echo "0x200" > /sys/kernel/debug/habanalabs/hl0/mmu_error
cat /sys/kernel/debug/habanalabs/hl0/mmu_error
+What: /sys/kernel/debug/habanalabs/hl<n>/monitor_dump
+Date: Mar 2022
+KernelVersion: 5.19
+Contact: osharabi@habana.ai
+Description: Allows the root user to dump monitors status from the device's
+ protected config space.
+ This property is a binary blob that contains the result of the
+ monitors registers dump.
+ This custom interface is needed (instead of using the generic
+ Linux user-space PCI mapping) because this space is protected
+ and cannot be accessed using PCI read.
+ This interface doesn't support concurrency in the same device.
+ Only supported on GAUDI.
+
+What: /sys/kernel/debug/habanalabs/hl<n>/monitor_dump_trig
+Date: Mar 2022
+KernelVersion: 5.19
+Contact: osharabi@habana.ai
+Description: Triggers dump of monitor data. The value to trigger the operation
+ must be 1. Triggering the monitor dump operation initiates dump of
+ current registers values of all monitors.
+ When the write is finished, the user can read the "monitor_dump"
+ blob
+
What: /sys/kernel/debug/habanalabs/hl<n>/set_power_state
Date: Jan 2019
KernelVersion: 5.1
}
/* Free the previous allocation, if there was any */
- entry->blob_desc.size = 0;
- vfree(entry->blob_desc.data);
+ entry->data_dma_blob_desc.size = 0;
+ vfree(entry->data_dma_blob_desc.data);
- entry->blob_desc.data = vmalloc(size);
- if (!entry->blob_desc.data)
+ entry->data_dma_blob_desc.data = vmalloc(size);
+ if (!entry->data_dma_blob_desc.data)
return -ENOMEM;
rc = hdev->asic_funcs->debugfs_read_dma(hdev, addr, size,
- entry->blob_desc.data);
+ entry->data_dma_blob_desc.data);
if (rc) {
dev_err(hdev->dev, "Failed to DMA from 0x%010llx\n", addr);
- vfree(entry->blob_desc.data);
- entry->blob_desc.data = NULL;
+ vfree(entry->data_dma_blob_desc.data);
+ entry->data_dma_blob_desc.data = NULL;
return -EIO;
}
- entry->blob_desc.size = size;
+ entry->data_dma_blob_desc.size = size;
+
+ return count;
+}
+
+static ssize_t hl_monitor_dump_trigger(struct file *f, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
+ struct hl_device *hdev = entry->hdev;
+ u32 size, trig;
+ ssize_t rc;
+
+ if (hdev->reset_info.in_reset) {
+ dev_warn_ratelimited(hdev->dev, "Can't dump monitors during reset\n");
+ return 0;
+ }
+ rc = kstrtouint_from_user(buf, count, 10, &trig);
+ if (rc)
+ return rc;
+
+ if (trig != 1) {
+ dev_err(hdev->dev, "Must write 1 to trigger monitor dump\n");
+ return -EINVAL;
+ }
+
+ size = sizeof(struct cpucp_monitor_dump);
+
+ /* Free the previous allocation, if there was any */
+ entry->mon_dump_blob_desc.size = 0;
+ vfree(entry->mon_dump_blob_desc.data);
+
+ entry->mon_dump_blob_desc.data = vmalloc(size);
+ if (!entry->mon_dump_blob_desc.data)
+ return -ENOMEM;
+
+ rc = hdev->asic_funcs->get_monitor_dump(hdev, entry->mon_dump_blob_desc.data);
+ if (rc) {
+ dev_err(hdev->dev, "Failed to dump monitors\n");
+ vfree(entry->mon_dump_blob_desc.data);
+ entry->mon_dump_blob_desc.data = NULL;
+ return -EIO;
+ }
+
+ entry->mon_dump_blob_desc.size = size;
return count;
}
.write = hl_dma_size_write
};
+static const struct file_operations hl_monitor_dump_fops = {
+ .owner = THIS_MODULE,
+ .write = hl_monitor_dump_trigger
+};
+
static const struct file_operations hl_i2c_data_fops = {
.owner = THIS_MODULE,
.read = hl_i2c_data_read,
if (!dev_entry->entry_arr)
return;
- dev_entry->blob_desc.size = 0;
- dev_entry->blob_desc.data = NULL;
+ dev_entry->data_dma_blob_desc.size = 0;
+ dev_entry->data_dma_blob_desc.data = NULL;
+ dev_entry->mon_dump_blob_desc.size = 0;
+ dev_entry->mon_dump_blob_desc.data = NULL;
INIT_LIST_HEAD(&dev_entry->file_list);
