xen: features for 4.4-rc0

- Improve balloon driver memory hotplug placement.
 - Use unpopulated hotplugged memory for foreign pages (if
   supported/enabled).
 - Support 64 KiB guest pages on arm64.
 - CPU hotplug support on arm/arm64.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJWOeSkAAoJEFxbo/MsZsTRph0H/0nE8Tx0GyGtOyCYfBdInTvI
 WgjvL8VR1XrweZMVis3668MzhLSYg6b5lvJsoi+L3jlzYRyze43iHXsKfvp+8p0o
 TVUhFnlHEHF8ASEtPydAi6HgS7Dn9OQ9LaZ45R1Gk0rHnwJjIQonhTn2jB0yS9Am
 Hf4aZXP2NVZphjYcloqNsLH0G6mGLtgq8cS0uKcVO2YIrR4Dr3sfj9qfq9mflf8n
 sA/5ifoHRfOUD1vJzYs4YmIBUv270jSsprWK/Mi2oXIxUTBpKRAV1RVCAPW6GFci
 HIZjIJkjEPWLsvxWEs0dUFJQGp3jel5h8vFPkDWBYs3+9rILU2DnLWpKGNDHx3k=
 =vUfa
 -----END PGP SIGNATURE-----

Merge tag 'for-linus-4.4-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip

Pull xen updates from David Vrabel:

 - Improve balloon driver memory hotplug placement.

 - Use unpopulated hotplugged memory for foreign pages (if
   supported/enabled).

 - Support 64 KiB guest pages on arm64.

 - CPU hotplug support on arm/arm64.

* tag 'for-linus-4.4-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip: (44 commits)
  xen: fix the check of e_pfn in xen_find_pfn_range
  x86/xen: add reschedule point when mapping foreign GFNs
  xen/arm: don't try to re-register vcpu_info on cpu_hotplug.
  xen, cpu_hotplug: call device_offline instead of cpu_down
  xen/arm: Enable cpu_hotplug.c
  xenbus: Support multiple grants ring with 64KB
  xen/grant-table: Add an helper to iterate over a specific number of grants
  xen/xenbus: Rename *RING_PAGE* to *RING_GRANT*
  xen/arm: correct comment in enlighten.c
  xen/gntdev: use types from linux/types.h in userspace headers
  xen/gntalloc: use types from linux/types.h in userspace headers
  xen/balloon: Use the correct sizeof when declaring frame_list
  xen/swiotlb: Add support for 64KB page granularity
  xen/swiotlb: Pass addresses rather than frame numbers to xen_arch_need_swiotlb
  arm/xen: Add support for 64KB page granularity
  xen/privcmd: Add support for Linux 64KB page granularity
  net/xen-netback: Make it running on 64KB page granularity
  net/xen-netfront: Make it running on 64KB page granularity
  block/xen-blkback: Make it running on 64KB page granularity
  block/xen-blkfront: Make it running on 64KB page granularity
  ...

arch/arm/include/asm/xen/hypervisor.h

@@ -26,4 +26,14 @@ void __init xen_early_init(void);
 static inline void xen_early_init(void) { return; }
 #endif
 
+#ifdef CONFIG_HOTPLUG_CPU
+static inline void xen_arch_register_cpu(int num)
+{
+}
+
+static inline void xen_arch_unregister_cpu(int num)
+{
+}
+#endif
+
 #endif /* _ASM_ARM_XEN_HYPERVISOR_H */

arch/arm/include/asm/xen/page-coherent.h

@@ -35,11 +35,15 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
 	     dma_addr_t dev_addr, unsigned long offset, size_t size,
 	     enum dma_data_direction dir, struct dma_attrs *attrs)
 {
-	bool local = PFN_DOWN(dev_addr) == page_to_pfn(page);
+	bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page);
-	/* Dom0 is mapped 1:1, so if pfn == mfn the page is local otherwise
+	/*
-	 * is a foreign page grant-mapped in dom0. If the page is local we
+	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
-	 * can safely call the native dma_ops function, otherwise we call
+	 * multiple Xen page, it's not possible to have a mix of local and
-	 * the xen specific function. */
+	 * foreign Xen page. So if the first xen_pfn == mfn the page is local
+	 * otherwise it's a foreign page grant-mapped in dom0. If the page is
+	 * local we can safely call the native dma_ops function, otherwise we
+	 * call the xen specific function.
+	 */
 	if (local)
 		__generic_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
 	else
@@ -51,10 +55,14 @@ static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
 		struct dma_attrs *attrs)
 {
 	unsigned long pfn = PFN_DOWN(handle);
-	/* Dom0 is mapped 1:1, so calling pfn_valid on a foreign mfn will
+	/*
-	 * always return false. If the page is local we can safely call the
+	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
-	 * native dma_ops function, otherwise we call the xen specific
+	 * multiple Xen page, it's not possible to have a mix of local and
-	 * function. */
+	 * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
+	 * foreign mfn will always return false. If the page is local we can
+	 * safely call the native dma_ops function, otherwise we call the xen
+	 * specific function.
+	 */
 	if (pfn_valid(pfn)) {
 		if (__generic_dma_ops(hwdev)->unmap_page)
 			__generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);

arch/arm/include/asm/xen/page.h

@@ -13,9 +13,6 @@
 
 #define phys_to_machine_mapping_valid(pfn) (1)
 
-#define pte_mfn	    pte_pfn
-#define mfn_pte	    pfn_pte
-
 /* Xen machine address */
 typedef struct xmaddr {
 	phys_addr_t maddr;
@@ -31,6 +28,17 @@ typedef struct xpaddr {
 
 #define INVALID_P2M_ENTRY      (~0UL)
 
+/*
+ * The pseudo-physical frame (pfn) used in all the helpers is always based
+ * on Xen page granularity (i.e 4KB).
+ *
+ * A Linux page may be split across multiple non-contiguous Xen page so we
+ * have to keep track with frame based on 4KB page granularity.
+ *
+ * PV drivers should never make a direct usage of those helpers (particularly
+ * pfn_to_gfn and gfn_to_pfn).
+ */
+
 unsigned long __pfn_to_mfn(unsigned long pfn);
 extern struct rb_root phys_to_mach;
 
@@ -67,8 +75,8 @@ static inline unsigned long bfn_to_pfn(unsigned long bfn)
 #define bfn_to_local_pfn(bfn)	bfn_to_pfn(bfn)
 
 /* VIRT <-> GUEST conversion */
-#define virt_to_gfn(v)		(pfn_to_gfn(virt_to_pfn(v)))
+#define virt_to_gfn(v)		(pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT))
-#define gfn_to_virt(m)		(__va(gfn_to_pfn(m) << PAGE_SHIFT))
+#define gfn_to_virt(m)		(__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT))
 
 /* Only used in PV code. But ARM guests are always HVM. */
 static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr)
@@ -107,8 +115,8 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 #define xen_unmap(cookie) iounmap((cookie))
 
 bool xen_arch_need_swiotlb(struct device *dev,
-			   unsigned long pfn,
+			   phys_addr_t phys,
-			   unsigned long bfn);
+			   dma_addr_t dev_addr);
 unsigned long xen_get_swiotlb_free_pages(unsigned int order);
 
 #endif /* _ASM_ARM_XEN_PAGE_H */

arch/arm/xen/enlighten.c

@@ -86,16 +86,25 @@ static void xen_percpu_init(void)
 	int err;
 	int cpu = get_cpu();
 
+	/* 
+	 * VCPUOP_register_vcpu_info cannot be called twice for the same
+	 * vcpu, so if vcpu_info is already registered, just get out. This
+	 * can happen with cpu-hotplug.
+	 */
+	if (per_cpu(xen_vcpu, cpu) != NULL)
+		goto after_register_vcpu_info;
+
 	pr_info("Xen: initializing cpu%d\n", cpu);
 	vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
 
-	info.mfn = __pa(vcpup) >> PAGE_SHIFT;
+	info.mfn = virt_to_gfn(vcpup);
-	info.offset = offset_in_page(vcpup);
+	info.offset = xen_offset_in_page(vcpup);
 
 	err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);
 	BUG_ON(err);
 	per_cpu(xen_vcpu, cpu) = vcpup;
 
+after_register_vcpu_info:
 	enable_percpu_irq(xen_events_irq, 0);
 	put_cpu();
 }
@@ -124,6 +133,9 @@ static int xen_cpu_notification(struct notifier_block *self,
 	case CPU_STARTING:
 		xen_percpu_init();
 		break;
+	case CPU_DYING:
+		disable_percpu_irq(xen_events_irq);
+		break;
 	default:
 		break;
 	}
@@ -213,7 +225,7 @@ static int __init xen_guest_init(void)
 	xatp.domid = DOMID_SELF;
 	xatp.idx = 0;
 	xatp.space = XENMAPSPACE_shared_info;
-	xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT;
+	xatp.gpfn = virt_to_gfn(shared_info_page);
 	if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
 		BUG();
 
@@ -284,7 +296,7 @@ void xen_arch_resume(void) { }
 void xen_arch_suspend(void) { }
 
 
-/* In the hypervisor.S file. */
+/* In the hypercall.S file. */
 EXPORT_SYMBOL_GPL(HYPERVISOR_event_channel_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_grant_table_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_xen_version);

arch/arm/xen/mm.c

@@ -48,22 +48,22 @@ static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
 	size_t size, enum dma_data_direction dir, enum dma_cache_op op)
 {
 	struct gnttab_cache_flush cflush;
-	unsigned long pfn;
+	unsigned long xen_pfn;
 	size_t left = size;
 
-	pfn = (handle >> PAGE_SHIFT) + offset / PAGE_SIZE;
+	xen_pfn = (handle >> XEN_PAGE_SHIFT) + offset / XEN_PAGE_SIZE;
-	offset %= PAGE_SIZE;
+	offset %= XEN_PAGE_SIZE;
 
 	do {
 		size_t len = left;
 	
 		/* buffers in highmem or foreign pages cannot cross page
 		 * boundaries */
-		if (len + offset > PAGE_SIZE)
+		if (len + offset > XEN_PAGE_SIZE)
-			len = PAGE_SIZE - offset;
+			len = XEN_PAGE_SIZE - offset;
 
 		cflush.op = 0;
-		cflush.a.dev_bus_addr = pfn << PAGE_SHIFT;
+		cflush.a.dev_bus_addr = xen_pfn << XEN_PAGE_SHIFT;
 		cflush.offset = offset;
 		cflush.length = len;
 
@@ -79,7 +79,7 @@ static void dma_cache_maint(dma_addr_t handle, unsigned long offset,
 			HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1);
 
 		offset = 0;
-		pfn++;
+		xen_pfn++;
 		left -= len;
 	} while (left);
 }
@@ -138,10 +138,29 @@ void __xen_dma_sync_single_for_device(struct device *hwdev,
 }
 
 bool xen_arch_need_swiotlb(struct device *dev,
-			   unsigned long pfn,
+			   phys_addr_t phys,
-			   unsigned long bfn)
+			   dma_addr_t dev_addr)
 {
-	return (!hypercall_cflush && (pfn != bfn) && !is_device_dma_coherent(dev));
+	unsigned int xen_pfn = XEN_PFN_DOWN(phys);
+	unsigned int bfn = XEN_PFN_DOWN(dev_addr);
+
+	/*
+	 * The swiotlb buffer should be used if
+	 *	- Xen doesn't have the cache flush hypercall
+	 *	- The Linux page refers to foreign memory
+	 *	- The device doesn't support coherent DMA request
+	 *
+	 * The Linux page may be spanned acrros multiple Xen page, although
+	 * it's not possible to have a mix of local and foreign Xen page.
+	 * Furthermore, range_straddles_page_boundary is already checking
+	 * if buffer is physically contiguous in the host RAM.
+	 *
+	 * Therefore we only need to check the first Xen page to know if we
+	 * require a bounce buffer because the device doesn't support coherent
+	 * memory and we are not able to flush the cache.
+	 */
+	return (!hypercall_cflush && (xen_pfn != bfn) &&
+		!is_device_dma_coherent(dev));
 }
 
 int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,

arch/arm/xen/p2m.c

@@ -93,8 +93,8 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
 	for (i = 0; i < count; i++) {
 		if (map_ops[i].status)
 			continue;
-		set_phys_to_machine(map_ops[i].host_addr >> PAGE_SHIFT,
+		set_phys_to_machine(map_ops[i].host_addr >> XEN_PAGE_SHIFT,
-				    map_ops[i].dev_bus_addr >> PAGE_SHIFT);
+				    map_ops[i].dev_bus_addr >> XEN_PAGE_SHIFT);
 	}
 
 	return 0;
@@ -108,7 +108,7 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 	int i;
 
 	for (i = 0; i < count; i++) {
-		set_phys_to_machine(unmap_ops[i].host_addr >> PAGE_SHIFT,
+		set_phys_to_machine(unmap_ops[i].host_addr >> XEN_PAGE_SHIFT,
 				    INVALID_P2M_ENTRY);
 	}
 

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

@@ -57,4 +57,9 @@ static inline bool xen_x2apic_para_available(void)
 }
 #endif
 
+#ifdef CONFIG_HOTPLUG_CPU
+void xen_arch_register_cpu(int num);
+void xen_arch_unregister_cpu(int num);
+#endif
+
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */

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

@@ -12,7 +12,7 @@
 #include <asm/pgtable.h>
 
 #include <xen/interface/xen.h>
-#include <xen/grant_table.h>
+#include <xen/interface/grant_table.h>
 #include <xen/features.h>
 
 /* Xen machine address */
@@ -43,6 +43,8 @@ extern unsigned long *xen_p2m_addr;
 extern unsigned long  xen_p2m_size;
 extern unsigned long  xen_max_p2m_pfn;
 
+extern int xen_alloc_p2m_entry(unsigned long pfn);
+
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
@@ -296,8 +298,8 @@ void make_lowmem_page_readwrite(void *vaddr);
 #define xen_unmap(cookie) iounmap((cookie))
 
 static inline bool xen_arch_need_swiotlb(struct device *dev,
-					 unsigned long pfn,
+					 phys_addr_t phys,
-					 unsigned long bfn)
+					 dma_addr_t dev_addr)
 {
 	return false;
 }

arch/x86/xen/enlighten.c

@@ -75,6 +75,7 @@
 #include <asm/mwait.h>
 #include <asm/pci_x86.h>
 #include <asm/pat.h>
+#include <asm/cpu.h>
 
 #ifdef CONFIG_ACPI
 #include <linux/acpi.h>
@@ -1899,3 +1900,17 @@ const struct hypervisor_x86 x86_hyper_xen = {
 	.set_cpu_features       = xen_set_cpu_features,
 };
 EXPORT_SYMBOL(x86_hyper_xen);
+
+#ifdef CONFIG_HOTPLUG_CPU
+void xen_arch_register_cpu(int num)
+{
+	arch_register_cpu(num);
+}
+EXPORT_SYMBOL(xen_arch_register_cpu);
+
+void xen_arch_unregister_cpu(int num)
+{
+	arch_unregister_cpu(num);
+}
+EXPORT_SYMBOL(xen_arch_unregister_cpu);
+#endif

arch/x86/xen/grant-table.c

@@ -133,7 +133,7 @@ static int __init xlated_setup_gnttab_pages(void)
 		kfree(pages);
 		return -ENOMEM;
 	}
-	rc = alloc_xenballooned_pages(nr_grant_frames, pages, 0 /* lowmem */);
+	rc = alloc_xenballooned_pages(nr_grant_frames, pages);
 	if (rc) {
 		pr_warn("%s Couldn't balloon alloc %ld pfns rc:%d\n", __func__,
 			nr_grant_frames, rc);

arch/x86/xen/mmu.c

@@ -2888,6 +2888,7 @@ static int do_remap_gfn(struct vm_area_struct *vma,
 		addr += range;
 		if (err_ptr)
 			err_ptr += batch;
+		cond_resched();
 	}
 out:
 

arch/x86/xen/p2m.c

@@ -530,7 +530,7 @@ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg)
  * the new pages are installed with cmpxchg; if we lose the race then
  * simply free the page we allocated and use the one that's there.
  */
-static bool alloc_p2m(unsigned long pfn)
+int xen_alloc_p2m_entry(unsigned long pfn)
 {
 	unsigned topidx;
 	unsigned long *top_mfn_p, *mid_mfn;
@@ -540,6 +540,9 @@ static bool alloc_p2m(unsigned long pfn)
 	unsigned long addr = (unsigned long)(xen_p2m_addr + pfn);
 	unsigned long p2m_pfn;
 
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return 0;
+
 	ptep = lookup_address(addr, &level);
 	BUG_ON(!ptep || level != PG_LEVEL_4K);
 	pte_pg = (pte_t *)((unsigned long)ptep & ~(PAGE_SIZE - 1));
@@ -548,7 +551,7 @@ static bool alloc_p2m(unsigned long pfn)
 		/* PMD level is missing, allocate a new one */
 		ptep = alloc_p2m_pmd(addr, pte_pg);
 		if (!ptep)
-			return false;
+			return -ENOMEM;
 	}
 
 	if (p2m_top_mfn && pfn < MAX_P2M_PFN) {
@@ -566,7 +569,7 @@ static bool alloc_p2m(unsigned long pfn)
 
 			mid_mfn = alloc_p2m_page();
 			if (!mid_mfn)
-				return false;
+				return -ENOMEM;
 
 			p2m_mid_mfn_init(mid_mfn, p2m_missing);
 
@@ -592,7 +595,7 @@ static bool alloc_p2m(unsigned long pfn)
 
 		p2m = alloc_p2m_page();
 		if (!p2m)
-			return false;
+			return -ENOMEM;
 
 		if (p2m_pfn == PFN_DOWN(__pa(p2m_missing)))
 			p2m_init(p2m);
@@ -625,8 +628,9 @@ static bool alloc_p2m(unsigned long pfn)
 		HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn;
 	}
 
