* [PATCH 2/4] habanalabs: expose state dump
2021-07-04 11:50 [PATCH 1/4] habanalabs: use get_task_pid() to take PID Oded Gabbay
@ 2021-07-04 11:51 ` Oded Gabbay
2021-07-04 11:51 ` [PATCH 3/4] habanalabs: state dump monitors and fences infrastructure Oded Gabbay
2021-07-04 11:51 ` [PATCH 4/4] habanalabs/gaudi: implement state dump Oded Gabbay
2 siblings, 0 replies; 4+ messages in thread
From: Oded Gabbay @ 2021-07-04 11:51 UTC (permalink / raw)
To: linux-kernel; +Cc: Yuri Nudelman
From: Yuri Nudelman <ynudelman@habana.ai>
To improve the user's ability to debug the case where a workload that
is part of executing training/inference of a topology is getting stuck,
we need to add a 'core dump' each time a CS times-out. The 'core dump'
shall contain all relevant Sync Manager information and corresponding
fence values.
The most recent dumps shall be accessible via debugfs, under
'state_dump' node. Reading from the node will provide the oldest dump
available. Writing an integer value X will discard X dumps, starting
with the oldest one, i.e. subsequent read will now return newer
dumps.
Signed-off-by: Yuri Nudelman <ynudelman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
.../ABI/testing/debugfs-driver-habanalabs | 11 +
drivers/misc/habanalabs/common/Makefile | 3 +-
.../habanalabs/common/command_submission.c | 4 +
drivers/misc/habanalabs/common/debugfs.c | 93 ++++
drivers/misc/habanalabs/common/device.c | 2 +
drivers/misc/habanalabs/common/habanalabs.h | 132 +++++
drivers/misc/habanalabs/common/state_dump.c | 451 ++++++++++++++++++
drivers/misc/habanalabs/gaudi/gaudi.c | 24 +-
drivers/misc/habanalabs/goya/goya.c | 24 +-
9 files changed, 741 insertions(+), 3 deletions(-)
create mode 100644 drivers/misc/habanalabs/common/state_dump.c
diff --git a/Documentation/ABI/testing/debugfs-driver-habanalabs b/Documentation/ABI/testing/debugfs-driver-habanalabs
index e78ceb1f70b3..25f33500bcc9 100644
--- a/Documentation/ABI/testing/debugfs-driver-habanalabs
+++ b/Documentation/ABI/testing/debugfs-driver-habanalabs
@@ -215,6 +215,17 @@ Description: Sets the skip reset on timeout option for the device. Value of
"0" means device will be reset in case some CS has timed out,
otherwise it will not be reset.
+What: /sys/kernel/debug/habanalabs/hl<n>/state_dump
+Date: Oct 2021
+KernelVersion: 5.15
+Contact: ynudelman@habana.ai
+Description: Gets the state dump occurring on a CS timeout or failure.
+ State dump is used for debug and is created each time in case of
+ a problem in a CS execution, before reset.
+ Reading from the node returns the newest state dump available.
+ Writing an integer X discards X state dumps, so that the
+ next read would return X+1-st newest state dump.
+
What: /sys/kernel/debug/habanalabs/hl<n>/stop_on_err
Date: Mar 2020
KernelVersion: 5.6
diff --git a/drivers/misc/habanalabs/common/Makefile b/drivers/misc/habanalabs/common/Makefile
index 5d8b48288cf4..6ebe3c7001ff 100644
--- a/drivers/misc/habanalabs/common/Makefile
+++ b/drivers/misc/habanalabs/common/Makefile
@@ -10,4 +10,5 @@ HL_COMMON_FILES := common/habanalabs_drv.o common/device.o common/context.o \
common/asid.o common/habanalabs_ioctl.o \
common/command_buffer.o common/hw_queue.o common/irq.o \
common/sysfs.o common/hwmon.o common/memory.o \
- common/command_submission.o common/firmware_if.o
+ common/command_submission.o common/firmware_if.o \
+ common/state_dump.o
diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index 997a37e78241..a0846880400c 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -621,6 +621,10 @@ static void cs_timedout(struct work_struct *work)
break;
}
+ rc = hl_state_dump(hdev);
+ if (rc)
+ dev_err(hdev->dev, "Error during system state dump %d\n", rc);
+
cs_put(cs);
if (likely(!skip_reset_on_timeout)) {
diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c
index 77f7c2aa571d..51744e42b808 100644
--- a/drivers/misc/habanalabs/common/debugfs.c
+++ b/drivers/misc/habanalabs/common/debugfs.c
@@ -1043,6 +1043,60 @@ static ssize_t hl_security_violations_read(struct file *f, char __user *buf,
return 0;
}
+static ssize_t hl_state_dump_read(struct file *f, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
+ ssize_t rc;
+
+ down_read(&entry->state_dump_sem);
+ if (!entry->state_dump[entry->state_dump_head])
+ rc = 0;
+ else
+ rc = simple_read_from_buffer(
+ buf, count, ppos,
+ entry->state_dump[entry->state_dump_head],
+ strlen(entry->state_dump[entry->state_dump_head]));
+ up_read(&entry->state_dump_sem);
+
+ return rc;
+}
+
+static ssize_t hl_state_dump_write(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;
+ ssize_t rc;
+ u32 size;
+ int i;
+
+ rc = kstrtouint_from_user(buf, count, 10, &size);
+ if (rc)
+ return rc;
+
+ if (size <= 0 || size >= ARRAY_SIZE(entry->state_dump)) {
+ dev_err(hdev->dev, "Invalid number of dumps to skip\n");
+ return -EINVAL;
+ }
+
+ if (entry->state_dump[entry->state_dump_head]) {
+ down_write(&entry->state_dump_sem);
+ for (i = 0; i < size; ++i) {
+ vfree(entry->state_dump[entry->state_dump_head]);
+ entry->state_dump[entry->state_dump_head] = NULL;
+ if (entry->state_dump_head > 0)
+ entry->state_dump_head--;
+ else
+ entry->state_dump_head =
+ ARRAY_SIZE(entry->state_dump) - 1;
+ }
+ up_write(&entry->state_dump_sem);
+ }
+
+ return count;
+}
+
static const struct file_operations hl_data32b_fops = {
.owner = THIS_MODULE,
.read = hl_data_read32,
@@ -1110,6 +1164,12 @@ static const struct file_operations hl_security_violations_fops = {
.read = hl_security_violations_read
};
+static const struct file_operations hl_state_dump_fops = {
+ .owner = THIS_MODULE,
+ .read = hl_state_dump_read,
+ .write = hl_state_dump_write
+};
+
static const struct hl_info_list hl_debugfs_list[] = {
{"command_buffers", command_buffers_show, NULL},
{"command_submission", command_submission_show, NULL},
@@ -1172,6 +1232,7 @@ void hl_debugfs_add_device(struct hl_device *hdev)
INIT_LIST_HEAD(&dev_entry->userptr_list);
INIT_LIST_HEAD(&dev_entry->ctx_mem_hash_list);
mutex_init(&dev_entry->file_mutex);
+ init_rwsem(&dev_entry->state_dump_sem);
spin_lock_init(&dev_entry->cb_spinlock);
spin_lock_init(&dev_entry->cs_spinlock);
spin_lock_init(&dev_entry->cs_job_spinlock);
@@ -1283,6 +1344,12 @@ void hl_debugfs_add_device(struct hl_device *hdev)
dev_entry->root,
&hdev->skip_reset_on_timeout);
+ debugfs_create_file("state_dump",
+ 0600,
+ dev_entry->root,
+ dev_entry,
+ &hl_state_dump_fops);
+
for (i = 0, entry = dev_entry->entry_arr ; i < count ; i++, entry++) {
debugfs_create_file(hl_debugfs_list[i].name,
0444,
@@ -1297,6 +1364,7 @@ void hl_debugfs_add_device(struct hl_device *hdev)
void hl_debugfs_remove_device(struct hl_device *hdev)
{
struct hl_dbg_device_entry *entry = &hdev->hl_debugfs;
+ int i;
debugfs_remove_recursive(entry->root);
@@ -1304,6 +1372,9 @@ void hl_debugfs_remove_device(struct hl_device *hdev)
vfree(entry->blob_desc.data);
+ for (i = 0; i < ARRAY_SIZE(entry->state_dump); ++i)
+ vfree(entry->state_dump[i]);
+
kfree(entry->entry_arr);
}
@@ -1416,6 +1487,28 @@ void hl_debugfs_remove_ctx_mem_hash(struct hl_device *hdev, struct hl_ctx *ctx)
spin_unlock(&dev_entry->ctx_mem_hash_spinlock);
}
+/**
+ * hl_debugfs_set_state_dump - register state dump making it accessible via
+ * debugfs
+ * @hdev: pointer to the device structure
+ * @data: the actual dump data
+ * @length: the length of the data
+ */
+void hl_debugfs_set_state_dump(struct hl_device *hdev, char *data,
+ unsigned long length)
+{
+ struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
+
+ down_write(&dev_entry->state_dump_sem);
+
+ dev_entry->state_dump_head = (dev_entry->state_dump_head + 1) %
+ ARRAY_SIZE(dev_entry->state_dump);
+ vfree(dev_entry->state_dump[dev_entry->state_dump_head]);
+ dev_entry->state_dump[dev_entry->state_dump_head] = data;
+
+ up_write(&dev_entry->state_dump_sem);
+}
+
void __init hl_debugfs_init(void)
{
hl_debug_root = debugfs_create_dir("habanalabs", NULL);
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 45070e891544..86426052a191 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -1375,6 +1375,8 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass)
hdev->compute_ctx = NULL;
+ hdev->asic_funcs->state_dump_init(hdev);
+
hl_debugfs_add_device(hdev);
/* debugfs nodes are created in hl_ctx_init so it must be called after
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 5ae95d2abaa6..c1bb175d004b 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -20,6 +20,7 @@
#include <linux/scatterlist.h>
#include <linux/hashtable.h>
#include <linux/debugfs.h>
+#include <linux/rwsem.h>
#include <linux/bitfield.h>
#include <linux/genalloc.h>
#include <linux/sched/signal.h>
@@ -65,6 +66,11 @@
#define HL_COMMON_USER_INTERRUPT_ID 0xFFF
+#define HL_STATE_DUMP_HIST_LEN 5
+
+#define OBJ_NAMES_HASH_TABLE_BITS 7 /* 1 << 7 buckets */
+#define SYNC_TO_ENGINE_HASH_TABLE_BITS 7 /* 1 << 7 buckets */
+
/* Memory */
#define MEM_HASH_TABLE_BITS 7 /* 1 << 7 buckets */
@@ -1123,6 +1129,7 @@ struct fw_load_mgr {
* generic f/w compatible PLL Indexes
* @init_firmware_loader: initialize data for FW loader.
