[PATCH v11 3/4] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

[PATCH v11 3/4] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

[liulongfang]

From: Longfang Liu <liulongfang@huawei.com>

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 from the driver
attr file: used to get device attributes parameters from the driver
save file: used to read the data of the live migration device and save
it to the driver.
io_test: used to test IO read and write for the driver.

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
---
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 182 ++++++++++++++++++
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h    |  11 ++
 2 files changed, 193 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..a6f5e94bfaf2 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 +1320,164 @@ 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_check(struct seq_file *seq, 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;
+
+	if (!vdev->mig_ops || !migf) {
+		seq_printf(seq, "%s\n", "device not support debugfs!");
+		return -EINVAL;
+	}
+
+	/* If device not opened, the debugfs operation will trigger calltrace */
+	if (!vdev->open_count) {
+		seq_printf(seq, "%s\n", "device not opened!");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int hisi_acc_vf_debug_io(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_qm *vf_qm = &hisi_acc_vdev->vf_qm;
+	u64 value;
+	int ret;
+
+	ret = hisi_acc_vf_debug_check(seq, vdev);
+	if (ret)
+		goto io_err;
+
+	ret = qm_wait_dev_not_ready(vf_qm);
+	if (ret) {
+		seq_printf(seq, "%s\n", "VF device not ready!");
+		goto io_err;
+	}
+
+	value = readl(vf_qm->io_base + QM_MB_CMD_SEND_BASE);
+	seq_printf(seq, "%s:0x%llx\n", "debug mailbox val", value);
+
+io_err:
+	return 0;
+}
+
+static int hisi_acc_vf_debug_save(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 *migf = hisi_acc_vdev->debug_migf;
+	int ret;
+
+	ret = hisi_acc_vf_debug_check(seq, vdev);
+	if (ret)
+		goto save_err;
+
+	ret = vf_qm_state_save(hisi_acc_vdev, migf);
+	if (ret) {
+		seq_printf(seq, "%s\n", "failed to save device data!");
+		goto save_err;
+	}
+	seq_printf(seq, "%s\n", "successful to save device data!");
+
+save_err:
+	return 0;
+}
+
+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_hex_dump(seq, "Mig Data:", DUMP_PREFIX_OFFSET, 16, 1,
+				(unsigned char *)&debug_migf->vf_data,
+				vf_data_sz, false);
+	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;
+
+	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_devm_seqfile(dev, "io_test", vfio_hisi_acc,
+				  hisi_acc_vf_debug_io);
+	debugfs_create_devm_seqfile(dev, "save", vfio_hisi_acc,
+				  hisi_acc_vf_debug_save);
+
+	return 0;
+}
+
+static void hisi_acc_vf_debugfs_exit(struct hisi_acc_vf_core_device *hisi_acc_vdev)
+{
+	if (!debugfs_initialized())
+		return;
+
+	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);
@@ -1323,6 +1498,7 @@ static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
 	}
 
 	vfio_pci_core_finish_enable(vdev);
+
 	return 0;
 }
 
@@ -1420,9 +1596,14 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
 	ret = vfio_pci_core_register_device(&hisi_acc_vdev->core_device);
 	if (ret)
 		goto out_put_vdev;
+
+	if (ops == &hisi_acc_vfio_pci_migrn_ops)
+		hisi_acc_vfio_debug_init(hisi_acc_vdev);
 	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 +1612,7 @@ 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 */
-- 
2.24.0

Re: [PATCH v11 3/4] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

[Alex Williamson]

On Fri, 30 Jun 2023 17:24:56 +0800
liulongfang <liulongfang@huawei.com> wrote:

> From: Longfang Liu <liulongfang@huawei.com>
> 
> 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 from the driver
> attr file: used to get device attributes parameters from the driver
> save file: used to read the data of the live migration device and save
> it to the driver.
> io_test: used to test IO read and write for the driver.
> 
> Signed-off-by: Longfang Liu <liulongfang@huawei.com>
> ---
>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 182 ++++++++++++++++++
>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h    |  11 ++
>  2 files changed, 193 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..a6f5e94bfaf2 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)

Consider swapping the args to be more consistent with functions like
memcpy() where the destination is the first arg and source is the
second.

> +{
> +	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 +1320,164 @@ 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_check(struct seq_file *seq, 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;
> +
> +	if (!vdev->mig_ops || !migf) {
> +		seq_printf(seq, "%s\n", "device not support debugfs!");

"device does not support debugfs"?

> +		return -EINVAL;
> +	}
> +
> +	/* If device not opened, the debugfs operation will trigger calltrace */
> +	if (!vdev->open_count) {
> +		seq_printf(seq, "%s\n", "device not opened!");
> +		return -EINVAL;
> +	}

What prevents this from racing release of the device?

> +
> +	return 0;
> +}
> +
> +static int hisi_acc_vf_debug_io(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;

A tab sneaked in here.

> +	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;
> +	u64 value;
> +	int ret;
> +
> +	ret = hisi_acc_vf_debug_check(seq, vdev);
> +	if (ret)
> +		goto io_err;
> +
> +	ret = qm_wait_dev_not_ready(vf_qm);
> +	if (ret) {
> +		seq_printf(seq, "%s\n", "VF device not ready!");
> +		goto io_err;
> +	}
> +
> +	value = readl(vf_qm->io_base + QM_MB_CMD_SEND_BASE);
> +	seq_printf(seq, "%s:0x%llx\n", "debug mailbox val", value);
> +
> +io_err:
> +	return 0;

A goto that simply returns seems unnecessary vs return at the error
condition.  Also why don't we return the errno for error cases?  Do we
even need seq_printf() calls for error cases?

> +}
> +
> +static int hisi_acc_vf_debug_save(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;

Another tab.

> +	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;
> +	int ret;
> +
> +	ret = hisi_acc_vf_debug_check(seq, vdev);
> +	if (ret)
> +		goto save_err;
> +
> +	ret = vf_qm_state_save(hisi_acc_vdev, migf);
> +	if (ret) {
> +		seq_printf(seq, "%s\n", "failed to save device data!");
> +		goto save_err;
> +	}
> +	seq_printf(seq, "%s\n", "successful to save device data!");
> +
> +save_err:
> +	return 0;
> +}
> +
> +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;

Tab.

> +	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_hex_dump(seq, "Mig Data:", DUMP_PREFIX_OFFSET, 16, 1,
> +				(unsigned char *)&debug_migf->vf_data,
> +				vf_data_sz, false);
> +	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;

Tab.

> +	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;
> +
> +	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_devm_seqfile(dev, "io_test", vfio_hisi_acc,
> +				  hisi_acc_vf_debug_io);
> +	debugfs_create_devm_seqfile(dev, "save", vfio_hisi_acc,
> +				  hisi_acc_vf_debug_save);
> +
> +	return 0;
> +}
> +
> +static void hisi_acc_vf_debugfs_exit(struct hisi_acc_vf_core_device *hisi_acc_vdev)
> +{
> +	if (!debugfs_initialized())
> +		return;
> +
> +	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);
> @@ -1323,6 +1498,7 @@ static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
>  	}
>  
>  	vfio_pci_core_finish_enable(vdev);
> +
>  	return 0;
>  }
>  
> @@ -1420,9 +1596,14 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
>  	ret = vfio_pci_core_register_device(&hisi_acc_vdev->core_device);
>  	if (ret)
>  		goto out_put_vdev;
> +
> +	if (ops == &hisi_acc_vfio_pci_migrn_ops)
> +		hisi_acc_vfio_debug_init(hisi_acc_vdev);
>  	return 0;
>  
>  out_put_vdev:
> +	if (ops == &hisi_acc_vfio_pci_migrn_ops)
> +		hisi_acc_vf_debugfs_exit(hisi_acc_vdev);

Why do we need this?  There's no case where debug_init occurs before
this goto.

>  	vfio_put_device(&hisi_acc_vdev->core_device.vdev);
>  	return ret;
>  }
> @@ -1431,6 +1612,7 @@ 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,
> +};

Unused.

Thanks,
Alex

> +
>  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 */

Re: [PATCH v11 3/4] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

[liulongfang]

On 2023/7/15 6:07, Alex Williamson wrote:
> On Fri, 30 Jun 2023 17:24:56 +0800
> liulongfang <liulongfang@huawei.com> wrote:
> 
>> From: Longfang Liu <liulongfang@huawei.com>
>>
>> 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 from the driver
>> attr file: used to get device attributes parameters from the driver
>> save file: used to read the data of the live migration device and save
>> it to the driver.
>> io_test: used to test IO read and write for the driver.
>>
>> Signed-off-by: Longfang Liu <liulongfang@huawei.com>
>> ---
>>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 182 ++++++++++++++++++
>>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h    |  11 ++
>>  2 files changed, 193 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..a6f5e94bfaf2 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)
> 
> Consider swapping the args to be more consistent with functions like
> memcpy() where the destination is the first arg and source is the
> second.>
OK, These two parameters can be swapped.

>> +{
>> +	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 +1320,164 @@ 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_check(struct seq_file *seq, 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;
>> +
>> +	if (!vdev->mig_ops || !migf) {
>> +		seq_printf(seq, "%s\n", "device not support debugfs!");
> 
> "device does not support debugfs"?
> 
OK,"device does not support live migration"

>> +		return -EINVAL;
>> +	}
>> +
>> +	/* If device not opened, the debugfs operation will trigger calltrace */
>> +	if (!vdev->open_count) {
>> +		seq_printf(seq, "%s\n", "device not opened!");
>> +		return -EINVAL;
>> +	}
> 
> What prevents this from racing release of the device?
>
Now there are only read operations for debugfs. The open_count here only needs
to be used to prevent read operations when the device is not opened.
There is no need to deal with competition issues.

>> +
>> +	return 0;
>> +}
>> +
>> +static int hisi_acc_vf_debug_io(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;
> 
> A tab sneaked in here.
> 
Thanks.

>> +	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;
>> +	u64 value;
>> +	int ret;
>> +
>> +	ret = hisi_acc_vf_debug_check(seq, vdev);
>> +	if (ret)
>> +		goto io_err;
>> +
>> +	ret = qm_wait_dev_not_ready(vf_qm);
>> +	if (ret) {
>> +		seq_printf(seq, "%s\n", "VF device not ready!");
>> +		goto io_err;
>> +	}
>> +
>> +	value = readl(vf_qm->io_base + QM_MB_CMD_SEND_BASE);
>> +	seq_printf(seq, "%s:0x%llx\n", "debug mailbox val", value);
>> +
>> +io_err:
>> +	return 0;
> 
> A goto that simply returns seems unnecessary vs return at the error
Ok, no need to use goto here. The following one is also handled in the same way.

> condition.  Also why don't we return the errno for error cases?  Do we> even need seq_printf() calls for error cases?
>

Added logging of seq_printf only on critical steps.

>> +}
>> +
>> +static int hisi_acc_vf_debug_save(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;
> 
> Another tab.
> 
OK.

