Merge branch 'for-linus' of git://xenbits.xen.org/people/sstabellini/…

…linux-pvhvm

* 'for-linus' of git://xenbits.xen.org/people/sstabellini/linux-pvhvm:
  xen: suspend: remove xen_hvm_suspend
  xen: suspend: pull pre/post suspend hooks out into suspend_info
  xen: suspend: move arch specific pre/post suspend hooks into generic hooks
  xen: suspend: refactor non-arch specific pre/post suspend hooks
  xen: suspend: add "arch" to pre/post suspend hooks
  xen: suspend: pass extra hypercall argument via suspend_info struct
  xen: suspend: refactor cancellation flag into a structure
  xen: suspend: use HYPERVISOR_suspend for PVHVM case instead of open coding
  xen: switch to new schedop hypercall by default.
  xen: use new schedop interface for suspend
  xen: do not respond to unknown xenstore control requests
  xen: fix compile issue if XEN is enabled but XEN_PVHVM is disabled
  xen: PV on HVM: support PV spinlocks and IPIs
  xen: make the ballon driver work for hvm domains
  xen-blkfront: handle Xen major numbers other than XENVBD
  xen: do not use xen_info on HVM, set pv_info name to "Xen HVM"
  xen: no need to delay xen_setup_shutdown_event for hvm guests anymore

arch/ia64/xen/suspend.c

@@ -37,19 +37,14 @@ xen_mm_unpin_all(void)
 	/* nothing */
 }
 
-void xen_pre_device_suspend(void)
-{
-	/* nothing */
-}
-
 void
-xen_pre_suspend()
+xen_arch_pre_suspend()
 {
 	/* nothing */
 }
 
 void
-xen_post_suspend(int suspend_cancelled)
+xen_arch_post_suspend(int suspend_cancelled)
 {
 	if (suspend_cancelled)
 		return;

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

@@ -287,7 +287,7 @@ HYPERVISOR_fpu_taskswitch(int set)
 static inline int
 HYPERVISOR_sched_op(int cmd, void *arg)
 {
-	return _hypercall2(int, sched_op_new, cmd, arg);
+	return _hypercall2(int, sched_op, cmd, arg);
 }
 
 static inline long
@@ -422,10 +422,17 @@ HYPERVISOR_set_segment_base(int reg, unsigned long value)
 #endif
 
 static inline int
-HYPERVISOR_suspend(unsigned long srec)
+HYPERVISOR_suspend(unsigned long start_info_mfn)
 {
-	return _hypercall3(int, sched_op, SCHEDOP_shutdown,
-			   SHUTDOWN_suspend, srec);
+	struct sched_shutdown r = { .reason = SHUTDOWN_suspend };
+
+	/*
+	 * For a PV guest the tools require that the start_info mfn be
+	 * present in rdx/edx when the hypercall is made. Per the
+	 * hypercall calling convention this is the third hypercall
+	 * argument, which is start_info_mfn here.
+	 */
+	return _hypercall3(int, sched_op, SCHEDOP_shutdown, &r, start_info_mfn);
 }
 
 static inline int

arch/x86/xen/enlighten.c

@@ -1284,8 +1284,7 @@ static int init_hvm_pv_info(int *major, int *minor)
 
 	xen_setup_features();
 
-	pv_info = xen_info;
-	pv_info.kernel_rpl = 0;
+	pv_info.name = "Xen HVM";
 
 	xen_domain_type = XEN_HVM_DOMAIN;
 
@@ -1331,6 +1330,8 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_UP_PREPARE:
 		per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+		if (xen_have_vector_callback)
+			xen_init_lock_cpu(cpu);
 		break;
 	default:
 		break;
@@ -1355,6 +1356,7 @@ static void __init xen_hvm_guest_init(void)
 
 	if (xen_feature(XENFEAT_hvm_callback_vector))
 		xen_have_vector_callback = 1;
+	xen_hvm_smp_init();
 	register_cpu_notifier(&xen_hvm_cpu_notifier);
 	xen_unplug_emulated_devices();
 	have_vcpu_info_placement = 0;

arch/x86/xen/smp.c

@@ -509,3 +509,41 @@ void __init xen_smp_init(void)
 	xen_fill_possible_map();
 	xen_init_spinlocks();
 }
+
+static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
+{
+	native_smp_prepare_cpus(max_cpus);
+	WARN_ON(xen_smp_intr_init(0));
+
+	if (!xen_have_vector_callback)
+		return;
+	xen_init_lock_cpu(0);
+	xen_init_spinlocks();
+}
+
+static int __cpuinit xen_hvm_cpu_up(unsigned int cpu)
+{
+	int rc;
+	rc = native_cpu_up(cpu);
+	WARN_ON (xen_smp_intr_init(cpu));
+	return rc;
+}
+
+static void xen_hvm_cpu_die(unsigned int cpu)
+{
+	unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
+	unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
+	unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
+	unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
+	native_cpu_die(cpu);
+}
+
+void __init xen_hvm_smp_init(void)
+{
+	smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
+	smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
+	smp_ops.cpu_up = xen_hvm_cpu_up;
+	smp_ops.cpu_die = xen_hvm_cpu_die;
+	smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
+	smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
+}

arch/x86/xen/suspend.c

@@ -12,7 +12,7 @@
 #include "xen-ops.h"
 #include "mmu.h"
 
