linux_dsm_epyc7002/drivers/misc/habanalabs/habanalabs_ioctl.c

375 lines
9.3 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright 2016-2019 HabanaLabs, Ltd.
* All Rights Reserved.
*/
#include <uapi/misc/habanalabs.h>
#include "habanalabs.h"
#include <linux/fs.h>
#include <linux/uaccess.h>
#include <linux/slab.h>
habanalabs: add new IOCTL for debug, tracing and profiling Habanalabs ASICs use the ARM coresight infrastructure to support debug, tracing and profiling of neural networks topologies. Because the coresight is configured using register writes and reads, and some of the registers hold sensitive information (e.g. the address in the device's DRAM where the trace data is written to), the user must go through the kernel driver to configure this mechanism. This patch implements the common code of the IOCTL and calls the ASIC-specific function for the actual H/W configuration. The IOCTL supports configuration of seven coresight components: ETR, ETF, STM, FUNNEL, BMON, SPMU and TIMESTAMP The user specifies which component he wishes to configure and provides a pointer to a structure (located in its process space) that contains the relevant configuration. The common code copies the relevant data from the user-space to kernel space and then calls the ASIC-specific function to do the H/W configuration. After the configuration is done, which is usually composed of several IOCTL calls depending on what the user wanted to trace, the user can start executing the topology. The trace data will be written to the user's area in the device's DRAM. After the tracing operation is complete, and user will call the IOCTL again to disable the tracing operation. The user also need to read values from registers for some of the components (e.g. the size of the trace data in the device's DRAM). In that case, the user will provide a pointer to an "output" structure in user-space, which the IOCTL code will fill according the to selected component. Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2019-04-02 02:31:22 +07:00
static u32 hl_debug_struct_size[HL_DEBUG_OP_TIMESTAMP + 1] = {
[HL_DEBUG_OP_ETR] = sizeof(struct hl_debug_params_etr),
[HL_DEBUG_OP_ETF] = sizeof(struct hl_debug_params_etf),
[HL_DEBUG_OP_STM] = sizeof(struct hl_debug_params_stm),
[HL_DEBUG_OP_FUNNEL] = 0,
[HL_DEBUG_OP_BMON] = sizeof(struct hl_debug_params_bmon),
[HL_DEBUG_OP_SPMU] = sizeof(struct hl_debug_params_spmu),
[HL_DEBUG_OP_TIMESTAMP] = 0
};
static int device_status_info(struct hl_device *hdev, struct hl_info_args *args)
{
struct hl_info_device_status dev_stat = {0};
u32 size = args->return_size;
void __user *out = (void __user *) (uintptr_t) args->return_pointer;
if ((!size) || (!out))
return -EINVAL;
dev_stat.status = hl_device_status(hdev);
return copy_to_user(out, &dev_stat,
min((size_t)size, sizeof(dev_stat))) ? -EFAULT : 0;
}
static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args)
{
struct hl_info_hw_ip_info hw_ip = {0};
u32 size = args->return_size;
void __user *out = (void __user *) (uintptr_t) args->return_pointer;
struct asic_fixed_properties *prop = &hdev->asic_prop;
u64 sram_kmd_size, dram_kmd_size;
if ((!size) || (!out))
return -EINVAL;
sram_kmd_size = (prop->sram_user_base_address -
prop->sram_base_address);
dram_kmd_size = (prop->dram_user_base_address -
prop->dram_base_address);
hw_ip.device_id = hdev->asic_funcs->get_pci_id(hdev);
hw_ip.sram_base_address = prop->sram_user_base_address;
hw_ip.dram_base_address = prop->dram_user_base_address;
hw_ip.tpc_enabled_mask = prop->tpc_enabled_mask;
hw_ip.sram_size = prop->sram_size - sram_kmd_size;
hw_ip.dram_size = prop->dram_size - dram_kmd_size;
if (hw_ip.dram_size > 0)
hw_ip.dram_enabled = 1;
hw_ip.num_of_events = prop->num_of_events;
memcpy(hw_ip.armcp_version,
prop->armcp_info.armcp_version, VERSION_MAX_LEN);
hw_ip.armcp_cpld_version = __le32_to_cpu(prop->armcp_info.cpld_version);
hw_ip.psoc_pci_pll_nr = prop->psoc_pci_pll_nr;
hw_ip.psoc_pci_pll_nf = prop->psoc_pci_pll_nf;
hw_ip.psoc_pci_pll_od = prop->psoc_pci_pll_od;
hw_ip.psoc_pci_pll_div_factor = prop->psoc_pci_pll_div_factor;
return copy_to_user(out, &hw_ip,
min((size_t)size, sizeof(hw_ip))) ? -EFAULT : 0;
}
static int hw_events_info(struct hl_device *hdev, struct hl_info_args *args)
