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

From: Alex Williamson
Date: Fri Jul 14 2023 - 18:08:56 EST

Next message: Alex Williamson: "Re: [PATCH v11 4/4] Documentation: add debugfs description for vfio"
Previous message: Peter Zijlstra: "Re: [6.5.0-rc1] unchecked MSR access error: RDMSR from 0xe2 at rIP: 0xffffffff87090227 (native_read_msr+0x7/0x40) (intel_idle_init_cstates_icpu)"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

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

> From: Longfang Liu <liulongfang@xxxxxxxxxx>
>
> 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@xxxxxxxxxx>
> ---
> .../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 */

Next message: Alex Williamson: "Re: [PATCH v11 4/4] Documentation: add debugfs description for vfio"
Previous message: Peter Zijlstra: "Re: [6.5.0-rc1] unchecked MSR access error: RDMSR from 0xe2 at rIP: 0xffffffff87090227 (native_read_msr+0x7/0x40) (intel_idle_init_cstates_icpu)"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]