Merge branch 'perf/urgent' into perf/core

Conflicts:
	tools/perf/util/python.c

Merge reason: resolve the conflict with perf/urgent.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

Documentation/kernel-parameters.txt

@@ -999,7 +999,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			With this option on every unmap_single operation will
 			result in a hardware IOTLB flush operation as opposed
 			to batching them for performance.
-
+		sp_off [Default Off]
+			By default, super page will be supported if Intel IOMMU
+			has the capability. With this option, super page will
+			not be supported.
 	intremap=	[X86-64, Intel-IOMMU]
 			Format: { on (default) | off | nosid }
 			on	enable Interrupt Remapping (default)

Documentation/virtual/lguest/Makefile

@@ -1,5 +1,5 @@
 # This creates the demonstration utility "lguest" which runs a Linux guest.
-# Missing headers?  Add "-I../../include -I../../arch/x86/include"
+# Missing headers?  Add "-I../../../include -I../../../arch/x86/include"
 CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE
 
 all: lguest

Documentation/virtual/lguest/lguest.c

@@ -49,7 +49,7 @@
 #include <linux/virtio_rng.h>
 #include <linux/virtio_ring.h>
 #include <asm/bootparam.h>
-#include "../../include/linux/lguest_launcher.h"
+#include "../../../include/linux/lguest_launcher.h"
 /*L:110
  * We can ignore the 42 include files we need for this program, but I do want
  * to draw attention to the use of kernel-style types.
@@ -135,9 +135,6 @@ struct device {
 	/* Is it operational */
 	bool running;
 
-	/* Does Guest want an intrrupt on empty? */
-	bool irq_on_empty;
-
 	/* Device-specific data. */
 	void *priv;
 };
@@ -637,10 +634,7 @@ static void trigger_irq(struct virtqueue *vq)
 
 	/* If they don't want an interrupt, don't send one... */
 	if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) {
-		/* ... unless they've asked us to force one on empty. */
-		if (!vq->dev->irq_on_empty
-		    || lg_last_avail(vq) != vq->vring.avail->idx)
-			return;
+		return;
 	}
 
 	/* Send the Guest an interrupt tell them we used something up. */
@@ -1057,15 +1051,6 @@ static void create_thread(struct virtqueue *vq)
 	close(vq->eventfd);
 }
 
-static bool accepted_feature(struct device *dev, unsigned int bit)
-{
-	const u8 *features = get_feature_bits(dev) + dev->feature_len;
-
-	if (dev->feature_len < bit / CHAR_BIT)
-		return false;
-	return features[bit / CHAR_BIT] & (1 << (bit % CHAR_BIT));
-}
-
 static void start_device(struct device *dev)
 {
 	unsigned int i;
@@ -1079,8 +1064,6 @@ static void start_device(struct device *dev)
 		verbose(" %02x", get_feature_bits(dev)
 			[dev->feature_len+i]);
 
-	dev->irq_on_empty = accepted_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
-
 	for (vq = dev->vq; vq; vq = vq->next) {
 		if (vq->service)
 			create_thread(vq);
@@ -1564,7 +1547,6 @@ static void setup_tun_net(char *arg)
 	/* Set up the tun device. */
 	configure_device(ipfd, tapif, ip);
 
-	add_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
 	/* Expect Guest to handle everything except UFO */
 	add_feature(dev, VIRTIO_NET_F_CSUM);
 	add_feature(dev, VIRTIO_NET_F_GUEST_CSUM);

arch/ia64/include/asm/unistd.h

@@ -320,11 +320,12 @@
 #define __NR_clock_adjtime		1328
 #define __NR_syncfs			1329
 #define __NR_setns			1330
+#define __NR_sendmmsg			1331
 
 #ifdef __KERNEL__
 
 
-#define NR_syscalls			307 /* length of syscall table */
+#define NR_syscalls			308 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about

arch/ia64/kernel/entry.S

@@ -1776,6 +1776,7 @@ sys_call_table:
 	data8 sys_clock_adjtime
 	data8 sys_syncfs
 	data8 sys_setns				// 1330
+	data8 sys_sendmmsg
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
 #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */

arch/powerpc/platforms/powermac/pic.c

@@ -715,7 +715,8 @@ static struct syscore_ops pmacpic_syscore_ops = {
 
 static int __init init_pmacpic_syscore(void)
 {
-	register_syscore_ops(&pmacpic_syscore_ops);
+	if (pmac_irq_hw[0])
+		register_syscore_ops(&pmacpic_syscore_ops);
 	return 0;
 }
 

