summaryrefslogtreecommitdiff
path: root/drivers/vfio/pci/mlx5/main.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/vfio/pci/mlx5/main.c')
-rw-r--r--drivers/vfio/pci/mlx5/main.c136
1 files changed, 62 insertions, 74 deletions
diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index bbec5d288fee..0558d0649ddb 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -17,7 +17,6 @@
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include <linux/sched/mm.h>
-#include <linux/vfio_pci_core.h>
#include <linux/anon_inodes.h>
#include "cmd.h"
@@ -25,19 +24,13 @@
/* Arbitrary to prevent userspace from consuming endless memory */
#define MAX_MIGRATION_SIZE (512*1024*1024)
-struct mlx5vf_pci_core_device {
- struct vfio_pci_core_device core_device;
- u16 vhca_id;
- u8 migrate_cap:1;
- u8 deferred_reset:1;
- /* protect migration state */
- struct mutex state_mutex;
- enum vfio_device_mig_state mig_state;
- /* protect the reset_done flow */
- spinlock_t reset_lock;
- struct mlx5_vf_migration_file *resuming_migf;
- struct mlx5_vf_migration_file *saving_migf;
-};
+static struct mlx5vf_pci_core_device *mlx5vf_drvdata(struct pci_dev *pdev)
+{
+ struct vfio_pci_core_device *core_device = dev_get_drvdata(&pdev->dev);
+
+ return container_of(core_device, struct mlx5vf_pci_core_device,
+ core_device);
+}
static struct page *
mlx5vf_get_migration_page(struct mlx5_vf_migration_file *migf,
@@ -149,12 +142,22 @@ static ssize_t mlx5vf_save_read(struct file *filp, char __user *buf, size_t len,
return -ESPIPE;
pos = &filp->f_pos;
+ if (!(filp->f_flags & O_NONBLOCK)) {
+ if (wait_event_interruptible(migf->poll_wait,
+ READ_ONCE(migf->total_length) || migf->is_err))
+ return -ERESTARTSYS;
+ }
+
mutex_lock(&migf->lock);
+ if ((filp->f_flags & O_NONBLOCK) && !READ_ONCE(migf->total_length)) {
+ done = -EAGAIN;
+ goto out_unlock;
+ }
if (*pos > migf->total_length) {
done = -EINVAL;
goto out_unlock;
}
- if (migf->disabled) {
+ if (migf->disabled || migf->is_err) {
done = -ENODEV;
goto out_unlock;
}
@@ -194,9 +197,28 @@ out_unlock:
return done;
}
+static __poll_t mlx5vf_save_poll(struct file *filp,
+ struct poll_table_struct *wait)
+{
+ struct mlx5_vf_migration_file *migf = filp->private_data;
+ __poll_t pollflags = 0;
+
+ poll_wait(filp, &migf->poll_wait, wait);
+
+ mutex_lock(&migf->lock);
+ if (migf->disabled || migf->is_err)
+ pollflags = EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
+ else if (READ_ONCE(migf->total_length))
+ pollflags = EPOLLIN | EPOLLRDNORM;
+ mutex_unlock(&migf->lock);
+
+ return pollflags;
+}
+
static const struct file_operations mlx5vf_save_fops = {
.owner = THIS_MODULE,
.read = mlx5vf_save_read,
+ .poll = mlx5vf_save_poll,
.release = mlx5vf_release_file,
.llseek = no_llseek,
};
@@ -222,9 +244,11 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev)
stream_open(migf->filp->f_inode, migf->filp);
mutex_init(&migf->lock);
-
- ret = mlx5vf_cmd_query_vhca_migration_state(
- mvdev->core_device.pdev, mvdev->vhca_id, &migf->total_length);
+ init_waitqueue_head(&migf->poll_wait);
+ mlx5_cmd_init_async_ctx(mvdev->mdev, &migf->async_ctx);
+ INIT_WORK(&migf->async_data.work, mlx5vf_mig_file_cleanup_cb);
+ ret = mlx5vf_cmd_query_vhca_migration_state(mvdev,
+ &migf->total_length);
if (ret)
goto out_free;
@@ -233,8 +257,8 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev)
if (ret)
goto out_free;
- ret = mlx5vf_cmd_save_vhca_state(mvdev->core_device.pdev,
- mvdev->vhca_id, migf);
+ migf->mvdev = mvdev;
+ ret = mlx5vf_cmd_save_vhca_state(mvdev, migf);
if (ret)
goto out_free;
return migf;
@@ -339,7 +363,7 @@ mlx5vf_pci_resume_device_data(struct mlx5vf_pci_core_device *mvdev)
return migf;
}
-static void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev)
+void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev)
{
if (mvdev->resuming_migf) {
mlx5vf_disable_fd(mvdev->resuming_migf);
@@ -347,6 +371,8 @@ static void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev)
mvdev->resuming_migf = NULL;
}
if (mvdev->saving_migf) {
+ mlx5_cmd_cleanup_async_ctx(&mvdev->saving_migf->async_ctx);
+ cancel_work_sync(&mvdev->saving_migf->async_data.work);
mlx5vf_disable_fd(mvdev->saving_migf);
fput(mvdev->saving_migf->filp);
mvdev->saving_migf = NULL;
@@ -361,8 +387,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
int ret;
if (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_STOP) {
- ret = mlx5vf_cmd_suspend_vhca(
- mvdev->core_device.pdev, mvdev->vhca_id,
+ ret = mlx5vf_cmd_suspend_vhca(mvdev,
MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_RESPONDER);
if (ret)
return ERR_PTR(ret);
@@ -370,8 +395,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
}
if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_RUNNING_P2P) {
- ret = mlx5vf_cmd_resume_vhca(
- mvdev->core_device.pdev, mvdev->vhca_id,
+ ret = mlx5vf_cmd_resume_vhca(mvdev,
MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_RESPONDER);
if (ret)
return ERR_PTR(ret);
@@ -379,8 +403,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
}
if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) {
- ret = mlx5vf_cmd_suspend_vhca(
- mvdev->core_device.pdev, mvdev->vhca_id,
+ ret = mlx5vf_cmd_suspend_vhca(mvdev,
MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_INITIATOR);
if (ret)
return ERR_PTR(ret);
@@ -388,8 +411,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
}
if (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) {
- ret = mlx5vf_cmd_resume_vhca(
- mvdev->core_device.pdev, mvdev->vhca_id,
+ ret = mlx5vf_cmd_resume_vhca(mvdev,
MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_INITIATOR);
if (ret)
return ERR_PTR(ret);
@@ -424,8 +446,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
}
if (cur == VFIO_DEVICE_STATE_RESUMING && new == VFIO_DEVICE_STATE_STOP) {
- ret = mlx5vf_cmd_load_vhca_state(mvdev->core_device.pdev,
- mvdev->vhca_id,
+ ret = mlx5vf_cmd_load_vhca_state(mvdev,
mvdev->resuming_migf);
if (ret)
return ERR_PTR(ret);
@@ -444,7 +465,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
* This function is called in all state_mutex unlock cases to
* handle a 'deferred_reset' if exists.
