Merge tag 'vfio-v6.10-rc1' of https://github.com/awilliam/linux-vfio

Pull vfio updates from Alex Williamson:

 - The vfio fsl-mc bus driver has become orphaned. We'll consider
   removing it in future releases if a new maintainer isn't found (Alex
   Williamson)

 - Improved usage of opaque data in vfio-pci INTx handling, avoiding
   lookups of the eventfd through the interrupt and irqfd runtime paths
   (Alex Williamson)

 - Resolve an error path memory leak introduced in vfio-pci interrupt
   code (Ye Bin)

 - Addition of interrupt support for vfio devices exposed on the CDX
   bus, including a new MSI allocation helper and export of existing
   helpers for MSI alloc and free (Nipun Gupta)

 - A new vfio-pci variant driver supporting migration of Intel QAT VF
   devices for the GEN4 PFs (Xin Zeng & Yahui Cao)

 - Resolve a possibly circular locking dependency in vfio-pci by
   avoiding copy_to_user() from a PCI bus walk callback (Alex
   Williamson)

 - Trivial docs update to remove a duplicate semicolon (Foryun Ma)

* tag 'vfio-v6.10-rc1' of https://github.com/awilliam/linux-vfio:
  vfio/pci: Restore zero affected bus reset devices warning
  vfio: remove an extra semicolon
  vfio/pci: Collect hot-reset devices to local buffer
  vfio/qat: Add vfio_pci driver for Intel QAT SR-IOV VF devices
  vfio/cdx: add interrupt support
  genirq/msi: Add MSI allocation helper and export MSI functions
  vfio/pci: fix potential memory leak in vfio_intx_enable()
  vfio/pci: Pass eventfd context object through irqfd
  vfio/pci: Pass eventfd context to IRQ handler
  MAINTAINERS: Orphan vfio fsl-mc bus driver

Documentation/driver-api/vfio.rst

@@ -364,7 +364,7 @@ IOMMUFD IOAS/HWPT to enable userspace DMA::
 				    MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
 	map.iova = 0; /* 1MB starting at 0x0 from device view */
 	map.length = 1024 * 1024;
-	map.ioas_id = alloc_data.out_ioas_id;;
+	map.ioas_id = alloc_data.out_ioas_id;
 
 	ioctl(iommufd, IOMMU_IOAS_MAP, &map);
 

MAINTAINERS

@@ -23512,9 +23512,8 @@ F:	include/linux/vfio_pci_core.h
 F:	include/uapi/linux/vfio.h
 
 VFIO FSL-MC DRIVER
-M:	Diana Craciun <diana.craciun@oss.nxp.com>
 L:	kvm@vger.kernel.org
-S:	Maintained
+S:	Orphan
 F:	drivers/vfio/fsl-mc/
 
 VFIO HISILICON PCI DRIVER
@@ -23568,6 +23567,14 @@ L:	kvm@vger.kernel.org
 S:	Maintained
 F:	drivers/vfio/platform/
 
+VFIO QAT PCI DRIVER
+M:	Xin Zeng <xin.zeng@intel.com>
+M:	Giovanni Cabiddu <giovanni.cabiddu@intel.com>
+L:	kvm@vger.kernel.org
+L:	qat-linux@intel.com
+S:	Supported
+F:	drivers/vfio/pci/qat/
+
 VFIO VIRTIO PCI DRIVER
 M:	Yishai Hadas <yishaih@nvidia.com>
 L:	kvm@vger.kernel.org

