Merge tag 'for-linus-4.19-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from Juergen Gross:

 - add dma-buf functionality to Xen grant table handling

 - fix for booting the kernel as Xen PVH dom0

 - fix for booting the kernel as a Xen PV guest with
   CONFIG_DEBUG_VIRTUAL enabled

 - other minor performance and style fixes

* tag 'for-linus-4.19-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip:
  xen/balloon: fix balloon initialization for PVH Dom0
  xen: don't use privcmd_call() from xen_mc_flush()
  xen/pv: Call get_cpu_address_sizes to set x86_virt/phys_bits
  xen/biomerge: Use true and false for boolean values
  xen/gntdev: don't dereference a null gntdev_dmabuf on allocation failure
  xen/spinlock: Don't use pvqspinlock if only 1 vCPU
  xen/gntdev: Implement dma-buf import functionality
  xen/gntdev: Implement dma-buf export functionality
  xen/gntdev: Add initial support for dma-buf UAPI
  xen/gntdev: Make private routines/structures accessible
  xen/gntdev: Allow mappings for DMA buffers
  xen/grant-table: Allow allocating buffers suitable for DMA
  xen/balloon: Share common memory reservation routines
  xen/grant-table: Make set/clear page private code shared

arch/x86/include/asm/xen/hypercall.h

@@ -209,24 +209,37 @@ extern struct { char _entry[32]; } hypercall_page[];
 })
 
 static inline long
-privcmd_call(unsigned call,
-	     unsigned long a1, unsigned long a2,
-	     unsigned long a3, unsigned long a4,
-	     unsigned long a5)
+xen_single_call(unsigned int call,
+		unsigned long a1, unsigned long a2,
+		unsigned long a3, unsigned long a4,
+		unsigned long a5)
 {
 	__HYPERCALL_DECLS;
 	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
 
-	stac();
 	asm volatile(CALL_NOSPEC
 		     : __HYPERCALL_5PARAM
 		     : [thunk_target] "a" (&hypercall_page[call])
 		     : __HYPERCALL_CLOBBER5);
-	clac();
 
 	return (long)__res;
 }
 
+static inline long
+privcmd_call(unsigned int call,
+	     unsigned long a1, unsigned long a2,
+	     unsigned long a3, unsigned long a4,
+	     unsigned long a5)
+{
+	long res;
+
+	stac();
+	res = xen_single_call(call, a1, a2, a3, a4, a5);
+	clac();
+
+	return res;
+}
+
 static inline int
 HYPERVISOR_set_trap_table(struct trap_info *table)
 {

arch/x86/kernel/cpu/common.c

@@ -905,7 +905,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 	apply_forced_caps(c);
 }
 
-static void get_cpu_address_sizes(struct cpuinfo_x86 *c)
+void get_cpu_address_sizes(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
 

arch/x86/kernel/cpu/cpu.h

@@ -46,6 +46,7 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],
 			    *const __x86_cpu_dev_end[];
 
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
+extern void get_cpu_address_sizes(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
 extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
 extern u32 get_scattered_cpuid_leaf(unsigned int level,

arch/x86/xen/enlighten_pv.c

@@ -1256,6 +1256,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	get_cpu_cap(&boot_cpu_data);
 	x86_configure_nx();
 
+	/* Determine virtual and physical address sizes */
+	get_cpu_address_sizes(&boot_cpu_data);
+
 	/* Let's presume PV guests always boot on vCPU with id 0. */
 	per_cpu(xen_vcpu_id, 0) = 0;
 

arch/x86/xen/multicalls.c

@@ -80,9 +80,9 @@ void xen_mc_flush(void)
 		   and just do the call directly. */
 		mc = &b->entries[0];
 
-		mc->result = privcmd_call(mc->op,
-					  mc->args[0], mc->args[1], mc->args[2], 
-					  mc->args[3], mc->args[4]);
+		mc->result = xen_single_call(mc->op, mc->args[0], mc->args[1],
+					     mc->args[2], mc->args[3],
+					     mc->args[4]);
 		ret = mc->result < 0;
 		break;
 

arch/x86/xen/spinlock.c

@@ -130,6 +130,10 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_vcpu_stolen);
 void __init xen_init_spinlocks(void)
 {
 
+	/*  Don't need to use pvqspinlock code if there is only 1 vCPU. */
+	if (num_possible_cpus() == 1)
+		xen_pvspin = false;
+
 	if (!xen_pvspin) {
 		printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
 		return;

drivers/xen/Kconfig

@@ -152,6 +152,16 @@ config XEN_GNTDEV
 	help
 	  Allows userspace processes to use grants.
 
