Merge remote-tracking branch 'linus/master' into merge

Conflicts:
	Documentation/hwmon/ina2xx
	arch/powerpc/Kconfig
	arch/powerpc/boot/dts/b4860emu.dts
	arch/powerpc/boot/dts/b4qds.dtsi
	arch/powerpc/boot/dts/fsl/b4si-post.dtsi
	arch/powerpc/boot/dts/fsl/qoriq-sec6.0-0.dtsi
	arch/powerpc/boot/dts/p1023rdb.dts
	arch/powerpc/boot/dts/t4240emu.dts
	arch/powerpc/boot/dts/t4240qds.dts
	arch/powerpc/configs/85xx/p1023_defconfig
	arch/powerpc/configs/corenet32_smp_defconfig
	arch/powerpc/configs/corenet64_smp_defconfig
	arch/powerpc/configs/mpc85xx_smp_defconfig
	arch/powerpc/include/asm/cputable.h
	arch/powerpc/include/asm/device.h
	arch/powerpc/include/asm/epapr_hcalls.h
	arch/powerpc/include/asm/kvm_host.h
	arch/powerpc/include/asm/mpic.h
	arch/powerpc/include/asm/pci.h
	arch/powerpc/include/asm/ppc-opcode.h
	arch/powerpc/include/asm/ppc_asm.h
	arch/powerpc/include/asm/reg_booke.h
	arch/powerpc/kernel/epapr_paravirt.c
	arch/powerpc/kernel/process.c
	arch/powerpc/kernel/prom.c
	arch/powerpc/kernel/setup-common.c
	arch/powerpc/kernel/setup_32.c
	arch/powerpc/kernel/setup_64.c
	arch/powerpc/kernel/smp.c
	arch/powerpc/kernel/swsusp_asm64.S
	arch/powerpc/kernel/swsusp_booke.S
	arch/powerpc/kvm/book3s_pr.c
	arch/powerpc/kvm/booke.c
	arch/powerpc/kvm/booke.h
	arch/powerpc/kvm/e500.c
	arch/powerpc/kvm/e500.h
	arch/powerpc/kvm/e500_emulate.c
	arch/powerpc/kvm/e500mc.c
	arch/powerpc/kvm/powerpc.c
	arch/powerpc/perf/e6500-pmu.c
	arch/powerpc/platforms/85xx/Kconfig
	arch/powerpc/platforms/85xx/Makefile
	arch/powerpc/platforms/85xx/b4_qds.c
	arch/powerpc/platforms/85xx/c293pcie.c
	arch/powerpc/platforms/85xx/corenet_ds.c
	arch/powerpc/platforms/85xx/corenet_ds.h
	arch/powerpc/platforms/85xx/p1023_rds.c
	arch/powerpc/platforms/85xx/p2041_rdb.c
	arch/powerpc/platforms/85xx/p3041_ds.c
	arch/powerpc/platforms/85xx/p4080_ds.c
	arch/powerpc/platforms/85xx/p5020_ds.c
	arch/powerpc/platforms/85xx/p5040_ds.c
	arch/powerpc/platforms/85xx/smp.c
	arch/powerpc/platforms/85xx/t4240_qds.c
	arch/powerpc/platforms/Kconfig
	arch/powerpc/sysdev/Makefile
	arch/powerpc/sysdev/fsl_mpic_timer_wakeup.c
	arch/powerpc/sysdev/fsl_msi.c
	arch/powerpc/sysdev/fsl_pci.c
	arch/powerpc/sysdev/fsl_pci.h
	arch/powerpc/sysdev/fsl_soc.h
	arch/powerpc/sysdev/mpic.c
	arch/powerpc/sysdev/mpic_timer.c
	drivers/Kconfig
	drivers/clk/Kconfig
	drivers/clk/clk-ppc-corenet.c
	drivers/cpufreq/Kconfig.powerpc
	drivers/cpufreq/Makefile
	drivers/cpufreq/ppc-corenet-cpufreq.c
	drivers/crypto/caam/Kconfig
	drivers/crypto/caam/Makefile
	drivers/crypto/caam/ctrl.c
	drivers/crypto/caam/desc_constr.h
	drivers/crypto/caam/intern.h
	drivers/crypto/caam/jr.c
	drivers/crypto/caam/regs.h
	drivers/dma/fsldma.c
	drivers/hwmon/ina2xx.c
	drivers/iommu/Kconfig
	drivers/iommu/fsl_pamu.c
	drivers/iommu/fsl_pamu.h
	drivers/iommu/fsl_pamu_domain.c
	drivers/iommu/fsl_pamu_domain.h
	drivers/misc/Makefile
	drivers/mmc/card/block.c
	drivers/mmc/core/core.c
	drivers/mmc/host/sdhci-esdhc.h
	drivers/mmc/host/sdhci-pltfm.c
	drivers/mtd/nand/fsl_ifc_nand.c
	drivers/net/ethernet/freescale/gianfar.c
	drivers/net/ethernet/freescale/gianfar.h
	drivers/net/ethernet/freescale/gianfar_ethtool.c
	drivers/net/phy/at803x.c
	drivers/net/phy/phy_device.c
	drivers/net/phy/vitesse.c
	drivers/pci/msi.c
	drivers/staging/Kconfig
	drivers/staging/Makefile
	drivers/uio/Kconfig
	drivers/uio/Makefile
	drivers/uio/uio.c
	drivers/usb/host/ehci-fsl.c
	drivers/vfio/Kconfig
	drivers/vfio/Makefile
	include/crypto/algapi.h
	include/linux/iommu.h
	include/linux/mmc/sdhci.h
	include/linux/msi.h
	include/linux/netdev_features.h
	include/linux/phy.h
	include/linux/skbuff.h
	include/net/ip.h
	include/uapi/linux/vfio.h
	net/core/ethtool.c
	net/ipv4/route.c
	net/ipv6/route.c

