4 files changed, 178 insertions, 252 deletions

diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index c6bb5da2d2a7..579d83bf5358 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -1,6 +1,7 @@
 config VFIO_PCI
 	tristate "VFIO support for PCI devices"
 	depends on VFIO && PCI && EVENTFD
+	select VFIO_VIRQFD
 	help
 	  Support for the PCI VFIO bus driver.  This is required to make
 	  use of PCI drivers using the VFIO framework.
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index f8a186381ae8..69fab0fd15ae 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -11,6 +11,8 @@
  * Author: Tom Lyon, pugs@cisco.com
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/device.h>
 #include <linux/eventfd.h>
 #include <linux/file.h>
@@ -25,6 +27,7 @@
 #include <linux/types.h>
 #include <linux/uaccess.h>
 #include <linux/vfio.h>
+#include <linux/vgaarb.h>
 
 #include "vfio_pci_private.h"
 
@@ -32,13 +35,81 @@
 #define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@redhat.com>"
 #define DRIVER_DESC     "VFIO PCI - User Level meta-driver"
 
+static char ids[1024] __initdata;
+module_param_string(ids, ids, sizeof(ids), 0);
+MODULE_PARM_DESC(ids, "Initial PCI IDs to add to the vfio driver, format is \"vendor:device[:subvendor[:subdevice[:class[:class_mask]]]]\" and multiple comma separated entries can be specified");
+
 static bool nointxmask;
 module_param_named(nointxmask, nointxmask, bool, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(nointxmask,
 		  "Disable support for PCI 2.3 style INTx masking.  If this resolves problems for specific devices, report lspci -vvvxxx to linux-pci@vger.kernel.org so the device can be fixed automatically via the broken_intx_masking flag.");
 
+#ifdef CONFIG_VFIO_PCI_VGA
+static bool disable_vga;
+module_param(disable_vga, bool, S_IRUGO);
+MODULE_PARM_DESC(disable_vga, "Disable VGA resource access through vfio-pci");
+#endif
+
+static bool disable_idle_d3;
+module_param(disable_idle_d3, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(disable_idle_d3,
+		 "Disable using the PCI D3 low power state for idle, unused devices");
+
 static DEFINE_MUTEX(driver_lock);
 
+static inline bool vfio_vga_disabled(void)
+{
+#ifdef CONFIG_VFIO_PCI_VGA
+	return disable_vga;
+#else
+	return true;
+#endif
+}
+
+/*
+ * Our VGA arbiter participation is limited since we don't know anything
+ * about the device itself.  However, if the device is the only VGA device
+ * downstream of a bridge and VFIO VGA support is disabled, then we can
+ * safely return legacy VGA IO and memory as not decoded since the user
+ * has no way to get to it and routing can be disabled externally at the
+ * bridge.
+ */
+static unsigned int vfio_pci_set_vga_decode(void *opaque, bool single_vga)
+{
+	struct vfio_pci_device *vdev = opaque;
+	struct pci_dev *tmp = NULL, *pdev = vdev->pdev;
+	unsigned char max_busnr;
+	unsigned int decodes;
+
+	if (single_vga || !vfio_vga_disabled() || pci_is_root_bus(pdev->bus))
+		return VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
+		       VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM;
+
+	max_busnr = pci_bus_max_busnr(pdev->bus);
+	decodes = VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM;
+
+	while ((tmp = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, tmp)) != NULL) {
+		if (tmp == pdev ||
+		    pci_domain_nr(tmp->bus) != pci_domain_nr(pdev->bus) ||
+		    pci_is_root_bus(tmp->bus))
+			continue;
+
+		if (tmp->bus->number >= pdev->bus->number &&
+		    tmp->bus->number <= max_busnr) {
+			pci_dev_put(tmp);
+			decodes |= VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM;
+			break;
+		}
+	}
+
+	return decodes;
+}
+
+static inline bool vfio_pci_is_vga(struct pci_dev *pdev)
+{
+	return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA;
+}
+
 static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev);
 
 static int vfio_pci_enable(struct vfio_pci_device *vdev)
@@ -48,6 +119,8 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 	u16 cmd;
 	u8 msix_pos;
 
