Merge branches 'stable/bug.fixes-3.2' and 'stable/mmu.fixes' of...

Merge branches 'stable/bug.fixes-3.2' and 'stable/mmu.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

* 'stable/bug.fixes-3.2' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  xen/p2m/debugfs: Make type_name more obvious.
  xen/p2m/debugfs: Fix potential pointer exception.
  xen/enlighten: Fix compile warnings and set cx to known value.
  xen/xenbus: Remove the unnecessary check.
  xen/irq: If we fail during msi_capability_init return proper error code.
  xen/events: Don't check the info for NULL as it is already done.
  xen/events: BUG() when we can't allocate our event->irq array.

* 'stable/mmu.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  xen: Fix selfballooning and ensure it doesn't go too far
  xen/gntdev: Fix sleep-inside-spinlock
  xen: modify kernel mappings corresponding to granted pages
  xen: add an "highmem" parameter to alloc_xenballooned_pages
  xen/p2m: Use SetPagePrivate and its friends for M2P overrides.
  xen/p2m: Make debug/xen/mmu/p2m visible again.
  Revert "xen/debug: WARN_ON when identity PFN has no _PAGE_IOMAP flag set."

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

@@ -12,6 +12,7 @@
 #include <asm/pgtable.h>
 
 #include <xen/interface/xen.h>
+#include <xen/grant_table.h>
 #include <xen/features.h>
 
 /* Xen machine address */
@@ -48,14 +49,11 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s,
 					     unsigned long pfn_e);
 
 extern int m2p_add_override(unsigned long mfn, struct page *page,
-			    bool clear_pte);
+			    struct gnttab_map_grant_ref *kmap_op);
 extern int m2p_remove_override(struct page *page, bool clear_pte);
 extern struct page *m2p_find_override(unsigned long mfn);
 extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
 
-#ifdef CONFIG_XEN_DEBUG_FS
-extern int p2m_dump_show(struct seq_file *m, void *v);
-#endif
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {
 	unsigned long mfn;

arch/x86/pci/xen.c

@@ -175,8 +175,10 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 					       "pcifront-msi-x" :
 					       "pcifront-msi",
 						DOMID_SELF);
-		if (irq < 0)
+		if (irq < 0) {
+			ret = irq;
 			goto free;
+		}
 		i++;
 	}
 	kfree(v);
@@ -221,8 +223,10 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		if (msg.data != XEN_PIRQ_MSI_DATA ||
 		    xen_irq_from_pirq(pirq) < 0) {
 			pirq = xen_allocate_pirq_msi(dev, msidesc);
-			if (pirq < 0)
+			if (pirq < 0) {
+				irq = -ENODEV;
 				goto error;
+			}
 			xen_msi_compose_msg(dev, pirq, &msg);
 			__write_msi_msg(msidesc, &msg);
 			dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
@@ -244,7 +248,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 error:
 	dev_err(&dev->dev,
 		"Xen PCI frontend has not registered MSI/MSI-X support!\n");
-	return -ENODEV;
+	return irq;
 }
 
 #ifdef CONFIG_XEN_DOM0

arch/x86/xen/Kconfig

@@ -49,11 +49,3 @@ config XEN_DEBUG_FS
 	help
 	  Enable statistics output and various tuning options in debugfs.
 	  Enabling this option may incur a significant performance overhead.
-
-config XEN_DEBUG
-	bool "Enable Xen debug checks"
-	depends on XEN
-	default n
-	help
-	  Enable various WARN_ON checks in the Xen MMU code.
-	  Enabling this option WILL incur a significant performance overhead.

arch/x86/xen/enlighten.c

@@ -251,6 +251,7 @@ static void __init xen_init_cpuid_mask(void)
 			~((1 << X86_FEATURE_APIC) |  /* disable local APIC */
 			  (1 << X86_FEATURE_ACPI));  /* disable ACPI */
 	ax = 1;
+	cx = 0;
 	xen_cpuid(&ax, &bx, &cx, &dx);
 
 	xsave_mask =

arch/x86/xen/mmu.c

@@ -495,41 +495,6 @@ static pte_t xen_make_pte(pteval_t pte)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
 
