Merge tag 'vfio-v6.9-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Add warning in unlikely case that device is not captured with
   driver_override (Kunwu Chan)

 - Error handling improvements in mlx5-vfio-pci to detect firmware
   tracking object error states, logging of firmware error syndrom, and
   releasing of firmware resources in aborted migration sequence (Yishai
   Hadas)

 - Correct an un-alphabetized VFIO MAINTAINERS entry (Alex Williamson)

 - Make the mdev_bus_type const and also make the class struct const for
   a couple of the vfio-mdev sample drivers (Ricardo B. Marliere)

 - Addition of a new vfio-pci variant driver for the GPU of NVIDIA's
   Grace-Hopper superchip. During initialization of the chip-to-chip
   interconnect in this hardware module, the PCI BARs of the device
   become unused in favor of a faster, coherent mechanism for exposing
   device memory. This driver primarily changes the VFIO representation
   of the device to masquerade this coherent aperture to replace the
   physical PCI BARs for userspace drivers. This also incorporates use
   of a new vma flag allowing KVM to use write combining attributes for
   uncached device memory (Ankit Agrawal)

 - Reset fixes and cleanups for the pds-vfio-pci driver. Save and
   restore files were previously leaked if the device didn't pass
   through an error state, this is resolved and later re-fixed to
   prevent access to the now freed files. Reset handling is also
   refactored to remove the complicated deferred reset mechanism (Brett
   Creeley)

 - Remove some references to pl330 in the vfio-platform amba driver
   (Geert Uytterhoeven)

 - Remove twice redundant and ugly code to unpin incidental pins of the
   zero-page (Alex Williamson)

 - Deferred reset logic is also removed from the hisi-acc-vfio-pci
   driver as a simplification (Shameer Kolothum)

 - Enforce that mlx5-vfio-pci devices must support PRE_COPY and remove
   resulting unnecessary code. There is no device firmware that has been
   available publicly without this support (Yishai Hadas)

 - Switch over to using the .remove_new callback for vfio-platform in
   support of the broader transition for a void remove function (Uwe
   Kleine-König)

 - Resolve multiple issues in interrupt code for VFIO bus drivers that
   allow calling eventfd_signal() on a NULL context. This also remove a
   potential race in INTx setup on certain hardware for vfio-pci, races
   with various mechanisms to mask INTx, and leaked virqfds in
   vfio-platform (Alex Williamson)

* tag 'vfio-v6.9-rc1' of https://github.com/awilliam/linux-vfio: (29 commits)
  vfio/fsl-mc: Block calling interrupt handler without trigger
  vfio/platform: Create persistent IRQ handlers
  vfio/platform: Disable virqfds on cleanup
  vfio/pci: Create persistent INTx handler
  vfio: Introduce interface to flush virqfd inject workqueue
  vfio/pci: Lock external INTx masking ops
  vfio/pci: Disable auto-enable of exclusive INTx IRQ
  vfio/pds: Refactor/simplify reset logic
  vfio/pds: Make sure migration file isn't accessed after reset
  vfio/platform: Convert to platform remove callback returning void
  vfio/mlx5: Enforce PRE_COPY support
  vfio/mbochs: make mbochs_class constant
  vfio/mdpy: make mdpy_class constant
  hisi_acc_vfio_pci: Remove the deferred_reset logic
  Revert "vfio/type1: Unpin zero pages"
  vfio/nvgrace-gpu: Convey kvm to map device memory region as noncached
  vfio: amba: Rename pl330_ids[] to vfio_amba_ids[]
  vfio/pds: Always clear the save/restore FDs on reset
  vfio/nvgrace-gpu: Add vfio pci variant module for grace hopper
  vfio/pci: rename and export range_intersect_range
  ...

