by liulongfang

[permalink] [raw]

Subject: Re: [PATCH v9 1/5] vfio/migration: Add debugfs to live migration driver

On 2023/3/21 5:33, Alex Williamson wrote:
> On Mon, 20 Mar 2023 17:23:34 +0800
> Longfang Liu <[email protected]> wrote:
>
>> There are multiple devices, software and operational steps involved
>> in the process of live migration. An error occurred on any node may
>> cause the live migration operation to fail.
>> This complex process makes it very difficult to locate and analyze
>> the cause when the function fails.
>>
>> In order to quickly locate the cause of the problem when the
>> live migration fails, I added a set of debugfs to the vfio
>> live migration driver.
>>
>> +-------------------------------------------+
>> | |
>> | |
>> | QEMU |
>> | |
>> | |
>> +---+----------------------------+----------+
>> | ^ | ^
>> | | | |
>> | | | |
>> v | v |
>> +---------+--+ +---------+--+
>> |src vfio_dev| |dst vfio_dev|
>> +--+---------+ +--+---------+
>> | ^ | ^
>> | | | |
>> v | | |
>> +-----------+----+ +-----------+----+
>> |src dev debugfs | |dst dev debugfs |
>> +----------------+ +----------------+
>>
>> The entire debugfs directory will be based on the definition of
>> the CONFIG_DEBUG_FS macro. If this macro is not enabled, the
>> interfaces in vfio.h will be empty definitions, and the creation
>> and initialization of the debugfs directory will not be executed.
>>
>> vfio
>> |
>> +---<dev_name1>
>> | +---migration
>> | +--state
>> | +--hisi_acc
>> | +--attr
>> | +--data
>> | +--debug
>> |
>> +---<dev_name2>
>> +---migration
>> +--state
>> +--hisi_acc
>> +--attr
>> +--data
>> +--debug
>>
>> debugfs will create a public root directory "vfio" file.
>> then create a dev_name() file for each live migration device.
>> First, create a unified state acquisition file of "migration"
>> in this device directory.
>> Then, create a public live migration state lookup file "state"
>> Finally, create a directory file based on the device type,
>> and then create the device's own debugging files under
>> this directory file.
>>
>> Here, HiSilicon accelerator creates three debug files:
>> attr: used to obtain the attribute parameters of the
>> current live migration device.
>> data: used to get the live migration data of the current
>> live migration device.
>> debug: Used to debug the current live migration device
>> through commands.
>>
>> The live migration function of the current device can be tested by
>> operating the debug files, and the functional status of the equipment
>> and software at each stage can be tested step by step without
>> performing the complete live migration function. And after the live
>> migration is performed, the migration device data of the live migration
>> can be obtained through the debug files.
>>
>> Signed-off-by: Longfang Liu <[email protected]>
>> ---
>> drivers/vfio/Makefile | 2 +-
>> drivers/vfio/vfio.h | 14 +++++++
>> drivers/vfio/vfio_debugfs.c | 80 +++++++++++++++++++++++++++++++++++++
>> drivers/vfio/vfio_main.c | 5 +++
>> include/linux/vfio.h | 8 ++++
>> 5 files changed, 108 insertions(+), 1 deletion(-)
>> create mode 100644 drivers/vfio/vfio_debugfs.c
>>
>> diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
>> index 70e7dcb302ef..1debcff31d30 100644
>> --- a/drivers/vfio/Makefile
>> +++ b/drivers/vfio/Makefile