INIT_LIST_HEAD(&dev_entry->cb_list);
debugfs_create_blob("data_dma",
0400,
dev_entry->root,
- &dev_entry->blob_desc);
+ &dev_entry->data_dma_blob_desc);
+
+ debugfs_create_file("monitor_dump_trig",
+ 0200,
+ dev_entry->root,
+ dev_entry,
+ &hl_monitor_dump_fops);
+
+ debugfs_create_blob("monitor_dump",
+ 0400,
+ dev_entry->root,
+ &dev_entry->mon_dump_blob_desc);
debugfs_create_x8("skip_reset_on_timeout",
0644,
mutex_destroy(&entry->file_mutex);
- vfree(entry->blob_desc.data);
+ vfree(entry->data_dma_blob_desc.data);
+ vfree(entry->mon_dump_blob_desc.data);
for (i = 0; i < ARRAY_SIZE(entry->state_dump); ++i)
vfree(entry->state_dump[i]);
return rc;
}
+int hl_fw_get_monitor_dump(struct hl_device *hdev, void *data)
+{
+ struct cpucp_monitor_dump *mon_dump_cpu_addr;
+ dma_addr_t mon_dump_dma_addr;
+ struct cpucp_packet pkt = {};
+ size_t data_size;
+ __le32 *src_ptr;
+ u32 *dst_ptr;
+ u64 result;
+ int i, rc;
+
+ data_size = sizeof(struct cpucp_monitor_dump);
+ mon_dump_cpu_addr = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, data_size,
+ &mon_dump_dma_addr);
+ if (!mon_dump_cpu_addr) {
+ dev_err(hdev->dev,
+ "Failed to allocate DMA memory for CPU-CP monitor-dump packet\n");
+ return -ENOMEM;
+ }
+
+ memset(mon_dump_cpu_addr, 0, data_size);
+
+ pkt.ctl = cpu_to_le32(CPUCP_PACKET_MONITOR_DUMP_GET << CPUCP_PKT_CTL_OPCODE_SHIFT);
+ pkt.addr = cpu_to_le64(mon_dump_dma_addr);
+ pkt.data_max_size = cpu_to_le32(data_size);
+
+ rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
+ HL_CPUCP_MON_DUMP_TIMEOUT_USEC, &result);
+ if (rc) {
+ dev_err(hdev->dev, "Failed to handle CPU-CP monitor-dump packet, error %d\n", rc);
+ goto out;
+ }
+
+ /* result contains the actual size */
+ src_ptr = (__le32 *) mon_dump_cpu_addr;
+ dst_ptr = data;
+ for (i = 0; i < (data_size / sizeof(u32)); i++) {
+ *dst_ptr = le32_to_cpu(*src_ptr);
+ src_ptr++;
+ dst_ptr++;
+ }
+
+out:
+ hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, data_size, mon_dump_cpu_addr);
+
+ return rc;
+}
+
int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev,
struct hl_info_pci_counters *counters)
{
#define HL_CPUCP_INFO_TIMEOUT_USEC 10000000 /* 10s */
#define HL_CPUCP_EEPROM_TIMEOUT_USEC 10000000 /* 10s */
+#define HL_CPUCP_MON_DUMP_TIMEOUT_USEC 10000000 /* 10s */
#define HL_FW_STATUS_POLL_INTERVAL_USEC 10000 /* 10ms */
* @hw_queues_unlock: release H/W queues lock.
* @get_pci_id: retrieve PCI ID.
* @get_eeprom_data: retrieve EEPROM data from F/W.
+ * @get_monitor_dump: retrieve monitor registers dump from F/W.
* @send_cpu_message: send message to F/W. If the message is timedout, the
* driver will eventually reset the device. The timeout can
* be determined by the calling function or it can be 0 and
void (*hw_queues_lock)(struct hl_device *hdev);
void (*hw_queues_unlock)(struct hl_device *hdev);
u32 (*get_pci_id)(struct hl_device *hdev);
- int (*get_eeprom_data)(struct hl_device *hdev, void *data,
- size_t max_size);
+ int (*get_eeprom_data)(struct hl_device *hdev, void *data, size_t max_size);
+ int (*get_monitor_dump)(struct hl_device *hdev, void *data);
int (*send_cpu_message)(struct hl_device *hdev, u32 *msg,
u16 len, u32 timeout, u64 *result);
int (*pci_bars_map)(struct hl_device *hdev);
* @userptr_spinlock: protects userptr_list.
* @ctx_mem_hash_list: list of available contexts with MMU mappings.
* @ctx_mem_hash_spinlock: protects cb_list.
- * @blob_desc: descriptor of blob
+ * @data_dma_blob_desc: data DMA descriptor of blob.
+ * @mon_dump_blob_desc: monitor dump descriptor of blob.
* @state_dump: data of the system states in case of a bad cs.
* @state_dump_sem: protects state_dump.