{
u32 size, max_size = args->return_size;
void __user *out = (void __user *) (uintptr_t) args->return_pointer;
void *arr;
if ((!max_size) || (!out))
return -EINVAL;
arr = hdev->asic_funcs->get_events_stat(hdev, &size);
return copy_to_user(out, arr, min(max_size, size)) ? -EFAULT : 0;
}
static int dram_usage_info(struct hl_device *hdev, struct hl_info_args *args)
{
struct hl_info_dram_usage dram_usage = {0};
u32 max_size = args->return_size;
void __user *out = (void __user *) (uintptr_t) args->return_pointer;
struct asic_fixed_properties *prop = &hdev->asic_prop;
u64 dram_kmd_size;
if ((!max_size) || (!out))
return -EINVAL;
dram_kmd_size = (prop->dram_user_base_address -
prop->dram_base_address);
dram_usage.dram_free_mem = (prop->dram_size - dram_kmd_size) -
atomic64_read(&hdev->dram_used_mem);
dram_usage.ctx_dram_mem = atomic64_read(&hdev->user_ctx->dram_phys_mem);
return copy_to_user(out, &dram_usage,
min((size_t) max_size, sizeof(dram_usage))) ? -EFAULT : 0;
}
static int hw_idle(struct hl_device *hdev, struct hl_info_args *args)
{
struct hl_info_hw_idle hw_idle = {0};
u32 max_size = args->return_size;
void __user *out = (void __user *) (uintptr_t) args->return_pointer;
if ((!max_size) || (!out))
return -EINVAL;
hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev,
&hw_idle.busy_engines_mask, NULL);
return copy_to_user(out, &hw_idle,
min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0;
}
habanalabs: add new IOCTL for debug, tracing and profiling Habanalabs ASICs use the ARM coresight infrastructure to support debug, tracing and profiling of neural networks topologies. Because the coresight is configured using register writes and reads, and some of the registers hold sensitive information (e.g. the address in the device's DRAM where the trace data is written to), the user must go through the kernel driver to configure this mechanism. This patch implements the common code of the IOCTL and calls the ASIC-specific function for the actual H/W configuration. The IOCTL supports configuration of seven coresight components: ETR, ETF, STM, FUNNEL, BMON, SPMU and TIMESTAMP The user specifies which component he wishes to configure and provides a pointer to a structure (located in its process space) that contains the relevant configuration. The common code copies the relevant data from the user-space to kernel space and then calls the ASIC-specific function to do the H/W configuration. After the configuration is done, which is usually composed of several IOCTL calls depending on what the user wanted to trace, the user can start executing the topology. The trace data will be written to the user's area in the device's DRAM. After the tracing operation is complete, and user will call the IOCTL again to disable the tracing operation. The user also need to read values from registers for some of the components (e.g. the size of the trace data in the device's DRAM). In that case, the user will provide a pointer to an "output" structure in user-space, which the IOCTL code will fill according the to selected component. Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2019-04-02 02:31:22 +07:00
static int debug_coresight(struct hl_device *hdev, struct hl_debug_args *args)
{
struct hl_debug_params *params;
void *input = NULL, *output = NULL;
int rc;
params = kzalloc(sizeof(*params), GFP_KERNEL);
if (!params)
return -ENOMEM;
params->reg_idx = args->reg_idx;
params->enable = args->enable;
params->op = args->op;
if (args->input_ptr && args->input_size) {
input = memdup_user(u64_to_user_ptr(args->input_ptr),