-	return true;
+	return 0;
 }
+EXPORT_SYMBOL(xen_alloc_p2m_entry);
 
 unsigned long __init set_phys_range_identity(unsigned long pfn_s,
 				      unsigned long pfn_e)
@@ -688,7 +692,10 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
 {
 	if (unlikely(!__set_phys_to_machine(pfn, mfn))) {
-		if (!alloc_p2m(pfn))
+		int ret;
+
+		ret = xen_alloc_p2m_entry(pfn);
+		if (ret < 0)
 			return false;
 
 		return __set_phys_to_machine(pfn, mfn);

arch/x86/xen/setup.c

@@ -212,7 +212,7 @@ static unsigned long __init xen_find_pfn_range(unsigned long *min_pfn)
 		e_pfn = PFN_DOWN(entry->addr + entry->size);
 
 		/* We only care about E820 after this */
-		if (e_pfn < *min_pfn)
+		if (e_pfn <= *min_pfn)
 			continue;
 
 		s_pfn = PFN_UP(entry->addr);
@@ -829,6 +829,8 @@ char * __init xen_memory_setup(void)
 	addr = xen_e820_map[0].addr;
 	size = xen_e820_map[0].size;
 	while (i < xen_e820_map_entries) {
+		bool discard = false;
+
 		chunk_size = size;
 		type = xen_e820_map[i].type;
 
@@ -843,10 +845,11 @@ char * __init xen_memory_setup(void)
 				xen_add_extra_mem(pfn_s, n_pfns);
 				xen_max_p2m_pfn = pfn_s + n_pfns;
 			} else
-				type = E820_UNUSABLE;
+				discard = true;
 		}
 
-		xen_align_and_add_e820_region(addr, chunk_size, type);
+		if (!discard)
+			xen_align_and_add_e820_region(addr, chunk_size, type);
 
 		addr += chunk_size;
 		size -= chunk_size;

drivers/block/xen-blkback/blkback.c

@@ -87,7 +87,7 @@ MODULE_PARM_DESC(max_persistent_grants,
  * Maximum order of pages to be used for the shared ring between front and
  * backend, 4KB page granularity is used.
  */
-unsigned int xen_blkif_max_ring_order = XENBUS_MAX_RING_PAGE_ORDER;
+unsigned int xen_blkif_max_ring_order = XENBUS_MAX_RING_GRANT_ORDER;
 module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO);
 MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
 /*
@@ -961,7 +961,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req,
 		seg[n].nsec = segments[i].last_sect -
 			segments[i].first_sect + 1;
 		seg[n].offset = (segments[i].first_sect << 9);
-		if ((segments[i].last_sect >= (PAGE_SIZE >> 9)) ||
+		if ((segments[i].last_sect >= (XEN_PAGE_SIZE >> 9)) ||
 		    (segments[i].last_sect < segments[i].first_sect)) {
 			rc = -EINVAL;
 			goto unmap;
@@ -1210,6 +1210,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 
 	req_operation = req->operation == BLKIF_OP_INDIRECT ?
 			req->u.indirect.indirect_op : req->operation;
+
 	if ((req->operation == BLKIF_OP_INDIRECT) &&
 	    (req_operation != BLKIF_OP_READ) &&
 	    (req_operation != BLKIF_OP_WRITE)) {
@@ -1268,7 +1269,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
 			seg[i].nsec = req->u.rw.seg[i].last_sect -
 				req->u.rw.seg[i].first_sect + 1;
 			seg[i].offset = (req->u.rw.seg[i].first_sect << 9);
-			if ((req->u.rw.seg[i].last_sect >= (PAGE_SIZE >> 9)) ||
+			if ((req->u.rw.seg[i].last_sect >= (XEN_PAGE_SIZE >> 9)) ||
 			    (req->u.rw.seg[i].last_sect <
 			     req->u.rw.seg[i].first_sect))
 				goto fail_response;
@@ -1445,10 +1446,10 @@ static int __init xen_blkif_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
-	if (xen_blkif_max_ring_order > XENBUS_MAX_RING_PAGE_ORDER) {
+	if (xen_blkif_max_ring_order > XENBUS_MAX_RING_GRANT_ORDER) {
 		pr_info("Invalid max_ring_order (%d), will use default max: %d.\n",
-			xen_blkif_max_ring_order, XENBUS_MAX_RING_PAGE_ORDER);
+			xen_blkif_max_ring_order, XENBUS_MAX_RING_GRANT_ORDER);
-		xen_blkif_max_ring_order = XENBUS_MAX_RING_PAGE_ORDER;
+		xen_blkif_max_ring_order = XENBUS_MAX_RING_GRANT_ORDER;
 	}
 
 	rc = xen_blkif_interface_init();

drivers/block/xen-blkback/common.h

@@ -39,6 +39,7 @@
 #include <asm/pgalloc.h>
 #include <asm/hypervisor.h>
 #include <xen/grant_table.h>
+#include <xen/page.h>
 #include <xen/xenbus.h>
 #include <xen/interface/io/ring.h>
 #include <xen/interface/io/blkif.h>
@@ -51,12 +52,20 @@ extern unsigned int xen_blkif_max_ring_order;
  */
 #define MAX_INDIRECT_SEGMENTS 256
 
-#define SEGS_PER_INDIRECT_FRAME \
+/*
-	(PAGE_SIZE/sizeof(struct blkif_request_segment))
+ * Xen use 4K pages. The guest may use different page size (4K or 64K)
+ * Number of Xen pages per segment
+ */
+#define XEN_PAGES_PER_SEGMENT   (PAGE_SIZE / XEN_PAGE_SIZE)
+
+#define XEN_PAGES_PER_INDIRECT_FRAME \
+	(XEN_PAGE_SIZE/sizeof(struct blkif_request_segment))
+#define SEGS_PER_INDIRECT_FRAME	\
+	(XEN_PAGES_PER_INDIRECT_FRAME / XEN_PAGES_PER_SEGMENT)
+
 #define MAX_INDIRECT_PAGES \
 	((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
-#define INDIRECT_PAGES(_segs) \
+#define INDIRECT_PAGES(_segs) DIV_ROUND_UP(_segs, XEN_PAGES_PER_INDIRECT_FRAME)
-	((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
 
 /* Not a real protocol.  Used to generate ring structs which contain
  * the elements common to all protocols only.  This way we get a

drivers/block/xen-blkback/xenbus.c

@@ -176,21 +176,24 @@ static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t *gref,
 	{
 		struct blkif_sring *sring;
 		sring = (struct blkif_sring *)blkif->blk_ring;
-		BACK_RING_INIT(&blkif->blk_rings.native, sring, PAGE_SIZE * nr_grefs);
+		BACK_RING_INIT(&blkif->blk_rings.native, sring,
+			       XEN_PAGE_SIZE * nr_grefs);
 		break;
 	}
 	case BLKIF_PROTOCOL_X86_32:
 	{
 		struct blkif_x86_32_sring *sring_x86_32;
 		sring_x86_32 = (struct blkif_x86_32_sring *)blkif->blk_ring;
-		BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32, PAGE_SIZE * nr_grefs);
+		BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32,
+			       XEN_PAGE_SIZE * nr_grefs);
 		break;
 	}
 	case BLKIF_PROTOCOL_X86_64:
 	{
 		struct blkif_x86_64_sring *sring_x86_64;
 		sring_x86_64 = (struct blkif_x86_64_sring *)blkif->blk_ring;
-		BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64, PAGE_SIZE * nr_grefs);
+		BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64,
+			       XEN_PAGE_SIZE * nr_grefs);
 		break;
 	}
 	default:
@@ -826,7 +829,7 @@ again:
 static int connect_ring(struct backend_info *be)
 {
 	struct xenbus_device *dev = be->dev;
-	unsigned int ring_ref[XENBUS_MAX_RING_PAGES];
+	unsigned int ring_ref[XENBUS_MAX_RING_GRANTS];
 	unsigned int evtchn, nr_grefs, ring_page_order;
 	unsigned int pers_grants;
 	char protocol[64] = "";

drivers/block/xen-blkfront.c

@@ -68,7 +68,7 @@ enum blkif_state {
 
 struct grant {
 	grant_ref_t gref;
-	unsigned long pfn;
+	struct page *page;
 	struct list_head node;
 };
 
@@ -78,6 +78,7 @@ struct blk_shadow {
 	struct grant **grants_used;
 	struct grant **indirect_grants;
 	struct scatterlist *sg;
+	unsigned int num_sg;
 };
 
 struct split_bio {
@@ -106,8 +107,12 @@ static unsigned int xen_blkif_max_ring_order;
 module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO);
 MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
 
-#define BLK_RING_SIZE(info) __CONST_RING_SIZE(blkif, PAGE_SIZE * (info)->nr_ring_pages)
+#define BLK_RING_SIZE(info)	\
-#define BLK_MAX_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE * XENBUS_MAX_RING_PAGES)
+	__CONST_RING_SIZE(blkif, XEN_PAGE_SIZE * (info)->nr_ring_pages)
+
+#define BLK_MAX_RING_SIZE	\
+	__CONST_RING_SIZE(blkif, XEN_PAGE_SIZE * XENBUS_MAX_RING_GRANTS)
+
 /*
  * ring-ref%i i=(-1UL) would take 11 characters + 'ring-ref' is 8, so 19
  * characters are enough. Define to 20 to keep consist with backend.
@@ -128,7 +133,7 @@ struct blkfront_info
 	int vdevice;
 	blkif_vdev_t handle;
 	enum blkif_state connected;
-	int ring_ref[XENBUS_MAX_RING_PAGES];
+	int ring_ref[XENBUS_MAX_RING_GRANTS];
 	unsigned int nr_ring_pages;
 	struct blkif_front_ring ring;
 	unsigned int evtchn, irq;
@@ -146,6 +151,7 @@ struct blkfront_info
 	unsigned int discard_granularity;
 	unsigned int discard_alignment;
 	unsigned int feature_persistent:1;
+	/* Number of 4KB segments handled */
 	unsigned int max_indirect_segments;
 	int is_ready;
 	struct blk_mq_tag_set tag_set;
@@ -174,10 +180,23 @@ static DEFINE_SPINLOCK(minor_lock);
 
 #define DEV_NAME	"xvd"	/* name in /dev */
 
-#define SEGS_PER_INDIRECT_FRAME \
+/*
-	(PAGE_SIZE/sizeof(struct blkif_request_segment))
+ * Grants are always the same size as a Xen page (i.e 4KB).
-#define INDIRECT_GREFS(_segs) \
+ * A physical segment is always the same size as a Linux page.
-	((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
+ * Number of grants per physical segment
+ */
+#define GRANTS_PER_PSEG	(PAGE_SIZE / XEN_PAGE_SIZE)
+
+#define GRANTS_PER_INDIRECT_FRAME \
+	(XEN_PAGE_SIZE / sizeof(struct blkif_request_segment))
+
+#define PSEGS_PER_INDIRECT_FRAME	\
+	(GRANTS_INDIRECT_FRAME / GRANTS_PSEGS)
+
+#define INDIRECT_GREFS(_grants)		\
+	DIV_ROUND_UP(_grants, GRANTS_PER_INDIRECT_FRAME)
+
+#define GREFS(_psegs)	((_psegs) * GRANTS_PER_PSEG)
 
 static int blkfront_setup_indirect(struct blkfront_info *info);
 static int blkfront_gather_backend_features(struct blkfront_info *info);
@@ -221,7 +240,7 @@ static int fill_grant_buffer(struct blkfront_info *info, int num)
 				kfree(gnt_list_entry);
 				goto out_of_memory;
 			}
-			gnt_list_entry->pfn = page_to_pfn(granted_page);
+			gnt_list_entry->page = granted_page;
 		}
 
 		gnt_list_entry->gref = GRANT_INVALID_REF;
@@ -236,7 +255,7 @@ out_of_memory:
 	                         &info->grants, node) {
 		list_del(&gnt_list_entry->node);
 		if (info->feature_persistent)
-			__free_page(pfn_to_page(gnt_list_entry->pfn));
+			__free_page(gnt_list_entry->page);
 		kfree(gnt_list_entry);
 		i--;
 	}
@@ -244,34 +263,77 @@ out_of_memory:
 	return -ENOMEM;
 }
 
-static struct grant *get_grant(grant_ref_t *gref_head,
+static struct grant *get_free_grant(struct blkfront_info *info)
-                               unsigned long pfn,
-                               struct blkfront_info *info)
 {
 	struct grant *gnt_list_entry;
-	unsigned long buffer_gfn;
 
 	BUG_ON(list_empty(&info->grants));
 	gnt_list_entry = list_first_entry(&info->grants, struct grant,
-	                                  node);
+					  node);
 	list_del(&gnt_list_entry->node);
 
-	if (gnt_list_entry->gref != GRANT_INVALID_REF) {
+	if (gnt_list_entry->gref != GRANT_INVALID_REF)
 		info->persistent_gnts_c--;
+
+	return gnt_list_entry;
+}
+
+static inline void grant_foreign_access(const struct grant *gnt_list_entry,
+					const struct blkfront_info *info)
+{
+	gnttab_page_grant_foreign_access_ref_one(gnt_list_entry->gref,
+						 info->xbdev->otherend_id,
+						 gnt_list_entry->page,
+						 0);
+}
+
+static struct grant *get_grant(grant_ref_t *gref_head,
+			       unsigned long gfn,
+			       struct blkfront_info *info)
+{
+	struct grant *gnt_list_entry = get_free_grant(info);
+
+	if (gnt_list_entry->gref != GRANT_INVALID_REF)
 		return gnt_list_entry;
+
+	/* Assign a gref to this page */
+	gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
+	BUG_ON(gnt_list_entry->gref == -ENOSPC);
+	if (info->feature_persistent)
+		grant_foreign_access(gnt_list_entry, info);
+	else {
+		/* Grant access to the GFN passed by the caller */
+		gnttab_grant_foreign_access_ref(gnt_list_entry->gref,
+						info->xbdev->otherend_id,
+						gfn, 0);
 	}
 
+	return gnt_list_entry;
+}
+
+static struct grant *get_indirect_grant(grant_ref_t *gref_head,
+					struct blkfront_info *info)
+{
+	struct grant *gnt_list_entry = get_free_grant(info);
+
+	if (gnt_list_entry->gref != GRANT_INVALID_REF)
+		return gnt_list_entry;
+
 	/* Assign a gref to this page */
 	gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
 	BUG_ON(gnt_list_entry->gref == -ENOSPC);
 	if (!info->feature_persistent) {
-		BUG_ON(!pfn);
+		struct page *indirect_page;
-		gnt_list_entry->pfn = pfn;
+
+		/* Fetch a pre-allocated page to use for indirect grefs */
+		BUG_ON(list_empty(&info->indirect_pages));
+		indirect_page = list_first_entry(&info->indirect_pages,
+						 struct page, lru);
+		list_del(&indirect_page->lru);
+		gnt_list_entry->page = indirect_page;
 	}
-	buffer_gfn = pfn_to_gfn(gnt_list_entry->pfn);
+	grant_foreign_access(gnt_list_entry, info);
-	gnttab_grant_foreign_access_ref(gnt_list_entry->gref,
+
-	                                info->xbdev->otherend_id,
-	                                buffer_gfn, 0);
 	return gnt_list_entry;
 }
 
@@ -394,20 +456,128 @@ static int blkif_ioctl(struct block_device *bdev, fmode_t mode,
 	return 0;
 }
 
-/*
+static int blkif_queue_discard_req(struct request *req)
- * Generate a Xen blkfront IO request from a blk layer request.  Reads
- * and writes are handled as expected.
- *
- * @req: a request struct
- */
-static int blkif_queue_request(struct request *req)
 {
 	struct blkfront_info *info = req->rq_disk->private_data;
 	struct blkif_request *ring_req;
 	unsigned long id;
+
+	/* Fill out a communications ring structure. */
+	ring_req = RING_GET_REQUEST(&info->ring, info->ring.req_prod_pvt);
+	id = get_id_from_freelist(info);
+	info->shadow[id].request = req;
+
+	ring_req->operation = BLKIF_OP_DISCARD;
+	ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
+	ring_req->u.discard.id = id;
+	ring_req->u.discard.sector_number = (blkif_sector_t)blk_rq_pos(req);
+	if ((req->cmd_flags & REQ_SECURE) && info->feature_secdiscard)
+		ring_req->u.discard.flag = BLKIF_DISCARD_SECURE;
+	else
+		ring_req->u.discard.flag = 0;
+
+	info->ring.req_prod_pvt++;
+
+	/* Keep a private copy so we can reissue requests when recovering. */
+	info->shadow[id].req = *ring_req;
+
+	return 0;
+}
+
+struct setup_rw_req {
+	unsigned int grant_idx;
+	struct blkif_request_segment *segments;
+	struct blkfront_info *info;
+	struct blkif_request *ring_req;
+	grant_ref_t gref_head;
+	unsigned int id;
+	/* Only used when persistent grant is used and it's a read request */
+	bool need_copy;
+	unsigned int bvec_off;
+	char *bvec_data;
+};
+
+static void blkif_setup_rw_req_grant(unsigned long gfn, unsigned int offset,
+				     unsigned int len, void *data)
+{
+	struct setup_rw_req *setup = data;
+	int n, ref;
+	struct grant *gnt_list_entry;
 	unsigned int fsect, lsect;
-	int i, ref, n;
+	/* Convenient aliases */
-	struct blkif_request_segment *segments = NULL;
+	unsigned int grant_idx = setup->grant_idx;
+	struct blkif_request *ring_req = setup->ring_req;
+	struct blkfront_info *info = setup->info;
+	struct blk_shadow *shadow = &info->shadow[setup->id];
+
+	if ((ring_req->operation == BLKIF_OP_INDIRECT) &&
+	    (grant_idx % GRANTS_PER_INDIRECT_FRAME == 0)) {
+		if (setup->segments)
+			kunmap_atomic(setup->segments);
+
+		n = grant_idx / GRANTS_PER_INDIRECT_FRAME;
+		gnt_list_entry = get_indirect_grant(&setup->gref_head, info);
+		shadow->indirect_grants[n] = gnt_list_entry;
+		setup->segments = kmap_atomic(gnt_list_entry->page);
+		ring_req->u.indirect.indirect_grefs[n] = gnt_list_entry->gref;
+	}
+
+	gnt_list_entry = get_grant(&setup->gref_head, gfn, info);
+	ref = gnt_list_entry->gref;
+	shadow->grants_used[grant_idx] = gnt_list_entry;
+
+	if (setup->need_copy) {
+		void *shared_data;
+
+		shared_data = kmap_atomic(gnt_list_entry->page);
+		/*
+		 * this does not wipe data stored outside the
+		 * range sg->offset..sg->offset+sg->length.
+		 * Therefore, blkback *could* see data from
+		 * previous requests. This is OK as long as
+		 * persistent grants are shared with just one
+		 * domain. It may need refactoring if this
+		 * changes
+		 */
+		memcpy(shared_data + offset,
+		       setup->bvec_data + setup->bvec_off,
+		       len);
+
+		kunmap_atomic(shared_data);
+		setup->bvec_off += len;
+	}
+
+	fsect = offset >> 9;
+	lsect = fsect + (len >> 9) - 1;
+	if (ring_req->operation != BLKIF_OP_INDIRECT) {
+		ring_req->u.rw.seg[grant_idx] =
+			(struct blkif_request_segment) {
+				.gref       = ref,
+				.first_sect = fsect,
+				.last_sect  = lsect };
+	} else {
+		setup->segments[grant_idx % GRANTS_PER_INDIRECT_FRAME] =
+			(struct blkif_request_segment) {
+				.gref       = ref,
+				.first_sect = fsect,
+				.last_sect  = lsect };
+	}
+
+	(setup->grant_idx)++;
+}
+
+static int blkif_queue_rw_req(struct request *req)
+{
+	struct blkfront_info *info = req->rq_disk->private_data;
+	struct blkif_request *ring_req;
+	unsigned long id;
+	int i;
+	struct setup_rw_req setup = {
+		.grant_idx = 0,
+		.segments = NULL,
+		.info = info,
+		.need_copy = rq_data_dir(req) && info->feature_persistent,
+	};
 