drivers/vfio/cdx/Makefile

@@ -5,4 +5,4 @@
 
 obj-$(CONFIG_VFIO_CDX) += vfio-cdx.o
 
-vfio-cdx-objs := main.o
+vfio-cdx-objs := main.o intr.o

drivers/vfio/cdx/intr.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+ */
+
+#include <linux/vfio.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/eventfd.h>
+#include <linux/msi.h>
+#include <linux/interrupt.h>
+
+#include "linux/cdx/cdx_bus.h"
+#include "private.h"
+
+static irqreturn_t vfio_cdx_msihandler(int irq_no, void *arg)
+{
+	struct eventfd_ctx *trigger = arg;
+
+	eventfd_signal(trigger);
+	return IRQ_HANDLED;
+}
+
+static int vfio_cdx_msi_enable(struct vfio_cdx_device *vdev, int nvec)
+{
+	struct cdx_device *cdx_dev = to_cdx_device(vdev->vdev.dev);
+	struct device *dev = vdev->vdev.dev;
+	int msi_idx, ret;
+
+	vdev->cdx_irqs = kcalloc(nvec, sizeof(struct vfio_cdx_irq), GFP_KERNEL);
+	if (!vdev->cdx_irqs)
+		return -ENOMEM;
+
+	ret = cdx_enable_msi(cdx_dev);
+	if (ret) {
+		kfree(vdev->cdx_irqs);
+		return ret;
+	}
+
+	/* Allocate cdx MSIs */
+	ret = msi_domain_alloc_irqs(dev, MSI_DEFAULT_DOMAIN, nvec);
+	if (ret) {
+		cdx_disable_msi(cdx_dev);
+		kfree(vdev->cdx_irqs);
+		return ret;
+	}
+
+	for (msi_idx = 0; msi_idx < nvec; msi_idx++)
+		vdev->cdx_irqs[msi_idx].irq_no = msi_get_virq(dev, msi_idx);
+
+	vdev->msi_count = nvec;
+	vdev->config_msi = 1;
+
+	return 0;
+}
+
+static int vfio_cdx_msi_set_vector_signal(struct vfio_cdx_device *vdev,
+					  int vector, int fd)
+{
+	struct eventfd_ctx *trigger;
+	int irq_no, ret;
+
+	if (vector < 0 || vector >= vdev->msi_count)
+		return -EINVAL;
+
+	irq_no = vdev->cdx_irqs[vector].irq_no;
+
+	if (vdev->cdx_irqs[vector].trigger) {
+		free_irq(irq_no, vdev->cdx_irqs[vector].trigger);
+		kfree(vdev->cdx_irqs[vector].name);
+		eventfd_ctx_put(vdev->cdx_irqs[vector].trigger);
+		vdev->cdx_irqs[vector].trigger = NULL;
+	}
+
+	if (fd < 0)
+		return 0;
+
+	vdev->cdx_irqs[vector].name = kasprintf(GFP_KERNEL, "vfio-msi[%d](%s)",
+						vector, dev_name(vdev->vdev.dev));
+	if (!vdev->cdx_irqs[vector].name)
+		return -ENOMEM;
+
+	trigger = eventfd_ctx_fdget(fd);
+	if (IS_ERR(trigger)) {
+		kfree(vdev->cdx_irqs[vector].name);
+		return PTR_ERR(trigger);
+	}
+
+	ret = request_irq(irq_no, vfio_cdx_msihandler, 0,
+			  vdev->cdx_irqs[vector].name, trigger);
+	if (ret) {
+		kfree(vdev->cdx_irqs[vector].name);
+		eventfd_ctx_put(trigger);
+		return ret;
+	}
+
+	vdev->cdx_irqs[vector].trigger = trigger;
+
+	return 0;
+}
+
+static int vfio_cdx_msi_set_block(struct vfio_cdx_device *vdev,
+				  unsigned int start, unsigned int count,
+				  int32_t *fds)
+{
+	int i, j, ret = 0;
+
+	if (start >= vdev->msi_count || start + count > vdev->msi_count)
+		return -EINVAL;
+
+	for (i = 0, j = start; i < count && !ret; i++, j++) {
+		int fd = fds ? fds[i] : -1;
+
+		ret = vfio_cdx_msi_set_vector_signal(vdev, j, fd);
+	}
+
+	if (ret) {
+		for (--j; j >= (int)start; j--)
+			vfio_cdx_msi_set_vector_signal(vdev, j, -1);
+	}
+
+	return ret;
+}
+
+static void vfio_cdx_msi_disable(struct vfio_cdx_device *vdev)
+{
+	struct cdx_device *cdx_dev = to_cdx_device(vdev->vdev.dev);
+	struct device *dev = vdev->vdev.dev;
+
+	vfio_cdx_msi_set_block(vdev, 0, vdev->msi_count, NULL);
+
+	if (!vdev->config_msi)
+		return;
+
+	msi_domain_free_irqs_all(dev, MSI_DEFAULT_DOMAIN);
+	cdx_disable_msi(cdx_dev);
+	kfree(vdev->cdx_irqs);
+
+	vdev->cdx_irqs = NULL;
+	vdev->msi_count = 0;
+	vdev->config_msi = 0;
+}
+
+static int vfio_cdx_set_msi_trigger(struct vfio_cdx_device *vdev,
+				    unsigned int index, unsigned int start,
+				    unsigned int count, u32 flags,
+				    void *data)
+{
+	struct cdx_device *cdx_dev = to_cdx_device(vdev->vdev.dev);
+	int i;
+
+	if (start + count > cdx_dev->num_msi)
+		return -EINVAL;
+
+	if (!count && (flags & VFIO_IRQ_SET_DATA_NONE)) {
+		vfio_cdx_msi_disable(vdev);
+		return 0;
+	}
+
+	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		s32 *fds = data;
+		int ret;
+
+		if (vdev->config_msi)
+			return vfio_cdx_msi_set_block(vdev, start, count,
+						  fds);
+		ret = vfio_cdx_msi_enable(vdev, cdx_dev->num_msi);
+		if (ret)
+			return ret;
+
+		ret = vfio_cdx_msi_set_block(vdev, start, count, fds);
+		if (ret)
+			vfio_cdx_msi_disable(vdev);
+
+		return ret;
+	}
+
+	for (i = start; i < start + count; i++) {
+		if (!vdev->cdx_irqs[i].trigger)
+			continue;
+		if (flags & VFIO_IRQ_SET_DATA_NONE) {
+			eventfd_signal(vdev->cdx_irqs[i].trigger);
+		} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
+			u8 *bools = data;
+
+			if (bools[i - start])
+				eventfd_signal(vdev->cdx_irqs[i].trigger);
+		}
+	}
+
+	return 0;
+}
+
+int vfio_cdx_set_irqs_ioctl(struct vfio_cdx_device *vdev,
+			    u32 flags, unsigned int index,
+			    unsigned int start, unsigned int count,
+			    void *data)
+{
+	if (flags & VFIO_IRQ_SET_ACTION_TRIGGER)
+		return vfio_cdx_set_msi_trigger(vdev, index, start,
+			  count, flags, data);
+	else
+		return -EINVAL;
+}
+
+/* Free All IRQs for the given device */
+void vfio_cdx_irqs_cleanup(struct vfio_cdx_device *vdev)
+{
+	/*
+	 * Device does not support any interrupt or the interrupts
+	 * were not configured
+	 */
+	if (!vdev->cdx_irqs)
+		return;
+
+	vfio_cdx_set_msi_trigger(vdev, 0, 0, 0, VFIO_IRQ_SET_DATA_NONE, NULL);
+}

drivers/vfio/cdx/main.c

@@ -61,6 +61,7 @@ static void vfio_cdx_close_device(struct vfio_device *core_vdev)
 
 	kfree(vdev->regions);
 	cdx_dev_reset(core_vdev->dev);
+	vfio_cdx_irqs_cleanup(vdev);
 }
 
 static int vfio_cdx_bm_ctrl(struct vfio_device *core_vdev, u32 flags,
@@ -123,7 +124,7 @@ static int vfio_cdx_ioctl_get_info(struct vfio_cdx_device *vdev,
 	info.flags |= VFIO_DEVICE_FLAGS_RESET;
 
 	info.num_regions = cdx_dev->res_count;
-	info.num_irqs = 0;
+	info.num_irqs = cdx_dev->num_msi ? 1 : 0;
 
 	return copy_to_user(arg, &info, minsz) ? -EFAULT : 0;
 }
@@ -152,6 +153,62 @@ static int vfio_cdx_ioctl_get_region_info(struct vfio_cdx_device *vdev,
 	return copy_to_user(arg, &info, minsz) ? -EFAULT : 0;
 }
 
+static int vfio_cdx_ioctl_get_irq_info(struct vfio_cdx_device *vdev,
+				       struct vfio_irq_info __user *arg)
+{
+	unsigned long minsz = offsetofend(struct vfio_irq_info, count);
+	struct cdx_device *cdx_dev = to_cdx_device(vdev->vdev.dev);
+	struct vfio_irq_info info;
+
+	if (copy_from_user(&info, arg, minsz))
+		return -EFAULT;
+
+	if (info.argsz < minsz)
+		return -EINVAL;
+
+	if (info.index >= 1)
+		return -EINVAL;
+
+	if (!cdx_dev->num_msi)
+		return -EINVAL;
+
+	info.flags = VFIO_IRQ_INFO_EVENTFD | VFIO_IRQ_INFO_NORESIZE;
+	info.count = cdx_dev->num_msi;
+
+	return copy_to_user(arg, &info, minsz) ? -EFAULT : 0;
+}
+
+static int vfio_cdx_ioctl_set_irqs(struct vfio_cdx_device *vdev,
+				   struct vfio_irq_set __user *arg)
+{
+	unsigned long minsz = offsetofend(struct vfio_irq_set, count);
+	struct cdx_device *cdx_dev = to_cdx_device(vdev->vdev.dev);
+	struct vfio_irq_set hdr;
+	size_t data_size = 0;
+	u8 *data = NULL;
+	int ret = 0;
+
+	if (copy_from_user(&hdr, arg, minsz))
+		return -EFAULT;
+
+	ret = vfio_set_irqs_validate_and_prepare(&hdr, cdx_dev->num_msi,
+						 1, &data_size);
+	if (ret)
+		return ret;
+
+	if (data_size) {
+		data = memdup_user(arg->data, data_size);
+		if (IS_ERR(data))
+			return PTR_ERR(data);
+	}
+
+	ret = vfio_cdx_set_irqs_ioctl(vdev, hdr.flags, hdr.index,
+				      hdr.start, hdr.count, data);
+	kfree(data);
+
+	return ret;
+}
+
 static long vfio_cdx_ioctl(struct vfio_device *core_vdev,
 			   unsigned int cmd, unsigned long arg)
 {
@@ -164,6 +221,10 @@ static long vfio_cdx_ioctl(struct vfio_device *core_vdev,
 		return vfio_cdx_ioctl_get_info(vdev, uarg);
 	case VFIO_DEVICE_GET_REGION_INFO:
 		return vfio_cdx_ioctl_get_region_info(vdev, uarg);
+	case VFIO_DEVICE_GET_IRQ_INFO:
+		return vfio_cdx_ioctl_get_irq_info(vdev, uarg);
+	case VFIO_DEVICE_SET_IRQS:
+		return vfio_cdx_ioctl_set_irqs(vdev, uarg);
 	case VFIO_DEVICE_RESET:
 		return cdx_dev_reset(core_vdev->dev);
 	default:

