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
  ...

13 files changed, 136 insertions, 46 deletions

diff --git a/arch/arm/include/asm/xen/hypervisor.h b/arch/arm/include/asm/xen/hypervisor.h
index 04ff8e7b37df..95251512e2c4 100644
--- a/arch/arm/include/asm/xen/hypervisor.h
+++ b/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 */
diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
index efd562412850..0375c8caa061 100644
--- a/arch/arm/include/asm/xen/page-coherent.h
+++ b/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);
-	/* 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
-	 * can safely call the native dma_ops function, otherwise we call
-	 * the xen specific function. */
+	bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page);
+	/*
+	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
+	 * multiple Xen page, it's not possible to have a mix of local and
+	 * 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
-	 * native dma_ops function, otherwise we call the xen specific
-	 * function. */
+	/*
+	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
+	 * multiple Xen page, it's not possible to have a mix of local and
+	 * 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);
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index 127956353b00..415dbc6e43fd 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/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 gfn_to_virt(m)		(__va(gfn_to_pfn(m) << PAGE_SHIFT))
+#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) << 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,
-			   unsigned long bfn);
+			   phys_addr_t phys,
+			   dma_addr_t dev_addr);
 unsigned long xen_get_swiotlb_free_pages(unsigned int order);
 
 #endif /* _ASM_ARM_XEN_PAGE_H */
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index eeeab074e154..fc7ea529f462 100644
--- a/arch/arm/xen/enlighten.c
+++ b/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.offset = offset_in_page(vcpup);
+	info.mfn = virt_to_gfn(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);
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 6dd911d1f0ac..7c34f7126b04 100644
--- a/arch/arm/xen/mm.c
+++ b/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;
-	offset %= PAGE_SIZE;
+	xen_pfn = (handle >> XEN_PAGE_SHIFT) + offset / XEN_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)
-			len = PAGE_SIZE - offset;
+		if (len + offset > XEN_PAGE_SIZE)
+			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,
-			   unsigned long bfn)
+			   phys_addr_t phys,
+			   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,
diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c
index 887596c67b12..0ed01f2d5ee4 100644
--- a/arch/arm/xen/p2m.c
+++ b/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,
-				    map_ops[i].dev_bus_addr >> PAGE_SHIFT);
+		set_phys_to_machine(map_ops[i].host_addr >> XEN_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);
 	}
 
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index d866959e5685..8b2d4bea9962 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/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 */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 0679e11d2cf7..f5fb840b43e8 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/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,
-					 unsigned long bfn)
+					 phys_addr_t phys,
+					 dma_addr_t dev_addr)
 {
 	return false;
 }
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 993b7a71386d..5774800ff583 100644
--- a/arch/x86/xen/enlighten.c
+++ b/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
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index 1580e7a5a4cf..e079500b17f3 100644
--- a/arch/x86/xen/grant-table.c
+++ b/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);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 9c479fe40459..ac161db63388 100644
--- a/arch/x86/xen/mmu.c
+++ b/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:
 
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 660b3cfef234..cab9f766bb06 100644
--- a/arch/x86/xen/p2m.c
+++ b/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);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 63320b6d35bc..7ab29518a3b9 100644
--- a/arch/x86/xen/setup.c
+++ b/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;