Merge branches 'upstream/xenfs' and 'upstream/core' of...

Merge branches 'upstream/xenfs' and 'upstream/core' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen

* 'upstream/xenfs' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen:
  xen/privcmd: make privcmd visible in domU
  xen/privcmd: move remap_domain_mfn_range() to core xen code and export.
  privcmd: MMAPBATCH: Fix error handling/reporting
  xenbus: export xen_store_interface for xenfs
  xen/privcmd: make sure vma is ours before doing anything to it
  xen/privcmd: print SIGBUS faults
  xen/xenfs: set_page_dirty is supposed to return true if it dirties
  xen/privcmd: create address space to allow writable mmaps
  xen: add privcmd driver
  xen: add variable hypercall caller
  xen: add xen_set_domain_pte()
  xen: add /proc/xen/xsd_{kva,port} to xenfs

* 'upstream/core' of git://git.kernel.org/pub/scm/linux/kernel/git/jeremy/xen: (29 commits)
  xen: include xen/xen.h for definition of xen_initial_domain()
  xen: use host E820 map for dom0
  xen: correctly rebuild mfn list list after migration.
  xen: improvements to VIRQ_DEBUG output
  xen: set up IRQ before binding virq to evtchn
  xen: ensure that all event channels start off bound to VCPU 0
  xen/hvc: only notify if we actually sent something
  xen: don't add extra_pages for RAM after mem_end
  xen: add support for PAT
  xen: make sure xen_max_p2m_pfn is up to date
  xen: limit extra memory to a certain ratio of base
  xen: add extra pages for E820 RAM regions, even if beyond mem_end
  xen: make sure xen_extra_mem_start is beyond all non-RAM e820
  xen: implement "extra" memory to reserve space for pages not present at boot
  xen: Use host-provided E820 map
  xen: don't map missing memory
  xen: defer building p2m mfn structures until kernel is mapped
  xen: add return value to set_phys_to_machine()
  xen: convert p2m to a 3 level tree
  xen: make install_p2mtop_page() static
  ...

Fix up trivial conflict in arch/x86/xen/mmu.c, and fix the use of
'reserve_early()' - in the new memblock world order it is now
'memblock_x86_reserve_range()' instead. Pointed out by Jeremy.

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

@@ -200,6 +200,23 @@ extern struct { char _entry[32]; } hypercall_page[];
 	(type)__res;							\
 })
 
+static inline long
+privcmd_call(unsigned call,
+	     unsigned long a1, unsigned long a2,
+	     unsigned long a3, unsigned long a4,
+	     unsigned long a5)
+{
+	__HYPERCALL_DECLS;
+	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
+
+	asm volatile("call *%[call]"
+		     : __HYPERCALL_5PARAM
+		     : [call] "a" (&hypercall_page[call])
+		     : __HYPERCALL_CLOBBER5);
+
+	return (long)__res;
+}
+
 static inline int
 HYPERVISOR_set_trap_table(struct trap_info *table)
 {

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

@@ -37,14 +37,21 @@ typedef struct xpaddr {
 
 
 extern unsigned long get_phys_to_machine(unsigned long pfn);
-extern void set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {
+	unsigned long mfn;
+
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return pfn;
 
-	return get_phys_to_machine(pfn) & ~FOREIGN_FRAME_BIT;
+	mfn = get_phys_to_machine(pfn);
+
+	if (mfn != INVALID_P2M_ENTRY)
+		mfn &= ~FOREIGN_FRAME_BIT;
+
+	return mfn;
 }
 
 static inline int phys_to_machine_mapping_valid(unsigned long pfn)
@@ -159,6 +166,7 @@ static inline pte_t __pte_ma(pteval_t x)
 
 #define pgd_val_ma(x)	((x).pgd)
 
+void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid);
 
 xmaddr_t arbitrary_virt_to_machine(void *address);
 unsigned long arbitrary_virt_to_mfn(void *vaddr);

arch/x86/xen/Kconfig

@@ -19,15 +19,12 @@ config XEN_PVHVM
 	depends on X86_LOCAL_APIC
 
 config XEN_MAX_DOMAIN_MEMORY
-       int "Maximum allowed size of a domain in gigabytes"
-       default 8 if X86_32
-       default 32 if X86_64
+       int
+       default 128
        depends on XEN
        help
-         The pseudo-physical to machine address array is sized
-         according to the maximum possible memory size of a Xen
-         domain.  This array uses 1 page per gigabyte, so there's no
-         need to be too stingy here.
+         This only affects the sizing of some bss arrays, the unused
+         portions of which are freed.
 
 config XEN_SAVE_RESTORE
        bool

arch/x86/xen/enlighten.c

@@ -136,9 +136,6 @@ static void xen_vcpu_setup(int cpu)
 	info.mfn = arbitrary_virt_to_mfn(vcpup);
 	info.offset = offset_in_page(vcpup);
 
-	printk(KERN_DEBUG "trying to map vcpu_info %d at %p, mfn %llx, offset %d\n",
-	       cpu, vcpup, info.mfn, info.offset);
-
 	/* Check to see if the hypervisor will put the vcpu_info
 	   structure where we want it, which allows direct access via
 	   a percpu-variable. */
@@ -152,9 +149,6 @@ static void xen_vcpu_setup(int cpu)
 		/* This cpu is using the registered vcpu info, even if
 		   later ones fail to. */
 		per_cpu(xen_vcpu, cpu) = vcpup;
-
-		printk(KERN_DEBUG "cpu %d using vcpu_info at %p\n",
-		       cpu, vcpup);
 	}
 }
 
