kernel-magellan/patches-3.14/0103-3.14.4-all-fixes.patch

diff --git a/Makefile b/Makefile
index eed07f3f9308..d7c07fd8c944 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 14
-SUBLEVEL = 3
+SUBLEVEL = 4
 EXTRAVERSION =
 NAME = Shuffling Zombie Juror
 
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 47d09d07f093..6e8f83a32522 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -614,11 +614,13 @@ resume_user_mode_begin:
 
 resume_kernel_mode:
 
-#ifdef CONFIG_PREEMPT
-
-	; This is a must for preempt_schedule_irq()
+	; Disable Interrupts from this point on
+	; CONFIG_PREEMPT: This is a must for preempt_schedule_irq()
+	; !CONFIG_PREEMPT: To ensure restore_regs is intr safe
 	IRQ_DISABLE	r9
 
+#ifdef CONFIG_PREEMPT
+
 	; Can't preempt if preemption disabled
 	GET_CURR_THR_INFO_FROM_SP   r10
 	ld  r8, [r10, THREAD_INFO_PREEMPT_COUNT]
diff --git a/arch/arc/plat-arcfpga/Kconfig b/arch/arc/plat-arcfpga/Kconfig
index 295cefeb25d3..33058aa40e77 100644
--- a/arch/arc/plat-arcfpga/Kconfig
+++ b/arch/arc/plat-arcfpga/Kconfig
@@ -33,7 +33,6 @@ config ISS_SMP_EXTN
 	bool "ARC SMP Extensions (ISS Models only)"
 	default n
 	depends on SMP
-	select ARC_HAS_COH_RTSC
 	help
 	  SMP Extensions to ARC700, in a "simulation only" Model, supported in
 	  ARC ISS (Instruction Set Simulator).
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 7789857d1470..575d7904305b 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -42,6 +42,8 @@ static unsigned long hyp_idmap_start;
 static unsigned long hyp_idmap_end;
 static phys_addr_t hyp_idmap_vector;
 
+#define pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
+
 #define kvm_pmd_huge(_x)	(pmd_huge(_x) || pmd_trans_huge(_x))
 
 static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
@@ -199,14 +201,14 @@ void free_boot_hyp_pgd(void)
 	if (boot_hyp_pgd) {
 		unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
 		unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
-		kfree(boot_hyp_pgd);
+		free_pages((unsigned long)boot_hyp_pgd, pgd_order);
 		boot_hyp_pgd = NULL;
 	}
 
 	if (hyp_pgd)
 		unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
 
-	kfree(init_bounce_page);
+	free_page((unsigned long)init_bounce_page);
 	init_bounce_page = NULL;
 
 	mutex_unlock(&kvm_hyp_pgd_mutex);
@@ -236,7 +238,7 @@ void free_hyp_pgds(void)
 		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
 			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
 
-		kfree(hyp_pgd);
+		free_pages((unsigned long)hyp_pgd, pgd_order);
 		hyp_pgd = NULL;
 	}
 
@@ -930,7 +932,7 @@ int kvm_mmu_init(void)
 		size_t len = __hyp_idmap_text_end - __hyp_idmap_text_start;
 		phys_addr_t phys_base;
 
-		init_bounce_page = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		init_bounce_page = (void *)__get_free_page(GFP_KERNEL);
 		if (!init_bounce_page) {
 			kvm_err("Couldn't allocate HYP init bounce page\n");
 			err = -ENOMEM;
@@ -956,8 +958,9 @@ int kvm_mmu_init(void)
 			 (unsigned long)phys_base);
 	}
 
-	hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
-	boot_hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
+	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+
 	if (!hyp_pgd || !boot_hyp_pgd) {
 		kvm_err("Hyp mode PGD not allocated\n");
 		err = -ENOMEM;
diff --git a/arch/mips/kvm/kvm_mips_emul.c b/arch/mips/kvm/kvm_mips_emul.c
index 4b6274b47f33..e75ef8219caf 100644
--- a/arch/mips/kvm/kvm_mips_emul.c
+++ b/arch/mips/kvm/kvm_mips_emul.c
@@ -1571,17 +1571,17 @@ kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
 			arch->gprs[rt] = kvm_read_c0_guest_userlocal(cop0);
 #else
 			/* UserLocal not implemented */
-			er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu);
+			er = EMULATE_FAIL;
 #endif
 			break;
 
 		default:
-			printk("RDHWR not supported\n");
+			kvm_debug("RDHWR %#x not supported @ %p\n", rd, opc);
 			er = EMULATE_FAIL;
 			break;
 		}
 	} else {
-		printk("Emulate RI not supported @ %p: %#x\n", opc, inst);
+		kvm_debug("Emulate RI not supported @ %p: %#x\n", opc, inst);
 		er = EMULATE_FAIL;
 	}
 
@@ -1590,6 +1590,7 @@ kvm_mips_handle_ri(unsigned long cause, uint32_t *opc,
 	 */
 	if (er == EMULATE_FAIL) {
 		vcpu->arch.pc = curr_pc;
+		er = kvm_mips_emulate_ri_exc(cause, opc, run, vcpu);
 	}
 	return er;
 }
diff --git a/arch/mips/power/hibernate.S b/arch/mips/power/hibernate.S
index 7e0277a1048f..32a7c828f073 100644
--- a/arch/mips/power/hibernate.S
+++ b/arch/mips/power/hibernate.S
@@ -43,6 +43,7 @@ LEAF(swsusp_arch_resume)
 	bne t1, t3, 1b
 	PTR_L t0, PBE_NEXT(t0)
 	bnez t0, 0b
+	jal local_flush_tlb_all /* Avoid TLB mismatch after kernel resume */
 	PTR_LA t0, saved_regs
 	PTR_L ra, PT_R31(t0)
 	PTR_L sp, PT_R29(t0)
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index a613d2c82fd9..b142b8e0ed9e 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -8,7 +8,11 @@
 #include <linux/sched.h>
 
 #define COMPAT_USER_HZ		100
+#ifdef __BIG_ENDIAN__
 #define COMPAT_UTS_MACHINE	"ppc\0\0"
+#else
+#define COMPAT_UTS_MACHINE	"ppcle\0\0"
+#endif
 
 typedef u32		compat_size_t;
 typedef s32		compat_ssize_t;
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 90c06ec6eff5..ce17815b8b55 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -213,6 +213,7 @@
 #define SPRN_ACOP	0x1F	/* Available Coprocessor Register */
 #define SPRN_TFIAR	0x81	/* Transaction Failure Inst Addr   */
 #define SPRN_TEXASR	0x82	/* Transaction EXception & Summary */
+#define   TEXASR_FS	__MASK(63-36)	/* Transaction Failure Summary */
 #define SPRN_TEXASRU	0x83	/* ''	   ''	   ''	 Upper 32  */
 #define SPRN_TFHAR	0x80	/* Transaction Failure Handler Addr */
 #define SPRN_CTRLF	0x088
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index af064d28b365..31d021506d21 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -610,6 +610,31 @@ out_and_saveregs:
 	tm_save_sprs(thr);
 }
 
+extern void __tm_recheckpoint(struct thread_struct *thread,
+			      unsigned long orig_msr);
+
+void tm_recheckpoint(struct thread_struct *thread,
+		     unsigned long orig_msr)
+{
+	unsigned long flags;
+
+	/* We really can't be interrupted here as the TEXASR registers can't
+	 * change and later in the trecheckpoint code, we have a userspace R1.
+	 * So let's hard disable over this region.
+	 */
+	local_irq_save(flags);
+	hard_irq_disable();
+
+	/* The TM SPRs are restored here, so that TEXASR.FS can be set
+	 * before the trecheckpoint and no explosion occurs.
+	 */
+	tm_restore_sprs(thread);
+
+	__tm_recheckpoint(thread, orig_msr);
+
+	local_irq_restore(flags);
+}
+
 static inline void tm_recheckpoint_new_task(struct task_struct *new)
 {
 	unsigned long msr;
@@ -628,13 +653,10 @@ static inline void tm_recheckpoint_new_task(struct task_struct *new)
 	if (!new->thread.regs)
 		return;
 