arch/x86/kernel/Makefile

@@ -8,6 +8,7 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not profile debug and lowlevel utilities
+CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_pvclock.o = -pg
@@ -28,6 +29,7 @@ CFLAGS_paravirt.o	:= $(nostackp)
 GCOV_PROFILE_vsyscall_64.o	:= n
 GCOV_PROFILE_hpet.o		:= n
 GCOV_PROFILE_tsc.o		:= n
+GCOV_PROFILE_vread_tsc_64.o	:= n
 GCOV_PROFILE_paravirt.o		:= n
 
 # vread_tsc_64 is hot and should be fully optimized:

arch/x86/kernel/process.c

@@ -642,7 +642,7 @@ static int __init idle_setup(char *str)
 		boot_option_idle_override = IDLE_POLL;
 	} else if (!strcmp(str, "mwait")) {
 		boot_option_idle_override = IDLE_FORCE_MWAIT;
-		WARN_ONCE(1, "\idle=mwait\" will be removed in 2012\"\n");
+		WARN_ONCE(1, "\"idle=mwait\" will be removed in 2012\n");
 	} else if (!strcmp(str, "halt")) {
 		/*
 		 * When the boot option of idle=halt is added, halt is

arch/x86/kernel/smpboot.c

@@ -1332,7 +1332,7 @@ static inline void mwait_play_dead(void)
 	void *mwait_ptr;
 	struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info);
 
-	if (!this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c))
+	if (!(this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c)))
 		return;
 	if (!this_cpu_has(X86_FEATURE_CLFLSH))
 		return;

arch/x86/lguest/boot.c

@@ -993,6 +993,7 @@ static void lguest_time_irq(unsigned int irq, struct irq_desc *desc)
 static void lguest_time_init(void)
 {
 	/* Set up the timer interrupt (0) to go to our simple timer routine */
+	lguest_setup_irq(0);
 	irq_set_handler(0, lguest_time_irq);
 
 	clocksource_register_hz(&lguest_clock, NSEC_PER_SEC);

drivers/block/paride/pcd.c

@@ -321,7 +321,6 @@ static void pcd_init_units(void)
 		strcpy(disk->disk_name, cd->name);	/* umm... */
 		disk->fops = &pcd_bdops;
 		disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-		disk->events = DISK_EVENT_MEDIA_CHANGE;
 	}
 }
 

drivers/block/virtio_blk.c

@@ -6,10 +6,13 @@
 #include <linux/virtio.h>
 #include <linux/virtio_blk.h>
 #include <linux/scatterlist.h>
+#include <linux/string_helpers.h>
+#include <scsi/scsi_cmnd.h>
 
 #define PART_BITS 4
 
 static int major, index;
+struct workqueue_struct *virtblk_wq;
 
 struct virtio_blk
 {
@@ -26,6 +29,9 @@ struct virtio_blk
 
 	mempool_t *pool;
 
+	/* Process context for config space updates */
+	struct work_struct config_work;
+
 	/* What host tells us, plus 2 for header & tailer. */
 	unsigned int sg_elems;
 
@@ -141,7 +147,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 	num = blk_rq_map_sg(q, vbr->req, vblk->sg + out);
 
 	if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC) {
-		sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, 96);
+		sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
 		sg_set_buf(&vblk->sg[num + out + in++], &vbr->in_hdr,
 			   sizeof(vbr->in_hdr));
 	}
@@ -291,6 +297,46 @@ static ssize_t virtblk_serial_show(struct device *dev,
 }
 DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
 