@@ -836,6 +830,11 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
 		   Xen console noise. */
 		break;
 
+	case MSR_IA32_CR_PAT:
+		if (smp_processor_id() == 0)
+			xen_set_pat(((u64)high << 32) | low);
+		break;
+
 	default:
 		ret = native_write_msr_safe(msr, low, high);
 	}
@@ -874,8 +873,6 @@ void xen_setup_vcpu_info_placement(void)
 	/* xen_vcpu_setup managed to place the vcpu_info within the
 	   percpu area for all cpus, so make use of it */
 	if (have_vcpu_info_placement) {
-		printk(KERN_INFO "Xen: using vcpu_info placement\n");
-
 		pv_irq_ops.save_fl = __PV_IS_CALLEE_SAVE(xen_save_fl_direct);
 		pv_irq_ops.restore_fl = __PV_IS_CALLEE_SAVE(xen_restore_fl_direct);
 		pv_irq_ops.irq_disable = __PV_IS_CALLEE_SAVE(xen_irq_disable_direct);
@@ -1189,6 +1186,9 @@ asmlinkage void __init xen_start_kernel(void)
 	xen_raw_console_write("mapping kernel into physical memory\n");
 	pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
 
+	/* Allocate and initialize top and mid mfn levels for p2m structure */
+	xen_build_mfn_list_list();
+
 	init_mm.pgd = pgd;
 
 	/* keep using Xen gdt for now; no urgent need to change it */

arch/x86/xen/mmu.h

@@ -12,7 +12,6 @@ enum pt_level {
 
 
 bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
-bool install_p2mtop_page(unsigned long pfn, unsigned long *p);
 
 void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 

arch/x86/xen/setup.c

@@ -18,8 +18,10 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
+#include <xen/xen.h>
 #include <xen/page.h>
 #include <xen/interface/callback.h>
+#include <xen/interface/memory.h>
 #include <xen/interface/physdev.h>
 #include <xen/interface/memory.h>
 #include <xen/features.h>
@@ -34,6 +36,39 @@ extern void xen_sysenter_target(void);
 extern void xen_syscall_target(void);
 extern void xen_syscall32_target(void);
 
+/* Amount of extra memory space we add to the e820 ranges */
+phys_addr_t xen_extra_mem_start, xen_extra_mem_size;
+
+/* 
+ * The maximum amount of extra memory compared to the base size.  The
+ * main scaling factor is the size of struct page.  At extreme ratios
+ * of base:extra, all the base memory can be filled with page
+ * structures for the extra memory, leaving no space for anything
+ * else.
+ * 
+ * 10x seems like a reasonable balance between scaling flexibility and
+ * leaving a practically usable system.
+ */
+#define EXTRA_MEM_RATIO		(10)
+
+static __init void xen_add_extra_mem(unsigned long pages)
+{
+	u64 size = (u64)pages * PAGE_SIZE;
+	u64 extra_start = xen_extra_mem_start + xen_extra_mem_size;
+
+	if (!pages)
+		return;
+
+	e820_add_region(extra_start, size, E820_RAM);
+	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+
+	memblock_x86_reserve_range(extra_start, extra_start + size, "XEN EXTRA");
+
+	xen_extra_mem_size += size;
+
+	xen_max_p2m_pfn = PFN_DOWN(extra_start + size);
+}
+
 static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
 					      phys_addr_t end_addr)
 {
@@ -105,16 +140,65 @@ static unsigned long __init xen_return_unused_memory(unsigned long max_pfn,
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
  **/
-
 char * __init xen_memory_setup(void)
 {
+	static struct e820entry map[E820MAX] __initdata;
+
 	unsigned long max_pfn = xen_start_info->nr_pages;
+	unsigned long long mem_end;
+	int rc;
+	struct xen_memory_map memmap;
+	unsigned long extra_pages = 0;
+	unsigned long extra_limit;
+	int i;
+	int op;
 
 	max_pfn = min(MAX_DOMAIN_PAGES, max_pfn);
+	mem_end = PFN_PHYS(max_pfn);
+
+	memmap.nr_entries = E820MAX;
+	set_xen_guest_handle(memmap.buffer, map);
+
+	op = xen_initial_domain() ?
+		XENMEM_machine_memory_map :
+		XENMEM_memory_map;
+	rc = HYPERVISOR_memory_op(op, &memmap);
+	if (rc == -ENOSYS) {
+		memmap.nr_entries = 1;
+		map[0].addr = 0ULL;
+		map[0].size = mem_end;
+		/* 8MB slack (to balance backend allocations). */
+		map[0].size += 8ULL << 20;
+		map[0].type = E820_RAM;
+		rc = 0;
+	}
+	BUG_ON(rc);
 
 	e820.nr_map = 0;
+	xen_extra_mem_start = mem_end;
+	for (i = 0; i < memmap.nr_entries; i++) {
+		unsigned long long end = map[i].addr + map[i].size;
+
+		if (map[i].type == E820_RAM) {
+			if (map[i].addr < mem_end && end > mem_end) {
+				/* Truncate region to max_mem. */
+				u64 delta = end - mem_end;
+
+				map[i].size -= delta;
+				extra_pages += PFN_DOWN(delta);
+
+				end = mem_end;
+			}
+		}
 
