xen: branch for v6.2-rc1

-----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQRTLbB6QfY48x44uB6AXGG7T9hjvgUCY5bIVwAKCRCAXGG7T9hj
 vmOTAQCb5CR7W3ywFjkNOuR2qfHSMNUSTWh04+rUdvWFKoQJywD9EVgYT+jvQbXS
 2zejw/z2ZODLv6rhC+ML0CbXCzcy7gs=
 =L1rx
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-6.2-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - fix memory leaks in error paths

 - add support for virtio PCI-devices in Xen guests on ARM

 - two minor fixes

* tag 'for-linus-6.2-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/privcmd: Fix a possible warning in privcmd_ioctl_mmap_resource()
  x86/xen: Fix memory leak in xen_init_lock_cpu()
  x86/xen: Fix memory leak in xen_smp_intr_init{_pv}()
  xen: fix xen.h build for CONFIG_XEN_PVH=y
  xen/virtio: Handle PCI devices which Host controller is described in DT
  xen/virtio: Optimize the setup of "xen-grant-dma" devices

arch/arm/xen/enlighten.c

@@ -445,7 +445,7 @@ static int __init xen_guest_init(void)
 		return 0;
 
 	if (IS_ENABLED(CONFIG_XEN_VIRTIO))
-		virtio_set_mem_acc_cb(xen_virtio_mem_acc);
+		virtio_set_mem_acc_cb(xen_virtio_restricted_mem_acc);
 
 	if (!acpi_disabled)
 		xen_acpi_guest_init();

arch/x86/xen/smp.c

@@ -32,30 +32,30 @@ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 
 void xen_smp_intr_free(unsigned int cpu)
 {
+	kfree(per_cpu(xen_resched_irq, cpu).name);
+	per_cpu(xen_resched_irq, cpu).name = NULL;
 	if (per_cpu(xen_resched_irq, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu).irq, NULL);
 		per_cpu(xen_resched_irq, cpu).irq = -1;
-		kfree(per_cpu(xen_resched_irq, cpu).name);
-		per_cpu(xen_resched_irq, cpu).name = NULL;
 	}
+	kfree(per_cpu(xen_callfunc_irq, cpu).name);
+	per_cpu(xen_callfunc_irq, cpu).name = NULL;
 	if (per_cpu(xen_callfunc_irq, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu).irq, NULL);
 		per_cpu(xen_callfunc_irq, cpu).irq = -1;
-		kfree(per_cpu(xen_callfunc_irq, cpu).name);
-		per_cpu(xen_callfunc_irq, cpu).name = NULL;
 	}
+	kfree(per_cpu(xen_debug_irq, cpu).name);
+	per_cpu(xen_debug_irq, cpu).name = NULL;
 	if (per_cpu(xen_debug_irq, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu).irq, NULL);
 		per_cpu(xen_debug_irq, cpu).irq = -1;
-		kfree(per_cpu(xen_debug_irq, cpu).name);
-		per_cpu(xen_debug_irq, cpu).name = NULL;
 	}
+	kfree(per_cpu(xen_callfuncsingle_irq, cpu).name);
+	per_cpu(xen_callfuncsingle_irq, cpu).name = NULL;
 	if (per_cpu(xen_callfuncsingle_irq, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu).irq,
 				       NULL);
 		per_cpu(xen_callfuncsingle_irq, cpu).irq = -1;
-		kfree(per_cpu(xen_callfuncsingle_irq, cpu).name);
-		per_cpu(xen_callfuncsingle_irq, cpu).name = NULL;
 	}
 }
 
@@ -65,6 +65,7 @@ int xen_smp_intr_init(unsigned int cpu)
 	char *resched_name, *callfunc_name, *debug_name;
 
 	resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu);
+	per_cpu(xen_resched_irq, cpu).name = resched_name;
 	rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR,
 				    cpu,
 				    xen_reschedule_interrupt,
@@ -74,9 +75,9 @@ int xen_smp_intr_init(unsigned int cpu)
 	if (rc < 0)
 		goto fail;
 	per_cpu(xen_resched_irq, cpu).irq = rc;
-	per_cpu(xen_resched_irq, cpu).name = resched_name;
 
 	callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
+	per_cpu(xen_callfunc_irq, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
 				    cpu,
 				    xen_call_function_interrupt,
@@ -86,10 +87,10 @@ int xen_smp_intr_init(unsigned int cpu)
 	if (rc < 0)
 		goto fail;
 	per_cpu(xen_callfunc_irq, cpu).irq = rc;
-	per_cpu(xen_callfunc_irq, cpu).name = callfunc_name;
 