>> @@ -7,7 +7,7 @@ vfio-y += vfio_main.o \
>> vfio-$(CONFIG_IOMMUFD) += iommufd.o
>> vfio-$(CONFIG_VFIO_CONTAINER) += container.o
>> vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o
>> -
>> +vfio-$(CONFIG_DEBUG_FS) += vfio_debugfs.o
>> obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
>> obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
>> obj-$(CONFIG_VFIO_PCI) += pci/
>> diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
>> index e9721d8424bc..8e5cafa6aa3a 100644
>> --- a/drivers/vfio/vfio.h
>> +++ b/drivers/vfio/vfio.h
>> @@ -258,4 +258,18 @@ static inline void vfio_device_put_kvm(struct vfio_device *device)
>> }
>> #endif
>>
>> +#ifdef CONFIG_DEBUG_FS
>> +void vfio_debugfs_create_root(void);
>> +void vfio_debugfs_remove_root(void);
>> +
>> +void vfio_device_debugfs_init(struct vfio_device *vdev);
>> +void vfio_device_debugfs_exit(struct vfio_device *vdev);
>> +#else
>> +static inline void vfio_debugfs_create_root(void) { }
>> +static inline void vfio_debugfs_remove_root(void) { }
>> +
>> +static inline void vfio_device_debugfs_init(struct vfio_device *vdev) { }
>> +static inline void vfio_device_debugfs_exit(struct vfio_device *vdev) { }
>> +#endif /* CONFIG_DEBUG_FS */
>> +
>> #endif
>> diff --git a/drivers/vfio/vfio_debugfs.c b/drivers/vfio/vfio_debugfs.c
>> new file mode 100644
>> index 000000000000..f5b6bf2a1d48
>> --- /dev/null
>> +++ b/drivers/vfio/vfio_debugfs.c
>> @@ -0,0 +1,80 @@
>> +// SPDX-License-Identifier: GPL-2.0-only
>> +/*
>> + * Copyright (c) 2023, HiSilicon Ltd.
>> + */
>> +
>> +#include <linux/device.h>
>> +#include <linux/debugfs.h>
>> +#include <linux/seq_file.h>
>> +#include <linux/vfio.h>
>> +#include "vfio.h"
>> +
>> +static struct dentry *vfio_debugfs_root;
>> +
>> +static int vfio_device_state_read(struct seq_file *seq, void *data)
>> +{
>> + struct device *vf_dev = seq->private;
>> + struct vfio_device *vdev = container_of(vf_dev, struct vfio_device, device);
>> + enum vfio_device_mig_state state;
>> + int ret;
>> +
>> + ret = vdev->mig_ops->migration_get_state(vdev, &state);
>> + if (ret)
>> + return -EINVAL;
>> +
>> + switch (state) {
>> + case VFIO_DEVICE_STATE_RUNNING:
>> + seq_printf(seq, "%s\n", "RUNNING");
>> + break;
>> + case VFIO_DEVICE_STATE_STOP_COPY:
>> + seq_printf(seq, "%s\n", "STOP_COPY");
>> + break;
>> + case VFIO_DEVICE_STATE_STOP:
>> + seq_printf(seq, "%s\n", "STOP");
>> + break;
>> + case VFIO_DEVICE_STATE_RESUMING:
>> + seq_printf(seq, "%s\n", "RESUMING");
>> + break;
>> + case VFIO_DEVICE_STATE_RUNNING_P2P:
>> + seq_printf(seq, "%s\n", "RESUMING_P2P");
>> + break;
>> + case VFIO_DEVICE_STATE_ERROR:
>> + seq_printf(seq, "%s\n", "ERROR");
>> + break;
>> + default:
>> + seq_printf(seq, "%s\n", "Invalid");
>> + }
>> +
>> + return 0;
>> +}
>> +
>> +void vfio_device_debugfs_init(struct vfio_device *vdev)
>> +{
>> + struct dentry *vfio_dev_migration = NULL;
>> + struct device *dev = &vdev->device;
>> +
>> + vdev->debug_root = debugfs_create_dir(dev_name(vdev->dev), vfio_debugfs_root);
>> + vfio_dev_migration = debugfs_create_dir("migration", vdev->debug_root);
>
> Am I understanding correctly that there seems to be a standard with
> debugfs helpers to accept and test for bad inputs such that typical
> callers don't bother to test for ERR_PTRs from cases like above?
>