-	e820_add_region(0, PFN_PHYS((u64)max_pfn), E820_RAM);
+		if (end > xen_extra_mem_start)
+			xen_extra_mem_start = end;
+
+		/* If region is non-RAM or below mem_end, add what remains */
+		if ((map[i].type != E820_RAM || map[i].addr < mem_end) &&
+		    map[i].size > 0)
+			e820_add_region(map[i].addr, map[i].size, map[i].type);
+	}
 
 	/*
 	 * Even though this is normal, usable memory under Xen, reserve
@@ -136,7 +220,29 @@ char * __init xen_memory_setup(void)
 
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 
-	xen_return_unused_memory(xen_start_info->nr_pages, &e820);
+	extra_pages += xen_return_unused_memory(xen_start_info->nr_pages, &e820);
+
+	/*
+	 * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
+	 * factor the base size.  On non-highmem systems, the base
+	 * size is the full initial memory allocation; on highmem it
+	 * is limited to the max size of lowmem, so that it doesn't
+	 * get completely filled.
+	 *
+	 * In principle there could be a problem in lowmem systems if
+	 * the initial memory is also very large with respect to
+	 * lowmem, but we won't try to deal with that here.
+	 */
+	extra_limit = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
+			  max_pfn + extra_pages);
+
+	if (extra_limit >= max_pfn)
+		extra_pages = extra_limit - max_pfn;
+	else
+		extra_pages = 0;
+
+	if (!xen_initial_domain())
+		xen_add_extra_mem(extra_pages);
 
 	return "Xen";
 }

arch/x86/xen/xen-ops.h

@@ -30,6 +30,9 @@ void xen_setup_machphys_mapping(void);
 pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
 void xen_ident_map_ISA(void);
 void xen_reserve_top(void);
+extern unsigned long xen_max_p2m_pfn;
+
+void xen_set_pat(u64);
 
 char * __init xen_memory_setup(void);
 void __init xen_arch_setup(void);

drivers/char/hvc_xen.c

@@ -74,6 +74,7 @@ static int __write_console(const char *data, int len)
 	wmb();			/* write ring before updating pointer */
 	intf->out_prod = prod;
 
+	if (sent)
 		notify_daemon();
 	return sent;
 }

drivers/xen/events.c

@@ -261,7 +261,7 @@ static void init_evtchn_cpu_bindings(void)
 	}
 #endif
 
-	memset(cpu_evtchn_mask(0), ~0, sizeof(cpu_evtchn_mask(0)));
+	memset(cpu_evtchn_mask(0), ~0, sizeof(struct cpu_evtchn_s));
 }
 
 static inline void clear_evtchn(int port)
@@ -377,7 +377,7 @@ int bind_evtchn_to_irq(unsigned int evtchn)
 		irq = find_unbound_irq();
 
 		set_irq_chip_and_handler_name(irq, &xen_dynamic_chip,
-					      handle_edge_irq, "event");
+					      handle_fasteoi_irq, "event");
 
 		evtchn_to_irq[evtchn] = irq;
 		irq_info[irq] = mk_evtchn_info(evtchn);
@@ -435,6 +435,11 @@ static int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
 	irq = per_cpu(virq_to_irq, cpu)[virq];
 
 	if (irq == -1) {
+		irq = find_unbound_irq();
+
+		set_irq_chip_and_handler_name(irq, &xen_percpu_chip,
+					      handle_percpu_irq, "virq");
+
 		bind_virq.virq = virq;
 		bind_virq.vcpu = cpu;
 		if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_virq,
@@ -442,11 +447,6 @@ static int bind_virq_to_irq(unsigned int virq, unsigned int cpu)
 			BUG();
 		evtchn = bind_virq.port;
 
-		irq = find_unbound_irq();
-
-		set_irq_chip_and_handler_name(irq, &xen_percpu_chip,
-					      handle_percpu_irq, "virq");
-
 		evtchn_to_irq[evtchn] = irq;
 		irq_info[irq] = mk_virq_info(evtchn, virq);
 
@@ -578,41 +578,75 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id)
 {
 	struct shared_info *sh = HYPERVISOR_shared_info;
 	int cpu = smp_processor_id();
+	unsigned long *cpu_evtchn = cpu_evtchn_mask(cpu);
 	int i;
 	unsigned long flags;
 	static DEFINE_SPINLOCK(debug_lock);
+	struct vcpu_info *v;
 
 	spin_lock_irqsave(&debug_lock, flags);
 
