* [PATCH 2/3] habanalabs: support receiving ascii message from preboot f/w
2022-12-15 11:31 [PATCH 1/3] habanalabs: fix asic-specific functions documentation Oded Gabbay
@ 2022-12-15 11:31 ` Oded Gabbay
2022-12-15 11:31 ` [PATCH 3/3] habanalabs: pass-through request from user to f/w Oded Gabbay
1 sibling, 0 replies; 3+ messages in thread
From: Oded Gabbay @ 2022-12-15 11:31 UTC (permalink / raw)
To: linux-kernel; +Cc: Tal Cohen
From: Tal Cohen <talcohen@habana.ai>
An Ascii message that is sent from preboot towards the driver
will indicate the specific error that occurred on the f/w.
This commit supports that message and parse the ascii string
in order to print it into the kernel log
The commit also changes the way the descriptor struct is declared.
While its size increased (it now above 1024 bytes), it will be
allocated by using kmalloc instead of stack declaration.
Signed-off-by: Tal Cohen <talcohen@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
drivers/misc/habanalabs/common/firmware_if.c | 74 +++++++++++++++----
.../habanalabs/include/common/hl_boot_if.h | 19 +++++
2 files changed, 78 insertions(+), 15 deletions(-)
diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index ee4d1c5ca527..a8911e15d937 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -1915,7 +1915,7 @@ static int hl_fw_dynamic_validate_memory_bound(struct hl_device *hdev,
*
* @hdev: pointer to the habanalabs device structure
* @fw_loader: managing structure for loading device's FW
- * @fw_desc: the descriptor form FW
+ * @fw_desc: the descriptor from FW
*
* @return 0 on success, otherwise non-zero error code
*/
@@ -2007,6 +2007,43 @@ static int hl_fw_dynamic_validate_response(struct hl_device *hdev,
return rc;
}
+/*
+ * hl_fw_dynamic_read_descriptor_msg - read and show the ascii msg that sent by fw
+ *
+ * @hdev: pointer to the habanalabs device structure
+ * @fw_desc: the descriptor from FW
+ */
+static void hl_fw_dynamic_read_descriptor_msg(struct hl_device *hdev,
+ struct lkd_fw_comms_desc *fw_desc)
+{
+ int i;
+ char *msg;
+
+ for (i = 0 ; i < LKD_FW_ASCII_MSG_MAX ; i++) {
+ if (!fw_desc->ascii_msg[i].valid)
+ return;
+
+ /* force NULL termination */
+ msg = fw_desc->ascii_msg[i].msg;
+ msg[LKD_FW_ASCII_MSG_MAX_LEN - 1] = '\0';
+
+ switch (fw_desc->ascii_msg[i].msg_lvl) {
+ case LKD_FW_ASCII_MSG_ERR:
+ dev_err(hdev->dev, "fw: %s", fw_desc->ascii_msg[i].msg);
+ break;
+ case LKD_FW_ASCII_MSG_WRN:
+ dev_warn(hdev->dev, "fw: %s", fw_desc->ascii_msg[i].msg);
+ break;
+ case LKD_FW_ASCII_MSG_INF:
+ dev_info(hdev->dev, "fw: %s", fw_desc->ascii_msg[i].msg);
+ break;
+ default:
+ dev_dbg(hdev->dev, "fw: %s", fw_desc->ascii_msg[i].msg);
+ break;
+ }
+ }
+}
+
/**
* hl_fw_dynamic_read_and_validate_descriptor - read and validate FW descriptor
*
@@ -2071,6 +2108,10 @@ static int hl_fw_dynamic_read_and_validate_descriptor(struct hl_device *hdev,
rc = hl_fw_dynamic_validate_descriptor(hdev, fw_loader,
(struct lkd_fw_comms_desc *) temp_fw_desc);
+
+ if (!rc)
+ hl_fw_dynamic_read_descriptor_msg(hdev, temp_fw_desc);
+
vfree(temp_fw_desc);
return rc;
@@ -2491,51 +2532,54 @@ static void hl_fw_linux_update_state(struct hl_device *hdev,
static int hl_fw_dynamic_send_msg(struct hl_device *hdev,
struct fw_load_mgr *fw_loader, u8 msg_type, void *data)
{
- struct lkd_msg_comms msg;
+ struct lkd_msg_comms *msg;
int rc;
- memset(&msg, 0, sizeof(msg));