+	pci_set_power_state(pdev, PCI_D0);
+
 	/* Don't allow our initial saved state to include busmaster */
 	pci_clear_master(pdev);
 
@@ -93,10 +166,8 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
 	} else
 		vdev->msix_bar = 0xFF;
 
-#ifdef CONFIG_VFIO_PCI_VGA
-	if ((pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA)
+	if (!vfio_vga_disabled() && vfio_pci_is_vga(pdev))
 		vdev->has_vga = true;
-#endif
 
 	return 0;
 }
@@ -153,20 +224,17 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
 	 * Try to reset the device.  The success of this is dependent on
 	 * being able to lock the device, which is not always possible.
 	 */
-	if (vdev->reset_works) {
-		int ret = pci_try_reset_function(pdev);
-		if (ret)
-			pr_warn("%s: Failed to reset device %s (%d)\n",
-				__func__, dev_name(&pdev->dev), ret);
-		else
-			vdev->needs_reset = false;
-	}
+	if (vdev->reset_works && !pci_try_reset_function(pdev))
+		vdev->needs_reset = false;
 
 	pci_restore_state(pdev);
 out:
 	pci_disable_device(pdev);
 
 	vfio_pci_try_bus_reset(vdev);
+
+	if (!disable_idle_d3)
+		pci_set_power_state(pdev, PCI_D3hot);
 }
 
 static void vfio_pci_release(void *device_data)
@@ -885,6 +953,27 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret) {
 		iommu_group_put(group);
 		kfree(vdev);
+		return ret;
+	}
+
+	if (vfio_pci_is_vga(pdev)) {
+		vga_client_register(pdev, vdev, NULL, vfio_pci_set_vga_decode);
+		vga_set_legacy_decoding(pdev,
+					vfio_pci_set_vga_decode(vdev, false));
+	}
+
+	if (!disable_idle_d3) {
+		/*
+		 * pci-core sets the device power state to an unknown value at
+		 * bootup and after being removed from a driver.  The only
+		 * transition it allows from this unknown state is to D0, which
+		 * typically happens when a driver calls pci_enable_device().
+		 * We're not ready to enable the device yet, but we do want to
+		 * be able to get to D3.  Therefore first do a D0 transition
+		 * before going to D3.
+		 */
+		pci_set_power_state(pdev, PCI_D0);
+		pci_set_power_state(pdev, PCI_D3hot);
 	}
 
 	return ret;
@@ -895,10 +984,21 @@ static void vfio_pci_remove(struct pci_dev *pdev)
 	struct vfio_pci_device *vdev;
 
 	vdev = vfio_del_group_dev(&pdev->dev);
-	if (vdev) {
-		iommu_group_put(pdev->dev.iommu_group);
-		kfree(vdev);
+	if (!vdev)
+		return;
+
+	iommu_group_put(pdev->dev.iommu_group);
+	kfree(vdev);
+
+	if (vfio_pci_is_vga(pdev)) {
+		vga_client_register(pdev, NULL, NULL, NULL);
+		vga_set_legacy_decoding(pdev,
+				VGA_RSRC_NORMAL_IO | VGA_RSRC_NORMAL_MEM |
+				VGA_RSRC_LEGACY_IO | VGA_RSRC_LEGACY_MEM);
 	}
+
+	if (!disable_idle_d3)
+		pci_set_power_state(pdev, PCI_D0);
 }
 
 static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev,
@@ -1017,10 +1117,13 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
 
 put_devs:
 	for (i = 0; i < devs.cur_index; i++) {
-		if (!ret) {
-			tmp = vfio_device_data(devs.devices[i]);
+		tmp = vfio_device_data(devs.devices[i]);
+		if (!ret)
 			tmp->needs_reset = false;
-		}
+
+		if (!tmp->refcnt && !disable_idle_d3)
+			pci_set_power_state(tmp->pdev, PCI_D3hot);
+
 		vfio_device_put(devs.devices[i]);
 	}
 
@@ -1030,10 +1133,50 @@ put_devs:
 static void __exit vfio_pci_cleanup(void)
 {
 	pci_unregister_driver(&vfio_pci_driver);
-	vfio_pci_virqfd_exit();
 	vfio_pci_uninit_perm_bits();
 }
 
