Add a debugfs function to the migration driver in VFIO to provide a step-by-step test function for the migration driver.
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 v4 -> v5 Remove the newly added vfio_migration_ops and use seq_printf to optimize the implementation of debugfs.
Changes v3 -> v4 Change the migration_debug_operate interface to debug_root file.
Changes v2 -> v3 Extend the debugfs function from hisilicon device to vfio.
Changes v1 -> v2 Change the registration method of root_debugfs to register with module initialization.
Longfang Liu (5): vfio/migration: Add debugfs to live migration driver hisi_acc_vfio_pci: extract public functions for container_of hisi_acc_vfio_pci: register debugfs for hisilicon migration driver Documentation: add debugfs description for hisi_acc_vfio_pci vfio: update live migration device status
.../ABI/testing/debugfs-hisi-migration | 32 ++ drivers/vfio/pci/Makefile | 4 + .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 300 +++++++++++++++++- .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h | 11 + drivers/vfio/pci/mlx5/main.c | 3 + drivers/vfio/pci/vfio_pci_core.c | 3 + drivers/vfio/pci/vfio_pci_debugfs.c | 76 +++++ drivers/vfio/pci/vfio_pci_debugfs.h | 30 ++ include/linux/vfio.h | 6 + 9 files changed, 455 insertions(+), 10 deletions(-) create mode 100644 Documentation/ABI/testing/debugfs-hisi-migration create mode 100644 drivers/vfio/pci/vfio_pci_debugfs.c create mode 100644 drivers/vfio/pci/vfio_pci_debugfs.h
There are multiple devices, software and operational steps involved in the process of live migration. An error occurred on any node may cause the live migration operation to fail. This complex process makes it very difficult to locate and analyze the cause when the function fails.
In order to quickly locate the cause of the problem when the live migration fails, I added a set of debugfs to the vfio live migration driver.
+------------------------------------------+ | | | | | QEMU | | | | | +-----+-------------------------+----------+ | ^ | ^ v | v | +-----+--+ +-----+--+ | src VF | | dst VF | +-+------+ +-+------+ | ^ | ^ v | v | +-------+-+------+ +-------+-+------+ |Debugfs|state | |Debugfs|state | +-------+--------+ +-------+--------+ | debug_root | | debug_root | +-------+--------+ +-------+--------+
debugfs will create a public root directory "vfio_mig" file. then create a "debug_root" file for each live migration VF device. state file: used to get the status of the live migration device. debug_root: used to create your own custom debug files for live migration device drivers.
The live migration function of the current device can be tested by operating the debug files, and the functional status of the equipment and software at each stage can be tested step by step without performing the complete live migration function. And after the live migration is performed, the migration device data of the live migration can be obtained through the debug files.
Signed-off-by: Longfang Liu liulongfang@huawei.com --- drivers/vfio/pci/Makefile | 4 ++ drivers/vfio/pci/vfio_pci_core.c | 3 ++ drivers/vfio/pci/vfio_pci_debugfs.c | 76 +++++++++++++++++++++++++++++ drivers/vfio/pci/vfio_pci_debugfs.h | 30 ++++++++++++ include/linux/vfio.h | 6 +++ 5 files changed, 119 insertions(+) create mode 100644 drivers/vfio/pci/vfio_pci_debugfs.c create mode 100644 drivers/vfio/pci/vfio_pci_debugfs.h
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 24c524224da5..efe032623664 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -4,6 +4,10 @@ vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_con vfio-pci-core-$(CONFIG_VFIO_PCI_ZDEV_KVM) += vfio_pci_zdev.o obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o
+ifneq ($(CONFIG_DEBUG_FS),) + vfio-pci-core-y += vfio_pci_debugfs.o +endif + vfio-pci-y := vfio_pci.o vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o obj-$(CONFIG_VFIO_PCI) += vfio-pci.o diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index f9365a5bc961..e85df2deb8e6 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -31,6 +31,7 @@ #include <asm/eeh.h> #endif
+#include "vfio_pci_debugfs.h" #include "vfio_pci_priv.h"
