8 files changed, 105 insertions, 17 deletions

diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 6b830d4cb4c8..de58533d3664 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -57,7 +57,7 @@ static u32 xen_apic_read(u32 reg)
 		return 0;
 
 	if (reg == APIC_LVR)
-		return 0x10;
+		return 0x14;
 #ifdef CONFIG_X86_32
 	if (reg == APIC_LDR)
 		return SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index d669e9d89001..c9081c6671f0 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1,8 +1,12 @@
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+#include <linux/bootmem.h>
+#endif
 #include <linux/cpu.h>
 #include <linux/kexec.h>
 
 #include <xen/features.h>
 #include <xen/page.h>
+#include <xen/interface/memory.h>
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
@@ -331,3 +335,80 @@ void xen_arch_unregister_cpu(int num)
 }
 EXPORT_SYMBOL(xen_arch_unregister_cpu);
 #endif
+
+#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
+void __init arch_xen_balloon_init(struct resource *hostmem_resource)
+{
+	struct xen_memory_map memmap;
+	int rc;
+	unsigned int i, last_guest_ram;
+	phys_addr_t max_addr = PFN_PHYS(max_pfn);
+	struct e820_table *xen_e820_table;
+	const struct e820_entry *entry;
+	struct resource *res;
+
+	if (!xen_initial_domain())
+		return;
+
+	xen_e820_table = kmalloc(sizeof(*xen_e820_table), GFP_KERNEL);
+	if (!xen_e820_table)
+		return;
+
+	memmap.nr_entries = ARRAY_SIZE(xen_e820_table->entries);
+	set_xen_guest_handle(memmap.buffer, xen_e820_table->entries);
+	rc = HYPERVISOR_memory_op(XENMEM_machine_memory_map, &memmap);
+	if (rc) {
+		pr_warn("%s: Can't read host e820 (%d)\n", __func__, rc);
+		goto out;
+	}
+
+	last_guest_ram = 0;
+	for (i = 0; i < memmap.nr_entries; i++) {
+		if (xen_e820_table->entries[i].addr >= max_addr)
+			break;
+		if (xen_e820_table->entries[i].type == E820_TYPE_RAM)
+			last_guest_ram = i;
+	}
+
+	entry = &xen_e820_table->entries[last_guest_ram];
+	if (max_addr >= entry->addr + entry->size)
+		goto out; /* No unallocated host RAM. */
+
+	hostmem_resource->start = max_addr;
+	hostmem_resource->end = entry->addr + entry->size;
+
+	/*
+	 * Mark non-RAM regions between the end of dom0 RAM and end of host RAM
+	 * as unavailable. The rest of that region can be used for hotplug-based
+	 * ballooning.
+	 */
+	for (; i < memmap.nr_entries; i++) {
+		entry = &xen_e820_table->entries[i];
+
+		if (entry->type == E820_TYPE_RAM)
+			continue;
+
+		if (entry->addr >= hostmem_resource->end)
+			break;
+
+		res = kzalloc(sizeof(*res), GFP_KERNEL);
+		if (!res)
+			goto out;
+
+		res->name = "Unavailable host RAM";
+		res->start = entry->addr;
+		res->end = (entry->addr + entry->size < hostmem_resource->end) ?
+			    entry->addr + entry->size : hostmem_resource->end;
+		rc = insert_resource(hostmem_resource, res);
+		if (rc) {
+			pr_warn("%s: Can't insert [%llx - %llx) (%d)\n",
+				__func__, res->start, res->end, rc);
+			kfree(res);
+			goto  out;
+		}
+	}
+
+ out:
+	kfree(xen_e820_table);
+}
+#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index f2414c6c5e7c..c047f42552e1 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -88,6 +88,8 @@
 #include "multicalls.h"
 #include "pmu.h"
 
+#include "../kernel/cpu/cpu.h" /* get_cpu_cap() */
+
 void *xen_initial_gdt;
 
 static int xen_cpu_up_prepare_pv(unsigned int cpu);
@@ -826,7 +828,7 @@ static void xen_load_sp0(unsigned long sp0)
 	mcs = xen_mc_entry(0);
 	MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
-	this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
+	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
 }
 
 void xen_set_iopl_mask(unsigned mask)
@@ -1258,6 +1260,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
 
 	/* Work out if we support NX */
+	get_cpu_cap(&boot_cpu_data);
 	x86_configure_nx();
 
