Merge branch 'drm-fixes' of git://people.freedesktop.org/~airlied/linux

3 radeon fixes, I have some exynos fixes to push later but I'll queue
them separately once I've looked them over a bit.

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
  drm/radeon/kms: fix MSI re-arm on rv370+
  drm/radeon/kms/atom: bios scratch reg handling updates
  drm/radeon/kms: drop lock in return path of radeon_fence_count_emitted.
diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h
index 43268f1..6d42297 100644
--- a/arch/powerpc/include/asm/ppc-pci.h
+++ b/arch/powerpc/include/asm/ppc-pci.h
@@ -142,6 +142,11 @@
 	return pdev ? pci_name(pdev) : "<null>";
 } 
 
+static inline const char *eeh_driver_name(struct pci_dev *pdev)
+{
+	return (pdev && pdev->driver) ? pdev->driver->name : "<null>";
+}
+
 #endif /* CONFIG_EEH */
 
 #else /* CONFIG_PCI */
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 78a2051..84cc784 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -83,8 +83,18 @@
 
 #ifndef __ASSEMBLY__
 
-#define instruction_pointer(regs) ((regs)->nip)
-#define user_stack_pointer(regs) ((regs)->gpr[1])
+#define GET_IP(regs)		((regs)->nip)
+#define GET_USP(regs)		((regs)->gpr[1])
+#define GET_FP(regs)		(0)
+#define SET_FP(regs, val)
+
+#ifdef CONFIG_SMP
+extern unsigned long profile_pc(struct pt_regs *regs);
+#define profile_pc profile_pc
+#endif
+
+#include <asm-generic/ptrace.h>
+
 #define kernel_stack_pointer(regs) ((regs)->gpr[1])
 static inline int is_syscall_success(struct pt_regs *regs)
 {
@@ -99,12 +109,6 @@
 		return -regs->gpr[3];
 }
 
-#ifdef CONFIG_SMP
-extern unsigned long profile_pc(struct pt_regs *regs);
-#else
-#define profile_pc(regs) instruction_pointer(regs)
-#endif
-
 #ifdef __powerpc64__
 #define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1)
 #else
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 701d4ac..01e2877 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -118,10 +118,14 @@
 static inline notrace void decrementer_check_overflow(void)
 {
 	u64 now = get_tb_or_rtc();
-	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
+	u64 *next_tb;
+
+	preempt_disable();
+	next_tb = &__get_cpu_var(decrementers_next_tb);
 
 	if (now >= *next_tb)
 		set_dec(1);
+	preempt_enable();
 }
 
 notrace void arch_local_irq_restore(unsigned long en)
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 517b1d8..9f843cd 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -716,7 +716,6 @@
 	int cpu;
 
 	slb_set_size(SLB_MIN_SIZE);
-	stop_topology_update();
 	printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n", smp_processor_id());
 
 	while (rc == H_MULTI_THREADS_ACTIVE && !atomic_read(&data->done) &&
@@ -732,7 +731,6 @@
 		rc = atomic_read(&data->error);
 
 	atomic_set(&data->error, rc);
-	start_topology_update();
 	pSeries_coalesce_init();
 
 	if (wake_when_done) {
@@ -846,6 +844,7 @@
 	atomic_set(&data.error, 0);
 	data.token = rtas_token("ibm,suspend-me");
 	data.complete = &done;
+	stop_topology_update();
 
 	/* Call function on all CPUs.  One of us will make the
 	 * rtas call
@@ -858,6 +857,8 @@
 	if (atomic_read(&data.error) != 0)
 		printk(KERN_ERR "Error doing global join\n");
 
+	start_topology_update();
+
 	return atomic_read(&data.error);
 }
 #else /* CONFIG_PPC_PSERIES */
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index a70bc1e..f92b9ef 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -52,32 +52,38 @@
 
 static unsigned int pnv_get_one_msi(struct pnv_phb *phb)
 {
-	unsigned int id;
+	unsigned long flags;
+	unsigned int id, rc;
 
-	spin_lock(&phb->lock);
+	spin_lock_irqsave(&phb->lock, flags);
+
 	id = find_next_zero_bit(phb->msi_map, phb->msi_count, phb->msi_next);
 	if (id >= phb->msi_count && phb->msi_next)
 		id = find_next_zero_bit(phb->msi_map, phb->msi_count, 0);
 	if (id >= phb->msi_count) {
-		spin_unlock(&phb->lock);
-		return 0;
+		rc = 0;
+		goto out;
 	}
 	__set_bit(id, phb->msi_map);
-	spin_unlock(&phb->lock);
-	return id + phb->msi_base;
+	rc = id + phb->msi_base;
+out:
+	spin_unlock_irqrestore(&phb->lock, flags);
+	return rc;
 }
 
 static void pnv_put_msi(struct pnv_phb *phb, unsigned int hwirq)
 {
+	unsigned long flags;
 	unsigned int id;
 
 	if (WARN_ON(hwirq < phb->msi_base ||
 		    hwirq >= (phb->msi_base + phb->msi_count)))
 		return;
 	id = hwirq - phb->msi_base;
-	spin_lock(&phb->lock);
+
+	spin_lock_irqsave(&phb->lock, flags);
 	__clear_bit(id, phb->msi_map);
-	spin_unlock(&phb->lock);
+	spin_unlock_irqrestore(&phb->lock, flags);
 }
 
 static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 5658690..c0b40af 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -551,9 +551,9 @@
 			printk (KERN_ERR "EEH: %d reads ignored for recovering device at "
 				"location=%s driver=%s pci addr=%s\n",
 				pdn->eeh_check_count, location,
-				dev->driver->name, eeh_pci_name(dev));
+				eeh_driver_name(dev), eeh_pci_name(dev));
 			printk (KERN_ERR "EEH: Might be infinite loop in %s driver\n",
-				dev->driver->name);
+				eeh_driver_name(dev));
 			dump_stack();
 		}
 		goto dn_unlock;
diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c
index b84a8b2..47226e0 100644
--- a/arch/powerpc/platforms/pseries/suspend.c
+++ b/arch/powerpc/platforms/pseries/suspend.c
@@ -24,6 +24,7 @@
 #include <asm/machdep.h>
 #include <asm/mmu.h>
 #include <asm/rtas.h>
+#include <asm/topology.h>
 
 static u64 stream_id;
 static struct device suspend_dev;
@@ -138,8 +139,11 @@
 			ssleep(1);
 	} while (rc == -EAGAIN);
 
-	if (!rc)
+	if (!rc) {
+		stop_topology_update();
 		rc = pm_suspend(PM_SUSPEND_MEM);
+		start_topology_update();
+	}
 
 	stream_id = 0;
 
diff --git a/arch/powerpc/platforms/wsp/ics.c b/arch/powerpc/platforms/wsp/ics.c
index 5768743..97fe82e 100644
--- a/arch/powerpc/platforms/wsp/ics.c
+++ b/arch/powerpc/platforms/wsp/ics.c
@@ -346,7 +346,7 @@
 	 * For the moment only implement delivery to all cpus or one cpu.
 	 * Get current irq_server for the given irq
 	 */
-	ret = cache_hwirq_map(ics, d->irq, cpumask);
+	ret = cache_hwirq_map(ics, hw_irq, cpumask);
 	if (ret == -1) {
 		char cpulist[128];
 		cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask);
diff --git a/arch/powerpc/platforms/wsp/wsp_pci.c b/arch/powerpc/platforms/wsp/wsp_pci.c
index e0262cd..d24b3ac 100644
--- a/arch/powerpc/platforms/wsp/wsp_pci.c
+++ b/arch/powerpc/platforms/wsp/wsp_pci.c
@@ -468,15 +468,15 @@
 #define DUMP_REG(x) \
 	pr_debug("%-30s : 0x%016llx\n", #x, in_be64(hose->cfg_data + x))
 
-#ifdef CONFIG_WSP_DD1_WORKAROUND_BAD_PCIE_CLASS
-	/* WSP DD1 has a bogus class code by default in the PCI-E
-	 * root complex's built-in P2P bridge */
+	/*
+	 * Some WSP variants  has a bogus class code by default in the PCI-E
+	 * root complex's built-in P2P bridge
+	 */
 	val = in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1);
 	pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", val);
 	out_be64(hose->cfg_data + PCIE_REG_SYS_CFG1,
 		 (val & ~PCIE_REG_SYS_CFG1_CLASS_CODE) | (PCI_CLASS_BRIDGE_PCI << 8));
 	pr_debug("PCI-E SYS_CFG1 : 0x%llx\n", in_be64(hose->cfg_data + PCIE_REG_SYS_CFG1));
-#endif /* CONFIG_WSP_DD1_WORKAROUND_BAD_PCIE_CLASS */
 
 #ifdef CONFIG_WSP_DD1_WORKAROUND_DD1_TCE_BUGS
 	/* XXX Disable TCE caching, it doesn't work on DD1 */
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index a295718..a850b4d 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -29,8 +29,8 @@
 extern void fpu_init(void);
 extern void mxcsr_feature_mask_init(void);
 extern int init_fpu(struct task_struct *child);
+extern void __math_state_restore(struct task_struct *);
 extern void math_state_restore(void);
-extern void __math_state_restore(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
 extern user_regset_active_fn fpregs_active, xfpregs_active;
@@ -212,19 +212,11 @@
 