>> +	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;
>> +	int ret;
>> +
>> +	ret = hisi_acc_vf_debug_check(seq, vdev);
>> +	if (ret)
>> +		goto save_err;
>> +
>> +	ret = vf_qm_state_save(hisi_acc_vdev, migf);
>> +	if (ret) {
>> +		seq_printf(seq, "%s\n", "failed to save device data!");
>> +		goto save_err;
>> +	}
>> +	seq_printf(seq, "%s\n", "successful to save device data!");
>> +
>> +save_err:
>> +	return 0;
>> +}
>> +
>> +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;
> 
> Tab.
> 
OK.
>> +	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_hex_dump(seq, "Mig Data:", DUMP_PREFIX_OFFSET, 16, 1,
>> +				(unsigned char *)&debug_migf->vf_data,
>> +				vf_data_sz, false);
>> +	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;
> 
> Tab.
> 
OK.
>> +	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;
>> +
>> +	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_devm_seqfile(dev, "io_test", vfio_hisi_acc,
>> +				  hisi_acc_vf_debug_io);
>> +	debugfs_create_devm_seqfile(dev, "save", vfio_hisi_acc,
>> +				  hisi_acc_vf_debug_save);
>> +
>> +	return 0;
>> +}
>> +
>> +static void hisi_acc_vf_debugfs_exit(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>> +{
>> +	if (!debugfs_initialized())
>> +		return;
>> +
>> +	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);
>> @@ -1323,6 +1498,7 @@ static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
>>  	}
>>  
>>  	vfio_pci_core_finish_enable(vdev);
>> +
>>  	return 0;
>>  }
>>  
>> @@ -1420,9 +1596,14 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
>>  	ret = vfio_pci_core_register_device(&hisi_acc_vdev->core_device);
>>  	if (ret)
>>  		goto out_put_vdev;
>> +
>> +	if (ops == &hisi_acc_vfio_pci_migrn_ops)
>> +		hisi_acc_vfio_debug_init(hisi_acc_vdev);
>>  	return 0;
>>  
>>  out_put_vdev:
>> +	if (ops == &hisi_acc_vfio_pci_migrn_ops)
>> +		hisi_acc_vf_debugfs_exit(hisi_acc_vdev);
> 
> Why do we need this?  There's no case where debug_init occurs before
> this goto.
>

Yes. These two lines are not needed here.

>>  	vfio_put_device(&hisi_acc_vdev->core_device.vdev);
>>  	return ret;
>>  }
>> @@ -1431,6 +1612,7 @@ 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,
>> +};
> 
> Unused.
> 
OK.

> Thanks,
> Alex
> 
Thanks,
Longfang.
>> +
>>  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 */
> 
> .
> 

[PATCH v11 0/4] debugfs to hisilicon migration driver

[Longfang Liu]

Add a debugfs function to the hisilicon migration driver in VFIO to
provide intermediate state values and data during device migration.

When the execution of live migration fails, the user can view the
status and data during the migration process separately from the
source and the destination, which is convenient for users to analyze
and locate problems.

Changes v10 -> v11
	Update conditions for debugfs registration

Changes v9 -> v10
	Optimize symmetry processing of mutex

Changes v8 -> v9
	Added device enable mutex

Changes v7 -> v8
	Delete unnecessary information

Changes v6 -> v7
	Remove redundant kernel error log printing and
	remove unrelated bugfix code

Changes v5 -> v6
	Modify log output calling error

Changes v4 -> v5
	Adjust the descriptioniptionbugfs file directory

Changes v3 -> v4
	Rebased on kernel6.9

Changes 2 -> v3
	Solve debugfs serialization problem.

Changes v1 -> v2
	Solve the racy problem of io_base.

Longfang Liu (4):
  hisi_acc_vfio_pci: extract public functions for container_of
  hisi_acc_vfio_pci: create subfunction for data reading
  hisi_acc_vfio_pci: register debugfs for hisilicon migration driver
  Documentation: add debugfs description for hisi migration

 .../ABI/testing/debugfs-hisi-migration        |  25 ++
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 279 ++++++++++++++++--
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h    |   7 +
 3 files changed, 280 insertions(+), 31 deletions(-)
 create mode 100644 Documentation/ABI/testing/debugfs-hisi-migration

-- 
2.24.0

[PATCH v11 1/4] hisi_acc_vfio_pci: extract public functions for container_of

[Longfang Liu]

In the current driver, vdev is obtained from struct
hisi_acc_vf_core_device through the container_of function.
This method is used in many places in the driver. In order to
reduce this repetitive operation, It was extracted into
a public function.

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
---
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 21 ++++++++++---------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 9a3e97108ace..45351be8e270 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -630,6 +630,12 @@ static void hisi_acc_vf_disable_fds(struct hisi_acc_vf_core_device *hisi_acc_vde
 	}
 }
 
+static struct hisi_acc_vf_core_device *hisi_acc_get_vf_dev(struct vfio_device *vdev)
+{
+	return container_of(vdev, struct hisi_acc_vf_core_device,
+			    core_device.vdev);
+}
+
 static void hisi_acc_vf_reset(struct hisi_acc_vf_core_device *hisi_acc_vdev)
 {
 	hisi_acc_vdev->vf_qm_state = QM_NOT_READY;
@@ -1033,8 +1039,7 @@ static struct file *
 hisi_acc_vfio_pci_set_device_state(struct vfio_device *vdev,
 				   enum vfio_device_mig_state new_state)
 {
-	struct hisi_acc_vf_core_device *hisi_acc_vdev = container_of(vdev,
-			struct hisi_acc_vf_core_device, core_device.vdev);
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
 	enum vfio_device_mig_state next_state;
 	struct file *res = NULL;
 	int ret;
@@ -1075,8 +1080,7 @@ static int
 hisi_acc_vfio_pci_get_device_state(struct vfio_device *vdev,
 				   enum vfio_device_mig_state *curr_state)
 {
-	struct hisi_acc_vf_core_device *hisi_acc_vdev = container_of(vdev,
-			struct hisi_acc_vf_core_device, core_device.vdev);
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev);
 
 	mutex_lock(&hisi_acc_vdev->state_mutex);
 	*curr_state = hisi_acc_vdev->mig_state;
@@ -1280,8 +1284,7 @@ static long hisi_acc_vfio_pci_ioctl(struct vfio_device *core_vdev, unsigned int
 
 static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
 {
-	struct hisi_acc_vf_core_device *hisi_acc_vdev = container_of(core_vdev,
-			struct hisi_acc_vf_core_device, core_device.vdev);
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
 	struct vfio_pci_core_device *vdev = &hisi_acc_vdev->core_device;
 	int ret;
 
@@ -1304,8 +1307,7 @@ static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
 
 static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev)
 {
-	struct hisi_acc_vf_core_device *hisi_acc_vdev = container_of(core_vdev,
-			struct hisi_acc_vf_core_device, core_device.vdev);
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
 	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
 
 	iounmap(vf_qm->io_base);
@@ -1320,8 +1322,7 @@ static const struct vfio_migration_ops hisi_acc_vfio_pci_migrn_state_ops = {
 
 static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
 {
-	struct hisi_acc_vf_core_device *hisi_acc_vdev = container_of(core_vdev,
-			struct hisi_acc_vf_core_device, core_device.vdev);
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
 	struct pci_dev *pdev = to_pci_dev(core_vdev->dev);
 	struct hisi_qm *pf_qm = hisi_acc_get_pf_qm(pdev);
 
-- 
2.24.0

[PATCH v11 2/4] hisi_acc_vfio_pci: create subfunction for data reading

[Longfang Liu]

This patch generates the code for the operation of reading data from
the device into a sub-function.
Then, it can be called during the device status data saving phase of
the live migration process and the device status data reading function
in debugfs.
Thereby reducing the redundant code of the driver.

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
---
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 54 +++++++++++--------
 1 file changed, 33 insertions(+), 21 deletions(-)

diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 45351be8e270..a8c53952d82e 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -486,31 +486,11 @@ static int vf_qm_load_data(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	return 0;
 }
 
-static int vf_qm_state_save(struct hisi_acc_vf_core_device *hisi_acc_vdev,
-			    struct hisi_acc_vf_migration_file *migf)
+static int vf_qm_read_data(struct hisi_qm *vf_qm, struct acc_vf_data *vf_data)
 {
-	struct acc_vf_data *vf_data = &migf->vf_data;
-	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
 	struct device *dev = &vf_qm->pdev->dev;
 	int ret;
 
-	if (unlikely(qm_wait_dev_not_ready(vf_qm))) {
-		/* Update state and return with match data */
-		vf_data->vf_qm_state = QM_NOT_READY;
-		hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
-		migf->total_length = QM_MATCH_SIZE;
-		return 0;
-	}
-
-	vf_data->vf_qm_state = QM_READY;
-	hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
-
-	ret = vf_qm_cache_wb(vf_qm);
-	if (ret) {
-		dev_err(dev, "failed to writeback QM Cache!\n");
-		return ret;
-	}
-
 	ret = qm_get_regs(vf_qm, vf_data);
 	if (ret)
 		return -EINVAL;
@@ -536,6 +516,38 @@ static int vf_qm_state_save(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 		return -EINVAL;
 	}
 
+	return 0;
+}
+
+static int vf_qm_state_save(struct hisi_acc_vf_core_device *hisi_acc_vdev,
+			    struct hisi_acc_vf_migration_file *migf)
+{
+	struct acc_vf_data *vf_data = &migf->vf_data;
+	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
+	struct device *dev = &vf_qm->pdev->dev;
+	int ret;
+
+	if (unlikely(qm_wait_dev_not_ready(vf_qm))) {
+		/* Update state and return with match data */
+		vf_data->vf_qm_state = QM_NOT_READY;
+		hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
+		migf->total_length = QM_MATCH_SIZE;
+		return 0;
+	}
+
+	vf_data->vf_qm_state = QM_READY;
+	hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
+
+	ret = vf_qm_cache_wb(vf_qm);
+	if (ret) {
+		dev_err(dev, "failed to writeback QM Cache!\n");
+		return ret;
+	}
+
+	ret = vf_qm_read_data(vf_qm, vf_data);
+	if (ret)
+		return -EINVAL;
+
 	migf->total_length = sizeof(struct acc_vf_data);
 	return 0;
 }
-- 
2.24.0

[PATCH v11 3/4] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

[Longfang Liu]

On the debugfs framework of VFIO, if the CONFIG_VFIO_DEBUGFS 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:

   vfio
    |
    +---<dev_name1>
    |    +---migration
    |        +--state
    |        +--hisi_acc
    |            +--dev_data
    |            +--migf_data
    |            +--cmd_state
    |
    +---<dev_name2>
         +---migration
             +--state
             +--hisi_acc
                 +--dev_data
                 +--migf_data
                 +--cmd_state

dev_data file: read device data that needs to be migrated from the
current device in real time
migf_data file: read the migration data of the last live migration
from the current driver.
cmd_state: used to get the cmd channel state for the device.

+----------------+        +--------------+       +---------------+
| migration dev  |        |   src  dev   |       |   dst  dev    |
+-------+--------+        +------+-------+       +-------+-------+
        |                        |                       |
        |                 +------v-------+       +-------v-------+
        |                 |  saving_migf |       | resuming_migf |
  read  |                 |     file     |       |     file      |
        |                 +------+-------+       +-------+-------+
        |                        |          copy         |
        |                        +------------+----------+
        |                                     |
+-------v--------+                    +-------v--------+
|   data buffer  |                    |   debug_migf   |
+-------+--------+                    +-------+--------+
        |                                     |
   cat  |                                 cat |
+-------v--------+                    +-------v--------+
|   dev_data     |                    |   migf_data    |
+----------------+                    +----------------+

When accessing debugfs, user can obtain the most recent status data
of the device through the "dev_data" file. It can read recent
complete status data of the device. If the current device is being
migrated, it will wait for it to complete.
The data for the last completed migration function will be stored
in debug_migf. Users can read it via "migf_data".