Author: torvalds

MAINTAINERS

@@ -23164,12 +23164,11 @@ L:	kvm@vger.kernel.org
 S:	Maintained
 F:	drivers/vfio/pci/mlx5/
 
-VFIO VIRTIO PCI DRIVER
-M:	Yishai Hadas <yishaih@nvidia.com>
+VFIO NVIDIA GRACE GPU DRIVER
+M:	Ankit Agrawal <ankita@nvidia.com>
 L:	kvm@vger.kernel.org
-L:	virtualization@lists.linux.dev
-S:	Maintained
-F:	drivers/vfio/pci/virtio
+S:	Supported
+F:	drivers/vfio/pci/nvgrace-gpu/
 
 VFIO PCI DEVICE SPECIFIC DRIVERS
 R:	Jason Gunthorpe <jgg@nvidia.com>
@@ -23194,6 +23193,13 @@ L:	kvm@vger.kernel.org
 S:	Maintained
 F:	drivers/vfio/platform/
 
+VFIO VIRTIO PCI DRIVER
+M:	Yishai Hadas <yishaih@nvidia.com>
+L:	kvm@vger.kernel.org
+L:	virtualization@lists.linux.dev
+S:	Maintained
+F:	drivers/vfio/pci/virtio
+
 VGA_SWITCHEROO
 R:	Lukas Wunner <lukas@wunner.de>
 S:	Maintained

drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c

@@ -141,13 +141,14 @@ static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev,
 	irq = &vdev->mc_irqs[index];
 
 	if (flags & VFIO_IRQ_SET_DATA_NONE) {
-		vfio_fsl_mc_irq_handler(hwirq, irq);
+		if (irq->trigger)
+			eventfd_signal(irq->trigger);
 
 	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
 		u8 trigger = *(u8 *)data;
 
-		if (trigger)
-			vfio_fsl_mc_irq_handler(hwirq, irq);
+		if (trigger && irq->trigger)
+			eventfd_signal(irq->trigger);
 	}
 
 	return 0;

drivers/vfio/mdev/mdev_driver.c

@@ -40,7 +40,7 @@ static int mdev_match(struct device *dev, struct device_driver *drv)
 	return 0;
 }
 
-struct bus_type mdev_bus_type = {
+const struct bus_type mdev_bus_type = {
 	.name		= "mdev",
 	.probe		= mdev_probe,
 	.remove		= mdev_remove,

drivers/vfio/mdev/mdev_private.h

@@ -13,7 +13,7 @@
 int  mdev_bus_register(void);
 void mdev_bus_unregister(void);
 
-extern struct bus_type mdev_bus_type;
+extern const struct bus_type mdev_bus_type;
 extern const struct attribute_group *mdev_device_groups[];
 
 #define to_mdev_type_attr(_attr)	\

drivers/vfio/pci/Kconfig

@@ -67,4 +67,6 @@ source "drivers/vfio/pci/pds/Kconfig"
 
 source "drivers/vfio/pci/virtio/Kconfig"
 
+source "drivers/vfio/pci/nvgrace-gpu/Kconfig"
+
 endmenu

drivers/vfio/pci/Makefile

@@ -15,3 +15,5 @@ obj-$(CONFIG_HISI_ACC_VFIO_PCI) += hisilicon/
 obj-$(CONFIG_PDS_VFIO_PCI) += pds/
 
 obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio/
+
+obj-$(CONFIG_NVGRACE_GPU_VFIO_PCI) += nvgrace-gpu/

drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c

@@ -630,25 +630,11 @@ static void hisi_acc_vf_disable_fds(struct hisi_acc_vf_core_device *hisi_acc_vde
 	}
 }
 
-/*
- * This function is called in all state_mutex unlock cases to
- * handle a 'deferred_reset' if exists.
- */
-static void
-hisi_acc_vf_state_mutex_unlock(struct hisi_acc_vf_core_device *hisi_acc_vdev)
+static void hisi_acc_vf_reset(struct hisi_acc_vf_core_device *hisi_acc_vdev)
 {
-again:
-	spin_lock(&hisi_acc_vdev->reset_lock);
-	if (hisi_acc_vdev->deferred_reset) {
-		hisi_acc_vdev->deferred_reset = false;
-		spin_unlock(&hisi_acc_vdev->reset_lock);
-		hisi_acc_vdev->vf_qm_state = QM_NOT_READY;
-		hisi_acc_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
-		hisi_acc_vf_disable_fds(hisi_acc_vdev);
-		goto again;
-	}
-	mutex_unlock(&hisi_acc_vdev->state_mutex);
-	spin_unlock(&hisi_acc_vdev->reset_lock);
+	hisi_acc_vdev->vf_qm_state = QM_NOT_READY;
+	hisi_acc_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+	hisi_acc_vf_disable_fds(hisi_acc_vdev);
 }
 