+config XEN_GNTDEV_DMABUF
+	bool "Add support for dma-buf grant access device driver extension"
+	depends on XEN_GNTDEV && XEN_GRANT_DMA_ALLOC && DMA_SHARED_BUFFER
+	help
+	  Allows userspace processes and kernel modules to use Xen backed
+	  dma-buf implementation. With this extension grant references to
+	  the pages of an imported dma-buf can be exported for other domain
+	  use and grant references coming from a foreign domain can be
+	  converted into a local dma-buf for local export.
+
 config XEN_GRANT_DEV_ALLOC
 	tristate "User-space grant reference allocator driver"
 	depends on XEN
@@ -161,6 +171,20 @@ config XEN_GRANT_DEV_ALLOC
 	  to other domains. This can be used to implement frontend drivers
 	  or as part of an inter-domain shared memory channel.
 
+config XEN_GRANT_DMA_ALLOC
+	bool "Allow allocating DMA capable buffers with grant reference module"
+	depends on XEN && HAS_DMA
+	help
+	  Extends grant table module API to allow allocating DMA capable
+	  buffers and mapping foreign grant references on top of it.
+	  The resulting buffer is similar to one allocated by the balloon
+	  driver in that proper memory reservation is made by
+	  ({increase|decrease}_reservation and VA mappings are updated if
+	  needed).
+	  This is useful for sharing foreign buffers with HW drivers which
+	  cannot work with scattered buffers provided by the balloon driver,
+	  but require DMAable memory instead.
+
 config SWIOTLB_XEN
 	def_bool y
 	select SWIOTLB

drivers/xen/Makefile

@@ -2,6 +2,7 @@
 obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
 obj-$(CONFIG_X86)			+= fallback.o
 obj-y	+= grant-table.o features.o balloon.o manage.o preempt.o time.o
+obj-y	+= mem-reservation.o
 obj-y	+= events/
 obj-y	+= xenbus/
 
@@ -40,5 +41,6 @@ obj-$(CONFIG_XEN_PVCALLS_BACKEND)	+= pvcalls-back.o
 obj-$(CONFIG_XEN_PVCALLS_FRONTEND)	+= pvcalls-front.o
 xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
+xen-gntdev-$(CONFIG_XEN_GNTDEV_DMABUF)	+= gntdev-dmabuf.o
 xen-gntalloc-y				:= gntalloc.o
 xen-privcmd-y				:= privcmd.o privcmd-buf.o

drivers/xen/balloon.c

@@ -71,6 +71,7 @@
 #include <xen/balloon.h>
 #include <xen/features.h>
 #include <xen/page.h>
+#include <xen/mem-reservation.h>
 
 static int xen_hotplug_unpopulated;
 
@@ -157,13 +158,6 @@ static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
 #define GFP_BALLOON \
 	(GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC)
 
-static void scrub_page(struct page *page)
-{
-#ifdef CONFIG_XEN_SCRUB_PAGES
-	clear_highpage(page);
-#endif
-}
-
 /* balloon_append: add the given page to the balloon. */
 static void __balloon_append(struct page *page)
 {
@@ -463,11 +457,6 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 	int rc;
 	unsigned long i;
 	struct page   *page;
-	struct xen_memory_reservation reservation = {
-		.address_bits = 0,
-		.extent_order = EXTENT_ORDER,
-		.domid        = DOMID_SELF
-	};
 
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
@@ -479,16 +468,11 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 			break;
 		}
 
-		/* XENMEM_populate_physmap requires a PFN based on Xen
-		 * granularity.
-		 */
 		frame_list[i] = page_to_xen_pfn(page);
 		page = balloon_next_page(page);
 	}
 