 	if (!xen_fifo_events) {
 		debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
+		per_cpu(xen_debug_irq, cpu).name = debug_name;
 		rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu,
 					     xen_debug_interrupt,
 					     IRQF_PERCPU | IRQF_NOBALANCING,
@@ -97,10 +98,10 @@ int xen_smp_intr_init(unsigned int cpu)
 		if (rc < 0)
 			goto fail;
 		per_cpu(xen_debug_irq, cpu).irq = rc;
-		per_cpu(xen_debug_irq, cpu).name = debug_name;
 	}
 
 	callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
+	per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
 				    cpu,
 				    xen_call_function_single_interrupt,
@@ -110,7 +111,6 @@ int xen_smp_intr_init(unsigned int cpu)
 	if (rc < 0)
 		goto fail;
 	per_cpu(xen_callfuncsingle_irq, cpu).irq = rc;
-	per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name;
 
 	return 0;
 

arch/x86/xen/smp_pv.c

@@ -97,18 +97,18 @@ asmlinkage __visible void cpu_bringup_and_idle(void)
 
 void xen_smp_intr_free_pv(unsigned int cpu)
 {
+	kfree(per_cpu(xen_irq_work, cpu).name);
+	per_cpu(xen_irq_work, cpu).name = NULL;
 	if (per_cpu(xen_irq_work, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_irq_work, cpu).irq, NULL);
 		per_cpu(xen_irq_work, cpu).irq = -1;
-		kfree(per_cpu(xen_irq_work, cpu).name);
-		per_cpu(xen_irq_work, cpu).name = NULL;
 	}
 
+	kfree(per_cpu(xen_pmu_irq, cpu).name);
+	per_cpu(xen_pmu_irq, cpu).name = NULL;
 	if (per_cpu(xen_pmu_irq, cpu).irq >= 0) {
 		unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL);
 		per_cpu(xen_pmu_irq, cpu).irq = -1;
-		kfree(per_cpu(xen_pmu_irq, cpu).name);
-		per_cpu(xen_pmu_irq, cpu).name = NULL;
 	}
 }
 
@@ -118,6 +118,7 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 	char *callfunc_name, *pmu_name;
 
 	callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu);
+	per_cpu(xen_irq_work, cpu).name = callfunc_name;
 	rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
 				    cpu,
 				    xen_irq_work_interrupt,
@@ -127,10 +128,10 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 	if (rc < 0)
 		goto fail;
 	per_cpu(xen_irq_work, cpu).irq = rc;
-	per_cpu(xen_irq_work, cpu).name = callfunc_name;
 
 	if (is_xen_pmu) {
 		pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu);
+		per_cpu(xen_pmu_irq, cpu).name = pmu_name;
 		rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu,
 					     xen_pmu_irq_handler,
 					     IRQF_PERCPU|IRQF_NOBALANCING,
@@ -138,7 +139,6 @@ int xen_smp_intr_init_pv(unsigned int cpu)
 		if (rc < 0)
 			goto fail;
 		per_cpu(xen_pmu_irq, cpu).irq = rc;
-		per_cpu(xen_pmu_irq, cpu).name = pmu_name;
 	}
 
 	return 0;

arch/x86/xen/spinlock.c

@@ -75,6 +75,7 @@ void xen_init_lock_cpu(int cpu)
 	     cpu, per_cpu(lock_kicker_irq, cpu));
 
 	name = kasprintf(GFP_KERNEL, "spinlock%d", cpu);
+	per_cpu(irq_name, cpu) = name;
 	irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR,
 				     cpu,
 				     dummy_handler,
@@ -85,7 +86,6 @@ void xen_init_lock_cpu(int cpu)
 	if (irq >= 0) {
 		disable_irq(irq); /* make sure it's never delivered */
 		per_cpu(lock_kicker_irq, cpu) = irq;
-		per_cpu(irq_name, cpu) = name;
 	}
 
 	printk("cpu %d spinlock event irq %d\n", cpu, irq);
@@ -98,6 +98,8 @@ void xen_uninit_lock_cpu(int cpu)
 	if (!xen_pvspin)
 		return;
 
+	kfree(per_cpu(irq_name, cpu));
+	per_cpu(irq_name, cpu) = NULL;
 	/*
 	 * When booting the kernel with 'mitigations=auto,nosmt', the secondary
 	 * CPUs are not activated, and lock_kicker_irq is not initialized.
@@ -108,8 +110,6 @@ void xen_uninit_lock_cpu(int cpu)
 
 	unbind_from_irqhandler(irq, NULL);
 	per_cpu(lock_kicker_irq, cpu) = -1;
-	kfree(per_cpu(irq_name, cpu));
-	per_cpu(irq_name, cpu) = NULL;
 }
 