-	/* The TM SPRs are restored here, so that TEXASR.FS can be set
-	 * before the trecheckpoint and no explosion occurs.
-	 */
-	tm_restore_sprs(&new->thread);
-
-	if (!MSR_TM_ACTIVE(new->thread.regs->msr))
+	if (!MSR_TM_ACTIVE(new->thread.regs->msr)){
+		tm_restore_sprs(&new->thread);
 		return;
+	}
 	msr = new->thread.tm_orig_msr;
 	/* Recheckpoint to restore original checkpointed register state. */
 	TM_DEBUG("*** tm_recheckpoint of pid %d "
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index a67e00aa3caa..4e47db686b5d 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -881,6 +881,8 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 	 * transactional versions should be loaded.
 	 */
 	tm_enable();
+	/* Make sure the transaction is marked as failed */
+	current->thread.tm_texasr |= TEXASR_FS;
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
 	/* Get the top half of the MSR */
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 8d253c29649b..d501dc4dc3e6 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -527,6 +527,8 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 	}
 #endif
 	tm_enable();
+	/* Make sure the transaction is marked as failed */
+	current->thread.tm_texasr |= TEXASR_FS;
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
 
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index ef47bcbd4352..03567c05950a 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -307,7 +307,7 @@ dont_backup_fp:
 	 *	Call with IRQs off, stacks get all out of sync for
 	 *	some periods in here!
 	 */
-_GLOBAL(tm_recheckpoint)
+_GLOBAL(__tm_recheckpoint)
 	mfcr	r5
 	mflr	r0
 	stw	r5, 8(r1)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 17fc9496b6ac..7a25d9218a05 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -86,7 +86,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 
 	/* CPU points to the first thread of the core */
 	if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) {
-#ifdef CONFIG_KVM_XICS
+#ifdef CONFIG_PPC_ICP_NATIVE
 		int real_cpu = cpu + vcpu->arch.ptid;
 		if (paca[real_cpu].kvm_hstate.xics_phys)
 			xics_wake_cpu(real_cpu);
@@ -1360,9 +1360,7 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 	smp_wmb();
 #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
 	if (cpu != smp_processor_id()) {
-#ifdef CONFIG_KVM_XICS
 		xics_wake_cpu(cpu);
-#endif
 		if (vcpu->arch.ptid)
 			++vc->n_woken;
 	}
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 0ea99e3d4815..2d6fe89ff89d 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -88,13 +88,14 @@ void set_default_offline_state(int cpu)
 
 static void rtas_stop_self(void)
 {
-	struct rtas_args args = {
-		.token = cpu_to_be32(rtas_stop_self_token),
+	static struct rtas_args args = {
 		.nargs = 0,
 		.nret = 1,
 		.rets = &args.args[0],
 	};
 
+	args.token = cpu_to_be32(rtas_stop_self_token);
+
 	local_irq_disable();
 
 	BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 708d60e40066..a778ee27518a 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -276,7 +276,6 @@ static void bpf_jit_noleaks(struct bpf_jit *jit, struct sock_filter *filter)
 	case BPF_S_LD_W_IND:
 	case BPF_S_LD_H_IND:
 	case BPF_S_LD_B_IND:
-	case BPF_S_LDX_B_MSH:
 	case BPF_S_LD_IMM:
 	case BPF_S_LD_MEM:
 	case BPF_S_MISC_TXA:
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index f8842c444560..0dd99ea1caf1 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -79,6 +79,7 @@ else
         UTS_MACHINE := x86_64
         CHECKFLAGS += -D__x86_64__ -m64
 
+        biarch := -m64
         KBUILD_AFLAGS += -m64
         KBUILD_CFLAGS += -m64
 
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index c29c2c3ec0ad..b06f5f55ada9 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -170,6 +170,9 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	acpi_status status;
 	int ret;
 
+	if (pr->apic_id == -1)
+		return -ENODEV;
+
 	status = acpi_evaluate_integer(pr->handle, "_STA", NULL, &sta);
 	if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_PRESENT))
 		return -ENODEV;
@@ -260,10 +263,8 @@ static int acpi_processor_get_info(struct acpi_device *device)
 	}
 
 	apic_id = acpi_get_apicid(pr->handle, device_declaration, pr->acpi_id);
-	if (apic_id < 0) {
+	if (apic_id < 0)
 		acpi_handle_debug(pr->handle, "failed to get CPU APIC ID.\n");
-		return -ENODEV;
-	}
 	pr->apic_id = apic_id;
 
 	cpu_index = acpi_map_cpuid(pr->apic_id, pr->acpi_id);
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index c81d809c111b..8f18342540d8 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1163,7 +1163,7 @@ static inline void ahci_gtf_filter_workaround(struct ata_host *host)
 #endif
 
 static int ahci_init_interrupts(struct pci_dev *pdev, unsigned int n_ports,
-			 struct ahci_host_priv *hpriv)
+				struct ahci_host_priv *hpriv)
 {
 	int rc, nvec;
 
@@ -1189,6 +1189,13 @@ static int ahci_init_interrupts(struct pci_dev *pdev, unsigned int n_ports,
 	else if (rc > 0)
 		goto single_msi;
 
+	/* fallback to single MSI mode if the controller enforced MRSM mode */
+	if (readl(hpriv->mmio + HOST_CTL) & HOST_MRSM) {
+		pci_disable_msi(pdev);
+		printk(KERN_INFO "ahci: MRSM is on, fallback to single MSI\n");
+		goto single_msi;
+	}
+
 	return nvec;
 
 single_msi:
@@ -1233,18 +1240,18 @@ int ahci_host_activate(struct ata_host *host, int irq, unsigned int n_msis)
 		return rc;
 
 	for (i = 0; i < host->n_ports; i++) {
-		const char* desc;
 		struct ahci_port_priv *pp = host->ports[i]->private_data;
 
-		/* pp is NULL for dummy ports */
-		if (pp)
-			desc = pp->irq_desc;
-		else
-			desc = dev_driver_string(host->dev);
+		/* Do not receive interrupts sent by dummy ports */
+		if (!pp) {
+			disable_irq(irq + i);
+			continue;
+		}
 
-		rc = devm_request_threaded_irq(host->dev,
-			irq + i, ahci_hw_interrupt, ahci_thread_fn, IRQF_SHARED,
-			desc, host->ports[i]);
+		rc = devm_request_threaded_irq(host->dev, irq + i,
+					       ahci_hw_interrupt,
+					       ahci_thread_fn, IRQF_SHARED,
+					       pp->irq_desc, host->ports[i]);
 		if (rc)
 			goto out_free_irqs;
 	}
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index 2289efdf8203..ad36faf31dbd 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -91,6 +91,7 @@ enum {
 	/* HOST_CTL bits */
 	HOST_RESET		= (1 << 0),  /* reset controller; self-clear */
 	HOST_IRQ_EN		= (1 << 1),  /* global IRQ enable */
+	HOST_MRSM		= (1 << 2),  /* MSI Revert to Single Message */
 	HOST_AHCI_EN		= (1 << 31), /* AHCI enabled */
 
 	/* HOST_CAP bits */
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 8cb2522d592a..0a79c540169c 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4224,8 +4224,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "PIONEER DVD-RW  DVR-216D",	NULL,	ATA_HORKAGE_NOSETXFER },
 
 	/* devices that don't properly handle queued TRIM commands */
-	{ "Micron_M500*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
-	{ "Crucial_CT???M500SSD*",	NULL,	ATA_HORKAGE_NO_NCQ_TRIM, },
+	{ "Micron_M500*",		"MU0[1-4]*",	ATA_HORKAGE_NO_NCQ_TRIM, },
+	{ "Crucial_CT???M500SSD*",	"MU0[1-4]*",	ATA_HORKAGE_NO_NCQ_TRIM, },
+	{ "Micron_M550*",		NULL,		ATA_HORKAGE_NO_NCQ_TRIM, },
+	{ "Crucial_CT???M550SSD*",	NULL,		ATA_HORKAGE_NO_NCQ_TRIM, },
 
 	/*
 	 * Some WD SATA-I drives spin up and down erratically when the link
@@ -4792,21 +4794,26 @@ 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 i;
+	unsigned int i, tag;
 
 	/* no command while frozen */
 	if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
 		return NULL;
 