* @init_cpu_scrambler_dram: Enable CPU specific DRAM scrambling
+ * @state_dump_init: initialize constants required for state dump
*/
struct hl_asic_funcs {
int (*early_init)(struct hl_device *hdev);
@@ -1248,6 +1255,7 @@ struct hl_asic_funcs {
int (*map_pll_idx_to_fw_idx)(u32 pll_idx);
void (*init_firmware_loader)(struct hl_device *hdev);
void (*init_cpu_scrambler_dram)(struct hl_device *hdev);
+ void (*state_dump_init)(struct hl_device *hdev);
};
@@ -1781,9 +1789,12 @@ struct hl_debugfs_entry {
* @ctx_mem_hash_list: list of available contexts with MMU mappings.
* @ctx_mem_hash_spinlock: protects cb_list.
* @blob_desc: 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.
* @mmu_addr: next virtual address to translate to physical address in mmu_show.
* @mmu_asid: ASID to use while translating in mmu_show.
+ * @state_dump_head: index of the latest state dump
* @i2c_bus: generic u8 debugfs file for bus value to use in i2c_data_read.
* @i2c_addr: generic u8 debugfs file for address value to use in i2c_data_read.
* @i2c_reg: generic u8 debugfs file for register value to use in i2c_data_read.
@@ -1805,14 +1816,117 @@ struct hl_dbg_device_entry {
struct list_head ctx_mem_hash_list;
spinlock_t ctx_mem_hash_spinlock;
struct debugfs_blob_wrapper blob_desc;
+ char *state_dump[HL_STATE_DUMP_HIST_LEN];
+ struct rw_semaphore state_dump_sem;
u64 addr;
u64 mmu_addr;
u32 mmu_asid;
+ u32 state_dump_head;
u8 i2c_bus;
u8 i2c_addr;
u8 i2c_reg;
};
+/**
+ * struct hl_hw_obj_name_entry - single hw object name, member of
+ * hl_state_dump_specs
+ * @node: link to the containing hash table
+ * @name: hw object name
+ * @id: object identifier
+ */
+struct hl_hw_obj_name_entry {
+ struct hlist_node node;
+ const char *name;
+ u32 id;
+};
+
+enum hl_state_dump_specs_props {
+ SP_SYNC_OBJ_BASE_ADDR,
+ SP_NEXT_SYNC_OBJ_ADDR,
+ SP_SYNC_OBJ_AMOUNT,
+ SP_MON_OBJ_WR_ADDR_LOW,
+ SP_MON_OBJ_WR_ADDR_HIGH,
+ SP_MON_OBJ_WR_DATA,
+ SP_MON_OBJ_ARM_DATA,
+ SP_MON_OBJ_STATUS,
+ SP_MONITORS_AMOUNT,
+ SP_TPC0_CMDQ,
+ SP_TPC0_CFG_SO,
+ SP_NEXT_TPC,
+ SP_MME_CMDQ,
+ SP_MME_CFG_SO,
+ SP_NEXT_MME,
+ SP_DMA_CMDQ,
+ SP_DMA_CFG_SO,
+ SP_DMA_QUEUES_OFFSET,
+ SP_NUM_OF_MME_ENGINES,
+ SP_SUB_MME_ENG_NUM,
+ SP_NUM_OF_DMA_ENGINES,
+ SP_NUM_OF_TPC_ENGINES,
+ SP_ENGINE_NUM_OF_QUEUES,
+ SP_ENGINE_NUM_OF_STREAMS,
+ SP_ENGINE_NUM_OF_FENCES,
+ SP_FENCE0_CNT_OFFSET,
+ SP_FENCE0_RDATA_OFFSET,
+ SP_CP_STS_OFFSET,
+ SP_NUM_CORES,
+
+ SP_MAX
+};
+
+enum hl_sync_engine_type {
+ ENGINE_TPC,
+ ENGINE_DMA,
+ ENGINE_MME,
+};
+
+/**
+ * struct hl_sync_to_engine_map_entry - sync object id to engine mapping entry
+ * @engine_type: type of the engine
+ * @engine_id: id of the engine
+ * @sync_id: id of the sync object
+ */
+struct hl_sync_to_engine_map_entry {
+ struct hlist_node node;
+ enum hl_sync_engine_type engine_type;
+ u32 engine_id;
+ u32 sync_id;
+};
+
+/**
+ * struct hl_sync_to_engine_map - maps sync object id to associated engine id
+ * @tb: hash table containing the mapping, each element is of type
+ * struct hl_sync_to_engine_map_entry
+ */
+struct hl_sync_to_engine_map {
+ DECLARE_HASHTABLE(tb, SYNC_TO_ENGINE_HASH_TABLE_BITS);
+};
+
+/**
+ * struct hl_state_dump_specs_funcs - virtual functions used by the state dump
+ * @gen_sync_to_engine_map: generate a hash map from sync obj id to its engine
+ */
+struct hl_state_dump_specs_funcs {
+ int (*gen_sync_to_engine_map)(struct hl_device *hdev,
+ struct hl_sync_to_engine_map *map);
+};
+
+/**
+ * struct hl_state_dump_specs - defines ASIC known hw objects names
+ * @so_id_to_str_tb: sync objects names index table
+ * @monitor_id_to_str_tb: monitors names index table
+ * @funcs: virtual functions used for state dump
+ * @sync_namager_names: readable names for sync manager if available (ex: N_E)
+ * @props: pointer to a per asic const props array required for state dump
+ */
+struct hl_state_dump_specs {
+ DECLARE_HASHTABLE(so_id_to_str_tb, OBJ_NAMES_HASH_TABLE_BITS);
+ DECLARE_HASHTABLE(monitor_id_to_str_tb, OBJ_NAMES_HASH_TABLE_BITS);
+ struct hl_state_dump_specs_funcs funcs;
+ const char * const *sync_namager_names;
+ s64 *props;
+};
+
/*
* DEVICES
@@ -2151,6 +2265,7 @@ struct hl_mmu_funcs {
* @mmu_func: device-related MMU functions.
* @fw_loader: FW loader manager.
* @pci_mem_region: array of memory regions in the PCI
+ * @state_dump_specs: constants and dictionaries needed to dump system state.
* @dram_used_mem: current DRAM memory consumption.
* @timeout_jiffies: device CS timeout value.
* @max_power: the max power of the device, as configured by the sysadmin. This
@@ -2295,6 +2410,8 @@ struct hl_device {
struct pci_mem_region pci_mem_region[PCI_REGION_NUMBER];
+ struct hl_state_dump_specs state_dump_specs;
+
atomic64_t dram_used_mem;
u64 timeout_jiffies;
u64 max_power;
@@ -2676,6 +2793,14 @@ void hl_release_pending_user_interrupts(struct hl_device *hdev);
int hl_cs_signal_sob_wraparound_handler(struct hl_device *hdev, u32 q_idx,
struct hl_hw_sob **hw_sob, u32 count);
+int hl_state_dump(struct hl_device *hdev);
+const char *hl_state_dump_get_sync_name(struct hl_device *hdev, u32 sync_id);
+void hl_state_dump_free_sync_to_engine_map(struct hl_sync_to_engine_map *map);
+__printf(4, 5) int hl_snprintf_resize(char **buf, size_t *size, size_t *offset,
+ const char *format, ...);
+char *hl_format_as_binary(char *buf, size_t buf_len, u32 n);
+const char *hl_sync_engine_to_string(enum hl_sync_engine_type engine_type);
+
#ifdef CONFIG_DEBUG_FS
void hl_debugfs_init(void);
@@ -2695,6 +2820,8 @@ void hl_debugfs_remove_userptr(struct hl_device *hdev,
struct hl_userptr *userptr);
void hl_debugfs_add_ctx_mem_hash(struct hl_device *hdev, struct hl_ctx *ctx);
void hl_debugfs_remove_ctx_mem_hash(struct hl_device *hdev, struct hl_ctx *ctx);
+void hl_debugfs_set_state_dump(struct hl_device *hdev, char *data,
+ unsigned long length);
#else
@@ -2768,6 +2895,11 @@ static inline void hl_debugfs_remove_ctx_mem_hash(struct hl_device *hdev,
{
}
+void hl_debugfs_set_state_dump(struct hl_device *hdev, char *data,
+ unsigned long length)
+{
+}
+
#endif
/* IOCTLs */
diff --git a/drivers/misc/habanalabs/common/state_dump.c b/drivers/misc/habanalabs/common/state_dump.c
new file mode 100644
index 000000000000..6a142a6acdfa
--- /dev/null
+++ b/drivers/misc/habanalabs/common/state_dump.c
@@ -0,0 +1,451 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2021 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include <uapi/misc/habanalabs.h>
+#include "habanalabs.h"
+
+/**
+ * A helper function, format an integer as binary using supplied scratch buffer,
+ * return the pointer to the buffer.