-#ifdef CONFIG_XEN_DEBUG
-pte_t xen_make_pte_debug(pteval_t pte)
-{
-	phys_addr_t addr = (pte & PTE_PFN_MASK);
-	phys_addr_t other_addr;
-	bool io_page = false;
-	pte_t _pte;
-
-	if (pte & _PAGE_IOMAP)
-		io_page = true;
-
-	_pte = xen_make_pte(pte);
-
-	if (!addr)
-		return _pte;
-
-	if (io_page &&
-	    (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
-		other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT;
-		WARN_ONCE(addr != other_addr,
-			"0x%lx is using VM_IO, but it is 0x%lx!\n",
-			(unsigned long)addr, (unsigned long)other_addr);
-	} else {
-		pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP;
-		other_addr = (_pte.pte & PTE_PFN_MASK);
-		WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set),
-			"0x%lx is missing VM_IO (and wasn't fixed)!\n",
-			(unsigned long)addr);
-	}
-
-	return _pte;
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug);
-#endif
-
 static pgd_t xen_make_pgd(pgdval_t pgd)
 {
 	pgd = pte_pfn_to_mfn(pgd);
@@ -1992,9 +1957,6 @@ void __init xen_ident_map_ISA(void)
 
 static void __init xen_post_allocator_init(void)
 {
-#ifdef CONFIG_XEN_DEBUG
-	pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
-#endif
 	pv_mmu_ops.set_pte = xen_set_pte;
 	pv_mmu_ops.set_pmd = xen_set_pmd;
 	pv_mmu_ops.set_pud = xen_set_pud;
@@ -2404,17 +2366,3 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 	return err;
 }
 EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
-
-#ifdef CONFIG_XEN_DEBUG_FS
-static int p2m_dump_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, p2m_dump_show, NULL);
-}
-
-static const struct file_operations p2m_dump_fops = {
-	.open		= p2m_dump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif /* CONFIG_XEN_DEBUG_FS */

arch/x86/xen/p2m.c

@@ -161,7 +161,9 @@
 #include <asm/xen/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
+#include <xen/grant_table.h>
 
+#include "multicalls.h"
 #include "xen-ops.h"
 
 static void __init m2p_override_init(void);
@@ -676,7 +678,8 @@ static unsigned long mfn_hash(unsigned long mfn)
 }
 
 /* Add an MFN override for a particular page */
-int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte)
+int m2p_add_override(unsigned long mfn, struct page *page,
+		struct gnttab_map_grant_ref *kmap_op)
 {
 	unsigned long flags;
 	unsigned long pfn;
@@ -692,16 +695,28 @@ int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte)
 					"m2p_add_override: pfn %lx not mapped", pfn))
 			return -EINVAL;
 	}
-
-	page->private = mfn;
+	WARN_ON(PagePrivate(page));
+	SetPagePrivate(page);
+	set_page_private(page, mfn);
 	page->index = pfn_to_mfn(pfn);
 
 	if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn))))
 		return -ENOMEM;
 
-	if (clear_pte && !PageHighMem(page))
-		/* Just zap old mapping for now */
-		pte_clear(&init_mm, address, ptep);
+	if (kmap_op != NULL) {
+		if (!PageHighMem(page)) {
+			struct multicall_space mcs =
+				xen_mc_entry(sizeof(*kmap_op));
+
+			MULTI_grant_table_op(mcs.mc,
+					GNTTABOP_map_grant_ref, kmap_op, 1);
+
+			xen_mc_issue(PARAVIRT_LAZY_MMU);
+		}
+		/* let's use dev_bus_addr to record the old mfn instead */
+		kmap_op->dev_bus_addr = page->index;
+		page->index = (unsigned long) kmap_op;
+	}
 	spin_lock_irqsave(&m2p_override_lock, flags);
 	list_add(&page->lru,  &m2p_overrides[mfn_hash(mfn)]);
 	spin_unlock_irqrestore(&m2p_override_lock, flags);
@@ -735,13 +750,56 @@ int m2p_remove_override(struct page *page, bool clear_pte)
 	spin_lock_irqsave(&m2p_override_lock, flags);
 	list_del(&page->lru);
 	spin_unlock_irqrestore(&m2p_override_lock, flags);
-	set_phys_to_machine(pfn, page->index);
+	WARN_ON(!PagePrivate(page));
+	ClearPagePrivate(page);
 