-	/* the last tag is reserved for internal command. */
-	for (i = 0; i < ATA_MAX_QUEUE - 1; i++)
-		if (!test_and_set_bit(i, &ap->qc_allocated)) {
-			qc = __ata_qc_from_tag(ap, i);
+	for (i = 0; i < ATA_MAX_QUEUE; i++) {
+		tag = (i + ap->last_tag + 1) % ATA_MAX_QUEUE;
+
+		/* the last tag is reserved for internal command. */
+		if (tag == ATA_TAG_INTERNAL)
+			continue;
+
+		if (!test_and_set_bit(tag, &ap->qc_allocated)) {
+			qc = __ata_qc_from_tag(ap, tag);
+			qc->tag = tag;
+			ap->last_tag = tag;
 			break;
 		}
-
-	if (qc)
-		qc->tag = i;
+	}
 
 	return qc;
 }
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 2023043ce7c0..dab515cd77bf 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3053,7 +3053,10 @@ static int raw_cmd_copyout(int cmd, void __user *param,
 	int ret;
 
 	while (ptr) {
-		ret = copy_to_user(param, ptr, sizeof(*ptr));
+		struct floppy_raw_cmd cmd = *ptr;
+		cmd.next = NULL;
+		cmd.kernel_data = NULL;
+		ret = copy_to_user(param, &cmd, sizeof(cmd));
 		if (ret)
 			return -EFAULT;
 		param += sizeof(struct floppy_raw_cmd);
@@ -3107,10 +3110,11 @@ loop:
 		return -ENOMEM;
 	*rcmd = ptr;
 	ret = copy_from_user(ptr, param, sizeof(*ptr));
-	if (ret)
-		return -EFAULT;
 	ptr->next = NULL;
 	ptr->buffer_length = 0;
+	ptr->kernel_data = NULL;
+	if (ret)
+		return -EFAULT;
 	param += sizeof(struct floppy_raw_cmd);
 	if (ptr->cmd_count > 33)
 			/* the command may now also take up the space
@@ -3126,7 +3130,6 @@ loop:
 	for (i = 0; i < 16; i++)
 		ptr->reply[i] = 0;
 	ptr->resultcode = 0;
-	ptr->kernel_data = NULL;
 
 	if (ptr->flags & (FD_RAW_READ | FD_RAW_WRITE)) {
 		if (ptr->length <= 0)
diff --git a/drivers/cpufreq/at32ap-cpufreq.c b/drivers/cpufreq/at32ap-cpufreq.c
index a1c79f549edb..7b612c8bb09e 100644
--- a/drivers/cpufreq/at32ap-cpufreq.c
+++ b/drivers/cpufreq/at32ap-cpufreq.c
@@ -52,7 +52,7 @@ static int at32_set_target(struct cpufreq_policy *policy, unsigned int index)
 static int at32_cpufreq_driver_init(struct cpufreq_policy *policy)
 {
 	unsigned int frequency, rate, min_freq;
-	static struct clk *cpuclk;
+	struct clk *cpuclk;
 	int retval, steps, i;
 
 	if (policy->cpu != 0)
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index b6581abc9207..8dead6fb28e8 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -69,7 +69,7 @@ static int loongson2_cpufreq_target(struct cpufreq_policy *policy,
 
 static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	static struct clk *cpuclk;
+	struct clk *cpuclk;
 	int i;
 	unsigned long rate;
 	int ret;
diff --git a/drivers/cpufreq/unicore2-cpufreq.c b/drivers/cpufreq/unicore2-cpufreq.c
index 36cc330b8747..99d280d6f370 100644
--- a/drivers/cpufreq/unicore2-cpufreq.c
+++ b/drivers/cpufreq/unicore2-cpufreq.c
@@ -45,7 +45,7 @@ static int ucv2_target(struct cpufreq_policy *policy,
 	freqs.new = target_freq;
 
 	cpufreq_notify_transition(policy, &freqs, CPUFREQ_PRECHANGE);
-	ret = clk_set_rate(policy->mclk, target_freq * 1000);
+	ret = clk_set_rate(policy->clk, target_freq * 1000);
 	cpufreq_notify_post_transition(policy, &freqs, ret);
 
 	return ret;
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index cd8da451d199..bf5ad0f5a77a 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -182,11 +182,13 @@ static void edma_execute(struct edma_chan *echan)
 				  echan->ecc->dummy_slot);
 	}
 
-	edma_resume(echan->ch_num);
-
 	if (edesc->processed <= MAX_NR_SG) {
 		dev_dbg(dev, "first transfer starting %d\n", echan->ch_num);
 		edma_start(echan->ch_num);
+	} else {
+		dev_dbg(dev, "chan: %d: completed %d elements, resuming\n",
+			echan->ch_num, edesc->processed);
+		edma_resume(echan->ch_num);
 	}
 
 	/*
diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c
index 532bcb336eff..8ffdd7d2bade 100644
--- a/drivers/gpio/gpio-mxs.c
+++ b/drivers/gpio/gpio-mxs.c
@@ -214,7 +214,8 @@ static void __init mxs_gpio_init_gc(struct mxs_gpio_port *port, int irq_base)
 	ct->regs.ack = PINCTRL_IRQSTAT(port) + MXS_CLR;
 	ct->regs.mask = PINCTRL_IRQEN(port);
 
-	irq_setup_generic_chip(gc, IRQ_MSK(32), 0, IRQ_NOREQUEST, 0);
+	irq_setup_generic_chip(gc, IRQ_MSK(32), IRQ_GC_INIT_NESTED_LOCK,
+			       IRQ_NOREQUEST, 0);
 }
 
 static int mxs_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
diff --git a/drivers/gpu/drm/bochs/bochs.h b/drivers/gpu/drm/bochs/bochs.h
index 741965c001a6..460820551b09 100644
--- a/drivers/gpu/drm/bochs/bochs.h
+++ b/drivers/gpu/drm/bochs/bochs.h
@@ -1,5 +1,6 @@
 #include <linux/io.h>
 #include <linux/fb.h>
+#include <linux/console.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_crtc.h>
diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c
index 395bba261c9a..9c13df29fd20 100644
--- a/drivers/gpu/drm/bochs/bochs_drv.c
+++ b/drivers/gpu/drm/bochs/bochs_drv.c
@@ -95,6 +95,49 @@ static struct drm_driver bochs_driver = {
 };
 
 /* ---------------------------------------------------------------------- */
+/* pm interface                                                           */
+
+static int bochs_pm_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct bochs_device *bochs = drm_dev->dev_private;
+
+	drm_kms_helper_poll_disable(drm_dev);
+
+	if (bochs->fb.initialized) {
+		console_lock();
+		fb_set_suspend(bochs->fb.helper.fbdev, 1);
+		console_unlock();
+	}
+
+	return 0;
+}
+
+static int bochs_pm_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct bochs_device *bochs = drm_dev->dev_private;
+
+	drm_helper_resume_force_mode(drm_dev);
+
+	if (bochs->fb.initialized) {
+		console_lock();
+		fb_set_suspend(bochs->fb.helper.fbdev, 0);
+		console_unlock();
+	}
+
+	drm_kms_helper_poll_enable(drm_dev);
+	return 0;
+}
+
+static const struct dev_pm_ops bochs_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(bochs_pm_suspend,
+				bochs_pm_resume)
+};
+
+/* ---------------------------------------------------------------------- */
 /* pci interface                                                          */
 
 static int bochs_kick_out_firmware_fb(struct pci_dev *pdev)
@@ -155,6 +198,7 @@ static struct pci_driver bochs_pci_driver = {
 	.id_table =	bochs_pci_tbl,
 	.probe =	bochs_pci_probe,
 	.remove =	bochs_pci_remove,
+	.driver.pm =    &bochs_pm_ops,
 };
 
 /* ---------------------------------------------------------------------- */
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index 953fc8aea69c..08ce520f61a5 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/console.h>
 #include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
 
 #include "cirrus_drv.h"
 
@@ -75,6 +76,41 @@ static void cirrus_pci_remove(struct pci_dev *pdev)
 	drm_put_dev(dev);
 }
 
