Merge tag 'vfio-v5.19-rc1' of https://github.com/awilliam/linux-vfio

Pull vfio updates from Alex Williamson:

 - Improvements to mlx5 vfio-pci variant driver, including support for
   parallel migration per PF (Yishai Hadas)

 - Remove redundant iommu_present() check (Robin Murphy)

 - Ongoing refactoring to consolidate the VFIO driver facing API to use
   vfio_device (Jason Gunthorpe)

 - Use drvdata to store vfio_device among all vfio-pci and variant
   drivers (Jason Gunthorpe)

 - Remove redundant code now that IOMMU core manages group DMA ownership
   (Jason Gunthorpe)

 - Remove vfio_group from external API handling struct file ownership
   (Jason Gunthorpe)

 - Correct typo in uapi comments (Thomas Huth)

 - Fix coccicheck detected deadlock (Wan Jiabing)

 - Use rwsem to remove races and simplify code around container and kvm
   association to groups (Jason Gunthorpe)

 - Harden access to devices in low power states and use runtime PM to
   enable d3cold support for unused devices (Abhishek Sahu)

 - Fix dma_owner handling of fake IOMMU groups (Jason Gunthorpe)

 - Set driver_managed_dma on vfio-pci variant drivers (Jason Gunthorpe)

 - Pass KVM pointer directly rather than via notifier (Matthew Rosato)

* tag 'vfio-v5.19-rc1' of https://github.com/awilliam/linux-vfio: (38 commits)
  vfio: remove VFIO_GROUP_NOTIFY_SET_KVM
  vfio/pci: Add driver_managed_dma to the new vfio_pci drivers
  vfio: Do not manipulate iommu dma_owner for fake iommu groups
  vfio/pci: Move the unused device into low power state with runtime PM
  vfio/pci: Virtualize PME related registers bits and initialize to zero
  vfio/pci: Change the PF power state to D0 before enabling VFs
  vfio/pci: Invalidate mmaps and block the access in D3hot power state
  vfio: Change struct vfio_group::container_users to a non-atomic int
  vfio: Simplify the life cycle of the group FD
  vfio: Fully lock struct vfio_group::container
  vfio: Split up vfio_group_get_device_fd()
  vfio: Change struct vfio_group::opened from an atomic to bool
  vfio: Add missing locking for struct vfio_group::kvm
  kvm/vfio: Fix potential deadlock problem in vfio
  include/uapi/linux/vfio.h: Fix trivial typo - _IORW should be _IOWR instead
  vfio/pci: Use the struct file as the handle not the vfio_group
  kvm/vfio: Remove vfio_group from kvm
  vfio: Change vfio_group_set_kvm() to vfio_file_set_kvm()
  vfio: Change vfio_external_check_extension() to vfio_file_enforced_coherent()
  vfio: Remove vfio_external_group_match_file()
  ...

6 files changed, 46 insertions, 68 deletions

diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 8d1b2771c1aa..0c2be9421ab7 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -16,6 +16,7 @@
 #include <asm/idals.h>
 
 #include "vfio_ccw_cp.h"
+#include "vfio_ccw_private.h"
 
 struct pfn_array {
 	/* Starting guest physical I/O address. */
@@ -98,17 +99,17 @@ static int pfn_array_alloc(struct pfn_array *pa, u64 iova, unsigned int len)
  * If the pin request partially succeeds, or fails completely,
  * all pages are left unpinned and a negative error value is returned.
  */
-static int pfn_array_pin(struct pfn_array *pa, struct device *mdev)
+static int pfn_array_pin(struct pfn_array *pa, struct vfio_device *vdev)
 {
 	int ret = 0;
 
-	ret = vfio_pin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr,
+	ret = vfio_pin_pages(vdev, pa->pa_iova_pfn, pa->pa_nr,
 			     IOMMU_READ | IOMMU_WRITE, pa->pa_pfn);
 
 	if (ret < 0) {
 		goto err_out;
 	} else if (ret > 0 && ret != pa->pa_nr) {
-		vfio_unpin_pages(mdev, pa->pa_iova_pfn, ret);
+		vfio_unpin_pages(vdev, pa->pa_iova_pfn, ret);
 		ret = -EINVAL;
 		goto err_out;
 	}
@@ -122,11 +123,11 @@ err_out:
 }
 