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
---
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 204 ++++++++++++++++++
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h    |   7 +
 2 files changed, 211 insertions(+)

diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index a8c53952d82e..0577d4ddfb34 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -627,15 +627,30 @@ static void hisi_acc_vf_disable_fd(struct hisi_acc_vf_migration_file *migf)
 	mutex_unlock(&migf->lock);
 }
 
+static void hisi_acc_debug_migf_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev,
+	struct hisi_acc_vf_migration_file *src_migf)
+{
+	struct hisi_acc_vf_migration_file *dst_migf = hisi_acc_vdev->debug_migf;
+
+	if (!dst_migf)
+		return;
+
+	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_fds(struct hisi_acc_vf_core_device *hisi_acc_vdev)
 {
 	if (hisi_acc_vdev->resuming_migf) {
+		hisi_acc_debug_migf_copy(hisi_acc_vdev, hisi_acc_vdev->resuming_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_debug_migf_copy(hisi_acc_vdev, hisi_acc_vdev->saving_migf);
 		hisi_acc_vf_disable_fd(hisi_acc_vdev->saving_migf);
 		fput(hisi_acc_vdev->saving_migf->filp);
 		hisi_acc_vdev->saving_migf = NULL;
@@ -1294,6 +1309,140 @@ 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_check(struct seq_file *seq, 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;
+	int ret;
+
+	lockdep_assert_held(&hisi_acc_vdev->open_mutex);
+	/*
+	 * When the device is not opened, the io_base is not mapped.
+	 * The driver cannot perform device read and write operations.
+	 */
+	if (!hisi_acc_vdev->dev_opened) {
+		seq_printf(seq, "device not opened!\n");
+		return -EINVAL;
+	}
+
+	ret = qm_wait_dev_not_ready(vf_qm);
+	if (ret) {
+		seq_printf(seq, "VF device not ready!\n");
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int hisi_acc_vf_debug_cmd(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_qm *vf_qm = &hisi_acc_vdev->vf_qm;
+	u64 value;
+	int ret;
+
+	mutex_lock(&hisi_acc_vdev->open_mutex);
+	ret = hisi_acc_vf_debug_check(seq, vdev);
+	if (ret) {
+		mutex_unlock(&hisi_acc_vdev->open_mutex);
+		return ret;
+	}
+
+	value = readl(vf_qm->io_base + QM_MB_CMD_SEND_BASE);
+	if (value == QM_MB_CMD_NOT_READY) {
+		mutex_unlock(&hisi_acc_vdev->open_mutex);
+		seq_printf(seq, "mailbox cmd channel not ready!\n");
+		return -EINVAL;
+	}
+	mutex_unlock(&hisi_acc_vdev->open_mutex);
+	seq_printf(seq, "mailbox cmd channel ready!\n");
+
+	return 0;
+}
+
+static int hisi_acc_vf_dev_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);
+	size_t vf_data_sz = offsetofend(struct acc_vf_data, padding);
+	struct acc_vf_data *vf_data = NULL;
+	int ret;
+
+	mutex_lock(&hisi_acc_vdev->open_mutex);
+	ret = hisi_acc_vf_debug_check(seq, vdev);
+	if (ret) {
+		mutex_unlock(&hisi_acc_vdev->open_mutex);
+		return ret;
+	}
+
+	mutex_lock(&hisi_acc_vdev->state_mutex);
+	vf_data = kzalloc(sizeof(struct acc_vf_data), GFP_KERNEL);
+	if (!vf_data) {
+		ret = -ENOMEM;
+		goto mutex_release;
+	}
+
+	vf_data->vf_qm_state = hisi_acc_vdev->vf_qm_state;
+	ret = vf_qm_read_data(&hisi_acc_vdev->vf_qm, vf_data);
+	if (ret)
+		goto migf_err;
+
+	seq_hex_dump(seq, "Dev Data:", DUMP_PREFIX_OFFSET, 16, 1,
+			(unsigned char *)vf_data,
+			vf_data_sz, false);
+
+	seq_printf(seq,
+		 "acc device:\n"
+		 "guest driver load: %u\n"
+		 "data size: %lu\n",
+		 hisi_acc_vdev->vf_qm_state,
+		 sizeof(struct acc_vf_data));
+
+migf_err:
+	kfree(vf_data);
+mutex_release:
+	mutex_unlock(&hisi_acc_vdev->open_mutex);
+	mutex_unlock(&hisi_acc_vdev->state_mutex);
+
+	return ret;
+}
+
+static int hisi_acc_vf_migf_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);
+	size_t vf_data_sz = offsetofend(struct acc_vf_data, padding);
+	struct hisi_acc_vf_migration_file *debug_migf = hisi_acc_vdev->debug_migf;
+
+	/* Check whether the live migration operation has been performed */
+	if (debug_migf->total_length < QM_MATCH_SIZE) {
+		seq_printf(seq, "device not migrated!\n");
+		return -EAGAIN;
+	}
+
+	seq_hex_dump(seq, "Mig Data:", DUMP_PREFIX_OFFSET, 16, 1,
+			(unsigned char *)&debug_migf->vf_data,
+			vf_data_sz, false);
+
+	seq_printf(seq,
+		 "acc device:\n"
+		 "guest driver load: %u\n"
+		 "device opened: %d\n"
+		 "migrate data length: %lu\n",
+		 hisi_acc_vdev->vf_qm_state,
+		 hisi_acc_vdev->dev_opened,
+		 debug_migf->total_length);
+
+	return 0;
+}
+
 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);
@@ -1305,12 +1454,16 @@ static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
 		return ret;
 
 	if (core_vdev->mig_ops) {
+		mutex_lock(&hisi_acc_vdev->open_mutex);
 		ret = hisi_acc_vf_qm_init(hisi_acc_vdev);
 		if (ret) {
+			mutex_unlock(&hisi_acc_vdev->open_mutex);
 			vfio_pci_core_disable(vdev);
 			return ret;
 		}
 		hisi_acc_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+		hisi_acc_vdev->dev_opened = true;
+		mutex_unlock(&hisi_acc_vdev->open_mutex);
 	}
 
 	vfio_pci_core_finish_enable(vdev);
@@ -1322,7 +1475,10 @@ static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev)
 	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
 	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
 
+	mutex_lock(&hisi_acc_vdev->open_mutex);
+	hisi_acc_vdev->dev_opened = false;
 	iounmap(vf_qm->io_base);
+	mutex_unlock(&hisi_acc_vdev->open_mutex);
 	vfio_pci_core_close_device(core_vdev);
 }
 
@@ -1342,6 +1498,7 @@ static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
 	hisi_acc_vdev->pf_qm = pf_qm;
 	hisi_acc_vdev->vf_dev = pdev;
 	mutex_init(&hisi_acc_vdev->state_mutex);
+	mutex_init(&hisi_acc_vdev->open_mutex);
 
 	core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY;
 	core_vdev->mig_ops = &hisi_acc_vfio_pci_migrn_state_ops;
@@ -1387,6 +1544,50 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
 	.detach_ioas = vfio_iommufd_physical_detach_ioas,
 };
 
+static void 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() ||
+	    !IS_ENABLED(CONFIG_VFIO_DEBUGFS))
+		return;
+
+	if (vdev->ops != &hisi_acc_vfio_pci_migrn_ops)
+		return;
+
+	vfio_dev_migration = debugfs_lookup("migration", vdev->debug_root);
+	if (!vfio_dev_migration) {
+		dev_err(dev, "failed to lookup migration debugfs file!\n");
+		return;
+	}
+
+	migf = kzalloc(sizeof(struct hisi_acc_vf_migration_file), GFP_KERNEL);
+	if (!migf)
+		return;
+	hisi_acc_vdev->debug_migf = migf;
+
+	vfio_hisi_acc = debugfs_create_dir("hisi_acc", vfio_dev_migration);
+	debugfs_create_devm_seqfile(dev, "dev_data", vfio_hisi_acc,
+				  hisi_acc_vf_dev_read);
+	debugfs_create_devm_seqfile(dev, "migf_data", vfio_hisi_acc,
+				  hisi_acc_vf_migf_read);
+	debugfs_create_devm_seqfile(dev, "cmd_state", vfio_hisi_acc,
+				  hisi_acc_vf_debug_cmd);
+}
+
+static void hisi_acc_vf_debugfs_exit(struct hisi_acc_vf_core_device *hisi_acc_vdev)
+{
+	/* If migrn_ops is not used, debug_migf is NULL */
+	if (hisi_acc_vdev->debug_migf) {
+		kfree(hisi_acc_vdev->debug_migf);
+		hisi_acc_vdev->debug_migf = NULL;
+	}
+}
+
 static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct hisi_acc_vf_core_device *hisi_acc_vdev;
@@ -1413,6 +1614,8 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
 	ret = vfio_pci_core_register_device(&hisi_acc_vdev->core_device);
 	if (ret)
 		goto out_put_vdev;
+
+	hisi_acc_vfio_debug_init(hisi_acc_vdev);
 	return 0;
 
 out_put_vdev:
@@ -1425,6 +1628,7 @@ static void hisi_acc_vfio_pci_remove(struct pci_dev *pdev)
 	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_drvdata(pdev);
 
 	vfio_pci_core_unregister_device(&hisi_acc_vdev->core_device);
+	hisi_acc_vf_debugfs_exit(hisi_acc_vdev);
 	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 5bab46602fad..2a78ffd060c3 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
@@ -32,6 +32,7 @@
 #define QM_SQC_VFT_BASE_MASK_V2		GENMASK(15, 0)
 #define QM_SQC_VFT_NUM_SHIFT_V2		45
 #define QM_SQC_VFT_NUM_MASK_V2		GENMASK(9, 0)
+#define QM_MB_CMD_NOT_READY	0xffffffff
 
 /* RW regs */
 #define QM_REGS_MAX_LEN		7
@@ -99,6 +100,8 @@ struct hisi_acc_vf_migration_file {
 struct hisi_acc_vf_core_device {
 	struct vfio_pci_core_device core_device;
 	u8 match_done;
+	/* To make sure the device is opened */
+	bool dev_opened;
 
 	/* For migration state */
 	struct mutex state_mutex;
@@ -111,5 +114,9 @@ struct hisi_acc_vf_core_device {
 	int vf_id;
 	struct hisi_acc_vf_migration_file *resuming_migf;
 	struct hisi_acc_vf_migration_file *saving_migf;
+
+	/* To save migration data */
+	struct hisi_acc_vf_migration_file *debug_migf;
+	struct mutex open_mutex;
 };
 #endif /* HISI_ACC_VFIO_PCI_H */
-- 
2.24.0

[PATCH v11 4/4] Documentation: add debugfs description for hisi migration

[Longfang Liu]

Add a debugfs document description file to help users understand
how to use the hisilicon accelerator live migration driver's
debugfs.