 #endif	/* CONFIG_X86_64 */
 
-/* We need a safe address that is cheap to find and that is already
-   in L1 during context switch. The best choices are unfortunately
-   different for UP and SMP */
-#ifdef CONFIG_SMP
-#define safe_address (__per_cpu_offset[0])
-#else
-#define safe_address (__get_cpu_var(kernel_cpustat).cpustat[CPUTIME_USER])
-#endif
-
 /*
- * These must be called with preempt disabled
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact.
  */
-static inline void fpu_save_init(struct fpu *fpu)
+static inline int fpu_save_init(struct fpu *fpu)
 {
 	if (use_xsave()) {
 		fpu_xsave(fpu);
@@ -233,33 +225,33 @@
 		 * xsave header may indicate the init state of the FP.
 		 */
 		if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
-			return;
+			return 1;
 	} else if (use_fxsr()) {
 		fpu_fxsave(fpu);
 	} else {
 		asm volatile("fnsave %[fx]; fwait"
 			     : [fx] "=m" (fpu->state->fsave));
-		return;
+		return 0;
 	}
 
-	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES))
+	/*
+	 * If exceptions are pending, we need to clear them so
+	 * that we don't randomly get exceptions later.
+	 *
+	 * FIXME! Is this perhaps only true for the old-style
+	 * irq13 case? Maybe we could leave the x87 state
+	 * intact otherwise?
+	 */
+	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
 		asm volatile("fnclex");
-
-	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
-	   is pending.  Clear the x87 state here by setting it to fixed
-	   values. safe_address is a random variable that should be in L1 */
-	alternative_input(
-		ASM_NOP8 ASM_NOP2,
-		"emms\n\t"	  	/* clear stack tags */
-		"fildl %P[addr]",	/* set F?P to defined value */
-		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (safe_address));
+		return 0;
+	}
+	return 1;
 }
 
-static inline void __save_init_fpu(struct task_struct *tsk)
+static inline int __save_init_fpu(struct task_struct *tsk)
 {
-	fpu_save_init(&tsk->thread.fpu);
-	task_thread_info(tsk)->status &= ~TS_USEDFPU;
+	return fpu_save_init(&tsk->thread.fpu);
 }
 
 static inline int fpu_fxrstor_checking(struct fpu *fpu)
@@ -281,29 +273,128 @@
 }
 
 /*
+ * Software FPU state helpers. Careful: these need to
+ * be preemption protection *and* they need to be
+ * properly paired with the CR0.TS changes!
+ */
+static inline int __thread_has_fpu(struct task_struct *tsk)
+{
+	return tsk->thread.has_fpu;
+}
+
+/* Must be paired with an 'stts' after! */
+static inline void __thread_clear_has_fpu(struct task_struct *tsk)
+{
+	tsk->thread.has_fpu = 0;
+}
+
+/* Must be paired with a 'clts' before! */
+static inline void __thread_set_has_fpu(struct task_struct *tsk)
+{
+	tsk->thread.has_fpu = 1;
+}
+
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void __thread_fpu_end(struct task_struct *tsk)
+{
+	__thread_clear_has_fpu(tsk);
+	stts();
+}
+
+static inline void __thread_fpu_begin(struct task_struct *tsk)
+{
+	clts();
+	__thread_set_has_fpu(tsk);
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ *  - switch_fpu_prepare() saves the old state and
+ *    sets the new state of the CR0.TS bit. This is
+ *    done within the context of the old process.
+ *
+ *  - switch_fpu_finish() restores the new state as
+ *    necessary.
+ */
+typedef struct { int preload; } fpu_switch_t;
+
+/*
+ * FIXME! We could do a totally lazy restore, but we need to
+ * add a per-cpu "this was the task that last touched the FPU
+ * on this CPU" variable, and the task needs to have a "I last
+ * touched the FPU on this CPU" and check them.
+ *
+ * We don't do that yet, so "fpu_lazy_restore()" always returns
+ * false, but some day..
+ */
+#define fpu_lazy_restore(tsk) (0)
+#define fpu_lazy_state_intact(tsk) do { } while (0)
+
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new)
+{
+	fpu_switch_t fpu;
+
+	fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+	if (__thread_has_fpu(old)) {
+		if (__save_init_fpu(old))
+			fpu_lazy_state_intact(old);
+		__thread_clear_has_fpu(old);
+		old->fpu_counter++;
+
+		/* Don't change CR0.TS if we just switch! */
+		if (fpu.preload) {
+			__thread_set_has_fpu(new);
+			prefetch(new->thread.fpu.state);
+		} else
+			stts();
+	} else {
+		old->fpu_counter = 0;
+		if (fpu.preload) {
+			if (fpu_lazy_restore(new))
+				fpu.preload = 0;
+			else
+				prefetch(new->thread.fpu.state);
+			__thread_fpu_begin(new);
+		}
+	}
+	return fpu;
+}
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
+{
+	if (fpu.preload)
+		__math_state_restore(new);
+}
+
+/*
  * Signal frame handlers...
  */
 extern int save_i387_xstate(void __user *buf);
 extern int restore_i387_xstate(void __user *buf);
 
-static inline void __unlazy_fpu(struct task_struct *tsk)
-{
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
-		__save_init_fpu(tsk);
-		stts();
-	} else
-		tsk->fpu_counter = 0;
-}
-
 static inline void __clear_fpu(struct task_struct *tsk)
 {
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+	if (__thread_has_fpu(tsk)) {
 		/* Ignore delayed exceptions from user space */
 		asm volatile("1: fwait\n"
 			     "2:\n"
 			     _ASM_EXTABLE(1b, 2b));
-		task_thread_info(tsk)->status &= ~TS_USEDFPU;
-		stts();
+		__thread_fpu_end(tsk);
 	}
 }
 
@@ -311,14 +402,14 @@
  * Were we in an interrupt that interrupted kernel mode?
  *
  * We can do a kernel_fpu_begin/end() pair *ONLY* if that
- * pair does nothing at all: TS_USEDFPU must be clear (so
+ * pair does nothing at all: the thread must not have fpu (so
  * that we don't try to save the FPU state), and TS must
  * be set (so that the clts/stts pair does nothing that is
  * visible in the interrupted kernel thread).
  */
 static inline bool interrupted_kernel_fpu_idle(void)
 {
-	return !(current_thread_info()->status & TS_USEDFPU) &&
+	return !__thread_has_fpu(current) &&
 		(read_cr0() & X86_CR0_TS);
 }
 
@@ -352,13 +443,15 @@
 
 static inline void kernel_fpu_begin(void)
 {
-	struct thread_info *me = current_thread_info();
+	struct task_struct *me = current;
 
 	WARN_ON_ONCE(!irq_fpu_usable());
 	preempt_disable();
-	if (me->status & TS_USEDFPU)
-		__save_init_fpu(me->task);
-	else
+	if (__thread_has_fpu(me)) {
+		__save_init_fpu(me);
+		__thread_clear_has_fpu(me);
+		/* We do 'stts()' in kernel_fpu_end() */
+	} else
 		clts();
 }
 
@@ -400,21 +493,64 @@
 }
 
 /*
+ * The question "does this thread have fpu access?"
+ * is slightly racy, since preemption could come in
+ * and revoke it immediately after the test.
+ *
+ * However, even in that very unlikely scenario,
+ * we can just assume we have FPU access - typically
+ * to save the FP state - we'll just take a #NM
+ * fault and get the FPU access back.
+ *
+ * The actual user_fpu_begin/end() functions
+ * need to be preemption-safe, though.
+ *
+ * NOTE! user_fpu_end() must be used only after you
+ * have saved the FP state, and user_fpu_begin() must
+ * be used only immediately before restoring it.
+ * These functions do not do any save/restore on
+ * their own.
+ */
+static inline int user_has_fpu(void)
+{
+	return __thread_has_fpu(current);
+}
+
+static inline void user_fpu_end(void)
+{
+	preempt_disable();
+	__thread_fpu_end(current);
+	preempt_enable();
+}
+
+static inline void user_fpu_begin(void)
+{
+	preempt_disable();
+	if (!user_has_fpu())
+		__thread_fpu_begin(current);
+	preempt_enable();
+}
+
+/*
  * These disable preemption on their own and are safe
  */
 static inline void save_init_fpu(struct task_struct *tsk)
 {
-	WARN_ON_ONCE(task_thread_info(tsk)->status & TS_USEDFPU);
+	WARN_ON_ONCE(!__thread_has_fpu(tsk));
 	preempt_disable();
 	__save_init_fpu(tsk);
-	stts();
+	__thread_fpu_end(tsk);
 	preempt_enable();
 }
 
 static inline void unlazy_fpu(struct task_struct *tsk)
 {
 	preempt_disable();
-	__unlazy_fpu(tsk);
+	if (__thread_has_fpu(tsk)) {
+		__save_init_fpu(tsk);
+		__thread_fpu_end(tsk);
+	} else
+		tsk->fpu_counter = 0;
 	preempt_enable();
 }
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index aa9088c..f7c89e2 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -454,6 +454,7 @@
 	unsigned long		trap_no;
 	unsigned long		error_code;
 	/* floating point and extended processor state */
+	unsigned long		has_fpu;
 	struct fpu		fpu;
 #ifdef CONFIG_X86_32
 	/* Virtual 86 mode info */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index bc817cd..cfd8144 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -247,8 +247,6 @@
  * ever touches our thread-synchronous status, so we don't
  * have to worry about atomic accesses.
  */
-#define TS_USEDFPU		0x0001	/* FPU was used by this task
-					   this quantum (SMP) */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
 #define TS_POLLING		0x0004	/* idle task polling need_resched,
 					   skip sending interrupt */
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 485204f..80bfe1a 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -299,22 +299,11 @@
 				 *next = &next_p->thread;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(init_tss, cpu);
-	bool preload_fpu;
+	fpu_switch_t fpu;
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	/*
-	 * If the task has used fpu the last 5 timeslices, just do a full
-	 * restore of the math state immediately to avoid the trap; the
-	 * chances of needing FPU soon are obviously high now
-	 */
-	preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
-
-	__unlazy_fpu(prev_p);
-
-	/* we're going to use this soon, after a few expensive things */
-	if (preload_fpu)
-		prefetch(next->fpu.state);
+	fpu = switch_fpu_prepare(prev_p, next_p);
 