It is stated in the debugfs_create_dir interface that an error will be
returned only when CONFIG_DEBUG_FS is not enabled.

>> +
>> + debugfs_create_devm_seqfile(dev, "state", vfio_dev_migration,
>> + vfio_device_state_read);
>> +}
>> +EXPORT_SYMBOL_GPL(vfio_device_debugfs_init);
>
> I think these should be more integrated into vfio core. As it is, this
> series doesn't enable the base migration/state entry support for
> drivers other than hisi_acc, where this proposal requires explicit
> setup and teardown by the driver probe and remove callbacks.
>
> Instead the init and exit functions here should be called directly from
> __vfio_register_dev() and vfio_unregister_group_dev() respectively.
> The setup of the migration directory and state file should be
> conditional on the device providing mig_ops, while the base dev_name
> directory is setup for all devices for future use cases.
>
> This would allow that mlx5 and future drivers automatically get this
> with no driver code, and in fact all devices would get debugfs dev_name
> directories for better test coverage. hisi_acc would only need to add
> driver specific entries after registering the device and free any
> related data after unregistering the device. In this way, none of the
> entry points here would need to be exported for drivers, which is
> perhaps the direction Jason was thinking with his prior comments.
>

I understand your plan.
I will fix it in the next version.

>> +
>> +void vfio_device_debugfs_exit(struct vfio_device *vdev)
>> +{
>> + debugfs_remove_recursive(vdev->debug_root);
>> +}
>> +EXPORT_SYMBOL_GPL(vfio_device_debugfs_exit);
>> +
>> +void vfio_debugfs_create_root(void)
>> +{
>> + vfio_debugfs_root = debugfs_create_dir("vfio", NULL);
>> +}
>> +
>> +void vfio_debugfs_remove_root(void)
>> +{
>> + debugfs_remove_recursive(vfio_debugfs_root);
>> + vfio_debugfs_root = NULL;
>> +}
>> +
>> diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
>> index 3a597e799918..09772fd3a396 100644
>> --- a/drivers/vfio/vfio_main.c
>> +++ b/drivers/vfio/vfio_main.c
>> @@ -1408,6 +1408,9 @@ static int __init vfio_init(void)
>> }
>>
>> pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
>> +
>> + vfio_debugfs_create_root();
>> +
>
> The pr_info is intended to be the last call in the init path.
>
OK.

>> return 0;
>>
>> err_dev_class:
>> @@ -1425,6 +1428,8 @@ static void __exit vfio_cleanup(void)
>> vfio_virqfd_exit();
>> vfio_group_cleanup();
>> xa_destroy(&vfio_device_set_xa);
>> +
>> + vfio_debugfs_remove_root();
>
> The added blank line is unnecessary, there's no conceptual reason to
> split this from the remaining teardown. I suspect this should also be
> first in the teardown since it was setup last on init and I don't see
> any other dependencies.
>OK.

>> }
>>
>> module_init(vfio_init);
>> diff --git a/include/linux/vfio.h b/include/linux/vfio.h
>> index 93134b023968..fa6b898ebb58 100644
>> --- a/include/linux/vfio.h
>> +++ b/include/linux/vfio.h
>> @@ -63,6 +63,14 @@ struct vfio_device {
>> struct iommufd_ctx *iommufd_ictx;
>> bool iommufd_attached;
>> #endif
>> +
>> +#ifdef CONFIG_DEBUG_FS
>> + /*
>> + * debug_root is a static property of the vfio_device
>> + * which must be set prior to registering the vfio_device.
>> + */
>
> What imposed this ordering requirement? In fact the code flow here
> makes the debugfs entries available event before the device is
> registered with vfio core, which seems problematic. This goes away if
> it's setup as described above. Thanks,
>
OK.
I will modify this comment.

Thanks.
Longfang.
> Alex
>
>> + struct dentry *debug_root;
>> +#endif
>> };
>>
>> /**
>
> .
>

2023-03-25 10:00:24

by liulongfang

[permalink] [raw]