+static int cirrus_pm_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct cirrus_device *cdev = drm_dev->dev_private;
+
+	drm_kms_helper_poll_disable(drm_dev);
+
+	if (cdev->mode_info.gfbdev) {
+		console_lock();
+		fb_set_suspend(cdev->mode_info.gfbdev->helper.fbdev, 1);
+		console_unlock();
+	}
+
+	return 0;
+}
+
+static int cirrus_pm_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct drm_device *drm_dev = pci_get_drvdata(pdev);
+	struct cirrus_device *cdev = drm_dev->dev_private;
+
+	drm_helper_resume_force_mode(drm_dev);
+
+	if (cdev->mode_info.gfbdev) {
+		console_lock();
+		fb_set_suspend(cdev->mode_info.gfbdev->helper.fbdev, 0);
+		console_unlock();
+	}
+
+	drm_kms_helper_poll_enable(drm_dev);
+	return 0;
+}
+
 static const struct file_operations cirrus_driver_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
@@ -103,11 +139,17 @@ static struct drm_driver driver = {
 	.dumb_destroy = drm_gem_dumb_destroy,
 };
 
+static const struct dev_pm_ops cirrus_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(cirrus_pm_suspend,
+				cirrus_pm_resume)
+};
+
 static struct pci_driver cirrus_pci_driver = {
 	.name = DRIVER_NAME,
 	.id_table = pciidlist,
 	.probe = cirrus_pci_probe,
 	.remove = cirrus_pci_remove,
+	.driver.pm = &cirrus_pm_ops,
 };
 
 static int __init cirrus_init(void)
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index 530f78f84dee..e9c89df482b5 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -308,6 +308,9 @@ static int cirrus_crtc_mode_set(struct drm_crtc *crtc,
 
 	WREG_HDR(hdr);
 	cirrus_crtc_do_set_base(crtc, old_fb, x, y, 0);
+
+	/* Unblank (needed on S3 resume, vgabios doesn't do it then) */
+	outb(0x20, 0x3c0);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index e2e39e65f109..a60a755f9977 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -765,6 +765,14 @@ static const struct dmi_system_id intel_no_crt[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "ZGB"),
 		},
 	},
+	{
+		.callback = intel_no_crt_dmi_callback,
+		.ident = "DELL XPS 8700",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "XPS 8700"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index d8d49d10f9bb..3c511c4adaca 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -1515,6 +1515,22 @@ static const struct dmi_system_id min_max_dmi_table[] __initconst = {
 		.driver_data = (int []){1232, 5710, 1156, 4696},
 	},
 	{
+		/* Lenovo ThinkPad Edge E431 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Edge E431"),
+		},
+		.driver_data = (int []){1024, 5022, 2508, 4832},
+	},
+	{
+		/* Lenovo ThinkPad T431s */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T431"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
+	{
 		/* Lenovo ThinkPad T440s */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
@@ -1523,6 +1539,14 @@ static const struct dmi_system_id min_max_dmi_table[] __initconst = {
 		.driver_data = (int []){1024, 5112, 2024, 4832},
 	},
 	{
+		/* Lenovo ThinkPad L440 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L440"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
+	{
 		/* Lenovo ThinkPad T540p */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
@@ -1530,6 +1554,32 @@ static const struct dmi_system_id min_max_dmi_table[] __initconst = {
 		},
 		.driver_data = (int []){1024, 5056, 2058, 4832},
 	},
+	{
+		/* Lenovo ThinkPad L540 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L540"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
+	{
+		/* Lenovo Yoga S1 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
+					"ThinkPad S1 Yoga"),
+		},
+		.driver_data = (int []){1232, 5710, 1156, 4696},
+	},
+	{
+		/* Lenovo ThinkPad X1 Carbon Haswell (3rd generation) */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION,
+					"ThinkPad X1 Carbon 2nd"),
+		},
+		.driver_data = (int []){1024, 5112, 2024, 4832},
+	},
 #endif
 	{ }
 };
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
index 9ef0752e8a08..5320332390b7 100644
--- a/drivers/md/dm-cache-metadata.c
+++ b/drivers/md/dm-cache-metadata.c
@@ -120,6 +120,12 @@ struct dm_cache_metadata {
 	unsigned policy_version[CACHE_POLICY_VERSION_SIZE];
 	size_t policy_hint_size;
 	struct dm_cache_statistics stats;
+
+	/*
+	 * Reading the space map root can fail, so we read it into this
+	 * buffer before the superblock is locked and updated.
+	 */
+	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
 };
 
 /*-------------------------------------------------------------------
@@ -260,11 +266,31 @@ static void __setup_mapping_info(struct dm_cache_metadata *cmd)
 	}
 }
 
+static int __save_sm_root(struct dm_cache_metadata *cmd)
+{
+	int r;
+	size_t metadata_len;
+
+	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
+	if (r < 0)
+		return r;
+
+	return dm_sm_copy_root(cmd->metadata_sm, &cmd->metadata_space_map_root,
+			       metadata_len);
+}
+
+static void __copy_sm_root(struct dm_cache_metadata *cmd,
+			   struct cache_disk_superblock *disk_super)
+{
+	memcpy(&disk_super->metadata_space_map_root,
+	       &cmd->metadata_space_map_root,
+	       sizeof(cmd->metadata_space_map_root));
+}
+
 static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 {
 	int r;
 	struct dm_block *sblock;
-	size_t metadata_len;
 	struct cache_disk_superblock *disk_super;
 	sector_t bdev_size = i_size_read(cmd->bdev->bd_inode) >> SECTOR_SHIFT;
 
@@ -272,12 +298,16 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 	if (bdev_size > DM_CACHE_METADATA_MAX_SECTORS)
 		bdev_size = DM_CACHE_METADATA_MAX_SECTORS;
 
-	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
+	r = dm_tm_pre_commit(cmd->tm);
 	if (r < 0)
 		return r;
 
-	r = dm_tm_pre_commit(cmd->tm);
-	if (r < 0)
+	/*
+	 * dm_sm_copy_root() can fail.  So we need to do it before we start
+	 * updating the superblock.
+	 */
+	r = __save_sm_root(cmd);
+	if (r)
 		return r;
 
 	r = superblock_lock_zero(cmd, &sblock);
@@ -293,10 +323,7 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 	memset(disk_super->policy_version, 0, sizeof(disk_super->policy_version));
 	disk_super->policy_hint_size = 0;
 
-	r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root,
-			    metadata_len);
-	if (r < 0)
-		goto bad_locked;
+	__copy_sm_root(cmd, disk_super);
 
 	disk_super->mapping_root = cpu_to_le64(cmd->root);
 	disk_super->hint_root = cpu_to_le64(cmd->hint_root);
@@ -313,10 +340,6 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd)
 	disk_super->write_misses = cpu_to_le32(0);
 
 	return dm_tm_commit(cmd->tm, sblock);
-
-bad_locked:
-	dm_bm_unlock(sblock);
-	return r;
 }
 
 static int __format_metadata(struct dm_cache_metadata *cmd)
@@ -530,8 +553,9 @@ static int __begin_transaction_flags(struct dm_cache_metadata *cmd,
 	disk_super = dm_block_data(sblock);
 	update_flags(disk_super, mutator);
 	read_superblock_fields(cmd, disk_super);
+	dm_bm_unlock(sblock);
 
-	return dm_bm_flush_and_unlock(cmd->bm, sblock);
+	return dm_bm_flush(cmd->bm);
 }
 
 static int __begin_transaction(struct dm_cache_metadata *cmd)
@@ -559,7 +583,6 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 				flags_mutator mutator)
 {
 	int r;
-	size_t metadata_len;
 	struct cache_disk_superblock *disk_super;
 	struct dm_block *sblock;
 
@@ -577,8 +600,8 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 	if (r < 0)
 		return r;
 
