diff --git a/Makefile b/Makefile
index d6c64eb82525..a22bcb567348 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 4
-SUBLEVEL = 100
+SUBLEVEL = 101
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 
@@ -592,6 +592,8 @@ KBUILD_CFLAGS	+= -fomit-frame-pointer
 endif
 endif
 
+KBUILD_CFLAGS   += $(call cc-option, -fno-var-tracking-assignments)
+
 ifdef CONFIG_DEBUG_INFO
 KBUILD_CFLAGS	+= -g
 KBUILD_AFLAGS	+= -gdwarf-2
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 02f300fbf070..e0a8707dd137 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -292,7 +292,9 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 		 * psw and gprs are stored on the stack
 		 */
 		if (addr == (addr_t) &dummy->regs.psw.mask &&
-		    ((data & ~PSW_MASK_USER) != psw_user_bits ||
+		    (((data^psw_user_bits) & ~PSW_MASK_USER) ||
+		     (((data^psw_user_bits) & PSW_MASK_ASC) &&
+		      ((data|psw_user_bits) & PSW_MASK_ASC) == PSW_MASK_ASC) ||
 		     ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))))
 			/* Invalid psw mask. */
 			return -EINVAL;
@@ -595,7 +597,10 @@ static int __poke_user_compat(struct task_struct *child,
 		 */
 		if (addr == (addr_t) &dummy32->regs.psw.mask) {
 			/* Build a 64 bit psw mask from 31 bit mask. */
-			if ((tmp & ~PSW32_MASK_USER) != psw32_user_bits)
+			if (((tmp^psw32_user_bits) & ~PSW32_MASK_USER) ||
+			    (((tmp^psw32_user_bits) & PSW32_MASK_ASC) &&
+			     ((tmp|psw32_user_bits) & PSW32_MASK_ASC)
+			     == PSW32_MASK_ASC))
 				/* Invalid psw mask. */
 				return -EINVAL;
 			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_USER) |
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index e1e7f9c831da..e36c5cf38fde 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -428,8 +428,8 @@ sysenter_do_call:
 	cmpl $(NR_syscalls), %eax
 	jae sysenter_badsys
 	call *sys_call_table(,%eax,4)
-	movl %eax,PT_EAX(%esp)
 sysenter_after_call:
+	movl %eax,PT_EAX(%esp)
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
@@ -510,6 +510,7 @@ ENTRY(system_call)
 	jae syscall_badsys
 syscall_call:
 	call *sys_call_table(,%eax,4)
+syscall_after_call:
 	movl %eax,PT_EAX(%esp)		# store the return value
 syscall_exit:
 	LOCKDEP_SYS_EXIT
@@ -678,12 +679,12 @@ syscall_fault:
 END(syscall_fault)
 
 syscall_badsys:
-	movl $-ENOSYS,PT_EAX(%esp)
-	jmp syscall_exit
+	movl $-ENOSYS,%eax
+	jmp syscall_after_call
 END(syscall_badsys)
 
 sysenter_badsys:
-	movl $-ENOSYS,PT_EAX(%esp)
+	movl $-ENOSYS,%eax
 	jmp sysenter_after_call
 END(syscall_badsys)
 	CFI_ENDPROC
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 4af6f5cc1167..f606487bba56 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -27,18 +27,15 @@ struct request *blk_queue_find_tag(struct request_queue *q, int tag)
 EXPORT_SYMBOL(blk_queue_find_tag);
 
 /**
- * __blk_free_tags - release a given set of tag maintenance info
+ * blk_free_tags - release a given set of tag maintenance info
  * @bqt:	the tag map to free
  *
- * Tries to free the specified @bqt.  Returns true if it was
- * actually freed and false if there are still references using it
+ * Drop the reference count on @bqt and frees it when the last reference
+ * is dropped.
  */
-static int __blk_free_tags(struct blk_queue_tag *bqt)
+void blk_free_tags(struct blk_queue_tag *bqt)
 {
-	int retval;
-
-	retval = atomic_dec_and_test(&bqt->refcnt);
-	if (retval) {
+	if (atomic_dec_and_test(&bqt->refcnt)) {
 		BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) <
 							bqt->max_depth);
 