Subject: Re: [PATCH v9 3/5] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

On 2023/3/21 6:09, Alex Williamson wrote:
> On Mon, 20 Mar 2023 17:23:36 +0800
> Longfang Liu <[email protected]> wrote:
>
>> On the debugfs framework of VFIO, if the CONFIG_DEBUG_FS macro is
>> enabled, the debug function is registered for the live migration driver
>> of the HiSilicon accelerator device.
>>
>> After registering the HiSilicon accelerator device on the debugfs
>> framework of live migration of vfio, a directory file "hisi_acc"
>> of debugfs is created, and then three debug function files are
>> created in this directory:
>>
>> data file: used to get the migration data of the live migration device
>> attr file: used to get device attributes of the live migration device
>> debug file: used to test for acquiring and writing device state data
>> for VF device.
>>
>> Signed-off-by: Longfang Liu <[email protected]>
>> ---
>> .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 290 ++++++++++++++++++
>> .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h | 11 +
>> 2 files changed, 301 insertions(+)
>>
>> diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
>> index a1589947e721..22ebe0e8f90f 100644
>> --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
>> +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
>> @@ -15,6 +15,7 @@
>> #include <linux/anon_inodes.h>
>>
>> #include "hisi_acc_vfio_pci.h"
>> +#include "../../vfio.h"
>>
>> /* Return 0 on VM acc device ready, -ETIMEDOUT hardware timeout */
>> static int qm_wait_dev_not_ready(struct hisi_qm *qm)
>> @@ -606,6 +607,18 @@ hisi_acc_check_int_state(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>> }
>> }
>>
>> +static void hisi_acc_vf_migf_save(struct hisi_acc_vf_migration_file *src_migf,
>> + struct hisi_acc_vf_migration_file *dst_migf)
>> +{
>> + if (!dst_migf)
>> + return;
>> +
>> + dst_migf->disabled = false;
>> + dst_migf->total_length = src_migf->total_length;
>> + memcpy(&dst_migf->vf_data, &src_migf->vf_data,
>> + sizeof(struct acc_vf_data));
>> +}
>> +
>> static void hisi_acc_vf_disable_fd(struct hisi_acc_vf_migration_file *migf)
>> {
>> mutex_lock(&migf->lock);
>> @@ -618,12 +631,16 @@ static void hisi_acc_vf_disable_fd(struct hisi_acc_vf_migration_file *migf)
>> static void hisi_acc_vf_disable_fds(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>> {
>> if (hisi_acc_vdev->resuming_migf) {
>> + hisi_acc_vf_migf_save(hisi_acc_vdev->resuming_migf,
>> + hisi_acc_vdev->debug_migf);
>> hisi_acc_vf_disable_fd(hisi_acc_vdev->resuming_migf);
>> fput(hisi_acc_vdev->resuming_migf->filp);
>> hisi_acc_vdev->resuming_migf = NULL;
>> }
>>
>> if (hisi_acc_vdev->saving_migf) {
>> + hisi_acc_vf_migf_save(hisi_acc_vdev->saving_migf,
>> + hisi_acc_vdev->debug_migf);
>> hisi_acc_vf_disable_fd(hisi_acc_vdev->saving_migf);
>> fput(hisi_acc_vdev->saving_migf->filp);
>> hisi_acc_vdev->saving_migf = NULL;
>> @@ -1303,6 +1320,273 @@ static long hisi_acc_vfio_pci_ioctl(struct vfio_device *core_vdev, unsigned int
>> return vfio_pci_core_ioctl(core_vdev, cmd, arg);
>> }
>>
>> +static int hisi_acc_vf_debug_io(struct vfio_device *vdev)
>> +{
>> + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
>> + struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
>> + struct device *dev = vdev->dev;
>> + u64 data;
>> + int ret;
>> +
>> + ret = qm_wait_dev_not_ready(vf_qm);
>> + if (ret)
>> + dev_err(dev, "VF device not ready!\n");
>> +
>> + data = readl(vf_qm->io_base + QM_MB_CMD_SEND_BASE);
>> + dev_info(dev, "debug mailbox val: 0x%llx\n", data);
>> +
>> + return ret;
>> +}
>> +
>> +static int hisi_acc_vf_debug_resume(struct vfio_device *vdev)
>> +{
>> + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
>> + struct hisi_acc_vf_migration_file *migf = hisi_acc_vdev->debug_migf;
>> + struct device *dev = vdev->dev;
>> + int ret;
>> +
>> + ret = vf_qm_state_save(hisi_acc_vdev, migf);
>> + if (ret) {
>> + dev_err(dev, "failed to save device data!\n");
>> + return -EINVAL;
>> + }
>> +
>> + ret = vf_qm_check_match(hisi_acc_vdev, migf);
>> + if (ret) {
>> + dev_err(dev, "failed to match the VF!\n");
>> + return -EINVAL;
>> + }
>> +
>> + ret = vf_qm_load_data(hisi_acc_vdev, migf);
>> + if (ret) {
>> + dev_err(dev, "failed to recover the VF!\n");
>> + return -EINVAL;
>> + }
>> +
>> + vf_qm_fun_reset(&hisi_acc_vdev->vf_qm);
>> + dev_info(dev, "successful to resume device data!\n");
>> +
>> + return 0;
>> +}
>> +
>> +static int hisi_acc_vf_debug_save(struct vfio_device *vdev)
>> +{
>> + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
>> + struct hisi_acc_vf_migration_file *migf = hisi_acc_vdev->debug_migf;
>> + struct device *dev = vdev->dev;
>> + int ret;
>> +
>> + ret = vf_qm_state_save(hisi_acc_vdev, migf);
>> + if (ret) {
>> + dev_err(dev, "failed to save device data!\n");
>> + return -EINVAL;
>> + }
>> + dev_info(dev, "successful to save device data!\n");
>> +
>> + return 0;
>> +}
>
> It seems backwards that we've defined the 'debug' file to be writable
> only in order to select which operation to perform, where the user then
> needs to look in dmesg for information related to an errno. Wouldn't
> it make more sense to create separate save, restore, and io_test files
> that perform the operation when read and return a buffer indicating the
> error condition or success? What's the benefit of multiplexing these
> through writes to a single debug file?
>