-	set_xen_guest_handle(reservation.extent_start, frame_list);
-	reservation.nr_extents = nr_pages;
-	rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
+	rc = xenmem_reservation_increase(nr_pages, frame_list);
 	if (rc <= 0)
 		return BP_EAGAIN;
 
@@ -496,29 +480,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 		page = balloon_retrieve(false);
 		BUG_ON(page == NULL);
 
-#ifdef CONFIG_XEN_HAVE_PVMMU
-		/*
-		 * We don't support PV MMU when Linux and Xen is using
-		 * different page granularity.
-		 */
-		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
-
-		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			unsigned long pfn = page_to_pfn(page);
-
-			set_phys_to_machine(pfn, frame_list[i]);
-
-			/* Link back into the page tables if not highmem. */
-			if (!PageHighMem(page)) {
-				int ret;
-				ret = HYPERVISOR_update_va_mapping(
-						(unsigned long)__va(pfn << PAGE_SHIFT),
-						mfn_pte(frame_list[i], PAGE_KERNEL),
-						0);
-				BUG_ON(ret);
-			}
-		}
-#endif
+		xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]);
 
 		/* Relinquish the page back to the allocator. */
 		free_reserved_page(page);
@@ -535,11 +497,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 	unsigned long i;
 	struct page *page, *tmp;
 	int ret;
-	struct xen_memory_reservation reservation = {
-		.address_bits = 0,
-		.extent_order = EXTENT_ORDER,
-		.domid        = DOMID_SELF
-	};
 	LIST_HEAD(pages);
 
 	if (nr_pages > ARRAY_SIZE(frame_list))
@@ -553,7 +510,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 			break;
 		}
 		adjust_managed_page_count(page, -1);
-		scrub_page(page);
+		xenmem_reservation_scrub_page(page);
 		list_add(&page->lru, &pages);
 	}
 
@@ -572,28 +529,10 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 	 */
 	i = 0;
 	list_for_each_entry_safe(page, tmp, &pages, lru) {
-		/* XENMEM_decrease_reservation requires a GFN */
 		frame_list[i++] = xen_page_to_gfn(page);
 
-#ifdef CONFIG_XEN_HAVE_PVMMU
-		/*
-		 * We don't support PV MMU when Linux and Xen is using
-		 * different page granularity.
-		 */
-		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
-
-		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			unsigned long pfn = page_to_pfn(page);
+		xenmem_reservation_va_mapping_reset(1, &page);
 
-			if (!PageHighMem(page)) {
-				ret = HYPERVISOR_update_va_mapping(
-						(unsigned long)__va(pfn << PAGE_SHIFT),
-						__pte_ma(0), 0);
-				BUG_ON(ret);
-			}
-			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
-		}
-#endif
 		list_del(&page->lru);
 
 		balloon_append(page);
@@ -601,9 +540,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 
 	flush_tlb_all();
 
-	set_xen_guest_handle(reservation.extent_start, frame_list);
-	reservation.nr_extents   = nr_pages;
-	ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
+	ret = xenmem_reservation_decrease(nr_pages, frame_list);
 	BUG_ON(ret != nr_pages);
 
 	balloon_stats.current_pages -= nr_pages;

drivers/xen/biomerge.c

@@ -17,7 +17,7 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 	 * XXX: Add support for merging bio_vec when using different page
 	 * size in Xen and Linux.
 	 */
-	return 0;
+	return false;
 #endif
 }
 EXPORT_SYMBOL(xen_biovec_phys_mergeable);