-	printk("vcpu %d\n  ", cpu);
+	printk("\nvcpu %d\n  ", cpu);
 
 	for_each_online_cpu(i) {
-		struct vcpu_info *v = per_cpu(xen_vcpu, i);
-		printk("%d: masked=%d pending=%d event_sel %08lx\n  ", i,
-			(get_irq_regs() && i == cpu) ? xen_irqs_disabled(get_irq_regs()) : v->evtchn_upcall_mask,
-			v->evtchn_upcall_pending,
+		int pending;
+		v = per_cpu(xen_vcpu, i);
+		pending = (get_irq_regs() && i == cpu)
+			? xen_irqs_disabled(get_irq_regs())
+			: v->evtchn_upcall_mask;
+		printk("%d: masked=%d pending=%d event_sel %0*lx\n  ", i,
+		       pending, v->evtchn_upcall_pending,
+		       (int)(sizeof(v->evtchn_pending_sel)*2),
 		       v->evtchn_pending_sel);
 	}
-	printk("pending:\n   ");
-	for(i = ARRAY_SIZE(sh->evtchn_pending)-1; i >= 0; i--)
-		printk("%08lx%s", sh->evtchn_pending[i],
+	v = per_cpu(xen_vcpu, cpu);
+
+	printk("\npending:\n   ");
+	for (i = ARRAY_SIZE(sh->evtchn_pending)-1; i >= 0; i--)
+		printk("%0*lx%s", (int)sizeof(sh->evtchn_pending[0])*2,
+		       sh->evtchn_pending[i],
+		       i % 8 == 0 ? "\n   " : " ");
+	printk("\nglobal mask:\n   ");
+	for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--)
+		printk("%0*lx%s",
+		       (int)(sizeof(sh->evtchn_mask[0])*2),
+		       sh->evtchn_mask[i],
 		       i % 8 == 0 ? "\n   " : " ");
-	printk("\nmasks:\n   ");
-	for(i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--)
-		printk("%08lx%s", sh->evtchn_mask[i],
+
+	printk("\nglobally unmasked:\n   ");
+	for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--)
+		printk("%0*lx%s", (int)(sizeof(sh->evtchn_mask[0])*2),
+		       sh->evtchn_pending[i] & ~sh->evtchn_mask[i],
 		       i % 8 == 0 ? "\n   " : " ");
 
-	printk("\nunmasked:\n   ");
-	for(i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--)
-		printk("%08lx%s", sh->evtchn_pending[i] & ~sh->evtchn_mask[i],
+	printk("\nlocal cpu%d mask:\n   ", cpu);
+	for (i = (NR_EVENT_CHANNELS/BITS_PER_LONG)-1; i >= 0; i--)
+		printk("%0*lx%s", (int)(sizeof(cpu_evtchn[0])*2),
+		       cpu_evtchn[i],
 		       i % 8 == 0 ? "\n   " : " ");
 
+	printk("\nlocally unmasked:\n   ");
+	for (i = ARRAY_SIZE(sh->evtchn_mask)-1; i >= 0; i--) {
+		unsigned long pending = sh->evtchn_pending[i]
+			& ~sh->evtchn_mask[i]
+			& cpu_evtchn[i];
+		printk("%0*lx%s", (int)(sizeof(sh->evtchn_mask[0])*2),
+		       pending, i % 8 == 0 ? "\n   " : " ");
+	}
+
 	printk("\npending list:\n");
-	for(i = 0; i < NR_EVENT_CHANNELS; i++) {
+	for (i = 0; i < NR_EVENT_CHANNELS; i++) {
 		if (sync_test_bit(i, sh->evtchn_pending)) {
-			printk("  %d: event %d -> irq %d\n",
+			int word_idx = i / BITS_PER_LONG;
+			printk("  %d: event %d -> irq %d%s%s%s\n",
 			       cpu_from_evtchn(i), i,
-			       evtchn_to_irq[i]);
+			       evtchn_to_irq[i],
+			       sync_test_bit(word_idx, &v->evtchn_pending_sel)
+					     ? "" : " l2-clear",
+			       !sync_test_bit(i, sh->evtchn_mask)
+					     ? "" : " globally-masked",
+			       sync_test_bit(i, cpu_evtchn)
+					     ? "" : " locally-masked");
 		}
 	}
 
@@ -663,6 +697,9 @@ static void __xen_evtchn_do_upcall(void)
 				int irq = evtchn_to_irq[port];
 				struct irq_desc *desc;
 
+				mask_evtchn(port);
+				clear_evtchn(port);
+
 				if (irq != -1) {
 					desc = irq_to_desc(irq);
 					if (desc)
@@ -800,10 +837,10 @@ static void ack_dynirq(unsigned int irq)
 {
 	int evtchn = evtchn_from_irq(irq);
 
-	move_native_irq(irq);
+	move_masked_irq(irq);
 
 	if (VALID_EVTCHN(evtchn))
-		clear_evtchn(evtchn);
+		unmask_evtchn(evtchn);
 }
 
 static int retrigger_dynirq(unsigned int irq)
@@ -959,7 +996,7 @@ static struct irq_chip xen_dynamic_chip __read_mostly = {
 	.mask		= disable_dynirq,
 	.unmask		= enable_dynirq,
 
-	.ack		= ack_dynirq,
+	.eoi		= ack_dynirq,
 	.set_affinity	= set_affinity_irq,
 	.retrigger	= retrigger_dynirq,
 };

drivers/xen/xenbus/xenbus_probe.c

@@ -64,9 +64,11 @@
 
 
 int xen_store_evtchn;
-EXPORT_SYMBOL(xen_store_evtchn);
+EXPORT_SYMBOL_GPL(xen_store_evtchn);
 
 struct xenstore_domain_interface *xen_store_interface;
+EXPORT_SYMBOL_GPL(xen_store_interface);
+
 static unsigned long xen_store_mfn;
 
 static BLOCKING_NOTIFIER_HEAD(xenstore_chain);