Update the file paths that need to be maintained in MAINTAINERS

Signed-off-by: Longfang Liu <liulongfang@huawei.com>
Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
---
 .../ABI/testing/debugfs-hisi-migration        | 25 +++++++++++++++++++
 1 file changed, 25 insertions(+)
 create mode 100644 Documentation/ABI/testing/debugfs-hisi-migration

diff --git a/Documentation/ABI/testing/debugfs-hisi-migration b/Documentation/ABI/testing/debugfs-hisi-migration
new file mode 100644
index 000000000000..89e4fde5ec6a
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-hisi-migration
@@ -0,0 +1,25 @@
+What:		/sys/kernel/debug/vfio/<device>/migration/hisi_acc/dev_data
+Date:		Oct 2024
+KernelVersion:  6.12
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	Read the configuration data and some status data
+		required for device live migration. These data include device
+		status data, queue configuration data, some task configuration
+		data and device attribute data. The output format of the data
+		is defined by the live migration driver.
+
+What:		/sys/kernel/debug/vfio/<device>/migration/hisi_acc/migf_data
+Date:		Oct 2024
+KernelVersion:  6.12
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	Read the data from the last completed live migration.
+		This data includes the same device status data as in "dev_data".
+		The migf_data is the dev_data that is migrated.
+
+What:		/sys/kernel/debug/vfio/<device>/migration/hisi_acc/cmd_state
+Date:		Oct 2024
+KernelVersion:  6.12
+Contact:	Longfang Liu <liulongfang@huawei.com>
+Description:	Used to obtain the device command sending and receiving
+		channel status. Returns failure or success logs based on the
+		results.
-- 
2.24.0

Re: [PATCH v11 3/4] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

[Alex Williamson]

On Fri, 25 Oct 2024 17:01:42 +0800
Longfang Liu <liulongfang@huawei.com> wrote:

> On the debugfs framework of VFIO, if the CONFIG_VFIO_DEBUGFS 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:
> 
>    vfio
>     |
>     +---<dev_name1>
>     |    +---migration
>     |        +--state
>     |        +--hisi_acc
>     |            +--dev_data
>     |            +--migf_data
>     |            +--cmd_state
>     |
>     +---<dev_name2>
>          +---migration
>              +--state
>              +--hisi_acc
>                  +--dev_data
>                  +--migf_data
>                  +--cmd_state
> 
> dev_data file: read device data that needs to be migrated from the
> current device in real time
> migf_data file: read the migration data of the last live migration
> from the current driver.
> cmd_state: used to get the cmd channel state for the device.
> 
> +----------------+        +--------------+       +---------------+
> | migration dev  |        |   src  dev   |       |   dst  dev    |
> +-------+--------+        +------+-------+       +-------+-------+
>         |                        |                       |
>         |                 +------v-------+       +-------v-------+
>         |                 |  saving_migf |       | resuming_migf |
>   read  |                 |     file     |       |     file      |
>         |                 +------+-------+       +-------+-------+
>         |                        |          copy         |
>         |                        +------------+----------+
>         |                                     |
> +-------v--------+                    +-------v--------+
> |   data buffer  |                    |   debug_migf   |
> +-------+--------+                    +-------+--------+
>         |                                     |
>    cat  |                                 cat |
> +-------v--------+                    +-------v--------+
> |   dev_data     |                    |   migf_data    |
> +----------------+                    +----------------+
> 
> When accessing debugfs, user can obtain the most recent status data
> of the device through the "dev_data" file. It can read recent
> complete status data of the device. If the current device is being
> migrated, it will wait for it to complete.
> The data for the last completed migration function will be stored
> in debug_migf. Users can read it via "migf_data".
> 
> Signed-off-by: Longfang Liu <liulongfang@huawei.com>
> Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
> ---
>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 204 ++++++++++++++++++
>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h    |   7 +
>  2 files changed, 211 insertions(+)
> 
> diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
> index a8c53952d82e..0577d4ddfb34 100644
> --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
> +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
> @@ -627,15 +627,30 @@ static void hisi_acc_vf_disable_fd(struct hisi_acc_vf_migration_file *migf)
>  	mutex_unlock(&migf->lock);
>  }
>  
> +static void hisi_acc_debug_migf_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev,
> +	struct hisi_acc_vf_migration_file *src_migf)
> +{
> +	struct hisi_acc_vf_migration_file *dst_migf = hisi_acc_vdev->debug_migf;
> +
> +	if (!dst_migf)
> +		return;
> +
> +	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_fds(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>  {
>  	if (hisi_acc_vdev->resuming_migf) {
> +		hisi_acc_debug_migf_copy(hisi_acc_vdev, hisi_acc_vdev->resuming_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_debug_migf_copy(hisi_acc_vdev, hisi_acc_vdev->saving_migf);
>  		hisi_acc_vf_disable_fd(hisi_acc_vdev->saving_migf);
>  		fput(hisi_acc_vdev->saving_migf->filp);
>  		hisi_acc_vdev->saving_migf = NULL;
> @@ -1294,6 +1309,140 @@ 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_check(struct seq_file *seq, 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;
> +	int ret;
> +
> +	lockdep_assert_held(&hisi_acc_vdev->open_mutex);
> +	/*
> +	 * When the device is not opened, the io_base is not mapped.
> +	 * The driver cannot perform device read and write operations.
> +	 */
> +	if (!hisi_acc_vdev->dev_opened) {
> +		seq_printf(seq, "device not opened!\n");
> +		return -EINVAL;
> +	}
> +
> +	ret = qm_wait_dev_not_ready(vf_qm);
> +	if (ret) {
> +		seq_printf(seq, "VF device not ready!\n");
> +		return -EBUSY;
> +	}
> +
> +	return 0;
> +}
> +
> +static int hisi_acc_vf_debug_cmd(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_qm *vf_qm = &hisi_acc_vdev->vf_qm;
> +	u64 value;
> +	int ret;
> +
> +	mutex_lock(&hisi_acc_vdev->open_mutex);
> +	ret = hisi_acc_vf_debug_check(seq, vdev);
> +	if (ret) {
> +		mutex_unlock(&hisi_acc_vdev->open_mutex);
> +		return ret;
> +	}
> +
> +	value = readl(vf_qm->io_base + QM_MB_CMD_SEND_BASE);
> +	if (value == QM_MB_CMD_NOT_READY) {
> +		mutex_unlock(&hisi_acc_vdev->open_mutex);
> +		seq_printf(seq, "mailbox cmd channel not ready!\n");
> +		return -EINVAL;
> +	}
> +	mutex_unlock(&hisi_acc_vdev->open_mutex);
> +	seq_printf(seq, "mailbox cmd channel ready!\n");
> +
> +	return 0;
> +}
> +
> +static int hisi_acc_vf_dev_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);
> +	size_t vf_data_sz = offsetofend(struct acc_vf_data, padding);
> +	struct acc_vf_data *vf_data = NULL;

Nit, this initialization is unnecessary.

> +	int ret;
> +
> +	mutex_lock(&hisi_acc_vdev->open_mutex);
> +	ret = hisi_acc_vf_debug_check(seq, vdev);
> +	if (ret) {
> +		mutex_unlock(&hisi_acc_vdev->open_mutex);
> +		return ret;
> +	}
> +
> +	mutex_lock(&hisi_acc_vdev->state_mutex);
> +	vf_data = kzalloc(sizeof(struct acc_vf_data), GFP_KERNEL);
> +	if (!vf_data) {
> +		ret = -ENOMEM;
> +		goto mutex_release;
> +	}
> +
> +	vf_data->vf_qm_state = hisi_acc_vdev->vf_qm_state;
> +	ret = vf_qm_read_data(&hisi_acc_vdev->vf_qm, vf_data);
> +	if (ret)
> +		goto migf_err;
> +
> +	seq_hex_dump(seq, "Dev Data:", DUMP_PREFIX_OFFSET, 16, 1,
> +			(unsigned char *)vf_data,

Casting to (const void *) would match the prototype.  This line should
also wrap to just inside the opening parenthesis of the previous line, 2
tabs, 5 spaces.

> +			vf_data_sz, false);
> +
> +	seq_printf(seq,
> +		 "acc device:\n"
> +		 "guest driver load: %u\n"
> +		 "data size: %lu\n",
> +		 hisi_acc_vdev->vf_qm_state,
> +		 sizeof(struct acc_vf_data));

Same here and throughout, wrap aligned to the relevant parenthesis.

I know you've described vf_qm_state as indicating whether or not the
guest driver is loaded, but I still can't figure out how to discern
that from the code.  It's largely only set based on the return value of
qm_wait_dev_not_ready(), which tests QM_VF_STATE, and describes the
function as testing if the device is ready.  Improved comments would
help future reviews.

What's the purpose of the "acc device:" prefix?

> +
> +migf_err:
> +	kfree(vf_data);
> +mutex_release:
> +	mutex_unlock(&hisi_acc_vdev->open_mutex);
> +	mutex_unlock(&hisi_acc_vdev->state_mutex);

Locks should be released in the reverse order they were acquired.

> +
> +	return ret;
> +}
> +
> +static int hisi_acc_vf_migf_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);
> +	size_t vf_data_sz = offsetofend(struct acc_vf_data, padding);
> +	struct hisi_acc_vf_migration_file *debug_migf = hisi_acc_vdev->debug_migf;
> +
> +	/* Check whether the live migration operation has been performed */
> +	if (debug_migf->total_length < QM_MATCH_SIZE) {
> +		seq_printf(seq, "device not migrated!\n");
> +		return -EAGAIN;
> +	}
> +
> +	seq_hex_dump(seq, "Mig Data:", DUMP_PREFIX_OFFSET, 16, 1,
> +			(unsigned char *)&debug_migf->vf_data,
> +			vf_data_sz, false);
> +
> +	seq_printf(seq,
> +		 "acc device:\n"
> +		 "guest driver load: %u\n"
> +		 "device opened: %d\n"
> +		 "migrate data length: %lu\n",
> +		 hisi_acc_vdev->vf_qm_state,
> +		 hisi_acc_vdev->dev_opened,
> +		 debug_migf->total_length);

This debugfs entry is described as returning the data from the last
migration, but vf_qm_state and dev_opened are relative to the current
device/guest driver state.  Both seem to have no relevance to the data
in debug_migf.

> +
> +	return 0;
> +}
> +
>  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);
> @@ -1305,12 +1454,16 @@ static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
>  		return ret;
>  
>  	if (core_vdev->mig_ops) {
> +		mutex_lock(&hisi_acc_vdev->open_mutex);
>  		ret = hisi_acc_vf_qm_init(hisi_acc_vdev);
>  		if (ret) {
> +			mutex_unlock(&hisi_acc_vdev->open_mutex);
>  			vfio_pci_core_disable(vdev);
>  			return ret;
>  		}
>  		hisi_acc_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
> +		hisi_acc_vdev->dev_opened = true;
> +		mutex_unlock(&hisi_acc_vdev->open_mutex);
>  	}
>  
>  	vfio_pci_core_finish_enable(vdev);
> @@ -1322,7 +1475,10 @@ static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev)
>  	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
>  	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
>  
> +	mutex_lock(&hisi_acc_vdev->open_mutex);
> +	hisi_acc_vdev->dev_opened = false;
>  	iounmap(vf_qm->io_base);
> +	mutex_unlock(&hisi_acc_vdev->open_mutex);
>  	vfio_pci_core_close_device(core_vdev);
>  }
>  
> @@ -1342,6 +1498,7 @@ static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
>  	hisi_acc_vdev->pf_qm = pf_qm;
>  	hisi_acc_vdev->vf_dev = pdev;
>  	mutex_init(&hisi_acc_vdev->state_mutex);
> +	mutex_init(&hisi_acc_vdev->open_mutex);
>  
>  	core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY;
>  	core_vdev->mig_ops = &hisi_acc_vfio_pci_migrn_state_ops;
> @@ -1387,6 +1544,50 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
>  	.detach_ioas = vfio_iommufd_physical_detach_ioas,
>  };
>  
> +static void 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() ||
> +	    !IS_ENABLED(CONFIG_VFIO_DEBUGFS))
> +		return;
> +
> +	if (vdev->ops != &hisi_acc_vfio_pci_migrn_ops)
> +		return;
> +
> +	vfio_dev_migration = debugfs_lookup("migration", vdev->debug_root);
> +	if (!vfio_dev_migration) {
> +		dev_err(dev, "failed to lookup migration debugfs file!\n");
> +		return;
> +	}
> +
> +	migf = kzalloc(sizeof(struct hisi_acc_vf_migration_file), GFP_KERNEL);
> +	if (!migf)
> +		return;
> +	hisi_acc_vdev->debug_migf = migf;
> +
> +	vfio_hisi_acc = debugfs_create_dir("hisi_acc", vfio_dev_migration);
> +	debugfs_create_devm_seqfile(dev, "dev_data", vfio_hisi_acc,
> +				  hisi_acc_vf_dev_read);
> +	debugfs_create_devm_seqfile(dev, "migf_data", vfio_hisi_acc,
> +				  hisi_acc_vf_migf_read);
> +	debugfs_create_devm_seqfile(dev, "cmd_state", vfio_hisi_acc,
> +				  hisi_acc_vf_debug_cmd);
> +}
> +
> +static void hisi_acc_vf_debugfs_exit(struct hisi_acc_vf_core_device *hisi_acc_vdev)
> +{
> +	/* If migrn_ops is not used, debug_migf is NULL */
> +	if (hisi_acc_vdev->debug_migf) {

This test is unnecessary, kfree(NULL) is valid.