 	/*
 	 * Used to store if we are able to queue the request by just using
@@ -415,28 +585,23 @@ static int blkif_queue_request(struct request *req)
 	 * as there are not sufficiently many free.
 	 */
 	bool new_persistent_gnts;
-	grant_ref_t gref_head;
-	struct grant *gnt_list_entry = NULL;
 	struct scatterlist *sg;
-	int nseg, max_grefs;
+	int num_sg, max_grefs, num_grant;
 
-	if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
+	max_grefs = req->nr_phys_segments * GRANTS_PER_PSEG;
-		return 1;
-
-	max_grefs = req->nr_phys_segments;
 	if (max_grefs > BLKIF_MAX_SEGMENTS_PER_REQUEST)
 		/*
 		 * If we are using indirect segments we need to account
 		 * for the indirect grefs used in the request.
 		 */
-		max_grefs += INDIRECT_GREFS(req->nr_phys_segments);
+		max_grefs += INDIRECT_GREFS(max_grefs);
 
 	/* Check if we have enough grants to allocate a requests */
 	if (info->persistent_gnts_c < max_grefs) {
 		new_persistent_gnts = 1;
 		if (gnttab_alloc_grant_references(
 		    max_grefs - info->persistent_gnts_c,
-		    &gref_head) < 0) {
+		    &setup.gref_head) < 0) {
 			gnttab_request_free_callback(
 				&info->callback,
 				blkif_restart_queue_callback,
@@ -452,151 +617,112 @@ static int blkif_queue_request(struct request *req)
 	id = get_id_from_freelist(info);
 	info->shadow[id].request = req;
 
-	if (unlikely(req->cmd_flags & (REQ_DISCARD | REQ_SECURE))) {
+	BUG_ON(info->max_indirect_segments == 0 &&
-		ring_req->operation = BLKIF_OP_DISCARD;
+	       GREFS(req->nr_phys_segments) > BLKIF_MAX_SEGMENTS_PER_REQUEST);
-		ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
+	BUG_ON(info->max_indirect_segments &&
-		ring_req->u.discard.id = id;
+	       GREFS(req->nr_phys_segments) > info->max_indirect_segments);
-		ring_req->u.discard.sector_number = (blkif_sector_t)blk_rq_pos(req);
+
-		if ((req->cmd_flags & REQ_SECURE) && info->feature_secdiscard)
+	num_sg = blk_rq_map_sg(req->q, req, info->shadow[id].sg);
-			ring_req->u.discard.flag = BLKIF_DISCARD_SECURE;
+	num_grant = 0;
-		else
+	/* Calculate the number of grant used */
-			ring_req->u.discard.flag = 0;
+	for_each_sg(info->shadow[id].sg, sg, num_sg, i)
+	       num_grant += gnttab_count_grant(sg->offset, sg->length);
+
+	ring_req->u.rw.id = id;
+	info->shadow[id].num_sg = num_sg;
+	if (num_grant > BLKIF_MAX_SEGMENTS_PER_REQUEST) {
+		/*
+		 * The indirect operation can only be a BLKIF_OP_READ or
+		 * BLKIF_OP_WRITE
+		 */
+		BUG_ON(req->cmd_flags & (REQ_FLUSH | REQ_FUA));
+		ring_req->operation = BLKIF_OP_INDIRECT;
+		ring_req->u.indirect.indirect_op = rq_data_dir(req) ?
+			BLKIF_OP_WRITE : BLKIF_OP_READ;
+		ring_req->u.indirect.sector_number = (blkif_sector_t)blk_rq_pos(req);
+		ring_req->u.indirect.handle = info->handle;
+		ring_req->u.indirect.nr_segments = num_grant;
 	} else {
-		BUG_ON(info->max_indirect_segments == 0 &&
+		ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
-		       req->nr_phys_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);
+		ring_req->u.rw.handle = info->handle;
-		BUG_ON(info->max_indirect_segments &&
+		ring_req->operation = rq_data_dir(req) ?
-		       req->nr_phys_segments > info->max_indirect_segments);
+			BLKIF_OP_WRITE : BLKIF_OP_READ;
-		nseg = blk_rq_map_sg(req->q, req, info->shadow[id].sg);
+		if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
-		ring_req->u.rw.id = id;
-		if (nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST) {
 			/*
-			 * The indirect operation can only be a BLKIF_OP_READ or
+			 * Ideally we can do an unordered flush-to-disk.
-			 * BLKIF_OP_WRITE
+			 * In case the backend onlysupports barriers, use that.
+			 * A barrier request a superset of FUA, so we can
+			 * implement it the same way.  (It's also a FLUSH+FUA,
+			 * since it is guaranteed ordered WRT previous writes.)
 			 */
-			BUG_ON(req->cmd_flags & (REQ_FLUSH | REQ_FUA));
+			switch (info->feature_flush &
-			ring_req->operation = BLKIF_OP_INDIRECT;
+				((REQ_FLUSH|REQ_FUA))) {
-			ring_req->u.indirect.indirect_op = rq_data_dir(req) ?
+			case REQ_FLUSH|REQ_FUA:
-				BLKIF_OP_WRITE : BLKIF_OP_READ;
+				ring_req->operation =
-			ring_req->u.indirect.sector_number = (blkif_sector_t)blk_rq_pos(req);
+					BLKIF_OP_WRITE_BARRIER;
-			ring_req->u.indirect.handle = info->handle;
+				break;
-			ring_req->u.indirect.nr_segments = nseg;
+			case REQ_FLUSH:
-		} else {
+				ring_req->operation =
-			ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
+					BLKIF_OP_FLUSH_DISKCACHE;
-			ring_req->u.rw.handle = info->handle;
+				break;
-			ring_req->operation = rq_data_dir(req) ?
+			default:
-				BLKIF_OP_WRITE : BLKIF_OP_READ;
+				ring_req->operation = 0;
-			if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
-				/*
-				 * Ideally we can do an unordered flush-to-disk. In case the
-				 * backend onlysupports barriers, use that. A barrier request
-				 * a superset of FUA, so we can implement it the same
-				 * way.  (It's also a FLUSH+FUA, since it is
-				 * guaranteed ordered WRT previous writes.)
-				 */
-				switch (info->feature_flush &
-					((REQ_FLUSH|REQ_FUA))) {
-				case REQ_FLUSH|REQ_FUA:
-					ring_req->operation =
-						BLKIF_OP_WRITE_BARRIER;
-					break;
-				case REQ_FLUSH:
-					ring_req->operation =
-						BLKIF_OP_FLUSH_DISKCACHE;
-					break;
-				default:
-					ring_req->operation = 0;
-				}
-			}
-			ring_req->u.rw.nr_segments = nseg;
-		}
-		for_each_sg(info->shadow[id].sg, sg, nseg, i) {
-			fsect = sg->offset >> 9;
-			lsect = fsect + (sg->length >> 9) - 1;
-
-			if ((ring_req->operation == BLKIF_OP_INDIRECT) &&
-			    (i % SEGS_PER_INDIRECT_FRAME == 0)) {
-				unsigned long uninitialized_var(pfn);
-
-				if (segments)
-					kunmap_atomic(segments);
-
-				n = i / SEGS_PER_INDIRECT_FRAME;
-				if (!info->feature_persistent) {
-					struct page *indirect_page;
-
-					/* Fetch a pre-allocated page to use for indirect grefs */
-					BUG_ON(list_empty(&info->indirect_pages));
-					indirect_page = list_first_entry(&info->indirect_pages,
-					                                 struct page, lru);
-					list_del(&indirect_page->lru);
-					pfn = page_to_pfn(indirect_page);
-				}
-				gnt_list_entry = get_grant(&gref_head, pfn, info);
-				info->shadow[id].indirect_grants[n] = gnt_list_entry;
-				segments = kmap_atomic(pfn_to_page(gnt_list_entry->pfn));
-				ring_req->u.indirect.indirect_grefs[n] = gnt_list_entry->gref;
-			}
-
-			gnt_list_entry = get_grant(&gref_head, page_to_pfn(sg_page(sg)), info);
-			ref = gnt_list_entry->gref;
-
-			info->shadow[id].grants_used[i] = gnt_list_entry;
-
-			if (rq_data_dir(req) && info->feature_persistent) {
-				char *bvec_data;
-				void *shared_data;
-
-				BUG_ON(sg->offset + sg->length > PAGE_SIZE);
-
-				shared_data = kmap_atomic(pfn_to_page(gnt_list_entry->pfn));
-				bvec_data = kmap_atomic(sg_page(sg));
-
-				/*
-				 * this does not wipe data stored outside the
-				 * range sg->offset..sg->offset+sg->length.
-				 * Therefore, blkback *could* see data from
-				 * previous requests. This is OK as long as
-				 * persistent grants are shared with just one
-				 * domain. It may need refactoring if this
-				 * changes
-				 */
-				memcpy(shared_data + sg->offset,
-				       bvec_data   + sg->offset,
-				       sg->length);
-
-				kunmap_atomic(bvec_data);
-				kunmap_atomic(shared_data);
-			}
-			if (ring_req->operation != BLKIF_OP_INDIRECT) {
-				ring_req->u.rw.seg[i] =
-						(struct blkif_request_segment) {
-							.gref       = ref,
-							.first_sect = fsect,
-							.last_sect  = lsect };
-			} else {
-				n = i % SEGS_PER_INDIRECT_FRAME;
-				segments[n] =
-					(struct blkif_request_segment) {
-							.gref       = ref,
-							.first_sect = fsect,
-							.last_sect  = lsect };
 			}
 		}
-		if (segments)
+		ring_req->u.rw.nr_segments = num_grant;
-			kunmap_atomic(segments);
 	}
 
+	setup.ring_req = ring_req;
+	setup.id = id;
+	for_each_sg(info->shadow[id].sg, sg, num_sg, i) {
+		BUG_ON(sg->offset + sg->length > PAGE_SIZE);
+
+		if (setup.need_copy) {
+			setup.bvec_off = sg->offset;
+			setup.bvec_data = kmap_atomic(sg_page(sg));
+		}
+
+		gnttab_foreach_grant_in_range(sg_page(sg),
+					      sg->offset,
+					      sg->length,
+					      blkif_setup_rw_req_grant,
+					      &setup);
+
+		if (setup.need_copy)
+			kunmap_atomic(setup.bvec_data);
+	}
+	if (setup.segments)
+		kunmap_atomic(setup.segments);
+
 	info->ring.req_prod_pvt++;
 
 	/* Keep a private copy so we can reissue requests when recovering. */
 	info->shadow[id].req = *ring_req;
 
 	if (new_persistent_gnts)
-		gnttab_free_grant_references(gref_head);
+		gnttab_free_grant_references(setup.gref_head);
 
 	return 0;
 }
 
+/*
+ * Generate a Xen blkfront IO request from a blk layer request.  Reads
+ * and writes are handled as expected.
+ *
+ * @req: a request struct
+ */
+static int blkif_queue_request(struct request *req)
+{
+	struct blkfront_info *info = req->rq_disk->private_data;
+
+	if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
+		return 1;
+
+	if (unlikely(req->cmd_flags & (REQ_DISCARD | REQ_SECURE)))
+		return blkif_queue_discard_req(req);
+	else
+		return blkif_queue_rw_req(req);
+}
 
 static inline void flush_requests(struct blkfront_info *info)
 {
@@ -691,14 +817,14 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 	/* Hard sector size and max sectors impersonate the equiv. hardware. */
 	blk_queue_logical_block_size(rq, sector_size);
 	blk_queue_physical_block_size(rq, physical_sector_size);
-	blk_queue_max_hw_sectors(rq, (segments * PAGE_SIZE) / 512);
+	blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
 
 	/* Each segment in a request is up to an aligned page in size. */
 	blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
 	blk_queue_max_segment_size(rq, PAGE_SIZE);
 
 	/* Ensure a merged request will fit in a single I/O ring slot. */
-	blk_queue_max_segments(rq, segments);
+	blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
 
 	/* Make sure buffer addresses are sector-aligned. */
 	blk_queue_dma_alignment(rq, 511);
@@ -972,7 +1098,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 				info->persistent_gnts_c--;
 			}
 			if (info->feature_persistent)
-				__free_page(pfn_to_page(persistent_gnt->pfn));
+				__free_page(persistent_gnt->page);
 			kfree(persistent_gnt);
 		}
 	}
@@ -1007,7 +1133,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 			persistent_gnt = info->shadow[i].grants_used[j];
 			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
 			if (info->feature_persistent)
-				__free_page(pfn_to_page(persistent_gnt->pfn));
+				__free_page(persistent_gnt->page);
 			kfree(persistent_gnt);
 		}
 
@@ -1021,7 +1147,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
 		for (j = 0; j < INDIRECT_GREFS(segs); j++) {
 			persistent_gnt = info->shadow[i].indirect_grants[j];
 			gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
-			__free_page(pfn_to_page(persistent_gnt->pfn));
+			__free_page(persistent_gnt->page);
 			kfree(persistent_gnt);
 		}
 
@@ -1057,33 +1183,65 @@ free_shadow:
 
 }
 
+struct copy_from_grant {
+	const struct blk_shadow *s;
+	unsigned int grant_idx;
+	unsigned int bvec_offset;
+	char *bvec_data;
+};
+
+static void blkif_copy_from_grant(unsigned long gfn, unsigned int offset,
+				  unsigned int len, void *data)
+{
+	struct copy_from_grant *info = data;
+	char *shared_data;
+	/* Convenient aliases */
+	const struct blk_shadow *s = info->s;
+
+	shared_data = kmap_atomic(s->grants_used[info->grant_idx]->page);
+
+	memcpy(info->bvec_data + info->bvec_offset,
+	       shared_data + offset, len);
+
+	info->bvec_offset += len;
+	info->grant_idx++;
+
+	kunmap_atomic(shared_data);
+}
+
 static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 			     struct blkif_response *bret)
 {
 	int i = 0;
 	struct scatterlist *sg;
-	char *bvec_data;
+	int num_sg, num_grant;
-	void *shared_data;
+	struct copy_from_grant data = {
-	int nseg;
+		.s = s,
+		.grant_idx = 0,
+	};
 
-	nseg = s->req.operation == BLKIF_OP_INDIRECT ?
+	num_grant = s->req.operation == BLKIF_OP_INDIRECT ?
 		s->req.u.indirect.nr_segments : s->req.u.rw.nr_segments;
+	num_sg = s->num_sg;
 
 	if (bret->operation == BLKIF_OP_READ && info->feature_persistent) {
-		for_each_sg(s->sg, sg, nseg, i) {
+		for_each_sg(s->sg, sg, num_sg, i) {
 			BUG_ON(sg->offset + sg->length > PAGE_SIZE);
-			shared_data = kmap_atomic(
+
-				pfn_to_page(s->grants_used[i]->pfn));
+			data.bvec_offset = sg->offset;
-			bvec_data = kmap_atomic(sg_page(sg));
+			data.bvec_data = kmap_atomic(sg_page(sg));
-			memcpy(bvec_data   + sg->offset,
+
-			       shared_data + sg->offset,
+			gnttab_foreach_grant_in_range(sg_page(sg),
-			       sg->length);
+						      sg->offset,
-			kunmap_atomic(bvec_data);
+						      sg->length,
-			kunmap_atomic(shared_data);
+						      blkif_copy_from_grant,
+						      &data);
+
+			kunmap_atomic(data.bvec_data);
 		}
 	}
 	/* Add the persistent grant into the list of free grants */
-	for (i = 0; i < nseg; i++) {
+	for (i = 0; i < num_grant; i++) {
 		if (gnttab_query_foreign_access(s->grants_used[i]->gref)) {
 			/*
 			 * If the grant is still mapped by the backend (the
@@ -1109,7 +1267,7 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 		}
 	}
 	if (s->req.operation == BLKIF_OP_INDIRECT) {
-		for (i = 0; i < INDIRECT_GREFS(nseg); i++) {
+		for (i = 0; i < INDIRECT_GREFS(num_grant); i++) {
 			if (gnttab_query_foreign_access(s->indirect_grants[i]->gref)) {
 				if (!info->feature_persistent)
 					pr_alert_ratelimited("backed has not unmapped grant: %u\n",
@@ -1125,7 +1283,7 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
 				 * available pages for indirect grefs.
 				 */
 				if (!info->feature_persistent) {
-					indirect_page = pfn_to_page(s->indirect_grants[i]->pfn);
+					indirect_page = s->indirect_grants[i]->page;
 					list_add(&indirect_page->lru, &info->indirect_pages);
 				}
 				s->indirect_grants[i]->gref = GRANT_INVALID_REF;
@@ -1254,8 +1412,8 @@ static int setup_blkring(struct xenbus_device *dev,
 {
 	struct blkif_sring *sring;
 	int err, i;
-	unsigned long ring_size = info->nr_ring_pages * PAGE_SIZE;
+	unsigned long ring_size = info->nr_ring_pages * XEN_PAGE_SIZE;
-	grant_ref_t gref[XENBUS_MAX_RING_PAGES];
+	grant_ref_t gref[XENBUS_MAX_RING_GRANTS];
 
 	for (i = 0; i < info->nr_ring_pages; i++)
 		info->ring_ref[i] = GRANT_INVALID_REF;
@@ -1583,8 +1741,8 @@ static int blkif_recover(struct blkfront_info *info)
 			atomic_set(&split_bio->pending, pending);
 			split_bio->bio = bio;
 			for (i = 0; i < pending; i++) {
-				offset = (i * segs * PAGE_SIZE) >> 9;
+				offset = (i * segs * XEN_PAGE_SIZE) >> 9;
-				size = min((unsigned int)(segs * PAGE_SIZE) >> 9,
+				size = min((unsigned int)(segs * XEN_PAGE_SIZE) >> 9,
 					   (unsigned int)bio_sectors(bio) - offset);
 				cloned_bio = bio_clone(bio, GFP_NOIO);
 				BUG_ON(cloned_bio == NULL);
@@ -1695,15 +1853,17 @@ static void blkfront_setup_discard(struct blkfront_info *info)
 
 static int blkfront_setup_indirect(struct blkfront_info *info)
 {
-	unsigned int segs;
+	unsigned int psegs, grants;
 	int err, i;
 
 	if (info->max_indirect_segments == 0)
-		segs = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+		grants = BLKIF_MAX_SEGMENTS_PER_REQUEST;
 	else
-		segs = info->max_indirect_segments;
+		grants = info->max_indirect_segments;
+	psegs = grants / GRANTS_PER_PSEG;
 