drivers/xen/gntdev-common.h

+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Common functionality of grant device.
+ *
+ * Copyright (c) 2006-2007, D G Murray.
+ *           (c) 2009 Gerd Hoffmann <kraxel@redhat.com>
+ *           (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#ifndef _GNTDEV_COMMON_H
+#define _GNTDEV_COMMON_H
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/mmu_notifier.h>
+#include <linux/types.h>
+
+struct gntdev_dmabuf_priv;
+
+struct gntdev_priv {
+	/* Maps with visible offsets in the file descriptor. */
+	struct list_head maps;
+	/*
+	 * Maps that are not visible; will be freed on munmap.
+	 * Only populated if populate_freeable_maps == 1
+	 */
+	struct list_head freeable_maps;
+	/* lock protects maps and freeable_maps. */
+	struct mutex lock;
+	struct mm_struct *mm;
+	struct mmu_notifier mn;
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	/* Device for which DMA memory is allocated. */
+	struct device *dma_dev;
+#endif
+
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	struct gntdev_dmabuf_priv *dmabuf_priv;
+#endif
+};
+
+struct gntdev_unmap_notify {
+	int flags;
+	/* Address relative to the start of the gntdev_grant_map. */
+	int addr;
+	int event;
+};
+
+struct gntdev_grant_map {
+	struct list_head next;
+	struct vm_area_struct *vma;
+	int index;
+	int count;
+	int flags;
+	refcount_t users;
+	struct gntdev_unmap_notify notify;
+	struct ioctl_gntdev_grant_ref *grants;
+	struct gnttab_map_grant_ref   *map_ops;
+	struct gnttab_unmap_grant_ref *unmap_ops;
+	struct gnttab_map_grant_ref   *kmap_ops;
+	struct gnttab_unmap_grant_ref *kunmap_ops;
+	struct page **pages;
+	unsigned long pages_vm_start;
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	/*
+	 * If dmabuf_vaddr is not NULL then this mapping is backed by DMA
+	 * capable memory.
+	 */
+
+	struct device *dma_dev;
+	/* Flags used to create this DMA buffer: GNTDEV_DMA_FLAG_XXX. */
+	int dma_flags;
+	void *dma_vaddr;
+	dma_addr_t dma_bus_addr;
+	/* Needed to avoid allocation in gnttab_dma_free_pages(). */
+	xen_pfn_t *frames;
+#endif
+};
+
+struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
+					  int dma_flags);
+
+void gntdev_add_map(struct gntdev_priv *priv, struct gntdev_grant_map *add);
+
+void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map);
+
+bool gntdev_account_mapped_pages(int count);
+
+int gntdev_map_grant_pages(struct gntdev_grant_map *map);
+
+#endif

drivers/xen/gntdev-dmabuf.h

+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Xen dma-buf functionality for gntdev.
+ *
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#ifndef _GNTDEV_DMABUF_H
+#define _GNTDEV_DMABUF_H
+
+#include <xen/gntdev.h>
+
+struct gntdev_dmabuf_priv;
+struct gntdev_priv;
+
+struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void);
+
+void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv);
+
+long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod,
+				       struct ioctl_gntdev_dmabuf_exp_from_refs __user *u);
+
+long gntdev_ioctl_dmabuf_exp_wait_released(struct gntdev_priv *priv,
+					   struct ioctl_gntdev_dmabuf_exp_wait_released __user *u);
+
+long gntdev_ioctl_dmabuf_imp_to_refs(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_to_refs __user *u);
+
+long gntdev_ioctl_dmabuf_imp_release(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_release __user *u);
+
+#endif

drivers/xen/grant-table.c

@@ -45,6 +45,9 @@
 #include <linux/workqueue.h>
 #include <linux/ratelimit.h>
 #include <linux/moduleparam.h>
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+#include <linux/dma-mapping.h>
+#endif
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -57,6 +60,7 @@
 #ifdef CONFIG_X86
 #include <asm/xen/cpuid.h>
 #endif
+#include <xen/mem-reservation.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
@@ -769,29 +773,18 @@ void gnttab_free_auto_xlat_frames(void)
 }
 EXPORT_SYMBOL_GPL(gnttab_free_auto_xlat_frames);
 
-/**
- * gnttab_alloc_pages - alloc pages suitable for grant mapping into
- * @nr_pages: number of pages to alloc
- * @pages: returns the pages
- */
-int gnttab_alloc_pages(int nr_pages, struct page **pages)
+int gnttab_pages_set_private(int nr_pages, struct page **pages)
 {
 	int i;
-	int ret;
-
-	ret = alloc_xenballooned_pages(nr_pages, pages);
-	if (ret < 0)
-		return ret;
 
 	for (i = 0; i < nr_pages; i++) {
 #if BITS_PER_LONG < 64
 		struct xen_page_foreign *foreign;
 
 		foreign = kzalloc(sizeof(*foreign), GFP_KERNEL);
-		if (!foreign) {
-			gnttab_free_pages(nr_pages, pages);
+		if (!foreign)
 			return -ENOMEM;
-		}
+
 		set_page_private(pages[i], (unsigned long)foreign);
 #endif
 		SetPagePrivate(pages[i]);
@@ -799,14 +792,30 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
+EXPORT_SYMBOL_GPL(gnttab_pages_set_private);
 