+static void virtblk_config_changed_work(struct work_struct *work)
+{
+	struct virtio_blk *vblk =
+		container_of(work, struct virtio_blk, config_work);
+	struct virtio_device *vdev = vblk->vdev;
+	struct request_queue *q = vblk->disk->queue;
+	char cap_str_2[10], cap_str_10[10];
+	u64 capacity, size;
+
+	/* Host must always specify the capacity. */
+	vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity),
+			  &capacity, sizeof(capacity));
+
+	/* If capacity is too big, truncate with warning. */
+	if ((sector_t)capacity != capacity) {
+		dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
+			 (unsigned long long)capacity);
+		capacity = (sector_t)-1;
+	}
+
+	size = capacity * queue_logical_block_size(q);
+	string_get_size(size, STRING_UNITS_2, cap_str_2, sizeof(cap_str_2));
+	string_get_size(size, STRING_UNITS_10, cap_str_10, sizeof(cap_str_10));
+
+	dev_notice(&vdev->dev,
+		  "new size: %llu %d-byte logical blocks (%s/%s)\n",
+		  (unsigned long long)capacity,
+		  queue_logical_block_size(q),
+		  cap_str_10, cap_str_2);
+
+	set_capacity(vblk->disk, capacity);
+}
+
+static void virtblk_config_changed(struct virtio_device *vdev)
+{
+	struct virtio_blk *vblk = vdev->priv;
+
+	queue_work(virtblk_wq, &vblk->config_work);
+}
+
 static int __devinit virtblk_probe(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk;
@@ -327,6 +373,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 	vblk->vdev = vdev;
 	vblk->sg_elems = sg_elems;
 	sg_init_table(vblk->sg, vblk->sg_elems);
+	INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
 
 	/* We expect one virtqueue, for output. */
 	vblk->vq = virtio_find_single_vq(vdev, blk_done, "requests");
@@ -477,6 +524,8 @@ static void __devexit virtblk_remove(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk = vdev->priv;
 
+	flush_work(&vblk->config_work);
+
 	/* Nothing should be pending. */
 	BUG_ON(!list_empty(&vblk->reqs));
 
@@ -508,27 +557,47 @@ static unsigned int features[] = {
  * Use __refdata to avoid this warning.
  */
 static struct virtio_driver __refdata virtio_blk = {
-	.feature_table = features,
-	.feature_table_size = ARRAY_SIZE(features),
-	.driver.name =	KBUILD_MODNAME,
-	.driver.owner =	THIS_MODULE,
-	.id_table =	id_table,
-	.probe =	virtblk_probe,
-	.remove =	__devexit_p(virtblk_remove),
+	.feature_table		= features,
+	.feature_table_size	= ARRAY_SIZE(features),
+	.driver.name		= KBUILD_MODNAME,
+	.driver.owner		= THIS_MODULE,
+	.id_table		= id_table,
+	.probe			= virtblk_probe,
+	.remove			= __devexit_p(virtblk_remove),
+	.config_changed		= virtblk_config_changed,
 };
 
 static int __init init(void)
 {
+	int error;
+
+	virtblk_wq = alloc_workqueue("virtio-blk", 0, 0);
+	if (!virtblk_wq)
+		return -ENOMEM;
+
 	major = register_blkdev(0, "virtblk");
-	if (major < 0)
-		return major;
-	return register_virtio_driver(&virtio_blk);
+	if (major < 0) {
+		error = major;
+		goto out_destroy_workqueue;
+	}
+
+	error = register_virtio_driver(&virtio_blk);
+	if (error)
+		goto out_unregister_blkdev;
+	return 0;
+
+out_unregister_blkdev:
+	unregister_blkdev(major, "virtblk");
+out_destroy_workqueue:
+	destroy_workqueue(virtblk_wq);
+	return error;
 }
 
 static void __exit fini(void)
 {
 	unregister_blkdev(major, "virtblk");
 	unregister_virtio_driver(&virtio_blk);
+	destroy_workqueue(virtblk_wq);
 }
 module_init(init);
 module_exit(fini);

drivers/cdrom/viocd.c

@@ -627,7 +627,6 @@ static int viocd_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	gendisk->fops = &viocd_fops;
 	gendisk->flags = GENHD_FL_CD | GENHD_FL_REMOVABLE |
 			 GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-	gendisk->events = DISK_EVENT_MEDIA_CHANGE;
 	set_capacity(gendisk, 0);
 	gendisk->private_data = d;
 	d->viocd_disk = gendisk;

drivers/char/virtio_console.c

@@ -1677,17 +1677,12 @@ static int __devinit virtcons_probe(struct virtio_device *vdev)
 	portdev->config.max_nr_ports = 1;
 	if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT)) {
 		multiport = true;
-		vdev->features[0] |= 1 << VIRTIO_CONSOLE_F_MULTIPORT;
-
 		vdev->config->get(vdev, offsetof(struct virtio_console_config,
 						 max_nr_ports),
 				  &portdev->config.max_nr_ports,
 				  sizeof(portdev->config.max_nr_ports));
 	}
 