+static void __init vfio_pci_fill_ids(void)
+{
+	char *p, *id;
+	int rc;
+
+	/* no ids passed actually */
+	if (ids[0] == '\0')
+		return;
+
+	/* add ids specified in the module parameter */
+	p = ids;
+	while ((id = strsep(&p, ","))) {
+		unsigned int vendor, device, subvendor = PCI_ANY_ID,
+			subdevice = PCI_ANY_ID, class = 0, class_mask = 0;
+		int fields;
+
+		if (!strlen(id))
+			continue;
+
+		fields = sscanf(id, "%x:%x:%x:%x:%x:%x",
+				&vendor, &device, &subvendor, &subdevice,
+				&class, &class_mask);
+
+		if (fields < 2) {
+			pr_warn("invalid id string \"%s\"\n", id);
+			continue;
+		}
+
+		rc = pci_add_dynid(&vfio_pci_driver, vendor, device,
+				   subvendor, subdevice, class, class_mask, 0);
+		if (rc)
+			pr_warn("failed to add dynamic id [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x (%d)\n",
+				vendor, device, subvendor, subdevice,
+				class, class_mask, rc);
+		else
+			pr_info("add [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x\n",
+				vendor, device, subvendor, subdevice,
+				class, class_mask);
+	}
+}
+
 static int __init vfio_pci_init(void)
 {
 	int ret;
@@ -1043,21 +1186,16 @@ static int __init vfio_pci_init(void)
 	if (ret)
 		return ret;
 
-	/* Start the virqfd cleanup handler */
-	ret = vfio_pci_virqfd_init();
-	if (ret)
-		goto out_virqfd;
-
 	/* Register and scan for devices */
 	ret = pci_register_driver(&vfio_pci_driver);
 	if (ret)
 		goto out_driver;
 
+	vfio_pci_fill_ids();
+
 	return 0;
 
 out_driver:
-	vfio_pci_virqfd_exit();
-out_virqfd:
 	vfio_pci_uninit_perm_bits();
 	return ret;
 }
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 2027a27546ef..1f577b4ac126 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -19,230 +19,19 @@
 #include <linux/msi.h>
 #include <linux/pci.h>
 #include <linux/file.h>
-#include <linux/poll.h>
 #include <linux/vfio.h>
 #include <linux/wait.h>
-#include <linux/workqueue.h>
 #include <linux/slab.h>
 
 #include "vfio_pci_private.h"
 