+ msg = kzalloc(sizeof(*msg), GFP_KERNEL);
+ if (!msg)
+ return -ENOMEM;
/* create message to be sent */
- msg.header.type = msg_type;
- msg.header.size = cpu_to_le16(sizeof(struct comms_msg_header));
- msg.header.magic = cpu_to_le32(HL_COMMS_MSG_MAGIC);
+ msg->header.type = msg_type;
+ msg->header.size = cpu_to_le16(sizeof(struct comms_msg_header));
+ msg->header.magic = cpu_to_le32(HL_COMMS_MSG_MAGIC);
switch (msg_type) {
case HL_COMMS_RESET_CAUSE_TYPE:
- msg.reset_cause = *(__u8 *) data;
+ msg->reset_cause = *(__u8 *) data;
break;
default:
dev_err(hdev->dev,
"Send COMMS message - invalid message type %u\n",
msg_type);
- return -EINVAL;
+ rc = -EINVAL;
+ goto out;
}
rc = hl_fw_dynamic_request_descriptor(hdev, fw_loader,
sizeof(struct lkd_msg_comms));
if (rc)
- return rc;
+ goto out;
/* copy message to space allocated by FW */
- rc = hl_fw_dynamic_copy_msg(hdev, &msg, fw_loader);
+ rc = hl_fw_dynamic_copy_msg(hdev, msg, fw_loader);
if (rc)
- return rc;
+ goto out;
rc = hl_fw_dynamic_send_protocol_cmd(hdev, fw_loader, COMMS_DATA_RDY,
0, true,
fw_loader->cpu_timeout);
if (rc)
- return rc;
+ goto out;
rc = hl_fw_dynamic_send_protocol_cmd(hdev, fw_loader, COMMS_EXEC,
0, true,
fw_loader->cpu_timeout);
- if (rc)
- return rc;
- return 0;
+out:
+ kfree(msg);
+ return rc;
}
/**
diff --git a/drivers/misc/habanalabs/include/common/hl_boot_if.h b/drivers/misc/habanalabs/include/common/hl_boot_if.h
index fe034111360e..370e62d0a96a 100644
--- a/drivers/misc/habanalabs/include/common/hl_boot_if.h
+++ b/drivers/misc/habanalabs/include/common/hl_boot_if.h
@@ -523,6 +523,23 @@ struct comms_msg_header {
__u8 reserved[4]; /* pad to 64 bit */
};
+enum lkd_fw_ascii_msg_lvls {
+ LKD_FW_ASCII_MSG_ERR = 0,
+ LKD_FW_ASCII_MSG_WRN = 1,
+ LKD_FW_ASCII_MSG_INF = 2,
+ LKD_FW_ASCII_MSG_DBG = 3,
+};
+
+#define LKD_FW_ASCII_MSG_MAX_LEN 128
+#define LKD_FW_ASCII_MSG_MAX 4 /* consider ABI when changing */
+
+struct lkd_fw_ascii_msg {
+ __u8 valid;
+ __u8 msg_lvl;
+ __u8 reserved[6];
+ char msg[LKD_FW_ASCII_MSG_MAX_LEN];
+};
+
/* this is the main FW descriptor - consider ABI when changing */
struct lkd_fw_comms_desc {
struct comms_desc_header header;
@@ -533,6 +550,7 @@ struct lkd_fw_comms_desc {
char reserved0[VERSION_MAX_LEN];
__le64 img_addr; /* address for next FW component load */
struct lkd_fw_binning_info binning_info;
+ struct lkd_fw_ascii_msg ascii_msg[LKD_FW_ASCII_MSG_MAX];
};
enum comms_reset_cause {
@@ -558,6 +576,7 @@ struct lkd_fw_comms_msg {
/* address for next FW component load */
__le64 img_addr;
struct lkd_fw_binning_info binning_info;
+ struct lkd_fw_ascii_msg ascii_msg[LKD_FW_ASCII_MSG_MAX];
};
struct {
__u8 reset_cause;
--
2.25.1
^ permalink raw reply related [flat|nested] 3+ messages in thread* [PATCH 3/3] habanalabs: pass-through request from user to f/w
2022-12-15 11:31 [PATCH 1/3] habanalabs: fix asic-specific functions documentation Oded Gabbay
2022-12-15 11:31 ` [PATCH 2/3] habanalabs: support receiving ascii message from preboot f/w Oded Gabbay
@ 2022-12-15 11:31 ` Oded Gabbay
1 sibling, 0 replies; 3+ messages in thread
From: Oded Gabbay @ 2022-12-15 11:31 UTC (permalink / raw)
To: linux-kernel; +Cc: farah kassabri
From: farah kassabri <fkassabri@habana.ai>
Add a uAPI, as part of the INFO IOCTL, to allow users to send
requests directly to f/w, according to a pre-defined set of opcodes
that the f/w exposes.