+ * @buf: the buffer to use
+ * @buf_len: buffer capacity
+ * @n: number to format
+ *
+ * Returns pointer to buf
+ */
+char *hl_format_as_binary(char *buf, size_t buf_len, u32 n)
+{
+ int i;
+ u32 bit;
+ bool leading0 = true;
+ char *wrptr = buf;
+
+ if (buf_len > 0 && buf_len < 3) {
+ *wrptr = '\0';
+ return buf;
+ }
+
+ wrptr[0] = '0';
+ wrptr[1] = 'b';
+ wrptr += 2;
+ /* Remove 3 characters from length for '0b' and '\0' termination */
+ buf_len -= 3;
+
+ for (i = 0; i < sizeof(n) * BITS_PER_BYTE && buf_len; ++i, n <<= 1) {
+ /* Writing bit calculation in one line would cause a false
+ * positive static code analysis error, so splitting.
+ */
+ bit = n & (1 << (sizeof(n) * BITS_PER_BYTE - 1));
+ bit = !!bit;
+ leading0 &= !bit;
+ if (!leading0) {
+ *wrptr = '0' + bit;
+ ++wrptr;
+ }
+ }
+
+ *wrptr = '\0';
+
+ return buf;
+}
+
+/**
+ * resize_to_fit - helper function, resize buffer to fit given amount of data
+ * @buf: destination buffer double pointer
+ * @size: pointer to the size container
+ * @desired_size: size the buffer must contain
+ *
+ * Returns 0 on success or error code on failure.
+ * On success, the size of buffer is at least desired_size. Buffer is allocated
+ * via vmalloc and must be freed with vfree.
+ */
+static int resize_to_fit(char **buf, size_t *size, size_t desired_size)
+{
+ char *resized_buf;
+ size_t new_size;
+
+ if (*size >= desired_size)
+ return 0;
+
+ /* Not enough space to print all, have to resize */
+ new_size =
+ max(PAGE_SIZE, round_up(desired_size, PAGE_SIZE));
+ resized_buf = vmalloc(new_size);
+ if (!resized_buf)
+ return -ENOMEM;
+ memcpy(resized_buf, *buf, *size);
+ vfree(*buf);
+ *buf = resized_buf;
+ *size = new_size;
+
+ return 1;
+}
+
+/**
+ * hl_snprintf_resize() - print formatted data to buffer, resize as needed
+ * @buf: buffer double pointer, to be written to and resized, must be either
+ * NULL or allocated with vmalloc.
+ * @size: current size of the buffer
+ * @offset: current offset to write to
+ * @format: format of the data
+ *
+ * This function will write formatted data into the buffer. If buffer is not
+ * large enough, it will be resized using vmalloc. Size may be modified if the
+ * buffer was resized, offset will be advanced by the number of bytes written
+ * not including the terminating character
+ *
+ * Returns 0 on success or error code on failure
+ *
+ * Note that the buffer has to be manually released using vfree.
+ */
+int hl_snprintf_resize(char **buf, size_t *size, size_t *offset,
+ const char *format, ...)
+{
+ va_list args;
+ size_t length;
+ int rc;
+
+ if (*buf == NULL && (*size != 0 || *offset != 0))
+ return -EINVAL;
+
+ va_start(args, format);
+ length = vsnprintf(*buf + *offset, *size - *offset, format, args);
+ va_end(args);
+
+ rc = resize_to_fit(buf, size, *offset + length + 1);
+ if (rc < 0)
+ return rc;
+ else if (rc > 0) {
+ /* Resize was needed, write again */
+ va_start(args, format);
+ length = vsnprintf(*buf + *offset, *size - *offset, format,
+ args);
+ va_end(args);
+ }
+
+ *offset += length;
+
+ return 0;
+}
+
+/**
+ * hl_sync_engine_to_string - convert engine type enum to string literal
+ * @engine_type: engine type (TPC/MME/DMA)
+ *
+ * Return the resolved string literal
+ */
+const char *hl_sync_engine_to_string(enum hl_sync_engine_type engine_type)
+{
+ switch (engine_type) {
+ case ENGINE_DMA:
+ return "DMA";
+ case ENGINE_MME:
+ return "MME";
+ case ENGINE_TPC:
+ return "TPC";
+ }
+ return "Invalid Engine Type";
+}
+
+/**
+ * hl_print_resize_sync_engine - helper function, format engine name and ID
+ * using hl_snprintf_resize
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ * @engine_type: engine type (TPC/MME/DMA)
+ * @engine_id: engine numerical id
+ *
+ * Returns 0 on success or error code on failure
+ */
+static int hl_print_resize_sync_engine(char **buf, size_t *size, size_t *offset,
+ enum hl_sync_engine_type engine_type,
+ u32 engine_id)
+{
+ return hl_snprintf_resize(buf, size, offset, "%s%u",
+ hl_sync_engine_to_string(engine_type), engine_id);
+}
+
+/**
+ * hl_state_dump_get_sync_name - transform sync object id to name if available
+ * @hdev: pointer to the device
+ * @sync_id: sync object id
+ *
+ * Returns a name literal or NULL if not resolved.
+ * Note: returning NULL shall not be considered as a failure, as not all
+ * sync objects are named.
+ */
+const char *hl_state_dump_get_sync_name(struct hl_device *hdev, u32 sync_id)
+{
+ struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+ struct hl_hw_obj_name_entry *entry;
+
+ hash_for_each_possible(sds->so_id_to_str_tb, entry,
+ node, sync_id)
+ if (sync_id == entry->id)
+ return entry->name;
+
+ return NULL;
+}
+
+/**
+ * hl_state_dump_free_sync_to_engine_map - free sync object to engine map
+ * @map: sync object to engine map
+ *
+ * Note: generic free implementation, the allocation is implemented per ASIC.
+ */
+void hl_state_dump_free_sync_to_engine_map(struct hl_sync_to_engine_map *map)
+{
+ struct hl_sync_to_engine_map_entry *entry;
+ struct hlist_node *tmp_node;
+ int i;
+
+ hash_for_each_safe(map->tb, i, tmp_node, entry, node) {
+ hash_del(&entry->node);
+ kfree(entry);
+ }
+}
+
+/**
+ * hl_state_dump_get_sync_to_engine - transform sync_id to
+ * hl_sync_to_engine_map_entry if available for current id
+ * @map: sync object to engine map
+ * @sync_id: sync object id
+ *
+ * Returns the translation entry if found or NULL if not.
+ * Note, returned NULL shall not be considered as a failure as the map
+ * does not cover all possible, it is a best effort sync ids.
+ */
+static struct hl_sync_to_engine_map_entry *
+hl_state_dump_get_sync_to_engine(struct hl_sync_to_engine_map *map, u32 sync_id)
+{
+ struct hl_sync_to_engine_map_entry *entry;
+
+ hash_for_each_possible(map->tb, entry, node, sync_id)
+ if (entry->sync_id == sync_id)
+ return entry;
+ return NULL;
+}
+
+/**
+ * hl_state_dump_read_sync_objects - read sync objects array
+ * @hdev: pointer to the device
+ * @index: sync manager block index starting with E_N
+ *
+ * Returns array of size SP_SYNC_OBJ_AMOUNT on success or NULL on failure
+ */
+static u32 *hl_state_dump_read_sync_objects(struct hl_device *hdev, u32 index)
+{
+ struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+ u32 *sync_objects;
+ s64 base_addr; /* Base addr can be negative */
+ int i;
+
+ base_addr =
+ sds->props[SP_SYNC_OBJ_BASE_ADDR] +
+ sds->props[SP_NEXT_SYNC_OBJ_ADDR] *
+ index;
+
+ sync_objects = vmalloc(
+ sds->props[SP_SYNC_OBJ_AMOUNT] *
+ sizeof(u32));
+ if (!sync_objects)
+ return NULL;
+
+ for (i = 0;
+ i < sds->props[SP_SYNC_OBJ_AMOUNT];
+ ++i) {
+ sync_objects[i] =
+ RREG32(base_addr + i * sizeof(u32));
+ }
+
+ return sync_objects;
+}
+
+/**
+ * hl_state_dump_free_sync_objects - free sync objects array allocated by
+ * hl_state_dump_read_sync_objects
+ * @sync_objects: sync objects array
+ */
+static void hl_state_dump_free_sync_objects(u32 *sync_objects)
+{
+ vfree(sync_objects);
+}
+
+
+/**
+ * hl_state_dump_print_syncs_single_block - print active sync objects on a
+ * single block
+ * @hdev: pointer to the device
+ * @index: sync manager block index starting with E_N
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ * @map: sync engines names map
+ *
+ * Returns 0 on success or error code on failure
+ */
+static int