-	/* Let the Host know we support multiple ports.*/
-	vdev->config->finalize_features(vdev);
-
 	err = init_vqs(portdev);
 	if (err < 0) {
 		dev_err(&vdev->dev, "Error %d initializing vqs\n", err);

drivers/ide/ide-cd.c

@@ -1782,7 +1782,6 @@ static int ide_cd_probe(ide_drive_t *drive)
 	ide_cd_read_toc(drive, &sense);
 	g->fops = &idecd_ops;
 	g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-	g->events = DISK_EVENT_MEDIA_CHANGE;
 	add_disk(g);
 	return 0;
 

drivers/misc/kgdbts.c

@@ -304,7 +304,10 @@ static int check_and_rewind_pc(char *put_str, char *arg)
 		return 1;
 	}
 	/* Readjust the instruction pointer if needed */
-	instruction_pointer_set(&kgdbts_regs, ip + offset);
+	ip += offset;
+#ifdef GDB_ADJUSTS_BREAK_OFFSET
+	instruction_pointer_set(&kgdbts_regs, ip);
+#endif
 	return 0;
 }
 

drivers/net/virtio_net.c

@@ -609,7 +609,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * before it gets out of hand.  Naturally, this wastes entries. */
 	if (capacity < 2+MAX_SKB_FRAGS) {
 		netif_stop_queue(dev);
-		if (unlikely(!virtqueue_enable_cb(vi->svq))) {
+		if (unlikely(!virtqueue_enable_cb_delayed(vi->svq))) {
 			/* More just got used, free them then recheck. */
 			capacity += free_old_xmit_skbs(vi);
 			if (capacity >= 2+MAX_SKB_FRAGS) {

drivers/pci/dmar.c

@@ -698,12 +698,7 @@ int __init detect_intel_iommu(void)
 	{
 #ifdef CONFIG_INTR_REMAP
 		struct acpi_table_dmar *dmar;
-		/*
-		 * for now we will disable dma-remapping when interrupt
-		 * remapping is enabled.
-		 * When support for queued invalidation for IOTLB invalidation
-		 * is added, we will not need this any more.
-		 */
+
 		dmar = (struct acpi_table_dmar *) dmar_tbl;
 		if (ret && cpu_has_x2apic && dmar->flags & 0x1)
 			printk(KERN_INFO

drivers/pci/intel-iommu.c

@@ -47,6 +47,8 @@
 #define ROOT_SIZE		VTD_PAGE_SIZE
 #define CONTEXT_SIZE		VTD_PAGE_SIZE
 
+#define IS_BRIDGE_HOST_DEVICE(pdev) \
+			    ((pdev->class >> 8) == PCI_CLASS_BRIDGE_HOST)
 #define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
 #define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
 #define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e)
@@ -116,6 +118,11 @@ static inline unsigned long align_to_level(unsigned long pfn, int level)
 	return (pfn + level_size(level) - 1) & level_mask(level);
 }
 
+static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
+{
+	return  1 << ((lvl - 1) * LEVEL_STRIDE);
+}
+
 /* VT-d pages must always be _smaller_ than MM pages. Otherwise things
    are never going to work. */
 static inline unsigned long dma_to_mm_pfn(unsigned long dma_pfn)
@@ -142,6 +149,12 @@ static struct intel_iommu **g_iommus;
 static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
 
+/*
+ * set to 1 to panic kernel if can't successfully enable VT-d
+ * (used when kernel is launched w/ TXT)
+ */
+static int force_on = 0;
+
 /*
  * 0: Present
  * 1-11: Reserved
@@ -338,6 +351,9 @@ struct dmar_domain {
 	int		iommu_coherency;/* indicate coherency of iommu access */
 	int		iommu_snooping; /* indicate snooping control feature*/
 	int		iommu_count;	/* reference count of iommu */
+	int		iommu_superpage;/* Level of superpages supported:
+					   0 == 4KiB (no superpages), 1 == 2MiB,
+					   2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
 	spinlock_t	iommu_lock;	/* protect iommu set in domain */
 	u64		max_addr;	/* maximum mapped address */
 };
@@ -387,6 +403,7 @@ int dmar_disabled = 1;
 static int dmar_map_gfx = 1;
 static int dmar_forcedac;
 static int intel_iommu_strict;
+static int intel_iommu_superpage = 1;
 