drivers/vfio/cdx/private.h

@@ -13,6 +13,14 @@ static inline u64 vfio_cdx_index_to_offset(u32 index)
 	return ((u64)(index) << VFIO_CDX_OFFSET_SHIFT);
 }
 
+struct vfio_cdx_irq {
+	u32			flags;
+	u32			count;
+	int			irq_no;
+	struct eventfd_ctx	*trigger;
+	char			*name;
+};
+
 struct vfio_cdx_region {
 	u32			flags;
 	u32			type;
@@ -23,8 +31,18 @@ struct vfio_cdx_region {
 struct vfio_cdx_device {
 	struct vfio_device	vdev;
 	struct vfio_cdx_region	*regions;
+	struct vfio_cdx_irq	*cdx_irqs;
 	u32			flags;
 #define BME_SUPPORT BIT(0)
+	u32			msi_count;
+	u8			config_msi;
 };
 
+int vfio_cdx_set_irqs_ioctl(struct vfio_cdx_device *vdev,
+			    u32 flags, unsigned int index,
+			    unsigned int start, unsigned int count,
+			    void *data);
+
+void vfio_cdx_irqs_cleanup(struct vfio_cdx_device *vdev);
+
 #endif /* VFIO_CDX_PRIVATE_H */

drivers/vfio/pci/Kconfig

@@ -69,4 +69,6 @@ source "drivers/vfio/pci/virtio/Kconfig"
 
 source "drivers/vfio/pci/nvgrace-gpu/Kconfig"
 
+source "drivers/vfio/pci/qat/Kconfig"
+
 endmenu

drivers/vfio/pci/Makefile

@@ -17,3 +17,5 @@ obj-$(CONFIG_PDS_VFIO_PCI) += pds/
 obj-$(CONFIG_VIRTIO_VFIO_PCI) += virtio/
 
 obj-$(CONFIG_NVGRACE_GPU_VFIO_PCI) += nvgrace-gpu/
+
+obj-$(CONFIG_QAT_VFIO_PCI) += qat/

drivers/vfio/pci/qat/Kconfig

+# SPDX-License-Identifier: GPL-2.0-only
+config QAT_VFIO_PCI
+	tristate "VFIO support for QAT VF PCI devices"
+	select VFIO_PCI_CORE
+	depends on CRYPTO_DEV_QAT_4XXX
+	help
+	  This provides migration support for Intel(R) QAT Virtual Function
+	  using the VFIO framework.
+
+	  To compile this as a module, choose M here: the module
+	  will be called qat_vfio_pci. If you don't know what to do here,
+	  say N.

drivers/vfio/pci/qat/Makefile

+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_QAT_VFIO_PCI) += qat_vfio_pci.o
+qat_vfio_pci-y := main.o