-	err = fill_grant_buffer(info, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE(info));
+	err = fill_grant_buffer(info,
+				(grants + INDIRECT_GREFS(grants)) * BLK_RING_SIZE(info));
 	if (err)
 		goto out_of_memory;
 
@@ -1713,7 +1873,7 @@ static int blkfront_setup_indirect(struct blkfront_info *info)
 		 * grants, we need to allocate a set of pages that can be
 		 * used for mapping indirect grefs
 		 */
-		int num = INDIRECT_GREFS(segs) * BLK_RING_SIZE(info);
+		int num = INDIRECT_GREFS(grants) * BLK_RING_SIZE(info);
 
 		BUG_ON(!list_empty(&info->indirect_pages));
 		for (i = 0; i < num; i++) {
@@ -1726,20 +1886,20 @@ static int blkfront_setup_indirect(struct blkfront_info *info)
 
 	for (i = 0; i < BLK_RING_SIZE(info); i++) {
 		info->shadow[i].grants_used = kzalloc(
-			sizeof(info->shadow[i].grants_used[0]) * segs,
+			sizeof(info->shadow[i].grants_used[0]) * grants,
 			GFP_NOIO);
-		info->shadow[i].sg = kzalloc(sizeof(info->shadow[i].sg[0]) * segs, GFP_NOIO);
+		info->shadow[i].sg = kzalloc(sizeof(info->shadow[i].sg[0]) * psegs, GFP_NOIO);
 		if (info->max_indirect_segments)
 			info->shadow[i].indirect_grants = kzalloc(
 				sizeof(info->shadow[i].indirect_grants[0]) *
-				INDIRECT_GREFS(segs),
+				INDIRECT_GREFS(grants),
 				GFP_NOIO);
 		if ((info->shadow[i].grants_used == NULL) ||
 			(info->shadow[i].sg == NULL) ||
 		     (info->max_indirect_segments &&
 		     (info->shadow[i].indirect_grants == NULL)))
 			goto out_of_memory;
-		sg_init_table(info->shadow[i].sg, segs);
+		sg_init_table(info->shadow[i].sg, psegs);
 	}
 
 
@@ -2125,9 +2285,9 @@ static int __init xlblk_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
-	if (xen_blkif_max_ring_order > XENBUS_MAX_RING_PAGE_ORDER) {
+	if (xen_blkif_max_ring_order > XENBUS_MAX_RING_GRANT_ORDER) {
 		pr_info("Invalid max_ring_order (%d), will use default max: %d.\n",
-			xen_blkif_max_ring_order, XENBUS_MAX_RING_PAGE_ORDER);
+			xen_blkif_max_ring_order, XENBUS_MAX_RING_GRANT_ORDER);
 		xen_blkif_max_ring_order = 0;
 	}
 

drivers/net/xen-netback/common.h

@@ -44,6 +44,7 @@
 #include <xen/interface/grant_table.h>
 #include <xen/grant_table.h>
 #include <xen/xenbus.h>
+#include <xen/page.h>
 #include <linux/debugfs.h>
 
 typedef unsigned int pending_ring_idx_t;
@@ -64,8 +65,8 @@ struct pending_tx_info {
 	struct ubuf_info callback_struct;
 };
 
-#define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE)
+#define XEN_NETIF_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, XEN_PAGE_SIZE)
-#define XEN_NETIF_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE)
+#define XEN_NETIF_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, XEN_PAGE_SIZE)
 
 struct xenvif_rx_meta {
 	int id;
@@ -80,16 +81,21 @@ struct xenvif_rx_meta {
 /* Discriminate from any valid pending_idx value. */
 #define INVALID_PENDING_IDX 0xFFFF
 
-#define MAX_BUFFER_OFFSET PAGE_SIZE
+#define MAX_BUFFER_OFFSET XEN_PAGE_SIZE
 
 #define MAX_PENDING_REQS XEN_NETIF_TX_RING_SIZE
 
+/* The maximum number of frags is derived from the size of a grant (same
+ * as a Xen page size for now).
+ */
+#define MAX_XEN_SKB_FRAGS (65536 / XEN_PAGE_SIZE + 1)
+
 /* It's possible for an skb to have a maximal number of frags
  * but still be less than MAX_BUFFER_OFFSET in size. Thus the
- * worst-case number of copy operations is MAX_SKB_FRAGS per
+ * worst-case number of copy operations is MAX_XEN_SKB_FRAGS per
  * ring slot.
  */
-#define MAX_GRANT_COPY_OPS (MAX_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE)
+#define MAX_GRANT_COPY_OPS (MAX_XEN_SKB_FRAGS * XEN_NETIF_RX_RING_SIZE)
 
 #define NETBACK_INVALID_HANDLE -1
 

drivers/net/xen-netback/netback.c

@@ -152,9 +152,9 @@ static inline pending_ring_idx_t pending_index(unsigned i)
 static int xenvif_rx_ring_slots_needed(struct xenvif *vif)
 {
 	if (vif->gso_mask)
-		return DIV_ROUND_UP(vif->dev->gso_max_size, PAGE_SIZE) + 1;
+		return DIV_ROUND_UP(vif->dev->gso_max_size, XEN_PAGE_SIZE) + 1;
 	else
-		return DIV_ROUND_UP(vif->dev->mtu, PAGE_SIZE);
+		return DIV_ROUND_UP(vif->dev->mtu, XEN_PAGE_SIZE);
 }
 
 static bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue)
@@ -274,6 +274,80 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif_queue *queue,
 	return meta;
 }
 
+struct gop_frag_copy {
+	struct xenvif_queue *queue;
+	struct netrx_pending_operations *npo;
+	struct xenvif_rx_meta *meta;
+	int head;
+	int gso_type;
+
+	struct page *page;
+};
+
+static void xenvif_setup_copy_gop(unsigned long gfn,
+				  unsigned int offset,
+				  unsigned int *len,
+				  struct gop_frag_copy *info)
+{
+	struct gnttab_copy *copy_gop;
+	struct xen_page_foreign *foreign;
+	/* Convenient aliases */
+	struct xenvif_queue *queue = info->queue;
+	struct netrx_pending_operations *npo = info->npo;
+	struct page *page = info->page;
+
+	BUG_ON(npo->copy_off > MAX_BUFFER_OFFSET);
+
+	if (npo->copy_off == MAX_BUFFER_OFFSET)
+		info->meta = get_next_rx_buffer(queue, npo);
+
+	if (npo->copy_off + *len > MAX_BUFFER_OFFSET)
+		*len = MAX_BUFFER_OFFSET - npo->copy_off;
+
+	copy_gop = npo->copy + npo->copy_prod++;
+	copy_gop->flags = GNTCOPY_dest_gref;
+	copy_gop->len = *len;
+
+	foreign = xen_page_foreign(page);
+	if (foreign) {
+		copy_gop->source.domid = foreign->domid;
+		copy_gop->source.u.ref = foreign->gref;
+		copy_gop->flags |= GNTCOPY_source_gref;
+	} else {
+		copy_gop->source.domid = DOMID_SELF;
+		copy_gop->source.u.gmfn = gfn;
+	}
+	copy_gop->source.offset = offset;
+
+	copy_gop->dest.domid = queue->vif->domid;
+	copy_gop->dest.offset = npo->copy_off;
+	copy_gop->dest.u.ref = npo->copy_gref;
+
+	npo->copy_off += *len;
+	info->meta->size += *len;
+
+	/* Leave a gap for the GSO descriptor. */
+	if (info->head && ((1 << info->gso_type) & queue->vif->gso_mask))
+		queue->rx.req_cons++;
+
+	info->head = 0; /* There must be something in this buffer now */
+}
+
+static void xenvif_gop_frag_copy_grant(unsigned long gfn,
+				       unsigned offset,
+				       unsigned int len,
+				       void *data)
+{
+	unsigned int bytes;
+
+	while (len) {
+		bytes = len;
+		xenvif_setup_copy_gop(gfn, offset, &bytes, data);
+		offset += bytes;
+		len -= bytes;
+	}
+}
+
 /*
  * Set up the grant operations for this fragment. If it's a flipping
  * interface, we also set up the unmap request from here.
@@ -283,83 +357,52 @@ static void xenvif_gop_frag_copy(struct xenvif_queue *queue, struct sk_buff *skb
 				 struct page *page, unsigned long size,
 				 unsigned long offset, int *head)
 {
-	struct gnttab_copy *copy_gop;
+	struct gop_frag_copy info = {
-	struct xenvif_rx_meta *meta;
+		.queue = queue,
+		.npo = npo,
+		.head = *head,
+		.gso_type = XEN_NETIF_GSO_TYPE_NONE,
+	};
 	unsigned long bytes;
-	int gso_type = XEN_NETIF_GSO_TYPE_NONE;
+
+	if (skb_is_gso(skb)) {
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
+			info.gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
+		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
+			info.gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
+	}
 
 	/* Data must not cross a page boundary. */
 	BUG_ON(size + offset > PAGE_SIZE<<compound_order(page));
 
-	meta = npo->meta + npo->meta_prod - 1;
+	info.meta = npo->meta + npo->meta_prod - 1;
 
 	/* Skip unused frames from start of page */
 	page += offset >> PAGE_SHIFT;
 	offset &= ~PAGE_MASK;
 
 	while (size > 0) {
-		struct xen_page_foreign *foreign;
-
 		BUG_ON(offset >= PAGE_SIZE);
-		BUG_ON(npo->copy_off > MAX_BUFFER_OFFSET);
-
-		if (npo->copy_off == MAX_BUFFER_OFFSET)
-			meta = get_next_rx_buffer(queue, npo);
 
 		bytes = PAGE_SIZE - offset;
 		if (bytes > size)
 			bytes = size;
 
-		if (npo->copy_off + bytes > MAX_BUFFER_OFFSET)
+		info.page = page;
-			bytes = MAX_BUFFER_OFFSET - npo->copy_off;
+		gnttab_foreach_grant_in_range(page, offset, bytes,
-
+					      xenvif_gop_frag_copy_grant,
-		copy_gop = npo->copy + npo->copy_prod++;
+					      &info);
-		copy_gop->flags = GNTCOPY_dest_gref;
-		copy_gop->len = bytes;
-
-		foreign = xen_page_foreign(page);
-		if (foreign) {
-			copy_gop->source.domid = foreign->domid;
-			copy_gop->source.u.ref = foreign->gref;
-			copy_gop->flags |= GNTCOPY_source_gref;
-		} else {
-			copy_gop->source.domid = DOMID_SELF;
-			copy_gop->source.u.gmfn =
-				virt_to_gfn(page_address(page));
-		}
-		copy_gop->source.offset = offset;
-
-		copy_gop->dest.domid = queue->vif->domid;
-		copy_gop->dest.offset = npo->copy_off;
-		copy_gop->dest.u.ref = npo->copy_gref;
-
-		npo->copy_off += bytes;
-		meta->size += bytes;
-
-		offset += bytes;
 		size -= bytes;
+		offset = 0;
 
-		/* Next frame */
+		/* Next page */
-		if (offset == PAGE_SIZE && size) {
+		if (size) {
 			BUG_ON(!PageCompound(page));
 			page++;
-			offset = 0;
 		}
-
-		/* Leave a gap for the GSO descriptor. */
-		if (skb_is_gso(skb)) {
-			if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
-				gso_type = XEN_NETIF_GSO_TYPE_TCPV4;
-			else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
-				gso_type = XEN_NETIF_GSO_TYPE_TCPV6;
-		}
-
-		if (*head && ((1 << gso_type) & queue->vif->gso_mask))
-			queue->rx.req_cons++;
-
-		*head = 0; /* There must be something in this buffer now. */
-
 	}
+
+	*head = info.head;
 }
 
 /*
@@ -758,7 +801,7 @@ static int xenvif_count_requests(struct xenvif_queue *queue,
 		first->size -= txp->size;
 		slots++;
 
-		if (unlikely((txp->offset + txp->size) > PAGE_SIZE)) {
+		if (unlikely((txp->offset + txp->size) > XEN_PAGE_SIZE)) {
 			netdev_err(queue->vif->dev, "Cross page boundary, txp->offset: %u, size: %u\n",
 				 txp->offset, txp->size);
 			xenvif_fatal_tx_err(queue->vif);
@@ -1339,11 +1382,11 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 		}
 
 		/* No crossing a page as the payload mustn't fragment. */
-		if (unlikely((txreq.offset + txreq.size) > PAGE_SIZE)) {
+		if (unlikely((txreq.offset + txreq.size) > XEN_PAGE_SIZE)) {
 			netdev_err(queue->vif->dev,
 				   "txreq.offset: %u, size: %u, end: %lu\n",
 				   txreq.offset, txreq.size,
-				   (unsigned long)(txreq.offset&~PAGE_MASK) + txreq.size);
+				   (unsigned long)(txreq.offset&~XEN_PAGE_MASK) + txreq.size);
 			xenvif_fatal_tx_err(queue->vif);
 			break;
 		}
@@ -1409,7 +1452,7 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 			virt_to_gfn(skb->data);
 		queue->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF;
 		queue->tx_copy_ops[*copy_ops].dest.offset =
-			offset_in_page(skb->data);
+			offset_in_page(skb->data) & ~XEN_PAGE_MASK;
 
 		queue->tx_copy_ops[*copy_ops].len = data_len;
 		queue->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref;
@@ -1894,7 +1937,7 @@ int xenvif_map_frontend_rings(struct xenvif_queue *queue,
 		goto err;
 
 	txs = (struct xen_netif_tx_sring *)addr;
-	BACK_RING_INIT(&queue->tx, txs, PAGE_SIZE);
+	BACK_RING_INIT(&queue->tx, txs, XEN_PAGE_SIZE);
 
 	err = xenbus_map_ring_valloc(xenvif_to_xenbus_device(queue->vif),
 				     &rx_ring_ref, 1, &addr);
@@ -1902,7 +1945,7 @@ int xenvif_map_frontend_rings(struct xenvif_queue *queue,
 		goto err;
 
 	rxs = (struct xen_netif_rx_sring *)addr;
-	BACK_RING_INIT(&queue->rx, rxs, PAGE_SIZE);
+	BACK_RING_INIT(&queue->rx, rxs, XEN_PAGE_SIZE);
 
 	return 0;
 

drivers/net/xen-netfront.c

@@ -74,8 +74,8 @@ struct netfront_cb {
 
 #define GRANT_INVALID_REF	0
 
-#define NET_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, PAGE_SIZE)
+#define NET_TX_RING_SIZE __CONST_RING_SIZE(xen_netif_tx, XEN_PAGE_SIZE)
-#define NET_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, PAGE_SIZE)
+#define NET_RX_RING_SIZE __CONST_RING_SIZE(xen_netif_rx, XEN_PAGE_SIZE)
 
 /* Minimum number of Rx slots (includes slot for GSO metadata). */
 #define NET_RX_SLOTS_MIN (XEN_NETIF_NR_SLOTS_MIN + 1)
@@ -291,7 +291,7 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
 		struct sk_buff *skb;
 		unsigned short id;
 		grant_ref_t ref;
-		unsigned long gfn;
+		struct page *page;
 		struct xen_netif_rx_request *req;
 
 		skb = xennet_alloc_one_rx_buffer(queue);
@@ -307,14 +307,13 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
 		BUG_ON((signed short)ref < 0);
 		queue->grant_rx_ref[id] = ref;
 
-		gfn = xen_page_to_gfn(skb_frag_page(&skb_shinfo(skb)->frags[0]));
+		page = skb_frag_page(&skb_shinfo(skb)->frags[0]);
 
 		req = RING_GET_REQUEST(&queue->rx, req_prod);
-		gnttab_grant_foreign_access_ref(ref,
+		gnttab_page_grant_foreign_access_ref_one(ref,
-						queue->info->xbdev->otherend_id,
+							 queue->info->xbdev->otherend_id,
-						gfn,
+							 page,
-						0);
+							 0);
-
 		req->id = id;
 		req->gref = ref;
 	}
@@ -415,25 +414,33 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue)
 	xennet_maybe_wake_tx(queue);
 }
 