 #define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
 static DEFINE_SPINLOCK(device_domain_lock);
@@ -417,6 +434,10 @@ static int __init intel_iommu_setup(char *str)
 			printk(KERN_INFO
 				"Intel-IOMMU: disable batched IOTLB flush\n");
 			intel_iommu_strict = 1;
+		} else if (!strncmp(str, "sp_off", 6)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: disable supported super page\n");
+			intel_iommu_superpage = 0;
 		}
 
 		str += strcspn(str, ",");
@@ -555,11 +576,32 @@ static void domain_update_iommu_snooping(struct dmar_domain *domain)
 	}
 }
 
+static void domain_update_iommu_superpage(struct dmar_domain *domain)
+{
+	int i, mask = 0xf;
+
+	if (!intel_iommu_superpage) {
+		domain->iommu_superpage = 0;
+		return;
+	}
+
+	domain->iommu_superpage = 4; /* 1TiB */
+
+	for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) {
+		mask |= cap_super_page_val(g_iommus[i]->cap);
+		if (!mask) {
+			break;
+		}
+	}
+	domain->iommu_superpage = fls(mask);
+}
+
 /* Some capabilities may be different across iommus */
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
 	domain_update_iommu_coherency(domain);
 	domain_update_iommu_snooping(domain);
+	domain_update_iommu_superpage(domain);
 }
 
 static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
@@ -689,23 +731,31 @@ out:
 }
 
 static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
-				      unsigned long pfn)
+				      unsigned long pfn, int large_level)
 {
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
 	struct dma_pte *parent, *pte = NULL;
 	int level = agaw_to_level(domain->agaw);
-	int offset;
+	int offset, target_level;
 
 	BUG_ON(!domain->pgd);
 	BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width);
 	parent = domain->pgd;
 
+	/* Search pte */
+	if (!large_level)
+		target_level = 1;
+	else
+		target_level = large_level;
+
 	while (level > 0) {
 		void *tmp_page;
 
 		offset = pfn_level_offset(pfn, level);
 		pte = &parent[offset];
-		if (level == 1)
+		if (!large_level && (pte->val & DMA_PTE_LARGE_PAGE))
+			break;
+		if (level == target_level)
 			break;
 
 		if (!dma_pte_present(pte)) {
@@ -733,10 +783,11 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
 	return pte;
 }
 
+
 /* return address's pte at specific level */
 static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain,
 					 unsigned long pfn,
-					 int level)
+					 int level, int *large_page)
 {
 	struct dma_pte *parent, *pte = NULL;
 	int total = agaw_to_level(domain->agaw);
@@ -749,8 +800,16 @@ static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain,
 		if (level == total)
 			return pte;
 
-		if (!dma_pte_present(pte))
+		if (!dma_pte_present(pte)) {
+			*large_page = total;
 			break;
+		}
+
+		if (pte->val & DMA_PTE_LARGE_PAGE) {
+			*large_page = total;
+			return pte;
+		}
+
 		parent = phys_to_virt(dma_pte_addr(pte));
 		total--;
 	}
@@ -763,6 +822,7 @@ static void dma_pte_clear_range(struct dmar_domain *domain,
 				unsigned long last_pfn)
 {
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
+	unsigned int large_page = 1;
 	struct dma_pte *first_pte, *pte;
 
 	BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
@@ -771,14 +831,15 @@ static void dma_pte_clear_range(struct dmar_domain *domain,
 
 	/* we don't need lock here; nobody else touches the iova range */
 	do {
-		first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1);
+		large_page = 1;
+		first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1, &large_page);
 		if (!pte) {
-			start_pfn = align_to_level(start_pfn + 1, 2);
+			start_pfn = align_to_level(start_pfn + 1, large_page + 1);
 			continue;
 		}
-		do { 
+		do {
 			dma_clear_pte(pte);
-			start_pfn++;
+			start_pfn += lvl_to_nr_pages(large_page);
 			pte++;
 		} while (start_pfn <= last_pfn && !first_pte_in_page(pte));
 
@@ -798,6 +859,7 @@ static void dma_pte_free_pagetable(struct dmar_domain *domain,
 	int total = agaw_to_level(domain->agaw);
 	int level;
 	unsigned long tmp;
+	int large_page = 2;
 