> +		kfree(hisi_acc_vdev->debug_migf);
> +		hisi_acc_vdev->debug_migf = NULL;
> +	}
> +}
> +
>  static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
>  {
>  	struct hisi_acc_vf_core_device *hisi_acc_vdev;
> @@ -1413,6 +1614,8 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
>  	ret = vfio_pci_core_register_device(&hisi_acc_vdev->core_device);
>  	if (ret)
>  		goto out_put_vdev;
> +
> +	hisi_acc_vfio_debug_init(hisi_acc_vdev);
>  	return 0;
>  
>  out_put_vdev:
> @@ -1425,6 +1628,7 @@ static void hisi_acc_vfio_pci_remove(struct pci_dev *pdev)
>  	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_drvdata(pdev);
>  
>  	vfio_pci_core_unregister_device(&hisi_acc_vdev->core_device);
> +	hisi_acc_vf_debugfs_exit(hisi_acc_vdev);
>  	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 5bab46602fad..2a78ffd060c3 100644
> --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
> +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
> @@ -32,6 +32,7 @@
>  #define QM_SQC_VFT_BASE_MASK_V2		GENMASK(15, 0)
>  #define QM_SQC_VFT_NUM_SHIFT_V2		45
>  #define QM_SQC_VFT_NUM_MASK_V2		GENMASK(9, 0)
> +#define QM_MB_CMD_NOT_READY	0xffffffff
>  
>  /* RW regs */
>  #define QM_REGS_MAX_LEN		7
> @@ -99,6 +100,8 @@ struct hisi_acc_vf_migration_file {
>  struct hisi_acc_vf_core_device {
>  	struct vfio_pci_core_device core_device;
>  	u8 match_done;
> +	/* To make sure the device is opened */

We can infer that from the field name, it would be more useful to
comment that io_base is only valid when dev_opened, which is protected
by open_mutex.

> +	bool dev_opened;

Seems like open_mutex would fit just as well here and have better
proximity to the data it protects.

>  
>  	/* For migration state */
>  	struct mutex state_mutex;
> @@ -111,5 +114,9 @@ struct hisi_acc_vf_core_device {
>  	int vf_id;
>  	struct hisi_acc_vf_migration_file *resuming_migf;
>  	struct hisi_acc_vf_migration_file *saving_migf;
> +
> +	/* To save migration data */

Clearly.  Describing it as an extra buffer for reporting migration data
through debugfs might be more useful.  Thanks,

Alex

> +	struct hisi_acc_vf_migration_file *debug_migf;
> +	struct mutex open_mutex;
>  };
>  #endif /* HISI_ACC_VFIO_PCI_H */

Re: [PATCH v11 4/4] Documentation: add debugfs description for hisi migration

[Alex Williamson]

On Fri, 25 Oct 2024 17:01:43 +0800
Longfang Liu <liulongfang@huawei.com> wrote:

> Add a debugfs document description file to help users understand
> how to use the hisilicon accelerator live migration driver's
> debugfs.
> 
> Update the file paths that need to be maintained in MAINTAINERS
> 
> Signed-off-by: Longfang Liu <liulongfang@huawei.com>
> Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
> ---
>  .../ABI/testing/debugfs-hisi-migration        | 25 +++++++++++++++++++
>  1 file changed, 25 insertions(+)
>  create mode 100644 Documentation/ABI/testing/debugfs-hisi-migration
> 
> diff --git a/Documentation/ABI/testing/debugfs-hisi-migration b/Documentation/ABI/testing/debugfs-hisi-migration
> new file mode 100644
> index 000000000000..89e4fde5ec6a
> --- /dev/null
> +++ b/Documentation/ABI/testing/debugfs-hisi-migration
> @@ -0,0 +1,25 @@
> +What:		/sys/kernel/debug/vfio/<device>/migration/hisi_acc/dev_data
> +Date:		Oct 2024
> +KernelVersion:  6.12

We're currently targeting v6.13, which is likely Jan 2025.  Thanks,

Alex

> +Contact:	Longfang Liu <liulongfang@huawei.com>
> +Description:	Read the configuration data and some status data
> +		required for device live migration. These data include device
> +		status data, queue configuration data, some task configuration
> +		data and device attribute data. The output format of the data
> +		is defined by the live migration driver.
> +
> +What:		/sys/kernel/debug/vfio/<device>/migration/hisi_acc/migf_data
> +Date:		Oct 2024
> +KernelVersion:  6.12
> +Contact:	Longfang Liu <liulongfang@huawei.com>
> +Description:	Read the data from the last completed live migration.
> +		This data includes the same device status data as in "dev_data".
> +		The migf_data is the dev_data that is migrated.
> +
> +What:		/sys/kernel/debug/vfio/<device>/migration/hisi_acc/cmd_state
> +Date:		Oct 2024
> +KernelVersion:  6.12
> +Contact:	Longfang Liu <liulongfang@huawei.com>
> +Description:	Used to obtain the device command sending and receiving
> +		channel status. Returns failure or success logs based on the
> +		results.

Re: [PATCH v11 3/4] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

[liulongfang]

On 2024/11/1 6:04, Alex Williamson wrote:
> On Fri, 25 Oct 2024 17:01:42 +0800
> Longfang Liu <liulongfang@huawei.com> wrote:
> 
>> On the debugfs framework of VFIO, if the CONFIG_VFIO_DEBUGFS 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:
>>
>>    vfio
>>     |
>>     +---<dev_name1>
>>     |    +---migration
>>     |        +--state
>>     |        +--hisi_acc
>>     |            +--dev_data
>>     |            +--migf_data
>>     |            +--cmd_state
>>     |
>>     +---<dev_name2>
>>          +---migration
>>              +--state
>>              +--hisi_acc
>>                  +--dev_data
>>                  +--migf_data
>>                  +--cmd_state
>>
>> dev_data file: read device data that needs to be migrated from the
>> current device in real time
>> migf_data file: read the migration data of the last live migration
>> from the current driver.
>> cmd_state: used to get the cmd channel state for the device.
>>
>> +----------------+        +--------------+       +---------------+
>> | migration dev  |        |   src  dev   |       |   dst  dev    |
>> +-------+--------+        +------+-------+       +-------+-------+
>>         |                        |                       |
>>         |                 +------v-------+       +-------v-------+
>>         |                 |  saving_migf |       | resuming_migf |
>>   read  |                 |     file     |       |     file      |
>>         |                 +------+-------+       +-------+-------+
>>         |                        |          copy         |
>>         |                        +------------+----------+
>>         |                                     |
>> +-------v--------+                    +-------v--------+
>> |   data buffer  |                    |   debug_migf   |
>> +-------+--------+                    +-------+--------+
>>         |                                     |
>>    cat  |                                 cat |
>> +-------v--------+                    +-------v--------+
>> |   dev_data     |                    |   migf_data    |
>> +----------------+                    +----------------+
>>
>> When accessing debugfs, user can obtain the most recent status data
>> of the device through the "dev_data" file. It can read recent
>> complete status data of the device. If the current device is being
>> migrated, it will wait for it to complete.
>> The data for the last completed migration function will be stored
>> in debug_migf. Users can read it via "migf_data".
>>
>> Signed-off-by: Longfang Liu <liulongfang@huawei.com>
>> Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
>> ---
>>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 204 ++++++++++++++++++
>>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h    |   7 +
>>  2 files changed, 211 insertions(+)
>>
>> diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
>> index a8c53952d82e..0577d4ddfb34 100644
>> --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
>> +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
>> @@ -627,15 +627,30 @@ static void hisi_acc_vf_disable_fd(struct hisi_acc_vf_migration_file *migf)
>>  	mutex_unlock(&migf->lock);
>>  }
>>  
>> +static void hisi_acc_debug_migf_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev,
>> +	struct hisi_acc_vf_migration_file *src_migf)
>> +{
>> +	struct hisi_acc_vf_migration_file *dst_migf = hisi_acc_vdev->debug_migf;
>> +
>> +	if (!dst_migf)
>> +		return;
>> +
>> +	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_fds(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>>  {
>>  	if (hisi_acc_vdev->resuming_migf) {
>> +		hisi_acc_debug_migf_copy(hisi_acc_vdev, hisi_acc_vdev->resuming_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_debug_migf_copy(hisi_acc_vdev, hisi_acc_vdev->saving_migf);
>>  		hisi_acc_vf_disable_fd(hisi_acc_vdev->saving_migf);
>>  		fput(hisi_acc_vdev->saving_migf->filp);
>>  		hisi_acc_vdev->saving_migf = NULL;
>> @@ -1294,6 +1309,140 @@ 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_check(struct seq_file *seq, 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;
>> +	int ret;
>> +
>> +	lockdep_assert_held(&hisi_acc_vdev->open_mutex);
>> +	/*
>> +	 * When the device is not opened, the io_base is not mapped.
>> +	 * The driver cannot perform device read and write operations.
>> +	 */
>> +	if (!hisi_acc_vdev->dev_opened) {
>> +		seq_printf(seq, "device not opened!\n");
>> +		return -EINVAL;
>> +	}
>> +
>> +	ret = qm_wait_dev_not_ready(vf_qm);
>> +	if (ret) {
>> +		seq_printf(seq, "VF device not ready!\n");
>> +		return -EBUSY;
>> +	}
>> +
>> +	return 0;
>> +}
>> +
>> +static int hisi_acc_vf_debug_cmd(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_qm *vf_qm = &hisi_acc_vdev->vf_qm;
>> +	u64 value;
>> +	int ret;
>> +
>> +	mutex_lock(&hisi_acc_vdev->open_mutex);
>> +	ret = hisi_acc_vf_debug_check(seq, vdev);
>> +	if (ret) {
>> +		mutex_unlock(&hisi_acc_vdev->open_mutex);
>> +		return ret;
>> +	}
>> +
>> +	value = readl(vf_qm->io_base + QM_MB_CMD_SEND_BASE);
>> +	if (value == QM_MB_CMD_NOT_READY) {
>> +		mutex_unlock(&hisi_acc_vdev->open_mutex);
>> +		seq_printf(seq, "mailbox cmd channel not ready!\n");
>> +		return -EINVAL;
>> +	}
>> +	mutex_unlock(&hisi_acc_vdev->open_mutex);
>> +	seq_printf(seq, "mailbox cmd channel ready!\n");
>> +
>> +	return 0;
>> +}
>> +
>> +static int hisi_acc_vf_dev_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);
>> +	size_t vf_data_sz = offsetofend(struct acc_vf_data, padding);
>> +	struct acc_vf_data *vf_data = NULL;
> 
> Nit, this initialization is unnecessary.
>

OK, delete it in next version.