 /* Unpin the pages before releasing the memory. */
-static void pfn_array_unpin_free(struct pfn_array *pa, struct device *mdev)
+static void pfn_array_unpin_free(struct pfn_array *pa, struct vfio_device *vdev)
 {
 	/* Only unpin if any pages were pinned to begin with */
 	if (pa->pa_nr)
-		vfio_unpin_pages(mdev, pa->pa_iova_pfn, pa->pa_nr);
+		vfio_unpin_pages(vdev, pa->pa_iova_pfn, pa->pa_nr);
 	pa->pa_nr = 0;
 	kfree(pa->pa_iova_pfn);
 }
@@ -190,8 +191,7 @@ static void convert_ccw0_to_ccw1(struct ccw1 *source, unsigned long len)
  * Within the domain (@mdev), copy @n bytes from a guest physical
  * address (@iova) to a host physical address (@to).
  */
-static long copy_from_iova(struct device *mdev,
-			   void *to, u64 iova,
+static long copy_from_iova(struct vfio_device *vdev, void *to, u64 iova,
 			   unsigned long n)
 {
 	struct pfn_array pa = {0};
@@ -203,9 +203,9 @@ static long copy_from_iova(struct device *mdev,
 	if (ret < 0)
 		return ret;
 
-	ret = pfn_array_pin(&pa, mdev);
+	ret = pfn_array_pin(&pa, vdev);
 	if (ret < 0) {
-		pfn_array_unpin_free(&pa, mdev);
+		pfn_array_unpin_free(&pa, vdev);
 		return ret;
 	}
 
@@ -226,7 +226,7 @@ static long copy_from_iova(struct device *mdev,
 			break;
 	}
 
-	pfn_array_unpin_free(&pa, mdev);
+	pfn_array_unpin_free(&pa, vdev);
 
 	return l;
 }
@@ -423,11 +423,13 @@ static int ccwchain_loop_tic(struct ccwchain *chain,
 
 static int ccwchain_handle_ccw(u32 cda, struct channel_program *cp)
 {
+	struct vfio_device *vdev =
+		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	struct ccwchain *chain;
 	int len, ret;
 
 	/* Copy 2K (the most we support today) of possible CCWs */
-	len = copy_from_iova(cp->mdev, cp->guest_cp, cda,
+	len = copy_from_iova(vdev, cp->guest_cp, cda,
 			     CCWCHAIN_LEN_MAX * sizeof(struct ccw1));
 	if (len)
 		return len;
@@ -508,6 +510,8 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 				 int idx,
 				 struct channel_program *cp)
 {
+	struct vfio_device *vdev =
+		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	struct ccw1 *ccw;
 	struct pfn_array *pa;
 	u64 iova;
@@ -526,7 +530,7 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 	if (ccw_is_idal(ccw)) {
 		/* Read first IDAW to see if it's 4K-aligned or not. */
 		/* All subsequent IDAws will be 4K-aligned. */
-		ret = copy_from_iova(cp->mdev, &iova, ccw->cda, sizeof(iova));
+		ret = copy_from_iova(vdev, &iova, ccw->cda, sizeof(iova));
 		if (ret)
 			return ret;
 	} else {
@@ -555,7 +559,7 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 
 	if (ccw_is_idal(ccw)) {
 		/* Copy guest IDAL into host IDAL */
-		ret = copy_from_iova(cp->mdev, idaws, ccw->cda, idal_len);
+		ret = copy_from_iova(vdev, idaws, ccw->cda, idal_len);
 		if (ret)
 			goto out_unpin;
 
@@ -574,7 +578,7 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 	}
 
 	if (ccw_does_data_transfer(ccw)) {
-		ret = pfn_array_pin(pa, cp->mdev);
+		ret = pfn_array_pin(pa, vdev);
 		if (ret < 0)
 			goto out_unpin;
 	} else {
@@ -590,7 +594,7 @@ static int ccwchain_fetch_direct(struct ccwchain *chain,
 	return 0;
 
 out_unpin:
-	pfn_array_unpin_free(pa, cp->mdev);
+	pfn_array_unpin_free(pa, vdev);
 out_free_idaws:
 	kfree(idaws);
 out_init:
@@ -632,8 +636,10 @@ static int ccwchain_fetch_one(struct ccwchain *chain,
  * Returns:
  *   %0 on success and a negative error value on failure.
  */
-int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
+int cp_init(struct channel_program *cp, union orb *orb)
 {
+	struct vfio_device *vdev =
+		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	/* custom ratelimit used to avoid flood during guest IPL */
 	static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 1);
 	int ret;
@@ -650,11 +656,12 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
 	 * the problem if something does break.
 	 */
 	if (!orb->cmd.pfch && __ratelimit(&ratelimit_state))
-		dev_warn(mdev, "Prefetching channel program even though prefetch not specified in ORB");
+		dev_warn(
+			vdev->dev,
+			"Prefetching channel program even though prefetch not specified in ORB");
 