-static struct xen_netif_tx_request *xennet_make_one_txreq(
+struct xennet_gnttab_make_txreq {
-	struct netfront_queue *queue, struct sk_buff *skb,
+	struct netfront_queue *queue;
-	struct page *page, unsigned int offset, unsigned int len)
+	struct sk_buff *skb;
+	struct page *page;
+	struct xen_netif_tx_request *tx; /* Last request */
+	unsigned int size;
+};
+
+static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset,
+				  unsigned int len, void *data)
 {
+	struct xennet_gnttab_make_txreq *info = data;
 	unsigned int id;
 	struct xen_netif_tx_request *tx;
 	grant_ref_t ref;
-
+	/* convenient aliases */
-	len = min_t(unsigned int, PAGE_SIZE - offset, len);
+	struct page *page = info->page;
+	struct netfront_queue *queue = info->queue;
+	struct sk_buff *skb = info->skb;
 
 	id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs);
 	tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++);
 	ref = gnttab_claim_grant_reference(&queue->gref_tx_head);
 	BUG_ON((signed short)ref < 0);
 
-	gnttab_grant_foreign_access_ref(ref,
+	gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id,
-					queue->info->xbdev->otherend_id,
+					gfn, GNTMAP_readonly);
-					xen_page_to_gfn(page),
-					GNTMAP_readonly);
 
 	queue->tx_skbs[id].skb = skb;
 	queue->grant_tx_page[id] = page;
@@ -445,7 +452,34 @@ static struct xen_netif_tx_request *xennet_make_one_txreq(
 	tx->size = len;
 	tx->flags = 0;
 
-	return tx;
+	info->tx = tx;
+	info->size += tx->size;
+}
+
+static struct xen_netif_tx_request *xennet_make_first_txreq(
+	struct netfront_queue *queue, struct sk_buff *skb,
+	struct page *page, unsigned int offset, unsigned int len)
+{
+	struct xennet_gnttab_make_txreq info = {
+		.queue = queue,
+		.skb = skb,
+		.page = page,
+		.size = 0,
+	};
+
+	gnttab_for_one_grant(page, offset, len, xennet_tx_setup_grant, &info);
+
+	return info.tx;
+}
+
+static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset,
+				  unsigned int len, void *data)
+{
+	struct xennet_gnttab_make_txreq *info = data;
+
+	info->tx->flags |= XEN_NETTXF_more_data;
+	skb_get(info->skb);
+	xennet_tx_setup_grant(gfn, offset, len, data);
 }
 
 static struct xen_netif_tx_request *xennet_make_txreqs(
@@ -453,20 +487,30 @@ static struct xen_netif_tx_request *xennet_make_txreqs(
 	struct sk_buff *skb, struct page *page,
 	unsigned int offset, unsigned int len)
 {
+	struct xennet_gnttab_make_txreq info = {
+		.queue = queue,
+		.skb = skb,
+		.tx = tx,
+	};
+
 	/* Skip unused frames from start of page */
 	page += offset >> PAGE_SHIFT;
 	offset &= ~PAGE_MASK;
 
 	while (len) {
-		tx->flags |= XEN_NETTXF_more_data;
+		info.page = page;
-		tx = xennet_make_one_txreq(queue, skb_get(skb),
+		info.size = 0;
-					   page, offset, len);
+
+		gnttab_foreach_grant_in_range(page, offset, len,
+					      xennet_make_one_txreq,
+					      &info);
+
 		page++;
 		offset = 0;
-		len -= tx->size;
+		len -= info.size;
 	}
 
-	return tx;
+	return info.tx;
 }
 
 /*
@@ -476,9 +520,10 @@ static struct xen_netif_tx_request *xennet_make_txreqs(
 static int xennet_count_skb_slots(struct sk_buff *skb)
 {
 	int i, frags = skb_shinfo(skb)->nr_frags;
-	int pages;
+	int slots;
 
-	pages = PFN_UP(offset_in_page(skb->data) + skb_headlen(skb));
+	slots = gnttab_count_grant(offset_in_page(skb->data),
+				   skb_headlen(skb));
 
 	for (i = 0; i < frags; i++) {
 		skb_frag_t *frag = skb_shinfo(skb)->frags + i;
@@ -488,10 +533,10 @@ static int xennet_count_skb_slots(struct sk_buff *skb)
 		/* Skip unused frames from start of page */
 		offset &= ~PAGE_MASK;
 
-		pages += PFN_UP(offset + size);
+		slots += gnttab_count_grant(offset, size);
 	}
 
-	return pages;
+	return slots;
 }
 
 static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
@@ -512,6 +557,8 @@ static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
 	return queue_idx;
 }
 
+#define MAX_XEN_SKB_FRAGS (65536 / XEN_PAGE_SIZE + 1)
+
 static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct netfront_info *np = netdev_priv(dev);
@@ -546,7 +593,7 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	slots = xennet_count_skb_slots(skb);
-	if (unlikely(slots > MAX_SKB_FRAGS + 1)) {
+	if (unlikely(slots > MAX_XEN_SKB_FRAGS + 1)) {
 		net_dbg_ratelimited("xennet: skb rides the rocket: %d slots, %d bytes\n",
 				    slots, skb->len);
 		if (skb_linearize(skb))
@@ -567,10 +614,13 @@ static int xennet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	/* First request for the linear area. */
-	first_tx = tx = xennet_make_one_txreq(queue, skb,
+	first_tx = tx = xennet_make_first_txreq(queue, skb,
-					      page, offset, len);
+						page, offset, len);
-	page++;
+	offset += tx->size;
-	offset = 0;
+	if (offset == PAGE_SIZE) {
+		page++;
+		offset = 0;
+	}
 	len -= tx->size;
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
@@ -732,7 +782,7 @@ static int xennet_get_responses(struct netfront_queue *queue,
 
 	for (;;) {
 		if (unlikely(rx->status < 0 ||
-			     rx->offset + rx->status > PAGE_SIZE)) {
+			     rx->offset + rx->status > XEN_PAGE_SIZE)) {
 			if (net_ratelimit())
 				dev_warn(dev, "rx->offset: %u, size: %d\n",
 					 rx->offset, rx->status);
@@ -1496,7 +1546,7 @@ static int setup_netfront(struct xenbus_device *dev,
 		goto fail;
 	}
 	SHARED_RING_INIT(txs);
-	FRONT_RING_INIT(&queue->tx, txs, PAGE_SIZE);
+	FRONT_RING_INIT(&queue->tx, txs, XEN_PAGE_SIZE);
 
 	err = xenbus_grant_ring(dev, txs, 1, &gref);
 	if (err < 0)
@@ -1510,7 +1560,7 @@ static int setup_netfront(struct xenbus_device *dev,
 		goto alloc_rx_ring_fail;
 	}
 	SHARED_RING_INIT(rxs);
-	FRONT_RING_INIT(&queue->rx, rxs, PAGE_SIZE);
+	FRONT_RING_INIT(&queue->rx, rxs, XEN_PAGE_SIZE);
 
 	err = xenbus_grant_ring(dev, rxs, 1, &gref);
 	if (err < 0)

drivers/tty/hvc/hvc_xen.c

@@ -230,7 +230,7 @@ static int xen_hvm_console_init(void)
 	if (r < 0 || v == 0)
 		goto err;
 	gfn = v;
-	info->intf = xen_remap(gfn << PAGE_SHIFT, PAGE_SIZE);
+	info->intf = xen_remap(gfn << XEN_PAGE_SHIFT, XEN_PAGE_SIZE);
 	if (info->intf == NULL)
 		goto err;
 	info->vtermno = HVC_COOKIE;
@@ -472,7 +472,7 @@ static int xencons_resume(struct xenbus_device *dev)
 	struct xencons_info *info = dev_get_drvdata(&dev->dev);
 
 	xencons_disconnect_backend(info);
-	memset(info->intf, 0, PAGE_SIZE);
+	memset(info->intf, 0, XEN_PAGE_SIZE);
 	return xencons_connect_backend(dev, info);
 }
 

drivers/xen/Makefile

@@ -1,6 +1,4 @@
-ifeq ($(filter y, $(CONFIG_ARM) $(CONFIG_ARM64)),)
 obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
-endif
 obj-$(CONFIG_X86)			+= fallback.o
 obj-y	+= grant-table.o features.o balloon.o manage.o preempt.o
 obj-y	+= events/

drivers/xen/balloon.c

@@ -54,6 +54,8 @@
 #include <linux/memory.h>
 #include <linux/memory_hotplug.h>
 #include <linux/percpu-defs.h>
+#include <linux/slab.h>
+#include <linux/sysctl.h>
 
 #include <asm/page.h>
 #include <asm/pgalloc.h>
@@ -70,16 +72,64 @@
 #include <xen/features.h>
 #include <xen/page.h>
 
+static int xen_hotplug_unpopulated;
+
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+
+static int zero;
+static int one = 1;
+
+static struct ctl_table balloon_table[] = {
+	{
+		.procname	= "hotplug_unpopulated",
+		.data		= &xen_hotplug_unpopulated,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1         = &zero,
+		.extra2         = &one,
+	},
+	{ }
+};
+
+static struct ctl_table balloon_root[] = {
+	{
+		.procname	= "balloon",
+		.mode		= 0555,
+		.child		= balloon_table,
+	},
+	{ }
+};
+
+static struct ctl_table xen_root[] = {
+	{
+		.procname	= "xen",
+		.mode		= 0555,
+		.child		= balloon_root,
+	},
+	{ }
+};
+
+#endif
+
+/*
+ * 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)
+
 /*
  * balloon_process() state:
  *
  * BP_DONE: done or nothing to do,
+ * BP_WAIT: wait to be rescheduled,
  * BP_EAGAIN: error, go to sleep,
  * BP_ECANCELED: error, balloon operation canceled.
  */
 
 enum bp_state {
 	BP_DONE,
+	BP_WAIT,
 	BP_EAGAIN,
 	BP_ECANCELED
 };
@@ -91,11 +141,12 @@ struct balloon_stats balloon_stats;
 EXPORT_SYMBOL_GPL(balloon_stats);
 
 /* We increase/decrease in batches which fit in a page */
-static xen_pfn_t frame_list[PAGE_SIZE / sizeof(unsigned long)];
+static xen_pfn_t frame_list[PAGE_SIZE / sizeof(xen_pfn_t)];
 
 
 /* List of ballooned pages, threaded through the mem_map array. */
 static LIST_HEAD(ballooned_pages);
+static DECLARE_WAIT_QUEUE_HEAD(balloon_wq);
 
 /* Main work function, always executed in process context. */
 static void balloon_process(struct work_struct *work);
@@ -124,6 +175,7 @@ static void __balloon_append(struct page *page)
 		list_add(&page->lru, &ballooned_pages);
 		balloon_stats.balloon_low++;
 	}
+	wake_up(&balloon_wq);
 }
 
 static void balloon_append(struct page *page)
@@ -133,17 +185,16 @@ static void balloon_append(struct page *page)
 }
 
 /* balloon_retrieve: rescue a page from the balloon, if it is not empty. */
-static struct page *balloon_retrieve(bool prefer_highmem)
+static struct page *balloon_retrieve(bool require_lowmem)
 {
 	struct page *page;
 
 	if (list_empty(&ballooned_pages))
 		return NULL;
 
-	if (prefer_highmem)
+	page = list_entry(ballooned_pages.next, struct page, lru);
-		page = list_entry(ballooned_pages.prev, struct page, lru);
+	if (require_lowmem && PageHighMem(page))
-	else
+		return NULL;
-		page = list_entry(ballooned_pages.next, struct page, lru);
 	list_del(&page->lru);
 
 	if (PageHighMem(page))
@@ -166,6 +217,9 @@ static struct page *balloon_next_page(struct page *page)
 
 static enum bp_state update_schedule(enum bp_state state)
 {
+	if (state == BP_WAIT)
+		return BP_WAIT;
+
 	if (state == BP_ECANCELED)
 		return BP_ECANCELED;
 
@@ -193,43 +247,75 @@ static enum bp_state update_schedule(enum bp_state state)
 }
 
 #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
-static long current_credit(void)
+static struct resource *additional_memory_resource(phys_addr_t size)
 {
-	return balloon_stats.target_pages - balloon_stats.current_pages -
+	struct resource *res;
-		balloon_stats.hotplug_pages;
+	int ret;
+
+	res = kzalloc(sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return NULL;
+
+	res->name = "System RAM";
+	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+
+	ret = allocate_resource(&iomem_resource, res,
+				size, 0, -1,
+				PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL);
+	if (ret < 0) {
+		pr_err("Cannot allocate new System RAM resource\n");
+		kfree(res);
+		return NULL;
+	}
+
+	return res;
 }
 
-static bool balloon_is_inflated(void)
+static void release_memory_resource(struct resource *resource)
 {
-	if (balloon_stats.balloon_low || balloon_stats.balloon_high ||
+	if (!resource)
-			balloon_stats.balloon_hotplug)
+		return;
-		return true;
+
-	else
+	/*
-		return false;
+	 * No need to reset region to identity mapped since we now
+	 * know that no I/O can be in this region
+	 */
+	release_resource(resource);
+	kfree(resource);
 }
 
-/*
+static enum bp_state reserve_additional_memory(void)
- * reserve_additional_memory() adds memory region of size >= credit above
- * max_pfn. New region is section aligned and size is modified to be multiple
- * of section size. Those features allow optimal use of address space and
- * establish proper alignment when this function is called first time after
- * boot (last section not fully populated at boot time contains unused memory
- * pages with PG_reserved bit not set; online_pages_range() does not allow page
- * onlining in whole range if first onlined page does not have PG_reserved
- * bit set). Real size of added memory is established at page onlining stage.
- */
-
-static enum bp_state reserve_additional_memory(long credit)
 {
+	long credit;
+	struct resource *resource;
 	int nid, rc;
-	u64 hotplug_start_paddr;
+	unsigned long balloon_hotplug;
-	unsigned long balloon_hotplug = credit;
 
-	hotplug_start_paddr = PFN_PHYS(SECTION_ALIGN_UP(max_pfn));
+	credit = balloon_stats.target_pages + balloon_stats.target_unpopulated
-	balloon_hotplug = round_up(balloon_hotplug, PAGES_PER_SECTION);
+		- balloon_stats.total_pages;
-	nid = memory_add_physaddr_to_nid(hotplug_start_paddr);
+
+	/*
+	 * Already hotplugged enough pages?  Wait for them to be
+	 * onlined.
+	 */
+	if (credit <= 0)
+		return BP_WAIT;
+
+	balloon_hotplug = round_up(credit, PAGES_PER_SECTION);
+
+	resource = additional_memory_resource(balloon_hotplug * PAGE_SIZE);
+	if (!resource)
+		goto err;
+
+	nid = memory_add_physaddr_to_nid(resource->start);
 
 #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);
+
         /*
          * add_memory() will build page tables for the new memory so
          * the p2m must contain invalid entries so the correct
@@ -242,29 +328,28 @@ static enum bp_state reserve_additional_memory(long credit)
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
 		unsigned long pfn, i;
 
-		pfn = PFN_DOWN(hotplug_start_paddr);
+		pfn = PFN_DOWN(resource->start);
 		for (i = 0; i < balloon_hotplug; i++) {
 			if (!set_phys_to_machine(pfn + i, INVALID_P2M_ENTRY)) {
 				pr_warn("set_phys_to_machine() failed, no memory added\n");
-				return BP_ECANCELED;
+				goto err;
 			}
                 }
 	}
 #endif
 
-	rc = add_memory(nid, hotplug_start_paddr, balloon_hotplug << PAGE_SHIFT);
+	rc = add_memory_resource(nid, resource);
-
 	if (rc) {
 		pr_warn("Cannot add additional memory (%i)\n", rc);
-		return BP_ECANCELED;
+		goto err;
 	}
 
-	balloon_hotplug -= credit;
+	balloon_stats.total_pages += balloon_hotplug;
 
-	balloon_stats.hotplug_pages += credit;
+	return BP_WAIT;
-	balloon_stats.balloon_hotplug = balloon_hotplug;
+  err:
-
+	release_memory_resource(resource);
-	return BP_DONE;
+	return BP_ECANCELED;
 }
 
 static void xen_online_page(struct page *page)
@@ -275,11 +360,6 @@ static void xen_online_page(struct page *page)
 
 	__balloon_append(page);
 
-	if (balloon_stats.hotplug_pages)
-		--balloon_stats.hotplug_pages;
-	else
-		--balloon_stats.balloon_hotplug;
-
 	mutex_unlock(&balloon_mutex);
 }
 
@@ -296,53 +376,34 @@ static struct notifier_block xen_memory_nb = {
 	.priority = 0
 };
 #else
+static enum bp_state reserve_additional_memory(void)
+{
+	balloon_stats.target_pages = balloon_stats.current_pages;
+	return BP_ECANCELED;
+}
+#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
+
 static long current_credit(void)
 {
-	unsigned long target = balloon_stats.target_pages;
+	return balloon_stats.target_pages - balloon_stats.current_pages;
-
-	target = min(target,
-		     balloon_stats.current_pages +
-		     balloon_stats.balloon_low +
-		     balloon_stats.balloon_high);
-
-	return target - balloon_stats.current_pages;
 }
 
 static bool balloon_is_inflated(void)
 {
-	if (balloon_stats.balloon_low || balloon_stats.balloon_high)
+	return balloon_stats.balloon_low || balloon_stats.balloon_high;
-		return true;
-	else
-		return false;
 }
 
-static enum bp_state reserve_additional_memory(long credit)
-{
-	balloon_stats.target_pages = balloon_stats.current_pages;
-	return BP_DONE;
-}
-#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
-
 static enum bp_state increase_reservation(unsigned long nr_pages)
 {
 	int rc;
-	unsigned long  pfn, i;
+	unsigned long i;
 	struct page   *page;
 	struct xen_memory_reservation reservation = {
 		.address_bits = 0,
-		.extent_order = 0,
+		.extent_order = EXTENT_ORDER,
 		.domid        = DOMID_SELF
 	};
 
-#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
-	if (!balloon_stats.balloon_low && !balloon_stats.balloon_high) {
-		nr_pages = min(nr_pages, balloon_stats.balloon_hotplug);
-		balloon_stats.hotplug_pages += nr_pages;
-		balloon_stats.balloon_hotplug -= nr_pages;
-		return BP_DONE;
-	}
-#endif
-
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
 
