Merge tag 'for-linus-6.9-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - Xen event channel handling fix for a regression with a rare kernel
   config and some added hardening

 - better support of running Xen dom0 in PVH mode

 - a cleanup for the xen grant-dma-iommu driver

* tag 'for-linus-6.9-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/events: increment refcnt only if event channel is refcounted
  xen/evtchn: avoid WARN() when unbinding an event channel
  x86/xen: attempt to inflate the memory balloon on PVH
  xen/grant-dma-iommu: Convert to platform remove callback returning void

10 files changed, 143 insertions, 59 deletions

diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index a9088250770f..64fbd2dbc5b7 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -62,6 +62,11 @@ void xen_arch_unregister_cpu(int num);
 #ifdef CONFIG_PVH
 void __init xen_pvh_init(struct boot_params *boot_params);
 void __init mem_map_via_hcall(struct boot_params *boot_params_p);
+#ifdef CONFIG_XEN_PVH
+void __init xen_reserve_extra_memory(struct boot_params *bootp);
+#else
+static inline void xen_reserve_extra_memory(struct boot_params *bootp) { }
+#endif
 #endif
 
 /* Lazy mode for batching updates / context switch */
diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c
index 944e0290f2c0..8c2d4b8de25d 100644
--- a/arch/x86/platform/pvh/enlighten.c
+++ b/arch/x86/platform/pvh/enlighten.c
@@ -75,6 +75,9 @@ static void __init init_pvh_bootparams(bool xen_guest)
 	} else
 		xen_raw_printk("Warning: Can fit ISA range into e820\n");
 
+	if (xen_guest)
+		xen_reserve_extra_memory(&pvh_bootparams);
+
 	pvh_bootparams.hdr.cmd_line_ptr =
 		pvh_start_info.cmdline_paddr;
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 3c61bb98c10e..a01ca255b0c6 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -6,6 +6,7 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/kexec.h>
+#include <linux/memblock.h>
 #include <linux/slab.h>
 #include <linux/panic_notifier.h>
 
@@ -350,3 +351,34 @@ void xen_arch_unregister_cpu(int num)
 }
 EXPORT_SYMBOL(xen_arch_unregister_cpu);
 #endif
+
+/* Amount of extra memory space we add to the e820 ranges */
+struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
+
+void __init xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns)
+{
+	unsigned int i;
+
+	/*
+	 * No need to check for zero size, should happen rarely and will only
+	 * write a new entry regarded to be unused due to zero size.
+	 */
+	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+		/* Add new region. */
+		if (xen_extra_mem[i].n_pfns == 0) {
+			xen_extra_mem[i].start_pfn = start_pfn;
+			xen_extra_mem[i].n_pfns = n_pfns;
+			break;
+		}
+		/* Append to existing region. */
+		if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns ==
+		    start_pfn) {
+			xen_extra_mem[i].n_pfns += n_pfns;
+			break;
+		}
+	}
+	if (i == XEN_EXTRA_MEM_MAX_REGIONS)
+		printk(KERN_WARNING "Warning: not enough extra memory regions\n");
+
+	memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
+}
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index 9e9db601bd52..27a2a02ef8fb 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/acpi.h>
 #include <linux/export.h>
+#include <linux/mm.h>
 