1 files changed, 88 insertions, 28 deletions

diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 83f48ad..b23e9ff 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -76,6 +76,7 @@ struct vfio_group {
 	struct notifier_block		nb;
 	struct list_head		vfio_next;
 	struct list_head		container_next;
+	atomic_t			opened;
 };
 
 struct vfio_device {
@@ -206,6 +207,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
 	INIT_LIST_HEAD(&group->device_list);
 	mutex_init(&group->device_lock);
 	atomic_set(&group->container_users, 0);
+	atomic_set(&group->opened, 0);
 	group->iommu_group = iommu_group;
 
 	group->nb.notifier_call = vfio_iommu_group_notifier;
@@ -494,27 +496,6 @@ static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
 	return 0;
 }
 
-static int vfio_group_nb_del_dev(struct vfio_group *group, struct device *dev)
-{
-	struct vfio_device *device;
-
-	/*
-	 * Expect to fall out here.  If a device was in use, it would
-	 * have been bound to a vfio sub-driver, which would have blocked
-	 * in .remove at vfio_del_group_dev.  Sanity check that we no
-	 * longer track the device, so it's safe to remove.
-	 */
-	device = vfio_group_get_device(group, dev);
-	if (likely(!device))
-		return 0;
-
-	WARN("Device %s removed from live group %d!\n", dev_name(dev),
-	     iommu_group_id(group->iommu_group));
-
-	vfio_device_put(device);
-	return 0;
-}
-
 static int vfio_group_nb_verify(struct vfio_group *group, struct device *dev)
 {
 	/* We don't care what happens when the group isn't in use */
@@ -531,13 +512,11 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
 	struct device *dev = data;
 
 	/*
-	 * Need to go through a group_lock lookup to get a reference or
-	 * we risk racing a group being removed.  Leave a WARN_ON for
-	 * debuging, but if the group no longer exists, a spurious notify
-	 * is harmless.
+	 * Need to go through a group_lock lookup to get a reference or we
+	 * risk racing a group being removed.  Ignore spurious notifies.
 	 */
 	group = vfio_group_try_get(group);
-	if (WARN_ON(!group))
+	if (!group)
 		return NOTIFY_OK;
 