drivers/xen/xenfs/Makefile

 obj-$(CONFIG_XENFS) += xenfs.o
 
-xenfs-objs = super.o xenbus.o
+xenfs-y			  = super.o xenbus.o privcmd.o
\ No newline at end of file
+xenfs-$(CONFIG_XEN_DOM0) += xenstored.o

drivers/xen/xenfs/privcmd.c

+/******************************************************************************
+ * privcmd.c
+ *
+ * Interface to privileged domain-0 commands.
+ *
+ * Copyright (c) 2002-2004, K A Fraser, B Dragovic
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/uaccess.h>
+#include <linux/swap.h>
+#include <linux/smp_lock.h>
+#include <linux/highmem.h>
+#include <linux/pagemap.h>
+#include <linux/seq_file.h>
+
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm/tlb.h>
+#include <asm/xen/hypervisor.h>
+#include <asm/xen/hypercall.h>
+
+#include <xen/xen.h>
+#include <xen/privcmd.h>
+#include <xen/interface/xen.h>
+#include <xen/features.h>
+#include <xen/page.h>
+#include <xen/xen-ops.h>
+
+#ifndef HAVE_ARCH_PRIVCMD_MMAP
+static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma);
+#endif
+
+static long privcmd_ioctl_hypercall(void __user *udata)
+{
+	struct privcmd_hypercall hypercall;
+	long ret;
+
+	if (copy_from_user(&hypercall, udata, sizeof(hypercall)))
+		return -EFAULT;
+
+	ret = privcmd_call(hypercall.op,
+			   hypercall.arg[0], hypercall.arg[1],
+			   hypercall.arg[2], hypercall.arg[3],
+			   hypercall.arg[4]);
+
+	return ret;
+}
+
+static void free_page_list(struct list_head *pages)
+{
+	struct page *p, *n;
+
+	list_for_each_entry_safe(p, n, pages, lru)
+		__free_page(p);
+
+	INIT_LIST_HEAD(pages);
+}
+
+/*
+ * Given an array of items in userspace, return a list of pages
+ * containing the data.  If copying fails, either because of memory
+ * allocation failure or a problem reading user memory, return an
+ * error code; its up to the caller to dispose of any partial list.
+ */
+static int gather_array(struct list_head *pagelist,
+			unsigned nelem, size_t size,
+			void __user *data)
+{
+	unsigned pageidx;
+	void *pagedata;
+	int ret;
+
+	if (size > PAGE_SIZE)
+		return 0;
+
+	pageidx = PAGE_SIZE;
+	pagedata = NULL;	/* quiet, gcc */
+	while (nelem--) {
+		if (pageidx > PAGE_SIZE-size) {
+			struct page *page = alloc_page(GFP_KERNEL);
+
+			ret = -ENOMEM;
+			if (page == NULL)
+				goto fail;
+
+			pagedata = page_address(page);
+
+			list_add_tail(&page->lru, pagelist);
+			pageidx = 0;
+		}
+
+		ret = -EFAULT;
+		if (copy_from_user(pagedata + pageidx, data, size))
+			goto fail;
+
+		data += size;
+		pageidx += size;
+	}
+
+	ret = 0;
+
+fail:
+	return ret;
+}
+
+/*
+ * Call function "fn" on each element of the array fragmented
+ * over a list of pages.
+ */
+static int traverse_pages(unsigned nelem, size_t size,
+			  struct list_head *pos,
+			  int (*fn)(void *data, void *state),
+			  void *state)
+{
+	void *pagedata;
+	unsigned pageidx;
+	int ret = 0;
+
+	BUG_ON(size > PAGE_SIZE);
+
+	pageidx = PAGE_SIZE;
+	pagedata = NULL;	/* hush, gcc */
+
+	while (nelem--) {
+		if (pageidx > PAGE_SIZE-size) {
+			struct page *page;
+			pos = pos->next;
+			page = list_entry(pos, struct page, lru);
+			pagedata = page_address(page);
+			pageidx = 0;
+		}
+
+		ret = (*fn)(pagedata + pageidx, state);
+		if (ret)
+			break;
+		pageidx += size;
+	}
+
+	return ret;
+}
+
+struct mmap_mfn_state {
+	unsigned long va;
+	struct vm_area_struct *vma;
+	domid_t domain;
+};
+
+static int mmap_mfn_range(void *data, void *state)
+{
+	struct privcmd_mmap_entry *msg = data;
+	struct mmap_mfn_state *st = state;
+	struct vm_area_struct *vma = st->vma;
+	int rc;
+
+	/* Do not allow range to wrap the address space. */
+	if ((msg->npages > (LONG_MAX >> PAGE_SHIFT)) ||
+	    ((unsigned long)(msg->npages << PAGE_SHIFT) >= -st->va))
+		return -EINVAL;
+
+	/* Range chunks must be contiguous in va space. */
+	if ((msg->va != st->va) ||
+	    ((msg->va+(msg->npages<<PAGE_SHIFT)) > vma->vm_end))
+		return -EINVAL;
+
+	rc = xen_remap_domain_mfn_range(vma,
+					msg->va & PAGE_MASK,
+					msg->mfn, msg->npages,
+					vma->vm_page_prot,
+					st->domain);
+	if (rc < 0)
+		return rc;
+
+	st->va += msg->npages << PAGE_SHIFT;
+
+	return 0;
+}
+
+static long privcmd_ioctl_mmap(void __user *udata)
+{
+	struct privcmd_mmap mmapcmd;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int rc;
+	LIST_HEAD(pagelist);
+	struct mmap_mfn_state state;
+
+	if (!xen_initial_domain())