 #include <xen/hvc-console.h>
 
@@ -73,3 +74,70 @@ void __init mem_map_via_hcall(struct boot_params *boot_params_p)
 	}
 	boot_params_p->e820_entries = memmap.nr_entries;
 }
+
+/*
+ * Reserve e820 UNUSABLE regions to inflate the memory balloon.
+ *
+ * On PVH dom0 the host memory map is used, RAM regions available to dom0 are
+ * located as the same place as in the native memory map, but since dom0 gets
+ * less memory than the total amount of host RAM the ranges that can't be
+ * populated are converted from RAM -> UNUSABLE.  Use such regions (up to the
+ * ratio signaled in EXTRA_MEM_RATIO) in order to inflate the balloon driver at
+ * boot.  Doing so prevents the guest (even if just temporary) from using holes
+ * in the memory map in order to map grants or foreign addresses, and
+ * hopefully limits the risk of a clash with a device MMIO region.  Ideally the
+ * hypervisor should notify us which memory ranges are suitable for creating
+ * foreign mappings, but that's not yet implemented.
+ */
+void __init xen_reserve_extra_memory(struct boot_params *bootp)
+{
+	unsigned int i, ram_pages = 0, extra_pages;
+
+	for (i = 0; i < bootp->e820_entries; i++) {
+		struct boot_e820_entry *e = &bootp->e820_table[i];
+
+		if (e->type != E820_TYPE_RAM)
+			continue;
+		ram_pages += PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr);
+	}
+
+	/* Max amount of extra memory. */
+	extra_pages = EXTRA_MEM_RATIO * ram_pages;
+
+	/*
+	 * Convert UNUSABLE ranges to RAM and reserve them for foreign mapping
+	 * purposes.
+	 */
+	for (i = 0; i < bootp->e820_entries && extra_pages; i++) {
+		struct boot_e820_entry *e = &bootp->e820_table[i];
+		unsigned long pages;
+
+		if (e->type != E820_TYPE_UNUSABLE)
+			continue;
+
+		pages = min(extra_pages,
+			PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr));
+
+		if (pages != (PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr))) {
+			struct boot_e820_entry *next;
+
+			if (bootp->e820_entries ==
+			    ARRAY_SIZE(bootp->e820_table))
+				/* No space left to split - skip region. */
+				continue;
+
+			/* Split entry. */
+			next = e + 1;
+			memmove(next, e,
+				(bootp->e820_entries - i) * sizeof(*e));
+			bootp->e820_entries++;
+			next->addr = PAGE_ALIGN(e->addr) + PFN_PHYS(pages);
+			e->size = next->addr - e->addr;
+			next->size -= e->size;
+		}
+		e->type = E820_TYPE_RAM;
+		extra_pages -= pages;
+
+		xen_add_extra_mem(PFN_UP(e->addr), pages);
+	}
+}
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index b3e37961065a..380591028cb8 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -38,9 +38,6 @@
 
 #define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024)
 
-/* Amount of extra memory space we add to the e820 ranges */
-struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
-
 /* Number of pages released from the initial allocation. */
 unsigned long xen_released_pages;
 
@@ -64,18 +61,6 @@ static struct {
 } xen_remap_buf __initdata __aligned(PAGE_SIZE);
 static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;
 
-/*
- * The maximum amount of extra memory compared to the base size.  The
- * main scaling factor is the size of struct page.  At extreme ratios
- * of base:extra, all the base memory can be filled with page
- * structures for the extra memory, leaving no space for anything
- * else.
- *
- * 10x seems like a reasonable balance between scaling flexibility and
- * leaving a practically usable system.
- */
-#define EXTRA_MEM_RATIO		(10)
-
 static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB);
 
 static void __init xen_parse_512gb(void)
@@ -96,35 +81,6 @@ static void __init xen_parse_512gb(void)
 	xen_512gb_limit = val;
 }
 
-static void __init xen_add_extra_mem(unsigned long start_pfn,
-				     unsigned long n_pfns)
-{
-	int i;
-
-	/*
-	 * No need to check for zero size, should happen rarely and will only
-	 * write a new entry regarded to be unused due to zero size.
-	 */
-	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
-		/* Add new region. */
-		if (xen_extra_mem[i].n_pfns == 0) {
-			xen_extra_mem[i].start_pfn = start_pfn;
-			xen_extra_mem[i].n_pfns = n_pfns;
-			break;
-		}
-		/* Append to existing region. */
-		if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns ==
-		    start_pfn) {
-			xen_extra_mem[i].n_pfns += n_pfns;
-			break;
-		}
-	}
-	if (i == XEN_EXTRA_MEM_MAX_REGIONS)
-		printk(KERN_WARNING "Warning: not enough extra memory regions\n");
-
-	memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
-}
-
 static void __init xen_del_extra_mem(unsigned long start_pfn,
 				     unsigned long n_pfns)
 {
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index a87ab36889e7..79cf93f2c92f 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -163,4 +163,18 @@ void xen_hvm_post_suspend(int suspend_cancelled);
 static inline void xen_hvm_post_suspend(int suspend_cancelled) {}
 #endif
 
