4 files changed, 113 insertions, 58 deletions

diff --git a/kernel/arch/arm/xen/enlighten.c b/kernel/arch/arm/xen/enlighten.c
index 7d0f07020..fc7ea529f 100644
--- a/kernel/arch/arm/xen/enlighten.c
+++ b/kernel/arch/arm/xen/enlighten.c
@@ -24,6 +24,7 @@
 #include <linux/cpuidle.h>
 #include <linux/cpufreq.h>
 #include <linux/cpu.h>
+#include <linux/console.h>
 
 #include <linux/mm.h>
 
@@ -44,44 +45,39 @@ static struct vcpu_info __percpu *xen_vcpu_info;
 unsigned long xen_released_pages;
 struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
 
-/* TODO: to be removed */
-__read_mostly int xen_have_vector_callback;
-EXPORT_SYMBOL_GPL(xen_have_vector_callback);
+static __read_mostly unsigned int xen_events_irq;
 
-int xen_platform_pci_unplug = XEN_UNPLUG_ALL;
-EXPORT_SYMBOL_GPL(xen_platform_pci_unplug);
+static __initdata struct device_node *xen_node;
 
-static __read_mostly int xen_events_irq = -1;
-
-int xen_remap_domain_mfn_array(struct vm_area_struct *vma,
+int xen_remap_domain_gfn_array(struct vm_area_struct *vma,
 			       unsigned long addr,
-			       xen_pfn_t *mfn, int nr,
+			       xen_pfn_t *gfn, int nr,
 			       int *err_ptr, pgprot_t prot,
 			       unsigned domid,
 			       struct page **pages)
 {
-	return xen_xlate_remap_gfn_array(vma, addr, mfn, nr, err_ptr,
+	return xen_xlate_remap_gfn_array(vma, addr, gfn, nr, err_ptr,
 					 prot, domid, pages);
 }
-EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_array);
+EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_array);
 
 /* Not used by XENFEAT_auto_translated guests. */
-int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
+int xen_remap_domain_gfn_range(struct vm_area_struct *vma,
                               unsigned long addr,
-                              xen_pfn_t mfn, int nr,
+                              xen_pfn_t gfn, int nr,
                               pgprot_t prot, unsigned domid,
                               struct page **pages)
 {
 	return -ENOSYS;
 }
-EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
+EXPORT_SYMBOL_GPL(xen_remap_domain_gfn_range);
 
-int xen_unmap_domain_mfn_range(struct vm_area_struct *vma,
+int xen_unmap_domain_gfn_range(struct vm_area_struct *vma,
 			       int nr, struct page **pages)
 {
 	return xen_xlate_unmap_gfn_range(vma, nr, pages);
 }
-EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range);
+EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range);
 
 static void xen_percpu_init(void)
 {
@@ -90,16 +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();
 }
@@ -128,6 +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;
 	}
@@ -150,40 +158,28 @@ static irqreturn_t xen_arm_callback(int irq, void *arg)
  * documentation of the Xen Device Tree format.
  */
 #define GRANT_TABLE_PHYSADDR 0
-static int __init xen_guest_init(void)
+void __init xen_early_init(void)
 {
-	struct xen_add_to_physmap xatp;
-	static struct shared_info *shared_info_page = 0;
-	struct device_node *node;
 	int len;
 	const char *s = NULL;
 	const char *version = NULL;
 	const char *xen_prefix = "xen,xen-";
-	struct resource res;
-	phys_addr_t grant_frames;
 
-	node = of_find_compatible_node(NULL, NULL, "xen,xen");
-	if (!node) {
+	xen_node = of_find_compatible_node(NULL, NULL, "xen,xen");
+	if (!xen_node) {
 		pr_debug("No Xen support\n");
-		return 0;
+		return;
 	}
-	s = of_get_property(node, "compatible", &len);
+	s = of_get_property(xen_node, "compatible", &len);
 	if (strlen(xen_prefix) + 3  < len &&
 			!strncmp(xen_prefix, s, strlen(xen_prefix)))
 		version = s + strlen(xen_prefix);
 	if (version == NULL) {
 		pr_debug("Xen version not found\n");
-		return 0;
+		return;
 	}
-	if (of_address_to_resource(node, GRANT_TABLE_PHYSADDR, &res))
-		return 0;
-	grant_frames = res.start;
-	xen_events_irq = irq_of_parse_and_map(node, 0);
-	pr_info("Xen %s support found, events_irq=%d gnttab_frame=%pa\n",
-			version, xen_events_irq, &grant_frames);
 