 /*
- * IRQfd - generic
- */
-struct virqfd {
-	struct vfio_pci_device	*vdev;
-	struct eventfd_ctx	*eventfd;
-	int			(*handler)(struct vfio_pci_device *, void *);
-	void			(*thread)(struct vfio_pci_device *, void *);
-	void			*data;
-	struct work_struct	inject;
-	wait_queue_t		wait;
-	poll_table		pt;
-	struct work_struct	shutdown;
-	struct virqfd		**pvirqfd;
-};
-
-static struct workqueue_struct *vfio_irqfd_cleanup_wq;
-
-int __init vfio_pci_virqfd_init(void)
-{
-	vfio_irqfd_cleanup_wq =
-		create_singlethread_workqueue("vfio-irqfd-cleanup");
-	if (!vfio_irqfd_cleanup_wq)
-		return -ENOMEM;
-
-	return 0;
-}
-
-void vfio_pci_virqfd_exit(void)
-{
-	destroy_workqueue(vfio_irqfd_cleanup_wq);
-}
-
-static void virqfd_deactivate(struct virqfd *virqfd)
-{
-	queue_work(vfio_irqfd_cleanup_wq, &virqfd->shutdown);
-}
-
-static int virqfd_wakeup(wait_queue_t *wait, unsigned mode, int sync, void *key)
-{
-	struct virqfd *virqfd = container_of(wait, struct virqfd, wait);
-	unsigned long flags = (unsigned long)key;
-
-	if (flags & POLLIN) {
-		/* An event has been signaled, call function */
-		if ((!virqfd->handler ||
-		     virqfd->handler(virqfd->vdev, virqfd->data)) &&
-		    virqfd->thread)
-			schedule_work(&virqfd->inject);
-	}
-
-	if (flags & POLLHUP) {
-		unsigned long flags;
-		spin_lock_irqsave(&virqfd->vdev->irqlock, flags);
-
-		/*
-		 * The eventfd is closing, if the virqfd has not yet been
-		 * queued for release, as determined by testing whether the
-		 * vdev pointer to it is still valid, queue it now.  As
-		 * with kvm irqfds, we know we won't race against the virqfd
-		 * going away because we hold wqh->lock to get here.
-		 */
-		if (*(virqfd->pvirqfd) == virqfd) {
-			*(virqfd->pvirqfd) = NULL;
-			virqfd_deactivate(virqfd);
-		}
-
-		spin_unlock_irqrestore(&virqfd->vdev->irqlock, flags);
-	}
-
-	return 0;
-}
-
-static void virqfd_ptable_queue_proc(struct file *file,
-				     wait_queue_head_t *wqh, poll_table *pt)
-{
-	struct virqfd *virqfd = container_of(pt, struct virqfd, pt);
-	add_wait_queue(wqh, &virqfd->wait);
-}
-
-static void virqfd_shutdown(struct work_struct *work)
-{
-	struct virqfd *virqfd = container_of(work, struct virqfd, shutdown);
-	u64 cnt;
-
-	eventfd_ctx_remove_wait_queue(virqfd->eventfd, &virqfd->wait, &cnt);
-	flush_work(&virqfd->inject);
-	eventfd_ctx_put(virqfd->eventfd);
-
-	kfree(virqfd);
-}
-
-static void virqfd_inject(struct work_struct *work)
-{
-	struct virqfd *virqfd = container_of(work, struct virqfd, inject);
-	if (virqfd->thread)
-		virqfd->thread(virqfd->vdev, virqfd->data);
-}
-
-static int virqfd_enable(struct vfio_pci_device *vdev,
-			 int (*handler)(struct vfio_pci_device *, void *),
-			 void (*thread)(struct vfio_pci_device *, void *),
-			 void *data, struct virqfd **pvirqfd, int fd)
-{
-	struct fd irqfd;
-	struct eventfd_ctx *ctx;
-	struct virqfd *virqfd;
-	int ret = 0;
-	unsigned int events;
-
-	virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL);
-	if (!virqfd)
-		return -ENOMEM;
-
-	virqfd->pvirqfd = pvirqfd;
-	virqfd->vdev = vdev;
-	virqfd->handler = handler;
-	virqfd->thread = thread;
-	virqfd->data = data;
-
-	INIT_WORK(&virqfd->shutdown, virqfd_shutdown);
-	INIT_WORK(&virqfd->inject, virqfd_inject);
-
-	irqfd = fdget(fd);
-	if (!irqfd.file) {
-		ret = -EBADF;
-		goto err_fd;
-	}
-
-	ctx = eventfd_ctx_fileget(irqfd.file);
-	if (IS_ERR(ctx)) {
-		ret = PTR_ERR(ctx);
-		goto err_ctx;
-	}
-
-	virqfd->eventfd = ctx;
-
-	/*
-	 * virqfds can be released by closing the eventfd or directly
-	 * through ioctl.  These are both done through a workqueue, so
-	 * we update the pointer to the virqfd under lock to avoid
-	 * pushing multiple jobs to release the same virqfd.
-	 */
-	spin_lock_irq(&vdev->irqlock);
-
-	if (*pvirqfd) {
-		spin_unlock_irq(&vdev->irqlock);
-		ret = -EBUSY;
-		goto err_busy;
-	}
-	*pvirqfd = virqfd;
-
-	spin_unlock_irq(&vdev->irqlock);
-
-	/*
-	 * Install our own custom wake-up handling so we are notified via
-	 * a callback whenever someone signals the underlying eventfd.
-	 */
-	init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
-	init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
-
-	events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt);
-
-	/*
-	 * Check if there was an event already pending on the eventfd
-	 * before we registered and trigger it as if we didn't miss it.
-	 */
-	if (events & POLLIN) {
-		if ((!handler || handler(vdev, data)) && thread)
-			schedule_work(&virqfd->inject);
-	}
-
-	/*
-	 * Do not drop the file until the irqfd is fully initialized,
-	 * otherwise we might race against the POLLHUP.
-	 */
-	fdput(irqfd);
-
-	return 0;
-err_busy:
-	eventfd_ctx_put(ctx);
-err_ctx:
-	fdput(irqfd);
-err_fd:
-	kfree(virqfd);
-
-	return ret;
-}
-
-static void virqfd_disable(struct vfio_pci_device *vdev,
-			   struct virqfd **pvirqfd)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&vdev->irqlock, flags);
-
-	if (*pvirqfd) {
-		virqfd_deactivate(*pvirqfd);
-		*pvirqfd = NULL;
-	}
-
-	spin_unlock_irqrestore(&vdev->irqlock, flags);
-
-	/*
-	 * Block until we know all outstanding shutdown jobs have completed.
-	 * Even if we don't queue the job, flush the wq to be sure it's
-	 * been released.
-	 */
-	flush_workqueue(vfio_irqfd_cleanup_wq);
-}
-
-/*
  * INTx
  */
-static void vfio_send_intx_eventfd(struct vfio_pci_device *vdev, void *unused)
+static void vfio_send_intx_eventfd(void *opaque, void *unused)
 {
+	struct vfio_pci_device *vdev = opaque;
+
 	if (likely(is_intx(vdev) && !vdev->virq_disabled))
 		eventfd_signal(vdev->ctx[0].trigger, 1);
 }
@@ -285,9 +74,9 @@ void vfio_pci_intx_mask(struct vfio_pci_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(struct vfio_pci_device *vdev,
-					void *unused)
+static int vfio_pci_intx_unmask_handler(void *opaque, void *unused)
 {
+	struct vfio_pci_device *vdev = opaque;
 	struct pci_dev *pdev = vdev->pdev;
 	unsigned long flags;
 	int ret = 0;
@@ -440,8 +229,8 @@ static int vfio_intx_set_signal(struct vfio_pci_device *vdev, int fd)
 static void vfio_intx_disable(struct vfio_pci_device *vdev)
 {
 	vfio_intx_set_signal(vdev, -1);
-	virqfd_disable(vdev, &vdev->ctx[0].unmask);
-	virqfd_disable(vdev, &vdev->ctx[0].mask);
+	vfio_virqfd_disable(&vdev->ctx[0].unmask);
+	vfio_virqfd_disable(&vdev->ctx[0].mask);
 	vdev->irq_type = VFIO_PCI_NUM_IRQS;
 	vdev->num_ctx = 0;
 	kfree(vdev->ctx);
@@ -605,8 +394,8 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix)
 	vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix);
 