 /**
- * gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
- * @nr_pages; number of pages to free
- * @pages: the pages
+ * gnttab_alloc_pages - alloc pages suitable for grant mapping into
+ * @nr_pages: number of pages to alloc
+ * @pages: returns the pages
  */
-void gnttab_free_pages(int nr_pages, struct page **pages)
+int gnttab_alloc_pages(int nr_pages, struct page **pages)
+{
+	int ret;
+
+	ret = alloc_xenballooned_pages(nr_pages, pages);
+	if (ret < 0)
+		return ret;
+
+	ret = gnttab_pages_set_private(nr_pages, pages);
+	if (ret < 0)
+		gnttab_free_pages(nr_pages, pages);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
+
+void gnttab_pages_clear_private(int nr_pages, struct page **pages)
 {
 	int i;
 
@@ -818,10 +827,114 @@ void gnttab_free_pages(int nr_pages, struct page **pages)
 			ClearPagePrivate(pages[i]);
 		}
 	}
+}
+EXPORT_SYMBOL_GPL(gnttab_pages_clear_private);
+
+/**
+ * gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
+ * @nr_pages; number of pages to free
+ * @pages: the pages
+ */
+void gnttab_free_pages(int nr_pages, struct page **pages)
+{
+	gnttab_pages_clear_private(nr_pages, pages);
 	free_xenballooned_pages(nr_pages, pages);
 }
 EXPORT_SYMBOL_GPL(gnttab_free_pages);
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+/**
+ * gnttab_dma_alloc_pages - alloc DMAable pages suitable for grant mapping into
+ * @args: arguments to the function
+ */
+int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args)
+{
+	unsigned long pfn, start_pfn;
+	size_t size;
+	int i, ret;
+
+	size = args->nr_pages << PAGE_SHIFT;
+	if (args->coherent)
+		args->vaddr = dma_alloc_coherent(args->dev, size,
+						 &args->dev_bus_addr,
+						 GFP_KERNEL | __GFP_NOWARN);
+	else
+		args->vaddr = dma_alloc_wc(args->dev, size,
+					   &args->dev_bus_addr,
+					   GFP_KERNEL | __GFP_NOWARN);
+	if (!args->vaddr) {
+		pr_debug("Failed to allocate DMA buffer of size %zu\n", size);
+		return -ENOMEM;
+	}
+
+	start_pfn = __phys_to_pfn(args->dev_bus_addr);
+	for (pfn = start_pfn, i = 0; pfn < start_pfn + args->nr_pages;
+			pfn++, i++) {
+		struct page *page = pfn_to_page(pfn);
+
+		args->pages[i] = page;
+		args->frames[i] = xen_page_to_gfn(page);
+		xenmem_reservation_scrub_page(page);
+	}
+
+	xenmem_reservation_va_mapping_reset(args->nr_pages, args->pages);
+
+	ret = xenmem_reservation_decrease(args->nr_pages, args->frames);
+	if (ret != args->nr_pages) {
+		pr_debug("Failed to decrease reservation for DMA buffer\n");
+		ret = -EFAULT;
+		goto fail;
+	}
+
+	ret = gnttab_pages_set_private(args->nr_pages, args->pages);
+	if (ret < 0)
+		goto fail;
+
+	return 0;
+
+fail:
+	gnttab_dma_free_pages(args);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_dma_alloc_pages);
+
+/**
+ * gnttab_dma_free_pages - free DMAable pages
+ * @args: arguments to the function
+ */
+int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args)
+{
+	size_t size;
+	int i, ret;
+
+	gnttab_pages_clear_private(args->nr_pages, args->pages);
+
+	for (i = 0; i < args->nr_pages; i++)
+		args->frames[i] = page_to_xen_pfn(args->pages[i]);
+
+	ret = xenmem_reservation_increase(args->nr_pages, args->frames);
+	if (ret != args->nr_pages) {
+		pr_debug("Failed to decrease reservation for DMA buffer\n");
+		ret = -EFAULT;
+	} else {
+		ret = 0;
+	}
+
+	xenmem_reservation_va_mapping_update(args->nr_pages, args->pages,
+					     args->frames);
+
+	size = args->nr_pages << PAGE_SHIFT;
+	if (args->coherent)
+		dma_free_coherent(args->dev, size,
+				  args->vaddr, args->dev_bus_addr);
+	else
+		dma_free_wc(args->dev, size,
+			    args->vaddr, args->dev_bus_addr);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_dma_free_pages);
+#endif
+
 /* Handling of paged out grant targets (GNTST_eagain) */
 #define MAX_DELAY 256
 static inline void