>> +	int ret;
>> +
>> +	mutex_lock(&hisi_acc_vdev->open_mutex);
>> +	ret = hisi_acc_vf_debug_check(seq, vdev);
>> +	if (ret) {
>> +		mutex_unlock(&hisi_acc_vdev->open_mutex);
>> +		return ret;
>> +	}
>> +
>> +	mutex_lock(&hisi_acc_vdev->state_mutex);
>> +	vf_data = kzalloc(sizeof(struct acc_vf_data), GFP_KERNEL);
>> +	if (!vf_data) {
>> +		ret = -ENOMEM;
>> +		goto mutex_release;
>> +	}
>> +
>> +	vf_data->vf_qm_state = hisi_acc_vdev->vf_qm_state;
>> +	ret = vf_qm_read_data(&hisi_acc_vdev->vf_qm, vf_data);
>> +	if (ret)
>> +		goto migf_err;
>> +
>> +	seq_hex_dump(seq, "Dev Data:", DUMP_PREFIX_OFFSET, 16, 1,
>> +			(unsigned char *)vf_data,
> 
> Casting to (const void *) would match the prototype.  This line should
> also wrap to just inside the opening parenthesis of the previous line, 2
> tabs, 5 spaces.
>

OK, I will adjust it in the next version.

>> +			vf_data_sz, false);
>> +
>> +	seq_printf(seq,
>> +		 "acc device:\n"
>> +		 "guest driver load: %u\n"
>> +		 "data size: %lu\n",
>> +		 hisi_acc_vdev->vf_qm_state,
>> +		 sizeof(struct acc_vf_data));
> 
> Same here and throughout, wrap aligned to the relevant parenthesis.
>

OK.

> I know you've described vf_qm_state as indicating whether or not the
> guest driver is loaded, but I still can't figure out how to discern
> that from the code.  It's largely only set based on the return value of
> qm_wait_dev_not_ready(), which tests QM_VF_STATE, and describes the
> function as testing if the device is ready.  Improved comments would
> help future reviews.
>

This QM_VF_STATE register will be written to QM_READY when the acc device
driver is loaded, and QM_NOT_READY will be written after the device
driver is unloaded.

I will add a comment where vf_qm_state is declared.

> What's the purpose of the "acc device:" prefix?
>

OK, it can be deleted.

>> +
>> +migf_err:
>> +	kfree(vf_data);
>> +mutex_release:
>> +	mutex_unlock(&hisi_acc_vdev->open_mutex);
>> +	mutex_unlock(&hisi_acc_vdev->state_mutex);
> 
> Locks should be released in the reverse order they were acquired.
>

OK.

>> +
>> +	return ret;
>> +}
>> +
>> +static int hisi_acc_vf_migf_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);
>> +	size_t vf_data_sz = offsetofend(struct acc_vf_data, padding);
>> +	struct hisi_acc_vf_migration_file *debug_migf = hisi_acc_vdev->debug_migf;
>> +
>> +	/* Check whether the live migration operation has been performed */
>> +	if (debug_migf->total_length < QM_MATCH_SIZE) {
>> +		seq_printf(seq, "device not migrated!\n");
>> +		return -EAGAIN;
>> +	}
>> +
>> +	seq_hex_dump(seq, "Mig Data:", DUMP_PREFIX_OFFSET, 16, 1,
>> +			(unsigned char *)&debug_migf->vf_data,
>> +			vf_data_sz, false);
>> +
>> +	seq_printf(seq,
>> +		 "acc device:\n"
>> +		 "guest driver load: %u\n"
>> +		 "device opened: %d\n"
>> +		 "migrate data length: %lu\n",
>> +		 hisi_acc_vdev->vf_qm_state,
>> +		 hisi_acc_vdev->dev_opened,
>> +		 debug_migf->total_length);
> 
> This debugfs entry is described as returning the data from the last
> migration, but vf_qm_state and dev_opened are relative to the current
> device/guest driver state.  Both seem to have no relevance to the data
> in debug_migf.
>

The benefit of dev_opened retention is that user can obtain the device status
during the cat migf_data operation.

And vf_qm_state does need to be retained.
Because adding a driver or not adding a driver to the Guest OS has a great impact
on the results of live migration, it is a key factor. It has a great impact on
the success or failure of live migration.

When adding a driver, live migration will read device status data, and data will
be written back to device after the migration is completed.
When no driver is added, live migration only executes a process. It does not
perform data reading and data recovery operations.

>> +
>> +	return 0;
>> +}
>> +
>>  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);
>> @@ -1305,12 +1454,16 @@ static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
>>  		return ret;
>>  
>>  	if (core_vdev->mig_ops) {
>> +		mutex_lock(&hisi_acc_vdev->open_mutex);
>>  		ret = hisi_acc_vf_qm_init(hisi_acc_vdev);
>>  		if (ret) {
>> +			mutex_unlock(&hisi_acc_vdev->open_mutex);
>>  			vfio_pci_core_disable(vdev);
>>  			return ret;
>>  		}
>>  		hisi_acc_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
>> +		hisi_acc_vdev->dev_opened = true;
>> +		mutex_unlock(&hisi_acc_vdev->open_mutex);
>>  	}
>>  
>>  	vfio_pci_core_finish_enable(vdev);
>> @@ -1322,7 +1475,10 @@ static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev)
>>  	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
>>  	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
>>  
>> +	mutex_lock(&hisi_acc_vdev->open_mutex);
>> +	hisi_acc_vdev->dev_opened = false;
>>  	iounmap(vf_qm->io_base);
>> +	mutex_unlock(&hisi_acc_vdev->open_mutex);
>>  	vfio_pci_core_close_device(core_vdev);
>>  }
>>  
>> @@ -1342,6 +1498,7 @@ static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
>>  	hisi_acc_vdev->pf_qm = pf_qm;
>>  	hisi_acc_vdev->vf_dev = pdev;
>>  	mutex_init(&hisi_acc_vdev->state_mutex);
>> +	mutex_init(&hisi_acc_vdev->open_mutex);
>>  
>>  	core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY;
>>  	core_vdev->mig_ops = &hisi_acc_vfio_pci_migrn_state_ops;
>> @@ -1387,6 +1544,50 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
>>  	.detach_ioas = vfio_iommufd_physical_detach_ioas,
>>  };
>>  
>> +static void 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() ||
>> +	    !IS_ENABLED(CONFIG_VFIO_DEBUGFS))
>> +		return;
>> +
>> +	if (vdev->ops != &hisi_acc_vfio_pci_migrn_ops)
>> +		return;
>> +
>> +	vfio_dev_migration = debugfs_lookup("migration", vdev->debug_root);
>> +	if (!vfio_dev_migration) {
>> +		dev_err(dev, "failed to lookup migration debugfs file!\n");
>> +		return;
>> +	}
>> +
>> +	migf = kzalloc(sizeof(struct hisi_acc_vf_migration_file), GFP_KERNEL);
>> +	if (!migf)
>> +		return;
>> +	hisi_acc_vdev->debug_migf = migf;
>> +
>> +	vfio_hisi_acc = debugfs_create_dir("hisi_acc", vfio_dev_migration);
>> +	debugfs_create_devm_seqfile(dev, "dev_data", vfio_hisi_acc,
>> +				  hisi_acc_vf_dev_read);
>> +	debugfs_create_devm_seqfile(dev, "migf_data", vfio_hisi_acc,
>> +				  hisi_acc_vf_migf_read);
>> +	debugfs_create_devm_seqfile(dev, "cmd_state", vfio_hisi_acc,
>> +				  hisi_acc_vf_debug_cmd);
>> +}
>> +
>> +static void hisi_acc_vf_debugfs_exit(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>> +{
>> +	/* If migrn_ops is not used, debug_migf is NULL */
>> +	if (hisi_acc_vdev->debug_migf) {
> 
> This test is unnecessary, kfree(NULL) is valid.
>

OK, It will be deleted. Comments will also be updated.

>> +		kfree(hisi_acc_vdev->debug_migf);
>> +		hisi_acc_vdev->debug_migf = NULL;
>> +	}
>> +}
>> +
>>  static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
>>  {
>>  	struct hisi_acc_vf_core_device *hisi_acc_vdev;
>> @@ -1413,6 +1614,8 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
>>  	ret = vfio_pci_core_register_device(&hisi_acc_vdev->core_device);
>>  	if (ret)
>>  		goto out_put_vdev;
>> +
>> +	hisi_acc_vfio_debug_init(hisi_acc_vdev);
>>  	return 0;
>>  
>>  out_put_vdev:
>> @@ -1425,6 +1628,7 @@ static void hisi_acc_vfio_pci_remove(struct pci_dev *pdev)
>>  	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_drvdata(pdev);
>>  
>>  	vfio_pci_core_unregister_device(&hisi_acc_vdev->core_device);
>> +	hisi_acc_vf_debugfs_exit(hisi_acc_vdev);
>>  	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 5bab46602fad..2a78ffd060c3 100644
>> --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
>> +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
>> @@ -32,6 +32,7 @@
>>  #define QM_SQC_VFT_BASE_MASK_V2		GENMASK(15, 0)
>>  #define QM_SQC_VFT_NUM_SHIFT_V2		45
>>  #define QM_SQC_VFT_NUM_MASK_V2		GENMASK(9, 0)
>> +#define QM_MB_CMD_NOT_READY	0xffffffff
>>  
>>  /* RW regs */
>>  #define QM_REGS_MAX_LEN		7
>> @@ -99,6 +100,8 @@ struct hisi_acc_vf_migration_file {
>>  struct hisi_acc_vf_core_device {
>>  	struct vfio_pci_core_device core_device;
>>  	u8 match_done;
>> +	/* To make sure the device is opened */
> 
> We can infer that from the field name, it would be more useful to
> comment that io_base is only valid when dev_opened, which is protected
> by open_mutex.
>

OK, the comments will be updated according to your instructions.

>> +	bool dev_opened;
> 
> Seems like open_mutex would fit just as well here and have better
> proximity to the data it protects.
> 

OK, I'm going to move it over here.

>>  
>>  	/* For migration state */
>>  	struct mutex state_mutex;
>> @@ -111,5 +114,9 @@ struct hisi_acc_vf_core_device {
>>  	int vf_id;
>>  	struct hisi_acc_vf_migration_file *resuming_migf;
>>  	struct hisi_acc_vf_migration_file *saving_migf;
>> +
>> +	/* To save migration data */
> 
> Clearly.  Describing it as an extra buffer for reporting migration data
> through debugfs might be more useful.  Thanks,
>

OK, the comments will be updated according to your instructions.

Thanks.
Longfang.

> Alex
> 
>> +	struct hisi_acc_vf_migration_file *debug_migf;
>> +	struct mutex open_mutex;
>>  };
>>  #endif /* HISI_ACC_VFIO_PCI_H */
> 
> 
> .
> 

Re: [PATCH v11 4/4] Documentation: add debugfs description for hisi migration

[liulongfang]

On 2024/11/1 6:09, Alex Williamson wrote:
> On Fri, 25 Oct 2024 17:01:43 +0800
> Longfang Liu <liulongfang@huawei.com> wrote:
> 
>> Add a debugfs document description file to help users understand
>> how to use the hisilicon accelerator live migration driver's
>> debugfs.
>>
>> Update the file paths that need to be maintained in MAINTAINERS
>>
>> Signed-off-by: Longfang Liu <liulongfang@huawei.com>
>> Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
>> ---
>>  .../ABI/testing/debugfs-hisi-migration        | 25 +++++++++++++++++++
>>  1 file changed, 25 insertions(+)
>>  create mode 100644 Documentation/ABI/testing/debugfs-hisi-migration
>>
>> diff --git a/Documentation/ABI/testing/debugfs-hisi-migration b/Documentation/ABI/testing/debugfs-hisi-migration
>> new file mode 100644
>> index 000000000000..89e4fde5ec6a
>> --- /dev/null
>> +++ b/Documentation/ABI/testing/debugfs-hisi-migration
>> @@ -0,0 +1,25 @@
>> +What:		/sys/kernel/debug/vfio/<device>/migration/hisi_acc/dev_data
>> +Date:		Oct 2024
>> +KernelVersion:  6.12
> 
> We're currently targeting v6.13, which is likely Jan 2025.  Thanks,
>

OK!