#define DRIVER_AUTHOR "Alex Williamson alex.williamson@redhat.com" @@ -2555,11 +2556,13 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_set_params);
static void vfio_pci_core_cleanup(void) { + vfio_pci_debugfs_remove_root(); vfio_pci_uninit_perm_bits(); }
static int __init vfio_pci_core_init(void) { + vfio_pci_debugfs_create_root(); /* Allocate shared config space permission data used by all devices */ return vfio_pci_init_perm_bits(); } diff --git a/drivers/vfio/pci/vfio_pci_debugfs.c b/drivers/vfio/pci/vfio_pci_debugfs.c new file mode 100644 index 000000000000..33d663fb04f2 --- /dev/null +++ b/drivers/vfio/pci/vfio_pci_debugfs.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022, HiSilicon Ltd. + */ + +#include <linux/pci.h> +#include <linux/vfio_pci_core.h> + +#include "vfio_pci_debugfs.h" + +static struct dentry *vfio_pci_debugfs_root; + +static int vfio_pci_vf_state_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; + enum vfio_device_mig_state state; + + (void)vdev->mig_ops->migration_get_state(vdev, &state); + switch (state) { + case VFIO_DEVICE_STATE_RUNNING: + seq_printf(seq, "%s\n", "RUNNING"); + break; + case VFIO_DEVICE_STATE_STOP_COPY: + seq_printf(seq, "%s\n", "STOP_COPY"); + break; + case VFIO_DEVICE_STATE_STOP: + seq_printf(seq, "%s\n", "STOP"); + break; + case VFIO_DEVICE_STATE_RESUMING: + seq_printf(seq, "%s\n", "RESUMING"); + break; + case VFIO_DEVICE_STATE_RUNNING_P2P: + seq_printf(seq, "%s\n", "RESUMING_P2P"); + break; + case VFIO_DEVICE_STATE_ERROR: + seq_printf(seq, "%s\n", "ERROR"); + break; + default: + seq_printf(seq, "%s\n", "Invalid"); + } + + return 0; +} + +void vfio_pci_vf_debugfs_init(struct vfio_device *vdev) +{ + struct device *dev = vdev->dev; + + vdev->debug_root = debugfs_create_dir(dev_name(dev), vfio_pci_debugfs_root); + + debugfs_create_devm_seqfile(dev, "state", vdev->debug_root, + vfio_pci_vf_state_read); +} +EXPORT_SYMBOL_GPL(vfio_pci_vf_debugfs_init); + +void vfio_pci_vf_debugfs_exit(struct vfio_device *vdev) +{ + debugfs_remove_recursive(vdev->debug_root); +} +EXPORT_SYMBOL_GPL(vfio_pci_vf_debugfs_exit); + +void vfio_pci_debugfs_create_root(void) +{ + vfio_pci_debugfs_root = debugfs_create_dir("vfio_mig", NULL); +} +EXPORT_SYMBOL_GPL(vfio_pci_debugfs_create_root); + +void vfio_pci_debugfs_remove_root(void) +{ + debugfs_remove_recursive(vfio_pci_debugfs_root); + vfio_pci_debugfs_root = NULL; +} +EXPORT_SYMBOL_GPL(vfio_pci_debugfs_remove_root); + diff --git a/drivers/vfio/pci/vfio_pci_debugfs.h b/drivers/vfio/pci/vfio_pci_debugfs.h new file mode 100644 index 000000000000..8d1a4aef05db --- /dev/null +++ b/drivers/vfio/pci/vfio_pci_debugfs.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * vfio_pci_debugfs.h - VFIO migration debugfs interface + * + * Copyright (c) 2022, HiSilicon Ltd. + * + * Author: Longfang Liu liulongfang@huawei.com + */ + +#ifndef __VFIO_PCI_DEBUGFS_H +#define __VFIO_PCI_DEBUGFS_H + +#include <linux/debugfs.h> +#include <linux/vfio.h> + +#ifdef CONFIG_DEBUG_FS +void vfio_pci_debugfs_create_root(void); +void vfio_pci_debugfs_remove_root(void); + +void vfio_pci_vf_debugfs_init(struct vfio_device *vdev); +void vfio_pci_vf_debugfs_exit(struct vfio_device *vdev); +#else +static inline void vfio_pci_debugfs_create_root(void) { } +static inline void vfio_pci_debugfs_remove_root(void) { } + +static inline void vfio_pci_vf_debugfs_init(struct vfio_device *vdev) { } +static inline void vfio_pci_vf_debugfs_exit(struct vfio_device *vdev) { } +#endif /* CONFIG_DEBUG_FS */ + +#endif /* __VFIO_PCI_DEBUGFS_H */ diff --git a/include/linux/vfio.h b/include/linux/vfio.h index b4d5d4ca3d7d..7d6d02f165cf 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -54,6 +54,12 @@ struct vfio_device { struct completion comp; struct list_head group_next; struct list_head iommu_entry; + + /* + * debug_root is a static property of the vfio_device + * which must be set prior to registering the vfio_device. + */ + struct dentry *debug_root; };
/**
On Sat, Dec 17, 2022 at 02:32:44PM +0800, Longfang Liu wrote:
There are multiple devices, software and operational steps involved in the process of live migration. An error occurred on any node may cause the live migration operation to fail. This complex process makes it very difficult to locate and analyze the cause when the function fails.