 	/*
 	 * Reload esp0.
@@ -354,11 +343,6 @@
 		     task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
 		__switch_to_xtra(prev_p, next_p, tss);
 
-	/* If we're going to preload the fpu context, make sure clts
-	   is run while we're batching the cpu state updates. */
-	if (preload_fpu)
-		clts();
-
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
@@ -368,15 +352,14 @@
 	 */
 	arch_end_context_switch(next_p);
 
-	if (preload_fpu)
-		__math_state_restore();
-
 	/*
 	 * Restore %gs if needed (which is common)
 	 */
 	if (prev->gs | next->gs)
 		lazy_load_gs(next->gs);
 
+	switch_fpu_finish(next_p, fpu);
+
 	percpu_write(current_task, next_p);
 
 	return prev_p;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9b9fe4a..1fd94bc 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -386,18 +386,9 @@
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(init_tss, cpu);
 	unsigned fsindex, gsindex;
-	bool preload_fpu;
+	fpu_switch_t fpu;
 
-	/*
-	 * If the task has used fpu the last 5 timeslices, just do a full
-	 * restore of the math state immediately to avoid the trap; the
-	 * chances of needing FPU soon are obviously high now
-	 */
-	preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
-
-	/* we're going to use this soon, after a few expensive things */
-	if (preload_fpu)
-		prefetch(next->fpu.state);
+	fpu = switch_fpu_prepare(prev_p, next_p);
 
 	/*
 	 * Reload esp0, LDT and the page table pointer:
@@ -427,13 +418,6 @@
 
 	load_TLS(next, cpu);
 
-	/* Must be after DS reload */
-	__unlazy_fpu(prev_p);
-
-	/* Make sure cpu is ready for new context */
-	if (preload_fpu)
-		clts();
-
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
@@ -474,6 +458,8 @@
 		wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
 	prev->gsindex = gsindex;
 
+	switch_fpu_finish(next_p, fpu);
+
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
@@ -492,13 +478,6 @@
 		     task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
 		__switch_to_xtra(prev_p, next_p, tss);
 
-	/*
-	 * Preload the FPU context, now that we've determined that the
-	 * task is likely to be using it. 
-	 */
-	if (preload_fpu)
-		__math_state_restore();
-
 	return prev_p;
 }
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 8ba27db..77da5b4 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -571,25 +571,34 @@
 }
 
 /*
- * __math_state_restore assumes that cr0.TS is already clear and the
- * fpu state is all ready for use.  Used during context switch.
+ * This gets called with the process already owning the
+ * FPU state, and with CR0.TS cleared. It just needs to
+ * restore the FPU register state.
  */
-void __math_state_restore(void)
+void __math_state_restore(struct task_struct *tsk)
 {
-	struct thread_info *thread = current_thread_info();
-	struct task_struct *tsk = thread->task;
+	/* We need a safe address that is cheap to find and that is already
+	   in L1. We've just brought in "tsk->thread.has_fpu", so use that */
+#define safe_address (tsk->thread.has_fpu)
+
+	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+	   is pending.  Clear the x87 state here by setting it to fixed
+	   values. safe_address is a random variable that should be in L1 */
+	alternative_input(
+		ASM_NOP8 ASM_NOP2,
+		"emms\n\t"	  	/* clear stack tags */
+		"fildl %P[addr]",	/* set F?P to defined value */
+		X86_FEATURE_FXSAVE_LEAK,
+		[addr] "m" (safe_address));
 
 	/*
 	 * Paranoid restore. send a SIGSEGV if we fail to restore the state.
 	 */
 	if (unlikely(restore_fpu_checking(tsk))) {
-		stts();
+		__thread_fpu_end(tsk);
 		force_sig(SIGSEGV, tsk);
 		return;
 	}
-
-	thread->status |= TS_USEDFPU;	/* So we fnsave on switch_to() */
-	tsk->fpu_counter++;
 }
 
 /*
@@ -604,8 +613,7 @@
  */
 void math_state_restore(void)
 {
-	struct thread_info *thread = current_thread_info();
-	struct task_struct *tsk = thread->task;
+	struct task_struct *tsk = current;
 
 	if (!tsk_used_math(tsk)) {
 		local_irq_enable();
@@ -622,16 +630,16 @@
 		local_irq_disable();
 	}
 
-	clts();				/* Allow maths ops (or we recurse) */
+	__thread_fpu_begin(tsk);
+	__math_state_restore(tsk);
 
-	__math_state_restore();
+	tsk->fpu_counter++;
 }
 EXPORT_SYMBOL_GPL(math_state_restore);
 
 dotraplinkage void __kprobes
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
-	WARN_ON_ONCE(!user_mode_vm(regs));
 #ifdef CONFIG_MATH_EMULATION
 	if (read_cr0() & X86_CR0_EM) {
 		struct math_emu_info info = { };
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index a391134..7110911 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -47,7 +47,7 @@
 	if (!fx)
 		return;
 
-	BUG_ON(task_thread_info(tsk)->status & TS_USEDFPU);
+	BUG_ON(__thread_has_fpu(tsk));
 
 	xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
 
@@ -168,7 +168,7 @@
 	if (!used_math())
 		return 0;
 
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+	if (user_has_fpu()) {
 		if (use_xsave())
 			err = xsave_user(buf);
 		else
@@ -176,8 +176,7 @@
 
 		if (err)
 			return err;
-		task_thread_info(tsk)->status &= ~TS_USEDFPU;
-		stts();
+		user_fpu_end();
 	} else {
 		sanitize_i387_state(tsk);
 		if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
@@ -292,10 +291,7 @@
 			return err;
 	}
 
-	if (!(task_thread_info(current)->status & TS_USEDFPU)) {
-		clts();
-		task_thread_info(current)->status |= TS_USEDFPU;
-	}
+	user_fpu_begin();
 	if (use_xsave())
 		err = restore_user_xstate(buf);
 	else
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index d29216c..3b4c8d8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1457,7 +1457,7 @@
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
-	if (current_thread_info()->status & TS_USEDFPU)
+	if (__thread_has_fpu(current))
 		clts();
 	load_gdt(&__get_cpu_var(host_gdt));
 }
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 492ade8..d99346e 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -374,7 +374,7 @@
 
 int __init pci_xen_hvm_init(void)
 {
-	if (!xen_feature(XENFEAT_hvm_pirqs))
+	if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs))
 		return 0;
 
 #ifdef CONFIG_ACPI
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 041d4fe..501d4e0 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -409,6 +409,13 @@
 	play_dead_common();
 	HYPERVISOR_vcpu_op(VCPUOP_down, smp_processor_id(), NULL);
 	cpu_bringup();
+	/*
+	 * Balance out the preempt calls - as we are running in cpu_idle
+	 * loop which has been called at bootup from cpu_bringup_and_idle.
+	 * The cpucpu_bringup_and_idle called cpu_bringup which made a
+	 * preempt_disable() So this preempt_enable will balance it out.
+	 */
+	preempt_enable();
 }
 
 #else /* !CONFIG_HOTPLUG_CPU */
diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index f04af93..107f6f7 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -31,11 +31,6 @@
         return (x & y) | (z & (x | y));
 }
 
-static inline u64 RORu64(u64 x, u64 y)
-{
-        return (x >> y) | (x << (64 - y));
-}
-
 static const u64 sha512_K[80] = {
         0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL, 0xb5c0fbcfec4d3b2fULL,
         0xe9b5dba58189dbbcULL, 0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
@@ -66,10 +61,10 @@
         0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL,
 };
 
-#define e0(x)       (RORu64(x,28) ^ RORu64(x,34) ^ RORu64(x,39))
-#define e1(x)       (RORu64(x,14) ^ RORu64(x,18) ^ RORu64(x,41))
-#define s0(x)       (RORu64(x, 1) ^ RORu64(x, 8) ^ (x >> 7))
-#define s1(x)       (RORu64(x,19) ^ RORu64(x,61) ^ (x >> 6))
+#define e0(x)       (ror64(x,28) ^ ror64(x,34) ^ ror64(x,39))
+#define e1(x)       (ror64(x,14) ^ ror64(x,18) ^ ror64(x,41))
+#define s0(x)       (ror64(x, 1) ^ ror64(x, 8) ^ (x >> 7))
+#define s1(x)       (ror64(x,19) ^ ror64(x,61) ^ (x >> 6))
 
 static inline void LOAD_OP(int I, u64 *W, const u8 *input)
 {
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 0cad48a..c6a383d 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -1694,6 +1694,7 @@
 
 		md->power_ro_lock.show = power_ro_lock_show;
 		md->power_ro_lock.store = power_ro_lock_store;
+		sysfs_attr_init(&md->power_ro_lock.attr);
 		md->power_ro_lock.attr.mode = mode;
 		md->power_ro_lock.attr.name =
 					"ro_lock_until_next_power_on";
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index f545a3e..690255c 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -290,8 +290,11 @@
 static void mmc_pre_req(struct mmc_host *host, struct mmc_request *mrq,
 		 bool is_first_req)
 {
-	if (host->ops->pre_req)
+	if (host->ops->pre_req) {
+		mmc_host_clk_hold(host);
 		host->ops->pre_req(host, mrq, is_first_req);
+		mmc_host_clk_release(host);
+	}
 }
 
 /**
@@ -306,8 +309,11 @@
 static void mmc_post_req(struct mmc_host *host, struct mmc_request *mrq,
 			 int err)
 {
-	if (host->ops->post_req)
+	if (host->ops->post_req) {
+		mmc_host_clk_hold(host);
 		host->ops->post_req(host, mrq, err);
+		mmc_host_clk_release(host);
+	}
 }
 