+hl_state_dump_print_syncs_single_block(struct hl_device *hdev, u32 index,
+ char **buf, size_t *size, size_t *offset,
+ struct hl_sync_to_engine_map *map)
+{
+ struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+ const char *sync_name;
+ u32 *sync_objects = NULL;
+ int rc = 0, i;
+
+ if (sds->sync_namager_names) {
+ rc = hl_snprintf_resize(
+ buf, size, offset, "%s\n",
+ sds->sync_namager_names[index]);
+ if (rc)
+ goto out;
+ }
+
+ sync_objects = hl_state_dump_read_sync_objects(hdev, index);
+ if (!sync_objects) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ for (i = 0;
+ i < sds->props[SP_SYNC_OBJ_AMOUNT];
+ ++i) {
+ struct hl_sync_to_engine_map_entry *entry;
+ u64 sync_object_addr;
+
+ if (!sync_objects[i])
+ continue;
+
+ sync_object_addr =
+ sds->props[SP_SYNC_OBJ_BASE_ADDR] +
+ sds->props[SP_NEXT_SYNC_OBJ_ADDR] *
+ index + i * sizeof(u32);
+
+ rc = hl_snprintf_resize(buf, size, offset, "sync id: %u", i);
+ if (rc)
+ goto free_sync_objects;
+ sync_name = hl_state_dump_get_sync_name(hdev, i);
+ if (sync_name) {
+ rc = hl_snprintf_resize(buf, size, offset, " %s",
+ sync_name);
+ if (rc)
+ goto free_sync_objects;
+ }
+ rc = hl_snprintf_resize(buf, size, offset, ", value: %u",
+ sync_objects[i]);
+ if (rc)
+ goto free_sync_objects;
+
+ /* Append engine string */
+ entry = hl_state_dump_get_sync_to_engine(map,
+ (u32)sync_object_addr);
+ if (entry) {
+ rc = hl_snprintf_resize(buf, size, offset, ", Engine: ");
+ if (rc)
+ goto free_sync_objects;
+ rc = hl_print_resize_sync_engine(buf, size, offset,
+ entry->engine_type,
+ entry->engine_id);
+ if (rc)
+ goto free_sync_objects;
+ }
+
+ rc = hl_snprintf_resize(buf, size, offset, "\n");
+ if (rc)
+ goto free_sync_objects;
+ }
+
+free_sync_objects:
+ hl_state_dump_free_sync_objects(sync_objects);
+out:
+ return rc;
+}
+
+/**
+ * hl_state_dump_print_syncs - print active sync objects
+ * @hdev: pointer to the device
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ *
+ * Returns 0 on success or error code on failure
+ */
+static int hl_state_dump_print_syncs(struct hl_device *hdev,
+ char **buf, size_t *size,
+ size_t *offset)
+
+{
+ struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+ struct hl_sync_to_engine_map *map;
+ u32 index;
+ int rc = 0;
+
+ map = kzalloc(sizeof(*map), GFP_KERNEL);
+ if (!map)
+ return -ENOMEM;
+
+ rc = sds->funcs.gen_sync_to_engine_map(hdev, map);
+ if (rc)
+ goto free_map_mem;
+
+ rc = hl_snprintf_resize(buf, size, offset, "Non zero sync objects:\n");
+ if (rc)
+ goto out;
+
+ if (sds->sync_namager_names) {
+ for (index = 0; sds->sync_namager_names[index]; ++index) {
+ rc = hl_state_dump_print_syncs_single_block(
+ hdev, index, buf, size, offset, map);
+ if (rc)
+ goto out;
+ }
+ } else {
+ for (index = 0; index < sds->props[SP_NUM_CORES]; ++index) {
+ rc = hl_state_dump_print_syncs_single_block(
+ hdev, index, buf, size, offset, map);
+ if (rc)
+ goto out;
+ }
+ }
+
+out:
+ hl_state_dump_free_sync_to_engine_map(map);
+free_map_mem:
+ kfree(map);
+
+ return rc;
+}
+
+/**
+ * hl_state_dump() - dump system state
+ * @hdev: pointer to device structure
+ */
+int hl_state_dump(struct hl_device *hdev)
+{
+ char *buf = NULL;
+ size_t offset = 0, size = 0;
+ int rc;
+
+ rc = hl_snprintf_resize(&buf, &size, &offset,
+ "Timestamp taken on: %llu\n\n",
+ ktime_to_ns(ktime_get()));
+
+ rc = hl_state_dump_print_syncs(hdev, &buf, &size, &offset);
+ if (rc)
+ goto err;
+
+ hl_snprintf_resize(&buf, &size, &offset, "\n");
+
+ hl_debugfs_set_state_dump(hdev, buf, size);
+
+ return 0;
+err:
+ vfree(buf);
+ return rc;
+}
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index aa8a0ca5aca2..7f90f637d7f4 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -348,6 +348,8 @@ static enum hl_queue_type gaudi_queue_type[GAUDI_QUEUE_ID_SIZE] = {
QUEUE_TYPE_INT, /* GAUDI_QUEUE_ID_NIC_9_3 */
};
+static s64 gaudi_state_dump_specs_props[SP_MAX] = {0};
+
struct ecc_info_extract_params {
u64 block_address;
u32 num_memories;
@@ -8977,6 +8979,25 @@ static int gaudi_map_pll_idx_to_fw_idx(u32 pll_idx)
}
}
+static int gaudi_gen_sync_to_engine_map(struct hl_device *hdev,
+ struct hl_sync_to_engine_map *map)
+{
+ /* Not implemented */
+ return 0;
+}
+
+
+static struct hl_state_dump_specs_funcs gaudi_state_dump_funcs = {
+ .gen_sync_to_engine_map = gaudi_gen_sync_to_engine_map,
+};
+
+static void gaudi_state_dump_init(struct hl_device *hdev)
+{
+ /* Not implemented */
+ hdev->state_dump_specs.props = gaudi_state_dump_specs_props;
+ hdev->state_dump_specs.funcs = gaudi_state_dump_funcs;
+}
+
static const struct hl_asic_funcs gaudi_funcs = {
.early_init = gaudi_early_init,
.early_fini = gaudi_early_fini,
@@ -9062,7 +9083,8 @@ static const struct hl_asic_funcs gaudi_funcs = {
.enable_events_from_fw = gaudi_enable_events_from_fw,
.map_pll_idx_to_fw_idx = gaudi_map_pll_idx_to_fw_idx,
.init_firmware_loader = gaudi_init_firmware_loader,
- .init_cpu_scrambler_dram = gaudi_init_scrambler_hbm
+ .init_cpu_scrambler_dram = gaudi_init_scrambler_hbm,
+ .state_dump_init = gaudi_state_dump_init
};
/**
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 755e08cf2ecc..2c3d642d31ab 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -350,6 +350,8 @@ static u32 goya_all_events[] = {
GOYA_ASYNC_EVENT_ID_FIX_THERMAL_ENV_E
};
+static s64 goya_state_dump_specs_props[SP_MAX] = {0};
+
static int goya_mmu_clear_pgt_range(struct hl_device *hdev);
static int goya_mmu_set_dram_default_page(struct hl_device *hdev);
static int goya_mmu_add_mappings_for_device_cpu(struct hl_device *hdev);
@@ -5524,6 +5526,25 @@ static int goya_map_pll_idx_to_fw_idx(u32 pll_idx)
}
}
+static int goya_gen_sync_to_engine_map(struct hl_device *hdev,
+ struct hl_sync_to_engine_map *map)
+{
+ /* Not implemented */
+ return 0;
+}
+
+
+static struct hl_state_dump_specs_funcs goya_state_dump_funcs = {
+ .gen_sync_to_engine_map = goya_gen_sync_to_engine_map,
+};
+
+static void goya_state_dump_init(struct hl_device *hdev)
+{
+ /* Not implemented */
+ hdev->state_dump_specs.props = goya_state_dump_specs_props;
+ hdev->state_dump_specs.funcs = goya_state_dump_funcs;
+}
+
static const struct hl_asic_funcs goya_funcs = {
.early_init = goya_early_init,
.early_fini = goya_early_fini,
@@ -5609,7 +5630,8 @@ static const struct hl_asic_funcs goya_funcs = {
.enable_events_from_fw = goya_enable_events_from_fw,
.map_pll_idx_to_fw_idx = goya_map_pll_idx_to_fw_idx,
.init_firmware_loader = goya_init_firmware_loader,
- .init_cpu_scrambler_dram = goya_cpu_init_scrambler_dram
+ .init_cpu_scrambler_dram = goya_cpu_init_scrambler_dram,
+ .state_dump_init = goya_state_dump_init,
};
/*
--
2.25.1
^ permalink raw reply related [flat|nested] 4+ messages in thread* [PATCH 3/4] habanalabs: state dump monitors and fences infrastructure
2021-07-04 11:50 [PATCH 1/4] habanalabs: use get_task_pid() to take PID Oded Gabbay
2021-07-04 11:51 ` [PATCH 2/4] habanalabs: expose state dump Oded Gabbay
@ 2021-07-04 11:51 ` Oded Gabbay
2021-07-04 11:51 ` [PATCH 4/4] habanalabs/gaudi: implement state dump Oded Gabbay
2 siblings, 0 replies; 4+ messages in thread
From: Oded Gabbay @ 2021-07-04 11:51 UTC (permalink / raw)
To: linux-kernel; +Cc: Yuri Nudelman
From: Yuri Nudelman <ynudelman@habana.ai>
With the infrastructure in place, monitors and fences dump shall be
implemented.