+/*
+ * The maximum amount of extra memory compared to the base size.  The
+ * main scaling factor is the size of struct page.  At extreme ratios
+ * of base:extra, all the base memory can be filled with page
+ * structures for the extra memory, leaving no space for anything
+ * else.
+ *
+ * 10x seems like a reasonable balance between scaling flexibility and
+ * leaving a practically usable system.
+ */
+#define EXTRA_MEM_RATIO		(10)
+
+void xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns);
+
 #endif /* XEN_OPS_H */
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 976c6cdf9ee6..aaf2514fcfa4 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -672,7 +672,6 @@ EXPORT_SYMBOL(xen_free_ballooned_pages);
 
 static void __init balloon_add_regions(void)
 {
-#if defined(CONFIG_XEN_PV)
 	unsigned long start_pfn, pages;
 	unsigned long pfn, extra_pfn_end;
 	unsigned int i;
@@ -696,7 +695,6 @@ static void __init balloon_add_regions(void)
 
 		balloon_stats.total_pages += extra_pfn_end - start_pfn;
 	}
-#endif
 }
 
 static int __init balloon_init(void)
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 2faa4bf78c7a..81effbd53dc5 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -1190,7 +1190,7 @@ int xen_pirq_from_irq(unsigned irq)
 EXPORT_SYMBOL_GPL(xen_pirq_from_irq);
 
 static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip,
-				   struct xenbus_device *dev)
+				   struct xenbus_device *dev, bool shared)
 {
 	int ret = -ENOMEM;
 	struct irq_info *info;
@@ -1224,7 +1224,8 @@ static int bind_evtchn_to_irq_chip(evtchn_port_t evtchn, struct irq_chip *chip,
 		 */
 		bind_evtchn_to_cpu(info, 0, false);
 	} else if (!WARN_ON(info->type != IRQT_EVTCHN)) {
-		info->refcnt++;
+		if (shared && !WARN_ON(info->refcnt < 0))
+			info->refcnt++;
 	}
 
 	ret = info->irq;
@@ -1237,13 +1238,13 @@ out:
 
 int bind_evtchn_to_irq(evtchn_port_t evtchn)
 {
-	return bind_evtchn_to_irq_chip(evtchn, &xen_dynamic_chip, NULL);
+	return bind_evtchn_to_irq_chip(evtchn, &xen_dynamic_chip, NULL, false);
 }
 EXPORT_SYMBOL_GPL(bind_evtchn_to_irq);
 
 int bind_evtchn_to_irq_lateeoi(evtchn_port_t evtchn)
 {
-	return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip, NULL);
+	return bind_evtchn_to_irq_chip(evtchn, &xen_lateeoi_chip, NULL, false);
 }
 EXPORT_SYMBOL_GPL(bind_evtchn_to_irq_lateeoi);
 
@@ -1295,7 +1296,8 @@ static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu)
 
 static int bind_interdomain_evtchn_to_irq_chip(struct xenbus_device *dev,
 					       evtchn_port_t remote_port,
-					       struct irq_chip *chip)
+					       struct irq_chip *chip,
+					       bool shared)
 {
 	struct evtchn_bind_interdomain bind_interdomain;
 	int err;
@@ -1307,14 +1309,14 @@ static int bind_interdomain_evtchn_to_irq_chip(struct xenbus_device *dev,
 					  &bind_interdomain);
 
 	return err ? : bind_evtchn_to_irq_chip(bind_interdomain.local_port,
-					       chip, dev);
+					       chip, dev, shared);
 }
 
 int bind_interdomain_evtchn_to_irq_lateeoi(struct xenbus_device *dev,
 					   evtchn_port_t remote_port)
 {
 	return bind_interdomain_evtchn_to_irq_chip(dev, remote_port,
-						   &xen_lateeoi_chip);
+						   &xen_lateeoi_chip, false);
 }
 EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq_lateeoi);
 