@@ -50,9 +47,8 @@ static int __blk_free_tags(struct blk_queue_tag *bqt)
 
 		kfree(bqt);
 	}
-
-	return retval;
 }
+EXPORT_SYMBOL(blk_free_tags);
 
 /**
  * __blk_queue_free_tags - release tag maintenance info
@@ -69,28 +65,13 @@ void __blk_queue_free_tags(struct request_queue *q)
 	if (!bqt)
 		return;
 
-	__blk_free_tags(bqt);
+	blk_free_tags(bqt);
 
 	q->queue_tags = NULL;
 	queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
 }
 
 /**
- * blk_free_tags - release a given set of tag maintenance info
- * @bqt:	the tag map to free
- *
- * For externally managed @bqt frees the map.  Callers of this
- * function must guarantee to have released all the queues that
- * might have been using this tag map.
- */
-void blk_free_tags(struct blk_queue_tag *bqt)
-{
-	if (unlikely(!__blk_free_tags(bqt)))
-		BUG();
-}
-EXPORT_SYMBOL(blk_free_tags);
-
-/**
  * blk_queue_free_tags - release tag maintenance info
  * @q:  the request queue for the device
  *
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 0e87baf8fcc2..0a450eb517e0 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -446,6 +446,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 
 	/* Promise */
 	{ PCI_VDEVICE(PROMISE, 0x3f20), board_ahci },	/* PDC42819 */
+	{ PCI_VDEVICE(PROMISE, 0x3781), board_ahci },   /* FastTrak TX8660 ahci-mode */
 
 	/* Asmedia */
 	{ PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci },	/* ASM1060 */
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 6e67fdebdada..6b922365d5e9 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4693,6 +4693,10 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
  *	ata_qc_new - Request an available ATA command, for queueing
  *	@ap: target port
  *
+ *	Some ATA host controllers may implement a queue depth which is less
+ *	than ATA_MAX_QUEUE. So we shouldn't allocate a tag which is beyond
+ *	the hardware limitation.
+ *
  *	LOCKING:
  *	None.
  */
@@ -4700,14 +4704,15 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
 static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
 {
 	struct ata_queued_cmd *qc = NULL;
+	unsigned int max_queue = ap->host->n_tags;
 	unsigned int i, tag;
 
 	/* no command while frozen */
 	if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
 		return NULL;
 
-	for (i = 0; i < ATA_MAX_QUEUE; i++) {
-		tag = (i + ap->last_tag + 1) % ATA_MAX_QUEUE;
+	for (i = 0, tag = ap->last_tag + 1; i < max_queue; i++, tag++) {
+		tag = tag < max_queue ? tag : 0;
 
 		/* the last tag is reserved for internal command. */
 		if (tag == ATA_TAG_INTERNAL)
@@ -5959,6 +5964,7 @@ void ata_host_init(struct ata_host *host, struct device *dev,
 {
 	spin_lock_init(&host->lock);
 	mutex_init(&host->eh_mutex);
+	host->n_tags = ATA_MAX_QUEUE - 1;
 	host->dev = dev;
 	host->flags = flags;
 	host->ops = ops;
@@ -6041,6 +6047,8 @@ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht)
 {
 	int i, rc;
 
+	host->n_tags = clamp(sht->can_queue, 1, ATA_MAX_QUEUE - 1);
+
 	/* host must have been started */
 	if (!(host->flags & ATA_HOST_STARTED)) {
 		dev_err(host->dev, "BUG: trying to register unstarted host\n");
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index f04c0961f993..e5206fc76562 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -331,7 +331,7 @@ static int build_snap_context(struct ceph_snap_realm *realm)
 