The f/w will put the result in a kernel-allocated buffer, which the
driver will then copy to the user-supplied buffer.
This will allow f/w tools to communicate directly with the f/w
without the need to add a new uAPI to the driver for each new type
of request.
Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
drivers/misc/habanalabs/common/firmware_if.c | 24 +++++++
drivers/misc/habanalabs/common/habanalabs.h | 2 +
.../misc/habanalabs/common/habanalabs_ioctl.c | 51 +++++++++++++++
.../misc/habanalabs/include/common/cpucp_if.h | 65 +++++++++++++++++--
include/uapi/misc/habanalabs.h | 4 ++
5 files changed, 139 insertions(+), 7 deletions(-)
diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index a8911e15d937..eb000e035026 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -3145,3 +3145,27 @@ int hl_fw_get_sec_attest_info(struct hl_device *hdev, struct cpucp_sec_attest_in
sizeof(struct cpucp_sec_attest_info), nonce,
HL_CPUCP_SEC_ATTEST_INFO_TINEOUT_USEC);
}
+
+int hl_fw_send_generic_request(struct hl_device *hdev, enum hl_passthrough_type sub_opcode,
+ dma_addr_t buff, u32 *size)
+{
+ struct cpucp_packet pkt = {0};
+ u64 result;
+ int rc = 0;
+
+ pkt.ctl = cpu_to_le32(CPUCP_PACKET_GENERIC_PASSTHROUGH << CPUCP_PKT_CTL_OPCODE_SHIFT);
+ pkt.addr = cpu_to_le64(buff);
+ pkt.data_max_size = cpu_to_le32(*size);
+ pkt.pkt_subidx = cpu_to_le32(sub_opcode);
+
+ 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 send CPUCP data of generic fw pkt\n");
+ else
+ dev_dbg(hdev->dev, "generic pkt was successful, result: 0x%llx\n", result);
+
+ *size = (u32)result;
+
+ return rc;
+}
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 210dd607e18b..c609b2e44ad3 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -3790,6 +3790,8 @@ int hl_fw_get_clk_rate(struct hl_device *hdev, u32 *cur_clk, u32 *max_clk);
void hl_fw_set_pll_profile(struct hl_device *hdev);
void hl_sysfs_add_dev_clk_attr(struct hl_device *hdev, struct attribute_group *dev_clk_attr_grp);
void hl_sysfs_add_dev_vrm_attr(struct hl_device *hdev, struct attribute_group *dev_vrm_attr_grp);
+int hl_fw_send_generic_request(struct hl_device *hdev, enum hl_passthrough_type sub_opcode,
+ dma_addr_t buff, u32 *size);
void hw_sob_get(struct hl_hw_sob *hw_sob);
void hw_sob_put(struct hl_hw_sob *hw_sob);
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index b6abfa7761a7..4d642987ad02 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -820,6 +820,54 @@ static int user_mappings_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
? -EFAULT : 0;
}
+static int send_fw_generic_request(struct hl_device *hdev, struct hl_info_args *info_args)
+{
+ void __user *buff = (void __user *) (uintptr_t) info_args->return_pointer;
+ u32 size = info_args->return_size;
+ dma_addr_t dma_handle;
+ bool need_input_buff;
+ void *fw_buff;
+ int rc = 0;
+
+ switch (info_args->fw_sub_opcode) {
+ case HL_PASSTHROUGH_VERSIONS:
+ need_input_buff = false;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (size > SZ_1M) {
+ dev_err(hdev->dev, "buffer size cannot exceed 1MB\n");
+ return -EINVAL;
+ }
+
+ fw_buff = hl_cpu_accessible_dma_pool_alloc(hdev, size, &dma_handle);