 /**
@@ -620,7 +626,9 @@
 		int err;
 
 		host->en_dis_recurs = 1;
+		mmc_host_clk_hold(host);
 		err = host->ops->enable(host);
+		mmc_host_clk_release(host);
 		host->en_dis_recurs = 0;
 
 		if (err) {
@@ -640,7 +648,9 @@
 		int err;
 
 		host->en_dis_recurs = 1;
+		mmc_host_clk_hold(host);
 		err = host->ops->disable(host, lazy);
+		mmc_host_clk_release(host);
 		host->en_dis_recurs = 0;
 
 		if (err < 0) {
@@ -1121,6 +1131,10 @@
 		 * might not allow this operation
 		 */
 		voltage = regulator_get_voltage(supply);
+
+		if (mmc->caps2 & MMC_CAP2_BROKEN_VOLTAGE)
+			min_uV = max_uV = voltage;
+
 		if (voltage < 0)
 			result = voltage;
 		else if (voltage < min_uV || voltage > max_uV)
@@ -1203,8 +1217,11 @@
 
 	host->ios.signal_voltage = signal_voltage;
 
-	if (host->ops->start_signal_voltage_switch)
+	if (host->ops->start_signal_voltage_switch) {
+		mmc_host_clk_hold(host);
 		err = host->ops->start_signal_voltage_switch(host, &host->ios);
+		mmc_host_clk_release(host);
+	}
 
 	return err;
 }
@@ -1239,6 +1256,7 @@
 	int err = 0;
 
 	card = host->card;
+	mmc_claim_host(host);
 
 	/*
 	 * Send power notify command only if card
@@ -1269,6 +1287,7 @@
 		/* Set the card state to no notification after the poweroff */
 		card->poweroff_notify_state = MMC_NO_POWER_NOTIFICATION;
 	}
+	mmc_release_host(host);
 }
 
 /*
@@ -1327,12 +1346,28 @@
 
 void mmc_power_off(struct mmc_host *host)
 {
+	int err = 0;
 	mmc_host_clk_hold(host);
 
 	host->ios.clock = 0;
 	host->ios.vdd = 0;
 
-	mmc_poweroff_notify(host);
+	/*
+	 * For eMMC 4.5 device send AWAKE command before
+	 * POWER_OFF_NOTIFY command, because in sleep state
+	 * eMMC 4.5 devices respond to only RESET and AWAKE cmd
+	 */
+	if (host->card && mmc_card_is_sleep(host->card) &&
+	    host->bus_ops->resume) {
+		err = host->bus_ops->resume(host);
+
+		if (!err)
+			mmc_poweroff_notify(host);
+		else
+			pr_warning("%s: error %d during resume "
+				   "(continue with poweroff sequence)\n",
+				   mmc_hostname(host), err);
+	}
 
 	/*
 	 * Reset ocr mask to be the highest possible voltage supported for
@@ -2386,12 +2421,6 @@
 		 */
 		if (mmc_try_claim_host(host)) {
 			if (host->bus_ops->suspend) {
-				/*
-				 * For eMMC 4.5 device send notify command
-				 * before sleep, because in sleep state eMMC 4.5
-				 * devices respond to only RESET and AWAKE cmd
-				 */
-				mmc_poweroff_notify(host);
 				err = host->bus_ops->suspend(host);
 			}
 			mmc_do_release_host(host);
diff --git a/drivers/mmc/core/host.h b/drivers/mmc/core/host.h
index fb8a5cd..08a7852 100644
--- a/drivers/mmc/core/host.h
+++ b/drivers/mmc/core/host.h
@@ -14,27 +14,6 @@
 
 int mmc_register_host_class(void);
 void mmc_unregister_host_class(void);
-
-#ifdef CONFIG_MMC_CLKGATE
-void mmc_host_clk_hold(struct mmc_host *host);
-void mmc_host_clk_release(struct mmc_host *host);
-unsigned int mmc_host_clk_rate(struct mmc_host *host);
-
-#else
-static inline void mmc_host_clk_hold(struct mmc_host *host)
-{
-}
-
-static inline void mmc_host_clk_release(struct mmc_host *host)
-{
-}
-
-static inline unsigned int mmc_host_clk_rate(struct mmc_host *host)
-{
-	return host->ios.clock;
-}
-#endif
-
 void mmc_host_deeper_disable(struct work_struct *work);
 
 #endif
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index 59b9ba5..a480663 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -376,7 +376,7 @@
 	}
 
 	card->ext_csd.raw_hc_erase_gap_size =
-		ext_csd[EXT_CSD_PARTITION_ATTRIBUTE];
+		ext_csd[EXT_CSD_HC_WP_GRP_SIZE];
 	card->ext_csd.raw_sec_trim_mult =
 		ext_csd[EXT_CSD_SEC_TRIM_MULT];
 	card->ext_csd.raw_sec_erase_mult =
@@ -551,7 +551,7 @@
 		goto out;
 
 	/* only compare read only fields */
-	err = (!(card->ext_csd.raw_partition_support ==
+	err = !((card->ext_csd.raw_partition_support ==
 			bw_ext_csd[EXT_CSD_PARTITION_SUPPORT]) &&
 		(card->ext_csd.raw_erased_mem_count ==
 			bw_ext_csd[EXT_CSD_ERASED_MEM_CONT]) &&
@@ -1006,7 +1006,8 @@
 			err = mmc_select_hs200(card);
 		else if	(host->caps & MMC_CAP_MMC_HIGHSPEED)
 			err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-					 EXT_CSD_HS_TIMING, 1, 0);
+					 EXT_CSD_HS_TIMING, 1,
+					 card->ext_csd.generic_cmd6_time);
 
 		if (err && err != -EBADMSG)
 			goto free_card;
@@ -1116,7 +1117,7 @@
 	 * Activate wide bus and DDR (if supported).
 	 */
 	if (!mmc_card_hs200(card) &&
-	    (card->csd.mmca_vsn >= CSD_SPEC_VER_3) &&
+	    (card->csd.mmca_vsn >= CSD_SPEC_VER_4) &&
 	    (host->caps & (MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA))) {
 		static unsigned ext_csd_bits[][2] = {
 			{ EXT_CSD_BUS_WIDTH_8, EXT_CSD_DDR_BUS_WIDTH_8 },
@@ -1315,11 +1316,13 @@
 	BUG_ON(!host->card);
 
 	mmc_claim_host(host);
-	if (mmc_card_can_sleep(host))
+	if (mmc_card_can_sleep(host)) {
 		err = mmc_card_sleep(host);
-	else if (!mmc_host_is_spi(host))
+		if (!err)
+			mmc_card_set_sleep(host->card);
+	} else if (!mmc_host_is_spi(host))
 		mmc_deselect_cards(host);
-	host->card->state &= ~MMC_STATE_HIGHSPEED;
+	host->card->state &= ~(MMC_STATE_HIGHSPEED | MMC_STATE_HIGHSPEED_200);
 	mmc_release_host(host);
 
 	return err;
@@ -1339,7 +1342,11 @@
 	BUG_ON(!host->card);
 
 	mmc_claim_host(host);
-	err = mmc_init_card(host, host->ocr, host->card);
+	if (mmc_card_is_sleep(host->card)) {
+		err = mmc_card_awake(host);
+		mmc_card_clr_sleep(host->card);
+	} else
+		err = mmc_init_card(host, host->ocr, host->card);
 	mmc_release_host(host);
 
 	return err;
@@ -1349,7 +1356,8 @@
 {
 	int ret;
 
-	host->card->state &= ~MMC_STATE_HIGHSPEED;
+	host->card->state &= ~(MMC_STATE_HIGHSPEED | MMC_STATE_HIGHSPEED_200);
+	mmc_card_clr_sleep(host->card);
 	mmc_claim_host(host);
 	ret = mmc_init_card(host, host->ocr, host->card);
 	mmc_release_host(host);
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index c63ad03..5017f93 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -451,9 +451,11 @@
 	 * information and let the hardware specific code
 	 * return what is possible given the options
 	 */
+	mmc_host_clk_hold(card->host);
 	drive_strength = card->host->ops->select_drive_strength(
 		card->sw_caps.uhs_max_dtr,
 		host_drv_type, card_drv_type);
+	mmc_host_clk_release(card->host);
 
 	err = mmc_sd_switch(card, 1, 2, drive_strength, status);
 	if (err)
@@ -660,9 +662,12 @@
 		goto out;
 
 	/* SPI mode doesn't define CMD19 */
-	if (!mmc_host_is_spi(card->host) && card->host->ops->execute_tuning)
+	if (!mmc_host_is_spi(card->host) && card->host->ops->execute_tuning) {
+		mmc_host_clk_hold(card->host);
 		err = card->host->ops->execute_tuning(card->host,
 						      MMC_SEND_TUNING_BLOCK);
+		mmc_host_clk_release(card->host);
+	}
 
 out:
 	kfree(status);
@@ -850,8 +855,11 @@
 	if (!reinit) {
 		int ro = -1;
 
-		if (host->ops->get_ro)
+		if (host->ops->get_ro) {
+			mmc_host_clk_hold(card->host);
 			ro = host->ops->get_ro(host);
+			mmc_host_clk_release(card->host);
+		}
 
 		if (ro < 0) {
 			pr_warning("%s: host does not "
@@ -967,8 +975,11 @@
 		 * Since initialization is now complete, enable preset
 		 * value registers for UHS-I cards.
 		 */
-		if (host->ops->enable_preset_value)
+		if (host->ops->enable_preset_value) {
+			mmc_host_clk_hold(card->host);
 			host->ops->enable_preset_value(host, true);
+			mmc_host_clk_release(card->host);
+		}
 	} else {
 		/*
 		 * Attempt to change to high-speed (if supported)
@@ -1151,8 +1162,11 @@
 		return err;
 