 PV_CALLEE_SAVE_REGS_THUNK(xen_vcpu_stolen);

drivers/xen/grant-dma-ops.c

@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/dma-map-ops.h>
 #include <linux/of.h>
+#include <linux/pci.h>
 #include <linux/pfn.h>
 #include <linux/xarray.h>
 #include <linux/virtio_anchor.h>
@@ -292,50 +293,48 @@ static const struct dma_map_ops xen_grant_dma_ops = {
 	.dma_supported = xen_grant_dma_supported,
 };
 
-static bool xen_is_dt_grant_dma_device(struct device *dev)
+static struct device_node *xen_dt_get_node(struct device *dev)
 {
-	struct device_node *iommu_np;
-	bool has_iommu;
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+		struct pci_bus *bus = pdev->bus;
 
-	iommu_np = of_parse_phandle(dev->of_node, "iommus", 0);
-	has_iommu = iommu_np &&
-		    of_device_is_compatible(iommu_np, "xen,grant-dma");
-	of_node_put(iommu_np);
+		/* Walk up to the root bus to look for PCI Host controller */
+		while (!pci_is_root_bus(bus))
+			bus = bus->parent;
 
-	return has_iommu;
-}
+		return of_node_get(bus->bridge->parent->of_node);
+	}
 
-bool xen_is_grant_dma_device(struct device *dev)
-{
-	/* XXX Handle only DT devices for now */
-	if (dev->of_node)
-		return xen_is_dt_grant_dma_device(dev);
-
-	return false;
-}
-
-bool xen_virtio_mem_acc(struct virtio_device *dev)
-{
-	if (IS_ENABLED(CONFIG_XEN_VIRTIO_FORCE_GRANT) || xen_pv_domain())
-		return true;
-
-	return xen_is_grant_dma_device(dev->dev.parent);
+	return of_node_get(dev->of_node);
 }
 
 static int xen_dt_grant_init_backend_domid(struct device *dev,
-					   struct xen_grant_dma_data *data)
+					   struct device_node *np,
+					   domid_t *backend_domid)
 {
-	struct of_phandle_args iommu_spec;
+	struct of_phandle_args iommu_spec = { .args_count = 1 };
 
-	if (of_parse_phandle_with_args(dev->of_node, "iommus", "#iommu-cells",
-			0, &iommu_spec)) {
-		dev_err(dev, "Cannot parse iommus property\n");
-		return -ESRCH;
+	if (dev_is_pci(dev)) {
+		struct pci_dev *pdev = to_pci_dev(dev);
+		u32 rid = PCI_DEVID(pdev->bus->number, pdev->devfn);
+
+		if (of_map_id(np, rid, "iommu-map", "iommu-map-mask", &iommu_spec.np,
+				iommu_spec.args)) {
+			dev_dbg(dev, "Cannot translate ID\n");
+			return -ESRCH;
+		}
+	} else {
+		if (of_parse_phandle_with_args(np, "iommus", "#iommu-cells",
+				0, &iommu_spec)) {
+			dev_dbg(dev, "Cannot parse iommus property\n");
+			return -ESRCH;
+		}
 	}
 
 	if (!of_device_is_compatible(iommu_spec.np, "xen,grant-dma") ||
 			iommu_spec.args_count != 1) {
-		dev_err(dev, "Incompatible IOMMU node\n");
+		dev_dbg(dev, "Incompatible IOMMU node\n");
 		of_node_put(iommu_spec.np);
 		return -ESRCH;
 	}
@@ -346,12 +345,31 @@ static int xen_dt_grant_init_backend_domid(struct device *dev,
 	 * The endpoint ID here means the ID of the domain where the
 	 * corresponding backend is running
 	 */
-	data->backend_domid = iommu_spec.args[0];
+	*backend_domid = iommu_spec.args[0];
 
 	return 0;
 }
 
-void xen_grant_setup_dma_ops(struct device *dev)
+static int xen_grant_init_backend_domid(struct device *dev,
+					domid_t *backend_domid)
+{
+	struct device_node *np;
+	int ret = -ENODEV;
+
+	np = xen_dt_get_node(dev);
+	if (np) {
+		ret = xen_dt_grant_init_backend_domid(dev, np, backend_domid);
+		of_node_put(np);
+	} else if (IS_ENABLED(CONFIG_XEN_VIRTIO_FORCE_GRANT) || xen_pv_domain()) {
+		dev_info(dev, "Using dom0 as backend\n");
+		*backend_domid = 0;
+		ret = 0;
+	}
+
+	return ret;
+}
+
+static void xen_grant_setup_dma_ops(struct device *dev, domid_t backend_domid)
 {
 	struct xen_grant_dma_data *data;
 
