5 files changed, 70 insertions, 12 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b132ade26f77..95dccce8e979 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -63,6 +63,7 @@
 #include <asm/stackprotector.h>
 #include <asm/hypervisor.h>
 #include <asm/mwait.h>
+#include <asm/pci_x86.h>
 
 #ifdef CONFIG_ACPI
 #include <linux/acpi.h>
@@ -261,7 +262,8 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 
 static bool __init xen_check_mwait(void)
 {
-#ifdef CONFIG_ACPI
+#if defined(CONFIG_ACPI) && !defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR) && \
+	!defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR_MODULE)
 	struct xen_platform_op op = {
 		.cmd			= XENPF_set_processor_pminfo,
 		.u.set_pminfo.id	= -1,
@@ -349,7 +351,6 @@ static void __init xen_init_cpuid_mask(void)
 	/* Xen will set CR4.OSXSAVE if supported and not disabled by force */
 	if ((cx & xsave_mask) != xsave_mask)
 		cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
-
 	if (xen_check_mwait())
 		cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32));
 }
@@ -809,9 +810,40 @@ static void xen_io_delay(void)
 }
 
 #ifdef CONFIG_X86_LOCAL_APIC
+static unsigned long xen_set_apic_id(unsigned int x)
+{
+	WARN_ON(1);
+	return x;
+}
+static unsigned int xen_get_apic_id(unsigned long x)
+{
+	return ((x)>>24) & 0xFFu;
+}
 static u32 xen_apic_read(u32 reg)
 {
-	return 0;
+	struct xen_platform_op op = {
+		.cmd = XENPF_get_cpuinfo,
+		.interface_version = XENPF_INTERFACE_VERSION,
+		.u.pcpu_info.xen_cpuid = 0,
+	};
+	int ret = 0;
+
+	/* Shouldn't need this as APIC is turned off for PV, and we only
+	 * get called on the bootup processor. But just in case. */
+	if (!xen_initial_domain() || smp_processor_id())
+		return 0;
+
+	if (reg == APIC_LVR)
+		return 0x10;
+
+	if (reg != APIC_ID)
+		return 0;
+
+	ret = HYPERVISOR_dom0_op(&op);
+	if (ret)
+		return 0;
+
+	return op.u.pcpu_info.apic_id << 24;
 }
 
 static void xen_apic_write(u32 reg, u32 val)
@@ -849,6 +881,8 @@ static void set_xen_basic_apic_ops(void)
 	apic->icr_write = xen_apic_icr_write;
 	apic->wait_icr_idle = xen_apic_wait_icr_idle;
 	apic->safe_wait_icr_idle = xen_safe_apic_wait_icr_idle;
+	apic->set_apic_id = xen_set_apic_id;
+	apic->get_apic_id = xen_get_apic_id;
 }
 
 #endif
@@ -967,7 +1001,7 @@ void xen_setup_shared_info(void)
 	xen_setup_mfn_list_list();
 }
 
-/* This is called once we have the cpu_possible_map */
+/* This is called once we have the cpu_possible_mask */
 void xen_setup_vcpu_info_placement(void)
 {
 	int cpu;
@@ -1365,8 +1399,10 @@ asmlinkage void __init xen_start_kernel(void)
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
 	}
-		
-
+#ifdef CONFIG_PCI
+	/* PCI BIOS service won't work from a PV guest. */
+	pci_probe &= ~PCI_PROBE_BIOS;
+#endif
 	xen_raw_console_write("about to get started...\n");
 
 	xen_setup_runstate_info(0);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 988828b479ed..69f5857660ac 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -353,8 +353,13 @@ static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
 	if (val & _PAGE_PRESENT) {
 		unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
+		unsigned long pfn = mfn_to_pfn(mfn);
+
 		pteval_t flags = val & PTE_FLAGS_MASK;
-		val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+		if (unlikely(pfn == ~0))
+			val = flags & ~_PAGE_PRESENT;
+		else
+			val = ((pteval_t)pfn << PAGE_SHIFT) | flags;
 	}
 
 	return val;
@@ -1859,6 +1864,7 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 #endif	/* CONFIG_X86_64 */
 
 static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;
+static unsigned char fake_ioapic_mapping[PAGE_SIZE] __page_aligned_bss;
 
 static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 {
@@ -1899,7 +1905,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 		 * We just don't map the IO APIC - all access is via
 		 * hypercalls.  Keep the address in the pte for reference.
 		 */
-		pte = pfn_pte(PFN_DOWN(__pa(dummy_mapping)), PAGE_KERNEL);
+		pte = pfn_pte(PFN_DOWN(__pa(fake_ioapic_mapping)), PAGE_KERNEL);
 		break;
 #endif
 
@@ -2064,6 +2070,7 @@ void __init xen_init_mmu_ops(void)
 	pv_mmu_ops = xen_mmu_ops;
 
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
+	memset(fake_ioapic_mapping, 0xfd, PAGE_SIZE);
 }
 
 /* Protected by xen_reservation_lock. */
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index b480d4207a4c..967633ad98c4 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -12,8 +12,8 @@ int xen_swiotlb __read_mostly;
 
 static struct dma_map_ops xen_swiotlb_dma_ops = {
 	.mapping_error = xen_swiotlb_dma_mapping_error,
-	.alloc_coherent = xen_swiotlb_alloc_coherent,
-	.free_coherent = xen_swiotlb_free_coherent,
+	.alloc = xen_swiotlb_alloc_coherent,
+	.free = xen_swiotlb_free_coherent,
 	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
 	.sync_single_for_device = xen_swiotlb_sync_single_for_device,
 	.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 02900e8ce26c..0503c0c493a9 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -59,7 +59,7 @@ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 
 static void __cpuinit cpu_bringup(void)
 {
-	int cpu = smp_processor_id();
+	int cpu;
 
 	cpu_init();
 	touch_softlockup_watchdog();
@@ -178,6 +178,7 @@ static void __init xen_fill_possible_map(void)
 static void __init xen_filter_cpu_maps(void)
 {
 	int i, rc;
+	unsigned int subtract = 0;
 
 	if (!xen_initial_domain())
 		return;
@@ -192,8 +193,22 @@ static void __init xen_filter_cpu_maps(void)
 		} else {
 			set_cpu_possible(i, false);
 			set_cpu_present(i, false);
+			subtract++;
 		}
 	}
+#ifdef CONFIG_HOTPLUG_CPU
+	/* This is akin to using 'nr_cpus' on the Linux command line.
+	 * Which is OK as when we use 'dom0_max_vcpus=X' we can only
+	 * have up to X, while nr_cpu_ids is greater than X. This
+	 * normally is not a problem, except when CPU hotplugging
+	 * is involved and then there might be more than X CPUs
+	 * in the guest - which will not work as there is no
+	 * hypercall to expand the max number of VCPUs an already
+	 * running guest has. So cap it up to X. */
+	if (subtract)
+		nr_cpu_ids = nr_cpu_ids - subtract;
+#endif
+
 }
 
 static void __init xen_smp_prepare_boot_cpu(void)
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 79d7362ad6d1..3e45aa000718 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -96,7 +96,7 @@ ENTRY(xen_restore_fl_direct)
 
 	/* check for unmasked and pending */
 	cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
-	jz 1f
+	jnz 1f
 2:	call check_events
 1:
 ENDPATCH(xen_restore_fl_direct)