-	if (clear_pte && !PageHighMem(page))
-		set_pte_at(&init_mm, address, ptep,
-				pfn_pte(pfn, PAGE_KERNEL));
-		/* No tlb flush necessary because the caller already
-		 * left the pte unmapped. */
+	if (clear_pte) {
+		struct gnttab_map_grant_ref *map_op =
+			(struct gnttab_map_grant_ref *) page->index;
+		set_phys_to_machine(pfn, map_op->dev_bus_addr);
+		if (!PageHighMem(page)) {
+			struct multicall_space mcs;
+			struct gnttab_unmap_grant_ref *unmap_op;
+
+			/*
+			 * It might be that we queued all the m2p grant table
+			 * hypercalls in a multicall, then m2p_remove_override
+			 * get called before the multicall has actually been
+			 * issued. In this case handle is going to -1 because
+			 * it hasn't been modified yet.
+			 */
+			if (map_op->handle == -1)
+				xen_mc_flush();
+			/*
+			 * Now if map_op->handle is negative it means that the
+			 * hypercall actually returned an error.
+			 */
+			if (map_op->handle == GNTST_general_error) {
+				printk(KERN_WARNING "m2p_remove_override: "
+						"pfn %lx mfn %lx, failed to modify kernel mappings",
+						pfn, mfn);
+				return -1;
+			}
+
+			mcs = xen_mc_entry(
+					sizeof(struct gnttab_unmap_grant_ref));
+			unmap_op = mcs.args;
+			unmap_op->host_addr = map_op->host_addr;
+			unmap_op->handle = map_op->handle;
+			unmap_op->dev_bus_addr = 0;
+
+			MULTI_grant_table_op(mcs.mc,
+					GNTTABOP_unmap_grant_ref, unmap_op, 1);
+
+			xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+			set_pte_at(&init_mm, address, ptep,
+					pfn_pte(pfn, PAGE_KERNEL));
+			__flush_tlb_single(address);
+			map_op->host_addr = 0;
+		}
+	} else
+		set_phys_to_machine(pfn, page->index);
 
 	return 0;
 }
@@ -758,7 +816,7 @@ struct page *m2p_find_override(unsigned long mfn)
 	spin_lock_irqsave(&m2p_override_lock, flags);
 
 	list_for_each_entry(p, bucket, lru) {
-		if (p->private == mfn) {
+		if (page_private(p) == mfn) {
 			ret = p;
 			break;
 		}
@@ -782,17 +840,21 @@ unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn)
 EXPORT_SYMBOL_GPL(m2p_find_override_pfn);
 
 #ifdef CONFIG_XEN_DEBUG_FS
-
-int p2m_dump_show(struct seq_file *m, void *v)
+#include <linux/debugfs.h>
+#include "debugfs.h"
+static int p2m_dump_show(struct seq_file *m, void *v)
 {
 	static const char * const level_name[] = { "top", "middle",
-						"entry", "abnormal" };
-	static const char * const type_name[] = { "identity", "missing",
-						"pfn", "abnormal"};
+						"entry", "abnormal", "error"};
 #define TYPE_IDENTITY 0
 #define TYPE_MISSING 1
 #define TYPE_PFN 2
 #define TYPE_UNKNOWN 3
+	static const char * const type_name[] = {
+				[TYPE_IDENTITY] = "identity",
+				[TYPE_MISSING] = "missing",
+				[TYPE_PFN] = "pfn",
+				[TYPE_UNKNOWN] = "abnormal"};
 	unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0;
 	unsigned int uninitialized_var(prev_level);
 	unsigned int uninitialized_var(prev_type);
@@ -856,4 +918,32 @@ int p2m_dump_show(struct seq_file *m, void *v)
 #undef TYPE_PFN
 #undef TYPE_UNKNOWN
 }
-#endif
+
+static int p2m_dump_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, p2m_dump_show, NULL);
+}
+
+static const struct file_operations p2m_dump_fops = {
+	.open		= p2m_dump_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static struct dentry *d_mmu_debug;
+
+static int __init xen_p2m_debugfs(void)
+{
+	struct dentry *d_xen = xen_init_debugfs();
+
+	if (d_xen == NULL)
+		return -ENOMEM;
+
+	d_mmu_debug = debugfs_create_dir("mmu", d_xen);
+
+	debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops);
+	return 0;
+}
+fs_initcall(xen_p2m_debugfs);
+#endif /* CONFIG_XEN_DEBUG_FS */