Signed-off-by: Yuri Nudelman <ynudelman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
drivers/misc/habanalabs/common/habanalabs.h | 33 +++
drivers/misc/habanalabs/common/state_dump.c | 311 ++++++++++++++++++--
drivers/misc/habanalabs/gaudi/gaudi.c | 27 ++
drivers/misc/habanalabs/goya/goya.c | 27 ++
4 files changed, 375 insertions(+), 23 deletions(-)
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index c1bb175d004b..3657d24ca467 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -1880,6 +1880,24 @@ enum hl_sync_engine_type {
ENGINE_MME,
};
+/**
+ * struct hl_mon_state_dump - represents a state dump of a single monitor
+ * @id: monitor id
+ * @wr_addr_low: address monitor will write to, low bits
+ * @wr_addr_high: address monitor will write to, high bits
+ * @wr_data: data monitor will write
+ * @arm_data: register value containing monitor configuration
+ * @status: monitor status
+ */
+struct hl_mon_state_dump {
+ u32 id;
+ u32 wr_addr_low;
+ u32 wr_addr_high;
+ u32 wr_data;
+ u32 arm_data;
+ u32 status;
+};
+
/**
* struct hl_sync_to_engine_map_entry - sync object id to engine mapping entry
* @engine_type: type of the engine
@@ -1905,10 +1923,23 @@ struct hl_sync_to_engine_map {
/**
* struct hl_state_dump_specs_funcs - virtual functions used by the state dump
* @gen_sync_to_engine_map: generate a hash map from sync obj id to its engine
+ * @print_single_monitor: format monitor data as string
+ * @monitor_valid: return true if given monitor dump is valid
+ * @print_fences_single_engine: format fences data as string
*/
struct hl_state_dump_specs_funcs {
int (*gen_sync_to_engine_map)(struct hl_device *hdev,
struct hl_sync_to_engine_map *map);
+ int (*print_single_monitor)(char **buf, size_t *size, size_t *offset,
+ struct hl_device *hdev,
+ struct hl_mon_state_dump *mon);
+ int (*monitor_valid)(struct hl_mon_state_dump *mon);
+ int (*print_fences_single_engine)(struct hl_device *hdev,
+ u64 base_offset,
+ u64 status_base_offset,
+ enum hl_sync_engine_type engine_type,
+ u32 engine_id, char **buf,
+ size_t *size, size_t *offset);
};
/**
@@ -2795,6 +2826,8 @@ int hl_cs_signal_sob_wraparound_handler(struct hl_device *hdev, u32 q_idx,
int hl_state_dump(struct hl_device *hdev);
const char *hl_state_dump_get_sync_name(struct hl_device *hdev, u32 sync_id);
+const char *hl_state_dump_get_monitor_name(struct hl_device *hdev,
+ struct hl_mon_state_dump *mon);
void hl_state_dump_free_sync_to_engine_map(struct hl_sync_to_engine_map *map);
__printf(4, 5) int hl_snprintf_resize(char **buf, size_t *size, size_t *offset,
const char *format, ...);
diff --git a/drivers/misc/habanalabs/common/state_dump.c b/drivers/misc/habanalabs/common/state_dump.c
index 6a142a6acdfa..34ffab4f9cbc 100644
--- a/drivers/misc/habanalabs/common/state_dump.c
+++ b/drivers/misc/habanalabs/common/state_dump.c
@@ -5,6 +5,7 @@
* All Rights Reserved.
*/
+#include <linux/vmalloc.h>
#include <uapi/misc/habanalabs.h>
#include "habanalabs.h"
@@ -72,8 +73,7 @@ static int resize_to_fit(char **buf, size_t *size, size_t desired_size)
return 0;
/* Not enough space to print all, have to resize */
- new_size =
- max(PAGE_SIZE, round_up(desired_size, PAGE_SIZE));
+ new_size = max(PAGE_SIZE, round_up(desired_size, PAGE_SIZE));
resized_buf = vmalloc(new_size);
if (!resized_buf)
return -ENOMEM;
@@ -192,6 +192,30 @@ const char *hl_state_dump_get_sync_name(struct hl_device *hdev, u32 sync_id)
return NULL;
}
+/**
+ * hl_state_dump_get_monitor_name - transform monitor object dump to monitor
+ * name if available
+ * @hdev: pointer to the device
+ * @mon: monitor state dump
+ *
+ * Returns a name literal or NULL if not resolved.
+ * Note: returning NULL shall not be considered as a failure, as not all
+ * monitors are named.
+ */
+const char *hl_state_dump_get_monitor_name(struct hl_device *hdev,
+ struct hl_mon_state_dump *mon)
+{
+ struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+ struct hl_hw_obj_name_entry *entry;
+
+ hash_for_each_possible(sds->monitor_id_to_str_tb,
+ entry, node, mon->id)
+ if (mon->id == entry->id)
+ return entry->name;
+
+ return NULL;
+}
+
/**
* hl_state_dump_free_sync_to_engine_map - free sync object to engine map
* @map: sync object to engine map
@@ -245,23 +269,15 @@ static u32 *hl_state_dump_read_sync_objects(struct hl_device *hdev, u32 index)
s64 base_addr; /* Base addr can be negative */
int i;
- base_addr =
- sds->props[SP_SYNC_OBJ_BASE_ADDR] +
- sds->props[SP_NEXT_SYNC_OBJ_ADDR] *
- index;
+ base_addr = sds->props[SP_SYNC_OBJ_BASE_ADDR] +
+ sds->props[SP_NEXT_SYNC_OBJ_ADDR] * index;
- sync_objects = vmalloc(
- sds->props[SP_SYNC_OBJ_AMOUNT] *
- sizeof(u32));
+ sync_objects = vmalloc(sds->props[SP_SYNC_OBJ_AMOUNT] * sizeof(u32));
if (!sync_objects)
return NULL;
- for (i = 0;
- i < sds->props[SP_SYNC_OBJ_AMOUNT];
- ++i) {
- sync_objects[i] =
- RREG32(base_addr + i * sizeof(u32));
- }
+ for (i = 0; i < sds->props[SP_SYNC_OBJ_AMOUNT]; ++i)
+ sync_objects[i] = RREG32(base_addr + i * sizeof(u32));
return sync_objects;
}
@@ -313,19 +329,16 @@ hl_state_dump_print_syncs_single_block(struct hl_device *hdev, u32 index,
goto out;
}
- for (i = 0;
- i < sds->props[SP_SYNC_OBJ_AMOUNT];
- ++i) {
+ for (i = 0; i < sds->props[SP_SYNC_OBJ_AMOUNT]; ++i) {
struct hl_sync_to_engine_map_entry *entry;
u64 sync_object_addr;
if (!sync_objects[i])
continue;
- sync_object_addr =
- sds->props[SP_SYNC_OBJ_BASE_ADDR] +
- sds->props[SP_NEXT_SYNC_OBJ_ADDR] *
- index + i * sizeof(u32);
+ sync_object_addr = sds->props[SP_SYNC_OBJ_BASE_ADDR] +
+ sds->props[SP_NEXT_SYNC_OBJ_ADDR] * index +
+ i * sizeof(u32);
rc = hl_snprintf_resize(buf, size, offset, "sync id: %u", i);
if (rc)
@@ -346,7 +359,8 @@ hl_state_dump_print_syncs_single_block(struct hl_device *hdev, u32 index,
entry = hl_state_dump_get_sync_to_engine(map,
(u32)sync_object_addr);
if (entry) {
- rc = hl_snprintf_resize(buf, size, offset, ", Engine: ");
+ rc = hl_snprintf_resize(buf, size, offset,
+ ", Engine: ");
if (rc)
goto free_sync_objects;
rc = hl_print_resize_sync_engine(buf, size, offset,
@@ -422,6 +436,245 @@ static int hl_state_dump_print_syncs(struct hl_device *hdev,
return rc;
}
+/**
+ * hl_state_dump_alloc_read_sm_block_monitors - read monitors for a specific
+ * block
+ * @hdev: pointer to the device
+ * @index: sync manager block index starting with E_N
+ *
+ * Returns an array of monitor data of size SP_MONITORS_AMOUNT or NULL
+ * on error
+ */
+static struct hl_mon_state_dump *
+hl_state_dump_alloc_read_sm_block_monitors(struct hl_device *hdev, u32 index)
+{
+ struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+ struct hl_mon_state_dump *monitors;
+ s64 base_addr; /* Base addr can be negative */
+ int i;
+
+ monitors = vmalloc(sds->props[SP_MONITORS_AMOUNT] *
+ sizeof(struct hl_mon_state_dump));
+ if (!monitors)
+ return NULL;
+
+ base_addr = sds->props[SP_NEXT_SYNC_OBJ_ADDR] * index;
+
+ for (i = 0; i < sds->props[SP_MONITORS_AMOUNT]; ++i) {
+ monitors[i].id = i;
+ monitors[i].wr_addr_low =
+ RREG32(base_addr + sds->props[SP_MON_OBJ_WR_ADDR_LOW] +
+ i * sizeof(u32));
+
+ monitors[i].wr_addr_high =
+ RREG32(base_addr + sds->props[SP_MON_OBJ_WR_ADDR_HIGH] +
+ i * sizeof(u32));
+
+ monitors[i].wr_data =
+ RREG32(base_addr + sds->props[SP_MON_OBJ_WR_DATA] +
+ i * sizeof(u32));
+
+ monitors[i].arm_data =
+ RREG32(base_addr + sds->props[SP_MON_OBJ_ARM_DATA] +
+ i * sizeof(u32));
+
+ monitors[i].status =
+ RREG32(base_addr + sds->props[SP_MON_OBJ_STATUS] +
+ i * sizeof(u32));
+ }
+
+ return monitors;
+}
+
+/**
+ * hl_state_dump_print_monitors_single_block - print active monitors
+ * @monitors: monitors array created with
+ * hl_state_dump_alloc_read_sm_block_monitors
+ */
+static void hl_state_dump_free_monitors(struct hl_mon_state_dump *monitors)