habanalabs: add new IOCTL for debug, tracing and profiling Habanalabs ASICs use the ARM coresight infrastructure to support debug, tracing and profiling of neural networks topologies. Because the coresight is configured using register writes and reads, and some of the registers hold sensitive information (e.g. the address in the device's DRAM where the trace data is written to), the user must go through the kernel driver to configure this mechanism. This patch implements the common code of the IOCTL and calls the ASIC-specific function for the actual H/W configuration. The IOCTL supports configuration of seven coresight components: ETR, ETF, STM, FUNNEL, BMON, SPMU and TIMESTAMP The user specifies which component he wishes to configure and provides a pointer to a structure (located in its process space) that contains the relevant configuration. The common code copies the relevant data from the user-space to kernel space and then calls the ASIC-specific function to do the H/W configuration. After the configuration is done, which is usually composed of several IOCTL calls depending on what the user wanted to trace, the user can start executing the topology. The trace data will be written to the user's area in the device's DRAM. After the tracing operation is complete, and user will call the IOCTL again to disable the tracing operation. The user also need to read values from registers for some of the components (e.g. the size of the trace data in the device's DRAM). In that case, the user will provide a pointer to an "output" structure in user-space, which the IOCTL code will fill according the to selected component. Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2019-04-02 02:31:22 +07:00
args->input_size);
if (IS_ERR(input)) {
rc = PTR_ERR(input);
input = NULL;
dev_err(hdev->dev,
"error %d when copying input debug data\n", rc);
goto out;
}
params->input = input;
}
if (args->output_ptr && args->output_size) {
output = kzalloc(args->output_size, GFP_KERNEL);
if (!output) {
rc = -ENOMEM;
goto out;
}
params->output = output;
params->output_size = args->output_size;
}
rc = hdev->asic_funcs->debug_coresight(hdev, params);
if (rc) {
dev_err(hdev->dev,
"debug coresight operation failed %d\n", rc);
goto out;
}
if (output) {
if (copy_to_user((void __user *) (uintptr_t) args->output_ptr,
output,
args->output_size)) {
dev_err(hdev->dev,
"copy to user failed in debug ioctl\n");
rc = -EFAULT;
goto out;
}
}
out:
kfree(params);
kfree(output);
kfree(input);
return rc;
}
static int hl_info_ioctl(struct hl_fpriv *hpriv, void *data)
{
struct hl_info_args *args = data;
struct hl_device *hdev = hpriv->hdev;
int rc;
/* We want to return device status even if it disabled or in reset */
if (args->op == HL_INFO_DEVICE_STATUS)
return device_status_info(hdev, args);
if (hl_device_disabled_or_in_reset(hdev)) {
dev_warn_ratelimited(hdev->dev,
"Device is %s. Can't execute INFO IOCTL\n",
atomic_read(&hdev->in_reset) ? "in_reset" : "disabled");
return -EBUSY;
}
switch (args->op) {
case HL_INFO_HW_IP_INFO:
rc = hw_ip_info(hdev, args);
break;
case HL_INFO_HW_EVENTS:
rc = hw_events_info(hdev, args);
break;
case HL_INFO_DRAM_USAGE:
rc = dram_usage_info(hdev, args);
break;
case HL_INFO_HW_IDLE:
rc = hw_idle(hdev, args);
break;
default:
dev_err(hdev->dev, "Invalid request %d\n", args->op);
rc = -ENOTTY;
break;
}
return rc;
}
habanalabs: add new IOCTL for debug, tracing and profiling Habanalabs ASICs use the ARM coresight infrastructure to support debug, tracing and profiling of neural networks topologies. Because the coresight is configured using register writes and reads, and some of the registers hold sensitive information (e.g. the address in the device's DRAM where the trace data is written to), the user must go through the kernel driver to configure this mechanism. This patch implements the common code of the IOCTL and calls the ASIC-specific function for the actual H/W configuration. The IOCTL supports configuration of seven coresight components: ETR, ETF, STM, FUNNEL, BMON, SPMU and TIMESTAMP The user specifies which component he wishes to configure and provides a pointer to a structure (located in its process space) that contains the relevant configuration. The common code copies the relevant data from the user-space to kernel space and then calls the ASIC-specific function to do the H/W configuration. After the configuration is done, which is usually composed of several IOCTL calls depending on what the user wanted to trace, the user can start executing the topology. The trace data will be written to the user's area in the device's DRAM. After the tracing operation is complete, and user will call the IOCTL again to disable the tracing operation. The user also need to read values from registers for some of the components (e.g. the size of the trace data in the device's DRAM). In that case, the user will provide a pointer to an "output" structure in user-space, which the IOCTL code will fill according the to selected component. Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2019-04-02 02:31:22 +07:00