-	if (xen_events_irq < 0)
-		return -ENODEV;
+	pr_info("Xen %s support found\n", version);
 
 	xen_domain_type = XEN_HVM_DOMAIN;
 
@@ -194,9 +190,34 @@ static int __init xen_guest_init(void)
 	else
 		xen_start_info->flags &= ~(SIF_INITDOMAIN|SIF_PRIVILEGED);
 
-	if (!shared_info_page)
-		shared_info_page = (struct shared_info *)
-			get_zeroed_page(GFP_KERNEL);
+	if (!console_set_on_cmdline && !xen_initial_domain())
+		add_preferred_console("hvc", 0, NULL);
+}
+
+static int __init xen_guest_init(void)
+{
+	struct xen_add_to_physmap xatp;
+	struct shared_info *shared_info_page = NULL;
+	struct resource res;
+	phys_addr_t grant_frames;
+
+	if (!xen_domain())
+		return 0;
+
+	if (of_address_to_resource(xen_node, GRANT_TABLE_PHYSADDR, &res)) {
+		pr_err("Xen grant table base address not found\n");
+		return -ENODEV;
+	}
+	grant_frames = res.start;
+
+	xen_events_irq = irq_of_parse_and_map(xen_node, 0);
+	if (!xen_events_irq) {
+		pr_err("Xen event channel interrupt not found\n");
+		return -ENODEV;
+	}
+
+	shared_info_page = (struct shared_info *)get_zeroed_page(GFP_KERNEL);
+
 	if (!shared_info_page) {
 		pr_err("not enough memory\n");
 		return -ENOMEM;
@@ -204,7 +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();
 
@@ -275,7 +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/kernel/arch/arm/xen/hypercall.S b/kernel/arch/arm/xen/hypercall.S
index f00e08075..10fd99c56 100644
--- a/kernel/arch/arm/xen/hypercall.S
+++ b/kernel/arch/arm/xen/hypercall.S
@@ -98,8 +98,23 @@ ENTRY(privcmd_call)
 	mov r1, r2
 	mov r2, r3
 	ldr r3, [sp, #8]
+	/*
+	 * Privcmd calls are issued by the userspace. We need to allow the
+	 * kernel to access the userspace memory before issuing the hypercall.
+	 */
+	uaccess_enable r4
+
+	/* r4 is loaded now as we use it as scratch register before */
 	ldr r4, [sp, #4]
 	__HVC(XEN_IMM)
+
+	/*
+	 * Disable userspace access from kernel. This is fine to do it
+	 * unconditionally as no set_fs(KERNEL_DS)/set_fs(get_ds()) is
+	 * called before.
+	 */
+	uaccess_disable r4
+
 	ldm sp!, {r4}
 	ret lr
 ENDPROC(privcmd_call);
diff --git a/kernel/arch/arm/xen/mm.c b/kernel/arch/arm/xen/mm.c
index 498325074..c5f9a9e3d 100644
--- a/kernel/arch/arm/xen/mm.c
+++ b/kernel/arch/arm/xen/mm.c
@@ -15,17 +15,17 @@
 #include <xen/xen.h>
 #include <xen/interface/grant_table.h>
 #include <xen/interface/memory.h>
+#include <xen/page.h>
 #include <xen/swiotlb-xen.h>
 
 #include <asm/cacheflush.h>
-#include <asm/xen/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
 unsigned long xen_get_swiotlb_free_pages(unsigned int order)
 {
 	struct memblock_region *reg;
-	gfp_t flags = __GFP_NOWARN;
+	gfp_t flags = __GFP_NOWARN|__GFP_KSWAPD_RECLAIM;
 
 	for_each_memblock(memory, reg) {
 		if (reg->base < (phys_addr_t)0xffffffff) {
@@ -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 mfn)
+			   phys_addr_t phys,
+			   dma_addr_t dev_addr)
 {
-	return (!hypercall_cflush && (pfn != mfn) && !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/kernel/arch/arm/xen/p2m.c b/kernel/arch/arm/xen/p2m.c
index cb7a14c5c..0ed01f2d5 100644
--- a/kernel/arch/arm/xen/p2m.c
+++ b/kernel/arch/arm/xen/p2m.c
@@ -10,10 +10,10 @@
 
 #include <xen/xen.h>
 #include <xen/interface/memory.h>
+#include <xen/page.h>
 #include <xen/swiotlb-xen.h>
 
 #include <asm/cacheflush.h>
-#include <asm/xen/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
@@ -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);
 	}