 	/* Disable preset value enable if already set since last time */
-	if (host->ops->enable_preset_value)
+	if (host->ops->enable_preset_value) {
+		mmc_host_clk_hold(host);
 		host->ops->enable_preset_value(host, false);
+		mmc_host_clk_release(host);
+	}
 
 	err = mmc_send_app_op_cond(host, 0, &ocr);
 	if (err)
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index bd7bacc..12cde6e 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -98,10 +98,11 @@
 	return ret;
 }
 
-static int sdio_read_cccr(struct mmc_card *card)
+static int sdio_read_cccr(struct mmc_card *card, u32 ocr)
 {
 	int ret;
 	int cccr_vsn;
+	int uhs = ocr & R4_18V_PRESENT;
 	unsigned char data;
 	unsigned char speed;
 
@@ -149,7 +150,7 @@
 		card->scr.sda_spec3 = 0;
 		card->sw_caps.sd3_bus_mode = 0;
 		card->sw_caps.sd3_drv_type = 0;
-		if (cccr_vsn >= SDIO_CCCR_REV_3_00) {
+		if (cccr_vsn >= SDIO_CCCR_REV_3_00 && uhs) {
 			card->scr.sda_spec3 = 1;
 			ret = mmc_io_rw_direct(card, 0, 0,
 				SDIO_CCCR_UHS, 0, &data);
@@ -712,7 +713,7 @@
 	/*
 	 * Read the common registers.
 	 */
-	err = sdio_read_cccr(card);
+	err = sdio_read_cccr(card, ocr);
 	if (err)
 		goto remove;
 
diff --git a/drivers/mmc/core/sdio_irq.c b/drivers/mmc/core/sdio_irq.c
index 68f81b9..f573e7f 100644
--- a/drivers/mmc/core/sdio_irq.c
+++ b/drivers/mmc/core/sdio_irq.c
@@ -146,15 +146,21 @@
 		}
 
 		set_current_state(TASK_INTERRUPTIBLE);
-		if (host->caps & MMC_CAP_SDIO_IRQ)
+		if (host->caps & MMC_CAP_SDIO_IRQ) {
+			mmc_host_clk_hold(host);
 			host->ops->enable_sdio_irq(host, 1);
+			mmc_host_clk_release(host);
+		}
 		if (!kthread_should_stop())
 			schedule_timeout(period);
 		set_current_state(TASK_RUNNING);
 	} while (!kthread_should_stop());
 
-	if (host->caps & MMC_CAP_SDIO_IRQ)
+	if (host->caps & MMC_CAP_SDIO_IRQ) {
+		mmc_host_clk_hold(host);
 		host->ops->enable_sdio_irq(host, 0);
+		mmc_host_clk_release(host);
+	}
 
 	pr_debug("%s: IRQ thread exiting with code %d\n",
 		 mmc_hostname(host), ret);
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index fcfe1eb..6985cdb 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -969,11 +969,14 @@
 	host->data_status = 0;
 
 	if (host->need_reset) {
+		iflags = atmci_readl(host, ATMCI_IMR);
+		iflags &= (ATMCI_SDIOIRQA | ATMCI_SDIOIRQB);
 		atmci_writel(host, ATMCI_CR, ATMCI_CR_SWRST);
 		atmci_writel(host, ATMCI_CR, ATMCI_CR_MCIEN);
 		atmci_writel(host, ATMCI_MR, host->mode_reg);
 		if (host->caps.has_cfg_reg)
 			atmci_writel(host, ATMCI_CFG, host->cfg_reg);
+		atmci_writel(host, ATMCI_IER, iflags);
 		host->need_reset = false;
 	}
 	atmci_writel(host, ATMCI_SDCR, slot->sdc_reg);
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 0e34279..8bec1c3 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -22,7 +22,6 @@
 #include <linux/ioport.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/scatterlist.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/stat.h>
@@ -502,8 +501,14 @@
 		host->dir_status = DW_MCI_SEND_STATUS;
 
 	if (dw_mci_submit_data_dma(host, data)) {
+		int flags = SG_MITER_ATOMIC;
+		if (host->data->flags & MMC_DATA_READ)
+			flags |= SG_MITER_TO_SG;
+		else
+			flags |= SG_MITER_FROM_SG;
+
+		sg_miter_start(&host->sg_miter, data->sg, data->sg_len, flags);
 		host->sg = data->sg;
-		host->pio_offset = 0;
 		host->part_buf_start = 0;
 		host->part_buf_count = 0;
 
@@ -972,6 +977,7 @@
 				 * generates a block interrupt, hence setting
 				 * the scatter-gather pointer to NULL.
 				 */
+				sg_miter_stop(&host->sg_miter);
 				host->sg = NULL;
 				ctrl = mci_readl(host, CTRL);
 				ctrl |= SDMMC_CTRL_FIFO_RESET;
@@ -1311,54 +1317,44 @@
 
 static void dw_mci_read_data_pio(struct dw_mci *host)
 {
-	struct scatterlist *sg = host->sg;
-	void *buf = sg_virt(sg);
-	unsigned int offset = host->pio_offset;
+	struct sg_mapping_iter *sg_miter = &host->sg_miter;
+	void *buf;
+	unsigned int offset;
 	struct mmc_data	*data = host->data;
 	int shift = host->data_shift;
 	u32 status;
 	unsigned int nbytes = 0, len;
+	unsigned int remain, fcnt;
 
 	do {
-		len = host->part_buf_count +
-			(SDMMC_GET_FCNT(mci_readl(host, STATUS)) << shift);
-		if (offset + len <= sg->length) {
-			dw_mci_pull_data(host, (void *)(buf + offset), len);
+		if (!sg_miter_next(sg_miter))
+			goto done;
 
+		host->sg = sg_miter->__sg;
+		buf = sg_miter->addr;
+		remain = sg_miter->length;
+		offset = 0;
+
+		do {
+			fcnt = (SDMMC_GET_FCNT(mci_readl(host, STATUS))
+					<< shift) + host->part_buf_count;
+			len = min(remain, fcnt);
+			if (!len)
+				break;
+			dw_mci_pull_data(host, (void *)(buf + offset), len);
 			offset += len;
 			nbytes += len;
-
-			if (offset == sg->length) {
-				flush_dcache_page(sg_page(sg));
-				host->sg = sg = sg_next(sg);
-				if (!sg)
-					goto done;
-
-				offset = 0;
-				buf = sg_virt(sg);
-			}
-		} else {
-			unsigned int remaining = sg->length - offset;
-			dw_mci_pull_data(host, (void *)(buf + offset),
-					 remaining);
-			nbytes += remaining;
-
-			flush_dcache_page(sg_page(sg));
-			host->sg = sg = sg_next(sg);
-			if (!sg)
-				goto done;
-
-			offset = len - remaining;
-			buf = sg_virt(sg);
-			dw_mci_pull_data(host, buf, offset);
-			nbytes += offset;
-		}
+			remain -= len;
+		} while (remain);
+		sg_miter->consumed = offset;
 
 		status = mci_readl(host, MINTSTS);
 		mci_writel(host, RINTSTS, SDMMC_INT_RXDR);
 		if (status & DW_MCI_DATA_ERROR_FLAGS) {
 			host->data_status = status;
 			data->bytes_xfered += nbytes;
+			sg_miter_stop(sg_miter);
+			host->sg = NULL;
 			smp_wmb();
 
 			set_bit(EVENT_DATA_ERROR, &host->pending_events);
@@ -1367,65 +1363,66 @@
 			return;
 		}
 	} while (status & SDMMC_INT_RXDR); /*if the RXDR is ready read again*/
-	host->pio_offset = offset;
 	data->bytes_xfered += nbytes;
+
+	if (!remain) {
+		if (!sg_miter_next(sg_miter))
+			goto done;
+		sg_miter->consumed = 0;
+	}
+	sg_miter_stop(sg_miter);
 	return;
 
 done:
 	data->bytes_xfered += nbytes;
+	sg_miter_stop(sg_miter);
+	host->sg = NULL;
 	smp_wmb();
 	set_bit(EVENT_XFER_COMPLETE, &host->pending_events);
 }
 
 static void dw_mci_write_data_pio(struct dw_mci *host)
 {
-	struct scatterlist *sg = host->sg;
-	void *buf = sg_virt(sg);
-	unsigned int offset = host->pio_offset;
+	struct sg_mapping_iter *sg_miter = &host->sg_miter;
+	void *buf;
+	unsigned int offset;
 	struct mmc_data	*data = host->data;
 	int shift = host->data_shift;
 	u32 status;
 	unsigned int nbytes = 0, len;
+	unsigned int fifo_depth = host->fifo_depth;
+	unsigned int remain, fcnt;
 
 	do {
-		len = ((host->fifo_depth -
-			SDMMC_GET_FCNT(mci_readl(host, STATUS))) << shift)
-			- host->part_buf_count;
-		if (offset + len <= sg->length) {
-			host->push_data(host, (void *)(buf + offset), len);
+		if (!sg_miter_next(sg_miter))
+			goto done;
 
+		host->sg = sg_miter->__sg;
+		buf = sg_miter->addr;
+		remain = sg_miter->length;
+		offset = 0;
+
+		do {
+			fcnt = ((fifo_depth -
+				 SDMMC_GET_FCNT(mci_readl(host, STATUS)))
+					<< shift) - host->part_buf_count;
+			len = min(remain, fcnt);
+			if (!len)
+				break;
+			host->push_data(host, (void *)(buf + offset), len);
 			offset += len;
 			nbytes += len;
-			if (offset == sg->length) {
-				host->sg = sg = sg_next(sg);
-				if (!sg)
-					goto done;
-
-				offset = 0;
-				buf = sg_virt(sg);
-			}
-		} else {
-			unsigned int remaining = sg->length - offset;
-
-			host->push_data(host, (void *)(buf + offset),
-					remaining);
-			nbytes += remaining;
-
-			host->sg = sg = sg_next(sg);
-			if (!sg)
-				goto done;
-
-			offset = len - remaining;
-			buf = sg_virt(sg);
-			host->push_data(host, (void *)buf, offset);
-			nbytes += offset;
-		}
+			remain -= len;
+		} while (remain);
+		sg_miter->consumed = offset;
 
 		status = mci_readl(host, MINTSTS);
 		mci_writel(host, RINTSTS, SDMMC_INT_TXDR);
 		if (status & DW_MCI_DATA_ERROR_FLAGS) {
 			host->data_status = status;
 			data->bytes_xfered += nbytes;
+			sg_miter_stop(sg_miter);
+			host->sg = NULL;
 
 			smp_wmb();
 