-	r = dm_sm_root_size(cmd->metadata_sm, &metadata_len);
-	if (r < 0)
+	r = __save_sm_root(cmd);
+	if (r)
 		return r;
 
 	r = superblock_lock(cmd, &sblock);
@@ -605,13 +628,7 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 	disk_super->read_misses = cpu_to_le32(cmd->stats.read_misses);
 	disk_super->write_hits = cpu_to_le32(cmd->stats.write_hits);
 	disk_super->write_misses = cpu_to_le32(cmd->stats.write_misses);
-
-	r = dm_sm_copy_root(cmd->metadata_sm, &disk_super->metadata_space_map_root,
-			    metadata_len);
-	if (r < 0) {
-		dm_bm_unlock(sblock);
-		return r;
-	}
+	__copy_sm_root(cmd, disk_super);
 
 	return dm_tm_commit(cmd->tm, sblock);
 }
@@ -1228,22 +1245,12 @@ static int begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *po
 	return 0;
 }
 
-int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
+static int save_hint(void *context, dm_cblock_t cblock, dm_oblock_t oblock, uint32_t hint)
 {
+	struct dm_cache_metadata *cmd = context;
+	__le32 value = cpu_to_le32(hint);
 	int r;
 
-	down_write(&cmd->root_lock);
-	r = begin_hints(cmd, policy);
-	up_write(&cmd->root_lock);
-
-	return r;
-}
-
-static int save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock,
-		     uint32_t hint)
-{
-	int r;
-	__le32 value = cpu_to_le32(hint);
 	__dm_bless_for_disk(&value);
 
 	r = dm_array_set_value(&cmd->hint_info, cmd->hint_root,
@@ -1253,16 +1260,25 @@ static int save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock,
 	return r;
 }
 
-int dm_cache_save_hint(struct dm_cache_metadata *cmd, dm_cblock_t cblock,
-		       uint32_t hint)
+static int write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
 {
 	int r;
 
-	if (!hints_array_initialized(cmd))
-		return 0;
+	r = begin_hints(cmd, policy);
+	if (r) {
+		DMERR("begin_hints failed");
+		return r;
+	}
+
+	return policy_walk_mappings(policy, save_hint, cmd);
+}
+
+int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *policy)
+{
+	int r;
 
 	down_write(&cmd->root_lock);
-	r = save_hint(cmd, cblock, hint);
+	r = write_hints(cmd, policy);
 	up_write(&cmd->root_lock);
 
 	return r;
diff --git a/drivers/md/dm-cache-metadata.h b/drivers/md/dm-cache-metadata.h
index cd906f14f98d..f0fb1dd26524 100644
--- a/drivers/md/dm-cache-metadata.h
+++ b/drivers/md/dm-cache-metadata.h
@@ -128,14 +128,7 @@ void dm_cache_dump(struct dm_cache_metadata *cmd);
  * rather than querying the policy for each cblock, we let it walk its data
  * structures and fill in the hints in whatever order it wishes.
  */
-
-int dm_cache_begin_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *p);
-
-/*
- * requests hints for every cblock and stores in the metadata device.
- */
-int dm_cache_save_hint(struct dm_cache_metadata *cmd,
-		       dm_cblock_t cblock, uint32_t hint);
+int dm_cache_write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *p);
 
 /*
  * Query method.  Are all the blocks in the cache clean?
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 074b9c8e4cf0..b82b58f0bb85 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -239,7 +239,7 @@ struct cache {
 	 */
 	dm_dblock_t discard_nr_blocks;
 	unsigned long *discard_bitset;
-	uint32_t discard_block_size; /* a power of 2 times sectors per block */
+	uint32_t discard_block_size;
 
 	/*
 	 * Rather than reconstructing the table line for the status we just
@@ -2171,35 +2171,6 @@ static int create_cache_policy(struct cache *cache, struct cache_args *ca,
 	return 0;
 }
 
-/*
- * We want the discard block size to be a power of two, at least the size
- * of the cache block size, and have no more than 2^14 discard blocks
- * across the origin.
- */
-#define MAX_DISCARD_BLOCKS (1 << 14)
-
-static bool too_many_discard_blocks(sector_t discard_block_size,
-				    sector_t origin_size)
-{
-	(void) sector_div(origin_size, discard_block_size);
-
-	return origin_size > MAX_DISCARD_BLOCKS;
-}
-
-static sector_t calculate_discard_block_size(sector_t cache_block_size,
-					     sector_t origin_size)
-{
-	sector_t discard_block_size;
-
-	discard_block_size = roundup_pow_of_two(cache_block_size);
-
-	if (origin_size)
-		while (too_many_discard_blocks(discard_block_size, origin_size))
-			discard_block_size *= 2;
-
-	return discard_block_size;
-}
-
 #define DEFAULT_MIGRATION_THRESHOLD 2048
 
 static int cache_create(struct cache_args *ca, struct cache **result)
@@ -2321,9 +2292,7 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	}
 	clear_bitset(cache->dirty_bitset, from_cblock(cache->cache_size));
 
-	cache->discard_block_size =
-		calculate_discard_block_size(cache->sectors_per_block,
-					     cache->origin_sectors);
+	cache->discard_block_size = cache->sectors_per_block;
 	cache->discard_nr_blocks = oblock_to_dblock(cache, cache->origin_blocks);
 	cache->discard_bitset = alloc_bitset(from_dblock(cache->discard_nr_blocks));
 	if (!cache->discard_bitset) {
@@ -2631,30 +2600,6 @@ static int write_discard_bitset(struct cache *cache)
 	return 0;
 }
 
-static int save_hint(void *context, dm_cblock_t cblock, dm_oblock_t oblock,
-		     uint32_t hint)
-{
-	struct cache *cache = context;
-	return dm_cache_save_hint(cache->cmd, cblock, hint);
-}
-
-static int write_hints(struct cache *cache)
-{
-	int r;
-
-	r = dm_cache_begin_hints(cache->cmd, cache->policy);
-	if (r) {
-		DMERR("dm_cache_begin_hints failed");
-		return r;
-	}
-
-	r = policy_walk_mappings(cache->policy, save_hint, cache);
-	if (r)
-		DMERR("policy_walk_mappings failed");
-
-	return r;
-}
-
 /*
  * returns true on success
  */
@@ -2672,7 +2617,7 @@ static bool sync_metadata(struct cache *cache)
 
 	save_stats(cache);
 
-	r3 = write_hints(cache);
+	r3 = dm_cache_write_hints(cache->cmd, cache->policy);
 	if (r3)
 		DMERR("could not write hints");
 
@@ -3120,7 +3065,7 @@ static void set_discard_limits(struct cache *cache, struct queue_limits *limits)
 	/*
 	 * FIXME: these limits may be incompatible with the cache device
 	 */
-	limits->max_discard_sectors = cache->discard_block_size * 1024;
+	limits->max_discard_sectors = cache->discard_block_size;
 	limits->discard_granularity = cache->discard_block_size << SECTOR_SHIFT;
 }
 
@@ -3145,7 +3090,7 @@ static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static struct target_type cache_target = {
 	.name = "cache",
-	.version = {1, 3, 0},
+	.version = {1, 4, 0},
 	.module = THIS_MODULE,
 	.ctr = cache_ctr,
 	.dtr = cache_dtr,
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index fb9efc829182..b086a945edcb 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -192,6 +192,13 @@ struct dm_pool_metadata {
 	 * operation possible in this state is the closing of the device.
 	 */
 	bool fail_io:1;
+
+	/*
+	 * Reading the space map roots can fail, so we read it into these
+	 * buffers before the superblock is locked and updated.
+	 */
+	__u8 data_space_map_root[SPACE_MAP_ROOT_SIZE];
+	__u8 metadata_space_map_root[SPACE_MAP_ROOT_SIZE];
 };
 
 struct dm_thin_device {
@@ -431,26 +438,53 @@ static void __setup_btree_details(struct dm_pool_metadata *pmd)
 	pmd->details_info.value_type.equal = NULL;
 }
 