drivers/vfio/pci/qat/main.c

+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2024 Intel Corporation */
+
+#include <linux/anon_inodes.h>
+#include <linux/container_of.h>
+#include <linux/device.h>
+#include <linux/file.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/sizes.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+#include <linux/vfio_pci_core.h>
+#include <linux/qat/qat_mig_dev.h>
+
+/*
+ * The migration data of each Intel QAT VF device is encapsulated into a
+ * 4096 bytes block. The data consists of two parts.
+ * The first is a pre-configured set of attributes of the VF being migrated,
+ * which are only set when it is created. This can be migrated during pre-copy
+ * stage and used for a device compatibility check.
+ * The second is the VF state. This includes the required MMIO regions and
+ * the shadow states maintained by the QAT PF driver. This part can only be
+ * saved when the VF is fully quiesced and be migrated during stop-copy stage.
+ * Both these 2 parts of data are saved in hierarchical structures including
+ * a preamble section and several raw state sections.
+ * When the pre-configured part of the migration data is fully retrieved from
+ * user space, the preamble section are used to validate the correctness of
+ * the data blocks and check the version compatibility. The raw state sections
+ * are then used to do a device compatibility check.
+ * When the device transits from RESUMING state, the VF states are extracted
+ * from the raw state sections of the VF state part of the migration data and
+ * then loaded into the device.
+ */
+
+struct qat_vf_migration_file {
+	struct file *filp;
+	/* protects migration region context */
+	struct mutex lock;
+	bool disabled;
+	struct qat_vf_core_device *qat_vdev;
+	ssize_t filled_size;
+};
+
+struct qat_vf_core_device {
+	struct vfio_pci_core_device core_device;
+	struct qat_mig_dev *mdev;
+	/* protects migration state */
+	struct mutex state_mutex;
+	enum vfio_device_mig_state mig_state;
+	struct qat_vf_migration_file *resuming_migf;
+	struct qat_vf_migration_file *saving_migf;
+};
+
+static int qat_vf_pci_open_device(struct vfio_device *core_vdev)
+{
+	struct qat_vf_core_device *qat_vdev =
+		container_of(core_vdev, struct qat_vf_core_device,
+			     core_device.vdev);
+	struct vfio_pci_core_device *vdev = &qat_vdev->core_device;
+	int ret;
+
+	ret = vfio_pci_core_enable(vdev);
+	if (ret)
+		return ret;
+
+	ret = qat_vfmig_open(qat_vdev->mdev);
+	if (ret) {
+		vfio_pci_core_disable(vdev);
+		return ret;
+	}
+	qat_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+
+	vfio_pci_core_finish_enable(vdev);
+
+	return 0;
+}
+
+static void qat_vf_disable_fd(struct qat_vf_migration_file *migf)
+{
+	mutex_lock(&migf->lock);
+	migf->disabled = true;
+	migf->filp->f_pos = 0;
+	migf->filled_size = 0;
+	mutex_unlock(&migf->lock);
+}
+
+static void qat_vf_disable_fds(struct qat_vf_core_device *qat_vdev)
+{
+	if (qat_vdev->resuming_migf) {
+		qat_vf_disable_fd(qat_vdev->resuming_migf);
+		fput(qat_vdev->resuming_migf->filp);
+		qat_vdev->resuming_migf = NULL;
+	}
+
+	if (qat_vdev->saving_migf) {
+		qat_vf_disable_fd(qat_vdev->saving_migf);
+		fput(qat_vdev->saving_migf->filp);
+		qat_vdev->saving_migf = NULL;
+	}
+}
+
+static void qat_vf_pci_close_device(struct vfio_device *core_vdev)
+{
+	struct qat_vf_core_device *qat_vdev = container_of(core_vdev,
+			struct qat_vf_core_device, core_device.vdev);
+
+	qat_vfmig_close(qat_vdev->mdev);
+	qat_vf_disable_fds(qat_vdev);
+	vfio_pci_core_close_device(core_vdev);
+}
+
+static long qat_vf_precopy_ioctl(struct file *filp, unsigned int cmd,
+				 unsigned long arg)
+{
+	struct qat_vf_migration_file *migf = filp->private_data;
+	struct qat_vf_core_device *qat_vdev = migf->qat_vdev;
+	struct qat_mig_dev *mig_dev = qat_vdev->mdev;
+	struct vfio_precopy_info info;
+	loff_t *pos = &filp->f_pos;
+	unsigned long minsz;
+	int ret = 0;
+
+	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(&qat_vdev->state_mutex);
+	if (qat_vdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY &&
+	    qat_vdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY_P2P) {
+		mutex_unlock(&qat_vdev->state_mutex);
+		return -EINVAL;
+	}
+
+	mutex_lock(&migf->lock);
+	if (migf->disabled) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	if (*pos > mig_dev->setup_size) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	info.dirty_bytes = 0;
+	info.initial_bytes = mig_dev->setup_size - *pos;
+
+out:
+	mutex_unlock(&migf->lock);
+	mutex_unlock(&qat_vdev->state_mutex);
+	if (ret)
+		return ret;
+	return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
+}
+
+static ssize_t qat_vf_save_read(struct file *filp, char __user *buf,
+				size_t len, loff_t *pos)
+{
+	struct qat_vf_migration_file *migf = filp->private_data;
+	struct qat_mig_dev *mig_dev = migf->qat_vdev->mdev;
+	ssize_t done = 0;
+	loff_t *offs;
+	int ret;
+
+	if (pos)
+		return -ESPIPE;
+	offs = &filp->f_pos;
+
+	mutex_lock(&migf->lock);
+	if (*offs > migf->filled_size || *offs < 0) {
+		done = -EINVAL;
+		goto out_unlock;
+	}
+
+	if (migf->disabled) {
+		done = -ENODEV;
+		goto out_unlock;
+	}
+
+	len = min_t(size_t, migf->filled_size - *offs, len);
+	if (len) {
+		ret = copy_to_user(buf, mig_dev->state + *offs, len);
+		if (ret) {
+			done = -EFAULT;
+			goto out_unlock;
+		}
+		*offs += len;
+		done = len;
+	}
+
+out_unlock:
+	mutex_unlock(&migf->lock);
+	return done;
+}
+
+static int qat_vf_release_file(struct inode *inode, struct file *filp)
+{
+	struct qat_vf_migration_file *migf = filp->private_data;
+
+	qat_vf_disable_fd(migf);
+	mutex_destroy(&migf->lock);
+	kfree(migf);
+
+	return 0;
+}
+
+static const struct file_operations qat_vf_save_fops = {
+	.owner = THIS_MODULE,
+	.read = qat_vf_save_read,
+	.unlocked_ioctl = qat_vf_precopy_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
+	.release = qat_vf_release_file,
+	.llseek = no_llseek,
+};
+
+static int qat_vf_save_state(struct qat_vf_core_device *qat_vdev,
+			     struct qat_vf_migration_file *migf)
+{
+	int ret;
+
+	ret = qat_vfmig_save_state(qat_vdev->mdev);
+	if (ret)
+		return ret;
+	migf->filled_size = qat_vdev->mdev->state_size;
+
+	return 0;
+}
+
+static int qat_vf_save_setup(struct qat_vf_core_device *qat_vdev,
+			     struct qat_vf_migration_file *migf)
+{
+	int ret;
+
+	ret = qat_vfmig_save_setup(qat_vdev->mdev);