static int hl_debug_ioctl(struct hl_fpriv *hpriv, void *data)
{
struct hl_debug_args *args = data;
struct hl_device *hdev = hpriv->hdev;
int rc = 0;
if (hl_device_disabled_or_in_reset(hdev)) {
dev_warn_ratelimited(hdev->dev,
"Device is %s. Can't execute DEBUG IOCTL\n",
atomic_read(&hdev->in_reset) ? "in_reset" : "disabled");
return -EBUSY;
}
switch (args->op) {
case HL_DEBUG_OP_ETR:
case HL_DEBUG_OP_ETF:
case HL_DEBUG_OP_STM:
case HL_DEBUG_OP_FUNNEL:
case HL_DEBUG_OP_BMON:
case HL_DEBUG_OP_SPMU:
case HL_DEBUG_OP_TIMESTAMP:
if (!hdev->in_debug) {
dev_err_ratelimited(hdev->dev,
"Rejecting debug configuration request because device not in debug mode\n");
return -EFAULT;
}
habanalabs: add new IOCTL for debug, tracing and profiling Habanalabs ASICs use the ARM coresight infrastructure to support debug, tracing and profiling of neural networks topologies. Because the coresight is configured using register writes and reads, and some of the registers hold sensitive information (e.g. the address in the device's DRAM where the trace data is written to), the user must go through the kernel driver to configure this mechanism. This patch implements the common code of the IOCTL and calls the ASIC-specific function for the actual H/W configuration. The IOCTL supports configuration of seven coresight components: ETR, ETF, STM, FUNNEL, BMON, SPMU and TIMESTAMP The user specifies which component he wishes to configure and provides a pointer to a structure (located in its process space) that contains the relevant configuration. The common code copies the relevant data from the user-space to kernel space and then calls the ASIC-specific function to do the H/W configuration. After the configuration is done, which is usually composed of several IOCTL calls depending on what the user wanted to trace, the user can start executing the topology. The trace data will be written to the user's area in the device's DRAM. After the tracing operation is complete, and user will call the IOCTL again to disable the tracing operation. The user also need to read values from registers for some of the components (e.g. the size of the trace data in the device's DRAM). In that case, the user will provide a pointer to an "output" structure in user-space, which the IOCTL code will fill according the to selected component. Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2019-04-02 02:31:22 +07:00
args->input_size =
min(args->input_size, hl_debug_struct_size[args->op]);
rc = debug_coresight(hdev, args);
break;
case HL_DEBUG_OP_SET_MODE:
rc = hl_device_set_debug_mode(hdev, (bool) args->enable);
break;
habanalabs: add new IOCTL for debug, tracing and profiling Habanalabs ASICs use the ARM coresight infrastructure to support debug, tracing and profiling of neural networks topologies. Because the coresight is configured using register writes and reads, and some of the registers hold sensitive information (e.g. the address in the device's DRAM where the trace data is written to), the user must go through the kernel driver to configure this mechanism. This patch implements the common code of the IOCTL and calls the ASIC-specific function for the actual H/W configuration. The IOCTL supports configuration of seven coresight components: ETR, ETF, STM, FUNNEL, BMON, SPMU and TIMESTAMP The user specifies which component he wishes to configure and provides a pointer to a structure (located in its process space) that contains the relevant configuration. The common code copies the relevant data from the user-space to kernel space and then calls the ASIC-specific function to do the H/W configuration. After the configuration is done, which is usually composed of several IOCTL calls depending on what the user wanted to trace, the user can start executing the topology. The trace data will be written to the user's area in the device's DRAM. After the tracing operation is complete, and user will call the IOCTL again to disable the tracing operation. The user also need to read values from registers for some of the components (e.g. the size of the trace data in the device's DRAM). In that case, the user will provide a pointer to an "output" structure in user-space, which the IOCTL code will fill according the to selected component. Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2019-04-02 02:31:22 +07:00
