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

Author: torvalds

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

@@ -0,0 +1,217 @@
+// 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/