Although you have added new debug files. But the user's operation is simplified.
Users only need a simple cat operation to trigger the corresponding operation.
And it does not require the user to know the corresponding command.
This option is acceptable

>> +
>> +static int
>> +hisi_acc_vf_debug_operate(struct vfio_device *vdev, unsigned int cmd)
>> +{
>> + int ret;
>> +
>> + switch (cmd) {
>> + case STATE_SAVE:
>> + ret = hisi_acc_vf_debug_save(vdev);
>> + if (ret)
>> + return ret;
>> + break;
>> + case STATE_RESUME:
>> + ret = hisi_acc_vf_debug_resume(vdev);
>> + if (ret)
>> + return ret;
>> + break;
>> + case RW_IO_TEST:
>> + ret = hisi_acc_vf_debug_io(vdev);
>> + if (ret)
>> + return ret;
>> + break;
>> + default:
>> + return -EINVAL;
>> + }
>> +
>> + return 0;
>> +}
>
> Initialize ret = -EINVAL, 'return ret' outside the case, and drop the
> per-case returns.
>

After the above debug file is modified, it will be deleted here.

>> +
>> +static int hisi_acc_vf_debug_check(struct vfio_device *vdev)
>> +{
>> + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
>> + struct hisi_acc_vf_migration_file *migf = hisi_acc_vdev->debug_migf;
>> + enum vfio_device_mig_state state;
>> +
>> + if (!vdev->mig_ops || !migf) {
>> + dev_err(vdev->dev, "device not support debugfs!\n");
>> + return -EINVAL;
>> + }
>
> Why did we create the file then?
>
After the above debug file is modified, it will be deleted here.

>> +
>> + /* If device not opened, the debugfs operation will trigger calltrace */
>> + (void)vdev->mig_ops->migration_get_state(vdev, &state);
>> + if (state == VFIO_DEVICE_STATE_ERROR ||
>> + state == VFIO_DEVICE_STATE_STOP) {
>> + dev_err(vdev->dev, "device not opened!\n");
>> + return -EINVAL;
>> + }
>
> And we can't use something like open_count? What protects this from
> racing against the device being released?
>

There is indeed a need for a more atomic detection method to ensure
that the device can be operated.