Thanks.
Longfang.

> Alex
> 
>> +Contact:	Longfang Liu <liulongfang@huawei.com>
>> +Description:	Read the configuration data and some status data
>> +		required for device live migration. These data include device
>> +		status data, queue configuration data, some task configuration
>> +		data and device attribute data. The output format of the data
>> +		is defined by the live migration driver.
>> +
>> +What:		/sys/kernel/debug/vfio/<device>/migration/hisi_acc/migf_data
>> +Date:		Oct 2024
>> +KernelVersion:  6.12
>> +Contact:	Longfang Liu <liulongfang@huawei.com>
>> +Description:	Read the data from the last completed live migration.
>> +		This data includes the same device status data as in "dev_data".
>> +		The migf_data is the dev_data that is migrated.
>> +
>> +What:		/sys/kernel/debug/vfio/<device>/migration/hisi_acc/cmd_state
>> +Date:		Oct 2024
>> +KernelVersion:  6.12
>> +Contact:	Longfang Liu <liulongfang@huawei.com>
>> +Description:	Used to obtain the device command sending and receiving
>> +		channel status. Returns failure or success logs based on the
>> +		results.
> 
> 
> .
> 

Re: [PATCH v11 3/4] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

[liulongfang]

On 2024/11/4 15:54, liulongfang wrote:
> On 2024/11/1 6:04, Alex Williamson wrote:
>> On Fri, 25 Oct 2024 17:01:42 +0800
>> Longfang Liu <liulongfang@huawei.com> wrote:
>>
>>> On the debugfs framework of VFIO, if the CONFIG_VFIO_DEBUGFS 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:
>>>
>>>    vfio
>>>     |
>>>     +---<dev_name1>
>>>     |    +---migration
>>>     |        +--state
>>>     |        +--hisi_acc
>>>     |            +--dev_data
>>>     |            +--migf_data
>>>     |            +--cmd_state
>>>     |
>>>     +---<dev_name2>
>>>          +---migration
>>>              +--state
>>>              +--hisi_acc
>>>                  +--dev_data
>>>                  +--migf_data
>>>                  +--cmd_state
>>>
>>> dev_data file: read device data that needs to be migrated from the
>>> current device in real time
>>> migf_data file: read the migration data of the last live migration
>>> from the current driver.
>>> cmd_state: used to get the cmd channel state for the device.
>>>
>>> +----------------+        +--------------+       +---------------+
>>> | migration dev  |        |   src  dev   |       |   dst  dev    |
>>> +-------+--------+        +------+-------+       +-------+-------+
>>>         |                        |                       |
>>>         |                 +------v-------+       +-------v-------+
>>>         |                 |  saving_migf |       | resuming_migf |
>>>   read  |                 |     file     |       |     file      |
>>>         |                 +------+-------+       +-------+-------+
>>>         |                        |          copy         |
>>>         |                        +------------+----------+
>>>         |                                     |
>>> +-------v--------+                    +-------v--------+
>>> |   data buffer  |                    |   debug_migf   |
>>> +-------+--------+                    +-------+--------+
>>>         |                                     |
>>>    cat  |                                 cat |
>>> +-------v--------+                    +-------v--------+
>>> |   dev_data     |                    |   migf_data    |
>>> +----------------+                    +----------------+
>>>
>>> When accessing debugfs, user can obtain the most recent status data
>>> of the device through the "dev_data" file. It can read recent
>>> complete status data of the device. If the current device is being
>>> migrated, it will wait for it to complete.
>>> The data for the last completed migration function will be stored
>>> in debug_migf. Users can read it via "migf_data".
>>>
>>> Signed-off-by: Longfang Liu <liulongfang@huawei.com>
>>> Reviewed-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
>>> ---
>>>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 204 ++++++++++++++++++
>>>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h    |   7 +
>>>  2 files changed, 211 insertions(+)
>>>
>>> diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
>>> index a8c53952d82e..0577d4ddfb34 100644
>>> --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
>>> +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
>>> @@ -627,15 +627,30 @@ static void hisi_acc_vf_disable_fd(struct hisi_acc_vf_migration_file *migf)
>>>  	mutex_unlock(&migf->lock);
>>>  }
>>>  
>>> +static void hisi_acc_debug_migf_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev,
>>> +	struct hisi_acc_vf_migration_file *src_migf)
>>> +{
>>> +	struct hisi_acc_vf_migration_file *dst_migf = hisi_acc_vdev->debug_migf;
>>> +
>>> +	if (!dst_migf)
>>> +		return;
>>> +
>>> +	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_fds(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>>>  {
>>>  	if (hisi_acc_vdev->resuming_migf) {
>>> +		hisi_acc_debug_migf_copy(hisi_acc_vdev, hisi_acc_vdev->resuming_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_debug_migf_copy(hisi_acc_vdev, hisi_acc_vdev->saving_migf);
>>>  		hisi_acc_vf_disable_fd(hisi_acc_vdev->saving_migf);
>>>  		fput(hisi_acc_vdev->saving_migf->filp);
>>>  		hisi_acc_vdev->saving_migf = NULL;
>>> @@ -1294,6 +1309,140 @@ 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_check(struct seq_file *seq, 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;
>>> +	int ret;
>>> +
>>> +	lockdep_assert_held(&hisi_acc_vdev->open_mutex);
>>> +	/*
>>> +	 * When the device is not opened, the io_base is not mapped.
>>> +	 * The driver cannot perform device read and write operations.
>>> +	 */
>>> +	if (!hisi_acc_vdev->dev_opened) {
>>> +		seq_printf(seq, "device not opened!\n");
>>> +		return -EINVAL;
>>> +	}
>>> +
>>> +	ret = qm_wait_dev_not_ready(vf_qm);
>>> +	if (ret) {
>>> +		seq_printf(seq, "VF device not ready!\n");
>>> +		return -EBUSY;
>>> +	}
>>> +
>>> +	return 0;
>>> +}
>>> +
>>> +static int hisi_acc_vf_debug_cmd(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_qm *vf_qm = &hisi_acc_vdev->vf_qm;
>>> +	u64 value;
>>> +	int ret;
>>> +
>>> +	mutex_lock(&hisi_acc_vdev->open_mutex);
>>> +	ret = hisi_acc_vf_debug_check(seq, vdev);
>>> +	if (ret) {
>>> +		mutex_unlock(&hisi_acc_vdev->open_mutex);
>>> +		return ret;
>>> +	}
>>> +
>>> +	value = readl(vf_qm->io_base + QM_MB_CMD_SEND_BASE);
>>> +	if (value == QM_MB_CMD_NOT_READY) {
>>> +		mutex_unlock(&hisi_acc_vdev->open_mutex);
>>> +		seq_printf(seq, "mailbox cmd channel not ready!\n");
>>> +		return -EINVAL;
>>> +	}
>>> +	mutex_unlock(&hisi_acc_vdev->open_mutex);
>>> +	seq_printf(seq, "mailbox cmd channel ready!\n");
>>> +
>>> +	return 0;
>>> +}
>>> +
>>> +static int hisi_acc_vf_dev_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);
>>> +	size_t vf_data_sz = offsetofend(struct acc_vf_data, padding);
>>> +	struct acc_vf_data *vf_data = NULL;
>>
>> Nit, this initialization is unnecessary.
>>
> 
> OK, delete it in next version.
> 
>>> +	int ret;
>>> +
>>> +	mutex_lock(&hisi_acc_vdev->open_mutex);
>>> +	ret = hisi_acc_vf_debug_check(seq, vdev);
>>> +	if (ret) {
>>> +		mutex_unlock(&hisi_acc_vdev->open_mutex);
>>> +		return ret;
>>> +	}
>>> +
>>> +	mutex_lock(&hisi_acc_vdev->state_mutex);
>>> +	vf_data = kzalloc(sizeof(struct acc_vf_data), GFP_KERNEL);
>>> +	if (!vf_data) {
>>> +		ret = -ENOMEM;
>>> +		goto mutex_release;
>>> +	}
>>> +
>>> +	vf_data->vf_qm_state = hisi_acc_vdev->vf_qm_state;
>>> +	ret = vf_qm_read_data(&hisi_acc_vdev->vf_qm, vf_data);
>>> +	if (ret)
>>> +		goto migf_err;
>>> +
>>> +	seq_hex_dump(seq, "Dev Data:", DUMP_PREFIX_OFFSET, 16, 1,
>>> +			(unsigned char *)vf_data,
>>
>> Casting to (const void *) would match the prototype.  This line should
>> also wrap to just inside the opening parenthesis of the previous line, 2
>> tabs, 5 spaces.
>>
> 
> OK, I will adjust it in the next version.
> 
>>> +			vf_data_sz, false);
>>> +
>>> +	seq_printf(seq,
>>> +		 "acc device:\n"
>>> +		 "guest driver load: %u\n"
>>> +		 "data size: %lu\n",
>>> +		 hisi_acc_vdev->vf_qm_state,
>>> +		 sizeof(struct acc_vf_data));
>>
>> Same here and throughout, wrap aligned to the relevant parenthesis.
>>
> 
> OK.
> 
>> I know you've described vf_qm_state as indicating whether or not the
>> guest driver is loaded, but I still can't figure out how to discern
>> that from the code.  It's largely only set based on the return value of
>> qm_wait_dev_not_ready(), which tests QM_VF_STATE, and describes the
>> function as testing if the device is ready.  Improved comments would
>> help future reviews.
>>
> 
> This QM_VF_STATE register will be written to QM_READY when the acc device
> driver is loaded, and QM_NOT_READY will be written after the device
> driver is unloaded.
>> I will add a comment where vf_qm_state is declared.
> 
>> What's the purpose of the "acc device:" prefix?
>>
> 
> OK, it can be deleted.
> 
>>> +
>>> +migf_err:
>>> +	kfree(vf_data);
>>> +mutex_release:
>>> +	mutex_unlock(&hisi_acc_vdev->open_mutex);
>>> +	mutex_unlock(&hisi_acc_vdev->state_mutex);
>>
>> Locks should be released in the reverse order they were acquired.
>>
> 
> OK.
> 
>>> +
>>> +	return ret;
>>> +}
>>> +
>>> +static int hisi_acc_vf_migf_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);
>>> +	size_t vf_data_sz = offsetofend(struct acc_vf_data, padding);
>>> +	struct hisi_acc_vf_migration_file *debug_migf = hisi_acc_vdev->debug_migf;
>>> +
>>> +	/* Check whether the live migration operation has been performed */
>>> +	if (debug_migf->total_length < QM_MATCH_SIZE) {
>>> +		seq_printf(seq, "device not migrated!\n");
>>> +		return -EAGAIN;
>>> +	}
>>> +
>>> +	seq_hex_dump(seq, "Mig Data:", DUMP_PREFIX_OFFSET, 16, 1,
>>> +			(unsigned char *)&debug_migf->vf_data,
>>> +			vf_data_sz, false);
>>> +
>>> +	seq_printf(seq,
>>> +		 "acc device:\n"
>>> +		 "guest driver load: %u\n"
>>> +		 "device opened: %d\n"
>>> +		 "migrate data length: %lu\n",
>>> +		 hisi_acc_vdev->vf_qm_state,
>>> +		 hisi_acc_vdev->dev_opened,
>>> +		 debug_migf->total_length);
>>
>> This debugfs entry is described as returning the data from the last
>> migration, but vf_qm_state and dev_opened are relative to the current
>> device/guest driver state.  Both seem to have no relevance to the data
>> in debug_migf.
>>
> 
> The benefit of dev_opened retention is that user can obtain the device status
> during the cat migf_data operation.
>

I will remove dev_opened in the next version.
And hisi_acc_vdev->vf_qm_state is changed to debug_migf->vf_data.vf_qm_state
Keep information about whether the device driver in the Guest OS is loaded
when live migration occurs.