-void xen_pre_suspend(void)
+void xen_arch_pre_suspend(void)
 {
 	xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn);
 	xen_start_info->console.domU.mfn =
@@ -26,8 +26,9 @@ void xen_pre_suspend(void)
 		BUG();
 }
 
-void xen_hvm_post_suspend(int suspend_cancelled)
+void xen_arch_hvm_post_suspend(int suspend_cancelled)
 {
+#ifdef CONFIG_XEN_PVHVM
 	int cpu;
 	xen_hvm_init_shared_info();
 	xen_callback_vector();
@@ -37,9 +38,10 @@ void xen_hvm_post_suspend(int suspend_cancelled)
 			xen_setup_runstate_info(cpu);
 		}
 	}
+#endif
 }
 
-void xen_post_suspend(int suspend_cancelled)
+void xen_arch_post_suspend(int suspend_cancelled)
 {
 	xen_build_mfn_list_list();
 

arch/x86/xen/xen-ops.h

@@ -64,10 +64,12 @@ void xen_setup_vcpu_info_placement(void);
 
 #ifdef CONFIG_SMP
 void xen_smp_init(void);
+void __init xen_hvm_smp_init(void);
 
 extern cpumask_var_t xen_cpu_initialized_map;
 #else
 static inline void xen_smp_init(void) {}
+static inline void xen_hvm_smp_init(void) {}
 #endif
 
 #ifdef CONFIG_PARAVIRT_SPINLOCKS

drivers/block/xen-blkfront.c

@@ -120,6 +120,10 @@ static DEFINE_SPINLOCK(minor_lock);
 #define EXTENDED (1<<EXT_SHIFT)
 #define VDEV_IS_EXTENDED(dev) ((dev)&(EXTENDED))
 #define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED))
+#define EMULATED_HD_DISK_MINOR_OFFSET (0)
+#define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256)
+#define EMULATED_SD_DISK_MINOR_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET + (4 * 16))
+#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_HD_DISK_NAME_OFFSET + 4)
 
 #define DEV_NAME	"xvd"	/* name in /dev */
 
@@ -434,14 +438,73 @@ static void xlvbd_flush(struct blkfront_info *info)
 	       info->feature_flush ? "enabled" : "disabled");
 }
 
+static int xen_translate_vdev(int vdevice, int *minor, unsigned int *offset)
+{
+	int major;
+	major = BLKIF_MAJOR(vdevice);
+	*minor = BLKIF_MINOR(vdevice);
+	switch (major) {
+		case XEN_IDE0_MAJOR:
+			*offset = (*minor / 64) + EMULATED_HD_DISK_NAME_OFFSET;
+			*minor = ((*minor / 64) * PARTS_PER_DISK) +
+				EMULATED_HD_DISK_MINOR_OFFSET;
+			break;
+		case XEN_IDE1_MAJOR:
+			*offset = (*minor / 64) + 2 + EMULATED_HD_DISK_NAME_OFFSET;
+			*minor = (((*minor / 64) + 2) * PARTS_PER_DISK) +
+				EMULATED_HD_DISK_MINOR_OFFSET;
+			break;
+		case XEN_SCSI_DISK0_MAJOR:
+			*offset = (*minor / PARTS_PER_DISK) + EMULATED_SD_DISK_NAME_OFFSET;
+			*minor = *minor + EMULATED_SD_DISK_MINOR_OFFSET;
+			break;
+		case XEN_SCSI_DISK1_MAJOR:
+		case XEN_SCSI_DISK2_MAJOR:
+		case XEN_SCSI_DISK3_MAJOR:
+		case XEN_SCSI_DISK4_MAJOR:
+		case XEN_SCSI_DISK5_MAJOR:
+		case XEN_SCSI_DISK6_MAJOR:
+		case XEN_SCSI_DISK7_MAJOR:
+			*offset = (*minor / PARTS_PER_DISK) + 
+				((major - XEN_SCSI_DISK1_MAJOR + 1) * 16) +
+				EMULATED_SD_DISK_NAME_OFFSET;
+			*minor = *minor +
+				((major - XEN_SCSI_DISK1_MAJOR + 1) * 16 * PARTS_PER_DISK) +
+				EMULATED_SD_DISK_MINOR_OFFSET;
+			break;
+		case XEN_SCSI_DISK8_MAJOR:
+		case XEN_SCSI_DISK9_MAJOR:
+		case XEN_SCSI_DISK10_MAJOR:
+		case XEN_SCSI_DISK11_MAJOR:
+		case XEN_SCSI_DISK12_MAJOR:
+		case XEN_SCSI_DISK13_MAJOR:
+		case XEN_SCSI_DISK14_MAJOR:
+		case XEN_SCSI_DISK15_MAJOR:
+			*offset = (*minor / PARTS_PER_DISK) + 
+				((major - XEN_SCSI_DISK8_MAJOR + 8) * 16) +
+				EMULATED_SD_DISK_NAME_OFFSET;
+			*minor = *minor +
+				((major - XEN_SCSI_DISK8_MAJOR + 8) * 16 * PARTS_PER_DISK) +
+				EMULATED_SD_DISK_MINOR_OFFSET;
+			break;
+		case XENVBD_MAJOR:
+			*offset = *minor / PARTS_PER_DISK;
+			break;
+		default:
+			printk(KERN_WARNING "blkfront: your disk configuration is "
+					"incorrect, please use an xvd device instead\n");
+			return -ENODEV;
+	}
+	return 0;
+}
 