 	BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
 	BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width);
@@ -813,7 +875,10 @@ static void dma_pte_free_pagetable(struct dmar_domain *domain,
 			return;
 
 		do {
-			first_pte = pte = dma_pfn_level_pte(domain, tmp, level);
+			large_page = level;
+			first_pte = pte = dma_pfn_level_pte(domain, tmp, level, &large_page);
+			if (large_page > level)
+				level = large_page + 1;
 			if (!pte) {
 				tmp = align_to_level(tmp + 1, level + 1);
 				continue;
@@ -1397,6 +1462,7 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 	else
 		domain->iommu_snooping = 0;
 
+	domain->iommu_superpage = fls(cap_super_page_val(iommu->cap));
 	domain->iommu_count = 1;
 	domain->nid = iommu->node;
 
@@ -1417,6 +1483,10 @@ static void domain_exit(struct dmar_domain *domain)
 	if (!domain)
 		return;
 
+	/* Flush any lazy unmaps that may reference this domain */
+	if (!intel_iommu_strict)
+		flush_unmaps_timeout(0);
+
 	domain_remove_dev_info(domain);
 	/* destroy iovas */
 	put_iova_domain(&domain->iovad);
@@ -1648,6 +1718,34 @@ static inline unsigned long aligned_nrpages(unsigned long host_addr,
 	return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
 }
 
+/* Return largest possible superpage level for a given mapping */
+static inline int hardware_largepage_caps(struct dmar_domain *domain,
+					  unsigned long iov_pfn,
+					  unsigned long phy_pfn,
+					  unsigned long pages)
+{
+	int support, level = 1;
+	unsigned long pfnmerge;
+
+	support = domain->iommu_superpage;
+
+	/* To use a large page, the virtual *and* physical addresses
+	   must be aligned to 2MiB/1GiB/etc. Lower bits set in either
+	   of them will mean we have to use smaller pages. So just
+	   merge them and check both at once. */
+	pfnmerge = iov_pfn | phy_pfn;
+
+	while (support && !(pfnmerge & ~VTD_STRIDE_MASK)) {
+		pages >>= VTD_STRIDE_SHIFT;
+		if (!pages)
+			break;
+		pfnmerge >>= VTD_STRIDE_SHIFT;
+		level++;
+		support--;
+	}
+	return level;
+}
+
 static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			    struct scatterlist *sg, unsigned long phys_pfn,
 			    unsigned long nr_pages, int prot)
@@ -1656,6 +1754,8 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 	phys_addr_t uninitialized_var(pteval);
 	int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
 	unsigned long sg_res;
+	unsigned int largepage_lvl = 0;
+	unsigned long lvl_pages = 0;
 
 	BUG_ON(addr_width < BITS_PER_LONG && (iov_pfn + nr_pages - 1) >> addr_width);
 
@@ -1671,7 +1771,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
 	}
 
-	while (nr_pages--) {
+	while (nr_pages > 0) {
 		uint64_t tmp;
 
 		if (!sg_res) {
@@ -1679,11 +1779,21 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset;
 			sg->dma_length = sg->length;
 			pteval = page_to_phys(sg_page(sg)) | prot;
+			phys_pfn = pteval >> VTD_PAGE_SHIFT;
 		}
+
 		if (!pte) {
-			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn);
+			largepage_lvl = hardware_largepage_caps(domain, iov_pfn, phys_pfn, sg_res);
+
+			first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, largepage_lvl);
 			if (!pte)
 				return -ENOMEM;
+			/* It is large page*/
+			if (largepage_lvl > 1)
+				pteval |= DMA_PTE_LARGE_PAGE;
+			else
+				pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE;
+
 		}
 		/* We don't need lock here, nobody else
 		 * touches the iova range
@@ -1699,16 +1809,38 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 			}
 			WARN_ON(1);
 		}
+
+		lvl_pages = lvl_to_nr_pages(largepage_lvl);
+
+		BUG_ON(nr_pages < lvl_pages);
+		BUG_ON(sg_res < lvl_pages);
+
+		nr_pages -= lvl_pages;
+		iov_pfn += lvl_pages;
+		phys_pfn += lvl_pages;
+		pteval += lvl_pages * VTD_PAGE_SIZE;
+		sg_res -= lvl_pages;
+
+		/* If the next PTE would be the first in a new page, then we
+		   need to flush the cache on the entries we've just written.
+		   And then we'll need to recalculate 'pte', so clear it and
+		   let it get set again in the if (!pte) block above.
+
+		   If we're done (!nr_pages) we need to flush the cache too.
+
+		   Also if we've been setting superpages, we may need to
+		   recalculate 'pte' and switch back to smaller pages for the
+		   end of the mapping, if the trailing size is not enough to
+		   use another superpage (i.e. sg_res < lvl_pages). */
 		pte++;
-		if (!nr_pages || first_pte_in_page(pte)) {
+		if (!nr_pages || first_pte_in_page(pte) ||
+		    (largepage_lvl > 1 && sg_res < lvl_pages)) {
 			domain_flush_cache(domain, first_pte,
 					   (void *)pte - (void *)first_pte);
 			pte = NULL;
 		}
-		iov_pfn++;
-		pteval += VTD_PAGE_SIZE;
-		sg_res--;
-		if (!sg_res)
+
+		if (!sg_res && nr_pages)
 			sg = sg_next(sg);
 	}
 	return 0;
@@ -2016,7 +2148,7 @@ static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr,
 	if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
 		return 0;
 	return iommu_prepare_identity_map(pdev, rmrr->base_address,
-		rmrr->end_address + 1);
+		rmrr->end_address);
 }
 