 	INIT_LIST_HEAD(&cp->ccwchain_list);
 	memcpy(&cp->orb, orb, sizeof(*orb));
-	cp->mdev = mdev;
 
 	/* Build a ccwchain for the first CCW segment */
 	ret = ccwchain_handle_ccw(orb->cmd.cpa, cp);
@@ -682,6 +689,8 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
  */
 void cp_free(struct channel_program *cp)
 {
+	struct vfio_device *vdev =
+		&container_of(cp, struct vfio_ccw_private, cp)->vdev;
 	struct ccwchain *chain, *temp;
 	int i;
 
@@ -691,7 +700,7 @@ void cp_free(struct channel_program *cp)
 	cp->initialized = false;
 	list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) {
 		for (i = 0; i < chain->ch_len; i++) {
-			pfn_array_unpin_free(chain->ch_pa + i, cp->mdev);
+			pfn_array_unpin_free(chain->ch_pa + i, vdev);
 			ccwchain_cda_free(chain, i);
 		}
 		ccwchain_free(chain);
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
index ba31240ce965..e4c436199b4c 100644
--- a/drivers/s390/cio/vfio_ccw_cp.h
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -37,13 +37,11 @@
 struct channel_program {
 	struct list_head ccwchain_list;
 	union orb orb;
-	struct device *mdev;
 	bool initialized;
 	struct ccw1 *guest_cp;
 };
 
-extern int cp_init(struct channel_program *cp, struct device *mdev,
-		   union orb *orb);
+extern int cp_init(struct channel_program *cp, union orb *orb);
 extern void cp_free(struct channel_program *cp);
 extern int cp_prefetch(struct channel_program *cp);
 extern union orb *cp_get_orb(struct channel_program *cp, u32 intparm, u8 lpm);
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index e435a9cd92da..8483a266051c 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -262,8 +262,7 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 			errstr = "transport mode";
 			goto err_out;
 		}
-		io_region->ret_code = cp_init(&private->cp, mdev_dev(mdev),
-					      orb);
+		io_region->ret_code = cp_init(&private->cp, orb);
 		if (io_region->ret_code) {
 			VFIO_CCW_MSG_EVENT(2,
 					   "%pUl (%x.%x.%04x): cp_init=%d\n",
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index c4d60cdbf247..b49e2e9db2dc 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -183,7 +183,7 @@ static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 
 	private->nb.notifier_call = vfio_ccw_mdev_notifier;
 
-	ret = vfio_register_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
+	ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY,
 				     &events, &private->nb);
 	if (ret)
 		return ret;
@@ -204,8 +204,7 @@ static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 
 out_unregister:
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
-				 &private->nb);
+	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY, &private->nb);
 	return ret;
 }
 
@@ -223,7 +222,7 @@ static void vfio_ccw_mdev_close_device(struct vfio_device *vdev)
 
 	cp_free(&private->cp);
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY, &private->nb);
+	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY, &private->nb);
 }
 
 static ssize_t vfio_ccw_mdev_read_io_region(struct vfio_ccw_private *private,
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index ee0a3bf8f476..a7d2a95796d3 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -124,8 +124,7 @@ static void vfio_ap_free_aqic_resources(struct vfio_ap_queue *q)
 		q->saved_isc = VFIO_AP_ISC_INVALID;
 	}
 	if (q->saved_pfn && !WARN_ON(!q->matrix_mdev)) {
-		vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev),
-				 &q->saved_pfn, 1);
+		vfio_unpin_pages(&q->matrix_mdev->vdev, &q->saved_pfn, 1);
 		q->saved_pfn = 0;
 	}
 }
@@ -258,7 +257,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
 		return status;
 	}
 
-	ret = vfio_pin_pages(mdev_dev(q->matrix_mdev->mdev), &g_pfn, 1,
+	ret = vfio_pin_pages(&q->matrix_mdev->vdev, &g_pfn, 1,
 			     IOMMU_READ | IOMMU_WRITE, &h_pfn);
 	switch (ret) {
 	case 1:
@@ -301,7 +300,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
 		break;
 	case AP_RESPONSE_OTHERWISE_CHANGED:
 		/* We could not modify IRQ setings: clear new configuration */
-		vfio_unpin_pages(mdev_dev(q->matrix_mdev->mdev), &g_pfn, 1);
+		vfio_unpin_pages(&q->matrix_mdev->vdev, &g_pfn, 1);
 		kvm_s390_gisc_unregister(kvm, isc);
 		break;
 	default:
@@ -1250,7 +1249,7 @@ static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb,
 		struct vfio_iommu_type1_dma_unmap *unmap = data;
 		unsigned long g_pfn = unmap->iova >> PAGE_SHIFT;
 