 static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 			       struct blkfront_info *info,
 			       u16 vdisk_info, u16 sector_size)
 {
 	struct gendisk *gd;
 	int nr_minors = 1;
-	int err = -ENODEV;
+	int err;
 	unsigned int offset;
 	int minor;
 	int nr_parts;
@@ -456,12 +519,20 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	}
 
 	if (!VDEV_IS_EXTENDED(info->vdevice)) {
-		minor = BLKIF_MINOR(info->vdevice);
-		nr_parts = PARTS_PER_DISK;
+		err = xen_translate_vdev(info->vdevice, &minor, &offset);
+		if (err)
+			return err;		
+ 		nr_parts = PARTS_PER_DISK;
 	} else {
 		minor = BLKIF_MINOR_EXT(info->vdevice);
 		nr_parts = PARTS_PER_EXT_DISK;
+		offset = minor / nr_parts;
+		if (xen_hvm_domain() && offset <= EMULATED_HD_DISK_NAME_OFFSET + 4)
+			printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with "
+					"emulated IDE disks,\n\t choose an xvd device name"
+					"from xvde on\n", info->vdevice);
 	}
+	err = -ENODEV;
 
 	if ((minor % nr_parts) == 0)
 		nr_minors = nr_parts;
@@ -475,8 +546,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 	if (gd == NULL)
 		goto release;
 
-	offset = minor / nr_parts;
-
 	if (nr_minors > 1) {
 		if (offset < 26)
 			sprintf(gd->disk_name, "%s%c", DEV_NAME, 'a' + offset);

drivers/xen/balloon.c

@@ -232,7 +232,7 @@ static int increase_reservation(unsigned long nr_pages)
 		set_phys_to_machine(pfn, frame_list[i]);
 
 		/* Link back into the page tables if not highmem. */
-		if (pfn < max_low_pfn) {
+		if (!xen_hvm_domain() && pfn < max_low_pfn) {
 			int ret;
 			ret = HYPERVISOR_update_va_mapping(
 				(unsigned long)__va(pfn << PAGE_SHIFT),
@@ -280,7 +280,7 @@ static int decrease_reservation(unsigned long nr_pages)
 
 		scrub_page(page);
 
-		if (!PageHighMem(page)) {
+		if (!xen_hvm_domain() && !PageHighMem(page)) {
 			ret = HYPERVISOR_update_va_mapping(
 				(unsigned long)__va(pfn << PAGE_SHIFT),
 				__pte_ma(0), 0);
@@ -392,15 +392,19 @@ static struct notifier_block xenstore_notifier;
 
 static int __init balloon_init(void)
 {
-	unsigned long pfn, extra_pfn_end;
+ 	unsigned long pfn, nr_pages, extra_pfn_end;
 	struct page *page;
 
-	if (!xen_pv_domain())
+	if (!xen_domain())
 		return -ENODEV;
 
 	pr_info("xen_balloon: Initialising balloon driver.\n");
 
-	balloon_stats.current_pages = min(xen_start_info->nr_pages, max_pfn);
+ 	if (xen_pv_domain())
+ 		nr_pages = xen_start_info->nr_pages;
+ 	else
+ 		nr_pages = max_pfn;
+ 	balloon_stats.current_pages = min(nr_pages, max_pfn);
 	balloon_stats.target_pages  = balloon_stats.current_pages;
 	balloon_stats.balloon_low   = 0;
 	balloon_stats.balloon_high  = 0;