* @addr: next address to read/write from/to in read/write32.
spinlock_t userptr_spinlock;
struct list_head ctx_mem_hash_list;
spinlock_t ctx_mem_hash_spinlock;
- struct debugfs_blob_wrapper blob_desc;
+ struct debugfs_blob_wrapper data_dma_blob_desc;
+ struct debugfs_blob_wrapper mon_dump_blob_desc;
char *state_dump[HL_STATE_DUMP_HIST_LEN];
struct rw_semaphore state_dump_sem;
u64 addr;
u32 sts_boot_dev_sts1_reg, u32 boot_err0_reg,
u32 boot_err1_reg);
int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size);
+int hl_fw_get_monitor_dump(struct hl_device *hdev, void *data);
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,
return hl_fw_get_eeprom_data(hdev, data, max_size);
}
+static int gaudi_get_monitor_dump(struct hl_device *hdev, void *data)
+{
+ struct gaudi_device *gaudi = hdev->asic_specific;
+
+ if (!(gaudi->hw_cap_initialized & HW_CAP_CPU_Q))
+ return 0;
+
+ return hl_fw_get_monitor_dump(hdev, data);
+}
+
/*
* this function should be used only during initialization and/or after reset,
* when there are no active users.
.hw_queues_unlock = gaudi_hw_queues_unlock,
.get_pci_id = gaudi_get_pci_id,
.get_eeprom_data = gaudi_get_eeprom_data,
+ .get_monitor_dump = gaudi_get_monitor_dump,
.send_cpu_message = gaudi_send_cpu_message,
.pci_bars_map = gaudi_pci_bars_map,
.init_iatu = gaudi_init_iatu,
info->page_order_bitmask = 0;
}
+static int goya_get_monitor_dump(struct hl_device *hdev, void *data)
+{
+ return -EOPNOTSUPP;
+}
+
static int goya_mmu_prefetch_cache_range(struct hl_device *hdev, u32 flags, u32 asid, u64 va,
u64 size)
{
.hw_queues_unlock = goya_hw_queues_unlock,
.get_pci_id = goya_get_pci_id,
.get_eeprom_data = goya_get_eeprom_data,
+ .get_monitor_dump = goya_get_monitor_dump,
.send_cpu_message = goya_send_cpu_message,
.pci_bars_map = goya_pci_bars_map,
.init_iatu = goya_init_iatu,
*
* CPUCP_PACKET_ENGINE_CORE_ASID_SET -
* Packet to perform engine core ASID configuration
+ *
+ * CPUCP_PACKET_MONITOR_DUMP_GET -
+ * Get monitors registers dump from the CpuCP kernel.
+ * The CPU will put the registers dump in the a buffer allocated by the driver
+ * which address is passed via the CpuCp packet. In addition, the host's driver
+ * passes the max size it allows the CpuCP to write to the structure, to prevent
+ * data corruption in case of mismatched driver/FW versions.
+ * Relevant only to Gaudi.
*/
enum cpucp_packet_id {
CPUCP_PACKET_POWER_SET, /* internal */
CPUCP_PACKET_RESERVED, /* not used */
CPUCP_PACKET_ENGINE_CORE_ASID_SET, /* internal */
+ CPUCP_PACKET_RESERVED2, /* not used */
+ CPUCP_PACKET_RESERVED3, /* not used */
+ CPUCP_PACKET_RESERVED4, /* not used */
+ CPUCP_PACKET_RESERVED5, /* not used */
+ CPUCP_PACKET_MONITOR_DUMP_GET, /* debugfs */
};
#define CPUCP_PACKET_FENCE_VAL 0xFE8CE7A5
struct cpucp_hbm_row_info replaced_rows[CPUCP_HBM_ROW_REPLACE_MAX];
};
+/*
+ * struct dcore_monitor_regs_data - DCORE monitor regs data.
+ * the structure follows sync manager block layout. relevant only to Gaudi.
+ * @mon_pay_addrl: array of payload address low bits.
+ * @mon_pay_addrh: array of payload address high bits.
+ * @mon_pay_data: array of payload data.
+ * @mon_arm: array of monitor arm.
+ * @mon_status: array of monitor status.
+ */
+struct dcore_monitor_regs_data {
+ __le32 mon_pay_addrl[512];
+ __le32 mon_pay_addrh[512];
+ __le32 mon_pay_data[512];
+ __le32 mon_arm[512];
+ __le32 mon_status[512];
+};
+
+/* contains SM data for each SYNC_MNGR (relevant only to Gaudi) */
+struct cpucp_monitor_dump {
+ struct dcore_monitor_regs_data sync_mngr_w_s;
+ struct dcore_monitor_regs_data sync_mngr_e_s;
+ struct dcore_monitor_regs_data sync_mngr_w_n;
+ struct dcore_monitor_regs_data sync_mngr_e_n;
+};
+
#endif /* CPUCP_IF_H */
projects / platform / kernel / linux-starfive.git / commitdiff