In order to quickly locate the cause of the problem when the live migration fails, I added a set of debugfs to the vfio live migration driver.
+------------------------------------------+ | | | | | QEMU | | | | | +-----+-------------------------+----------+ | ^ | ^ v | v | +-----+--+ +-----+--+ | src VF | | dst VF | +-+------+ +-+------+ | ^ | ^ v | v | +-------+-+------+ +-------+-+------+ |Debugfs|state | |Debugfs|state | +-------+--------+ +-------+--------+ | debug_root | | debug_root | +-------+--------+ +-------+--------+
debugfs will create a public root directory "vfio_mig" file. then create a "debug_root" file for each live migration VF device. state file: used to get the status of the live migration device. debug_root: used to create your own custom debug files for live migration device drivers.
The live migration function of the current device can be tested by operating the debug files, and the functional status of the equipment and software at each stage can be tested step by step without performing the complete live migration function. And after the live migration is performed, the migration device data of the live migration can be obtained through the debug files.
Signed-off-by: Longfang Liu liulongfang@huawei.com
drivers/vfio/pci/Makefile | 4 ++ drivers/vfio/pci/vfio_pci_core.c | 3 ++ drivers/vfio/pci/vfio_pci_debugfs.c | 76 +++++++++++++++++++++++++++++ drivers/vfio/pci/vfio_pci_debugfs.h | 30 ++++++++++++ include/linux/vfio.h | 6 +++ 5 files changed, 119 insertions(+) create mode 100644 drivers/vfio/pci/vfio_pci_debugfs.c create mode 100644 drivers/vfio/pci/vfio_pci_debugfs.h
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 24c524224da5..efe032623664 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -4,6 +4,10 @@ vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_con vfio-pci-core-$(CONFIG_VFIO_PCI_ZDEV_KVM) += vfio_pci_zdev.o obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o
+ifneq ($(CONFIG_DEBUG_FS),)
- vfio-pci-core-y += vfio_pci_debugfs.o
+endif
This is now how makefile should be written
vfio-pci-core-$(CONFIG_DEBUG_FS) += vfio_pci_debugfs.o
+static int vfio_pci_vf_state_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;
- enum vfio_device_mig_state state;
- (void)vdev->mig_ops->migration_get_state(vdev, &state);
Do not use (void) like this, and why not handle the error?
- switch (state) {
- case VFIO_DEVICE_STATE_RUNNING:
seq_printf(seq, "%s\n", "RUNNING");
break;
- case VFIO_DEVICE_STATE_STOP_COPY:
seq_printf(seq, "%s\n", "STOP_COPY");
break;
- case VFIO_DEVICE_STATE_STOP:
seq_printf(seq, "%s\n", "STOP");
break;
- case VFIO_DEVICE_STATE_RESUMING:
seq_printf(seq, "%s\n", "RESUMING");
break;
- case VFIO_DEVICE_STATE_RUNNING_P2P:
seq_printf(seq, "%s\n", "RESUMING_P2P");
break;
- case VFIO_DEVICE_STATE_ERROR:
seq_printf(seq, "%s\n", "ERROR");
break;
- default:
seq_printf(seq, "%s\n", "Invalid");
- }
- return 0;
+}
+void vfio_pci_vf_debugfs_init(struct vfio_device *vdev) +{
- struct device *dev = vdev->dev;
- vdev->debug_root = debugfs_create_dir(dev_name(dev), vfio_pci_debugfs_root);
- debugfs_create_devm_seqfile(dev, "state", vdev->debug_root,
vfio_pci_vf_state_read);
+} +EXPORT_SYMBOL_GPL(vfio_pci_vf_debugfs_init);
+void vfio_pci_vf_debugfs_exit(struct vfio_device *vdev) +{
- debugfs_remove_recursive(vdev->debug_root);
+} +EXPORT_SYMBOL_GPL(vfio_pci_vf_debugfs_exit);
+void vfio_pci_debugfs_create_root(void) +{
- vfio_pci_debugfs_root = debugfs_create_dir("vfio_mig", NULL);
+} +EXPORT_SYMBOL_GPL(vfio_pci_debugfs_create_root);
+void vfio_pci_debugfs_remove_root(void) +{
- debugfs_remove_recursive(vfio_pci_debugfs_root);
- vfio_pci_debugfs_root = NULL;
+} +EXPORT_SYMBOL_GPL(vfio_pci_debugfs_remove_root);
Why are these exported symbols? The core code should handle this on its own.