+		return -EPERM;
+
+	if (copy_from_user(&mmapcmd, udata, sizeof(mmapcmd)))
+		return -EFAULT;
+
+	rc = gather_array(&pagelist,
+			  mmapcmd.num, sizeof(struct privcmd_mmap_entry),
+			  mmapcmd.entry);
+
+	if (rc || list_empty(&pagelist))
+		goto out;
+
+	down_write(&mm->mmap_sem);
+
+	{
+		struct page *page = list_first_entry(&pagelist,
+						     struct page, lru);
+		struct privcmd_mmap_entry *msg = page_address(page);
+
+		vma = find_vma(mm, msg->va);
+		rc = -EINVAL;
+
+		if (!vma || (msg->va != vma->vm_start) ||
+		    !privcmd_enforce_singleshot_mapping(vma))
+			goto out_up;
+	}
+
+	state.va = vma->vm_start;
+	state.vma = vma;
+	state.domain = mmapcmd.dom;
+
+	rc = traverse_pages(mmapcmd.num, sizeof(struct privcmd_mmap_entry),
+			    &pagelist,
+			    mmap_mfn_range, &state);
+
+
+out_up:
+	up_write(&mm->mmap_sem);
+
+out:
+	free_page_list(&pagelist);
+
+	return rc;
+}
+
+struct mmap_batch_state {
+	domid_t domain;
+	unsigned long va;
+	struct vm_area_struct *vma;
+	int err;
+
+	xen_pfn_t __user *user;
+};
+
+static int mmap_batch_fn(void *data, void *state)
+{
+	xen_pfn_t *mfnp = data;
+	struct mmap_batch_state *st = state;
+
+	if (xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1,
+				       st->vma->vm_page_prot, st->domain) < 0) {
+		*mfnp |= 0xf0000000U;
+		st->err++;
+	}
+	st->va += PAGE_SIZE;
+
+	return 0;
+}
+
+static int mmap_return_errors(void *data, void *state)
+{
+	xen_pfn_t *mfnp = data;
+	struct mmap_batch_state *st = state;
+
+	put_user(*mfnp, st->user++);
+
+	return 0;
+}
+
+static struct vm_operations_struct privcmd_vm_ops;
+
+static long privcmd_ioctl_mmap_batch(void __user *udata)
+{
+	int ret;
+	struct privcmd_mmapbatch m;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long nr_pages;
+	LIST_HEAD(pagelist);
+	struct mmap_batch_state state;
+
+	if (!xen_initial_domain())
+		return -EPERM;
+
+	if (copy_from_user(&m, udata, sizeof(m)))
+		return -EFAULT;
+
+	nr_pages = m.num;
+	if ((m.num <= 0) || (nr_pages > (LONG_MAX >> PAGE_SHIFT)))
+		return -EINVAL;
+
+	ret = gather_array(&pagelist, m.num, sizeof(xen_pfn_t),
+			   m.arr);
+
+	if (ret || list_empty(&pagelist))
+		goto out;
+
+	down_write(&mm->mmap_sem);
+
+	vma = find_vma(mm, m.addr);
+	ret = -EINVAL;
+	if (!vma ||
+	    vma->vm_ops != &privcmd_vm_ops ||
+	    (m.addr != vma->vm_start) ||
+	    ((m.addr + (nr_pages << PAGE_SHIFT)) != vma->vm_end) ||
+	    !privcmd_enforce_singleshot_mapping(vma)) {
+		up_write(&mm->mmap_sem);
+		goto out;
+	}
+
+	state.domain = m.dom;
+	state.vma = vma;
+	state.va = m.addr;
+	state.err = 0;
+
+	ret = traverse_pages(m.num, sizeof(xen_pfn_t),
+			     &pagelist, mmap_batch_fn, &state);
+
+	up_write(&mm->mmap_sem);
+
+	if (state.err > 0) {
+		ret = 0;
+
+		state.user = m.arr;
+		traverse_pages(m.num, sizeof(xen_pfn_t),
+			       &pagelist,
+			       mmap_return_errors, &state);
+	}
+
+out:
+	free_page_list(&pagelist);
+
+	return ret;
+}
+
+static long privcmd_ioctl(struct file *file,
+			  unsigned int cmd, unsigned long data)
+{
+	int ret = -ENOSYS;
+	void __user *udata = (void __user *) data;
+
+	switch (cmd) {
+	case IOCTL_PRIVCMD_HYPERCALL:
+		ret = privcmd_ioctl_hypercall(udata);
+		break;
+
+	case IOCTL_PRIVCMD_MMAP:
+		ret = privcmd_ioctl_mmap(udata);
+		break;
+
+	case IOCTL_PRIVCMD_MMAPBATCH:
+		ret = privcmd_ioctl_mmap_batch(udata);
+		break;
+
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+#ifndef HAVE_ARCH_PRIVCMD_MMAP
+static int privcmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n",
+	       vma, vma->vm_start, vma->vm_end,
+	       vmf->pgoff, vmf->virtual_address);
+
+	return VM_FAULT_SIGBUS;
+}
+
+static struct vm_operations_struct privcmd_vm_ops = {
+	.fault = privcmd_fault
+};
+
+static int privcmd_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	/* Unsupported for auto-translate guests. */
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return -ENOSYS;
+
+	/* DONTCOPY is essential for Xen as copy_page_range is broken. */
+	vma->vm_flags |= VM_RESERVED | VM_IO | VM_DONTCOPY;
+	vma->vm_ops = &privcmd_vm_ops;
+	vma->vm_private_data = NULL;
+
+	return 0;
+}
+
+static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma)
+{
+	return (xchg(&vma->vm_private_data, (void *)1) == NULL);
+}
+#endif
+
+const struct file_operations privcmd_file_ops = {
+	.unlocked_ioctl = privcmd_ioctl,
+	.mmap = privcmd_mmap,
+};