default:
dev_err(hdev->dev, "Invalid request %d\n", args->op);
rc = -ENOTTY;
break;
}
return rc;
}
#define HL_IOCTL_DEF(ioctl, _func) \
[_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func}
static const struct hl_ioctl_desc hl_ioctls[] = {
HL_IOCTL_DEF(HL_IOCTL_INFO, hl_info_ioctl),
HL_IOCTL_DEF(HL_IOCTL_CB, hl_cb_ioctl),
HL_IOCTL_DEF(HL_IOCTL_CS, hl_cs_ioctl),
HL_IOCTL_DEF(HL_IOCTL_WAIT_CS, hl_cs_wait_ioctl),
habanalabs: add new IOCTL for debug, tracing and profiling Habanalabs ASICs use the ARM coresight infrastructure to support debug, tracing and profiling of neural networks topologies. Because the coresight is configured using register writes and reads, and some of the registers hold sensitive information (e.g. the address in the device's DRAM where the trace data is written to), the user must go through the kernel driver to configure this mechanism. This patch implements the common code of the IOCTL and calls the ASIC-specific function for the actual H/W configuration. The IOCTL supports configuration of seven coresight components: ETR, ETF, STM, FUNNEL, BMON, SPMU and TIMESTAMP The user specifies which component he wishes to configure and provides a pointer to a structure (located in its process space) that contains the relevant configuration. The common code copies the relevant data from the user-space to kernel space and then calls the ASIC-specific function to do the H/W configuration. After the configuration is done, which is usually composed of several IOCTL calls depending on what the user wanted to trace, the user can start executing the topology. The trace data will be written to the user's area in the device's DRAM. After the tracing operation is complete, and user will call the IOCTL again to disable the tracing operation. The user also need to read values from registers for some of the components (e.g. the size of the trace data in the device's DRAM). In that case, the user will provide a pointer to an "output" structure in user-space, which the IOCTL code will fill according the to selected component. Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2019-04-02 02:31:22 +07:00
HL_IOCTL_DEF(HL_IOCTL_MEMORY, hl_mem_ioctl),
HL_IOCTL_DEF(HL_IOCTL_DEBUG, hl_debug_ioctl)
};
#define HL_CORE_IOCTL_COUNT ARRAY_SIZE(hl_ioctls)
long hl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
{
struct hl_fpriv *hpriv = filep->private_data;
struct hl_device *hdev = hpriv->hdev;
hl_ioctl_t *func;
const struct hl_ioctl_desc *ioctl = NULL;
unsigned int nr = _IOC_NR(cmd);
char stack_kdata[128] = {0};
char *kdata = NULL;
unsigned int usize, asize;
int retcode;
if (hdev->hard_reset_pending) {
dev_crit_ratelimited(hdev->dev,
"Device HARD reset pending! Please close FD\n");
return -ENODEV;
}
if ((nr >= HL_COMMAND_START) && (nr < HL_COMMAND_END)) {
u32 hl_size;
ioctl = &hl_ioctls[nr];
hl_size = _IOC_SIZE(ioctl->cmd);
usize = asize = _IOC_SIZE(cmd);
if (hl_size > asize)
asize = hl_size;
cmd = ioctl->cmd;
} else {
dev_err(hdev->dev, "invalid ioctl: pid=%d, nr=0x%02x\n",
task_pid_nr(current), nr);
return -ENOTTY;
}
/* Do not trust userspace, use our own definition */
func = ioctl->func;
if (unlikely(!func)) {
dev_dbg(hdev->dev, "no function\n");
retcode = -ENOTTY;
goto out_err;
}
if (cmd & (IOC_IN | IOC_OUT)) {
if (asize <= sizeof(stack_kdata)) {
kdata = stack_kdata;
} else {
kdata = kzalloc(asize, GFP_KERNEL);
if (!kdata) {
retcode = -ENOMEM;
goto out_err;
}
}
}
if (cmd & IOC_IN) {
if (copy_from_user(kdata, (void __user *)arg, usize)) {
retcode = -EFAULT;
goto out_err;
}
} else if (cmd & IOC_OUT) {
memset(kdata, 0, usize);
}
retcode = func(hpriv, kdata);
if (cmd & IOC_OUT)
if (copy_to_user((void __user *)arg, kdata, usize))
retcode = -EFAULT;
out_err:
if (retcode)
dev_dbg(hdev->dev,
"error in ioctl: pid=%d, cmd=0x%02x, nr=0x%02x\n",
task_pid_nr(current), cmd, nr);
if (kdata != stack_kdata)
kfree(kdata);
return retcode;
}