@@ -1430,7 +1432,8 @@ static int bind_evtchn_to_irqhandler_chip(evtchn_port_t evtchn,
 {
 	int irq, retval;
 
-	irq = bind_evtchn_to_irq_chip(evtchn, chip, NULL);
+	irq = bind_evtchn_to_irq_chip(evtchn, chip, NULL,
+				      irqflags & IRQF_SHARED);
 	if (irq < 0)
 		return irq;
 	retval = request_irq(irq, handler, irqflags, devname, dev_id);
@@ -1471,7 +1474,8 @@ static int bind_interdomain_evtchn_to_irqhandler_chip(
 {
 	int irq, retval;
 
-	irq = bind_interdomain_evtchn_to_irq_chip(dev, remote_port, chip);
+	irq = bind_interdomain_evtchn_to_irq_chip(dev, remote_port, chip,
+						  irqflags & IRQF_SHARED);
 	if (irq < 0)
 		return irq;
 
diff --git a/drivers/xen/evtchn.c b/drivers/xen/evtchn.c
index 59717628ca42..f6a2216c2c87 100644
--- a/drivers/xen/evtchn.c
+++ b/drivers/xen/evtchn.c
@@ -85,6 +85,7 @@ struct user_evtchn {
 	struct per_user_data *user;
 	evtchn_port_t port;
 	bool enabled;
+	bool unbinding;
 };
 
 static void evtchn_free_ring(evtchn_port_t *ring)
@@ -164,6 +165,10 @@ static irqreturn_t evtchn_interrupt(int irq, void *data)
 	struct per_user_data *u = evtchn->user;
 	unsigned int prod, cons;
 
+	/* Handler might be called when tearing down the IRQ. */
+	if (evtchn->unbinding)
+		return IRQ_HANDLED;
+
 	WARN(!evtchn->enabled,
 	     "Interrupt for port %u, but apparently not enabled; per-user %p\n",
 	     evtchn->port, u);
@@ -421,6 +426,7 @@ static void evtchn_unbind_from_user(struct per_user_data *u,
 
 	BUG_ON(irq < 0);
 
+	evtchn->unbinding = true;
 	unbind_from_irqhandler(irq, evtchn);
 
 	del_evtchn(u, evtchn);
diff --git a/drivers/xen/grant-dma-iommu.c b/drivers/xen/grant-dma-iommu.c
index 6a9fe02c6bfc..2ee750a03c2f 100644
--- a/drivers/xen/grant-dma-iommu.c
+++ b/drivers/xen/grant-dma-iommu.c
@@ -51,14 +51,12 @@ static int grant_dma_iommu_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int grant_dma_iommu_remove(struct platform_device *pdev)
+static void grant_dma_iommu_remove(struct platform_device *pdev)
 {
 	struct grant_dma_iommu_device *mmu = platform_get_drvdata(pdev);
 
 	platform_set_drvdata(pdev, NULL);
 	iommu_device_unregister(&mmu->iommu);
-
-	return 0;
 }
 
 static struct platform_driver grant_dma_iommu_driver = {
@@ -67,7 +65,7 @@ static struct platform_driver grant_dma_iommu_driver = {
 		.of_match_table = grant_dma_iommu_of_match,
 	},
 	.probe = grant_dma_iommu_probe,
-	.remove = grant_dma_iommu_remove,
+	.remove_new = grant_dma_iommu_remove,
 };
 
 static int __init grant_dma_iommu_init(void)