@@ -352,7 +413,11 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 			nr_pages = i;
 			break;
 		}
-		frame_list[i] = page_to_pfn(page);
+
+		/* XENMEM_populate_physmap requires a PFN based on Xen
+		 * granularity.
+		 */
+		frame_list[i] = page_to_xen_pfn(page);
 		page = balloon_next_page(page);
 	}
 
@@ -366,10 +431,16 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 		page = balloon_retrieve(false);
 		BUG_ON(page == NULL);
 
-		pfn = page_to_pfn(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);
+
 			set_phys_to_machine(pfn, frame_list[i]);
 
 			/* Link back into the page tables if not highmem. */
@@ -396,23 +467,15 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 {
 	enum bp_state state = BP_DONE;
-	unsigned long  pfn, i;
+	unsigned long i;
-	struct page   *page;
+	struct page *page, *tmp;
 	int ret;
 	struct xen_memory_reservation reservation = {
 		.address_bits = 0,
-		.extent_order = 0,
+		.extent_order = EXTENT_ORDER,
 		.domid        = DOMID_SELF
 	};
-
+	LIST_HEAD(pages);
-#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
-	if (balloon_stats.hotplug_pages) {
-		nr_pages = min(nr_pages, balloon_stats.hotplug_pages);
-		balloon_stats.hotplug_pages -= nr_pages;
-		balloon_stats.balloon_hotplug += nr_pages;
-		return BP_DONE;
-	}
-#endif
 
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
@@ -425,8 +488,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 			break;
 		}
 		scrub_page(page);
-
+		list_add(&page->lru, &pages);
-		frame_list[i] = page_to_pfn(page);
 	}
 
 	/*
@@ -438,14 +500,25 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 	 */
 	kmap_flush_unused();
 
-	/* Update direct mapping, invalidate P2M, and add to balloon. */
+	/*
-	for (i = 0; i < nr_pages; i++) {
+	 * Setup the frame, update direct mapping, invalidate P2M,
-		pfn = frame_list[i];
+	 * and add to balloon.
-		frame_list[i] = pfn_to_gfn(pfn);
+	 */
-		page = pfn_to_page(pfn);
+	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);
+
 			if (!PageHighMem(page)) {
 				ret = HYPERVISOR_update_va_mapping(
 						(unsigned long)__va(pfn << PAGE_SHIFT),
@@ -455,6 +528,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
 		}
 #endif
+		list_del(&page->lru);
 
 		balloon_append(page);
 	}
@@ -492,7 +566,7 @@ static void balloon_process(struct work_struct *work)
 			if (balloon_is_inflated())
 				state = increase_reservation(credit);
 			else
-				state = reserve_additional_memory(credit);
+				state = reserve_additional_memory();
 		}
 
 		if (credit < 0)
@@ -520,41 +594,71 @@ void balloon_set_new_target(unsigned long target)
 }
 EXPORT_SYMBOL_GPL(balloon_set_new_target);
 
+static int add_ballooned_pages(int nr_pages)
+{
+	enum bp_state st;
+
+	if (xen_hotplug_unpopulated) {
+		st = reserve_additional_memory();
+		if (st != BP_ECANCELED) {
+			mutex_unlock(&balloon_mutex);
+			wait_event(balloon_wq,
+				   !list_empty(&ballooned_pages));
+			mutex_lock(&balloon_mutex);
+			return 0;
+		}
+	}
+
+	st = decrease_reservation(nr_pages, GFP_USER);
+	if (st != BP_DONE)
+		return -ENOMEM;
+
+	return 0;
+}
+
 /**
  * alloc_xenballooned_pages - get pages that have been ballooned out
  * @nr_pages: Number of pages to get
  * @pages: pages returned
- * @highmem: allow highmem pages
  * @return 0 on success, error otherwise
  */
-int alloc_xenballooned_pages(int nr_pages, struct page **pages, bool highmem)
+int alloc_xenballooned_pages(int nr_pages, struct page **pages)
 {
 	int pgno = 0;
 	struct page *page;
+	int ret;
+
 	mutex_lock(&balloon_mutex);
+
+	balloon_stats.target_unpopulated += nr_pages;
+
 	while (pgno < nr_pages) {
-		page = balloon_retrieve(highmem);
+		page = balloon_retrieve(true);
-		if (page && (highmem || !PageHighMem(page))) {
+		if (page) {
 			pages[pgno++] = 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);
+
+			ret = xen_alloc_p2m_entry(page_to_pfn(page));
+			if (ret < 0)
+				goto out_undo;
+#endif
 		} else {
-			enum bp_state st;
+			ret = add_ballooned_pages(nr_pages - pgno);
-			if (page)
+			if (ret < 0)
-				balloon_append(page);
-			st = decrease_reservation(nr_pages - pgno,
-					highmem ? GFP_HIGHUSER : GFP_USER);
-			if (st != BP_DONE)
 				goto out_undo;
 		}
 	}
 	mutex_unlock(&balloon_mutex);
 	return 0;
  out_undo:
-	while (pgno)
-		balloon_append(pages[--pgno]);
-	/* Free the memory back to the kernel soon */
-	schedule_delayed_work(&balloon_worker, 0);
 	mutex_unlock(&balloon_mutex);
-	return -ENOMEM;
+	free_xenballooned_pages(pgno, pages);
+	return ret;
 }
 EXPORT_SYMBOL(alloc_xenballooned_pages);
 
@@ -574,6 +678,8 @@ void free_xenballooned_pages(int nr_pages, struct page **pages)
 			balloon_append(pages[i]);
 	}
 
+	balloon_stats.target_unpopulated -= nr_pages;
+
 	/* The balloon may be too large now. Shrink it if needed. */
 	if (current_credit())
 		schedule_delayed_work(&balloon_worker, 0);
@@ -602,6 +708,8 @@ static void __init balloon_add_region(unsigned long start_pfn,
 		   don't subtract from it. */
 		__balloon_append(page);
 	}
+
+	balloon_stats.total_pages += extra_pfn_end - start_pfn;
 }
 
 static int __init balloon_init(void)
@@ -619,6 +727,7 @@ static int __init balloon_init(void)
 	balloon_stats.target_pages  = balloon_stats.current_pages;
 	balloon_stats.balloon_low   = 0;
 	balloon_stats.balloon_high  = 0;
+	balloon_stats.total_pages   = balloon_stats.current_pages;
 
 	balloon_stats.schedule_delay = 1;
 	balloon_stats.max_schedule_delay = 32;
@@ -626,11 +735,9 @@ static int __init balloon_init(void)
 	balloon_stats.max_retry_count = RETRY_UNLIMITED;
 
 #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
-	balloon_stats.hotplug_pages = 0;
-	balloon_stats.balloon_hotplug = 0;
-
 	set_online_page_callback(&xen_online_page);
 	register_memory_notifier(&xen_memory_nb);
+	register_sysctl_table(xen_root);
 #endif
 
 	/*

drivers/xen/biomerge.c

@@ -6,10 +6,18 @@
 bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 			       const struct bio_vec *vec2)
 {
+#if XEN_PAGE_SIZE == PAGE_SIZE
 	unsigned long bfn1 = pfn_to_bfn(page_to_pfn(vec1->bv_page));
 	unsigned long bfn2 = pfn_to_bfn(page_to_pfn(vec2->bv_page));
 
 	return __BIOVEC_PHYS_MERGEABLE(vec1, vec2) &&
 		((bfn1 == bfn2) || ((bfn1+1) == bfn2));
+#else
+	/*
+	 * XXX: Add support for merging bio_vec when using different page
+	 * size in Xen and Linux.
+	 */
+	return 0;
+#endif
 }
 EXPORT_SYMBOL(xen_biovec_phys_mergeable);

drivers/xen/cpu_hotplug.c

@@ -11,15 +11,20 @@
 static void enable_hotplug_cpu(int cpu)
 {
 	if (!cpu_present(cpu))
-		arch_register_cpu(cpu);
+		xen_arch_register_cpu(cpu);
 
 	set_cpu_present(cpu, true);
 }
 
 static void disable_hotplug_cpu(int cpu)
 {
+	if (cpu_online(cpu)) {
+		lock_device_hotplug();
+		device_offline(get_cpu_device(cpu));
+		unlock_device_hotplug();
+	}
 	if (cpu_present(cpu))
-		arch_unregister_cpu(cpu);
+		xen_arch_unregister_cpu(cpu);
 
 	set_cpu_present(cpu, false);
 }
@@ -55,7 +60,6 @@ static void vcpu_hotplug(unsigned int cpu)
 		enable_hotplug_cpu(cpu);
 		break;
 	case 0:
-		(void)cpu_down(cpu);
 		disable_hotplug_cpu(cpu);
 		break;
 	default:
@@ -102,7 +106,11 @@ static int __init setup_vcpu_hotplug_event(void)
 	static struct notifier_block xsn_cpu = {
 		.notifier_call = setup_cpu_watcher };
 
+#ifdef CONFIG_X86
 	if (!xen_pv_domain())
+#else
+	if (!xen_domain())
+#endif
 		return -ENODEV;
 
 	register_xenstore_notifier(&xsn_cpu);

drivers/xen/events/events_base.c

@@ -40,11 +40,11 @@
 #include <asm/idle.h>
 #include <asm/io_apic.h>
 #include <asm/xen/pci.h>
-#include <xen/page.h>
 #endif
 #include <asm/sync_bitops.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
+#include <xen/page.h>
 
 #include <xen/xen.h>
 #include <xen/hvm.h>

drivers/xen/events/events_fifo.c

@@ -54,7 +54,7 @@
 
 #include "events_internal.h"
 
-#define EVENT_WORDS_PER_PAGE (PAGE_SIZE / sizeof(event_word_t))
+#define EVENT_WORDS_PER_PAGE (XEN_PAGE_SIZE / sizeof(event_word_t))
 #define MAX_EVENT_ARRAY_PAGES (EVTCHN_FIFO_NR_CHANNELS / EVENT_WORDS_PER_PAGE)
 
 struct evtchn_fifo_queue {

drivers/xen/grant-table.c

@@ -642,7 +642,7 @@ int gnttab_setup_auto_xlat_frames(phys_addr_t addr)
 	if (xen_auto_xlat_grant_frames.count)
 		return -EINVAL;
 
-	vaddr = xen_remap(addr, PAGE_SIZE * max_nr_gframes);
+	vaddr = xen_remap(addr, XEN_PAGE_SIZE * max_nr_gframes);
 	if (vaddr == NULL) {
 		pr_warn("Failed to ioremap gnttab share frames (addr=%pa)!\n",
 			&addr);
@@ -654,7 +654,7 @@ int gnttab_setup_auto_xlat_frames(phys_addr_t addr)
 		return -ENOMEM;
 	}
 	for (i = 0; i < max_nr_gframes; i++)
-		pfn[i] = PFN_DOWN(addr) + i;
+		pfn[i] = XEN_PFN_DOWN(addr) + i;
 
 	xen_auto_xlat_grant_frames.vaddr = vaddr;
 	xen_auto_xlat_grant_frames.pfn = pfn;
@@ -687,7 +687,7 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages)
 	int i;
 	int ret;
 
-	ret = alloc_xenballooned_pages(nr_pages, pages, false);
+	ret = alloc_xenballooned_pages(nr_pages, pages);
 	if (ret < 0)
 		return ret;
 
@@ -776,6 +776,54 @@ void gnttab_batch_copy(struct gnttab_copy *batch, unsigned count)
 }
 EXPORT_SYMBOL_GPL(gnttab_batch_copy);
 
+void gnttab_foreach_grant_in_range(struct page *page,
+				   unsigned int offset,
+				   unsigned int len,
+				   xen_grant_fn_t fn,
+				   void *data)
+{
+	unsigned int goffset;
+	unsigned int glen;
+	unsigned long xen_pfn;
+
+	len = min_t(unsigned int, PAGE_SIZE - offset, len);
+	goffset = xen_offset_in_page(offset);
+
+	xen_pfn = page_to_xen_pfn(page) + XEN_PFN_DOWN(offset);
+
+	while (len) {
+		glen = min_t(unsigned int, XEN_PAGE_SIZE - goffset, len);
+		fn(pfn_to_gfn(xen_pfn), goffset, glen, data);
+
+		goffset = 0;
+		xen_pfn++;
+		len -= glen;
+	}
+}
+EXPORT_SYMBOL_GPL(gnttab_foreach_grant_in_range);
+
+void gnttab_foreach_grant(struct page **pages,
+			  unsigned int nr_grefs,
+			  xen_grant_fn_t fn,
+			  void *data)
+{
+	unsigned int goffset = 0;
+	unsigned long xen_pfn = 0;
+	unsigned int i;
+
+	for (i = 0; i < nr_grefs; i++) {
+		if ((i % XEN_PFN_PER_PAGE) == 0) {
+			xen_pfn = page_to_xen_pfn(pages[i / XEN_PFN_PER_PAGE]);
+			goffset = 0;
+		}
+
+		fn(pfn_to_gfn(xen_pfn), goffset, XEN_PAGE_SIZE, data);
+
+		goffset += XEN_PAGE_SIZE;
+		xen_pfn++;
+	}
+}
+
 int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		    struct gnttab_map_grant_ref *kmap_ops,
 		    struct page **pages, unsigned int count)
@@ -978,7 +1026,7 @@ static void gnttab_request_version(void)
 {
 	/* Only version 1 is used, which will always be available. */
 	grant_table_version = 1;
-	grefs_per_grant_frame = PAGE_SIZE / sizeof(struct grant_entry_v1);
+	grefs_per_grant_frame = XEN_PAGE_SIZE / sizeof(struct grant_entry_v1);
 	gnttab_interface = &gnttab_v1_ops;
 
 	pr_info("Grant tables using version %d layout\n", grant_table_version);

drivers/xen/privcmd.c

@@ -401,7 +401,7 @@ static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs)
 	if (pages == NULL)
 		return -ENOMEM;
 
-	rc = alloc_xenballooned_pages(numpgs, pages, 0);
+	rc = alloc_xenballooned_pages(numpgs, pages);
 	if (rc != 0) {
 		pr_warn("%s Could not alloc %d pfns rc:%d\n", __func__,
 			numpgs, rc);
@@ -446,7 +446,7 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
 		return -EINVAL;
 	}
 
-	nr_pages = m.num;
+	nr_pages = DIV_ROUND_UP(m.num, XEN_PFN_PER_PAGE);
 	if ((m.num <= 0) || (nr_pages > (LONG_MAX >> PAGE_SHIFT)))
 		return -EINVAL;
 
@@ -494,7 +494,7 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
 			goto out_unlock;
 		}
 		if (xen_feature(XENFEAT_auto_translated_physmap)) {
-			ret = alloc_empty_pages(vma, m.num);
+			ret = alloc_empty_pages(vma, nr_pages);
 			if (ret < 0)
 				goto out_unlock;
 		} else
@@ -518,6 +518,7 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
 	state.global_error  = 0;
 	state.version       = version;
 
+	BUILD_BUG_ON(((PAGE_SIZE / sizeof(xen_pfn_t)) % XEN_PFN_PER_PAGE) != 0);
 	/* mmap_batch_fn guarantees ret == 0 */
 	BUG_ON(traverse_pages_block(m.num, sizeof(xen_pfn_t),
 				    &pagelist, mmap_batch_fn, &state));
@@ -582,12 +583,13 @@ static void privcmd_close(struct vm_area_struct *vma)
 {
 	struct page **pages = vma->vm_private_data;
 	int numpgs = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	int numgfns = (vma->vm_end - vma->vm_start) >> XEN_PAGE_SHIFT;
 	int rc;
 
 	if (!xen_feature(XENFEAT_auto_translated_physmap) || !numpgs || !pages)
 		return;
 
-	rc = xen_unmap_domain_gfn_range(vma, numpgs, pages);
+	rc = xen_unmap_domain_gfn_range(vma, numgfns, pages);
 	if (rc == 0)
 		free_xenballooned_pages(numpgs, pages);
 	else

drivers/xen/swiotlb-xen.c

@@ -76,27 +76,27 @@ static unsigned long xen_io_tlb_nslabs;
 static u64 start_dma_addr;
 
 /*
- * Both of these functions should avoid PFN_PHYS because phys_addr_t
+ * Both of these functions should avoid XEN_PFN_PHYS because phys_addr_t
  * can be 32bit when dma_addr_t is 64bit leading to a loss in
  * information if the shift is done before casting to 64bit.
  */
 static inline dma_addr_t xen_phys_to_bus(phys_addr_t paddr)
 {
-	unsigned long bfn = pfn_to_bfn(PFN_DOWN(paddr));
+	unsigned long bfn = pfn_to_bfn(XEN_PFN_DOWN(paddr));
-	dma_addr_t dma = (dma_addr_t)bfn << PAGE_SHIFT;
+	dma_addr_t dma = (dma_addr_t)bfn << XEN_PAGE_SHIFT;
 
-	dma |= paddr & ~PAGE_MASK;
+	dma |= paddr & ~XEN_PAGE_MASK;
 
 	return dma;
 }
 
 static inline phys_addr_t xen_bus_to_phys(dma_addr_t baddr)
 {
-	unsigned long pfn = bfn_to_pfn(PFN_DOWN(baddr));
+	unsigned long xen_pfn = bfn_to_pfn(XEN_PFN_DOWN(baddr));
-	dma_addr_t dma = (dma_addr_t)pfn << PAGE_SHIFT;
+	dma_addr_t dma = (dma_addr_t)xen_pfn << XEN_PAGE_SHIFT;
 	phys_addr_t paddr = dma;
 
-	paddr |= baddr & ~PAGE_MASK;
+	paddr |= baddr & ~XEN_PAGE_MASK;
 
 	return paddr;
 }
@@ -106,7 +106,7 @@ static inline dma_addr_t xen_virt_to_bus(void *address)
 	return xen_phys_to_bus(virt_to_phys(address));
 }
 
-static int check_pages_physically_contiguous(unsigned long pfn,
+static int check_pages_physically_contiguous(unsigned long xen_pfn,
 					     unsigned int offset,
 					     size_t length)
 {
@@ -114,11 +114,11 @@ static int check_pages_physically_contiguous(unsigned long pfn,
 	int i;
 	int nr_pages;
 