 	for (i = 0; i < vdev->num_ctx; i++) {
-		virqfd_disable(vdev, &vdev->ctx[i].unmask);
-		virqfd_disable(vdev, &vdev->ctx[i].mask);
+		vfio_virqfd_disable(&vdev->ctx[i].unmask);
+		vfio_virqfd_disable(&vdev->ctx[i].mask);
 	}
 
 	if (msix) {
@@ -639,11 +428,12 @@ static int vfio_pci_set_intx_unmask(struct vfio_pci_device *vdev,
 	} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
 		int32_t fd = *(int32_t *)data;
 		if (fd >= 0)
-			return virqfd_enable(vdev, vfio_pci_intx_unmask_handler,
-					     vfio_send_intx_eventfd, NULL,
-					     &vdev->ctx[0].unmask, fd);
+			return vfio_virqfd_enable((void *) vdev,
+						  vfio_pci_intx_unmask_handler,
+						  vfio_send_intx_eventfd, NULL,
+						  &vdev->ctx[0].unmask, fd);
 
-		virqfd_disable(vdev, &vdev->ctx[0].unmask);
+		vfio_virqfd_disable(&vdev->ctx[0].unmask);
 	}
 
 	return 0;
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index c9f9b323f152..ae0e1b4c1711 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -87,9 +87,6 @@ extern ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf,
 extern int vfio_pci_init_perm_bits(void);
 extern void vfio_pci_uninit_perm_bits(void);
 
-extern int vfio_pci_virqfd_init(void);
-extern void vfio_pci_virqfd_exit(void);
-
 extern int vfio_config_init(struct vfio_pci_device *vdev);
 extern void vfio_config_free(struct vfio_pci_device *vdev);
 #endif /* VFIO_PCI_PRIVATE_H */