Merge tag 'vfio-v6.2-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Replace deprecated git://github.com link in MAINTAINERS (Palmer
   Dabbelt)

 - Simplify vfio/mlx5 with module_pci_driver() helper (Shang XiaoJing)

 - Drop unnecessary buffer from ACPI call (Rafael Mendonca)

 - Correct latent missing include issue in iova-bitmap and fix support
   for unaligned bitmaps. Follow-up with better fix through refactor
   (Joao Martins)

 - Rework ccw mdev driver to split private data from parent structure,
   better aligning with the mdev lifecycle and allowing us to remove a
   temporary workaround (Eric Farman)

 - Add an interface to get an estimated migration data size for a
   device, allowing userspace to make informed decisions, ex. more
   accurately predicting VM downtime (Yishai Hadas)

 - Fix minor typo in vfio/mlx5 array declaration (Yishai Hadas)

 - Simplify module and Kconfig through consolidating SPAPR/EEH code and
   config options and folding virqfd module into main vfio module (Jason
   Gunthorpe)

 - Fix error path from device_register() across all vfio mdev and sample
   drivers (Alex Williamson)

 - Define migration pre-copy interface and implement for vfio/mlx5
   devices, allowing portions of the device state to be saved while the
   device continues operation, towards reducing the stop-copy state size
   (Jason Gunthorpe, Yishai Hadas, Shay Drory)

 - Implement pre-copy for hisi_acc devices (Shameer Kolothum)

 - Fixes to mdpy mdev driver remove path and error path on probe (Shang
   XiaoJing)

 - vfio/mlx5 fixes for incorrect return after copy_to_user() fault and
   incorrect buffer freeing (Dan Carpenter)

* tag 'vfio-v6.2-rc1' of https://github.com/awilliam/linux-vfio: (42 commits)
  vfio/mlx5: error pointer dereference in error handling
  vfio/mlx5: fix error code in mlx5vf_precopy_ioctl()
  samples: vfio-mdev: Fix missing pci_disable_device() in mdpy_fb_probe()
  hisi_acc_vfio_pci: Enable PRE_COPY flag
  hisi_acc_vfio_pci: Move the dev compatibility tests for early check
  hisi_acc_vfio_pci: Introduce support for PRE_COPY state transitions
  hisi_acc_vfio_pci: Add support for precopy IOCTL
  vfio/mlx5: Enable MIGRATION_PRE_COPY flag
  vfio/mlx5: Fallback to STOP_COPY upon specific PRE_COPY error
  vfio/mlx5: Introduce multiple loads
  vfio/mlx5: Consider temporary end of stream as part of PRE_COPY
  vfio/mlx5: Introduce vfio precopy ioctl implementation
  vfio/mlx5: Introduce SW headers for migration states
  vfio/mlx5: Introduce device transitions of PRE_COPY
  vfio/mlx5: Refactor to use queue based data chunks
  vfio/mlx5: Refactor migration file state
  vfio/mlx5: Refactor MKEY usage
  vfio/mlx5: Refactor PD usage
  vfio/mlx5: Enforce a single SAVE command at a time
  vfio: Extend the device migration protocol with PRE_COPY
  ...

2 files changed, 142 insertions, 16 deletions

diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 40019b11c5a9..0bba3b05c6c7 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -360,8 +360,8 @@ static int vf_qm_check_match(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	u32 que_iso_state;
 	int ret;
 
-	if (migf->total_length < QM_MATCH_SIZE)
-		return -EINVAL;
+	if (migf->total_length < QM_MATCH_SIZE || hisi_acc_vdev->match_done)
+		return 0;
 
 	if (vf_data->acc_magic != ACC_DEV_MAGIC) {
 		dev_err(dev, "failed to match ACC_DEV_MAGIC\n");
@@ -406,6 +406,7 @@ static int vf_qm_check_match(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	}
 
 	hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
+	hisi_acc_vdev->match_done = true;
 	return 0;
 }
 
@@ -493,10 +494,6 @@ static int vf_qm_state_save(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	struct device *dev = &vf_qm->pdev->dev;
 	int ret;
 
-	ret = vf_qm_get_match_data(hisi_acc_vdev, vf_data);
-	if (ret)
-		return 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;
@@ -673,12 +670,6 @@ static int hisi_acc_vf_load_state(struct hisi_acc_vf_core_device *hisi_acc_vdev)
 	struct hisi_acc_vf_migration_file *migf = hisi_acc_vdev->resuming_migf;
 	int ret;
 