+{
+ vfree(monitors);
+}
+
+/**
+ * hl_state_dump_print_monitors_single_block - print active monitors on a
+ * single block
+ * @hdev: pointer to the device
+ * @index: sync manager block index starting with E_N
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ *
+ * Returns 0 on success or error code on failure
+ */
+static int hl_state_dump_print_monitors_single_block(struct hl_device *hdev,
+ u32 index,
+ char **buf, size_t *size,
+ size_t *offset)
+{
+ struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+ struct hl_mon_state_dump *monitors = NULL;
+ int rc = 0, i;
+
+ if (sds->sync_namager_names) {
+ rc = hl_snprintf_resize(
+ buf, size, offset, "%s\n",
+ sds->sync_namager_names[index]);
+ if (rc)
+ goto out;
+ }
+
+ monitors = hl_state_dump_alloc_read_sm_block_monitors(hdev, index);
+ if (!monitors) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ for (i = 0; i < sds->props[SP_MONITORS_AMOUNT]; ++i) {
+ if (!(sds->funcs.monitor_valid(&monitors[i])))
+ continue;
+
+ /* Monitor is valid, dump it */
+ rc = sds->funcs.print_single_monitor(buf, size, offset, hdev,
+ &monitors[i]);
+ if (rc)
+ goto free_monitors;
+
+ hl_snprintf_resize(buf, size, offset, "\n");
+ }
+
+free_monitors:
+ hl_state_dump_free_monitors(monitors);
+out:
+ return rc;
+}
+
+/**
+ * hl_state_dump_print_monitors - print active monitors
+ * @hdev: pointer to the device
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ *
+ * Returns 0 on success or error code on failure
+ */
+static int hl_state_dump_print_monitors(struct hl_device *hdev,
+ char **buf, size_t *size,
+ size_t *offset)
+{
+ struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+ u32 index;
+ int rc = 0;
+
+ rc = hl_snprintf_resize(buf, size, offset,
+ "Valid (armed) monitor objects:\n");
+ if (rc)
+ goto out;
+
+ if (sds->sync_namager_names) {
+ for (index = 0; sds->sync_namager_names[index]; ++index) {
+ rc = hl_state_dump_print_monitors_single_block(
+ hdev, index, buf, size, offset);
+ if (rc)
+ goto out;
+ }
+ } else {
+ for (index = 0; index < sds->props[SP_NUM_CORES]; ++index) {
+ rc = hl_state_dump_print_monitors_single_block(
+ hdev, index, buf, size, offset);
+ if (rc)
+ goto out;
+ }
+ }
+
+out:
+ return rc;
+}
+
+/**
+ * hl_state_dump_print_engine_fences - print active fences for a specific
+ * engine
+ * @hdev: pointer to the device
+ * @engine_type: engine type to use
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ */
+static int
+hl_state_dump_print_engine_fences(struct hl_device *hdev,
+ enum hl_sync_engine_type engine_type,
+ char **buf, size_t *size, size_t *offset)
+{
+ struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+ int rc = 0, i, n_fences;
+ u64 base_addr, next_fence;
+
+ switch (engine_type) {
+ case ENGINE_TPC:
+ n_fences = sds->props[SP_NUM_OF_TPC_ENGINES];
+ base_addr = sds->props[SP_TPC0_CMDQ];
+ next_fence = sds->props[SP_NEXT_TPC];
+ break;
+ case ENGINE_MME:
+ n_fences = sds->props[SP_NUM_OF_MME_ENGINES];
+ base_addr = sds->props[SP_MME_CMDQ];
+ next_fence = sds->props[SP_NEXT_MME];
+ break;
+ case ENGINE_DMA:
+ n_fences = sds->props[SP_NUM_OF_DMA_ENGINES];
+ base_addr = sds->props[SP_DMA_CMDQ];
+ next_fence = sds->props[SP_DMA_QUEUES_OFFSET];
+ break;
+ default:
+ return -EINVAL;
+ }
+ for (i = 0; i < n_fences; ++i) {
+ rc = sds->funcs.print_fences_single_engine(
+ hdev,
+ base_addr + next_fence * i +
+ sds->props[SP_FENCE0_CNT_OFFSET],
+ base_addr + next_fence * i +
+ sds->props[SP_CP_STS_OFFSET],
+ engine_type, i, buf, size, offset);
+ if (rc)
+ goto out;
+ }
+out:
+ return rc;
+}
+
+/**
+ * hl_state_dump_print_fences - print active fences
+ * @hdev: pointer to the device
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ */
+static int hl_state_dump_print_fences(struct hl_device *hdev, char **buf,
+ size_t *size, size_t *offset)
+{
+ int rc = 0;
+
+ rc = hl_snprintf_resize(buf, size, offset, "Valid (armed) fences:\n");
+ if (rc)
+ goto out;
+
+ rc = hl_state_dump_print_engine_fences(hdev, ENGINE_TPC, buf, size, offset);
+ if (rc)
+ goto out;
+
+ rc = hl_state_dump_print_engine_fences(hdev, ENGINE_MME, buf, size, offset);
+ if (rc)
+ goto out;
+
+ rc = hl_state_dump_print_engine_fences(hdev, ENGINE_DMA, buf, size, offset);
+ if (rc)
+ goto out;
+
+out:
+ return rc;
+}
+
/**
* hl_state_dump() - dump system state
* @hdev: pointer to device structure
@@ -442,6 +695,18 @@ int hl_state_dump(struct hl_device *hdev)
hl_snprintf_resize(&buf, &size, &offset, "\n");
+ rc = hl_state_dump_print_monitors(hdev, &buf, &size, &offset);
+ if (rc)
+ goto err;
+
+ hl_snprintf_resize(&buf, &size, &offset, "\n");
+
+ rc = hl_state_dump_print_fences(hdev, &buf, &size, &offset);
+ if (rc)
+ goto err;
+
+ hl_snprintf_resize(&buf, &size, &offset, "\n");
+
hl_debugfs_set_state_dump(hdev, buf, size);
return 0;
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 7f90f637d7f4..29ada339b66a 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -8986,9 +8986,36 @@ static int gaudi_gen_sync_to_engine_map(struct hl_device *hdev,
return 0;
}
+static int gaudi_monitor_valid(struct hl_mon_state_dump *mon)
+{
+ /* Not implemented */
+ return 0;
+}
+
+static int gaudi_print_single_monitor(char **buf, size_t *size, size_t *offset,
+ struct hl_device *hdev,
+ struct hl_mon_state_dump *mon)
+{
+ /* Not implemented */
+ return 0;
+}
+
+
+static int gaudi_print_fences_single_engine(
+ struct hl_device *hdev, u64 base_offset, u64 status_base_offset,
+ enum hl_sync_engine_type engine_type, u32 engine_id, char **buf,
+ size_t *size, size_t *offset)
+{
+ /* Not implemented */
+ return 0;
+}
+
static struct hl_state_dump_specs_funcs gaudi_state_dump_funcs = {
+ .monitor_valid = gaudi_monitor_valid,
+ .print_single_monitor = gaudi_print_single_monitor,
.gen_sync_to_engine_map = gaudi_gen_sync_to_engine_map,
+ .print_fences_single_engine = gaudi_print_fences_single_engine,
};
static void gaudi_state_dump_init(struct hl_device *hdev)
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 2c3d642d31ab..4144a8445eef 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -5533,9 +5533,36 @@ static int goya_gen_sync_to_engine_map(struct hl_device *hdev,
return 0;
}
+static int goya_monitor_valid(struct hl_mon_state_dump *mon)
+{
+ /* Not implemented */
+ return 0;
+}
+
+static int goya_print_single_monitor(char **buf, size_t *size, size_t *offset,
+ struct hl_device *hdev,
+ struct hl_mon_state_dump *mon)
+{
+ /* Not implemented */
+ return 0;
+}
+
+
+static int goya_print_fences_single_engine(
+ struct hl_device *hdev, u64 base_offset, u64 status_base_offset,
+ enum hl_sync_engine_type engine_type, u32 engine_id, char **buf,
+ size_t *size, size_t *offset)
+{
+ /* Not implemented */
+ return 0;
+}
+
static struct hl_state_dump_specs_funcs goya_state_dump_funcs = {
+ .monitor_valid = goya_monitor_valid,
+ .print_single_monitor = goya_print_single_monitor,
.gen_sync_to_engine_map = goya_gen_sync_to_engine_map,
+ .print_fences_single_engine = goya_print_fences_single_engine,
};
static void goya_state_dump_init(struct hl_device *hdev)
--
2.25.1
^ permalink raw reply related [flat|nested] 4+ messages in thread* [PATCH 4/4] habanalabs/gaudi: implement state dump
2021-07-04 11:50 [PATCH 1/4] habanalabs: use get_task_pid() to take PID Oded Gabbay
2021-07-04 11:51 ` [PATCH 2/4] habanalabs: expose state dump Oded Gabbay
2021-07-04 11:51 ` [PATCH 3/4] habanalabs: state dump monitors and fences infrastructure Oded Gabbay
@ 2021-07-04 11:51 ` Oded Gabbay
2 siblings, 0 replies; 4+ messages in thread
From: Oded Gabbay @ 2021-07-04 11:51 UTC (permalink / raw)
To: linux-kernel; +Cc: Yuri Nudelman
From: Yuri Nudelman <ynudelman@habana.ai>
At the first stage, only gaudi core dump shall be implemented, not
including the status registers.