@@ -1435,12 +1432,20 @@
 			return;
 		}
 	} while (status & SDMMC_INT_TXDR); /* if TXDR write again */
-	host->pio_offset = offset;
 	data->bytes_xfered += nbytes;
+
+	if (!remain) {
+		if (!sg_miter_next(sg_miter))
+			goto done;
+		sg_miter->consumed = 0;
+	}
+	sg_miter_stop(sg_miter);
 	return;
 
 done:
 	data->bytes_xfered += nbytes;
+	sg_miter_stop(sg_miter);
+	host->sg = NULL;
 	smp_wmb();
 	set_bit(EVENT_XFER_COMPLETE, &host->pending_events);
 }
@@ -1643,6 +1648,7 @@
 				 * block interrupt, hence setting the
 				 * scatter-gather pointer to NULL.
 				 */
+				sg_miter_stop(&host->sg_miter);
 				host->sg = NULL;
 
 				ctrl = mci_readl(host, CTRL);
diff --git a/drivers/mmc/host/of_mmc_spi.c b/drivers/mmc/host/of_mmc_spi.c
index ab66f24..1534b58 100644
--- a/drivers/mmc/host/of_mmc_spi.c
+++ b/drivers/mmc/host/of_mmc_spi.c
@@ -113,8 +113,8 @@
 		const int j = i * 2;
 		u32 mask;
 
-		mask = mmc_vddrange_to_ocrmask(voltage_ranges[j],
-					       voltage_ranges[j + 1]);
+		mask = mmc_vddrange_to_ocrmask(be32_to_cpu(voltage_ranges[j]),
+					       be32_to_cpu(voltage_ranges[j + 1]));
 		if (!mask) {
 			ret = -EINVAL;
 			dev_err(dev, "OF: voltage-range #%d is invalid\n", i);
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index ff4adc0..5d876ff 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -38,6 +38,23 @@
 	int base = reg & ~0x3;
 	int shift = (reg & 0x3) * 8;
 	u8 ret = (in_be32(host->ioaddr + base) >> shift) & 0xff;
+
+	/*
+	 * "DMA select" locates at offset 0x28 in SD specification, but on
+	 * P5020 or P3041, it locates at 0x29.
+	 */
+	if (reg == SDHCI_HOST_CONTROL) {
+		u32 dma_bits;
+
+		dma_bits = in_be32(host->ioaddr + reg);
+		/* DMA select is 22,23 bits in Protocol Control Register */
+		dma_bits = (dma_bits >> 5) & SDHCI_CTRL_DMA_MASK;
+
+		/* fixup the result */
+		ret &= ~SDHCI_CTRL_DMA_MASK;
+		ret |= dma_bits;
+	}
+
 	return ret;
 }
 
@@ -56,6 +73,21 @@
 
 static void esdhc_writeb(struct sdhci_host *host, u8 val, int reg)
 {
+	/*
+	 * "DMA select" location is offset 0x28 in SD specification, but on
+	 * P5020 or P3041, it's located at 0x29.
+	 */
+	if (reg == SDHCI_HOST_CONTROL) {
+		u32 dma_bits;
+
+		/* DMA select is 22,23 bits in Protocol Control Register */
+		dma_bits = (val & SDHCI_CTRL_DMA_MASK) << 5;
+		clrsetbits_be32(host->ioaddr + reg , SDHCI_CTRL_DMA_MASK << 5,
+			dma_bits);
+		val &= ~SDHCI_CTRL_DMA_MASK;
+		val |= in_be32(host->ioaddr + reg) & SDHCI_CTRL_DMA_MASK;
+	}
+
 	/* Prevent SDHCI core from writing reserved bits (e.g. HISPD). */
 	if (reg == SDHCI_HOST_CONTROL)
 		val &= ~ESDHC_HOST_CONTROL_RES;
diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c
index 7165e6a..6ebdc40 100644
--- a/drivers/mmc/host/sdhci-pci.c
+++ b/drivers/mmc/host/sdhci-pci.c
@@ -250,7 +250,7 @@
 
 static int mfd_sdio_probe_slot(struct sdhci_pci_slot *slot)
 {
-	slot->host->mmc->caps |= MMC_CAP_POWER_OFF_CARD;
+	slot->host->mmc->caps |= MMC_CAP_POWER_OFF_CARD | MMC_CAP_NONREMOVABLE;
 	return 0;
 }
 
diff --git a/drivers/mmc/host/sdhci-pltfm.c b/drivers/mmc/host/sdhci-pltfm.c
index 03970bc..c5c2a48 100644
--- a/drivers/mmc/host/sdhci-pltfm.c
+++ b/drivers/mmc/host/sdhci-pltfm.c
@@ -2,7 +2,7 @@
  * sdhci-pltfm.c Support for SDHCI platform devices
  * Copyright (c) 2009 Intel Corporation
  *
- * Copyright (c) 2007 Freescale Semiconductor, Inc.
+ * Copyright (c) 2007, 2011 Freescale Semiconductor, Inc.
  * Copyright (c) 2009 MontaVista Software, Inc.
  *
  * Authors: Xiaobo Xie <X.Xie@freescale.com>
@@ -71,6 +71,14 @@
 		if (sdhci_of_wp_inverted(np))
 			host->quirks |= SDHCI_QUIRK_INVERTED_WRITE_PROTECT;
 
+		if (of_device_is_compatible(np, "fsl,p2020-rev1-esdhc"))
+			host->quirks |= SDHCI_QUIRK_BROKEN_DMA;
+
+		if (of_device_is_compatible(np, "fsl,p2020-esdhc") ||
+		    of_device_is_compatible(np, "fsl,p1010-esdhc") ||
+		    of_device_is_compatible(np, "fsl,mpc8536-esdhc"))
+			host->quirks |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL;
+
 		clk = of_get_property(np, "clock-frequency", &size);
 		if (clk && size == sizeof(*clk) && *clk)
 			pltfm_host->clock = be32_to_cpup(clk);
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index f5d8b53..352d479 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -1327,7 +1327,7 @@
 	if (ret < 0)
 		goto clean_up2;
 
-	mmc_add_host(mmc);
+	INIT_DELAYED_WORK(&host->timeout_work, mmcif_timeout_work);
 
 	sh_mmcif_writel(host->addr, MMCIF_CE_INT_MASK, MASK_ALL);
 
@@ -1338,22 +1338,24 @@
 	}
 	ret = request_threaded_irq(irq[1], sh_mmcif_intr, sh_mmcif_irqt, 0, "sh_mmc:int", host);
 	if (ret) {
-		free_irq(irq[0], host);
 		dev_err(&pdev->dev, "request_irq error (sh_mmc:int)\n");
-		goto clean_up3;
+		goto clean_up4;
 	}
 
-	INIT_DELAYED_WORK(&host->timeout_work, mmcif_timeout_work);
-
-	mmc_detect_change(host->mmc, 0);
+	ret = mmc_add_host(mmc);
+	if (ret < 0)
+		goto clean_up5;
 
 	dev_info(&pdev->dev, "driver version %s\n", DRIVER_VERSION);
 	dev_dbg(&pdev->dev, "chip ver H'%04x\n",
 		sh_mmcif_readl(host->addr, MMCIF_CE_VERSION) & 0x0000ffff);
 	return ret;
 
+clean_up5:
+	free_irq(irq[1], host);
+clean_up4:
+	free_irq(irq[0], host);
 clean_up3:
-	mmc_remove_host(mmc);
 	pm_runtime_suspend(&pdev->dev);
 clean_up2:
 	pm_runtime_disable(&pdev->dev);
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index a95e6d9..f96c536 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -20,8 +20,8 @@
 #include <linux/mmc/tmio.h>
 #include <linux/mutex.h>
 #include <linux/pagemap.h>
-#include <linux/spinlock.h>
 #include <linux/scatterlist.h>
+#include <linux/spinlock.h>
 
 /* Definitions for values the CTRL_SDIO_STATUS register can take. */
 #define TMIO_SDIO_STAT_IOIRQ	0x0001
@@ -120,6 +120,7 @@
 void tmio_mmc_enable_dma(struct tmio_mmc_host *host, bool enable);
 void tmio_mmc_request_dma(struct tmio_mmc_host *host, struct tmio_mmc_data *pdata);
 void tmio_mmc_release_dma(struct tmio_mmc_host *host);
+void tmio_mmc_abort_dma(struct tmio_mmc_host *host);
 #else
 static inline void tmio_mmc_start_dma(struct tmio_mmc_host *host,
 			       struct mmc_data *data)
@@ -140,6 +141,10 @@
 static inline void tmio_mmc_release_dma(struct tmio_mmc_host *host)
 {
 }
+
+static inline void tmio_mmc_abort_dma(struct tmio_mmc_host *host)
+{
+}
 #endif
 
 #ifdef CONFIG_PM
diff --git a/drivers/mmc/host/tmio_mmc_dma.c b/drivers/mmc/host/tmio_mmc_dma.c
index 7a6e6cc..8253ec1 100644
--- a/drivers/mmc/host/tmio_mmc_dma.c
+++ b/drivers/mmc/host/tmio_mmc_dma.c
@@ -34,6 +34,18 @@
 #endif
 }
 