+ if (!fw_buff)
+ return -ENOMEM;
+
+
+ if (need_input_buff && copy_from_user(fw_buff, buff, size)) {
+ dev_dbg(hdev->dev, "Failed to copy from user FW buff\n");
+ rc = -EFAULT;
+ goto free_buff;
+ }
+
+ rc = hl_fw_send_generic_request(hdev, info_args->fw_sub_opcode, dma_handle, &size);
+ if (rc)
+ goto free_buff;
+
+ if (copy_to_user(buff, fw_buff, min(size, info_args->return_size))) {
+ dev_dbg(hdev->dev, "Failed to copy to user FW generic req output\n");
+ rc = -EFAULT;
+ }
+
+free_buff:
+ hl_cpu_accessible_dma_pool_free(hdev, info_args->return_size, fw_buff);
+
+ return rc;
+}
+
static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
struct device *dev)
{
@@ -947,6 +995,9 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
case HL_INFO_ENGINE_STATUS:
return engine_status_info(hpriv, args);
+ case HL_INFO_FW_GENERIC_REQ:
+ return send_fw_generic_request(hdev, args);
+
default:
dev_err(dev, "Invalid request %d\n", args->op);
rc = -EINVAL;
diff --git a/drivers/misc/habanalabs/include/common/cpucp_if.h b/drivers/misc/habanalabs/include/common/cpucp_if.h
index baa5aa43b6f4..0a66b7f85164 100644
--- a/drivers/misc/habanalabs/include/common/cpucp_if.h
+++ b/drivers/misc/habanalabs/include/common/cpucp_if.h
@@ -643,6 +643,10 @@ enum pq_init_status {
* data corruption in case of mismatched driver/FW versions.
* Relevant only to Gaudi.
*
+ * * CPUCP_PACKET_GENERIC_PASSTHROUGH -
+ * Generic opcode for all firmware info that is only passed to host
+ * through the LKD, without getting parsed there.
+ *
* CPUCP_PACKET_ACTIVE_STATUS_SET -
* LKD sends FW indication whether device is free or in use, this indication is reported
* also to the BMC.
@@ -704,9 +708,12 @@ enum cpucp_packet_id {
CPUCP_PACKET_RESERVED5, /* not used */
CPUCP_PACKET_RESERVED6, /* not used */
CPUCP_PACKET_RESERVED7, /* not used */
+ CPUCP_PACKET_GENERIC_PASSTHROUGH, /* IOCTL */
CPUCP_PACKET_RESERVED8, /* not used */
- CPUCP_PACKET_RESERVED9, /* not used */
CPUCP_PACKET_ACTIVE_STATUS_SET, /* internal */
+ CPUCP_PACKET_RESERVED9, /* not used */
+ CPUCP_PACKET_RESERVED10, /* not used */
+ CPUCP_PACKET_RESERVED11, /* not used */
CPUCP_PACKET_ID_MAX /* must be last */
};
@@ -805,8 +812,13 @@ struct cpucp_packet {
__le32 nonce;
};
- /* For NIC requests */
- __le32 port_index;
+ union {
+ /* For NIC requests */
+ __le32 port_index;
+
+ /* For Generic packet sub index */
+ __le32 pkt_subidx;
+ };
};
struct cpucp_unmask_irq_arr_packet {
@@ -976,6 +988,11 @@ enum pll_index {
IC_PLL = 16,
MC_PLL = 17,
EMMC_PLL = 18,
+ D2D_PLL = 19,
+ CS_PLL = 20,
+ C2C_PLL = 21,
+ NCH_PLL = 22,
+ C2M_PLL = 23,
PLL_MAX
};
@@ -1135,8 +1152,9 @@ enum cpucp_serdes_type {
HLS1_SERDES_TYPE,
HLS1H_SERDES_TYPE,
HLS2_SERDES_TYPE,
- UNKNOWN_SERDES_TYPE,
- MAX_NUM_SERDES_TYPE = UNKNOWN_SERDES_TYPE
+ HLS2_TYPE_1_SERDES_TYPE,
+ MAX_NUM_SERDES_TYPE, /* number of types */
+ UNKNOWN_SERDES_TYPE = 0xFFFF /* serdes_type is u16 */
};
struct cpucp_nic_info {
@@ -1160,6 +1178,21 @@ struct page_discard_info {
__le32 mmu_page_idx[PAGE_DISCARD_MAX];
};
+/*
+ * struct frac_val - fracture value represented by "integer.frac".