*/
-static void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev)
+void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev)
{
again:
spin_lock(&mvdev->reset_lock);
@@ -505,7 +526,7 @@ static int mlx5vf_pci_get_device_state(struct vfio_device *vdev,
static void mlx5vf_pci_aer_reset_done(struct pci_dev *pdev)
{
- struct mlx5vf_pci_core_device *mvdev = dev_get_drvdata(&pdev->dev);
+ struct mlx5vf_pci_core_device *mvdev = mlx5vf_drvdata(pdev);
if (!mvdev->migrate_cap)
return;
@@ -532,34 +553,16 @@ static int mlx5vf_pci_open_device(struct vfio_device *core_vdev)
struct mlx5vf_pci_core_device *mvdev = container_of(
core_vdev, struct mlx5vf_pci_core_device, core_device.vdev);
struct vfio_pci_core_device *vdev = &mvdev->core_device;
- int vf_id;
int ret;
ret = vfio_pci_core_enable(vdev);
if (ret)
return ret;
- if (!mvdev->migrate_cap) {
- vfio_pci_core_finish_enable(vdev);
- return 0;
- }
-
- vf_id = pci_iov_vf_id(vdev->pdev);
- if (vf_id < 0) {
- ret = vf_id;
- goto out_disable;
- }
-
- ret = mlx5vf_cmd_get_vhca_id(vdev->pdev, vf_id + 1, &mvdev->vhca_id);
- if (ret)
- goto out_disable;
-
- mvdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+ if (mvdev->migrate_cap)
+ mvdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
vfio_pci_core_finish_enable(vdev);
return 0;
-out_disable:
- vfio_pci_core_disable(vdev);
- return ret;
}
static void mlx5vf_pci_close_device(struct vfio_device *core_vdev)
@@ -596,32 +599,15 @@ static int mlx5vf_pci_probe(struct pci_dev *pdev,
if (!mvdev)
return -ENOMEM;
vfio_pci_core_init_device(&mvdev->core_device, pdev, &mlx5vf_pci_ops);
-
- if (pdev->is_virtfn) {
- struct mlx5_core_dev *mdev =
- mlx5_vf_get_core_dev(pdev);
-
- if (mdev) {
- if (MLX5_CAP_GEN(mdev, migration)) {
- mvdev->migrate_cap = 1;
- mvdev->core_device.vdev.migration_flags =
- VFIO_MIGRATION_STOP_COPY |
- VFIO_MIGRATION_P2P;
- mutex_init(&mvdev->state_mutex);
- spin_lock_init(&mvdev->reset_lock);
- }
- mlx5_vf_put_core_dev(mdev);
- }
- }
-
+ mlx5vf_cmd_set_migratable(mvdev);
+ dev_set_drvdata(&pdev->dev, &mvdev->core_device);
ret = vfio_pci_core_register_device(&mvdev->core_device);
if (ret)
goto out_free;
-
- dev_set_drvdata(&pdev->dev, mvdev);
return 0;
out_free:
+ mlx5vf_cmd_remove_migratable(mvdev);
vfio_pci_core_uninit_device(&mvdev->core_device);
kfree(mvdev);
return ret;
@@ -629,9 +615,10 @@ out_free:
static void mlx5vf_pci_remove(struct pci_dev *pdev)
{
- struct mlx5vf_pci_core_device *mvdev = dev_get_drvdata(&pdev->dev);
+ struct mlx5vf_pci_core_device *mvdev = mlx5vf_drvdata(pdev);
vfio_pci_core_unregister_device(&mvdev->core_device);
+ mlx5vf_cmd_remove_migratable(mvdev);
vfio_pci_core_uninit_device(&mvdev->core_device);
kfree(mvdev);
}
@@ -654,6 +641,7 @@ static struct pci_driver mlx5vf_pci_driver = {
.probe = mlx5vf_pci_probe,
.remove = mlx5vf_pci_remove,
.err_handler = &mlx5vf_err_handlers,
+ .driver_managed_dma = true,
};
static void __exit mlx5vf_pci_cleanup(void)
generated by cgit v1.2.3 (git 2.46.0) at 2025-07-01 09:35:07 +0000