+void tmio_mmc_abort_dma(struct tmio_mmc_host *host)
+{
+	tmio_mmc_enable_dma(host, false);
+
+	if (host->chan_rx)
+		dmaengine_terminate_all(host->chan_rx);
+	if (host->chan_tx)
+		dmaengine_terminate_all(host->chan_tx);
+
+	tmio_mmc_enable_dma(host, true);
+}
+
 static void tmio_mmc_start_dma_rx(struct tmio_mmc_host *host)
 {
 	struct scatterlist *sg = host->sg_ptr, *sg_tmp;
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index abad01b..5f9ad74 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -41,8 +41,8 @@
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/scatterlist.h>
-#include <linux/workqueue.h>
 #include <linux/spinlock.h>
+#include <linux/workqueue.h>
 
 #include "tmio_mmc.h"
 
@@ -246,6 +246,7 @@
 	/* Ready for new calls */
 	host->mrq = NULL;
 
+	tmio_mmc_abort_dma(host);
 	mmc_request_done(host->mmc, mrq);
 }
 
@@ -272,6 +273,9 @@
 	host->mrq = NULL;
 	spin_unlock_irqrestore(&host->lock, flags);
 
+	if (mrq->cmd->error || (mrq->data && mrq->data->error))
+		tmio_mmc_abort_dma(host);
+
 	mmc_request_done(host->mmc, mrq);
 }
 
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index 7cf3d2f..1620088 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -189,7 +189,7 @@
 
 	if (verbose_request)
 		dev_info(&pdev->xdev->dev,
-			 "read dev=%04x:%02x:%02x.%01x - offset %x size %d\n",
+			 "read dev=%04x:%02x:%02x.%d - offset %x size %d\n",
 			 pci_domain_nr(bus), bus->number, PCI_SLOT(devfn),
 			 PCI_FUNC(devfn), where, size);
 
@@ -228,7 +228,7 @@
 
 	if (verbose_request)
 		dev_info(&pdev->xdev->dev,
-			 "write dev=%04x:%02x:%02x.%01x - "
+			 "write dev=%04x:%02x:%02x.%d - "
 			 "offset %x size %d val %x\n",
 			 pci_domain_nr(bus), bus->number,
 			 PCI_SLOT(devfn), PCI_FUNC(devfn), where, size, val);
@@ -432,7 +432,7 @@
 		d = pci_scan_single_device(b, devfn);
 		if (d)
 			dev_info(&pdev->xdev->dev, "New device on "
-				 "%04x:%02x:%02x.%02x found.\n", domain, bus,
+				 "%04x:%02x:%02x.%d found.\n", domain, bus,
 				 PCI_SLOT(devfn), PCI_FUNC(devfn));
 	}
 
@@ -1041,7 +1041,7 @@
 		pci_dev = pci_get_slot(pci_bus, PCI_DEVFN(slot, func));
 		if (!pci_dev) {
 			dev_dbg(&pdev->xdev->dev,
-				"Cannot get PCI device %04x:%02x:%02x.%02x\n",
+				"Cannot get PCI device %04x:%02x:%02x.%d\n",
 				domain, bus, slot, func);
 			continue;
 		}
@@ -1049,7 +1049,7 @@
 		pci_dev_put(pci_dev);
 
 		dev_dbg(&pdev->xdev->dev,
-			"PCI device %04x:%02x:%02x.%02x removed.\n",
+			"PCI device %04x:%02x:%02x.%d removed.\n",
 			domain, bus, slot, func);
 	}
 
diff --git a/drivers/regulator/max8649.c b/drivers/regulator/max8649.c
index b06a239..d0e1180 100644
--- a/drivers/regulator/max8649.c
+++ b/drivers/regulator/max8649.c
@@ -150,7 +150,7 @@
 	if (ret != 0)
 		return ret;
 	val &= MAX8649_VOL_MASK;
-	voltage = max8649_list_voltage(rdev, (unsigned char)ret); /* uV */
+	voltage = max8649_list_voltage(rdev, (unsigned char)val); /* uV */
 
 	/* get rate */
 	ret = regmap_read(info->regmap, MAX8649_RAMP, &val);
diff --git a/drivers/regulator/mc13xxx-regulator-core.c b/drivers/regulator/mc13xxx-regulator-core.c
index 80ecafe..62dcd0a 100644
--- a/drivers/regulator/mc13xxx-regulator-core.c
+++ b/drivers/regulator/mc13xxx-regulator-core.c
@@ -254,6 +254,7 @@
 
 	return num;
 }
+EXPORT_SYMBOL_GPL(mc13xxx_get_num_regulators_dt);
 
 struct mc13xxx_regulator_init_data * __devinit mc13xxx_parse_regulators_dt(
 	struct platform_device *pdev, struct mc13xxx_regulator *regulators,
@@ -291,6 +292,7 @@
 
 	return data;
 }
+EXPORT_SYMBOL_GPL(mc13xxx_parse_regulators_dt);
 #endif
 
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c
index 14e2d99..4dcfced 100644
--- a/drivers/xen/cpu_hotplug.c
+++ b/drivers/xen/cpu_hotplug.c
@@ -30,7 +30,8 @@
 	sprintf(dir, "cpu/%u", cpu);
 	err = xenbus_scanf(XBT_NIL, dir, "availability", "%s", state);
 	if (err != 1) {
-		printk(KERN_ERR "XENBUS: Unable to read cpu state\n");
+		if (!xen_initial_domain())
+			printk(KERN_ERR "XENBUS: Unable to read cpu state\n");
 		return err;
 	}
 
diff --git a/drivers/xen/xen-pciback/pci_stub.c b/drivers/xen/xen-pciback/pci_stub.c
index 7944a17..19834d1 100644
--- a/drivers/xen/xen-pciback/pci_stub.c
+++ b/drivers/xen/xen-pciback/pci_stub.c
@@ -884,7 +884,7 @@
 	int err;
 
 	err =
-	    sscanf(buf, " %04x:%02x:%02x.%1x-%08x:%1x:%08x", domain, bus, slot,
+	    sscanf(buf, " %04x:%02x:%02x.%d-%08x:%1x:%08x", domain, bus, slot,
 		   func, reg, size, mask);
 	if (err == 7)
 		return 0;
@@ -904,7 +904,7 @@
 	pci_dev_id->bus = bus;
 	pci_dev_id->devfn = PCI_DEVFN(slot, func);
 
-	pr_debug(DRV_NAME ": wants to seize %04x:%02x:%02x.%01x\n",
+	pr_debug(DRV_NAME ": wants to seize %04x:%02x:%02x.%d\n",
 		 domain, bus, slot, func);
 
 	spin_lock_irqsave(&device_ids_lock, flags);
@@ -934,7 +934,7 @@
 
 			err = 0;
 
-			pr_debug(DRV_NAME ": removed %04x:%02x:%02x.%01x from "
+			pr_debug(DRV_NAME ": removed %04x:%02x:%02x.%d from "
 				 "seize list\n", domain, bus, slot, func);
 		}
 	}
@@ -1029,7 +1029,7 @@
 			break;
 
 		count += scnprintf(buf + count, PAGE_SIZE - count,
-				   "%04x:%02x:%02x.%01x\n",
+				   "%04x:%02x:%02x.%d\n",
 				   pci_dev_id->domain, pci_dev_id->bus,
 				   PCI_SLOT(pci_dev_id->devfn),
 				   PCI_FUNC(pci_dev_id->devfn));
diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c
index d5dcf8d..64b11f9 100644
--- a/drivers/xen/xen-pciback/xenbus.c
+++ b/drivers/xen/xen-pciback/xenbus.c
@@ -206,6 +206,7 @@
 		goto out;
 	}
 
+	/* Note: The PV protocol uses %02x, don't change it */
 	err = xenbus_printf(XBT_NIL, pdev->xdev->nodename, str,
 			    "%04x:%02x:%02x.%02x", domain, bus,
 			    PCI_SLOT(devfn), PCI_FUNC(devfn));
@@ -229,7 +230,7 @@
 		err = -EINVAL;
 		xenbus_dev_fatal(pdev->xdev, err,
 				 "Couldn't locate PCI device "
-				 "(%04x:%02x:%02x.%01x)! "
+				 "(%04x:%02x:%02x.%d)! "
 				 "perhaps already in-use?",
 				 domain, bus, slot, func);
 		goto out;
@@ -274,7 +275,7 @@
 	if (!dev) {
 		err = -EINVAL;
 		dev_dbg(&pdev->xdev->dev, "Couldn't locate PCI device "
-			"(%04x:%02x:%02x.%01x)! not owned by this domain\n",
+			"(%04x:%02x:%02x.%d)! not owned by this domain\n",
 			domain, bus, slot, func);
 		goto out;
 	}
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index 527dc2a..89f7625 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -369,6 +369,10 @@
 		goto out;
 	}
 	token++;
+	if (memchr(token, 0, u->u.msg.len - (token - path)) == NULL) {
+		rc = -EILSEQ;
+		goto out;
+	}
 
 	if (msg_type == XS_WATCH) {
 		watch = alloc_watch_adapter(path, token);
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 3c1063a..94300fe 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -56,6 +56,26 @@
 }
 
