGE_SIZE_4KB)
-			if (hl_mmu_unmap(hdev->kernel_ctx,
+			if (hl_mmu_unmap_page(hdev->kernel_ctx,
 					VA_CPU_ACCESSIBLE_MEM_ADDR + cpu_off,
 					PAGE_SIZE_4KB,
 					(cpu_off + PAGE_SIZE_4KB) >= SZ_2M))
@@ -5005,7 +5009,7 @@ void goya_mmu_remove_device_cpu_mappings(struct hl_device *hdev)
 	}
 
 	for (off = 0 ; off < CPU_FW_IMAGE_SIZE ; off += PAGE_SIZE_2MB)
-		if (hl_mmu_unmap(hdev->kernel_ctx,
+		if (hl_mmu_unmap_page(hdev->kernel_ctx,
 				prop->dram_base_address + off, PAGE_SIZE_2MB,
 				(off + PAGE_SIZE_2MB) >= CPU_FW_IMAGE_SIZE))
 			dev_warn_ratelimited(hdev->dev,
Signature · 1 line
2.17.1
#2 lore raw

Re: [PATCH] habanalabs: print CS type when it is stuck

In reply to Oded Gabbay
I love your patch! Yet something to improve:

Hi Oded,

I love your patch! Yet something to improve:

[auto build test ERROR on char-misc/char-misc-testing]
[also build test ERROR on linux/master linus/master v5.10-rc4 next-20201118] [If your patch is applied to the wrong git tree, kindly drop us a note. And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Oded-Gabbay/habanalabs-print-CS-type-when-it-is-stuck/20201118-215554
base:   https://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git 93c69b2d17372463ae33b79b3002c22a208945b3
config: x86_64-randconfig-a013-20201118 (attached as .config)
compiler: clang version 12.0.0 (https://github.com/llvm/llvm-project b2613fb2f0f53691dd0211895afbb9413457fca7)

reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross
# install x86_64 cross compiling tool for clang build
# apt-get install binutils-x86-64-linux-gnu
# https://github.com/0day-ci/linux/commit/71112c9df0288d0689aa5c7fbdd396f2b099daa4
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Oded-Gabbay/habanalabs-print-CS-type-when-it-is-stuck/20201118-215554 git checkout 71112c9df0288d0689aa5c7fbdd396f2b099daa4
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64

If you fix the issue, kindly add following tag as appropriate

All errors (new ones prefixed by >>):

>> drivers/misc/habanalabs/common/command_submission.c:400:7: error: use of undeclared identifier 'CS_TYPE_COLLECTIVE_WAIT'
           case CS_TYPE_COLLECTIVE_WAIT:
                ^

1 error generated.

vim +/CS_TYPE_COLLECTIVE_WAIT +400 drivers/misc/habanalabs/common/command_submission.c

366
367 static void cs_timedout(struct work_struct *work)
368 {
369 struct hl_device *hdev;
370 int rc;
371 struct hl_cs *cs = container_of(work, struct hl_cs,
372 work_tdr.work);
373 rc = cs_get_unless_zero(cs);
374 if (!rc)
375 return;
376
377 if ((!cs->submitted) || (cs->completed)) {
378 cs_put(cs);
379 return;
380 }
381
382 /* Mark the CS is timed out so we won't try to cancel its TDR */
383 cs->timedout = true;
384
385 hdev = cs->ctx->hdev;
386
387 switch (cs->type) {
388 case CS_TYPE_SIGNAL:
389 dev_err(hdev->dev,
390 "Signal command submission %llu has not finished in time!\n",
391 cs->sequence);
392 break;
393
394 case CS_TYPE_WAIT:
395 dev_err(hdev->dev,
396 "Wait command submission %llu has not finished in time!\n",
397 cs->sequence);
398 break;
399

 > 400		case CS_TYPE_COLLECTIVE_WAIT:

401 dev_err(hdev->dev,
402 "Collective Wait command submission %llu has not finished in time!\n",
403 cs->sequence);
404 break;
405
406 default:
407 dev_err(hdev->dev,
408 "Command submission %llu has not finished in time!\n",
409 cs->sequence);
410 break;
411 }
412
413 cs_put(cs);
414
415 if (hdev->reset_on_lockup)
416 hl_device_reset(hdev, false, false);
417 }
418

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org