If the device defines migration_get_state() then the debugfs should be created.
Mabye you need an op to populate the driver's debugfs to also trigger creating the directory
Jason
On 2023/1/3 23:05, Jason Gunthorpe Wrote:
On Sat, Dec 17, 2022 at 02:32:44PM +0800, Longfang Liu wrote:
There are multiple devices, software and operational steps involved in the process of live migration. An error occurred on any node may cause the live migration operation to fail. This complex process makes it very difficult to locate and analyze the cause when the function fails.
In order to quickly locate the cause of the problem when the live migration fails, I added a set of debugfs to the vfio live migration driver.
+------------------------------------------+ | | | | | QEMU | | | | | +-----+-------------------------+----------+ | ^ | ^ v | v | +-----+--+ +-----+--+ | src VF | | dst VF | +-+------+ +-+------+ | ^ | ^ v | v | +-------+-+------+ +-------+-+------+ |Debugfs|state | |Debugfs|state | +-------+--------+ +-------+--------+ | debug_root | | debug_root | +-------+--------+ +-------+--------+
debugfs will create a public root directory "vfio_mig" file. then create a "debug_root" file for each live migration VF device. state file: used to get the status of the live migration device. debug_root: used to create your own custom debug files for live migration device drivers.
The live migration function of the current device can be tested by operating the debug files, and the functional status of the equipment and software at each stage can be tested step by step without performing the complete live migration function. And after the live migration is performed, the migration device data of the live migration can be obtained through the debug files.
Signed-off-by: Longfang Liu liulongfang@huawei.com
drivers/vfio/pci/Makefile | 4 ++ drivers/vfio/pci/vfio_pci_core.c | 3 ++ drivers/vfio/pci/vfio_pci_debugfs.c | 76 +++++++++++++++++++++++++++++ drivers/vfio/pci/vfio_pci_debugfs.h | 30 ++++++++++++ include/linux/vfio.h | 6 +++ 5 files changed, 119 insertions(+) create mode 100644 drivers/vfio/pci/vfio_pci_debugfs.c create mode 100644 drivers/vfio/pci/vfio_pci_debugfs.h
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile index 24c524224da5..efe032623664 100644 --- a/drivers/vfio/pci/Makefile +++ b/drivers/vfio/pci/Makefile @@ -4,6 +4,10 @@ vfio-pci-core-y := vfio_pci_core.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_con vfio-pci-core-$(CONFIG_VFIO_PCI_ZDEV_KVM) += vfio_pci_zdev.o obj-$(CONFIG_VFIO_PCI_CORE) += vfio-pci-core.o
+ifneq ($(CONFIG_DEBUG_FS),)
- vfio-pci-core-y += vfio_pci_debugfs.o
+endif
This is now how makefile should be written
vfio-pci-core-$(CONFIG_DEBUG_FS) += vfio_pci_debugfs.o
Ok, here it will be changed on the next patch version.
+static int vfio_pci_vf_state_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;
- enum vfio_device_mig_state state;
- (void)vdev->mig_ops->migration_get_state(vdev, &state);
Do not use (void) like this, and why not handle the error?
Ok, here I will add an error handling.