+	if (ret)
+		return ret;
+	migf->filled_size = qat_vdev->mdev->setup_size;
+
+	return 0;
+}
+
+/*
+ * Allocate a file handler for user space and then save the migration data for
+ * the device being migrated. If this is called in the pre-copy stage, save the
+ * pre-configured device data. Otherwise, if this is called in the stop-copy
+ * stage, save the device state. In both cases, update the data size which can
+ * then be read from user space.
+ */
+static struct qat_vf_migration_file *
+qat_vf_save_device_data(struct qat_vf_core_device *qat_vdev, bool pre_copy)
+{
+	struct qat_vf_migration_file *migf;
+	int ret;
+
+	migf = kzalloc(sizeof(*migf), GFP_KERNEL);
+	if (!migf)
+		return ERR_PTR(-ENOMEM);
+
+	migf->filp = anon_inode_getfile("qat_vf_mig", &qat_vf_save_fops,
+					migf, O_RDONLY);
+	ret = PTR_ERR_OR_ZERO(migf->filp);
+	if (ret) {
+		kfree(migf);
+		return ERR_PTR(ret);
+	}
+
+	stream_open(migf->filp->f_inode, migf->filp);
+	mutex_init(&migf->lock);
+
+	if (pre_copy)
+		ret = qat_vf_save_setup(qat_vdev, migf);
+	else
+		ret = qat_vf_save_state(qat_vdev, migf);
+	if (ret) {
+		fput(migf->filp);
+		return ERR_PTR(ret);
+	}
+
+	migf->qat_vdev = qat_vdev;
+
+	return migf;
+}
+
+static ssize_t qat_vf_resume_write(struct file *filp, const char __user *buf,
+				   size_t len, loff_t *pos)
+{
+	struct qat_vf_migration_file *migf = filp->private_data;
+	struct qat_mig_dev *mig_dev = migf->qat_vdev->mdev;
+	loff_t end, *offs;
+	ssize_t done = 0;
+	int ret;
+
+	if (pos)
+		return -ESPIPE;
+	offs = &filp->f_pos;
+
+	if (*offs < 0 ||
+	    check_add_overflow((loff_t)len, *offs, &end))
+		return -EOVERFLOW;
+
+	if (end > mig_dev->state_size)
+		return -ENOMEM;
+
+	mutex_lock(&migf->lock);
+	if (migf->disabled) {
+		done = -ENODEV;
+		goto out_unlock;
+	}
+
+	ret = copy_from_user(mig_dev->state + *offs, buf, len);
+	if (ret) {
+		done = -EFAULT;
+		goto out_unlock;
+	}
+	*offs += len;
+	migf->filled_size += len;
+
+	/*
+	 * Load the pre-configured device data first to check if the target
+	 * device is compatible with the source device.
+	 */
+	ret = qat_vfmig_load_setup(mig_dev, migf->filled_size);
+	if (ret && ret != -EAGAIN) {
+		done = ret;
+		goto out_unlock;
+	}
+	done = len;
+
+out_unlock:
+	mutex_unlock(&migf->lock);
+	return done;
+}
+
+static const struct file_operations qat_vf_resume_fops = {
+	.owner = THIS_MODULE,
+	.write = qat_vf_resume_write,
+	.release = qat_vf_release_file,
+	.llseek = no_llseek,
+};
+
+static struct qat_vf_migration_file *
+qat_vf_resume_device_data(struct qat_vf_core_device *qat_vdev)
+{
+	struct qat_vf_migration_file *migf;
+	int ret;
+
+	migf = kzalloc(sizeof(*migf), GFP_KERNEL);
+	if (!migf)
+		return ERR_PTR(-ENOMEM);
+
+	migf->filp = anon_inode_getfile("qat_vf_mig", &qat_vf_resume_fops, migf, O_WRONLY);
+	ret = PTR_ERR_OR_ZERO(migf->filp);
+	if (ret) {
+		kfree(migf);
+		return ERR_PTR(ret);
+	}
+
+	migf->qat_vdev = qat_vdev;
+	migf->filled_size = 0;
+	stream_open(migf->filp->f_inode, migf->filp);
+	mutex_init(&migf->lock);
+
+	return migf;
+}
+
+static int qat_vf_load_device_data(struct qat_vf_core_device *qat_vdev)
+{
+	return qat_vfmig_load_state(qat_vdev->mdev);
+}
+
+static struct file *qat_vf_pci_step_device_state(struct qat_vf_core_device *qat_vdev, u32 new)
+{
+	u32 cur = qat_vdev->mig_state;
+	int ret;
+
+	/*
+	 * As the device is not capable of just stopping P2P DMAs, suspend the
+	 * device completely once any of the P2P states are reached.
+	 * When it is suspended, all its MMIO registers can still be operated
+	 * correctly, jobs submitted through ring are queued while no jobs are
+	 * processed by the device. The MMIO states can be safely migrated to
+	 * the target VF during stop-copy stage and restored correctly in the
+	 * target VF. All queued jobs can be resumed then.
+	 */
+	if ((cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) ||
+	    (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_PRE_COPY_P2P)) {
+		ret = qat_vfmig_suspend(qat_vdev->mdev);
+		if (ret)
+			return ERR_PTR(ret);
+		return NULL;
+	}
+
+	if ((cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) ||
+	    (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && new == VFIO_DEVICE_STATE_PRE_COPY)) {
+		qat_vfmig_resume(qat_vdev->mdev);
+		return NULL;
+	}
+
+	if ((cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_STOP) ||
+	    (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_RUNNING_P2P))
+		return NULL;
+
+	if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_STOP_COPY) {
+		struct qat_vf_migration_file *migf;
+
+		migf = qat_vf_save_device_data(qat_vdev, false);
+		if (IS_ERR(migf))
+			return ERR_CAST(migf);
+		get_file(migf->filp);
+		qat_vdev->saving_migf = migf;
+		return migf->filp;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_RESUMING) {
+		struct qat_vf_migration_file *migf;
+
+		migf = qat_vf_resume_device_data(qat_vdev);
+		if (IS_ERR(migf))
+			return ERR_CAST(migf);
+		get_file(migf->filp);
+		qat_vdev->resuming_migf = migf;
+		return migf->filp;
+	}
+
+	if ((cur == VFIO_DEVICE_STATE_STOP_COPY && new == VFIO_DEVICE_STATE_STOP) ||
+	    (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_RUNNING) ||
+	    (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && new == VFIO_DEVICE_STATE_RUNNING_P2P)) {
+		qat_vf_disable_fds(qat_vdev);
+		return NULL;
+	}
+
+	if ((cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_PRE_COPY) ||
+	    (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_PRE_COPY_P2P)) {
+		struct qat_vf_migration_file *migf;
+
+		migf = qat_vf_save_device_data(qat_vdev, true);
+		if (IS_ERR(migf))
+			return ERR_CAST(migf);
+		get_file(migf->filp);
+		qat_vdev->saving_migf = migf;
+		return migf->filp;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && new == VFIO_DEVICE_STATE_STOP_COPY) {
+		struct qat_vf_migration_file *migf = qat_vdev->saving_migf;
+
+		if (!migf)
+			return ERR_PTR(-EINVAL);
+		ret = qat_vf_save_state(qat_vdev, migf);
+		if (ret)
+			return ERR_PTR(ret);
+		return NULL;
+	}
+
+	if (cur == VFIO_DEVICE_STATE_RESUMING && new == VFIO_DEVICE_STATE_STOP) {
+		ret = qat_vf_load_device_data(qat_vdev);
+		if (ret)
+			return ERR_PTR(ret);
+
+		qat_vf_disable_fds(qat_vdev);
+		return NULL;
+	}
+
+	/* vfio_mig_get_next_state() does not use arcs other than the above */
+	WARN_ON(true);
+	return ERR_PTR(-EINVAL);
+}
+