>> +
>> + return 0;
>> +}
>> +
>> +static ssize_t hisi_acc_vf_debug_write(struct file *filp, const char __user *buffer,
>> + size_t count, loff_t *pos)
>> +{
>> + struct vfio_device *vdev = filp->private_data;
>> + char tbuf[VFIO_DEV_DBG_LEN];
>> + unsigned long cmd;
>> + int len, ret;
>> +
>> + if (*pos)
>> + return 0;
>> +
>> + if (count >= VFIO_DEV_DBG_LEN)
>> + return -ENOSPC;
>> +
>> + ret = hisi_acc_vf_debug_check(vdev);
>> + if (ret)
>> + return -EINVAL;
>> +
>> + len = simple_write_to_buffer(tbuf, VFIO_DEV_DBG_LEN - 1,
>> + pos, buffer, count);
>> + if (len < 0 || len > VFIO_DEV_DBG_LEN - 1)
>> + return -EINVAL;
>> + tbuf[len] = '\0';
>> + if (kstrtoul(tbuf, 0, &cmd))
>> + return -EFAULT;
>> +
>> + ret = hisi_acc_vf_debug_operate(vdev, cmd);
>> + if (ret) {
>> + dev_err(vdev->dev, "device debug test failed!\n");
>> + return -EINVAL;
>> + }
>> +
>> + return count;
>> +}
>> +
>> +static const struct file_operations hisi_acc_vf_debug_fops = {
>> + .owner = THIS_MODULE,
>> + .open = simple_open,
>> + .write = hisi_acc_vf_debug_write,
>> +};
>> +
>> +static void seq_print_hex_data(struct seq_file *seq, const void *buf, size_t len)
>> +{
>> +#define HEX_LINE_SIZE 131
>> +#define HEX_ROW_SIZE 16
>> + unsigned char linebuf[HEX_LINE_SIZE];
>> + int i, linelen, remaining = len;
>> + const u8 *ptr = buf;
>> +
>> + for (i = 0; i < len; i += HEX_ROW_SIZE) {
>> + linelen = min(remaining, HEX_ROW_SIZE);
>> + remaining -= HEX_ROW_SIZE;
>> +
>> + hex_dump_to_buffer(ptr + i, linelen, HEX_ROW_SIZE, 1,
>> + linebuf, sizeof(linebuf), false);
>> +
>> + seq_printf(seq, "%s%.8x: %s\n", "Mig Data:", i, linebuf);
>> + }
>> +}
>
> Can't this use seq_hex_dump()? If there's a _good_ reason why not, it
> should be noted in comments and the function should be renamed not to
> pollute the seq_ namespace. Thanks,
>

I'll debug it with seq_hex_dump().