-	next_bfn = pfn_to_bfn(pfn);
+	next_bfn = pfn_to_bfn(xen_pfn);
-	nr_pages = (offset + length + PAGE_SIZE-1) >> PAGE_SHIFT;
+	nr_pages = (offset + length + XEN_PAGE_SIZE-1) >> XEN_PAGE_SHIFT;
 
 	for (i = 1; i < nr_pages; i++) {
-		if (pfn_to_bfn(++pfn) != ++next_bfn)
+		if (pfn_to_bfn(++xen_pfn) != ++next_bfn)
 			return 0;
 	}
 	return 1;
@@ -126,28 +126,27 @@ static int check_pages_physically_contiguous(unsigned long pfn,
 
 static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
 {
-	unsigned long pfn = PFN_DOWN(p);
+	unsigned long xen_pfn = XEN_PFN_DOWN(p);
-	unsigned int offset = p & ~PAGE_MASK;
+	unsigned int offset = p & ~XEN_PAGE_MASK;
 
-	if (offset + size <= PAGE_SIZE)
+	if (offset + size <= XEN_PAGE_SIZE)
 		return 0;
-	if (check_pages_physically_contiguous(pfn, offset, size))
+	if (check_pages_physically_contiguous(xen_pfn, offset, size))
 		return 0;
 	return 1;
 }
 
 static int is_xen_swiotlb_buffer(dma_addr_t dma_addr)
 {
-	unsigned long bfn = PFN_DOWN(dma_addr);
+	unsigned long bfn = XEN_PFN_DOWN(dma_addr);
-	unsigned long pfn = bfn_to_local_pfn(bfn);
+	unsigned long xen_pfn = bfn_to_local_pfn(bfn);
-	phys_addr_t paddr;
+	phys_addr_t paddr = XEN_PFN_PHYS(xen_pfn);
 
 	/* If the address is outside our domain, it CAN
 	 * have the same virtual address as another address
 	 * in our domain. Therefore _only_ check address within our domain.
 	 */
-	if (pfn_valid(pfn)) {
+	if (pfn_valid(PFN_DOWN(paddr))) {
-		paddr = PFN_PHYS(pfn);
 		return paddr >= virt_to_phys(xen_io_tlb_start) &&
 		       paddr < virt_to_phys(xen_io_tlb_end);
 	}
@@ -392,7 +391,7 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 */
 	if (dma_capable(dev, dev_addr, size) &&
 	    !range_straddles_page_boundary(phys, size) &&
-		!xen_arch_need_swiotlb(dev, PFN_DOWN(phys), PFN_DOWN(dev_addr)) &&
+		!xen_arch_need_swiotlb(dev, phys, dev_addr) &&
 		!swiotlb_force) {
 		/* we are not interested in the dma_addr returned by
 		 * xen_dma_map_page, only in the potential cache flushes executed
@@ -551,7 +550,7 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 		dma_addr_t dev_addr = xen_phys_to_bus(paddr);
 
 		if (swiotlb_force ||
-		    xen_arch_need_swiotlb(hwdev, PFN_DOWN(paddr), PFN_DOWN(dev_addr)) ||
+		    xen_arch_need_swiotlb(hwdev, paddr, dev_addr) ||
 		    !dma_capable(hwdev, dev_addr, sg->length) ||
 		    range_straddles_page_boundary(paddr, sg->length)) {
 			phys_addr_t map = swiotlb_tbl_map_single(hwdev,

drivers/xen/xenbus/xenbus_client.c

@@ -49,6 +49,10 @@
 
 #include "xenbus_probe.h"
 
+#define XENBUS_PAGES(_grants)	(DIV_ROUND_UP(_grants, XEN_PFN_PER_PAGE))
+
+#define XENBUS_MAX_RING_PAGES	(XENBUS_PAGES(XENBUS_MAX_RING_GRANTS))
+
 struct xenbus_map_node {
 	struct list_head next;
 	union {
@@ -57,10 +61,11 @@ struct xenbus_map_node {
 		} pv;
 		struct {
 			struct page *pages[XENBUS_MAX_RING_PAGES];
+			unsigned long addrs[XENBUS_MAX_RING_GRANTS];
 			void *addr;
 		} hvm;
 	};
-	grant_handle_t handles[XENBUS_MAX_RING_PAGES];
+	grant_handle_t handles[XENBUS_MAX_RING_GRANTS];
 	unsigned int   nr_handles;
 };
 
@@ -388,7 +393,7 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr,
 		}
 		grefs[i] = err;
 
-		vaddr = vaddr + PAGE_SIZE;
+		vaddr = vaddr + XEN_PAGE_SIZE;
 	}
 
 	return 0;
@@ -479,12 +484,12 @@ static int __xenbus_map_ring(struct xenbus_device *dev,
 			     unsigned int flags,
 			     bool *leaked)
 {
-	struct gnttab_map_grant_ref map[XENBUS_MAX_RING_PAGES];
+	struct gnttab_map_grant_ref map[XENBUS_MAX_RING_GRANTS];
-	struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_PAGES];
+	struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_GRANTS];
 	int i, j;
 	int err = GNTST_okay;
 
-	if (nr_grefs > XENBUS_MAX_RING_PAGES)
+	if (nr_grefs > XENBUS_MAX_RING_GRANTS)
 		return -EINVAL;
 
 	for (i = 0; i < nr_grefs; i++) {
@@ -540,22 +545,22 @@ static int xenbus_map_ring_valloc_pv(struct xenbus_device *dev,
 {
 	struct xenbus_map_node *node;
 	struct vm_struct *area;
-	pte_t *ptes[XENBUS_MAX_RING_PAGES];
+	pte_t *ptes[XENBUS_MAX_RING_GRANTS];
-	phys_addr_t phys_addrs[XENBUS_MAX_RING_PAGES];
+	phys_addr_t phys_addrs[XENBUS_MAX_RING_GRANTS];
 	int err = GNTST_okay;
 	int i;
 	bool leaked;
 
 	*vaddr = NULL;
 
-	if (nr_grefs > XENBUS_MAX_RING_PAGES)
+	if (nr_grefs > XENBUS_MAX_RING_GRANTS)
 		return -EINVAL;
 
 	node = kzalloc(sizeof(*node), GFP_KERNEL);
 	if (!node)
 		return -ENOMEM;
 
-	area = alloc_vm_area(PAGE_SIZE * nr_grefs, ptes);
+	area = alloc_vm_area(XEN_PAGE_SIZE * nr_grefs, ptes);
 	if (!area) {
 		kfree(node);
 		return -ENOMEM;
@@ -591,21 +596,44 @@ failed:
 	return err;
 }
 
+struct map_ring_valloc_hvm
+{
+	unsigned int idx;
+
+	/* Why do we need two arrays? See comment of __xenbus_map_ring */
+	phys_addr_t phys_addrs[XENBUS_MAX_RING_GRANTS];
+	unsigned long addrs[XENBUS_MAX_RING_GRANTS];
+};
+
+static void xenbus_map_ring_setup_grant_hvm(unsigned long gfn,
+					    unsigned int goffset,
+					    unsigned int len,
+					    void *data)
+{
+	struct map_ring_valloc_hvm *info = data;
+	unsigned long vaddr = (unsigned long)gfn_to_virt(gfn);
+
+	info->phys_addrs[info->idx] = vaddr;
+	info->addrs[info->idx] = vaddr;
+
+	info->idx++;
+}
+
 static int xenbus_map_ring_valloc_hvm(struct xenbus_device *dev,
 				      grant_ref_t *gnt_ref,
 				      unsigned int nr_grefs,
 				      void **vaddr)
 {
 	struct xenbus_map_node *node;
-	int i;
 	int err;
 	void *addr;
 	bool leaked = false;
-	/* Why do we need two arrays? See comment of __xenbus_map_ring */
+	struct map_ring_valloc_hvm info = {
-	phys_addr_t phys_addrs[XENBUS_MAX_RING_PAGES];
+		.idx = 0,
-	unsigned long addrs[XENBUS_MAX_RING_PAGES];
+	};
+	unsigned int nr_pages = XENBUS_PAGES(nr_grefs);
 
-	if (nr_grefs > XENBUS_MAX_RING_PAGES)
+	if (nr_grefs > XENBUS_MAX_RING_GRANTS)
 		return -EINVAL;
 
 	*vaddr = NULL;
@@ -614,25 +642,22 @@ static int xenbus_map_ring_valloc_hvm(struct xenbus_device *dev,
 	if (!node)
 		return -ENOMEM;
 
-	err = alloc_xenballooned_pages(nr_grefs, node->hvm.pages,
+	err = alloc_xenballooned_pages(nr_pages, node->hvm.pages);
-				       false /* lowmem */);
 	if (err)
 		goto out_err;
 
-	for (i = 0; i < nr_grefs; i++) {
+	gnttab_foreach_grant(node->hvm.pages, nr_grefs,
-		unsigned long pfn = page_to_pfn(node->hvm.pages[i]);
+			     xenbus_map_ring_setup_grant_hvm,
-		phys_addrs[i] = (unsigned long)pfn_to_kaddr(pfn);
+			     &info);
-		addrs[i] = (unsigned long)pfn_to_kaddr(pfn);
-	}
 
 	err = __xenbus_map_ring(dev, gnt_ref, nr_grefs, node->handles,
-				phys_addrs, GNTMAP_host_map, &leaked);
+				info.phys_addrs, GNTMAP_host_map, &leaked);
 	node->nr_handles = nr_grefs;
 
 	if (err)
 		goto out_free_ballooned_pages;
 
-	addr = vmap(node->hvm.pages, nr_grefs, VM_MAP | VM_IOREMAP,
+	addr = vmap(node->hvm.pages, nr_pages, VM_MAP | VM_IOREMAP,
 		    PAGE_KERNEL);
 	if (!addr) {
 		err = -ENOMEM;
@@ -650,14 +675,13 @@ static int xenbus_map_ring_valloc_hvm(struct xenbus_device *dev,
 
  out_xenbus_unmap_ring:
 	if (!leaked)
-		xenbus_unmap_ring(dev, node->handles, node->nr_handles,
+		xenbus_unmap_ring(dev, node->handles, nr_grefs, info.addrs);
-				  addrs);
 	else
 		pr_alert("leaking %p size %u page(s)",
-			 addr, nr_grefs);
+			 addr, nr_pages);
  out_free_ballooned_pages:
 	if (!leaked)
-		free_xenballooned_pages(nr_grefs, node->hvm.pages);
+		free_xenballooned_pages(nr_pages, node->hvm.pages);
  out_err:
 	kfree(node);
 	return err;
@@ -687,10 +711,10 @@ int xenbus_map_ring(struct xenbus_device *dev, grant_ref_t *gnt_refs,
 		    unsigned int nr_grefs, grant_handle_t *handles,
 		    unsigned long *vaddrs, bool *leaked)
 {
-	phys_addr_t phys_addrs[XENBUS_MAX_RING_PAGES];
+	phys_addr_t phys_addrs[XENBUS_MAX_RING_GRANTS];
 	int i;
 
-	if (nr_grefs > XENBUS_MAX_RING_PAGES)
+	if (nr_grefs > XENBUS_MAX_RING_GRANTS)
 		return -EINVAL;
 
 	for (i = 0; i < nr_grefs; i++)
@@ -723,7 +747,7 @@ EXPORT_SYMBOL_GPL(xenbus_unmap_ring_vfree);
 static int xenbus_unmap_ring_vfree_pv(struct xenbus_device *dev, void *vaddr)
 {
 	struct xenbus_map_node *node;
-	struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_PAGES];
+	struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_GRANTS];
 	unsigned int level;
 	int i;
 	bool leaked = false;
@@ -750,7 +774,7 @@ static int xenbus_unmap_ring_vfree_pv(struct xenbus_device *dev, void *vaddr)
 		unsigned long addr;
 
 		memset(&unmap[i], 0, sizeof(unmap[i]));
-		addr = (unsigned long)vaddr + (PAGE_SIZE * i);
+		addr = (unsigned long)vaddr + (XEN_PAGE_SIZE * i);
 		unmap[i].host_addr = arbitrary_virt_to_machine(
 			lookup_address(addr, &level)).maddr;
 		unmap[i].dev_bus_addr = 0;
@@ -783,13 +807,33 @@ static int xenbus_unmap_ring_vfree_pv(struct xenbus_device *dev, void *vaddr)
 	return err;
 }
 
+struct unmap_ring_vfree_hvm
+{
+	unsigned int idx;
+	unsigned long addrs[XENBUS_MAX_RING_GRANTS];
+};
+
+static void xenbus_unmap_ring_setup_grant_hvm(unsigned long gfn,
+					      unsigned int goffset,
+					      unsigned int len,
+					      void *data)
+{
+	struct unmap_ring_vfree_hvm *info = data;
+
+	info->addrs[info->idx] = (unsigned long)gfn_to_virt(gfn);
+
+	info->idx++;
+}
+
 static int xenbus_unmap_ring_vfree_hvm(struct xenbus_device *dev, void *vaddr)
 {
 	int rv;
 	struct xenbus_map_node *node;
 	void *addr;
-	unsigned long addrs[XENBUS_MAX_RING_PAGES];
+	struct unmap_ring_vfree_hvm info = {
-	int i;
+		.idx = 0,
+	};
+	unsigned int nr_pages;
 
 	spin_lock(&xenbus_valloc_lock);
 	list_for_each_entry(node, &xenbus_valloc_pages, next) {
@@ -809,18 +853,20 @@ static int xenbus_unmap_ring_vfree_hvm(struct xenbus_device *dev, void *vaddr)
 		return GNTST_bad_virt_addr;
 	}
 
-	for (i = 0; i < node->nr_handles; i++)
+	nr_pages = XENBUS_PAGES(node->nr_handles);
-		addrs[i] = (unsigned long)pfn_to_kaddr(page_to_pfn(node->hvm.pages[i]));
+
+	gnttab_foreach_grant(node->hvm.pages, node->nr_handles,
+			     xenbus_unmap_ring_setup_grant_hvm,
+			     &info);
 
 	rv = xenbus_unmap_ring(dev, node->handles, node->nr_handles,
-			       addrs);
+			       info.addrs);
 	if (!rv) {
 		vunmap(vaddr);
-		free_xenballooned_pages(node->nr_handles, node->hvm.pages);
+		free_xenballooned_pages(nr_pages, node->hvm.pages);
 	}
 	else
-		WARN(1, "Leaking %p, size %u page(s)\n", vaddr,
+		WARN(1, "Leaking %p, size %u page(s)\n", vaddr, nr_pages);
-		     node->nr_handles);
 
 	kfree(node);
 	return rv;
@@ -841,11 +887,11 @@ int xenbus_unmap_ring(struct xenbus_device *dev,
 		      grant_handle_t *handles, unsigned int nr_handles,
 		      unsigned long *vaddrs)
 {
-	struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_PAGES];
+	struct gnttab_unmap_grant_ref unmap[XENBUS_MAX_RING_GRANTS];
 	int i;
 	int err;
 
-	if (nr_handles > XENBUS_MAX_RING_PAGES)
+	if (nr_handles > XENBUS_MAX_RING_GRANTS)
 		return -EINVAL;
 
 	for (i = 0; i < nr_handles; i++)

drivers/xen/xenbus/xenbus_probe.c

@@ -802,7 +802,8 @@ static int __init xenbus_init(void)
 			goto out_error;
 		xen_store_gfn = (unsigned long)v;
 		xen_store_interface =
-			xen_remap(xen_store_gfn << PAGE_SHIFT, PAGE_SIZE);
+			xen_remap(xen_store_gfn << XEN_PAGE_SHIFT,
+				  XEN_PAGE_SIZE);
 		break;
 	default:
 		pr_warn("Xenstore state unknown\n");

drivers/xen/xlate_mmu.c

@@ -38,31 +38,28 @@
 #include <xen/interface/xen.h>
 #include <xen/interface/memory.h>
 
-/* map fgfn of domid to lpfn in the current domain */
+typedef void (*xen_gfn_fn_t)(unsigned long gfn, void *data);
-static int map_foreign_page(unsigned long lpfn, unsigned long fgfn,
+
-			    unsigned int domid)
+/* Break down the pages in 4KB chunk and call fn for each gfn */
+static void xen_for_each_gfn(struct page **pages, unsigned nr_gfn,
+			     xen_gfn_fn_t fn, void *data)
 {
-	int rc;
+	unsigned long xen_pfn = 0;
-	struct xen_add_to_physmap_range xatp = {
+	struct page *page;
-		.domid = DOMID_SELF,
+	int i;
-		.foreign_domid = domid,
-		.size = 1,
-		.space = XENMAPSPACE_gmfn_foreign,
-	};
-	xen_ulong_t idx = fgfn;
-	xen_pfn_t gpfn = lpfn;
-	int err = 0;
 
-	set_xen_guest_handle(xatp.idxs, &idx);
+	for (i = 0; i < nr_gfn; i++) {
-	set_xen_guest_handle(xatp.gpfns, &gpfn);
+		if ((i % XEN_PFN_PER_PAGE) == 0) {
-	set_xen_guest_handle(xatp.errs, &err);
+			page = pages[i / XEN_PFN_PER_PAGE];
-
+			xen_pfn = page_to_xen_pfn(page);
-	rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp);
+		}
-	return rc < 0 ? rc : err;
+		fn(pfn_to_gfn(xen_pfn++), data);
+	}
 }
 
 struct remap_data {
 	xen_pfn_t *fgfn; /* foreign domain's gfn */
+	int nr_fgfn; /* Number of foreign gfn left to map */
 	pgprot_t prot;
 	domid_t  domid;
 	struct vm_area_struct *vma;
@@ -71,24 +68,71 @@ struct remap_data {
 	struct xen_remap_gfn_info *info;
 	int *err_ptr;
 	int mapped;
+
+	/* Hypercall parameters */
+	int h_errs[XEN_PFN_PER_PAGE];
+	xen_ulong_t h_idxs[XEN_PFN_PER_PAGE];
+	xen_pfn_t h_gpfns[XEN_PFN_PER_PAGE];
+
+	int h_iter;	/* Iterator */
 };
 