-		vfio_unpin_pages(mdev_dev(matrix_mdev->mdev), &g_pfn, 1);
+		vfio_unpin_pages(&matrix_mdev->vdev, &g_pfn, 1);
 		return NOTIFY_OK;
 	}
 
@@ -1285,25 +1284,6 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
 	}
 }
 
-static int vfio_ap_mdev_group_notifier(struct notifier_block *nb,
-				       unsigned long action, void *data)
-{
-	int notify_rc = NOTIFY_OK;
-	struct ap_matrix_mdev *matrix_mdev;
-
-	if (action != VFIO_GROUP_NOTIFY_SET_KVM)
-		return NOTIFY_OK;
-
-	matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier);
-
-	if (!data)
-		vfio_ap_mdev_unset_kvm(matrix_mdev);
-	else if (vfio_ap_mdev_set_kvm(matrix_mdev, data))
-		notify_rc = NOTIFY_DONE;
-
-	return notify_rc;
-}
-
 static struct vfio_ap_queue *vfio_ap_find_queue(int apqn)
 {
 	struct device *dev;
@@ -1403,25 +1383,23 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev)
 	unsigned long events;
 	int ret;
 
-	matrix_mdev->group_notifier.notifier_call = vfio_ap_mdev_group_notifier;
-	events = VFIO_GROUP_NOTIFY_SET_KVM;
+	if (!vdev->kvm)
+		return -EINVAL;
 
-	ret = vfio_register_notifier(vdev->dev, VFIO_GROUP_NOTIFY,
-				     &events, &matrix_mdev->group_notifier);
+	ret = vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm);
 	if (ret)
 		return ret;
 
 	matrix_mdev->iommu_notifier.notifier_call = vfio_ap_mdev_iommu_notifier;
 	events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
-	ret = vfio_register_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
-				     &events, &matrix_mdev->iommu_notifier);
+	ret = vfio_register_notifier(vdev, VFIO_IOMMU_NOTIFY, &events,
+				     &matrix_mdev->iommu_notifier);
 	if (ret)
-		goto out_unregister_group;
+		goto err_kvm;
 	return 0;
 
-out_unregister_group:
-	vfio_unregister_notifier(vdev->dev, VFIO_GROUP_NOTIFY,
-				 &matrix_mdev->group_notifier);
+err_kvm:
+	vfio_ap_mdev_unset_kvm(matrix_mdev);
 	return ret;
 }
 
@@ -1430,10 +1408,8 @@ static void vfio_ap_mdev_close_device(struct vfio_device *vdev)
 	struct ap_matrix_mdev *matrix_mdev =
 		container_of(vdev, struct ap_matrix_mdev, vdev);
 
-	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
+	vfio_unregister_notifier(vdev, VFIO_IOMMU_NOTIFY,
 				 &matrix_mdev->iommu_notifier);
-	vfio_unregister_notifier(vdev->dev, VFIO_GROUP_NOTIFY,
-				 &matrix_mdev->group_notifier);
 	vfio_ap_mdev_unset_kvm(matrix_mdev);
 }
 
diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h
index 648fcaf8104a..a26efd804d0d 100644
--- a/drivers/s390/crypto/vfio_ap_private.h
+++ b/drivers/s390/crypto/vfio_ap_private.h
@@ -81,8 +81,6 @@ struct ap_matrix {
  * @node:	allows the ap_matrix_mdev struct to be added to a list
  * @matrix:	the adapters, usage domains and control domains assigned to the
  *		mediated matrix device.
- * @group_notifier: notifier block used for specifying callback function for
- *		    handling the VFIO_GROUP_NOTIFY_SET_KVM event
  * @iommu_notifier: notifier block used for specifying callback function for
  *		    handling the VFIO_IOMMU_NOTIFY_DMA_UNMAP even
  * @kvm:	the struct holding guest's state
@@ -94,7 +92,6 @@ struct ap_matrix_mdev {
 	struct vfio_device vdev;
 	struct list_head node;
 	struct ap_matrix matrix;
-	struct notifier_block group_notifier;
 	struct notifier_block iommu_notifier;
 	struct kvm *kvm;
 	crypto_hook pqap_hook;