Thanks，
Longfang.

> And vf_qm_state does need to be retained.
> Because adding a driver or not adding a driver to the Guest OS has a great impact
> on the results of live migration, it is a key factor. It has a great impact on
> the success or failure of live migration.
> 
> When adding a driver, live migration will read device status data, and data will
> be written back to device after the migration is completed.
> When no driver is added, live migration only executes a process. It does not
> perform data reading and data recovery operations.
> 
>>> +
>>> +	return 0;
>>> +}
>>> +
>>>  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);
>>> @@ -1305,12 +1454,16 @@ static int hisi_acc_vfio_pci_open_device(struct vfio_device *core_vdev)
>>>  		return ret;
>>>  
>>>  	if (core_vdev->mig_ops) {
>>> +		mutex_lock(&hisi_acc_vdev->open_mutex);
>>>  		ret = hisi_acc_vf_qm_init(hisi_acc_vdev);
>>>  		if (ret) {
>>> +			mutex_unlock(&hisi_acc_vdev->open_mutex);
>>>  			vfio_pci_core_disable(vdev);
>>>  			return ret;
>>>  		}
>>>  		hisi_acc_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
>>> +		hisi_acc_vdev->dev_opened = true;
>>> +		mutex_unlock(&hisi_acc_vdev->open_mutex);
>>>  	}
>>>  
>>>  	vfio_pci_core_finish_enable(vdev);
>>> @@ -1322,7 +1475,10 @@ static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev)
>>>  	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(core_vdev);
>>>  	struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm;
>>>  
>>> +	mutex_lock(&hisi_acc_vdev->open_mutex);
>>> +	hisi_acc_vdev->dev_opened = false;
>>>  	iounmap(vf_qm->io_base);
>>> +	mutex_unlock(&hisi_acc_vdev->open_mutex);
>>>  	vfio_pci_core_close_device(core_vdev);
>>>  }
>>>  
>>> @@ -1342,6 +1498,7 @@ static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
>>>  	hisi_acc_vdev->pf_qm = pf_qm;
>>>  	hisi_acc_vdev->vf_dev = pdev;
>>>  	mutex_init(&hisi_acc_vdev->state_mutex);
>>> +	mutex_init(&hisi_acc_vdev->open_mutex);
>>>  
>>>  	core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY;
>>>  	core_vdev->mig_ops = &hisi_acc_vfio_pci_migrn_state_ops;
>>> @@ -1387,6 +1544,50 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
>>>  	.detach_ioas = vfio_iommufd_physical_detach_ioas,
>>>  };
>>>  
>>> +static void 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() ||
>>> +	    !IS_ENABLED(CONFIG_VFIO_DEBUGFS))
>>> +		return;
>>> +
>>> +	if (vdev->ops != &hisi_acc_vfio_pci_migrn_ops)
>>> +		return;
>>> +
>>> +	vfio_dev_migration = debugfs_lookup("migration", vdev->debug_root);
>>> +	if (!vfio_dev_migration) {
>>> +		dev_err(dev, "failed to lookup migration debugfs file!\n");
>>> +		return;
>>> +	}
>>> +
>>> +	migf = kzalloc(sizeof(struct hisi_acc_vf_migration_file), GFP_KERNEL);
>>> +	if (!migf)
>>> +		return;
>>> +	hisi_acc_vdev->debug_migf = migf;
>>> +
>>> +	vfio_hisi_acc = debugfs_create_dir("hisi_acc", vfio_dev_migration);
>>> +	debugfs_create_devm_seqfile(dev, "dev_data", vfio_hisi_acc,
>>> +				  hisi_acc_vf_dev_read);
>>> +	debugfs_create_devm_seqfile(dev, "migf_data", vfio_hisi_acc,
>>> +				  hisi_acc_vf_migf_read);
>>> +	debugfs_create_devm_seqfile(dev, "cmd_state", vfio_hisi_acc,
>>> +				  hisi_acc_vf_debug_cmd);
>>> +}
>>> +
>>> +static void hisi_acc_vf_debugfs_exit(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>>> +{
>>> +	/* If migrn_ops is not used, debug_migf is NULL */
>>> +	if (hisi_acc_vdev->debug_migf) {
>>
>> This test is unnecessary, kfree(NULL) is valid.
>>
> 
> OK, It will be deleted. Comments will also be updated.
> 
>>> +		kfree(hisi_acc_vdev->debug_migf);
>>> +		hisi_acc_vdev->debug_migf = NULL;
>>> +	}
>>> +}
>>> +
>>>  static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
>>>  {
>>>  	struct hisi_acc_vf_core_device *hisi_acc_vdev;
>>> @@ -1413,6 +1614,8 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
>>>  	ret = vfio_pci_core_register_device(&hisi_acc_vdev->core_device);
>>>  	if (ret)
>>>  		goto out_put_vdev;
>>> +
>>> +	hisi_acc_vfio_debug_init(hisi_acc_vdev);
>>>  	return 0;
>>>  
>>>  out_put_vdev:
>>> @@ -1425,6 +1628,7 @@ static void hisi_acc_vfio_pci_remove(struct pci_dev *pdev)
>>>  	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_drvdata(pdev);
>>>  
>>>  	vfio_pci_core_unregister_device(&hisi_acc_vdev->core_device);
>>> +	hisi_acc_vf_debugfs_exit(hisi_acc_vdev);
>>>  	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 5bab46602fad..2a78ffd060c3 100644
>>> --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
>>> +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
>>> @@ -32,6 +32,7 @@
>>>  #define QM_SQC_VFT_BASE_MASK_V2		GENMASK(15, 0)
>>>  #define QM_SQC_VFT_NUM_SHIFT_V2		45
>>>  #define QM_SQC_VFT_NUM_MASK_V2		GENMASK(9, 0)
>>> +#define QM_MB_CMD_NOT_READY	0xffffffff
>>>  
>>>  /* RW regs */
>>>  #define QM_REGS_MAX_LEN		7
>>> @@ -99,6 +100,8 @@ struct hisi_acc_vf_migration_file {
>>>  struct hisi_acc_vf_core_device {
>>>  	struct vfio_pci_core_device core_device;
>>>  	u8 match_done;
>>> +	/* To make sure the device is opened */
>>
>> We can infer that from the field name, it would be more useful to
>> comment that io_base is only valid when dev_opened, which is protected
>> by open_mutex.
>>
> 
> OK, the comments will be updated according to your instructions.
> 
>>> +	bool dev_opened;
>>
>> Seems like open_mutex would fit just as well here and have better
>> proximity to the data it protects.
>>
> 
> OK, I'm going to move it over here.
> 
>>>  
>>>  	/* For migration state */
>>>  	struct mutex state_mutex;
>>> @@ -111,5 +114,9 @@ struct hisi_acc_vf_core_device {
>>>  	int vf_id;
>>>  	struct hisi_acc_vf_migration_file *resuming_migf;
>>>  	struct hisi_acc_vf_migration_file *saving_migf;
>>> +
>>> +	/* To save migration data */
>>
>> Clearly.  Describing it as an extra buffer for reporting migration data
>> through debugfs might be more useful.  Thanks,
>>
> 
> OK, the comments will be updated according to your instructions.
> 
> Thanks.
> Longfang.
> 
>> Alex
>>
>>> +	struct hisi_acc_vf_migration_file *debug_migf;
>>> +	struct mutex open_mutex;
>>>  };
>>>  #endif /* HISI_ACC_VFIO_PCI_H */
>>
>>
>> .
>>
> 
> .
> 

RE: [PATCH v11 3/4] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

[Shameerali Kolothum Thodi]

> -----Original Message-----
> From: liulongfang <liulongfang@huawei.com>
> Sent: Monday, November 4, 2024 8:31 AM
> To: Alex Williamson <alex.williamson@redhat.com>
> Cc: jgg@nvidia.com; Shameerali Kolothum Thodi
> <shameerali.kolothum.thodi@huawei.com>; Jonathan Cameron
> <jonathan.cameron@huawei.com>; kvm@vger.kernel.org; linux-
> kernel@vger.kernel.org; linuxarm@openeuler.org
> Subject: Re: [PATCH v11 3/4] hisi_acc_vfio_pci: register debugfs for hisilicon
> migration driver
[...]

> >>> +
> >>> +	seq_printf(seq,
> >>> +		 "acc device:\n"
> >>> +		 "guest driver load: %u\n"
> >>> +		 "device opened: %d\n"
> >>> +		 "migrate data length: %lu\n",
> >>> +		 hisi_acc_vdev->vf_qm_state,
> >>> +		 hisi_acc_vdev->dev_opened,
> >>> +		 debug_migf->total_length);
> >>
> >> This debugfs entry is described as returning the data from the last
> >> migration, but vf_qm_state and dev_opened are relative to the current
> >> device/guest driver state.  Both seem to have no relevance to the data
> >> in debug_migf.
> >>
> >
> > The benefit of dev_opened retention is that user can obtain the device
> status
> > during the cat migf_data operation.
> >
> 
> I will remove dev_opened in the next version.
> And hisi_acc_vdev->vf_qm_state is changed to debug_migf-
> >vf_data.vf_qm_state
> Keep information about whether the device driver in the Guest OS is loaded
> when live migration occurs.

I think you already get that when you dump debug_migf->vf_data.
So not required.

Thanks,
Shameer

Re: [PATCH v11 3/4] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

[liulongfang]

On 2024/11/4 16:56, Shameerali Kolothum Thodi wrote:
> 
> 
>> -----Original Message-----
>> From: liulongfang <liulongfang@huawei.com>
>> Sent: Monday, November 4, 2024 8:31 AM
>> To: Alex Williamson <alex.williamson@redhat.com>
>> Cc: jgg@nvidia.com; Shameerali Kolothum Thodi
>> <shameerali.kolothum.thodi@huawei.com>; Jonathan Cameron
>> <jonathan.cameron@huawei.com>; kvm@vger.kernel.org; linux-
>> kernel@vger.kernel.org; linuxarm@openeuler.org
>> Subject: Re: [PATCH v11 3/4] hisi_acc_vfio_pci: register debugfs for hisilicon
>> migration driver
> [...]
> 
>>>>> +
>>>>> +	seq_printf(seq,
>>>>> +		 "acc device:\n"
>>>>> +		 "guest driver load: %u\n"
>>>>> +		 "device opened: %d\n"
>>>>> +		 "migrate data length: %lu\n",
>>>>> +		 hisi_acc_vdev->vf_qm_state,
>>>>> +		 hisi_acc_vdev->dev_opened,
>>>>> +		 debug_migf->total_length);
>>>>
>>>> This debugfs entry is described as returning the data from the last
>>>> migration, but vf_qm_state and dev_opened are relative to the current
>>>> device/guest driver state.  Both seem to have no relevance to the data
>>>> in debug_migf.
>>>>
>>>
>>> The benefit of dev_opened retention is that user can obtain the device
>> status
>>> during the cat migf_data operation.
>>>
>>
>> I will remove dev_opened in the next version.
>> And hisi_acc_vdev->vf_qm_state is changed to debug_migf-
>>> vf_data.vf_qm_state
>> Keep information about whether the device driver in the Guest OS is loaded
>> when live migration occurs.
> 
> I think you already get that when you dump debug_migf->vf_data.
> So not required.
>
OK, vf_qm_state still needs to be deleted.

Thanks,
Longfang.

> Thanks,
> Shameer
> 
> .
>