drivers/xen/mem-reservation.c

+// SPDX-License-Identifier: GPL-2.0
+
+/******************************************************************************
+ * Xen memory reservation utilities.
+ *
+ * Copyright (c) 2003, B Dragovic
+ * Copyright (c) 2003-2004, M Williamson, K Fraser
+ * Copyright (c) 2005 Dan M. Smith, IBM Corporation
+ * Copyright (c) 2010 Daniel Kiper
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#include <asm/xen/hypercall.h>
+
+#include <xen/interface/memory.h>
+#include <xen/mem-reservation.h>
+
+/*
+ * Use one extent per PAGE_SIZE to avoid to break down the page into
+ * multiple frame.
+ */
+#define EXTENT_ORDER (fls(XEN_PFN_PER_PAGE) - 1)
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+void __xenmem_reservation_va_mapping_update(unsigned long count,
+					    struct page **pages,
+					    xen_pfn_t *frames)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		struct page *page = pages[i];
+		unsigned long pfn = page_to_pfn(page);
+
+		BUG_ON(!page);
+
+		/*
+		 * We don't support PV MMU when Linux and Xen is using
+		 * different page granularity.
+		 */
+		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
+
+		set_phys_to_machine(pfn, frames[i]);
+
+		/* Link back into the page tables if not highmem. */
+		if (!PageHighMem(page)) {
+			int ret;
+
+			ret = HYPERVISOR_update_va_mapping(
+					(unsigned long)__va(pfn << PAGE_SHIFT),
+					mfn_pte(frames[i], PAGE_KERNEL),
+					0);
+			BUG_ON(ret);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(__xenmem_reservation_va_mapping_update);
+
+void __xenmem_reservation_va_mapping_reset(unsigned long count,
+					   struct page **pages)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		struct page *page = pages[i];
+		unsigned long pfn = page_to_pfn(page);
+
+		/*
+		 * We don't support PV MMU when Linux and Xen are using
+		 * different page granularity.
+		 */
+		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
+
+		if (!PageHighMem(page)) {
+			int ret;
+
+			ret = HYPERVISOR_update_va_mapping(
+					(unsigned long)__va(pfn << PAGE_SHIFT),
+					__pte_ma(0), 0);
+			BUG_ON(ret);
+		}
+		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+	}
+}
+EXPORT_SYMBOL_GPL(__xenmem_reservation_va_mapping_reset);
+#endif /* CONFIG_XEN_HAVE_PVMMU */
+
+/* @frames is an array of PFNs */
+int xenmem_reservation_increase(int count, xen_pfn_t *frames)
+{
+	struct xen_memory_reservation reservation = {
+		.address_bits = 0,
+		.extent_order = EXTENT_ORDER,
+		.domid        = DOMID_SELF
+	};
+
+	/* XENMEM_populate_physmap requires a PFN based on Xen granularity. */
+	set_xen_guest_handle(reservation.extent_start, frames);
+	reservation.nr_extents = count;
+	return HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
+}
+EXPORT_SYMBOL_GPL(xenmem_reservation_increase);
+
+/* @frames is an array of GFNs */
+int xenmem_reservation_decrease(int count, xen_pfn_t *frames)
+{
+	struct xen_memory_reservation reservation = {
+		.address_bits = 0,
+		.extent_order = EXTENT_ORDER,
+		.domid        = DOMID_SELF
+	};
+
+	/* XENMEM_decrease_reservation requires a GFN */
+	set_xen_guest_handle(reservation.extent_start, frames);
+	reservation.nr_extents = count;
+	return HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
+}
+EXPORT_SYMBOL_GPL(xenmem_reservation_decrease);