drivers/block/xen-blkback/blkback.c

@@ -396,7 +396,7 @@ static int xen_blkbk_map(struct blkif_request *req,
 			continue;
 
 		ret = m2p_add_override(PFN_DOWN(map[i].dev_bus_addr),
-			blkbk->pending_page(pending_req, i), false);
+			blkbk->pending_page(pending_req, i), NULL);
 		if (ret) {
 			pr_alert(DRV_PFX "Failed to install M2P override for %lx (ret: %d)\n",
 				 (unsigned long)map[i].dev_bus_addr, ret);

drivers/xen/balloon.c

@@ -501,20 +501,24 @@ EXPORT_SYMBOL_GPL(balloon_set_new_target);
  * alloc_xenballooned_pages - get pages that have been ballooned out
  * @nr_pages: Number of pages to get
  * @pages: pages returned
+ * @highmem: highmem or lowmem pages
  * @return 0 on success, error otherwise
  */
-int alloc_xenballooned_pages(int nr_pages, struct page** pages)
+int alloc_xenballooned_pages(int nr_pages, struct page **pages, bool highmem)
 {
 	int pgno = 0;
 	struct page* page;
 	mutex_lock(&balloon_mutex);
 	while (pgno < nr_pages) {
-		page = balloon_retrieve(true);
-		if (page) {
+		page = balloon_retrieve(highmem);
+		if (page && PageHighMem(page) == highmem) {
 			pages[pgno++] = page;
 		} else {
 			enum bp_state st;
-			st = decrease_reservation(nr_pages - pgno, GFP_HIGHUSER);
+			if (page)
+				balloon_append(page);
+			st = decrease_reservation(nr_pages - pgno,
+					highmem ? GFP_HIGHUSER : GFP_USER);
 			if (st != BP_DONE)
 				goto out_undo;
 		}

drivers/xen/events.c

@@ -432,7 +432,8 @@ static int __must_check xen_allocate_irq_dynamic(void)
 
 	irq = irq_alloc_desc_from(first, -1);
 
-	xen_irq_init(irq);
+	if (irq >= 0)
+		xen_irq_init(irq);
 
 	return irq;
 }
@@ -713,7 +714,7 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 	mutex_lock(&irq_mapping_update_lock);
 
 	irq = xen_allocate_irq_dynamic();
-	if (irq == -1)
+	if (irq < 0)
 		goto out;
 
 	irq_set_chip_and_handler_name(irq, &xen_pirq_chip, handle_edge_irq,
@@ -729,7 +730,7 @@ int xen_bind_pirq_msi_to_irq(struct pci_dev *dev, struct msi_desc *msidesc,
 error_irq:
 	mutex_unlock(&irq_mapping_update_lock);
 	xen_free_irq(irq);
-	return -1;
+	return ret;
 }
 #endif
 