Thanks,
Longfang.
> Alex
>
>> +
>> +static int hisi_acc_vf_data_read(struct seq_file *seq, void *data)
>> +{
>> + struct device *vf_dev = seq->private;
>> + struct vfio_pci_core_device *core_device = dev_get_drvdata(vf_dev);
>> + struct vfio_device *vdev = &core_device->vdev;
>> + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
>> + struct hisi_acc_vf_migration_file *debug_migf = hisi_acc_vdev->debug_migf;
>> + size_t vf_data_sz = offsetofend(struct acc_vf_data, padding);
>> +
>> + if (debug_migf && debug_migf->total_length)
>> + seq_print_hex_data(seq, (unsigned char *)&debug_migf->vf_data,
>> + vf_data_sz);
>> + else
>> + seq_printf(seq, "%s\n", "device not migrated!");
>> +
>> + return 0;
>> +}
>> +
>> +static int hisi_acc_vf_attr_read(struct seq_file *seq, void *data)
>> +{
>> + struct device *vf_dev = seq->private;
>> + struct vfio_pci_core_device *core_device = dev_get_drvdata(vf_dev);
>> + struct vfio_device *vdev = &core_device->vdev;
>> + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
>> + struct hisi_acc_vf_migration_file *debug_migf = hisi_acc_vdev->debug_migf;
>> +
>> + if (debug_migf && debug_migf->total_length) {
>> + seq_printf(seq,
>> + "acc device:\n"
>> + "device state: %d\n"
>> + "device ready: %u\n"
>> + "data valid: %d\n"
>> + "data size: %lu\n",
>> + hisi_acc_vdev->mig_state,
>> + hisi_acc_vdev->vf_qm_state,
>> + debug_migf->disabled,
>> + debug_migf->total_length);
>> + } else {
>> + seq_printf(seq, "%s\n", "device not migrated!");
>> + }
>> +
>> + return 0;
>> +}
>> +
>> +static int hisi_acc_vfio_debug_init(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>> +{
>> + struct vfio_device *vdev = &hisi_acc_vdev->core_device.vdev;
>> + struct dentry *vfio_dev_migration = NULL;
>> + struct dentry *vfio_hisi_acc = NULL;
>> + struct device *dev = vdev->dev;
>> + void *migf = NULL;
>> +
>> + if (!debugfs_initialized())
>> + return 0;
>> +
>> + vfio_device_debugfs_init(vdev);
>> +
>> + migf = kzalloc(sizeof(struct hisi_acc_vf_migration_file), GFP_KERNEL);
>> + if (!migf)
>> + return -ENOMEM;
>> +
>> + hisi_acc_vdev->debug_migf = migf;
>> +
>> + vfio_dev_migration = debugfs_lookup("migration", vdev->debug_root);
>> + if (!vfio_dev_migration) {
>> + dev_err(dev, "failed to lookup migration debugfs file!\n");
>> + return -ENODEV;
>> + }
>> +
>> + vfio_hisi_acc = debugfs_create_dir("hisi_acc", vfio_dev_migration);
>> + debugfs_create_devm_seqfile(dev, "data", vfio_hisi_acc,
>> + hisi_acc_vf_data_read);
>> + debugfs_create_devm_seqfile(dev, "attr", vfio_hisi_acc,
>> + hisi_acc_vf_attr_read);
>> + debugfs_create_file("debug", 0200, vfio_hisi_acc,
>> + vdev, &hisi_acc_vf_debug_fops);
>> +
>> + return 0;
>> +}
>> +
>> +static void hisi_acc_vf_debugfs_exit(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>> +{
>> + struct vfio_device *vdev = &hisi_acc_vdev->core_device.vdev;
>> +
>> + if (!debugfs_initialized())
>> + return;
>> +
>> + vfio_device_debugfs_exit(vdev);
>> + kfree(hisi_acc_vdev->debug_migf);
>> +}
>> +
>> static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
>> {
>> struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
>> @@ -1416,6 +1700,9 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
>> if (IS_ERR(hisi_acc_vdev))
>> return PTR_ERR(hisi_acc_vdev);
>>
>> + if (ops == &hisi_acc_vfio_pci_migrn_ops)
>> + hisi_acc_vfio_debug_init(hisi_acc_vdev);
>> +
>> dev_set_drvdata(&pdev->dev, &hisi_acc_vdev->core_device);
>> ret = vfio_pci_core_register_device(&hisi_acc_vdev->core_device);
>> if (ret)
>> @@ -1423,6 +1710,8 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
>> return 0;
>>
>> out_put_vdev:
>> + if (ops == &hisi_acc_vfio_pci_migrn_ops)
>> + hisi_acc_vf_debugfs_exit(hisi_acc_vdev);
>> vfio_put_device(&hisi_acc_vdev->core_device.vdev);
>> return ret;
>> }
>> @@ -1431,6 +1720,7 @@ static void hisi_acc_vfio_pci_remove(struct pci_dev *pdev)
>> {
>> struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_drvdata(pdev);
>>
>> + hisi_acc_vf_debugfs_exit(hisi_acc_vdev);
>> vfio_pci_core_unregister_device(&hisi_acc_vdev->core_device);
>> vfio_put_device(&hisi_acc_vdev->core_device.vdev);
>> }
>> diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
>> index dcabfeec6ca1..ef50b12f018d 100644
>> --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
>> +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
>> @@ -49,6 +49,14 @@
>> #define QM_EQC_DW0 0X8000
>> #define QM_AEQC_DW0 0X8020
>>
>> +#define VFIO_DEV_DBG_LEN 256
>> +
>> +enum mig_debug_cmd {
>> + STATE_SAVE,
>> + STATE_RESUME,
>> + RW_IO_TEST,
>> +};
>> +
>> struct acc_vf_data {
>> #define QM_MATCH_SIZE offsetofend(struct acc_vf_data, qm_rsv_state)
>> /* QM match information */
>> @@ -113,5 +121,8 @@ struct hisi_acc_vf_core_device {
>> spinlock_t reset_lock;
>> struct hisi_acc_vf_migration_file *resuming_migf;
>> struct hisi_acc_vf_migration_file *saving_migf;
>> +
>> + /* For debugfs */
>> + struct hisi_acc_vf_migration_file *debug_migf;
>> };
>> #endif /* HISI_ACC_VFIO_PCI_H */
>
> .
>