@@ -365,16 +383,7 @@ void xen_grant_setup_dma_ops(struct device *dev)
 	if (!data)
 		goto err;
 
-	if (dev->of_node) {
-		if (xen_dt_grant_init_backend_domid(dev, data))
-			goto err;
-	} else if (IS_ENABLED(CONFIG_XEN_VIRTIO_FORCE_GRANT)) {
-		dev_info(dev, "Using dom0 as backend\n");
-		data->backend_domid = 0;
-	} else {
-		/* XXX ACPI device unsupported for now */
-		goto err;
-	}
+	data->backend_domid = backend_domid;
 
 	if (store_xen_grant_dma_data(dev, data)) {
 		dev_err(dev, "Cannot store Xen grant DMA data\n");
@@ -392,12 +401,14 @@ err:
 
 bool xen_virtio_restricted_mem_acc(struct virtio_device *dev)
 {
-	bool ret = xen_virtio_mem_acc(dev);
+	domid_t backend_domid;
 
-	if (ret)
-		xen_grant_setup_dma_ops(dev->dev.parent);
+	if (!xen_grant_init_backend_domid(dev->dev.parent, &backend_domid)) {
+		xen_grant_setup_dma_ops(dev->dev.parent, backend_domid);
+		return true;
+	}
 
-	return ret;
+	return false;
 }
 
 MODULE_DESCRIPTION("Xen grant DMA-mapping layer");

drivers/xen/privcmd.c

@@ -760,7 +760,7 @@ static long privcmd_ioctl_mmap_resource(struct file *file,
 		goto out;
 	}
 
-	pfns = kcalloc(kdata.num, sizeof(*pfns), GFP_KERNEL);
+	pfns = kcalloc(kdata.num, sizeof(*pfns), GFP_KERNEL | __GFP_NOWARN);
 	if (!pfns) {
 		rc = -ENOMEM;
 		goto out;

include/xen/arm/xen-ops.h

@@ -8,9 +8,7 @@
 static inline void xen_setup_dma_ops(struct device *dev)
 {
 #ifdef CONFIG_XEN
-	if (xen_is_grant_dma_device(dev))
-		xen_grant_setup_dma_ops(dev);
-	else if (xen_swiotlb_detect())
+	if (xen_swiotlb_detect())
 		dev->dma_ops = &xen_swiotlb_dma_ops;
 #endif
 }

include/xen/xen-ops.h

@@ -216,26 +216,10 @@ static inline void xen_preemptible_hcall_end(void) { }
 #endif /* CONFIG_XEN_PV && !CONFIG_PREEMPTION */
 
 #ifdef CONFIG_XEN_GRANT_DMA_OPS
-void xen_grant_setup_dma_ops(struct device *dev);
-bool xen_is_grant_dma_device(struct device *dev);
-bool xen_virtio_mem_acc(struct virtio_device *dev);
 bool xen_virtio_restricted_mem_acc(struct virtio_device *dev);
 #else
-static inline void xen_grant_setup_dma_ops(struct device *dev)
-{
-}
-static inline bool xen_is_grant_dma_device(struct device *dev)
-{
-	return false;
-}
-
 struct virtio_device;
 
-static inline bool xen_virtio_mem_acc(struct virtio_device *dev)
-{
-	return false;
-}
-
 static inline bool xen_virtio_restricted_mem_acc(struct virtio_device *dev)
 {
 	return false;

include/xen/xen.h

@@ -2,6 +2,8 @@
 #ifndef _XEN_XEN_H
 #define _XEN_XEN_H
 
+#include <linux/types.h>
+
 enum xen_domain_type {
 	XEN_NATIVE,		/* running on bare hardware    */
 	XEN_PV_DOMAIN,		/* running in a PV domain      */
@@ -25,8 +27,6 @@ extern bool xen_pvh;
 #define xen_hvm_domain()	(xen_domain_type == XEN_HVM_DOMAIN)
 #define xen_pvh_domain()	(xen_pvh)
 
-#include <linux/types.h>
-
 extern uint32_t xen_start_flags;
 
 #include <xen/interface/hvm/start_info.h>