+static int save_sm_roots(struct dm_pool_metadata *pmd)
+{
+	int r;
+	size_t len;
+
+	r = dm_sm_root_size(pmd->metadata_sm, &len);
+	if (r < 0)
+		return r;
+
+	r = dm_sm_copy_root(pmd->metadata_sm, &pmd->metadata_space_map_root, len);
+	if (r < 0)
+		return r;
+
+	r = dm_sm_root_size(pmd->data_sm, &len);
+	if (r < 0)
+		return r;
+
+	return dm_sm_copy_root(pmd->data_sm, &pmd->data_space_map_root, len);
+}
+
+static void copy_sm_roots(struct dm_pool_metadata *pmd,
+			  struct thin_disk_superblock *disk)
+{
+	memcpy(&disk->metadata_space_map_root,
+	       &pmd->metadata_space_map_root,
+	       sizeof(pmd->metadata_space_map_root));
+
+	memcpy(&disk->data_space_map_root,
+	       &pmd->data_space_map_root,
+	       sizeof(pmd->data_space_map_root));
+}
+
 static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 {
 	int r;
 	struct dm_block *sblock;
-	size_t metadata_len, data_len;
 	struct thin_disk_superblock *disk_super;
 	sector_t bdev_size = i_size_read(pmd->bdev->bd_inode) >> SECTOR_SHIFT;
 
 	if (bdev_size > THIN_METADATA_MAX_SECTORS)
 		bdev_size = THIN_METADATA_MAX_SECTORS;
 
-	r = dm_sm_root_size(pmd->metadata_sm, &metadata_len);
-	if (r < 0)
-		return r;
-
-	r = dm_sm_root_size(pmd->data_sm, &data_len);
+	r = dm_sm_commit(pmd->data_sm);
 	if (r < 0)
 		return r;
 
-	r = dm_sm_commit(pmd->data_sm);
+	r = save_sm_roots(pmd);
 	if (r < 0)
 		return r;
 
@@ -471,15 +505,7 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 	disk_super->trans_id = 0;
 	disk_super->held_root = 0;
 
-	r = dm_sm_copy_root(pmd->metadata_sm, &disk_super->metadata_space_map_root,
-			    metadata_len);
-	if (r < 0)
-		goto bad_locked;
-
-	r = dm_sm_copy_root(pmd->data_sm, &disk_super->data_space_map_root,
-			    data_len);
-	if (r < 0)
-		goto bad_locked;
+	copy_sm_roots(pmd, disk_super);
 
 	disk_super->data_mapping_root = cpu_to_le64(pmd->root);
 	disk_super->device_details_root = cpu_to_le64(pmd->details_root);
@@ -488,10 +514,6 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd)
 	disk_super->data_block_size = cpu_to_le32(pmd->data_block_size);
 
 	return dm_tm_commit(pmd->tm, sblock);
-
-bad_locked:
-	dm_bm_unlock(sblock);
-	return r;
 }
 
 static int __format_metadata(struct dm_pool_metadata *pmd)
@@ -769,6 +791,10 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	if (r < 0)
 		return r;
 
+	r = save_sm_roots(pmd);
+	if (r < 0)
+		return r;
+
 	r = superblock_lock(pmd, &sblock);
 	if (r)
 		return r;
@@ -780,21 +806,9 @@ static int __commit_transaction(struct dm_pool_metadata *pmd)
 	disk_super->trans_id = cpu_to_le64(pmd->trans_id);
 	disk_super->flags = cpu_to_le32(pmd->flags);
 
-	r = dm_sm_copy_root(pmd->metadata_sm, &disk_super->metadata_space_map_root,
-			    metadata_len);
-	if (r < 0)
-		goto out_locked;
-
-	r = dm_sm_copy_root(pmd->data_sm, &disk_super->data_space_map_root,
-			    data_len);
-	if (r < 0)
-		goto out_locked;
+	copy_sm_roots(pmd, disk_super);
 
 	return dm_tm_commit(pmd->tm, sblock);
-
-out_locked:
-	dm_bm_unlock(sblock);
-	return r;
 }
 
 struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev,
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index be70d38745f7..60cc50685c14 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -1392,9 +1392,9 @@ static void process_deferred_bios(struct pool *pool)
 		 */
 		if (ensure_next_mapping(pool)) {
 			spin_lock_irqsave(&pool->lock, flags);
+			bio_list_add(&pool->deferred_bios, bio);
 			bio_list_merge(&pool->deferred_bios, &bios);
 			spin_unlock_irqrestore(&pool->lock, flags);
-
 			break;
 		}
 
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 455f79279a16..087411c95ffc 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -595,25 +595,14 @@ int dm_bm_unlock(struct dm_block *b)
 }
 EXPORT_SYMBOL_GPL(dm_bm_unlock);
 
-int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
-			   struct dm_block *superblock)
+int dm_bm_flush(struct dm_block_manager *bm)
 {
-	int r;
-
 	if (bm->read_only)
 		return -EPERM;
 
-	r = dm_bufio_write_dirty_buffers(bm->bufio);
-	if (unlikely(r)) {
-		dm_bm_unlock(superblock);
-		return r;
-	}
-
-	dm_bm_unlock(superblock);
-
 	return dm_bufio_write_dirty_buffers(bm->bufio);
 }
-EXPORT_SYMBOL_GPL(dm_bm_flush_and_unlock);
+EXPORT_SYMBOL_GPL(dm_bm_flush);
 
 void dm_bm_prefetch(struct dm_block_manager *bm, dm_block_t b)
 {
diff --git a/drivers/md/persistent-data/dm-block-manager.h b/drivers/md/persistent-data/dm-block-manager.h
index 13cd58e1fe69..1b95dfc17786 100644
--- a/drivers/md/persistent-data/dm-block-manager.h
+++ b/drivers/md/persistent-data/dm-block-manager.h
@@ -105,8 +105,7 @@ int dm_bm_unlock(struct dm_block *b);
  *
  * This method always blocks.
  */
-int dm_bm_flush_and_unlock(struct dm_block_manager *bm,
-			   struct dm_block *superblock);
+int dm_bm_flush(struct dm_block_manager *bm);
 
 /*
  * Request data is prefetched into the cache.
diff --git a/drivers/md/persistent-data/dm-transaction-manager.c b/drivers/md/persistent-data/dm-transaction-manager.c
index 81da1a26042e..3bc30a0ae3d6 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.c
+++ b/drivers/md/persistent-data/dm-transaction-manager.c
@@ -154,7 +154,7 @@ int dm_tm_pre_commit(struct dm_transaction_manager *tm)
 	if (r < 0)
 		return r;
 
-	return 0;
+	return dm_bm_flush(tm->bm);
 }
 EXPORT_SYMBOL_GPL(dm_tm_pre_commit);
 
@@ -164,8 +164,9 @@ int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root)
 		return -EWOULDBLOCK;
 
 	wipe_shadow_table(tm);
+	dm_bm_unlock(root);
 
-	return dm_bm_flush_and_unlock(tm->bm, root);
+	return dm_bm_flush(tm->bm);
 }
 EXPORT_SYMBOL_GPL(dm_tm_commit);
 
diff --git a/drivers/md/persistent-data/dm-transaction-manager.h b/drivers/md/persistent-data/dm-transaction-manager.h
index b5b139076ca5..2772ed2a781a 100644
--- a/drivers/md/persistent-data/dm-transaction-manager.h
+++ b/drivers/md/persistent-data/dm-transaction-manager.h
@@ -38,18 +38,17 @@ struct dm_transaction_manager *dm_tm_create_non_blocking_clone(struct dm_transac
 /*
  * We use a 2-phase commit here.
  *
- * i) In the first phase the block manager is told to start flushing, and
- * the changes to the space map are written to disk.  You should interrogate
- * your particular space map to get detail of its root node etc. to be
- * included in your superblock.
+ * i) Make all changes for the transaction *except* for the superblock.
+ * Then call dm_tm_pre_commit() to flush them to disk.
  *
- * ii) @root will be committed last.  You shouldn't use more than the
- * first 512 bytes of @root if you wish the transaction to survive a power
- * failure.  You *must* have a write lock held on @root for both stage (i)
- * and (ii).  The commit will drop the write lock.
+ * ii) Lock your superblock.  Update.  Then call dm_tm_commit() which will
+ * unlock the superblock and flush it.  No other blocks should be updated
+ * during this period.  Care should be taken to never unlock a partially
+ * updated superblock; perform any operations that could fail *before* you
+ * take the superblock lock.
  */
 int dm_tm_pre_commit(struct dm_transaction_manager *tm);
-int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *root);
+int dm_tm_commit(struct dm_transaction_manager *tm, struct dm_block *superblock);
 