 #ifdef CONFIG_DMAR_FLOPPY_WA
@@ -2030,7 +2162,7 @@ static inline void iommu_prepare_isa(void)
 		return;
 
 	printk(KERN_INFO "IOMMU: Prepare 0-16MiB unity mapping for LPC\n");
-	ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024);
+	ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024 - 1);
 
 	if (ret)
 		printk(KERN_ERR "IOMMU: Failed to create 0-16MiB identity map; "
@@ -2106,10 +2238,10 @@ static int identity_mapping(struct pci_dev *pdev)
 	if (likely(!iommu_identity_mapping))
 		return 0;
 
+	info = pdev->dev.archdata.iommu;
+	if (info && info != DUMMY_DEVICE_DOMAIN_INFO)
+		return (info->domain == si_domain);
 
-	list_for_each_entry(info, &si_domain->devices, link)
-		if (info->dev == pdev)
-			return 1;
 	return 0;
 }
 
@@ -2187,8 +2319,19 @@ static int iommu_should_identity_map(struct pci_dev *pdev, int startup)
 	 * Assume that they will -- if they turn out not to be, then we can 
 	 * take them out of the 1:1 domain later.
 	 */
-	if (!startup)
-		return pdev->dma_mask > DMA_BIT_MASK(32);
+	if (!startup) {
+		/*
+		 * If the device's dma_mask is less than the system's memory
+		 * size then this is not a candidate for identity mapping.
+		 */
+		u64 dma_mask = pdev->dma_mask;
+
+		if (pdev->dev.coherent_dma_mask &&
+		    pdev->dev.coherent_dma_mask < dma_mask)
+			dma_mask = pdev->dev.coherent_dma_mask;
+
+		return dma_mask >= dma_get_required_mask(&pdev->dev);
+	}
 
 	return 1;
 }
@@ -2203,6 +2346,9 @@ static int __init iommu_prepare_static_identity_mapping(int hw)
 		return -EFAULT;
 
 	for_each_pci_dev(pdev) {
+		/* Skip Host/PCI Bridge devices */
+		if (IS_BRIDGE_HOST_DEVICE(pdev))
+			continue;
 		if (iommu_should_identity_map(pdev, 1)) {
 			printk(KERN_INFO "IOMMU: %s identity mapping for device %s\n",
 			       hw ? "hardware" : "software", pci_name(pdev));
@@ -2218,7 +2364,7 @@ static int __init iommu_prepare_static_identity_mapping(int hw)
 	return 0;
 }
 
-static int __init init_dmars(int force_on)
+static int __init init_dmars(void)
 {
 	struct dmar_drhd_unit *drhd;
 	struct dmar_rmrr_unit *rmrr;
@@ -2592,8 +2738,7 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr,
 	iommu = domain_get_iommu(domain);
 	size = aligned_nrpages(paddr, size);
 
-	iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size),
-				pdev->dma_mask);
+	iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), dma_mask);
 	if (!iova)
 		goto error;
 
@@ -3118,7 +3263,17 @@ static int init_iommu_hw(void)
 		if (iommu->qi)
 			dmar_reenable_qi(iommu);
 