-	/* Check dev compatibility */
-	ret = vf_qm_check_match(hisi_acc_vdev, migf);
-	if (ret) {
-		dev_err(dev, "failed to match the VF!\n");
-		return ret;
-	}
 	/* Recover data to VF */
 	ret = vf_qm_load_data(hisi_acc_vdev, migf);
 	if (ret) {
@@ -732,6 +723,10 @@ static ssize_t hisi_acc_vf_resume_write(struct file *filp, const char __user *bu
 	*pos += len;
 	done = len;
 	migf->total_length += len;
+
+	ret = vf_qm_check_match(migf->hisi_acc_vdev, migf);
+	if (ret)
+		done = -EFAULT;
 out_unlock:
 	mutex_unlock(&migf->lock);
 	return done;
@@ -764,9 +759,58 @@ hisi_acc_vf_pci_resume(struct hisi_acc_vf_core_device *hisi_acc_vdev)
 
 	stream_open(migf->filp->f_inode, migf->filp);
 	mutex_init(&migf->lock);
+	migf->hisi_acc_vdev = hisi_acc_vdev;
 	return migf;
 }
 
+static long hisi_acc_vf_precopy_ioctl(struct file *filp,
+				      unsigned int cmd, unsigned long arg)
+{
+	struct hisi_acc_vf_migration_file *migf = filp->private_data;
+	struct hisi_acc_vf_core_device *hisi_acc_vdev = migf->hisi_acc_vdev;
+	loff_t *pos = &filp->f_pos;
+	struct vfio_precopy_info info;
+	unsigned long minsz;
+	int ret;
+
+	if (cmd != VFIO_MIG_GET_PRECOPY_INFO)
+		return -ENOTTY;
+
+	minsz = offsetofend(struct vfio_precopy_info, dirty_bytes);
+
+	if (copy_from_user(&info, (void __user *)arg, minsz))
+		return -EFAULT;
+	if (info.argsz < minsz)
+		return -EINVAL;
+
+	mutex_lock(&hisi_acc_vdev->state_mutex);
+	if (hisi_acc_vdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY) {
+		mutex_unlock(&hisi_acc_vdev->state_mutex);
+		return -EINVAL;
+	}
+
+	mutex_lock(&migf->lock);
+
+	if (migf->disabled) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	if (*pos > migf->total_length) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	info.dirty_bytes = 0;
+	info.initial_bytes = migf->total_length - *pos;
+
+	ret = copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
+out:
+	mutex_unlock(&migf->lock);
+	mutex_unlock(&hisi_acc_vdev->state_mutex);
+	return ret;
+}
+
 static ssize_t hisi_acc_vf_save_read(struct file *filp, char __user *buf, size_t len,
 				     loff_t *pos)
 {
@@ -807,12 +851,14 @@ out_unlock:
 static const struct file_operations hisi_acc_vf_save_fops = {
 	.owner = THIS_MODULE,
 	.read = hisi_acc_vf_save_read,
+	.unlocked_ioctl = hisi_acc_vf_precopy_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
 	.release = hisi_acc_vf_release_file,
 	.llseek = no_llseek,
 };
 
 static struct hisi_acc_vf_migration_file *
-hisi_acc_vf_stop_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev)
+hisi_acc_open_saving_migf(struct hisi_acc_vf_core_device *hisi_acc_vdev)
 {
 	struct hisi_acc_vf_migration_file *migf;
 	int ret;
@@ -832,8 +878,9 @@ hisi_acc_vf_stop_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev)
 
 	stream_open(migf->filp->f_inode, migf->filp);
 	mutex_init(&migf->lock);
+	migf->hisi_acc_vdev = hisi_acc_vdev;
 
-	ret = vf_qm_state_save(hisi_acc_vdev, migf);
+	ret = vf_qm_get_match_data(hisi_acc_vdev, &migf->vf_data);
 	if (ret) {
 		fput(migf->filp);
 		return ERR_PTR(ret);
@@ -842,6 +889,44 @@ hisi_acc_vf_stop_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev)
 	return migf;
 }
 