 /*
  * These methods are the only way to get hold of a writeable block.
diff --git a/drivers/mmc/host/sdhci-bcm-kona.c b/drivers/mmc/host/sdhci-bcm-kona.c
index 7a190fe4dff1..e5565aa5ed36 100644
--- a/drivers/mmc/host/sdhci-bcm-kona.c
+++ b/drivers/mmc/host/sdhci-bcm-kona.c
@@ -314,7 +314,7 @@ err_pltfm_free:
 	return ret;
 }
 
-static int __exit sdhci_bcm_kona_remove(struct platform_device *pdev)
+static int sdhci_bcm_kona_remove(struct platform_device *pdev)
 {
 	return sdhci_pltfm_unregister(pdev);
 }
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index c36e9b84487c..2c059890a394 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -1220,6 +1220,7 @@ static int atmel_pmecc_nand_init_params(struct platform_device *pdev,
 		goto err;
 	}
 
+	nand_chip->options |= NAND_NO_SUBPAGE_WRITE;
 	nand_chip->ecc.read_page = atmel_nand_pmecc_read_page;
 	nand_chip->ecc.write_page = atmel_nand_pmecc_write_page;
 
diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c
index fec31d71b84e..fe8a020ecf25 100644
--- a/drivers/mtd/nand/diskonchip.c
+++ b/drivers/mtd/nand/diskonchip.c
@@ -1438,7 +1438,7 @@ static int __init doc_probe(unsigned long physadr)
 	int reg, len, numchips;
 	int ret = 0;
 
-	if (!request_mem_region(physadr, DOC_IOREMAP_LEN, NULL))
+	if (!request_mem_region(physadr, DOC_IOREMAP_LEN, "DiskOnChip"))
 		return -EBUSY;
 	virtadr = ioremap(physadr, DOC_IOREMAP_LEN);
 	if (!virtadr) {
diff --git a/drivers/mtd/nand/nuc900_nand.c b/drivers/mtd/nand/nuc900_nand.c
index 9ee09a8177c6..7360f7872d9a 100644
--- a/drivers/mtd/nand/nuc900_nand.c
+++ b/drivers/mtd/nand/nuc900_nand.c
@@ -225,7 +225,7 @@ static void nuc900_nand_enable(struct nuc900_nand *nand)
 	val = __raw_readl(nand->reg + REG_FMICSR);
 
 	if (!(val & NAND_EN))
-		__raw_writel(val | NAND_EN, REG_FMICSR);
+		__raw_writel(val | NAND_EN, nand->reg + REG_FMICSR);
 
 	val = __raw_readl(nand->reg + REG_SMCSR);
 
diff --git a/drivers/mtd/sm_ftl.c b/drivers/mtd/sm_ftl.c
index 4b8e89583f2a..cf49c22673b9 100644
--- a/drivers/mtd/sm_ftl.c
+++ b/drivers/mtd/sm_ftl.c
@@ -59,15 +59,12 @@ static struct attribute_group *sm_create_sysfs_attributes(struct sm_ftl *ftl)
 	struct attribute_group *attr_group;
 	struct attribute **attributes;
 	struct sm_sysfs_attribute *vendor_attribute;
+	char *vendor;
 
-	int vendor_len = strnlen(ftl->cis_buffer + SM_CIS_VENDOR_OFFSET,
-					SM_SMALL_PAGE - SM_CIS_VENDOR_OFFSET);
-
-	char *vendor = kmalloc(vendor_len, GFP_KERNEL);
+	vendor = kstrndup(ftl->cis_buffer + SM_CIS_VENDOR_OFFSET,
+			  SM_SMALL_PAGE - SM_CIS_VENDOR_OFFSET, GFP_KERNEL);
 	if (!vendor)
 		goto error1;
-	memcpy(vendor, ftl->cis_buffer + SM_CIS_VENDOR_OFFSET, vendor_len);
-	vendor[vendor_len] = 0;
 
 	/* Initialize sysfs attributes */
 	vendor_attribute =
@@ -78,7 +75,7 @@ static struct attribute_group *sm_create_sysfs_attributes(struct sm_ftl *ftl)
 	sysfs_attr_init(&vendor_attribute->dev_attr.attr);
 
 	vendor_attribute->data = vendor;
-	vendor_attribute->len = vendor_len;
+	vendor_attribute->len = strlen(vendor);
 	vendor_attribute->dev_attr.attr.name = "vendor";
 	vendor_attribute->dev_attr.attr.mode = S_IRUGO;
 	vendor_attribute->dev_attr.show = sm_attr_show;
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 8d76fca7fde7..ca2dfbe01598 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -89,9 +89,8 @@
 #define      MVNETA_TX_IN_PRGRS                  BIT(1)
 #define      MVNETA_TX_FIFO_EMPTY                BIT(8)
 #define MVNETA_RX_MIN_FRAME_SIZE                 0x247c
-#define MVNETA_SERDES_CFG			 0x24A0
+#define MVNETA_SGMII_SERDES_CFG			 0x24A0
 #define      MVNETA_SGMII_SERDES_PROTO		 0x0cc7
-#define      MVNETA_RGMII_SERDES_PROTO		 0x0667
 #define MVNETA_TYPE_PRIO                         0x24bc
 #define      MVNETA_FORCE_UNI                    BIT(21)
 #define MVNETA_TXQ_CMD_1                         0x24e4
@@ -712,6 +711,35 @@ static void mvneta_rxq_bm_disable(struct mvneta_port *pp,
 	mvreg_write(pp, MVNETA_RXQ_CONFIG_REG(rxq->id), val);
 }
 
+
+
+/* Sets the RGMII Enable bit (RGMIIEn) in port MAC control register */
+static void mvneta_gmac_rgmii_set(struct mvneta_port *pp, int enable)
+{
+	u32  val;
+
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+
+	if (enable)
+		val |= MVNETA_GMAC2_PORT_RGMII;
+	else
+		val &= ~MVNETA_GMAC2_PORT_RGMII;
+
+	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
+}
+
+/* Config SGMII port */
+static void mvneta_port_sgmii_config(struct mvneta_port *pp)
+{
+	u32 val;
+
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
+	val |= MVNETA_GMAC2_PCS_ENABLE;
+	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
+
+	mvreg_write(pp, MVNETA_SGMII_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
+}
+
 /* Start the Ethernet port RX and TX activity */
 static void mvneta_port_up(struct mvneta_port *pp)
 {
@@ -2729,15 +2757,12 @@ static void mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 	mvreg_write(pp, MVNETA_UNIT_INTR_CAUSE, 0);
 
 	if (phy_mode == PHY_INTERFACE_MODE_SGMII)
-		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
-	else
-		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_RGMII_SERDES_PROTO);
+		mvneta_port_sgmii_config(pp);
 
-	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
-
-	val |= MVNETA_GMAC2_PCS_ENABLE | MVNETA_GMAC2_PORT_RGMII;
+	mvneta_gmac_rgmii_set(pp, 1);
 
 	/* Cancel Port Reset */
+	val = mvreg_read(pp, MVNETA_GMAC_CTRL_2);
 	val &= ~MVNETA_GMAC2_PORT_RESET;
 	mvreg_write(pp, MVNETA_GMAC_CTRL_2, val);
 
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 55897d508a76..0526ddff977d 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1698,7 +1698,7 @@ int ath_cabq_update(struct ath_softc *sc)
 
 	ath9k_hw_get_txq_props(sc->sc_ah, qnum, &qi);
 