@@ -779,7 +780,7 @@ int xen_irq_from_pirq(unsigned pirq)
 	mutex_lock(&irq_mapping_update_lock);
 
 	list_for_each_entry(info, &xen_irq_list_head, list) {
-		if (info == NULL || info->type != IRQT_PIRQ)
+		if (info->type != IRQT_PIRQ)
 			continue;
 		irq = info->irq;
 		if (info->u.pirq.pirq == pirq)
@@ -1670,6 +1671,7 @@ void __init xen_init_IRQ(void)
 
 	evtchn_to_irq = kcalloc(NR_EVENT_CHANNELS, sizeof(*evtchn_to_irq),
 				    GFP_KERNEL);
+	BUG_ON(!evtchn_to_irq);
 	for (i = 0; i < NR_EVENT_CHANNELS; i++)
 		evtchn_to_irq[i] = -1;
 

drivers/xen/gntdev.c

@@ -83,6 +83,7 @@ struct grant_map {
 	struct ioctl_gntdev_grant_ref *grants;
 	struct gnttab_map_grant_ref   *map_ops;
 	struct gnttab_unmap_grant_ref *unmap_ops;
+	struct gnttab_map_grant_ref   *kmap_ops;
 	struct page **pages;
 };
 
@@ -116,19 +117,22 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
 	add->grants    = kzalloc(sizeof(add->grants[0])    * count, GFP_KERNEL);
 	add->map_ops   = kzalloc(sizeof(add->map_ops[0])   * count, GFP_KERNEL);
 	add->unmap_ops = kzalloc(sizeof(add->unmap_ops[0]) * count, GFP_KERNEL);
+	add->kmap_ops  = kzalloc(sizeof(add->kmap_ops[0])  * count, GFP_KERNEL);
 	add->pages     = kzalloc(sizeof(add->pages[0])     * count, GFP_KERNEL);
 	if (NULL == add->grants    ||
 	    NULL == add->map_ops   ||
 	    NULL == add->unmap_ops ||
+	    NULL == add->kmap_ops  ||
 	    NULL == add->pages)
 		goto err;
 
-	if (alloc_xenballooned_pages(count, add->pages))
+	if (alloc_xenballooned_pages(count, add->pages, false /* lowmem */))
 		goto err;
 
 	for (i = 0; i < count; i++) {
 		add->map_ops[i].handle = -1;
 		add->unmap_ops[i].handle = -1;
+		add->kmap_ops[i].handle = -1;
 	}
 
 	add->index = 0;
@@ -142,6 +146,7 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
 	kfree(add->grants);
 	kfree(add->map_ops);
 	kfree(add->unmap_ops);
+	kfree(add->kmap_ops);
 	kfree(add);
 	return NULL;
 }
@@ -243,10 +248,35 @@ static int map_grant_pages(struct grant_map *map)
 			gnttab_set_unmap_op(&map->unmap_ops[i], addr,
 				map->flags, -1 /* handle */);
 		}
+	} else {
+		/*
+		 * Setup the map_ops corresponding to the pte entries pointing
+		 * to the kernel linear addresses of the struct pages.
+		 * These ptes are completely different from the user ptes dealt
+		 * with find_grant_ptes.
+		 */
+		for (i = 0; i < map->count; i++) {
+			unsigned level;
+			unsigned long address = (unsigned long)
+				pfn_to_kaddr(page_to_pfn(map->pages[i]));
+			pte_t *ptep;
+			u64 pte_maddr = 0;
+			BUG_ON(PageHighMem(map->pages[i]));
+
+			ptep = lookup_address(address, &level);
+			pte_maddr = arbitrary_virt_to_machine(ptep).maddr;
+			gnttab_set_map_op(&map->kmap_ops[i], pte_maddr,
+				map->flags |
+				GNTMAP_host_map |
+				GNTMAP_contains_pte,
+				map->grants[i].ref,
+				map->grants[i].domid);
+		}
 	}
 
 	pr_debug("map %d+%d\n", map->index, map->count);
-	err = gnttab_map_refs(map->map_ops, map->pages, map->count);
+	err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL,
+			map->pages, map->count);
 	if (err)
 		return err;
 
@@ -462,13 +492,11 @@ static int gntdev_release(struct inode *inode, struct file *flip)
 
 	pr_debug("priv %p\n", priv);
 