- switch (state) {
- case VFIO_DEVICE_STATE_RUNNING:
seq_printf(seq, "%s\n", "RUNNING");
break;
- case VFIO_DEVICE_STATE_STOP_COPY:
seq_printf(seq, "%s\n", "STOP_COPY");
break;
- case VFIO_DEVICE_STATE_STOP:
seq_printf(seq, "%s\n", "STOP");
break;
- case VFIO_DEVICE_STATE_RESUMING:
seq_printf(seq, "%s\n", "RESUMING");
break;
- case VFIO_DEVICE_STATE_RUNNING_P2P:
seq_printf(seq, "%s\n", "RESUMING_P2P");
break;
- case VFIO_DEVICE_STATE_ERROR:
seq_printf(seq, "%s\n", "ERROR");
break;
- default:
seq_printf(seq, "%s\n", "Invalid");
- }
- return 0;
+}
+void vfio_pci_vf_debugfs_init(struct vfio_device *vdev) +{
- struct device *dev = vdev->dev;
- vdev->debug_root = debugfs_create_dir(dev_name(dev), vfio_pci_debugfs_root);
- debugfs_create_devm_seqfile(dev, "state", vdev->debug_root,
vfio_pci_vf_state_read);
+} +EXPORT_SYMBOL_GPL(vfio_pci_vf_debugfs_init);
+void vfio_pci_vf_debugfs_exit(struct vfio_device *vdev) +{
- debugfs_remove_recursive(vdev->debug_root);
+} +EXPORT_SYMBOL_GPL(vfio_pci_vf_debugfs_exit);
+void vfio_pci_debugfs_create_root(void) +{
- vfio_pci_debugfs_root = debugfs_create_dir("vfio_mig", NULL);
+} +EXPORT_SYMBOL_GPL(vfio_pci_debugfs_create_root);
+void vfio_pci_debugfs_remove_root(void) +{
- debugfs_remove_recursive(vfio_pci_debugfs_root);
- vfio_pci_debugfs_root = NULL;
+} +EXPORT_SYMBOL_GPL(vfio_pci_debugfs_remove_root);
Why are these exported symbols? The core code should handle this on its own.
I included this set of interfaces through the #ifdef CONFIG_DEBUG_FS macro in vfio_pci_debugfs.h. If EXPORT_SYMBOL_GPL is not added here, a compilation error will appear:
ERROR: modpost: "vfio_pci_vf_debugfs_exit" [drivers/vfio/pci/hisilicon/hisi-acc-vfio-pci.ko] undefined! ERROR: modpost: "vfio_pci_vf_debugfs_init" [drivers/vfio/pci/hisilicon/hisi-acc-vfio-pci.ko] undefined! scripts/Makefile.modpost:126: recipe for target 'Module.symvers' failed
If the device defines migration_get_state() then the debugfs should be created.
The trigger strategy created by the current debugfs is determined in the device driver according to the setting method of vfio_device_ops. If vfio_device_ops is enabled with live migration, then its migration_get_state() will also be enabled.
Mabye you need an op to populate the driver's debugfs to also trigger creating the directory
It is also possible to put this trigger strategy in the corresponding device driver, right? Putting this strategy in this public vfio_pci_debugfs.c will also increase the implementation complexity of this function.
Jason .
Thanks, Longfang.
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, I extracted a public function to replace it.
Signed-off-by: Longfang Liu liulongfang@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 51941bb4f31f..6a219b01c965 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); +} + /* * This function is called in all state_mutex unlock cases to * handle a 'deferred_reset' if exists. @@ -1042,8 +1048,7 @@ 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; @@ -1084,8 +1089,7 @@ 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; @@ -1301,8 +1305,7 @@ 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;
@@ -1325,8 +1328,7 @@ 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); @@ -1341,8 +1343,7 @@ 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);
On the debugfs framework of VFIO, register the debug function for the live migration driver of the hisilicon accelerator device.
On the basis of the original public debug function, a private debug function is added:
mig_data file: used to get the migration data of the live migration device mig_attr file: used to get device attributes of the live migration device debug file: used to test for acquiring and writing device state data for VF device.