 /**
+ * rol64 - rotate a 64-bit value left
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u64 rol64(__u64 word, unsigned int shift)
+{
+	return (word << shift) | (word >> (64 - shift));
+}
+
+/**
+ * ror64 - rotate a 64-bit value right
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u64 ror64(__u64 word, unsigned int shift)
+{
+	return (word >> shift) | (word << (64 - shift));
+}
+
+/**
  * rol32 - rotate a 32-bit value left
  * @word: value to rotate
  * @shift: bits to roll
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 9f22ba5..19a41d1 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -217,6 +217,7 @@
 #define MMC_CARD_SDXC		(1<<6)		/* card is SDXC */
 #define MMC_CARD_REMOVED	(1<<7)		/* card has been removed */
 #define MMC_STATE_HIGHSPEED_200	(1<<8)		/* card is in HS200 mode */
+#define MMC_STATE_SLEEP		(1<<9)		/* card is in sleep state */
 	unsigned int		quirks; 	/* card quirks */
 #define MMC_QUIRK_LENIENT_FN0	(1<<0)		/* allow SDIO FN0 writes outside of the VS CCCR range */
 #define MMC_QUIRK_BLKSZ_FOR_BYTE_MODE (1<<1)	/* use func->cur_blksize */
@@ -382,6 +383,7 @@
 #define mmc_sd_card_uhs(c)	((c)->state & MMC_STATE_ULTRAHIGHSPEED)
 #define mmc_card_ext_capacity(c) ((c)->state & MMC_CARD_SDXC)
 #define mmc_card_removed(c)	((c) && ((c)->state & MMC_CARD_REMOVED))
+#define mmc_card_is_sleep(c)	((c)->state & MMC_STATE_SLEEP)
 
 #define mmc_card_set_present(c)	((c)->state |= MMC_STATE_PRESENT)
 #define mmc_card_set_readonly(c) ((c)->state |= MMC_STATE_READONLY)
@@ -393,7 +395,9 @@
 #define mmc_sd_card_set_uhs(c) ((c)->state |= MMC_STATE_ULTRAHIGHSPEED)
 #define mmc_card_set_ext_capacity(c) ((c)->state |= MMC_CARD_SDXC)
 #define mmc_card_set_removed(c) ((c)->state |= MMC_CARD_REMOVED)
+#define mmc_card_set_sleep(c)	((c)->state |= MMC_STATE_SLEEP)
 
+#define mmc_card_clr_sleep(c)	((c)->state &= ~MMC_STATE_SLEEP)
 /*
  * Quirk add/remove for MMC products.
  */
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index e8779c6..aae5d1f 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -14,6 +14,8 @@
 #ifndef LINUX_MMC_DW_MMC_H
 #define LINUX_MMC_DW_MMC_H
 
+#include <linux/scatterlist.h>
+
 #define MAX_MCI_SLOTS	2
 
 enum dw_mci_state {
@@ -40,7 +42,7 @@
  * @lock: Spinlock protecting the queue and associated data.
  * @regs: Pointer to MMIO registers.
  * @sg: Scatterlist entry currently being processed by PIO code, if any.
- * @pio_offset: Offset into the current scatterlist entry.
+ * @sg_miter: PIO mapping scatterlist iterator.
  * @cur_slot: The slot which is currently using the controller.
  * @mrq: The request currently being processed on @cur_slot,
  *	or NULL if the controller is idle.
@@ -115,7 +117,7 @@
 	void __iomem		*regs;
 
 	struct scatterlist	*sg;
-	unsigned int		pio_offset;
+	struct sg_mapping_iter	sg_miter;
 
 	struct dw_mci_slot	*cur_slot;
 	struct mmc_request	*mrq;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 0beba1e..ee2b036 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -257,6 +257,7 @@
 #define MMC_CAP2_HS200_1_2V_SDR	(1 << 6)        /* can support */
 #define MMC_CAP2_HS200		(MMC_CAP2_HS200_1_8V_SDR | \
 				 MMC_CAP2_HS200_1_2V_SDR)
+#define MMC_CAP2_BROKEN_VOLTAGE	(1 << 7)	/* Use the broken voltage */
 
 	mmc_pm_flag_t		pm_caps;	/* supported pm features */
 	unsigned int        power_notify_type;
@@ -444,4 +445,23 @@
 	return !(host->caps2 & MMC_CAP2_BOOTPART_NOACC);
 }
 
+#ifdef CONFIG_MMC_CLKGATE
+void mmc_host_clk_hold(struct mmc_host *host);
+void mmc_host_clk_release(struct mmc_host *host);
+unsigned int mmc_host_clk_rate(struct mmc_host *host);
+
+#else
+static inline void mmc_host_clk_hold(struct mmc_host *host)
+{
+}
+
+static inline void mmc_host_clk_release(struct mmc_host *host)
+{
+}
+
+static inline unsigned int mmc_host_clk_rate(struct mmc_host *host)
+{
+	return host->ios.clock;
+}
+#endif
 #endif /* LINUX_MMC_HOST_H */
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 9350f3c..1358987 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4374,6 +4374,7 @@
 	ALC882_FIXUP_ACER_ASPIRE_8930G,
 	ALC882_FIXUP_ASPIRE_8930G_VERBS,
 	ALC885_FIXUP_MACPRO_GPIO,
+	ALC889_FIXUP_DAC_ROUTE,
 };
 
 static void alc889_fixup_coef(struct hda_codec *codec,
@@ -4427,6 +4428,23 @@
 	alc882_gpio_mute(codec, 1, 0);
 }
 
+/* Fix the connection of some pins for ALC889:
+ * At least, Acer Aspire 5935 shows the connections to DAC3/4 don't
+ * work correctly (bko#42740)
+ */
+static void alc889_fixup_dac_route(struct hda_codec *codec,
+				   const struct alc_fixup *fix, int action)
+{
+	if (action == ALC_FIXUP_ACT_PRE_PROBE) {
+		hda_nid_t conn1[2] = { 0x0c, 0x0d };
+		hda_nid_t conn2[2] = { 0x0e, 0x0f };
+		snd_hda_override_conn_list(codec, 0x14, 2, conn1);
+		snd_hda_override_conn_list(codec, 0x15, 2, conn1);
+		snd_hda_override_conn_list(codec, 0x18, 2, conn2);
+		snd_hda_override_conn_list(codec, 0x1a, 2, conn2);
+	}
+}
+
 static const struct alc_fixup alc882_fixups[] = {
 	[ALC882_FIXUP_ABIT_AW9D_MAX] = {
 		.type = ALC_FIXUP_PINS,
@@ -4574,6 +4592,10 @@
 		.type = ALC_FIXUP_FUNC,
 		.v.func = alc885_fixup_macpro_gpio,
 	},
+	[ALC889_FIXUP_DAC_ROUTE] = {
+		.type = ALC_FIXUP_FUNC,
+		.v.func = alc889_fixup_dac_route,
+	},
 };
 
 static const struct snd_pci_quirk alc882_fixup_tbl[] = {
@@ -4598,6 +4620,7 @@
 	SND_PCI_QUIRK(0x1025, 0x0142, "Acer Aspire 7730G",
 		      ALC882_FIXUP_ACER_ASPIRE_4930G),
 	SND_PCI_QUIRK(0x1025, 0x0155, "Packard-Bell M5120", ALC882_FIXUP_PB_M5210),
+	SND_PCI_QUIRK(0x1025, 0x0259, "Acer Aspire 5935", ALC889_FIXUP_DAC_ROUTE),
 	SND_PCI_QUIRK(0x1025, 0x0296, "Acer Aspire 7736z", ALC882_FIXUP_ACER_ASPIRE_7736),
 	SND_PCI_QUIRK(0x1043, 0x13c2, "Asus A7M", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x1043, 0x1873, "ASUS W90V", ALC882_FIXUP_ASUS_W90V),
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 948f0be..6345df1 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -5078,9 +5078,9 @@
 				spec->gpio_dir, spec->gpio_data);
 	} else {
 		notmtd_lvl = spec->gpio_led_polarity ?
-				AC_PINCTL_VREF_HIZ : AC_PINCTL_VREF_GRD;
+				AC_PINCTL_VREF_50 : AC_PINCTL_VREF_GRD;
 		muted_lvl = spec->gpio_led_polarity ?
-				AC_PINCTL_VREF_GRD : AC_PINCTL_VREF_HIZ;
+				AC_PINCTL_VREF_GRD : AC_PINCTL_VREF_50;
 		spec->vref_led = muted ? muted_lvl : notmtd_lvl;
 		stac_vrefout_set(codec,	spec->vref_mute_led_nid,
 				 spec->vref_led);
diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index 284e311..dff9a00 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -666,6 +666,9 @@
 	/* init input-src */
 	for (i = 0; i < spec->num_adc_nids; i++) {
 		int adc_idx = spec->inputs[spec->cur_mux[i]].adc_idx;
+		/* secondary ADCs must have the unique MUX */
+		if (i > 0 && !spec->mux_nids[i])
+			break;
 		if (spec->mux_nids[adc_idx]) {
 			int mux_idx = spec->inputs[spec->cur_mux[i]].mux_idx;
 			snd_hda_codec_write(codec, spec->mux_nids[adc_idx], 0,
diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
index 9f3b01b..e0a4263 100644
--- a/sound/pci/intel8x0.c
+++ b/sound/pci/intel8x0.c
@@ -2102,6 +2102,12 @@
 	},
 	{
 		.subvendor = 0x161f,
+		.subdevice = 0x202f,
+		.name = "Gateway M520",
+		.type = AC97_TUNE_INV_EAPD
+	},
+	{
+		.subvendor = 0x161f,
 		.subdevice = 0x203a,
 		.name = "Gateway 4525GZ",		/* AD1981B */
 		.type = AC97_TUNE_INV_EAPD
diff --git a/sound/soc/sh/fsi.c b/sound/soc/sh/fsi.c
index db6c89a..ea4a82d0 100644
--- a/sound/soc/sh/fsi.c
+++ b/sound/soc/sh/fsi.c
@@ -1152,12 +1152,8 @@
 {
 	struct fsi_priv *fsi = fsi_get_priv(substream);
 	struct fsi_stream *io = fsi_get_stream(fsi, fsi_is_play(substream));
-	int samples_pos = io->buff_sample_pos - 1;
 
-	if (samples_pos < 0)
-		samples_pos = 0;
-
-	return fsi_sample2frame(fsi, samples_pos);
+	return fsi_sample2frame(fsi, io->buff_sample_pos);
 }
 
 static struct snd_pcm_ops fsi_pcm_ops = {