-	spin_lock(&priv->lock);
 	while (!list_empty(&priv->maps)) {
 		map = list_entry(priv->maps.next, struct grant_map, next);
 		list_del(&map->next);
 		gntdev_put_map(map);
 	}
-	spin_unlock(&priv->lock);
 
 	if (use_ptemod)
 		mmu_notifier_unregister(&priv->mn, priv->mm);
@@ -532,10 +560,11 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
 	map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count);
 	if (map) {
 		list_del(&map->next);
-		gntdev_put_map(map);
 		err = 0;
 	}
 	spin_unlock(&priv->lock);
+	if (map)
+		gntdev_put_map(map);
 	return err;
 }
 

drivers/xen/grant-table.c

@@ -448,7 +448,8 @@ unsigned int gnttab_max_grant_frames(void)
 EXPORT_SYMBOL_GPL(gnttab_max_grant_frames);
 
 int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
-		    struct page **pages, unsigned int count)
+			struct gnttab_map_grant_ref *kmap_ops,
+			struct page **pages, unsigned int count)
 {
 	int i, ret;
 	pte_t *pte;
@@ -488,8 +489,7 @@ int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 			 */
 			return -EOPNOTSUPP;
 		}
-		ret = m2p_add_override(mfn, pages[i],
-				       map_ops[i].flags & GNTMAP_contains_pte);
+		ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]);
 		if (ret)
 			return ret;
 	}

drivers/xen/xen-selfballoon.c

@@ -68,6 +68,8 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/bootmem.h>
+#include <linux/swap.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/module.h>
@@ -93,6 +95,15 @@ static unsigned int selfballoon_uphysteresis __read_mostly = 1;
 /* In HZ, controls frequency of worker invocation. */
 static unsigned int selfballoon_interval __read_mostly = 5;
 
+/*
+ * Minimum usable RAM in MB for selfballooning target for balloon.
+ * If non-zero, it is added to totalreserve_pages and self-ballooning
+ * will not balloon below the sum.  If zero, a piecewise linear function
+ * is calculated as a minimum and added to totalreserve_pages.  Note that
+ * setting this value indiscriminately may cause OOMs and crashes.
+ */
+static unsigned int selfballoon_min_usable_mb;
+
 static void selfballoon_process(struct work_struct *work);
 static DECLARE_DELAYED_WORK(selfballoon_worker, selfballoon_process);
 
@@ -189,20 +200,23 @@ static int __init xen_selfballooning_setup(char *s)
 __setup("selfballooning", xen_selfballooning_setup);
 #endif /* CONFIG_FRONTSWAP */
 
+#define MB2PAGES(mb)	((mb) << (20 - PAGE_SHIFT))
+
 /*
  * Use current balloon size, the goal (vm_committed_as), and hysteresis
  * parameters to set a new target balloon size
  */
 static void selfballoon_process(struct work_struct *work)
 {
-	unsigned long cur_pages, goal_pages, tgt_pages;
+	unsigned long cur_pages, goal_pages, tgt_pages, floor_pages;
+	unsigned long useful_pages;
 	bool reset_timer = false;
 