Signed-off-by: Longfang Liu liulongfang@huawei.com --- .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 276 ++++++++++++++++++ .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h | 11 + 2 files changed, 287 insertions(+)
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c index 6a219b01c965..186a44091b59 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_pci_debugfs.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 +1320,259 @@ static long hisi_acc_vfio_pci_ioctl(struct vfio_device *core_vdev, unsigned int return vfio_pci_core_ioctl(core_vdev, cmd, arg); }
+static int hisi_acc_vf_debug_io(struct vfio_device *vdev) +{ + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev); + struct hisi_qm *vf_qm = &hisi_acc_vdev->vf_qm; + struct device *dev = vdev->dev; + u64 data; + int ret; + + ret = qm_wait_dev_not_ready(vf_qm); + if (ret) + dev_err(dev, "VF device not ready!\n"); + + data = readl(vf_qm->io_base + QM_MB_CMD_SEND_BASE); + dev_info(dev, "debug mailbox val: 0x%llx\n", data); + + return ret; +} + +static int hisi_acc_vf_debug_resume(struct vfio_device *vdev) +{ + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev); + struct hisi_acc_vf_migration_file *migf = hisi_acc_vdev->debug_migf; + struct device *dev = vdev->dev; + int ret; + + ret = vf_qm_state_save(hisi_acc_vdev, migf); + if (ret) { + dev_err(dev, "failed to save device data!\n"); + return -EINVAL; + } + + ret = vf_qm_check_match(hisi_acc_vdev, migf); + if (ret) { + dev_err(dev, "failed to match the VF!\n"); + return -EINVAL; + } + + ret = vf_qm_load_data(hisi_acc_vdev, migf); + if (ret) { + dev_err(dev, "failed to recover the VF!\n"); + return -EINVAL; + } + + vf_qm_fun_reset(&hisi_acc_vdev->vf_qm); + dev_info(dev, "successful to resume device data!\n"); + + return 0; +} + +static int hisi_acc_vf_debug_save(struct vfio_device *vdev) +{ + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev); + struct hisi_acc_vf_migration_file *migf = hisi_acc_vdev->debug_migf; + struct device *dev = vdev->dev; + int ret; + + ret = vf_qm_state_save(hisi_acc_vdev, migf); + if (ret) { + dev_err(dev, "failed to save device data!\n"); + return -EINVAL; + } + dev_info(dev, "successful to save device data!\n"); + + return 0; +} + +static int +hisi_acc_vf_debug_operate(struct vfio_device *vdev, unsigned int cmd) +{ + int ret; + + switch (cmd) { + case STATE_SAVE: + ret = hisi_acc_vf_debug_save(vdev); + if (ret) + return ret; + break; + case STATE_RESUME: + ret = hisi_acc_vf_debug_resume(vdev); + if (ret) + return ret; + break; + case RW_IO_TEST: + ret = hisi_acc_vf_debug_io(vdev); + if (ret) + return ret; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int hisi_acc_vf_debug_check(struct vfio_device *vdev) +{ + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev); + struct hisi_acc_vf_migration_file *migf = hisi_acc_vdev->debug_migf; + enum vfio_device_mig_state state; + + if (!vdev->mig_ops || !migf) { + dev_err(vdev->dev, "device not support debugfs!\n"); + return -EINVAL; + } + + /* If device not opened, the debugfs operation will trigger calltrace */ + (void)vdev->mig_ops->migration_get_state(vdev, &state); + if (state == VFIO_DEVICE_STATE_ERROR || + state == VFIO_DEVICE_STATE_STOP) { + dev_err(vdev->dev, "device not opened!\n"); + return -EINVAL; + } + + return 0; +} + +static ssize_t hisi_acc_vf_debug_write(struct file *filp, const char __user *buffer, + size_t count, loff_t *pos) +{ + struct vfio_device *vdev = filp->private_data; + char tbuf[VFIO_DEV_DBG_LEN]; + unsigned long cmd; + int len, ret; + + if (*pos) + return 0; + + if (count >= VFIO_DEV_DBG_LEN) + return -ENOSPC; + + ret = hisi_acc_vf_debug_check(vdev); + if (ret) + return -EINVAL; + + len = simple_write_to_buffer(tbuf, VFIO_DEV_DBG_LEN - 1, + pos, buffer, count); + if (len < 0 || len > VFIO_DEV_DBG_LEN - 1) + return -EINVAL; + tbuf[len] = '\0'; + if (kstrtoul(tbuf, 0, &cmd)) + return -EFAULT; + + ret = hisi_acc_vf_debug_operate(vdev, cmd); + if (ret) { + dev_err(vdev->dev, "device debug test failed!