 static void hisi_acc_vf_start_device(struct hisi_acc_vf_core_device *hisi_acc_vdev)
@@ -804,8 +790,10 @@ static long hisi_acc_vf_precopy_ioctl(struct file *filp,
 
 	info.dirty_bytes = 0;
 	info.initial_bytes = migf->total_length - *pos;
+	mutex_unlock(&migf->lock);
+	mutex_unlock(&hisi_acc_vdev->state_mutex);
 
-	ret = copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
+	return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
 out:
 	mutex_unlock(&migf->lock);
 	mutex_unlock(&hisi_acc_vdev->state_mutex);
@@ -1071,7 +1059,7 @@ hisi_acc_vfio_pci_set_device_state(struct vfio_device *vdev,
 			break;
 		}
 	}
-	hisi_acc_vf_state_mutex_unlock(hisi_acc_vdev);
+	mutex_unlock(&hisi_acc_vdev->state_mutex);
 	return res;
 }
 
@@ -1092,7 +1080,7 @@ hisi_acc_vfio_pci_get_device_state(struct vfio_device *vdev,
 
 	mutex_lock(&hisi_acc_vdev->state_mutex);
 	*curr_state = hisi_acc_vdev->mig_state;
-	hisi_acc_vf_state_mutex_unlock(hisi_acc_vdev);
+	mutex_unlock(&hisi_acc_vdev->state_mutex);
 	return 0;
 }
 
@@ -1104,21 +1092,9 @@ static void hisi_acc_vf_pci_aer_reset_done(struct pci_dev *pdev)
 				VFIO_MIGRATION_STOP_COPY)
 		return;
 
-	/*
-	 * As the higher VFIO layers are holding locks across reset and using
-	 * those same locks with the mm_lock we need to prevent ABBA deadlock
-	 * with the state_mutex and mm_lock.
-	 * In case the state_mutex was taken already we defer the cleanup work
-	 * to the unlock flow of the other running context.
-	 */
-	spin_lock(&hisi_acc_vdev->reset_lock);
-	hisi_acc_vdev->deferred_reset = true;
-	if (!mutex_trylock(&hisi_acc_vdev->state_mutex)) {
-		spin_unlock(&hisi_acc_vdev->reset_lock);
-		return;
-	}
-	spin_unlock(&hisi_acc_vdev->reset_lock);
-	hisi_acc_vf_state_mutex_unlock(hisi_acc_vdev);
+	mutex_lock(&hisi_acc_vdev->state_mutex);
+	hisi_acc_vf_reset(hisi_acc_vdev);
+	mutex_unlock(&hisi_acc_vdev->state_mutex);
 }
 
 static int hisi_acc_vf_qm_init(struct hisi_acc_vf_core_device *hisi_acc_vdev)

drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h

@@ -98,8 +98,8 @@ struct hisi_acc_vf_migration_file {
 
 struct hisi_acc_vf_core_device {
 	struct vfio_pci_core_device core_device;
-	u8 match_done:1;
-	u8 deferred_reset:1;
+	u8 match_done;
+
 	/* For migration state */
 	struct mutex state_mutex;
 	enum vfio_device_mig_state mig_state;
@@ -109,8 +109,6 @@ struct hisi_acc_vf_core_device {
 	struct hisi_qm vf_qm;
 	u32 vf_qm_state;
 	int vf_id;
-	/* For reset handler */
-	spinlock_t reset_lock;
 	struct hisi_acc_vf_migration_file *resuming_migf;
 	struct hisi_acc_vf_migration_file *saving_migf;
 };