Signed-off-by: Yuri Nudelman <ynudelman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
drivers/misc/habanalabs/gaudi/gaudi.c | 298 +++++++++++++++++-
drivers/misc/habanalabs/gaudi/gaudiP.h | 12 +
.../include/gaudi/asic_reg/gaudi_regs.h | 3 +
.../habanalabs/include/gaudi/gaudi_masks.h | 17 +
4 files changed, 319 insertions(+), 11 deletions(-)
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 29ada339b66a..7dd36d1cb39e 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -106,6 +106,8 @@
#define GAUDI_PLL_MAX 10
+#define BIN_REG_STRING_SIZE sizeof("0b10101010101010101010101010101010")
+
static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = {
"gaudi cq 0_0", "gaudi cq 0_1", "gaudi cq 0_2", "gaudi cq 0_3",
"gaudi cq 1_0", "gaudi cq 1_1", "gaudi cq 1_2", "gaudi cq 1_3",
@@ -348,7 +350,90 @@ static enum hl_queue_type gaudi_queue_type[GAUDI_QUEUE_ID_SIZE] = {
QUEUE_TYPE_INT, /* GAUDI_QUEUE_ID_NIC_9_3 */
};
-static s64 gaudi_state_dump_specs_props[SP_MAX] = {0};
+static struct hl_hw_obj_name_entry gaudi_so_id_to_str[] = {
+ { .id = 0, .name = "SYNC_OBJ_DMA_DOWN_FEEDBACK" },
+ { .id = 1, .name = "SYNC_OBJ_DMA_UP_FEEDBACK" },
+ { .id = 2, .name = "SYNC_OBJ_DMA_STATIC_DRAM_SRAM_FEEDBACK" },
+ { .id = 3, .name = "SYNC_OBJ_DMA_SRAM_DRAM_FEEDBACK" },
+ { .id = 4, .name = "SYNC_OBJ_FIRST_COMPUTE_FINISH" },
+ { .id = 5, .name = "SYNC_OBJ_HOST_DRAM_DONE" },
+ { .id = 6, .name = "SYNC_OBJ_DBG_CTR_DEPRECATED" },
+ { .id = 7, .name = "SYNC_OBJ_DMA_ACTIVATIONS_DRAM_SRAM_FEEDBACK" },
+ { .id = 8, .name = "SYNC_OBJ_ENGINE_SEM_MME_0" },
+ { .id = 9, .name = "SYNC_OBJ_ENGINE_SEM_MME_1" },
+ { .id = 10, .name = "SYNC_OBJ_ENGINE_SEM_TPC_0" },
+ { .id = 11, .name = "SYNC_OBJ_ENGINE_SEM_TPC_1" },
+ { .id = 12, .name = "SYNC_OBJ_ENGINE_SEM_TPC_2" },
+ { .id = 13, .name = "SYNC_OBJ_ENGINE_SEM_TPC_3" },
+ { .id = 14, .name = "SYNC_OBJ_ENGINE_SEM_TPC_4" },
+ { .id = 15, .name = "SYNC_OBJ_ENGINE_SEM_TPC_5" },
+ { .id = 16, .name = "SYNC_OBJ_ENGINE_SEM_TPC_6" },
+ { .id = 17, .name = "SYNC_OBJ_ENGINE_SEM_TPC_7" },
+ { .id = 18, .name = "SYNC_OBJ_ENGINE_SEM_DMA_1" },
+ { .id = 19, .name = "SYNC_OBJ_ENGINE_SEM_DMA_2" },
+ { .id = 20, .name = "SYNC_OBJ_ENGINE_SEM_DMA_3" },
+ { .id = 21, .name = "SYNC_OBJ_ENGINE_SEM_DMA_4" },
+ { .id = 22, .name = "SYNC_OBJ_ENGINE_SEM_DMA_5" },
+ { .id = 23, .name = "SYNC_OBJ_ENGINE_SEM_DMA_6" },
+ { .id = 24, .name = "SYNC_OBJ_ENGINE_SEM_DMA_7" },
+ { .id = 25, .name = "SYNC_OBJ_DBG_CTR_0" },
+ { .id = 26, .name = "SYNC_OBJ_DBG_CTR_1" },
+};
+
+static struct hl_hw_obj_name_entry gaudi_monitor_id_to_str[] = {
+ { .id = 200, .name = "MON_OBJ_DMA_DOWN_FEEDBACK_RESET" },
+ { .id = 201, .name = "MON_OBJ_DMA_UP_FEADBACK_RESET" },
+ { .id = 203, .name = "MON_OBJ_DRAM_TO_SRAM_QUEUE_FENCE" },
+ { .id = 204, .name = "MON_OBJ_TPC_0_CLK_GATE" },
+ { .id = 205, .name = "MON_OBJ_TPC_1_CLK_GATE" },
+ { .id = 206, .name = "MON_OBJ_TPC_2_CLK_GATE" },
+ { .id = 207, .name = "MON_OBJ_TPC_3_CLK_GATE" },
+ { .id = 208, .name = "MON_OBJ_TPC_4_CLK_GATE" },
+ { .id = 209, .name = "MON_OBJ_TPC_5_CLK_GATE" },
+ { .id = 210, .name = "MON_OBJ_TPC_6_CLK_GATE" },
+ { .id = 211, .name = "MON_OBJ_TPC_7_CLK_GATE" },
+};
+
+static s64 gaudi_state_dump_specs_props[] = {
+ [SP_SYNC_OBJ_BASE_ADDR] = mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_0,
+ [SP_NEXT_SYNC_OBJ_ADDR] = NEXT_SYNC_OBJ_ADDR_INTERVAL,
+ [SP_SYNC_OBJ_AMOUNT] = NUM_OF_SOB_IN_BLOCK,
+ [SP_MON_OBJ_WR_ADDR_LOW] =
+ mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0,
+ [SP_MON_OBJ_WR_ADDR_HIGH] =
+ mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_ADDRH_0,
+ [SP_MON_OBJ_WR_DATA] = mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_DATA_0,
+ [SP_MON_OBJ_ARM_DATA] = mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_ARM_0,
+ [SP_MON_OBJ_STATUS] = mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_STATUS_0,
+ [SP_MONITORS_AMOUNT] = NUM_OF_MONITORS_IN_BLOCK,
+ [SP_TPC0_CMDQ] = mmTPC0_QM_GLBL_CFG0,
+ [SP_TPC0_CFG_SO] = mmTPC0_CFG_QM_SYNC_OBJECT_ADDR,
+ [SP_NEXT_TPC] = mmTPC1_QM_GLBL_CFG0 - mmTPC0_QM_GLBL_CFG0,
+ [SP_MME_CMDQ] = mmMME0_QM_GLBL_CFG0,
+ [SP_MME_CFG_SO] = mmMME0_CTRL_ARCH_DESC_SYNC_OBJECT_ADDR_LOW_LOCAL,
+ [SP_NEXT_MME] = mmMME2_QM_GLBL_CFG0 - mmMME0_QM_GLBL_CFG0,
+ [SP_DMA_CMDQ] = mmDMA0_QM_GLBL_CFG0,
+ [SP_DMA_CFG_SO] = mmDMA0_CORE_WR_COMP_ADDR_LO,
+ [SP_DMA_QUEUES_OFFSET] = mmDMA1_QM_GLBL_CFG0 - mmDMA0_QM_GLBL_CFG0,
+ [SP_NUM_OF_MME_ENGINES] = NUM_OF_MME_ENGINES,
+ [SP_SUB_MME_ENG_NUM] = NUM_OF_MME_SUB_ENGINES,
+ [SP_NUM_OF_DMA_ENGINES] = NUM_OF_DMA_ENGINES,
+ [SP_NUM_OF_TPC_ENGINES] = NUM_OF_TPC_ENGINES,
+ [SP_ENGINE_NUM_OF_QUEUES] = NUM_OF_QUEUES,
+ [SP_ENGINE_NUM_OF_STREAMS] = NUM_OF_STREAMS,
+ [SP_ENGINE_NUM_OF_FENCES] = NUM_OF_FENCES,
+ [SP_FENCE0_CNT_OFFSET] =
+ mmDMA0_QM_CP_FENCE0_CNT_0 - mmDMA0_QM_GLBL_CFG0,
+ [SP_FENCE0_RDATA_OFFSET] =
+ mmDMA0_QM_CP_FENCE0_RDATA_0 - mmDMA0_QM_GLBL_CFG0,
+ [SP_CP_STS_OFFSET] = mmDMA0_QM_CP_STS_0 - mmDMA0_QM_GLBL_CFG0,
+ [SP_NUM_CORES] = 1,
+};
+
+static const char * const gaudi_sync_manager_names[] = {
+ "SYNC_MGR_E_N", "SYNC_MGR_W_N", "SYNC_MGR_E_S", "SYNC_MGR_W_S",
+ NULL
+};
struct ecc_info_extract_params {
u64 block_address;
@@ -8979,25 +9064,141 @@ static int gaudi_map_pll_idx_to_fw_idx(u32 pll_idx)
}
}
+static int gaudi_add_sync_to_engine_map_entry(
+ struct hl_sync_to_engine_map *map, u32 reg_value,
+ enum hl_sync_engine_type engine_type, u32 engine_id)
+{
+ struct hl_sync_to_engine_map_entry *entry;
+
+ /* Reg value represents a partial address of sync object,
+ * it is used as unique identifier. For this we need to
+ * clear the cutoff cfg base bits from the value.