\n"); + return -EINVAL; + } + + return count; +} + +static const struct file_operations hisi_acc_vf_debug_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .write = hisi_acc_vf_debug_write, +}; + +static void seq_print_hex_data(struct seq_file *seq, const void *buf, size_t len) +{ +#define HEX_LINE_SIZE 131 +#define HEX_ROW_SIZE 16 + unsigned char linebuf[HEX_LINE_SIZE]; + int i, linelen, remaining = len; + const u8 *ptr = buf; + + for (i = 0; i < len; i += HEX_ROW_SIZE) { + linelen = min(remaining, HEX_ROW_SIZE); + remaining -= HEX_ROW_SIZE; + + hex_dump_to_buffer(ptr + i, linelen, HEX_ROW_SIZE, 1, + linebuf, sizeof(linebuf), false); + + seq_printf(seq, "%s%.8x: %s\n", "Mig Data:", i, linebuf); + } +} + +static int hisi_acc_vf_data_read(struct seq_file *seq, void *data) +{ + struct device *vf_dev = seq->private; + struct vfio_pci_core_device *core_device = dev_get_drvdata(vf_dev); + struct vfio_device *vdev = &core_device->vdev; + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev); + struct hisi_acc_vf_migration_file *debug_migf = hisi_acc_vdev->debug_migf; + size_t vf_data_sz = offsetofend(struct acc_vf_data, padding); + + if (debug_migf && debug_migf->total_length) + seq_print_hex_data(seq, (unsigned char *)&debug_migf->vf_data, + vf_data_sz); + else + seq_printf(seq, "%s\n", "device not migrated!"); + + return 0; +} + +static int hisi_acc_vf_attr_read(struct seq_file *seq, void *data) +{ + struct device *vf_dev = seq->private; + struct vfio_pci_core_device *core_device = dev_get_drvdata(vf_dev); + struct vfio_device *vdev = &core_device->vdev; + struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_get_vf_dev(vdev); + struct hisi_acc_vf_migration_file *debug_migf = hisi_acc_vdev->debug_migf; + + if (debug_migf && debug_migf->total_length) { + seq_printf(seq, + "acc device:\n" + "device state: %d\n" + "device ready: %u\n" + "data valid: %d\n" + "data size: %lu\n", + hisi_acc_vdev->mig_state, + hisi_acc_vdev->vf_qm_state, + debug_migf->disabled, + debug_migf->total_length); + } else { + seq_printf(seq, "%s\n", "device not migrated!"); + } + + return 0; +} + +static int hisi_acc_vfio_debug_init(struct hisi_acc_vf_core_device *hisi_acc_vdev) +{ + struct vfio_device *vdev = &hisi_acc_vdev->core_device.vdev; + struct device *dev = vdev->dev; + void *migf = NULL; + + vfio_pci_vf_debugfs_init(vdev); + + migf = kzalloc(sizeof(struct hisi_acc_vf_migration_file), GFP_KERNEL); + if (!migf) + return -ENOMEM; + + hisi_acc_vdev->debug_migf = migf; + + debugfs_create_devm_seqfile(dev, "mig_data", vdev->debug_root, + hisi_acc_vf_data_read); + debugfs_create_devm_seqfile(dev, "mig_attr", vdev->debug_root, + hisi_acc_vf_attr_read); + + debugfs_create_file("debug", 0200, vdev->debug_root, + vdev, &hisi_acc_vf_debug_fops); + + return 0; +} + +static void hisi_acc_vf_debugfs_exit(struct hisi_acc_vf_core_device *hisi_acc_vdev) +{ + struct vfio_device *vdev = &hisi_acc_vdev->core_device.vdev; + + kfree(hisi_acc_vdev->debug_migf); + vfio_pci_vf_debugfs_exit(vdev); +} + 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); @@ -1410,6 +1680,9 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device if (IS_ERR(hisi_acc_vdev)) return PTR_ERR(hisi_acc_vdev);
+ if (ops == &hisi_acc_vfio_pci_migrn_ops) + hisi_acc_vfio_debug_init(hisi_acc_vdev); + dev_set_drvdata(&pdev->dev, &hisi_acc_vdev->core_device); ret = vfio_pci_core_register_device(&hisi_acc_vdev->core_device); if (ret) @@ -1417,6 +1690,8 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device return 0;
out_put_vdev: + if (ops == &hisi_acc_vfio_pci_migrn_ops) + hisi_acc_vf_debugfs_exit(hisi_acc_vdev); vfio_put_device(&hisi_acc_vdev->core_device.vdev); return ret; } @@ -1425,6 +1700,7 @@ 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 */
On Sat, Dec 17, 2022 at 02:32:46PM +0800, Longfang Liu wrote:
On the debugfs framework of VFIO, register the debug function for the live migration driver of the hisilicon accelerator device.
On the basis of the original public debug function, a private debug function is added:
mig_data file: used to get the migration data of the live migration device mig_attr file: used to get device attributes of the live migration device debug file: used to test for acquiring and writing device state data for VF device.