drivers/xen/xen-balloon.c

@@ -81,7 +81,7 @@ static void watch_target(struct xenbus_watch *watch,
 			static_max = new_target;
 		else
 			static_max >>= PAGE_SHIFT - 10;
-		target_diff = xen_pv_domain() ? 0
+		target_diff = (xen_pv_domain() || xen_initial_domain()) ? 0
 				: static_max - balloon_stats.target_pages;
 	}
 

include/uapi/xen/gntdev.h

@@ -5,6 +5,7 @@
  * Interface to /dev/xen/gntdev.
  * 
  * Copyright (c) 2007, D G Murray
+ * Copyright (c) 2018, Oleksandr Andrushchenko, EPAM Systems Inc.
  * 
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version 2
@@ -200,4 +201,109 @@ struct ioctl_gntdev_grant_copy {
 /* Send an interrupt on the indicated event channel */
 #define UNMAP_NOTIFY_SEND_EVENT 0x2
 
+/*
+ * Flags to be used while requesting memory mapping's backing storage
+ * to be allocated with DMA API.
+ */
+
+/*
+ * The buffer is backed with memory allocated with dma_alloc_wc.
+ */
+#define GNTDEV_DMA_FLAG_WC		(1 << 0)
+
+/*
+ * The buffer is backed with memory allocated with dma_alloc_coherent.
+ */
+#define GNTDEV_DMA_FLAG_COHERENT	(1 << 1)
+
+/*
+ * Create a dma-buf [1] from grant references @refs of count @count provided
+ * by the foreign domain @domid with flags @flags.
+ *
+ * By default dma-buf is backed by system memory pages, but by providing
+ * one of the GNTDEV_DMA_FLAG_XXX flags it can also be created as
+ * a DMA write-combine or coherent buffer, e.g. allocated with dma_alloc_wc/
+ * dma_alloc_coherent.
+ *
+ * Returns 0 if dma-buf was successfully created and the corresponding
+ * dma-buf's file descriptor is returned in @fd.
+ *
+ * [1] Documentation/driver-api/dma-buf.rst
+ */
+
+#define IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS \
+	_IOC(_IOC_NONE, 'G', 9, \
+	     sizeof(struct ioctl_gntdev_dmabuf_exp_from_refs))
+struct ioctl_gntdev_dmabuf_exp_from_refs {
+	/* IN parameters. */
+	/* Specific options for this dma-buf: see GNTDEV_DMA_FLAG_XXX. */
+	__u32 flags;
+	/* Number of grant references in @refs array. */
+	__u32 count;
+	/* OUT parameters. */
+	/* File descriptor of the dma-buf. */
+	__u32 fd;
+	/* The domain ID of the grant references to be mapped. */
+	__u32 domid;
+	/* Variable IN parameter. */
+	/* Array of grant references of size @count. */
+	__u32 refs[1];
+};
+
+/*
+ * This will block until the dma-buf with the file descriptor @fd is
+ * released. This is only valid for buffers created with
+ * IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS.
+ *
+ * If within @wait_to_ms milliseconds the buffer is not released
+ * then -ETIMEDOUT error is returned.
+ * If the buffer with the file descriptor @fd does not exist or has already
+ * been released, then -ENOENT is returned. For valid file descriptors
+ * this must not be treated as error.
+ */
+#define IOCTL_GNTDEV_DMABUF_EXP_WAIT_RELEASED \
+	_IOC(_IOC_NONE, 'G', 10, \
+	     sizeof(struct ioctl_gntdev_dmabuf_exp_wait_released))
+struct ioctl_gntdev_dmabuf_exp_wait_released {
+	/* IN parameters */
+	__u32 fd;
+	__u32 wait_to_ms;
+};
+
+/*
+ * Import a dma-buf with file descriptor @fd and export granted references
+ * to the pages of that dma-buf into array @refs of size @count.
+ */
+#define IOCTL_GNTDEV_DMABUF_IMP_TO_REFS \
+	_IOC(_IOC_NONE, 'G', 11, \
+	     sizeof(struct ioctl_gntdev_dmabuf_imp_to_refs))
+struct ioctl_gntdev_dmabuf_imp_to_refs {
+	/* IN parameters. */
+	/* File descriptor of the dma-buf. */
+	__u32 fd;
+	/* Number of grant references in @refs array. */
+	__u32 count;
+	/* The domain ID for which references to be granted. */
+	__u32 domid;
+	/* Reserved - must be zero. */
+	__u32 reserved;
+	/* OUT parameters. */
+	/* Array of grant references of size @count. */
+	__u32 refs[1];
+};
+
+/*
+ * This will close all references to the imported buffer with file descriptor
+ * @fd, so it can be released by the owner. This is only valid for buffers
+ * created with IOCTL_GNTDEV_DMABUF_IMP_TO_REFS.
+ */
+#define IOCTL_GNTDEV_DMABUF_IMP_RELEASE \
+	_IOC(_IOC_NONE, 'G', 12, \
+	     sizeof(struct ioctl_gntdev_dmabuf_imp_release))
+struct ioctl_gntdev_dmabuf_imp_release {
+	/* IN parameters */
+	__u32 fd;
+	__u32 reserved;
+};
+
 #endif /* __LINUX_PUBLIC_GNTDEV_H__ */