 	/* alloc new snap context */
 	err = -ENOMEM;
-	if (num > (ULONG_MAX - sizeof(*snapc)) / sizeof(u64))
+	if (num > (SIZE_MAX - sizeof(*snapc)) / sizeof(u64))
 		goto fail;
 	snapc = kzalloc(sizeof(*snapc) + num*sizeof(u64), GFP_NOFS);
 	if (!snapc)
diff --git a/include/drm/drm_mem_util.h b/include/drm/drm_mem_util.h
index 6bd325fedc87..19a240446fca 100644
--- a/include/drm/drm_mem_util.h
+++ b/include/drm/drm_mem_util.h
@@ -31,7 +31,7 @@
 
 static __inline__ void *drm_calloc_large(size_t nmemb, size_t size)
 {
-	if (size != 0 && nmemb > ULONG_MAX / size)
+	if (size != 0 && nmemb > SIZE_MAX / size)
 		return NULL;
 
 	if (size * nmemb <= PAGE_SIZE)
@@ -44,7 +44,7 @@ static __inline__ void *drm_calloc_large(size_t nmemb, size_t size)
 /* Modeled after cairo's malloc_ab, it's like calloc but without the zeroing. */
 static __inline__ void *drm_malloc_ab(size_t nmemb, size_t size)
 {
-	if (size != 0 && nmemb > ULONG_MAX / size)
+	if (size != 0 && nmemb > SIZE_MAX / size)
 		return NULL;
 
 	if (size * nmemb <= PAGE_SIZE)
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 645231c373c8..b795ee5cd208 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -35,6 +35,7 @@
 #define LLONG_MAX	((long long)(~0ULL>>1))
 #define LLONG_MIN	(-LLONG_MAX - 1)
 #define ULLONG_MAX	(~0ULL)
+#define SIZE_MAX	(~(size_t)0)
 
 #define STACK_MAGIC	0xdeadbeef
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 50d7cb1ee947..dd16deb27dd8 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -539,6 +539,7 @@ struct ata_host {
 	struct device 		*dev;
 	void __iomem * const	*iomap;
 	unsigned int		n_ports;
+	unsigned int		n_tags;			/* nr of NCQ tags */
 	void			*private_data;
 	struct ata_port_operations *ops;
 	unsigned long		flags;
diff --git a/include/linux/slab.h b/include/linux/slab.h
index a595dce6b0c7..67d5d94b783a 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -242,7 +242,7 @@ size_t ksize(const void *);
  */
 static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags)
 {
-	if (size != 0 && n > ULONG_MAX / size)
+	if (size != 0 && n > SIZE_MAX / size)
 		return NULL;
 	return __kmalloc(n * size, flags);
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0d4e0ad97a04..efd682099a0a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2348,6 +2348,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		} else {
 			if (cow)
 				huge_ptep_set_wrprotect(src, addr, src_pte);
+			entry = huge_ptep_get(src_pte);
 			ptepage = pte_page(entry);
 			get_page(ptepage);
 			page_dup_rmap(ptepage);
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 45eb6217bf38..ad6ee88a3d48 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -750,7 +750,9 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
 	}
 
 	spin_lock_irqsave(&object->lock, flags);
-	if (ptr + size > object->pointer + object->size) {
+	if (size == SIZE_MAX) {
+		size = object->pointer + object->size - ptr;
+	} else if (ptr + size > object->pointer + object->size) {
 		kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr);
 		dump_object_info(object);
 		kmem_cache_free(scan_area_cache, area);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 1196c7728ede..ad9d90064a4b 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -349,6 +349,12 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
 	if (unlikely(!va))
 		return ERR_PTR(-ENOMEM);
 
+	/*
+	 * Only scan the relevant parts containing pointers to other objects
+	 * to avoid false negatives.
+	 */
+	kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK);
+
 retry:
 	spin_lock(&vmap_area_lock);
 	/*
@@ -1669,11 +1675,11 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	insert_vmalloc_vmlist(area);
 
 	/*
-	 * A ref_count = 3 is needed because the vm_struct and vmap_area
-	 * structures allocated in the __get_vm_area_node() function contain
-	 * references to the virtual address of the vmalloc'ed block.
+	 * A ref_count = 2 is needed because vm_struct allocated in
+	 * __get_vm_area_node() contains a reference to the virtual address of
+	 * the vmalloc'ed block.
 	 */
-	kmemleak_alloc(addr, real_size, 3, gfp_mask);
+	kmemleak_alloc(addr, real_size, 2, gfp_mask);
 
 	return addr;