 	/* Get mfn list */
diff --git a/arch/x86/xen/mmu_hvm.c b/arch/x86/xen/mmu_hvm.c
index 2cfcfe4f6b2a..dd2ad82eee80 100644
--- a/arch/x86/xen/mmu_hvm.c
+++ b/arch/x86/xen/mmu_hvm.c
@@ -75,6 +75,6 @@ void __init xen_hvm_init_mmu_ops(void)
 	if (is_pagetable_dying_supported())
 		pv_mmu_ops.exit_mmap = xen_hvm_exit_mmap;
 #ifdef CONFIG_PROC_VMCORE
-	register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram);
+	WARN_ON(register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram));
 #endif
 }
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index fc048ec686e7..d85076223a69 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1325,20 +1325,18 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 {
 	struct {
 		struct mmuext_op op;
-#ifdef CONFIG_SMP
-		DECLARE_BITMAP(mask, num_processors);
-#else
 		DECLARE_BITMAP(mask, NR_CPUS);
-#endif
 	} *args;
 	struct multicall_space mcs;
+	const size_t mc_entry_size = sizeof(args->op) +
+		sizeof(args->mask[0]) * BITS_TO_LONGS(num_possible_cpus());
 
 	trace_xen_mmu_flush_tlb_others(cpus, info->mm, info->start, info->end);
 
 	if (cpumask_empty(cpus))
 		return;		/* nothing to do */
 
-	mcs = xen_mc_entry(sizeof(*args));
+	mcs = xen_mc_entry(mc_entry_size);
 	args = mcs.args;
 	args->op.arg2.vcpumask = to_cpumask(args->mask);
 
@@ -1902,6 +1900,18 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	/* Graft it onto L4[511][510] */
 	copy_page(level2_kernel_pgt, l2);
 
+	/*
+	 * Zap execute permission from the ident map. Due to the sharing of
+	 * L1 entries we need to do this in the L2.
+	 */
+	if (__supported_pte_mask & _PAGE_NX) {
+		for (i = 0; i < PTRS_PER_PMD; ++i) {
+			if (pmd_none(level2_ident_pgt[i]))
+				continue;
+			level2_ident_pgt[i] = pmd_set_flags(level2_ident_pgt[i], _PAGE_NX);
+		}
+	}
+
 	/* Copy the initial P->M table mappings if necessary. */
 	i = pgd_index(xen_start_info->mfn_list);
 	if (i && i < pgd_index(__START_KERNEL_map))
@@ -2261,7 +2271,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 
 	switch (idx) {
 	case FIX_BTMAP_END ... FIX_BTMAP_BEGIN:
-	case FIX_RO_IDT:
 #ifdef CONFIG_X86_32
 	case FIX_WP_TEST:
 # ifdef CONFIG_HIGHMEM
@@ -2272,7 +2281,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 	case FIX_TEXT_POKE0:
 	case FIX_TEXT_POKE1:
-	case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END:
 		/* All local page mappings */
 		pte = pfn_pte(phys, prot);
 		break;
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index c114ca767b3b..6e0d2086eacb 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -808,7 +808,6 @@ char * __init xen_memory_setup(void)
 	addr = xen_e820_table.entries[0].addr;
 	size = xen_e820_table.entries[0].size;
 	while (i < xen_e820_table.nr_entries) {
-		bool discard = false;
 
 		chunk_size = size;
 		type = xen_e820_table.entries[i].type;
@@ -824,11 +823,10 @@ char * __init xen_memory_setup(void)
 				xen_add_extra_mem(pfn_s, n_pfns);
 				xen_max_p2m_pfn = pfn_s + n_pfns;
 			} else
-				discard = true;
+				type = E820_TYPE_UNUSABLE;
 		}
 
-		if (!discard)
-			xen_align_and_add_e820_region(addr, chunk_size, type);
+		xen_align_and_add_e820_region(addr, chunk_size, type);
 
 		addr += chunk_size;
 		size -= chunk_size;
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 02f3445a2b5f..cd97a62394e7 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -23,8 +23,6 @@ static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
 static DEFINE_PER_CPU(char *, irq_name);
 static bool xen_pvspin = true;
 
-#include <asm/qspinlock.h>
-
 static void xen_qlock_kick(int cpu)
 {
 	int irq = per_cpu(lock_kicker_irq, cpu);
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 75011b80660f..3b34745d0a52 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -72,7 +72,7 @@ u64 xen_clocksource_read(void);
 void xen_setup_cpu_clockevents(void);
 void xen_save_time_memory_area(void);
 void xen_restore_time_memory_area(void);
-void __init xen_init_time_ops(void);
+void __ref xen_init_time_ops(void);
 void __init xen_hvm_init_time_ops(void);
 
 irqreturn_t xen_debug_interrupt(int irq, void *dev_id);