+static void setup_hparams(unsigned long gfn, void *data)
+{
+	struct remap_data *info = data;
+
+	info->h_idxs[info->h_iter] = *info->fgfn;
+	info->h_gpfns[info->h_iter] = gfn;
+	info->h_errs[info->h_iter] = 0;
+
+	info->h_iter++;
+	info->fgfn++;
+}
+
 static int remap_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr,
 			void *data)
 {
 	struct remap_data *info = data;
 	struct page *page = info->pages[info->index++];
-	unsigned long pfn = page_to_pfn(page);
+	pte_t pte = pte_mkspecial(pfn_pte(page_to_pfn(page), info->prot));
-	pte_t pte = pte_mkspecial(pfn_pte(pfn, info->prot));
+	int rc, nr_gfn;
-	int rc;
+	uint32_t i;
+	struct xen_add_to_physmap_range xatp = {
+		.domid = DOMID_SELF,
+		.foreign_domid = info->domid,
+		.space = XENMAPSPACE_gmfn_foreign,
+	};
 
-	rc = map_foreign_page(pfn, *info->fgfn, info->domid);
+	nr_gfn = min_t(typeof(info->nr_fgfn), XEN_PFN_PER_PAGE, info->nr_fgfn);
-	*info->err_ptr++ = rc;
+	info->nr_fgfn -= nr_gfn;
-	if (!rc) {
+
-		set_pte_at(info->vma->vm_mm, addr, ptep, pte);
+	info->h_iter = 0;
-		info->mapped++;
+	xen_for_each_gfn(&page, nr_gfn, setup_hparams, info);
+	BUG_ON(info->h_iter != nr_gfn);
+
+	set_xen_guest_handle(xatp.idxs, info->h_idxs);
+	set_xen_guest_handle(xatp.gpfns, info->h_gpfns);
+	set_xen_guest_handle(xatp.errs, info->h_errs);
+	xatp.size = nr_gfn;
+
+	rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp);
+
+	/* info->err_ptr expect to have one error status per Xen PFN */
+	for (i = 0; i < nr_gfn; i++) {
+		int err = (rc < 0) ? rc : info->h_errs[i];
+
+		*(info->err_ptr++) = err;
+		if (!err)
+			info->mapped++;
 	}
-	info->fgfn++;
+
+	/*
+	 * Note: The hypercall will return 0 in most of the case if even if
+	 * all the fgmfn are not mapped. We still have to update the pte
+	 * as the userspace may decide to continue.
+	 */
+	if (!rc)
+		set_pte_at(info->vma->vm_mm, addr, ptep, pte);
 
 	return 0;
 }
@@ -102,13 +146,14 @@ int xen_xlate_remap_gfn_array(struct vm_area_struct *vma,
 {
 	int err;
 	struct remap_data data;
-	unsigned long range = nr << PAGE_SHIFT;
+	unsigned long range = DIV_ROUND_UP(nr, XEN_PFN_PER_PAGE) << PAGE_SHIFT;
 
 	/* Kept here for the purpose of making sure code doesn't break
 	   x86 PVOPS */
 	BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO)));
 
 	data.fgfn = gfn;
+	data.nr_fgfn = nr;
 	data.prot  = prot;
 	data.domid = domid;
 	data.vma   = vma;
@@ -123,21 +168,20 @@ int xen_xlate_remap_gfn_array(struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(xen_xlate_remap_gfn_array);
 
+static void unmap_gfn(unsigned long gfn, void *data)
+{
+	struct xen_remove_from_physmap xrp;
+
+	xrp.domid = DOMID_SELF;
+	xrp.gpfn = gfn;
+	(void)HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp);
+}
+
 int xen_xlate_unmap_gfn_range(struct vm_area_struct *vma,
 			      int nr, struct page **pages)
 {
-	int i;
+	xen_for_each_gfn(pages, nr, unmap_gfn, NULL);
 
-	for (i = 0; i < nr; i++) {
-		struct xen_remove_from_physmap xrp;
-		unsigned long pfn;
-
-		pfn = page_to_pfn(pages[i]);
-
-		xrp.domid = DOMID_SELF;
-		xrp.gpfn = pfn;
-		(void)HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp);
-	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xen_xlate_unmap_gfn_range);

include/linux/memory_hotplug.h

@@ -11,6 +11,7 @@ struct zone;
 struct pglist_data;
 struct mem_section;
 struct memory_block;
+struct resource;
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 
@@ -266,6 +267,7 @@ static inline void remove_memory(int nid, u64 start, u64 size) {}
 extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
 		void *arg, int (*func)(struct memory_block *, void *));
 extern int add_memory(int nid, u64 start, u64 size);
+extern int add_memory_resource(int nid, struct resource *resource);
 extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default,
 		bool for_device);
 extern int arch_add_memory(int nid, u64 start, u64 size, bool for_device);

include/uapi/xen/gntalloc.h

@@ -11,6 +11,8 @@
 #ifndef __LINUX_PUBLIC_GNTALLOC_H__
 #define __LINUX_PUBLIC_GNTALLOC_H__
 
+#include <linux/types.h>
+
 /*
  * Allocates a new page and creates a new grant reference.
  */
@@ -19,17 +21,17 @@ _IOC(_IOC_NONE, 'G', 5, sizeof(struct ioctl_gntalloc_alloc_gref))
 struct ioctl_gntalloc_alloc_gref {
 	/* IN parameters */
 	/* The ID of the domain to be given access to the grants. */
-	uint16_t domid;
+	__u16 domid;
 	/* Flags for this mapping */
-	uint16_t flags;
+	__u16 flags;
 	/* Number of pages to map */
-	uint32_t count;
+	__u32 count;
 	/* OUT parameters */
 	/* The offset to be used on a subsequent call to mmap(). */
-	uint64_t index;
+	__u64 index;
 	/* The grant references of the newly created grant, one per page */
 	/* Variable size, depending on count */
-	uint32_t gref_ids[1];
+	__u32 gref_ids[1];
 };
 
 #define GNTALLOC_FLAG_WRITABLE 1
@@ -43,9 +45,9 @@ _IOC(_IOC_NONE, 'G', 6, sizeof(struct ioctl_gntalloc_dealloc_gref))
 struct ioctl_gntalloc_dealloc_gref {
 	/* IN parameters */
 	/* The offset returned in the map operation */
-	uint64_t index;
+	__u64 index;
 	/* Number of references to unmap */
-	uint32_t count;
+	__u32 count;
 };
 
 /*
@@ -67,11 +69,11 @@ struct ioctl_gntalloc_unmap_notify {
 	 * be cleared. Otherwise, it can be any byte in the page whose
 	 * notification we are adjusting.
 	 */
-	uint64_t index;
+	__u64 index;
 	/* Action(s) to take on unmap */
-	uint32_t action;
+	__u32 action;
 	/* Event channel to notify */
-	uint32_t event_channel_port;
+	__u32 event_channel_port;
 };
 
 /* Clear (set to zero) the byte specified by index */

include/uapi/xen/gntdev.h

@@ -33,11 +33,13 @@
 #ifndef __LINUX_PUBLIC_GNTDEV_H__
 #define __LINUX_PUBLIC_GNTDEV_H__
 
+#include <linux/types.h>
+
 struct ioctl_gntdev_grant_ref {
 	/* The domain ID of the grant to be mapped. */
-	uint32_t domid;
+	__u32 domid;
 	/* The grant reference of the grant to be mapped. */
-	uint32_t ref;
+	__u32 ref;
 };
 
 /*
@@ -50,11 +52,11 @@ _IOC(_IOC_NONE, 'G', 0, sizeof(struct ioctl_gntdev_map_grant_ref))
 struct ioctl_gntdev_map_grant_ref {
 	/* IN parameters */
 	/* The number of grants to be mapped. */
-	uint32_t count;
+	__u32 count;
-	uint32_t pad;
+	__u32 pad;
 	/* OUT parameters */
 	/* The offset to be used on a subsequent call to mmap(). */
-	uint64_t index;
+	__u64 index;
 	/* Variable IN parameter. */
 	/* Array of grant references, of size @count. */
 	struct ioctl_gntdev_grant_ref refs[1];
@@ -70,10 +72,10 @@ _IOC(_IOC_NONE, 'G', 1, sizeof(struct ioctl_gntdev_unmap_grant_ref))
 struct ioctl_gntdev_unmap_grant_ref {
 	/* IN parameters */
 	/* The offset was returned by the corresponding map operation. */
-	uint64_t index;
+	__u64 index;
 	/* The number of pages to be unmapped. */
-	uint32_t count;
+	__u32 count;
-	uint32_t pad;
+	__u32 pad;
 };
 
 /*
@@ -93,13 +95,13 @@ _IOC(_IOC_NONE, 'G', 2, sizeof(struct ioctl_gntdev_get_offset_for_vaddr))
 struct ioctl_gntdev_get_offset_for_vaddr {
 	/* IN parameters */
 	/* The virtual address of the first mapped page in a range. */
-	uint64_t vaddr;
+	__u64 vaddr;
 	/* OUT parameters */
 	/* The offset that was used in the initial mmap() operation. */
-	uint64_t offset;
+	__u64 offset;
 	/* The number of pages mapped in the VM area that begins at @vaddr. */
-	uint32_t count;
+	__u32 count;
-	uint32_t pad;
+	__u32 pad;
 };
 
 /*
@@ -113,7 +115,7 @@ _IOC(_IOC_NONE, 'G', 3, sizeof(struct ioctl_gntdev_set_max_grants))
 struct ioctl_gntdev_set_max_grants {
 	/* IN parameter */
 	/* The maximum number of grants that may be mapped at once. */
-	uint32_t count;
+	__u32 count;
 };
 
 /*
@@ -135,11 +137,11 @@ struct ioctl_gntdev_unmap_notify {
 	 * be cleared. Otherwise, it can be any byte in the page whose
 	 * notification we are adjusting.
 	 */
-	uint64_t index;
+	__u64 index;
 	/* Action(s) to take on unmap */
-	uint32_t action;
+	__u32 action;
 	/* Event channel to notify */
-	uint32_t event_channel_port;
+	__u32 event_channel_port;
 };
 
 /* Clear (set to zero) the byte specified by index */

include/xen/balloon.h

@@ -8,30 +8,24 @@ struct balloon_stats {
 	/* We aim for 'current allocation' == 'target allocation'. */
 	unsigned long current_pages;
 	unsigned long target_pages;
+	unsigned long target_unpopulated;
 	/* Number of pages in high- and low-memory balloons. */
 	unsigned long balloon_low;
 	unsigned long balloon_high;
+	unsigned long total_pages;
 	unsigned long schedule_delay;
 	unsigned long max_schedule_delay;
 	unsigned long retry_count;
 	unsigned long max_retry_count;
-#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
-	unsigned long hotplug_pages;
-	unsigned long balloon_hotplug;
-#endif
 };
 
 extern struct balloon_stats balloon_stats;
 
 void balloon_set_new_target(unsigned long target);
 
-int alloc_xenballooned_pages(int nr_pages, struct page **pages,
+int alloc_xenballooned_pages(int nr_pages, struct page **pages);
-		bool highmem);
 void free_xenballooned_pages(int nr_pages, struct page **pages);
 
-struct page *get_balloon_scratch_page(void);
-void put_balloon_scratch_page(void);
-
 struct device;
 #ifdef CONFIG_XEN_SELFBALLOONING
 extern int register_xen_selfballooning(struct device *dev);

include/xen/grant_table.h

@@ -45,8 +45,10 @@
 #include <asm/xen/hypervisor.h>
 
 #include <xen/features.h>
+#include <xen/page.h>
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
+#include <linux/kernel.h>
 
 #define GNTTAB_RESERVED_XENSTORE 1
 
@@ -129,6 +131,15 @@ void gnttab_cancel_free_callback(struct gnttab_free_callback *callback);
 void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid,
 				     unsigned long frame, int readonly);
 
+/* Give access to the first 4K of the page */
+static inline void gnttab_page_grant_foreign_access_ref_one(
+	grant_ref_t ref, domid_t domid,
+	struct page *page, int readonly)
+{
+	gnttab_grant_foreign_access_ref(ref, domid, xen_page_to_gfn(page),
+					readonly);
+}
+
 void gnttab_grant_foreign_transfer_ref(grant_ref_t, domid_t domid,
 				       unsigned long pfn);
 
@@ -224,4 +235,50 @@ static inline struct xen_page_foreign *xen_page_foreign(struct page *page)
 #endif
 }
 
+/* Split Linux page in chunk of the size of the grant and call fn
+ *
+ * Parameters of fn:
+ *	gfn: guest frame number
+ *	offset: offset in the grant
+ *	len: length of the data in the grant.
+ *	data: internal information
+ */
+typedef void (*xen_grant_fn_t)(unsigned long gfn, unsigned int offset,
+			       unsigned int len, void *data);
+
+void gnttab_foreach_grant_in_range(struct page *page,
+				   unsigned int offset,
+				   unsigned int len,
+				   xen_grant_fn_t fn,
+				   void *data);
+
+/* Helper to get to call fn only on the first "grant chunk" */
+static inline void gnttab_for_one_grant(struct page *page, unsigned int offset,
+					unsigned len, xen_grant_fn_t fn,
+					void *data)
+{
+	/* The first request is limited to the size of one grant */
+	len = min_t(unsigned int, XEN_PAGE_SIZE - (offset & ~XEN_PAGE_MASK),
+		    len);
+
+	gnttab_foreach_grant_in_range(page, offset, len, fn, data);
+}
+
+/* Get @nr_grefs grants from an array of page and call fn for each grant */
+void gnttab_foreach_grant(struct page **pages,
+			  unsigned int nr_grefs,
+			  xen_grant_fn_t fn,
+			  void *data);
+
+/* Get the number of grant in a specified region
+ *
+ * start: Offset from the beginning of the first page
+ * len: total length of data (can cross multiple page)
+ */
+static inline unsigned int gnttab_count_grant(unsigned int start,
+					      unsigned int len)
+{
+	return XEN_PFN_UP(xen_offset_in_page(start) + len);
+}
+
 #endif /* __ASM_GNTTAB_H__ */

include/xen/page.h

@@ -1,11 +1,36 @@
 #ifndef _XEN_PAGE_H
 #define _XEN_PAGE_H
 
+#include <asm/page.h>
+
+/* The hypercall interface supports only 4KB page */
+#define XEN_PAGE_SHIFT	12
+#define XEN_PAGE_SIZE	(_AC(1, UL) << XEN_PAGE_SHIFT)
+#define XEN_PAGE_MASK	(~(XEN_PAGE_SIZE-1))
+#define xen_offset_in_page(p)	((unsigned long)(p) & ~XEN_PAGE_MASK)
+
+/*
+ * We assume that PAGE_SIZE is a multiple of XEN_PAGE_SIZE
+ * XXX: Add a BUILD_BUG_ON?
+ */
+
+#define xen_pfn_to_page(xen_pfn)	\
+	((pfn_to_page(((unsigned long)(xen_pfn) << XEN_PAGE_SHIFT) >> PAGE_SHIFT)))
+#define page_to_xen_pfn(page)		\
+	(((page_to_pfn(page)) << PAGE_SHIFT) >> XEN_PAGE_SHIFT)
+
+#define XEN_PFN_PER_PAGE	(PAGE_SIZE / XEN_PAGE_SIZE)
+
+#define XEN_PFN_DOWN(x)	((x) >> XEN_PAGE_SHIFT)
+#define XEN_PFN_UP(x)	(((x) + XEN_PAGE_SIZE-1) >> XEN_PAGE_SHIFT)
+#define XEN_PFN_PHYS(x)	((phys_addr_t)(x) << XEN_PAGE_SHIFT)
+
 #include <asm/xen/page.h>
 
+/* Return the GFN associated to the first 4KB of the page */
 static inline unsigned long xen_page_to_gfn(struct page *page)
 {
-	return pfn_to_gfn(page_to_pfn(page));
+	return pfn_to_gfn(page_to_xen_pfn(page));
 }
 
 struct xen_memory_region {

include/xen/xenbus.h

@@ -46,8 +46,8 @@
 #include <xen/interface/io/xenbus.h>
 #include <xen/interface/io/xs_wire.h>
 
-#define XENBUS_MAX_RING_PAGE_ORDER 4
+#define XENBUS_MAX_RING_GRANT_ORDER 4
-#define XENBUS_MAX_RING_PAGES      (1U << XENBUS_MAX_RING_PAGE_ORDER)
+#define XENBUS_MAX_RING_GRANTS      (1U << XENBUS_MAX_RING_GRANT_ORDER)
 #define INVALID_GRANT_HANDLE       (~0U)
 
 /* Register callback to watch this node. */

mm/memory_hotplug.c

@@ -1232,23 +1232,21 @@ int zone_for_memory(int nid, u64 start, u64 size, int zone_default,
 }
 
 /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
-int __ref add_memory(int nid, u64 start, u64 size)
+int __ref add_memory_resource(int nid, struct resource *res)
 {
+	u64 start, size;
 	pg_data_t *pgdat = NULL;
 	bool new_pgdat;
 	bool new_node;
-	struct resource *res;
 	int ret;
 
+	start = res->start;
+	size = resource_size(res);
+
 	ret = check_hotplug_memory_range(start, size);
 	if (ret)
 		return ret;
 
-	res = register_memory_resource(start, size);
-	ret = -EEXIST;
-	if (!res)
-		return ret;
-
 	{	/* Stupid hack to suppress address-never-null warning */
 		void *p = NODE_DATA(nid);
 		new_pgdat = !p;
@@ -1300,13 +1298,28 @@ error:
 	/* rollback pgdat allocation and others */
 	if (new_pgdat)
 		rollback_node_hotadd(nid, pgdat);
-	release_memory_resource(res);
 	memblock_remove(start, size);
 
 out:
 	mem_hotplug_done();
 	return ret;
 }
+EXPORT_SYMBOL_GPL(add_memory_resource);
+
+int __ref add_memory(int nid, u64 start, u64 size)
+{
+	struct resource *res;
+	int ret;
+
+	res = register_memory_resource(start, size);
+	if (!res)
+		return -EEXIST;
+
+	ret = add_memory_resource(nid, res);
+	if (ret < 0)
+		release_memory_resource(res);
+	return ret;
+}
 EXPORT_SYMBOL_GPL(add_memory);
 
 #ifdef CONFIG_MEMORY_HOTREMOVE