drivers/xen/xenfs/super.c

@@ -12,6 +12,8 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/magic.h>
+#include <linux/mm.h>
+#include <linux/backing-dev.h>
 
 #include <xen/xen.h>
 
@@ -22,6 +24,62 @@
 MODULE_DESCRIPTION("Xen filesystem");
 MODULE_LICENSE("GPL");
 
+static int xenfs_set_page_dirty(struct page *page)
+{
+	return !TestSetPageDirty(page);
+}
+
+static const struct address_space_operations xenfs_aops = {
+	.set_page_dirty = xenfs_set_page_dirty,
+};
+
+static struct backing_dev_info xenfs_backing_dev_info = {
+	.ra_pages	= 0,	/* No readahead */
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
+};
+
+static struct inode *xenfs_make_inode(struct super_block *sb, int mode)
+{
+	struct inode *ret = new_inode(sb);
+
+	if (ret) {
+		ret->i_mode = mode;
+		ret->i_mapping->a_ops = &xenfs_aops;
+		ret->i_mapping->backing_dev_info = &xenfs_backing_dev_info;
+		ret->i_uid = ret->i_gid = 0;
+		ret->i_blocks = 0;
+		ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME;
+	}
+	return ret;
+}
+
+static struct dentry *xenfs_create_file(struct super_block *sb,
+					struct dentry *parent,
+					const char *name,
+					const struct file_operations *fops,
+					void *data,
+					int mode)
+{
+	struct dentry *dentry;
+	struct inode *inode;
+
+	dentry = d_alloc_name(parent, name);
+	if (!dentry)
+		return NULL;
+
+	inode = xenfs_make_inode(sb, S_IFREG | mode);
+	if (!inode) {
+		dput(dentry);
+		return NULL;
+	}
+
+	inode->i_fop = fops;
+	inode->i_private = data;
+
+	d_add(dentry, inode);
+	return dentry;
+}
+
 static ssize_t capabilities_read(struct file *file, char __user *buf,
 				 size_t size, loff_t *off)
 {
@@ -44,10 +102,23 @@ static int xenfs_fill_super(struct super_block *sb, void *data, int silent)
 		[1] = {},
 		{ "xenbus", &xenbus_file_ops, S_IRUSR|S_IWUSR },
 		{ "capabilities", &capabilities_file_ops, S_IRUGO },
+		{ "privcmd", &privcmd_file_ops, S_IRUSR|S_IWUSR },
 		{""},
 	};
+	int rc;
 
-	return simple_fill_super(sb, XENFS_SUPER_MAGIC, xenfs_files);
+	rc = simple_fill_super(sb, XENFS_SUPER_MAGIC, xenfs_files);
+	if (rc < 0)
+		return rc;
+
+	if (xen_initial_domain()) {
+		xenfs_create_file(sb, sb->s_root, "xsd_kva",
+				  &xsd_kva_file_ops, NULL, S_IRUSR|S_IWUSR);
+		xenfs_create_file(sb, sb->s_root, "xsd_port",
+				  &xsd_port_file_ops, NULL, S_IRUSR|S_IWUSR);
+	}
+
+	return rc;
 }
 
 static int xenfs_get_sb(struct file_system_type *fs_type,
@@ -66,11 +137,25 @@ static struct file_system_type xenfs_type = {
 
 static int __init xenfs_init(void)
 {
-	if (xen_domain())
-		return register_filesystem(&xenfs_type);
-
-	printk(KERN_INFO "XENFS: not registering filesystem on non-xen platform\n");
+	int err;
+	if (!xen_domain()) {
+		printk(KERN_INFO "xenfs: not registering filesystem on non-xen platform\n");
 		return 0;
+	}
+
+	err = register_filesystem(&xenfs_type);
+	if (err) {
+		printk(KERN_ERR "xenfs: Unable to register filesystem!\n");
+		goto out;
+	}
+
+	err = bdi_init(&xenfs_backing_dev_info);
+	if (err)
+		unregister_filesystem(&xenfs_type);
+
+ out:
+
+	return err;
 }
 
 static void __exit xenfs_exit(void)

drivers/xen/xenfs/xenfs.h

@@ -2,5 +2,8 @@
 #define _XENFS_XENBUS_H
 
 extern const struct file_operations xenbus_file_ops;
+extern const struct file_operations privcmd_file_ops;
+extern const struct file_operations xsd_kva_file_ops;
+extern const struct file_operations xsd_port_file_ops;
 
