Re: [PATCH 2/3] hisi_acc_vfio_pci: register debugfs for hisilicon migration driver

[Alex Williamson]

On Thu, 25 Jan 2024 16:10:30 +0800
Longfang Liu <liulongfang@xxxxxxxxxx> 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
>     |            +--attr
>     |            +--data
>     |            +--save
>     |            +--cmd_state
>     |
>     +---<dev_name2>
>          +---migration
>              +--state
>              +--hisi_acc
>                  +--attr
>                  +--data
>                  +--save
>                  +--cmd_state
> 
> 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.
> cmd_state: used to get the cmd channel state for the device.
> 
> Signed-off-by: Longfang Liu <liulongfang@xxxxxxxxxx>
> ---
>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 190 ++++++++++++++++++
>  .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h    |   5 +
>  2 files changed, 195 insertions(+)
> 
> diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
> index 5f6e01571a7b..2cbbc52b7377 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)
> @@ -617,6 +618,18 @@ 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 *dst_migf,
> +	struct hisi_acc_vf_migration_file *src_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);
> @@ -629,12 +642,16 @@ 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->debug_migf,
> +						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_vf_migf_save(hisi_acc_vdev->debug_migf,
> +						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;
> @@ -1175,6 +1192,7 @@ static int hisi_acc_vf_qm_init(struct hisi_acc_vf_core_device *hisi_acc_vdev)
>  	if (!vf_qm->io_base)
>  		return -EIO;
>  
> +	mutex_init(&hisi_acc_vdev->enable_mutex);
>  	vf_qm->fun_type = QM_HW_VF;
>  	vf_qm->pdev = vf_dev;
>  	mutex_init(&vf_qm->mailbox_lock);
> @@ -1325,6 +1343,172 @@ 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 does not support live migration!");
> +		return -EINVAL;
> +	}
> +
> +	/**
> +	 * When the device is not opened, the io_base is not mapped.
> +	 * The driver cannot perform device read and write operations.
> +	 */
> +	if (!vdev->open_count) {
> +		seq_printf(seq, "%s\n", "device not opened!");
> +		return -EINVAL;
> +	}

This is racy, this check could occur while the user is already closing
the device and vfio_df_device_last_close() may have already iounmap'd
the io_base.  Only after that is open_count decremented.  The debugfs
interfaces would then proceed to access the unmapped space.  The
enable_mutex is entirely ineffective (and also asymmetric, initialized
in the open_device path but never destroyed).

In fact, the enable_mutex really only seems to be trying to protect
io_base (which it doesn't do), meanwhile the core driver execution path
can run concurrently to debugfs operations with no serialization.  It
looks like these operations would step on each other.

I think you might need an atomic to guard against io_base unmapping and
then maybe a mutex or semaphore to avoid debugfs accesses from
interfering with the actual core logic interacting with the device.
Thanks,

Alex

> +
> +	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;
> +
> +	ret = hisi_acc_vf_debug_check(seq, vdev);
> +	if (ret)
> +		return 0;
> +
> +	mutex_lock(&hisi_acc_vdev->enable_mutex);
> +	ret = qm_wait_dev_not_ready(vf_qm);
> +	if (ret) {
> +		mutex_unlock(&hisi_acc_vdev->enable_mutex);
> +		seq_printf(seq, "%s\n", "VF device not ready!");
> +		return 0;
> +	}
> +
> +	value = readl(vf_qm->io_base + QM_MB_CMD_SEND_BASE);
> +	mutex_unlock(&hisi_acc_vdev->enable_mutex);
> +	seq_printf(seq, "%s:0x%llx\n", "mailbox cmd channel state is OK", value);
> +
> +	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)
> +		return 0;
> +
> +	mutex_lock(&hisi_acc_vdev->enable_mutex);
> +	ret = vf_qm_state_save(hisi_acc_vdev, migf);
> +	if (ret) {
> +		mutex_unlock(&hisi_acc_vdev->enable_mutex);
> +		seq_printf(seq, "%s\n", "failed to save device data!");
> +		return 0;
> +	}
> +	mutex_unlock(&hisi_acc_vdev->enable_mutex);
> +	seq_printf(seq, "%s\n", "successful to save device data!");
> +
> +	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) {
> +		kfree(migf);
> +		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, "cmd_state", vfio_hisi_acc,
> +				  hisi_acc_vf_debug_cmd);
> +	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);
> @@ -1353,7 +1537,9 @@ 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->enable_mutex);
>  	iounmap(vf_qm->io_base);
> +	mutex_unlock(&hisi_acc_vdev->enable_mutex);
>  	vfio_pci_core_close_device(core_vdev);
>  }
>  
> @@ -1444,6 +1630,9 @@ 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:
> @@ -1456,6 +1645,7 @@ 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 c58fc5861492..38327b97d535 100644
> --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
> +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
> @@ -116,5 +116,10 @@ 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;
> +
> +	/* To make sure the device is enabled */
> +	struct mutex enable_mutex;
> +	/* For debugfs */
> +	struct hisi_acc_vf_migration_file *debug_migf;
>  };
>  #endif /* HISI_ACC_VFIO_PCI_H */