-	for_each_active_iommu(iommu, drhd) {
+	for_each_iommu(iommu, drhd) {
+		if (drhd->ignored) {
+			/*
+			 * we always have to disable PMRs or DMA may fail on
+			 * this device
+			 */
+			if (force_on)
+				iommu_disable_protect_mem_regions(iommu);
+			continue;
+		}
+	
 		iommu_flush_write_buffer(iommu);
 
 		iommu_set_root_entry(iommu);
@@ -3127,7 +3282,8 @@ static int init_iommu_hw(void)
 					   DMA_CCMD_GLOBAL_INVL);
 		iommu->flush.flush_iotlb(iommu, 0, 0, 0,
 					 DMA_TLB_GLOBAL_FLUSH);
-		iommu_enable_translation(iommu);
+		if (iommu_enable_translation(iommu))
+			return 1;
 		iommu_disable_protect_mem_regions(iommu);
 	}
 
@@ -3194,7 +3350,10 @@ static void iommu_resume(void)
 	unsigned long flag;
 
 	if (init_iommu_hw()) {
-		WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
+		if (force_on)
+			panic("tboot: IOMMU setup failed, DMAR can not resume!\n");
+		else
+			WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
 		return;
 	}
 
@@ -3271,7 +3430,6 @@ static struct notifier_block device_nb = {
 int __init intel_iommu_init(void)
 {
 	int ret = 0;
-	int force_on = 0;
 
 	/* VT-d is required for a TXT/tboot launch, so enforce that */
 	force_on = tboot_force_iommu();
@@ -3309,7 +3467,7 @@ int __init intel_iommu_init(void)
 
 	init_no_remapping_devices();
 
-	ret = init_dmars(force_on);
+	ret = init_dmars();
 	if (ret) {
 		if (force_on)
 			panic("tboot: Failed to initialize DMARs\n");
@@ -3380,8 +3538,8 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain,
 	spin_lock_irqsave(&device_domain_lock, flags);
 	list_for_each_safe(entry, tmp, &domain->devices) {
 		info = list_entry(entry, struct device_domain_info, link);
-		/* No need to compare PCI domain; it has to be the same */
-		if (info->bus == pdev->bus->number &&
+		if (info->segment == pci_domain_nr(pdev->bus) &&
+		    info->bus == pdev->bus->number &&
 		    info->devfn == pdev->devfn) {
 			list_del(&info->link);
 			list_del(&info->global);
@@ -3419,10 +3577,13 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain,
 		domain_update_iommu_cap(domain);
 		spin_unlock_irqrestore(&domain->iommu_lock, tmp_flags);
 
-		spin_lock_irqsave(&iommu->lock, tmp_flags);
-		clear_bit(domain->id, iommu->domain_ids);
-		iommu->domains[domain->id] = NULL;
-		spin_unlock_irqrestore(&iommu->lock, tmp_flags);
+		if (!(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) &&
+		    !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY)) {
+			spin_lock_irqsave(&iommu->lock, tmp_flags);
+			clear_bit(domain->id, iommu->domain_ids);
+			iommu->domains[domain->id] = NULL;
+			spin_unlock_irqrestore(&iommu->lock, tmp_flags);
+		}
 	}
 
 	spin_unlock_irqrestore(&device_domain_lock, flags);
@@ -3505,6 +3666,7 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 	domain->iommu_count = 0;
 	domain->iommu_coherency = 0;
 	domain->iommu_snooping = 0;
+	domain->iommu_superpage = 0;
 	domain->max_addr = 0;
 	domain->nid = -1;
 
@@ -3720,7 +3882,7 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	struct dma_pte *pte;
 	u64 phys = 0;
 
-	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT);
+	pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, 0);
 	if (pte)
 		phys = dma_pte_addr(pte);
 

drivers/pci/iova.c

@@ -63,8 +63,16 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 	curr = iovad->cached32_node;
 	cached_iova = container_of(curr, struct iova, node);
 
-	if (free->pfn_lo >= cached_iova->pfn_lo)
-		iovad->cached32_node = rb_next(&free->node);
+	if (free->pfn_lo >= cached_iova->pfn_lo) {
+		struct rb_node *node = rb_next(&free->node);
+		struct iova *iova = container_of(node, struct iova, node);
+
+		/* only cache if it's below 32bit pfn */
+		if (node && iova->pfn_lo < iovad->dma_32bit_pfn)
+			iovad->cached32_node = node;
+		else
+			iovad->cached32_node = NULL;
+	}
 }
 
 /* Computes the padding size required, to make the