 #endif	/* _XENFS_XENBUS_H */

drivers/xen/xenfs/xenstored.c

+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+
+#include <xen/page.h>
+
+#include "xenfs.h"
+#include "../xenbus/xenbus_comms.h"
+
+static ssize_t xsd_read(struct file *file, char __user *buf,
+			    size_t size, loff_t *off)
+{
+	const char *str = (const char *)file->private_data;
+	return simple_read_from_buffer(buf, size, off, str, strlen(str));
+}
+
+static int xsd_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static int xsd_kva_open(struct inode *inode, struct file *file)
+{
+	file->private_data = (void *)kasprintf(GFP_KERNEL, "0x%p",
+					       xen_store_interface);
+	if (!file->private_data)
+		return -ENOMEM;
+	return 0;
+}
+
+static int xsd_kva_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	size_t size = vma->vm_end - vma->vm_start;
+
+	if ((size > PAGE_SIZE) || (vma->vm_pgoff != 0))
+		return -EINVAL;
+
+	if (remap_pfn_range(vma, vma->vm_start,
+			    virt_to_pfn(xen_store_interface),
+			    size, vma->vm_page_prot))
+		return -EAGAIN;
+
+	return 0;
+}
+
+const struct file_operations xsd_kva_file_ops = {
+	.open = xsd_kva_open,
+	.mmap = xsd_kva_mmap,
+	.read = xsd_read,
+	.release = xsd_release,
+};
+
+static int xsd_port_open(struct inode *inode, struct file *file)
+{
+	file->private_data = (void *)kasprintf(GFP_KERNEL, "%d",
+					       xen_store_evtchn);
+	if (!file->private_data)
+		return -ENOMEM;
+	return 0;
+}
+
+const struct file_operations xsd_port_file_ops = {
+	.open = xsd_port_open,
+	.read = xsd_read,
+	.release = xsd_release,
+};

include/xen/Kbuild

 header-y += evtchn.h
+header-y += privcmd.h

include/xen/interface/memory.h

@@ -186,6 +186,35 @@ struct xen_translate_gpfn_list {
 };
 DEFINE_GUEST_HANDLE_STRUCT(xen_translate_gpfn_list);
 
+/*
+ * Returns the pseudo-physical memory map as it was when the domain
+ * was started (specified by XENMEM_set_memory_map).
+ * arg == addr of struct xen_memory_map.
+ */
+#define XENMEM_memory_map           9
+struct xen_memory_map {
+    /*
+     * On call the number of entries which can be stored in buffer. On
+     * return the number of entries which have been stored in
+     * buffer.
+     */
+    unsigned int nr_entries;
+
+    /*
+     * Entries in the buffer are in the same format as returned by the
+     * BIOS INT 0x15 EAX=0xE820 call.
+     */
+    GUEST_HANDLE(void) buffer;
+};
+DEFINE_GUEST_HANDLE_STRUCT(xen_memory_map);
+
+/*
+ * Returns the real physical memory map. Passes the same structure as
+ * XENMEM_memory_map.
+ * arg == addr of struct xen_memory_map.
+ */
+#define XENMEM_machine_memory_map   10
+
 
 /*
  * Prevent the balloon driver from changing the memory reservation

include/xen/privcmd.h

+/******************************************************************************
+ * privcmd.h
+ *
+ * Interface to /proc/xen/privcmd.
+ *
+ * Copyright (c) 2003-2005, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __LINUX_PUBLIC_PRIVCMD_H__
+#define __LINUX_PUBLIC_PRIVCMD_H__
+
+#include <linux/types.h>
+
+typedef unsigned long xen_pfn_t;
+
+#ifndef __user
+#define __user
+#endif
+
+struct privcmd_hypercall {
+	__u64 op;
+	__u64 arg[5];
+};
+
+struct privcmd_mmap_entry {
+	__u64 va;
+	__u64 mfn;
+	__u64 npages;
+};
+
+struct privcmd_mmap {
+	int num;
+	domid_t dom; /* target domain */
+	struct privcmd_mmap_entry __user *entry;
+};
+
+struct privcmd_mmapbatch {
+	int num;     /* number of pages to populate */
+	domid_t dom; /* target domain */
+	__u64 addr;  /* virtual address */
+	xen_pfn_t __user *arr; /* array of mfns - top nibble set on err */
+};
+
+/*
+ * @cmd: IOCTL_PRIVCMD_HYPERCALL
+ * @arg: &privcmd_hypercall_t
+ * Return: Value returned from execution of the specified hypercall.
+ */
+#define IOCTL_PRIVCMD_HYPERCALL					\
+	_IOC(_IOC_NONE, 'P', 0, sizeof(struct privcmd_hypercall))
+#define IOCTL_PRIVCMD_MMAP					\
+	_IOC(_IOC_NONE, 'P', 2, sizeof(struct privcmd_mmap))
+#define IOCTL_PRIVCMD_MMAPBATCH					\
+	_IOC(_IOC_NONE, 'P', 3, sizeof(struct privcmd_mmapbatch))
+
+#endif /* __LINUX_PUBLIC_PRIVCMD_H__ */

include/xen/xen-ops.h

@@ -23,4 +23,9 @@ int xen_create_contiguous_region(unsigned long vstart, unsigned int order,
 
 void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order);
 
+int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
+			       unsigned long addr,
+			       unsigned long mfn, int nr,
+			       pgprot_t prot, unsigned domid);
+
 #endif /* INCLUDE_XEN_OPS_H */