include/xen/grant_table.h

@@ -198,6 +198,27 @@ void gnttab_free_auto_xlat_frames(void);
 int gnttab_alloc_pages(int nr_pages, struct page **pages);
 void gnttab_free_pages(int nr_pages, struct page **pages);
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+struct gnttab_dma_alloc_args {
+	/* Device for which DMA memory will be/was allocated. */
+	struct device *dev;
+	/* If set then DMA buffer is coherent and write-combine otherwise. */
+	bool coherent;
+
+	int nr_pages;
+	struct page **pages;
+	xen_pfn_t *frames;
+	void *vaddr;
+	dma_addr_t dev_bus_addr;
+};
+
+int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args);
+int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args);
+#endif
+
+int gnttab_pages_set_private(int nr_pages, struct page **pages);
+void gnttab_pages_clear_private(int nr_pages, struct page **pages);
+
 int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		    struct gnttab_map_grant_ref *kmap_ops,
 		    struct page **pages, unsigned int count);

include/xen/mem-reservation.h

+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Xen memory reservation utilities.
+ *
+ * Copyright (c) 2003, B Dragovic
+ * Copyright (c) 2003-2004, M Williamson, K Fraser
+ * Copyright (c) 2005 Dan M. Smith, IBM Corporation
+ * Copyright (c) 2010 Daniel Kiper
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#ifndef _XENMEM_RESERVATION_H
+#define _XENMEM_RESERVATION_H
+
+#include <linux/highmem.h>
+
+#include <xen/page.h>
+
+static inline void xenmem_reservation_scrub_page(struct page *page)
+{
+#ifdef CONFIG_XEN_SCRUB_PAGES
+	clear_highpage(page);
+#endif
+}
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+void __xenmem_reservation_va_mapping_update(unsigned long count,
+					    struct page **pages,
+					    xen_pfn_t *frames);
+
+void __xenmem_reservation_va_mapping_reset(unsigned long count,
+					   struct page **pages);
+#endif
+
+static inline void xenmem_reservation_va_mapping_update(unsigned long count,
+							struct page **pages,
+							xen_pfn_t *frames)
+{
+#ifdef CONFIG_XEN_HAVE_PVMMU
+	if (!xen_feature(XENFEAT_auto_translated_physmap))
+		__xenmem_reservation_va_mapping_update(count, pages, frames);
+#endif
+}
+
+static inline void xenmem_reservation_va_mapping_reset(unsigned long count,
+						       struct page **pages)
+{
+#ifdef CONFIG_XEN_HAVE_PVMMU
+	if (!xen_feature(XENFEAT_auto_translated_physmap))
+		__xenmem_reservation_va_mapping_reset(count, pages);
+#endif
+}
+
+int xenmem_reservation_increase(int count, xen_pfn_t *frames);
+
+int xenmem_reservation_decrease(int count, xen_pfn_t *frames);
+
+#endif