+static void qat_vf_reset_done(struct qat_vf_core_device *qat_vdev)
+{
+	qat_vdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+	qat_vfmig_reset(qat_vdev->mdev);
+	qat_vf_disable_fds(qat_vdev);
+}
+
+static struct file *qat_vf_pci_set_device_state(struct vfio_device *vdev,
+						enum vfio_device_mig_state new_state)
+{
+	struct qat_vf_core_device *qat_vdev = container_of(vdev,
+			struct qat_vf_core_device, core_device.vdev);
+	enum vfio_device_mig_state next_state;
+	struct file *res = NULL;
+	int ret;
+
+	mutex_lock(&qat_vdev->state_mutex);
+	while (new_state != qat_vdev->mig_state) {
+		ret = vfio_mig_get_next_state(vdev, qat_vdev->mig_state,
+					      new_state, &next_state);
+		if (ret) {
+			res = ERR_PTR(ret);
+			break;
+		}
+		res = qat_vf_pci_step_device_state(qat_vdev, next_state);
+		if (IS_ERR(res))
+			break;
+		qat_vdev->mig_state = next_state;
+		if (WARN_ON(res && new_state != qat_vdev->mig_state)) {
+			fput(res);
+			res = ERR_PTR(-EINVAL);
+			break;
+		}
+	}
+	mutex_unlock(&qat_vdev->state_mutex);
+
+	return res;
+}
+
+static int qat_vf_pci_get_device_state(struct vfio_device *vdev,
+				       enum vfio_device_mig_state *curr_state)
+{
+	struct qat_vf_core_device *qat_vdev = container_of(vdev,
+			struct qat_vf_core_device, core_device.vdev);
+
+	mutex_lock(&qat_vdev->state_mutex);
+	*curr_state = qat_vdev->mig_state;
+	mutex_unlock(&qat_vdev->state_mutex);
+
+	return 0;
+}
+
+static int qat_vf_pci_get_data_size(struct vfio_device *vdev,
+				    unsigned long *stop_copy_length)
+{
+	struct qat_vf_core_device *qat_vdev = container_of(vdev,
+			struct qat_vf_core_device, core_device.vdev);
+
+	mutex_lock(&qat_vdev->state_mutex);
+	*stop_copy_length = qat_vdev->mdev->state_size;
+	mutex_unlock(&qat_vdev->state_mutex);
+
+	return 0;
+}
+
+static const struct vfio_migration_ops qat_vf_pci_mig_ops = {
+	.migration_set_state = qat_vf_pci_set_device_state,
+	.migration_get_state = qat_vf_pci_get_device_state,
+	.migration_get_data_size = qat_vf_pci_get_data_size,
+};
+
+static void qat_vf_pci_release_dev(struct vfio_device *core_vdev)
+{
+	struct qat_vf_core_device *qat_vdev = container_of(core_vdev,
+			struct qat_vf_core_device, core_device.vdev);
+
+	qat_vfmig_cleanup(qat_vdev->mdev);
+	qat_vfmig_destroy(qat_vdev->mdev);
+	mutex_destroy(&qat_vdev->state_mutex);
+	vfio_pci_core_release_dev(core_vdev);
+}
+
+static int qat_vf_pci_init_dev(struct vfio_device *core_vdev)
+{
+	struct qat_vf_core_device *qat_vdev = container_of(core_vdev,
+			struct qat_vf_core_device, core_device.vdev);
+	struct qat_mig_dev *mdev;
+	struct pci_dev *parent;
+	int ret, vf_id;
+
+	core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P |
+				     VFIO_MIGRATION_PRE_COPY;
+	core_vdev->mig_ops = &qat_vf_pci_mig_ops;
+
+	ret = vfio_pci_core_init_dev(core_vdev);
+	if (ret)
+		return ret;
+
+	mutex_init(&qat_vdev->state_mutex);
+
+	parent = pci_physfn(qat_vdev->core_device.pdev);
+	vf_id = pci_iov_vf_id(qat_vdev->core_device.pdev);
+	if (vf_id < 0) {
+		ret = -ENODEV;
+		goto err_rel;
+	}
+
+	mdev = qat_vfmig_create(parent, vf_id);
+	if (IS_ERR(mdev)) {
+		ret = PTR_ERR(mdev);
+		goto err_rel;
+	}
+
+	ret = qat_vfmig_init(mdev);
+	if (ret)
+		goto err_destroy;
+
+	qat_vdev->mdev = mdev;
+
+	return 0;
+
+err_destroy:
+	qat_vfmig_destroy(mdev);
+err_rel:
+	vfio_pci_core_release_dev(core_vdev);
+	return ret;
+}
+
+static const struct vfio_device_ops qat_vf_pci_ops = {
+	.name = "qat-vf-vfio-pci",
+	.init = qat_vf_pci_init_dev,
+	.release = qat_vf_pci_release_dev,
+	.open_device = qat_vf_pci_open_device,
+	.close_device = qat_vf_pci_close_device,
+	.ioctl = vfio_pci_core_ioctl,
+	.read = vfio_pci_core_read,
+	.write = vfio_pci_core_write,
+	.mmap = vfio_pci_core_mmap,
+	.request = vfio_pci_core_request,
+	.match = vfio_pci_core_match,
+	.bind_iommufd = vfio_iommufd_physical_bind,
+	.unbind_iommufd = vfio_iommufd_physical_unbind,
+	.attach_ioas = vfio_iommufd_physical_attach_ioas,
+	.detach_ioas = vfio_iommufd_physical_detach_ioas,
+};
+
+static struct qat_vf_core_device *qat_vf_drvdata(struct pci_dev *pdev)
+{
+	struct vfio_pci_core_device *core_device = pci_get_drvdata(pdev);
+
+	return container_of(core_device, struct qat_vf_core_device, core_device);
+}
+
+static void qat_vf_pci_aer_reset_done(struct pci_dev *pdev)
+{
+	struct qat_vf_core_device *qat_vdev = qat_vf_drvdata(pdev);
+
+	if (!qat_vdev->mdev)
+		return;
+
+	mutex_lock(&qat_vdev->state_mutex);
+	qat_vf_reset_done(qat_vdev);
+	mutex_unlock(&qat_vdev->state_mutex);
+}
+
+static int
+qat_vf_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct device *dev = &pdev->dev;
+	struct qat_vf_core_device *qat_vdev;
+	int ret;
+
+	qat_vdev = vfio_alloc_device(qat_vf_core_device, core_device.vdev, dev, &qat_vf_pci_ops);
+	if (IS_ERR(qat_vdev))
+		return PTR_ERR(qat_vdev);
+
+	pci_set_drvdata(pdev, &qat_vdev->core_device);
+	ret = vfio_pci_core_register_device(&qat_vdev->core_device);
+	if (ret)
+		goto out_put_device;
+
+	return 0;
+
+out_put_device:
+	vfio_put_device(&qat_vdev->core_device.vdev);
+	return ret;
+}
+
+static void qat_vf_vfio_pci_remove(struct pci_dev *pdev)
+{
+	struct qat_vf_core_device *qat_vdev = qat_vf_drvdata(pdev);
+
+	vfio_pci_core_unregister_device(&qat_vdev->core_device);
+	vfio_put_device(&qat_vdev->core_device.vdev);
+}
+
+static const struct pci_device_id qat_vf_vfio_pci_table[] = {
+	/* Intel QAT GEN4 4xxx VF device */
+	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_INTEL, 0x4941) },
+	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_INTEL, 0x4943) },
+	{ PCI_DRIVER_OVERRIDE_DEVICE_VFIO(PCI_VENDOR_ID_INTEL, 0x4945) },
+	{}
+};
+MODULE_DEVICE_TABLE(pci, qat_vf_vfio_pci_table);
+
+static const struct pci_error_handlers qat_vf_err_handlers = {
+	.reset_done = qat_vf_pci_aer_reset_done,
+	.error_detected = vfio_pci_core_aer_err_detected,
+};
+
+static struct pci_driver qat_vf_vfio_pci_driver = {
+	.name = "qat_vfio_pci",
+	.id_table = qat_vf_vfio_pci_table,
+	.probe = qat_vf_vfio_pci_probe,
+	.remove = qat_vf_vfio_pci_remove,
+	.err_handler = &qat_vf_err_handlers,
+	.driver_managed_dma = true,
+};
+module_pci_driver(qat_vf_vfio_pci_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Xin Zeng <xin.zeng@intel.com>");
+MODULE_DESCRIPTION("QAT VFIO PCI - VFIO PCI driver with live migration support for Intel(R) QAT GEN4 device family");
+MODULE_IMPORT_NS(CRYPTO_QAT);