+ * @integer: the integer part of the fracture value;
+ * @frac: the fracture part of the fracture value.
+ */
+struct frac_val {
+ union {
+ struct {
+ __le16 integer;
+ __le16 frac;
+ };
+ __le32 val;
+ };
+};
+
/*
* struct ser_val - the SER (symbol error rate) value is represented by "integer * 10 ^ -exp".
* @integer: the integer part of the SER value;
@@ -1183,8 +1216,12 @@ struct ser_val {
* @pcs_link: has PCS link.
* @phy_ready: is PHY ready.
* @auto_neg: is Autoneg enabled.
- * @timeout_retransmission_cnt: timeout retransmission events
- * @high_ber_cnt: high ber events
+ * @timeout_retransmission_cnt: timeout retransmission events.
+ * @high_ber_cnt: high ber events.
+ * @pre_fec_ser: pre FEC SER value.
+ * @post_fec_ser: post FEC SER value.
+ * @throughput: measured throughput.
+ * @latency: measured latency.
*/
struct cpucp_nic_status {
__le32 port;
@@ -1200,6 +1237,10 @@ struct cpucp_nic_status {
__u8 auto_neg;
__le32 timeout_retransmission_cnt;
__le32 high_ber_cnt;
+ struct ser_val pre_fec_ser;
+ struct ser_val post_fec_ser;
+ struct frac_val bandwidth;
+ struct frac_val lat;
};
enum cpucp_hbm_row_replace_cause {
@@ -1317,4 +1358,14 @@ struct cpucp_monitor_dump {
struct dcore_monitor_regs_data sync_mngr_e_n;
};
+/*
+ * The Type of the generic request (and other input arguments) will be fetched from user by reading
+ * from "pkt_subidx" field in struct cpucp_packet.
+ *
+ * HL_PASSTHROUGHT_VERSIONS - Fetch all firmware versions.
+ */
+enum hl_passthrough_type {
+ HL_PASSTHROUGH_VERSIONS,
+};
+
#endif /* CPUCP_IF_H */
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index c67d18901c1d..90e628779264 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -789,6 +789,7 @@ enum hl_server_type {
* HL_INFO_ENGINE_STATUS - Retrieve the status of all the h/w engines in the asic.
* HL_INFO_PAGE_FAULT_EVENT - Retrieve parameters of captured page fault.
* HL_INFO_USER_MAPPINGS - Retrieve user mappings, captured after page fault event.
+ * HL_INFO_FW_GENERIC_REQ - Send generic request to FW.
*/
#define HL_INFO_HW_IP_INFO 0
#define HL_INFO_HW_EVENTS 1
@@ -822,6 +823,7 @@ enum hl_server_type {
#define HL_INFO_ENGINE_STATUS 32
#define HL_INFO_PAGE_FAULT_EVENT 33
#define HL_INFO_USER_MAPPINGS 34
+#define HL_INFO_FW_GENERIC_REQ 35
#define HL_INFO_VERSION_MAX_LEN 128
#define HL_INFO_CARD_NAME_MAX_LEN 16
@@ -1258,6 +1260,7 @@ enum gaudi_dcores {
* @sec_attest_nonce: Nonce number used for attestation report.
* @array_size: Number of array members copied to user buffer.
* Relevant for HL_INFO_USER_MAPPINGS info ioctl.
+ * @fw_sub_opcode: generic requests sub opcodes.
* @pad: Padding to 64 bit.
*/
struct hl_info_args {
@@ -1274,6 +1277,7 @@ struct hl_info_args {
__u32 user_buffer_actual_size;
__u32 sec_attest_nonce;
__u32 array_size;
+ __u32 fw_sub_opcode;
};
__u32 pad;
--
2.25.1
^ permalink raw reply related [flat|nested] 3+ messages in thread