+static struct hisi_acc_vf_migration_file *
+hisi_acc_vf_pre_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev)
+{
+	struct hisi_acc_vf_migration_file *migf;
+
+	migf = hisi_acc_open_saving_migf(hisi_acc_vdev);
+	if (IS_ERR(migf))
+		return migf;
+
+	migf->total_length = QM_MATCH_SIZE;
+	return migf;
+}
+
+static struct hisi_acc_vf_migration_file *
+hisi_acc_vf_stop_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev, bool open)
+{
+	int ret;
+	struct hisi_acc_vf_migration_file *migf = NULL;
+
+	if (open) {
+		/*
+		 * Userspace didn't use PRECOPY support. Hence saving_migf
+		 * is not opened yet.
+		 */
+		migf = hisi_acc_open_saving_migf(hisi_acc_vdev);
+		if (IS_ERR(migf))
+			return migf;
+	} else {
+		migf = hisi_acc_vdev->saving_migf;
+	}
+
+	ret = vf_qm_state_save(hisi_acc_vdev, migf);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return open ? migf : NULL;
+}
+
 static int hisi_acc_vf_stop_device(struct hisi_acc_vf_core_device *hisi_acc_vdev)
 {
 	struct device *dev = &hisi_acc_vdev->vf_dev->dev;
@@ -869,6 +954,31 @@ hisi_acc_vf_set_device_state(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	u32 cur = hisi_acc_vdev->mig_state;
 	int ret;
 
+	if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_PRE_COPY) {
+		struct hisi_acc_vf_migration_file *migf;
+
+		migf = hisi_acc_vf_pre_copy(hisi_acc_vdev);
+		if (IS_ERR(migf))
+			return ERR_CAST(migf);
+		get_file(migf->filp);
+		hisi_acc_vdev->saving_migf = migf;
+		return migf->filp;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_STOP_COPY) {
+		struct hisi_acc_vf_migration_file *migf;
+
+		ret = hisi_acc_vf_stop_device(hisi_acc_vdev);
+		if (ret)
+			return ERR_PTR(ret);
+
+		migf = hisi_acc_vf_stop_copy(hisi_acc_vdev, false);
+		if (IS_ERR(migf))
+			return ERR_CAST(migf);
+
+		return NULL;
+	}
+
 	if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_STOP) {
 		ret = hisi_acc_vf_stop_device(hisi_acc_vdev);
 		if (ret)
@@ -879,7 +989,7 @@ hisi_acc_vf_set_device_state(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 	if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_STOP_COPY) {
 		struct hisi_acc_vf_migration_file *migf;
 
-		migf = hisi_acc_vf_stop_copy(hisi_acc_vdev);
+		migf = hisi_acc_vf_stop_copy(hisi_acc_vdev, true);
 		if (IS_ERR(migf))
 			return ERR_CAST(migf);
 		get_file(migf->filp);
@@ -911,6 +1021,11 @@ hisi_acc_vf_set_device_state(struct hisi_acc_vf_core_device *hisi_acc_vdev,
 		return NULL;
 	}
 
+	if (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_RUNNING) {
+		hisi_acc_vf_disable_fds(hisi_acc_vdev);
+		return NULL;
+	}
+
 	if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_RUNNING) {
 		hisi_acc_vf_start_device(hisi_acc_vdev);
 		return NULL;
@@ -958,6 +1073,14 @@ hisi_acc_vfio_pci_set_device_state(struct vfio_device *vdev,
 }
 
 static int
+hisi_acc_vfio_pci_get_data_size(struct vfio_device *vdev,
+				unsigned long *stop_copy_length)
+{
+	*stop_copy_length = sizeof(struct acc_vf_data);
+	return 0;
+}
+
+static int
 hisi_acc_vfio_pci_get_device_state(struct vfio_device *vdev,
 				   enum vfio_device_mig_state *curr_state)
 {
@@ -1213,6 +1336,7 @@ static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev)
 static const struct vfio_migration_ops hisi_acc_vfio_pci_migrn_state_ops = {
 	.migration_set_state = hisi_acc_vfio_pci_set_device_state,
 	.migration_get_state = hisi_acc_vfio_pci_get_device_state,
+	.migration_get_data_size = hisi_acc_vfio_pci_get_data_size,
 };
 
 static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
@@ -1227,7 +1351,7 @@ static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
 	hisi_acc_vdev->vf_dev = pdev;
 	mutex_init(&hisi_acc_vdev->state_mutex);
 
-	core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY;
+	core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY;
 	core_vdev->mig_ops = &hisi_acc_vfio_pci_migrn_state_ops;
 
 	return vfio_pci_core_init_dev(core_vdev);
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
index 67343325b320..dcabfeec6ca1 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
@@ -91,12 +91,14 @@ struct hisi_acc_vf_migration_file {
 	struct mutex lock;
 	bool disabled;
 
+	struct hisi_acc_vf_core_device *hisi_acc_vdev;
 	struct acc_vf_data vf_data;
 	size_t total_length;
 };
 
 struct hisi_acc_vf_core_device {
 	struct vfio_pci_core_device core_device;
+	u8 match_done:1;
 	u8 deferred_reset:1;
 	/* For migration state */
 	struct mutex state_mutex;