drivers/vfio/pci/vfio_pci_core.c

@@ -778,25 +778,26 @@ static int vfio_pci_count_devs(struct pci_dev *pdev, void *data)
 }
 
 struct vfio_pci_fill_info {
-	struct vfio_pci_dependent_device __user *devices;
-	struct vfio_pci_dependent_device __user *devices_end;
 	struct vfio_device *vdev;
+	struct vfio_pci_dependent_device *devices;
+	int nr_devices;
 	u32 count;
 	u32 flags;
 };
 
 static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
 {
-	struct vfio_pci_dependent_device info = {
-		.segment = pci_domain_nr(pdev->bus),
-		.bus = pdev->bus->number,
-		.devfn = pdev->devfn,
-	};
+	struct vfio_pci_dependent_device *info;
 	struct vfio_pci_fill_info *fill = data;
 
-	fill->count++;
-	if (fill->devices >= fill->devices_end)
-		return 0;
+	/* The topology changed since we counted devices */
+	if (fill->count >= fill->nr_devices)
+		return -EAGAIN;
+
+	info = &fill->devices[fill->count++];
+	info->segment = pci_domain_nr(pdev->bus);
+	info->bus = pdev->bus->number;
+	info->devfn = pdev->devfn;
 
 	if (fill->flags & VFIO_PCI_HOT_RESET_FLAG_DEV_ID) {
 		struct iommufd_ctx *iommufd = vfio_iommufd_device_ictx(fill->vdev);
@@ -809,19 +810,19 @@ static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
 		 */
 		vdev = vfio_find_device_in_devset(dev_set, &pdev->dev);
 		if (!vdev) {
-			info.devid = VFIO_PCI_DEVID_NOT_OWNED;
+			info->devid = VFIO_PCI_DEVID_NOT_OWNED;
 		} else {
 			int id = vfio_iommufd_get_dev_id(vdev, iommufd);
 
 			if (id > 0)
-				info.devid = id;
+				info->devid = id;
 			else if (id == -ENOENT)
-				info.devid = VFIO_PCI_DEVID_OWNED;
+				info->devid = VFIO_PCI_DEVID_OWNED;
 			else
-				info.devid = VFIO_PCI_DEVID_NOT_OWNED;
+				info->devid = VFIO_PCI_DEVID_NOT_OWNED;
 		}
 		/* If devid is VFIO_PCI_DEVID_NOT_OWNED, clear owned flag. */
-		if (info.devid == VFIO_PCI_DEVID_NOT_OWNED)
+		if (info->devid == VFIO_PCI_DEVID_NOT_OWNED)
 			fill->flags &= ~VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED;
 	} else {
 		struct iommu_group *iommu_group;
@@ -830,13 +831,10 @@ static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data)
 		if (!iommu_group)
 			return -EPERM; /* Cannot reset non-isolated devices */
 
-		info.group_id = iommu_group_id(iommu_group);
+		info->group_id = iommu_group_id(iommu_group);
 		iommu_group_put(iommu_group);
 	}
 
-	if (copy_to_user(fill->devices, &info, sizeof(info)))
-		return -EFAULT;
-	fill->devices++;
 	return 0;
 }
 
@@ -1258,10 +1256,11 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info(
 {
 	unsigned long minsz =
 		offsetofend(struct vfio_pci_hot_reset_info, count);
+	struct vfio_pci_dependent_device *devices = NULL;
 	struct vfio_pci_hot_reset_info hdr;
 	struct vfio_pci_fill_info fill = {};
 	bool slot = false;
-	int ret = 0;
+	int ret, count;
 
 	if (copy_from_user(&hdr, arg, minsz))
 		return -EFAULT;
@@ -1277,9 +1276,26 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info(
 	else if (pci_probe_reset_bus(vdev->pdev->bus))
 		return -ENODEV;
 
-	fill.devices = arg->devices;
-	fill.devices_end = arg->devices +
-			   (hdr.argsz - sizeof(hdr)) / sizeof(arg->devices[0]);
+	ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs,
+					    &count, slot);
+	if (ret)
+		return ret;
+
+	if (WARN_ON(!count)) /* Should always be at least one */
+		return -ERANGE;
+
+	if (count > (hdr.argsz - sizeof(hdr)) / sizeof(*devices)) {
+		hdr.count = count;
+		ret = -ENOSPC;
+		goto header;
+	}
+
+	devices = kcalloc(count, sizeof(*devices), GFP_KERNEL);
+	if (!devices)
+		return -ENOMEM;
+
+	fill.devices = devices;
+	fill.nr_devices = count;
 	fill.vdev = &vdev->vdev;
 
 	if (vfio_device_cdev_opened(&vdev->vdev))
@@ -1291,16 +1307,23 @@ static int vfio_pci_ioctl_get_pci_hot_reset_info(
 					    &fill, slot);
 	mutex_unlock(&vdev->vdev.dev_set->lock);
 	if (ret)
-		return ret;
+		goto out;
+
+	if (copy_to_user(arg->devices, devices,
+			 sizeof(*devices) * fill.count)) {
+		ret = -EFAULT;
+		goto out;
+	}
 
 	hdr.count = fill.count;
 	hdr.flags = fill.flags;
-	if (copy_to_user(arg, &hdr, minsz))
-		return -EFAULT;
 
-	if (fill.count > fill.devices - arg->devices)
-		return -ENOSPC;
-	return 0;
+header:
+	if (copy_to_user(arg, &hdr, minsz))
+		ret = -EFAULT;
+out:
+	kfree(devices);
+	return ret;
 }
 
 static int

drivers/vfio/pci/vfio_pci_intrs.c

@@ -23,6 +23,7 @@
 #include "vfio_pci_priv.h"
 
 struct vfio_pci_irq_ctx {
+	struct vfio_pci_core_device	*vdev;
 	struct eventfd_ctx		*trigger;
 	struct virqfd			*unmask;
 	struct virqfd			*mask;
@@ -84,19 +85,14 @@ vfio_irq_ctx_alloc(struct vfio_pci_core_device *vdev, unsigned long index)
 /*
  * INTx
  */
-static void vfio_send_intx_eventfd(void *opaque, void *unused)
+static void vfio_send_intx_eventfd(void *opaque, void *data)
 {
 	struct vfio_pci_core_device *vdev = opaque;
 
 	if (likely(is_intx(vdev) && !vdev->virq_disabled)) {
-		struct vfio_pci_irq_ctx *ctx;
-		struct eventfd_ctx *trigger;
-
-		ctx = vfio_irq_ctx_get(vdev, 0);
-		if (WARN_ON_ONCE(!ctx))
-			return;
+		struct vfio_pci_irq_ctx *ctx = data;
+		struct eventfd_ctx *trigger = READ_ONCE(ctx->trigger);
 