Signed-off-by: Longfang Liu liulongfang@huawei.com
.../vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 276 ++++++++++++++++++ .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h | 11 + 2 files changed, 287 insertions(+)
You should put this all in its own file and not compile it when debugfs is turned off as well.
Jason
On 2023/1/3 23:07, Jason Gunthorpe Wrote:
On Sat, Dec 17, 2022 at 02:32:46PM +0800, Longfang Liu wrote:
On the debugfs framework of VFIO, register the debug function for the live migration driver of the hisilicon accelerator device.
On the basis of the original public debug function, a private debug function is added:
mig_data file: used to get the migration data of the live migration device mig_attr file: used to get device attributes of the live migration device debug file: used to test for acquiring and writing device state data for VF device.
Signed-off-by: Longfang Liu liulongfang@huawei.com
.../vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 276 ++++++++++++++++++ .../vfio/pci/hisilicon/hisi_acc_vfio_pci.h | 11 + 2 files changed, 287 insertions(+)
You should put this all in its own file and not compile it when debugfs is turned off as well.
Here use this macro #ifdef CONFIG_DEBUG_FS to wrap the creation part of debugfs. Do you think it can be handled like this?
Jason .
Thanks, Longfang.
Add a debugfs document description file to help users understand how to use the accelerator live migration driver's debugfs.
Signed-off-by: Longfang Liu liulongfang@huawei.com --- .../ABI/testing/debugfs-hisi-migration | 32 +++++++++++++++++++ 1 file changed, 32 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..a8cfc7688b88 --- /dev/null +++ b/Documentation/ABI/testing/debugfs-hisi-migration @@ -0,0 +1,32 @@ +What: /sys/kernel/debug/vfio_mig/<bdf>/state +Date: Nov 2022 +Contact: linux-kernel@vger.kernel.org +Description: Read the live migration status of the VF device. + The status of these live migrations includes: + ERROR, RUNNING, STOP, STOP_COPY, RESUMING. + +What: /sys/kernel/debug/vfio_mig/<bdf>/mig_data +Date: Nov 2022 +Contact: linux-kernel@vger.kernel.org +Description: Read the live migration data of the VF device. + The output format of the data is defined by the live + migration driver. + +What: /sys/kernel/debug/vfio_mig/<bdf>/mig_attr +Date: Nov 2022 +Contact: linux-kernel@vger.kernel.org +Description: Read the live migration attributes of the VF device. + The output format of the attributes is defined by the live + migration driver. + +What: /sys/kernel/debug/vfio_mig/<bdf>/debug +Date: Nov 2022 +Contact: linux-kernel@vger.kernel.org +Description: This debug file supports "echo" command write operations. + The command is actually represented by an integer number, and the + specific meaning is defined by the corresponding device driver. + For example, three commands are defined in the HiSilicon accelerator + live migration driver: + 0: State save + 1: State resume + 2: IO test
migration debugfs needs to perform debug operations based on the status of the current device. If the device is not loaded or has stopped, debugfs does not allow operations.
so, after the live migration function is executed and the device is turned off, the device no longer needs to be accessed. At this time, the status of the device needs to be set to stop.
Signed-off-by: Longfang Liu liulongfang@huawei.com --- drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 3 +++ drivers/vfio/pci/mlx5/main.c | 3 +++ 2 files changed, 6 insertions(+)
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c index 186a44091b59..3e58d635afb6 100644 --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c @@ -1601,6 +1601,9 @@ 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;
+ if (core_vdev->mig_ops) + hisi_acc_vdev->mig_state = VFIO_DEVICE_STATE_STOP; + iounmap(vf_qm->io_base); vfio_pci_core_close_device(core_vdev); } diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c index 031ac8cc215d..64b2fe58355a 100644 --- a/drivers/vfio/pci/mlx5/main.c +++ b/drivers/vfio/pci/mlx5/main.c @@ -1092,6 +1092,9 @@ static void mlx5vf_pci_close_device(struct vfio_device *core_vdev) struct mlx5vf_pci_core_device *mvdev = container_of( core_vdev, struct mlx5vf_pci_core_device, core_device.vdev);
+ if (mvdev->migrate_cap) + mvdev->mig_state = VFIO_DEVICE_STATE_STOP; + mlx5vf_cmd_close_migratable(mvdev); vfio_pci_core_close_device(core_vdev); }