 	if (xen_selfballooning_enabled) {
-		cur_pages = balloon_stats.current_pages;
+		cur_pages = totalram_pages;
 		tgt_pages = cur_pages; /* default is no change */
 		goal_pages = percpu_counter_read_positive(&vm_committed_as) +
-			balloon_stats.current_pages - totalram_pages;
+				totalreserve_pages;
 #ifdef CONFIG_FRONTSWAP
 		/* allow space for frontswap pages to be repatriated */
 		if (frontswap_selfshrinking && frontswap_enabled)
@@ -217,7 +231,26 @@ static void selfballoon_process(struct work_struct *work)
 				((goal_pages - cur_pages) /
 				  selfballoon_uphysteresis);
 		/* else if cur_pages == goal_pages, no change */
-		balloon_set_new_target(tgt_pages);
+		useful_pages = max_pfn - totalreserve_pages;
+		if (selfballoon_min_usable_mb != 0)
+			floor_pages = totalreserve_pages +
+					MB2PAGES(selfballoon_min_usable_mb);
+		/* piecewise linear function ending in ~3% slope */
+		else if (useful_pages < MB2PAGES(16))
+			floor_pages = max_pfn; /* not worth ballooning */
+		else if (useful_pages < MB2PAGES(64))
+			floor_pages = totalreserve_pages + MB2PAGES(16) +
+					((useful_pages - MB2PAGES(16)) >> 1);
+		else if (useful_pages < MB2PAGES(512))
+			floor_pages = totalreserve_pages + MB2PAGES(40) +
+					((useful_pages - MB2PAGES(40)) >> 3);
+		else /* useful_pages >= MB2PAGES(512) */
+			floor_pages = totalreserve_pages + MB2PAGES(99) +
+					((useful_pages - MB2PAGES(99)) >> 5);
+		if (tgt_pages < floor_pages)
+			tgt_pages = floor_pages;
+		balloon_set_new_target(tgt_pages +
+			balloon_stats.current_pages - totalram_pages);
 		reset_timer = true;
 	}
 #ifdef CONFIG_FRONTSWAP
@@ -340,6 +373,31 @@ static ssize_t store_selfballoon_uphys(struct sys_device *dev,
 static SYSDEV_ATTR(selfballoon_uphysteresis, S_IRUGO | S_IWUSR,
 		   show_selfballoon_uphys, store_selfballoon_uphys);
 
+SELFBALLOON_SHOW(selfballoon_min_usable_mb, "%d\n",
+				selfballoon_min_usable_mb);
+
+static ssize_t store_selfballoon_min_usable_mb(struct sys_device *dev,
+					       struct sysdev_attribute *attr,
+					       const char *buf,
+					       size_t count)
+{
+	unsigned long val;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	err = strict_strtoul(buf, 10, &val);
+	if (err || val == 0)
+		return -EINVAL;
+	selfballoon_min_usable_mb = val;
+	return count;
+}
+
+static SYSDEV_ATTR(selfballoon_min_usable_mb, S_IRUGO | S_IWUSR,
+		   show_selfballoon_min_usable_mb,
+		   store_selfballoon_min_usable_mb);
+
+
 #ifdef CONFIG_FRONTSWAP
 SELFBALLOON_SHOW(frontswap_selfshrinking, "%d\n", frontswap_selfshrinking);
 
@@ -421,6 +479,7 @@ static struct attribute *selfballoon_attrs[] = {
 	&attr_selfballoon_interval.attr,
 	&attr_selfballoon_downhysteresis.attr,
 	&attr_selfballoon_uphysteresis.attr,
+	&attr_selfballoon_min_usable_mb.attr,
 #ifdef CONFIG_FRONTSWAP
 	&attr_frontswap_selfshrinking.attr,
 	&attr_frontswap_hysteresis.attr,

drivers/xen/xenbus/xenbus_probe_backend.c

@@ -104,8 +104,6 @@ static int xenbus_uevent_backend(struct device *dev,
 
 	xdev = to_xenbus_device(dev);
 	bus = container_of(xdev->dev.bus, struct xen_bus_type, bus);
-	if (xdev == NULL)
-		return -ENODEV;
 
 	if (add_uevent_var(env, "MODALIAS=xen-backend:%s", xdev->devicetype))
 		return -ENOMEM;

include/xen/balloon.h

@@ -25,8 +25,9 @@ extern struct balloon_stats balloon_stats;
 
 void balloon_set_new_target(unsigned long target);
 
-int alloc_xenballooned_pages(int nr_pages, struct page** pages);
-void free_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 sys_device;
 #ifdef CONFIG_XEN_SELFBALLOONING

include/xen/grant_table.h

@@ -156,6 +156,7 @@ unsigned int gnttab_max_grant_frames(void);
 #define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr))
 
 int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
+			struct gnttab_map_grant_ref *kmap_ops,
 		    struct page **pages, unsigned int count);
 int gnttab_unmap_refs(struct gnttab_unmap_grant_ref *unmap_ops,
 		      struct page **pages, unsigned int count);