-		trigger = READ_ONCE(ctx->trigger);
 		if (likely(trigger))
 			eventfd_signal(trigger);
 	}
@@ -166,11 +162,11 @@ bool vfio_pci_intx_mask(struct vfio_pci_core_device *vdev)
  * a signal is necessary, which can then be handled via a work queue
  * or directly depending on the caller.
  */
-static int vfio_pci_intx_unmask_handler(void *opaque, void *unused)
+static int vfio_pci_intx_unmask_handler(void *opaque, void *data)
 {
 	struct vfio_pci_core_device *vdev = opaque;
 	struct pci_dev *pdev = vdev->pdev;
-	struct vfio_pci_irq_ctx *ctx;
+	struct vfio_pci_irq_ctx *ctx = data;
 	unsigned long flags;
 	int ret = 0;
 
@@ -186,10 +182,6 @@ static int vfio_pci_intx_unmask_handler(void *opaque, void *unused)
 		goto out_unlock;
 	}
 
-	ctx = vfio_irq_ctx_get(vdev, 0);
-	if (WARN_ON_ONCE(!ctx))
-		goto out_unlock;
-
 	if (ctx->masked && !vdev->virq_disabled) {
 		/*
 		 * A pending interrupt here would immediately trigger,
@@ -213,10 +205,12 @@ static int vfio_pci_intx_unmask_handler(void *opaque, void *unused)
 
 static void __vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev)
 {
+	struct vfio_pci_irq_ctx *ctx = vfio_irq_ctx_get(vdev, 0);
+
 	lockdep_assert_held(&vdev->igate);
 
-	if (vfio_pci_intx_unmask_handler(vdev, NULL) > 0)
-		vfio_send_intx_eventfd(vdev, NULL);
+	if (vfio_pci_intx_unmask_handler(vdev, ctx) > 0)
+		vfio_send_intx_eventfd(vdev, ctx);
 }
 
 void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev)
@@ -228,15 +222,11 @@ void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev)
 
 static irqreturn_t vfio_intx_handler(int irq, void *dev_id)
 {
-	struct vfio_pci_core_device *vdev = dev_id;
-	struct vfio_pci_irq_ctx *ctx;
+	struct vfio_pci_irq_ctx *ctx = dev_id;
+	struct vfio_pci_core_device *vdev = ctx->vdev;
 	unsigned long flags;
 	int ret = IRQ_NONE;
 
-	ctx = vfio_irq_ctx_get(vdev, 0);
-	if (WARN_ON_ONCE(!ctx))
-		return ret;
-
 	spin_lock_irqsave(&vdev->irqlock, flags);
 
 	if (!vdev->pci_2_3) {
@@ -252,7 +242,7 @@ static irqreturn_t vfio_intx_handler(int irq, void *dev_id)
 	spin_unlock_irqrestore(&vdev->irqlock, flags);
 
 	if (ret == IRQ_HANDLED)
-		vfio_send_intx_eventfd(vdev, NULL);
+		vfio_send_intx_eventfd(vdev, ctx);
 
 	return ret;
 }
@@ -277,11 +267,14 @@ static int vfio_intx_enable(struct vfio_pci_core_device *vdev,
 		return -ENOMEM;
 
 	ctx = vfio_irq_ctx_alloc(vdev, 0);
-	if (!ctx)
+	if (!ctx) {
+		kfree(name);
 		return -ENOMEM;
+	}
 
 	ctx->name = name;
 	ctx->trigger = trigger;
+	ctx->vdev = vdev;
 
 	/*
 	 * Fill the initial masked state based on virq_disabled.  After
@@ -312,7 +305,7 @@ static int vfio_intx_enable(struct vfio_pci_core_device *vdev,
 	vdev->irq_type = VFIO_PCI_INTX_IRQ_INDEX;
 
 	ret = request_irq(pdev->irq, vfio_intx_handler,
-			  irqflags, ctx->name, vdev);
+			  irqflags, ctx->name, ctx);
 	if (ret) {
 		vdev->irq_type = VFIO_PCI_NUM_IRQS;
 		kfree(name);
@@ -358,7 +351,7 @@ static void vfio_intx_disable(struct vfio_pci_core_device *vdev)
 	if (ctx) {
 		vfio_virqfd_disable(&ctx->unmask);
 		vfio_virqfd_disable(&ctx->mask);
-		free_irq(pdev->irq, vdev);
+		free_irq(pdev->irq, ctx);
 		if (ctx->trigger)
 			eventfd_ctx_put(ctx->trigger);
 		kfree(ctx->name);
@@ -606,7 +599,7 @@ static int vfio_pci_set_intx_unmask(struct vfio_pci_core_device *vdev,
 		if (fd >= 0)
 			return vfio_virqfd_enable((void *) vdev,
 						  vfio_pci_intx_unmask_handler,
-						  vfio_send_intx_eventfd, NULL,
+						  vfio_send_intx_eventfd, ctx,
 						  &ctx->unmask, fd);
 
 		vfio_virqfd_disable(&ctx->unmask);
@@ -673,11 +666,11 @@ static int vfio_pci_set_intx_trigger(struct vfio_pci_core_device *vdev,
 		return -EINVAL;
 
 	if (flags & VFIO_IRQ_SET_DATA_NONE) {
-		vfio_send_intx_eventfd(vdev, NULL);
+		vfio_send_intx_eventfd(vdev, vfio_irq_ctx_get(vdev, 0));
 	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
 		uint8_t trigger = *(uint8_t *)data;
 		if (trigger)
-			vfio_send_intx_eventfd(vdev, NULL);
+			vfio_send_intx_eventfd(vdev, vfio_irq_ctx_get(vdev, 0));
 	}
 	return 0;
 }

include/linux/msi.h

@@ -676,6 +676,12 @@ int platform_device_msi_init_and_alloc_irqs(struct device *dev, unsigned int nve
 void platform_device_msi_free_irqs_all(struct device *dev);
 
 bool msi_device_has_isolated_msi(struct device *dev);
+
+static inline int msi_domain_alloc_irqs(struct device *dev, unsigned int domid, int nirqs)
+{
+	return msi_domain_alloc_irqs_range(dev, domid, 0, nirqs - 1);
+}
+
 #else /* CONFIG_GENERIC_MSI_IRQ */
 static inline bool msi_device_has_isolated_msi(struct device *dev)
 {

kernel/irq/msi.c

@@ -1434,6 +1434,7 @@ int msi_domain_alloc_irqs_range(struct device *dev, unsigned int domid,
 	msi_unlock_descs(dev);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(msi_domain_alloc_irqs_range);
 
 /**
  * msi_domain_alloc_irqs_all_locked - Allocate all interrupts from a MSI interrupt domain
@@ -1680,6 +1681,7 @@ void msi_domain_free_irqs_range(struct device *dev, unsigned int domid,
 	msi_domain_free_irqs_range_locked(dev, domid, first, last);
 	msi_unlock_descs(dev);
 }
+EXPORT_SYMBOL_GPL(msi_domain_free_irqs_all);
 
 /**
  * msi_domain_free_irqs_all_locked - Free all interrupts from a MSI interrupt domain