 	switch (action) {
@@ -545,7 +524,13 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
 		vfio_group_nb_add_dev(group, dev);
 		break;
 	case IOMMU_GROUP_NOTIFY_DEL_DEVICE:
-		vfio_group_nb_del_dev(group, dev);
+		/*
+		 * Nothing to do here.  If the device is in use, then the
+		 * vfio sub-driver should block the remove callback until
+		 * it is unused.  If the device is unused or attached to a
+		 * stub driver, then it should be released and we don't
+		 * care that it will be going away.
+		 */
 		break;
 	case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
 		pr_debug("%s: Device %s, group %d binding to driver\n",
@@ -1126,7 +1111,7 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf)
 		 * We can't use anon_inode_getfd() because we need to modify
 		 * the f_mode flags directly to allow more than just ioctls
 		 */
-		ret = get_unused_fd();
+		ret = get_unused_fd_flags(O_CLOEXEC);
 		if (ret < 0) {
 			device->ops->release(device->device_data);
 			break;
@@ -1238,12 +1223,22 @@ static long vfio_group_fops_compat_ioctl(struct file *filep,
 static int vfio_group_fops_open(struct inode *inode, struct file *filep)
 {
 	struct vfio_group *group;
+	int opened;
 
 	group = vfio_group_get_from_minor(iminor(inode));
 	if (!group)
 		return -ENODEV;
 
+	/* Do we need multiple instances of the group open?  Seems not. */
+	opened = atomic_cmpxchg(&group->opened, 0, 1);
+	if (opened) {
+		vfio_group_put(group);
+		return -EBUSY;
+	}
+
+	/* Is something still in use from a previous open? */
 	if (group->container) {
+		atomic_dec(&group->opened);
 		vfio_group_put(group);
 		return -EBUSY;
 	}
@@ -1261,6 +1256,8 @@ static int vfio_group_fops_release(struct inode *inode, struct file *filep)
 
 	vfio_group_try_dissolve_container(group);
 
+	atomic_dec(&group->opened);
+
 	vfio_group_put(group);
 
 	return 0;
@@ -1358,6 +1355,68 @@ static const struct file_operations vfio_device_fops = {
 };
 
 /**
+ * External user API, exported by symbols to be linked dynamically.
+ *
+ * The protocol includes:
+ *  1. do normal VFIO init operation:
+ *	- opening a new container;
+ *	- attaching group(s) to it;
+ *	- setting an IOMMU driver for a container.
+ * When IOMMU is set for a container, all groups in it are
+ * considered ready to use by an external user.
+ *
+ * 2. User space passes a group fd to an external user.
+ * The external user calls vfio_group_get_external_user()
+ * to verify that:
+ *	- the group is initialized;
+ *	- IOMMU is set for it.
+ * If both checks passed, vfio_group_get_external_user()
+ * increments the container user counter to prevent
+ * the VFIO group from disposal before KVM exits.
+ *
+ * 3. The external user calls vfio_external_user_iommu_id()
+ * to know an IOMMU ID.
+ *
+ * 4. When the external KVM finishes, it calls
+ * vfio_group_put_external_user() to release the VFIO group.
+ * This call decrements the container user counter.
+ */
+struct vfio_group *vfio_group_get_external_user(struct file *filep)
+{
+	struct vfio_group *group = filep->private_data;
+
+	if (filep->f_op != &vfio_group_fops)
+		return ERR_PTR(-EINVAL);
+
+	if (!atomic_inc_not_zero(&group->container_users))
+		return ERR_PTR(-EINVAL);
+
+	if (!group->container->iommu_driver ||
+			!vfio_group_viable(group)) {
+		atomic_dec(&group->container_users);
+		return ERR_PTR(-EINVAL);
+	}
+
+	vfio_group_get(group);
+
+	return group;
+}
+EXPORT_SYMBOL_GPL(vfio_group_get_external_user);
+
+void vfio_group_put_external_user(struct vfio_group *group)
+{
+	vfio_group_put(group);
+	vfio_group_try_dissolve_container(group);
+}
+EXPORT_SYMBOL_GPL(vfio_group_put_external_user);
+
+int vfio_external_user_iommu_id(struct vfio_group *group)
+{
+	return iommu_group_id(group->iommu_group);
+}
+EXPORT_SYMBOL_GPL(vfio_external_user_iommu_id);
+
+/**
  * Module/class support
  */
 static char *vfio_devnode(struct device *dev, umode_t *mode)
@@ -1417,6 +1476,7 @@ static int __init vfio_init(void)
 	 * drivers.
 	 */
 	request_module_nowait("vfio_iommu_type1");
+	request_module_nowait("vfio_iommu_spapr_tce");
 
 	return 0;