+ */
+ if (reg_value == 0 || reg_value == 0xffffffff)
+ return 0;
+ reg_value -= (u32)CFG_BASE;
+
+ /* create a new hash entry */
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ return -ENOMEM;
+ entry->engine_type = engine_type;
+ entry->engine_id = engine_id;
+ entry->sync_id = reg_value;
+ hash_add(map->tb, &entry->node, reg_value);
+
+ return 0;
+}
+
static int gaudi_gen_sync_to_engine_map(struct hl_device *hdev,
struct hl_sync_to_engine_map *map)
{
- /* Not implemented */
+ struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+ struct gaudi_device *gaudi = hdev->asic_specific;
+ int i, j, rc;
+ u32 reg_value;
+
+ /* Iterate over TPC engines */
+ for (i = 0; i < sds->props[SP_NUM_OF_TPC_ENGINES]; ++i) {
+ /* TPC registered must be accessed with clock gating disabled */
+ mutex_lock(&gaudi->clk_gate_mutex);
+ hdev->asic_funcs->disable_clock_gating(hdev);
+
+ reg_value = RREG32(sds->props[SP_TPC0_CFG_SO] +
+ sds->props[SP_NEXT_TPC] * i);
+
+ /* We can reenable clock_gating */
+ hdev->asic_funcs->set_clock_gating(hdev);
+ mutex_unlock(&gaudi->clk_gate_mutex);
+
+ rc = gaudi_add_sync_to_engine_map_entry(map, reg_value,
+ ENGINE_TPC, i);
+ if (rc)
+ goto free_sync_to_engine_map;
+ }
+
+ /* Iterate over MME engines */
+ for (i = 0; i < sds->props[SP_NUM_OF_MME_ENGINES]; ++i) {
+ for (j = 0; j < sds->props[SP_SUB_MME_ENG_NUM]; ++j) {
+ /* MME registered must be accessed with clock gating
+ * disabled
+ */
+ mutex_lock(&gaudi->clk_gate_mutex);
+ hdev->asic_funcs->disable_clock_gating(hdev);
+
+ reg_value = RREG32(sds->props[SP_MME_CFG_SO] +
+ sds->props[SP_NEXT_MME] * i +
+ j * sizeof(u32));
+
+ /* We can reenable clock_gating */
+ hdev->asic_funcs->set_clock_gating(hdev);
+ mutex_unlock(&gaudi->clk_gate_mutex);
+
+ rc = gaudi_add_sync_to_engine_map_entry(
+ map, reg_value, ENGINE_MME,
+ i * sds->props[SP_SUB_MME_ENG_NUM] + j);
+ if (rc)
+ goto free_sync_to_engine_map;
+ }
+ }
+
+ /* Iterate over DMA engines */
+ for (i = 0; i < sds->props[SP_NUM_OF_DMA_ENGINES]; ++i) {
+ reg_value = RREG32(sds->props[SP_DMA_CFG_SO] +
+ sds->props[SP_DMA_QUEUES_OFFSET] * i);
+ rc = gaudi_add_sync_to_engine_map_entry(map, reg_value,
+ ENGINE_DMA, i);
+ if (rc)
+ goto free_sync_to_engine_map;
+ }
+
return 0;
+
+free_sync_to_engine_map:
+ hl_state_dump_free_sync_to_engine_map(map);
+
+ return rc;
}
static int gaudi_monitor_valid(struct hl_mon_state_dump *mon)
{
- /* Not implemented */
- return 0;
+ return FIELD_GET(
+ SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_STATUS_0_VALID_MASK,
+ mon->status);
}
static int gaudi_print_single_monitor(char **buf, size_t *size, size_t *offset,
struct hl_device *hdev,
struct hl_mon_state_dump *mon)
{
- /* Not implemented */
- return 0;
+ const char *name;
+ char scratch_buf1[BIN_REG_STRING_SIZE],
+ scratch_buf2[BIN_REG_STRING_SIZE];
+
+ name = hl_state_dump_get_monitor_name(hdev, mon);
+ if (!name)
+ name = "";
+
+ return hl_snprintf_resize(
+ buf, size, offset,
+ "Mon id: %u%s, wait for group id: %u mask %s to reach val: %u and write %u to address 0x%llx. Pending: %s",
+ mon->id, name,
+ FIELD_GET(SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SID_MASK,
+ mon->arm_data),
+ hl_format_as_binary(
+ scratch_buf1, sizeof(scratch_buf1),
+ FIELD_GET(
+ SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_MASK_MASK,
+ mon->arm_data)),
+ FIELD_GET(SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SOD_MASK,
+ mon->arm_data),
+ mon->wr_data,
+ (((u64)mon->wr_addr_high) << 32) | mon->wr_addr_low,
+ hl_format_as_binary(
+ scratch_buf2, sizeof(scratch_buf2),
+ FIELD_GET(
+ SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_STATUS_0_PENDING_MASK,
+ mon->status)));
}
@@ -9006,8 +9207,68 @@ static int gaudi_print_fences_single_engine(
enum hl_sync_engine_type engine_type, u32 engine_id, char **buf,
size_t *size, size_t *offset)
{
- /* Not implemented */
- return 0;
+ struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+ int rc = -ENOMEM, i;
+ u32 *statuses, *fences;
+
+ statuses = kcalloc(sds->props[SP_ENGINE_NUM_OF_QUEUES],
+ sizeof(*statuses), GFP_KERNEL);
+ if (!statuses)
+ goto out;
+
+ fences = kcalloc(sds->props[SP_ENGINE_NUM_OF_FENCES] *
+ sds->props[SP_ENGINE_NUM_OF_QUEUES],
+ sizeof(*fences), GFP_KERNEL);
+ if (!fences)
+ goto free_status;
+
+ for (i = 0; i < sds->props[SP_ENGINE_NUM_OF_FENCES]; ++i)
+ statuses[i] = RREG32(status_base_offset + i * sizeof(u32));
+
+ for (i = 0; i < sds->props[SP_ENGINE_NUM_OF_FENCES] *
+ sds->props[SP_ENGINE_NUM_OF_QUEUES]; ++i)
+ fences[i] = RREG32(base_offset + i * sizeof(u32));
+
+ /* The actual print */
+ for (i = 0; i < sds->props[SP_ENGINE_NUM_OF_QUEUES]; ++i) {
+ u32 fence_id;
+ u64 fence_cnt, fence_rdata;
+ const char *engine_name;
+
+ if (!FIELD_GET(TPC0_QM_CP_STS_0_FENCE_IN_PROGRESS_MASK,
+ statuses[i]))
+ continue;
+
+ fence_id =
+ FIELD_GET(TPC0_QM_CP_STS_0_FENCE_ID_MASK, statuses[i]);
+ fence_cnt = base_offset + CFG_BASE +
+ sizeof(u32) *
+ (i + fence_id * sds->props[SP_ENGINE_NUM_OF_QUEUES]);
+ fence_rdata = fence_cnt - sds->props[SP_FENCE0_CNT_OFFSET] +
+ sds->props[SP_FENCE0_RDATA_OFFSET];
+ engine_name = hl_sync_engine_to_string(engine_type);
+
+ rc = hl_snprintf_resize(
+ buf, size, offset,
+ "%s%u, stream %u: fence id %u cnt = 0x%llx (%s%u_QM.CP_FENCE%u_CNT_%u) rdata = 0x%llx (%s%u_QM.CP_FENCE%u_RDATA_%u) value = %u, cp_status = %u\n",
+ engine_name, engine_id,
+ i, fence_id,
+ fence_cnt, engine_name, engine_id, fence_id, i,
+ fence_rdata, engine_name, engine_id, fence_id, i,
+ fences[fence_id],
+ statuses[i]);
+ if (rc)
+ goto free_fences;
+ }
+
+ rc = 0;
+
+free_fences:
+ kfree(fences);
+free_status:
+ kfree(statuses);
+out:
+ return rc;
}
@@ -9020,9 +9281,24 @@ static struct hl_state_dump_specs_funcs gaudi_state_dump_funcs = {
static void gaudi_state_dump_init(struct hl_device *hdev)
{
- /* Not implemented */
- hdev->state_dump_specs.props = gaudi_state_dump_specs_props;
- hdev->state_dump_specs.funcs = gaudi_state_dump_funcs;
+ struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(gaudi_so_id_to_str); ++i)
+ hash_add(sds->so_id_to_str_tb,
+ &gaudi_so_id_to_str[i].node,
+ gaudi_so_id_to_str[i].id);
+
+ for (i = 0; i < ARRAY_SIZE(gaudi_monitor_id_to_str); ++i)
+ hash_add(sds->monitor_id_to_str_tb,
+ &gaudi_monitor_id_to_str[i].node,
+ gaudi_monitor_id_to_str[i].id);
+
+ sds->props = gaudi_state_dump_specs_props;
+
+ sds->sync_namager_names = gaudi_sync_manager_names;
+
+ sds->funcs = gaudi_state_dump_funcs;
}
static const struct hl_asic_funcs gaudi_funcs = {
diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h
index 957bf3720f70..838e98b0d43d 100644
--- a/drivers/misc/habanalabs/gaudi/gaudiP.h
+++ b/drivers/misc/habanalabs/gaudi/gaudiP.h
@@ -200,6 +200,18 @@
#define HW_CAP_TPC_MASK GENMASK(31, 24)
#define HW_CAP_TPC_SHIFT 24
+#define NEXT_SYNC_OBJ_ADDR_INTERVAL \
+ (mmSYNC_MNGR_W_N_SYNC_MNGR_OBJS_SOB_OBJ_0 - \
+ mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_0)
+#define NUM_OF_MME_ENGINES 2
+#define NUM_OF_MME_SUB_ENGINES 2
+#define NUM_OF_TPC_ENGINES 8
+#define NUM_OF_DMA_ENGINES 8
+#define NUM_OF_QUEUES 5
+#define NUM_OF_STREAMS 4
+#define NUM_OF_FENCES 4
+
+
#define GAUDI_CPU_PCI_MSB_ADDR(addr) (((addr) & GENMASK_ULL(49, 39)) >> 39)
#define GAUDI_PCI_TO_CPU_ADDR(addr) \
do { \
diff --git a/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h b/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h
index 5bb54b34a8ae..ffdfbd9b3220 100644
--- a/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h
+++ b/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h
@@ -126,6 +126,9 @@
#define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_1 0x4F2004
#define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_2047 0x4F3FFC
#define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0 0x4F4000
+#define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_ADDRH_0 0x4F4800
+#define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_DATA_0 0x4F5000
+#define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_ARM_0 0x4F5800
#define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_STATUS_0 0x4F6000
#define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_STATUS_511 0x4F67FC
diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
index 9aea7e996654..acc85d3ed98b 100644
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
@@ -449,4 +449,21 @@ enum axi_id {
#define PCIE_AUX_FLR_CTRL_HW_CTRL_MASK 0x1
#define PCIE_AUX_FLR_CTRL_INT_MASK_MASK 0x2
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_STATUS_0_VALID_SHIFT 0
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_STATUS_0_VALID_MASK 0x1
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_STATUS_0_PENDING_SHIFT 1
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_STATUS_0_PENDING_MASK 0x1FE
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SID_SHIFT 0
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SID_MASK 0xFF
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_MASK_SHIFT 8
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_MASK_MASK 0xFF00
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SOP_SHIFT 16
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SOP_MASK 0x10000
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SOD_SHIFT 17
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SOD_MASK 0xFFFE0000
+#define TPC0_QM_CP_STS_0_FENCE_ID_SHIFT 20
+#define TPC0_QM_CP_STS_0_FENCE_ID_MASK 0x300000
+#define TPC0_QM_CP_STS_0_FENCE_IN_PROGRESS_SHIFT 22
+#define TPC0_QM_CP_STS_0_FENCE_IN_PROGRESS_MASK 0x400000
+
#endif /* GAUDI_MASKS_H_ */
--
2.25.1
^ permalink raw reply related [flat|nested] 4+ messages in thread