-	qi.tqi_readyTime = (cur_conf->beacon_interval *
+	qi.tqi_readyTime = (TU_TO_USEC(cur_conf->beacon_interval) *
 			    ATH_CABQ_READY_TIME) / 100;
 	ath_txq_update(sc, qnum, &qi);
 
diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c
index 05ee7f10cc8f..24ccbe96e0c8 100644
--- a/drivers/net/wireless/b43/phy_n.c
+++ b/drivers/net/wireless/b43/phy_n.c
@@ -5176,22 +5176,22 @@ static void b43_nphy_channel_setup(struct b43_wldev *dev,
 	int ch = new_channel->hw_value;
 
 	u16 old_band_5ghz;
-	u32 tmp32;
+	u16 tmp16;
 
 	old_band_5ghz =
 		b43_phy_read(dev, B43_NPHY_BANDCTL) & B43_NPHY_BANDCTL_5GHZ;
 	if (new_channel->band == IEEE80211_BAND_5GHZ && !old_band_5ghz) {
-		tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4);
+		tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4);
 		b43_phy_set(dev, B43_PHY_B_BBCFG, 0xC000);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16);
 		b43_phy_set(dev, B43_NPHY_BANDCTL, B43_NPHY_BANDCTL_5GHZ);
 	} else if (new_channel->band == IEEE80211_BAND_2GHZ && old_band_5ghz) {
 		b43_phy_mask(dev, B43_NPHY_BANDCTL, ~B43_NPHY_BANDCTL_5GHZ);
-		tmp32 = b43_read32(dev, B43_MMIO_PSM_PHY_HDR);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32 | 4);
+		tmp16 = b43_read16(dev, B43_MMIO_PSM_PHY_HDR);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16 | 4);
 		b43_phy_mask(dev, B43_PHY_B_BBCFG, 0x3FFF);
-		b43_write32(dev, B43_MMIO_PSM_PHY_HDR, tmp32);
+		b43_write16(dev, B43_MMIO_PSM_PHY_HDR, tmp16);
 	}
 
 	b43_chantab_phy_upload(dev, e);
diff --git a/drivers/net/wireless/iwlwifi/dvm/main.c b/drivers/net/wireless/iwlwifi/dvm/main.c
index ba1b1ea54252..ea7e70cb34f0 100644
--- a/drivers/net/wireless/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/iwlwifi/dvm/main.c
@@ -252,13 +252,17 @@ static void iwl_bg_bt_runtime_config(struct work_struct *work)
 	struct iwl_priv *priv =
 		container_of(work, struct iwl_priv, bt_runtime_config);
 
+	mutex_lock(&priv->mutex);
 	if (test_bit(STATUS_EXIT_PENDING, &priv->status))
-		return;
+		goto out;
 
 	/* dont send host command if rf-kill is on */
 	if (!iwl_is_ready_rf(priv))
-		return;
+		goto out;
+
 	iwlagn_send_advance_bt_config(priv);
+out:
+	mutex_unlock(&priv->mutex);
 }
 
 static void iwl_bg_bt_full_concurrency(struct work_struct *work)
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index c35b8661b395..9a856e5031f1 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -179,7 +179,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm)
 	    !iwlwifi_mod_params.sw_crypto)
 		hw->flags |= IEEE80211_HW_MFP_CAPABLE;
 
-	if (mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT) {
+	if (0 && mvm->fw->ucode_capa.flags & IWL_UCODE_TLV_FLAGS_UAPSD_SUPPORT) {
 		hw->flags |= IEEE80211_HW_SUPPORTS_UAPSD;
 		hw->uapsd_queues = IWL_UAPSD_AC_INFO;
 		hw->uapsd_max_sp_len = IWL_UAPSD_MAX_SP;
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
index e06971be7df7..f923d8c9a296 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/hw.c
@@ -1025,9 +1025,20 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 	bool rtstatus = true;
 	int err = 0;
 	u8 tmp_u1b, u1byte;
+	unsigned long flags;
 
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD, "Rtl8188EE hw init\n");
 	rtlpriv->rtlhal.being_init_adapter = true;
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 
 	tmp_u1b = rtl_read_byte(rtlpriv, REG_SYS_CLKR+1);
@@ -1043,7 +1054,7 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 	if (rtstatus != true) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 
 	err = rtl88e_download_fw(hw, false);
@@ -1051,8 +1062,7 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now..\n");
 		err = 1;
-		rtlhal->fw_ready = false;
-		return err;
+		goto exit;
 	} else {
 		rtlhal->fw_ready = true;
 	}
@@ -1135,10 +1145,12 @@ int rtl88ee_hw_init(struct ieee80211_hw *hw)
 	}
 	rtl_write_byte(rtlpriv, REG_NAV_CTRL+2,  ((30000+127)/128));
 	rtl88e_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpriv->rtlhal.being_init_adapter = false;
 	RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD, "end of Rtl8188EE hw init %x\n",
 		 err);
-	return 0;
+	return err;
 }
 
 static enum version_8188e _rtl88ee_read_chip_version(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c b/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
index aece6c9cccf1..7622e44567cc 100644
--- a/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8188ee/trx.c
@@ -293,7 +293,7 @@ static void _rtl88ee_translate_rx_signal_stuff(struct ieee80211_hw *hw,
 	u8 *psaddr;
 	__le16 fc;
 	u16 type, ufc;
-	bool match_bssid, packet_toself, packet_beacon, addr;
+	bool match_bssid, packet_toself, packet_beacon = false, addr;
 
 	tmp_buf = skb->data + pstatus->rx_drvinfo_size + pstatus->rx_bufshift;
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c b/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
index 468bf73cc883..cd17c642e746 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192cu/hw.c
@@ -985,6 +985,17 @@ int rtl92cu_hw_init(struct ieee80211_hw *hw)
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	int err = 0;
 	static bool iqk_initialized;
+	unsigned long flags;
+
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
 
 	rtlhal->hw_type = HARDWARE_TYPE_RTL8192CU;
 	err = _rtl92cu_init_mac(hw);
@@ -997,7 +1008,7 @@ int rtl92cu_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now..\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 	rtlhal->last_hmeboxnum = 0; /* h2c */
 	_rtl92cu_phy_param_tab_init(hw);
@@ -1034,6 +1045,8 @@ int rtl92cu_hw_init(struct ieee80211_hw *hw)
 	_InitPABias(hw);
 	_update_mac_setting(hw);
 	rtl92c_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	return err;
 }
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/hw.c b/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
index 4f461786a7eb..c471400fe8f0 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/hw.c
@@ -955,7 +955,7 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_efuse *rtlefuse = rtl_efuse(rtl_priv(hw));
 	u8 tmp_byte = 0;
-
+	unsigned long flags;
 	bool rtstatus = true;
 	u8 tmp_u1b;
 	int err = false;
@@ -967,6 +967,16 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 
 	rtlpci->being_init_adapter = true;
 
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 
 	/* 1. MAC Initialize */
@@ -984,7 +994,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now... "
 			 "Please copy FW into /lib/firmware/rtlwifi\n");
-		return 1;
+		err = 1;
+		goto exit;
 	}
 
 	/* After FW download, we have to reset MAC register */
@@ -997,7 +1008,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 	/* 3. Initialize MAC/PHY Config by MACPHY_reg.txt */
 	if (!rtl92s_phy_mac_config(hw)) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "MAC Config failed\n");
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* because last function modify RCR, so we update
@@ -1016,7 +1028,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 	/* 4. Initialize BB After MAC Config PHY_reg.txt, AGC_Tab.txt */
 	if (!rtl92s_phy_bb_config(hw)) {
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_EMERG, "BB Config failed\n");
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* 5. Initiailze RF RAIO_A.txt RF RAIO_B.txt */
@@ -1033,7 +1046,8 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 
 	if (!rtl92s_phy_rf_config(hw)) {
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_DMESG, "RF Config failed\n");
-		return rtstatus;
+		err = rtstatus;
+		goto exit;
 	}
 
 	/* After read predefined TXT, we must set BB/MAC/RF
@@ -1122,8 +1136,9 @@ int rtl92se_hw_init(struct ieee80211_hw *hw)
 
 	rtlpriv->cfg->ops->led_control(hw, LED_CTL_POWER_ON);
 	rtl92s_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpci->being_init_adapter = false;
-
 	return err;
 }
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
index 27efbcdac6a9..d27abef140f0 100644
--- a/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
+++ b/drivers/net/wireless/rtlwifi/rtl8192se/trx.c
@@ -49,6 +49,12 @@ static u8 _rtl92se_map_hwqueue_to_fwqueue(struct sk_buff *skb,	u8 skb_queue)
 	if (ieee80211_is_nullfunc(fc))
 		return QSLT_HIGH;
 
+	/* Kernel commit 1bf4bbb4024dcdab changed EAPOL packets to use
+	 * queue V0 at priority 7; however, the RTL8192SE appears to have
+	 * that queue at priority 6
+	 */
+	if (skb->priority == 7)
+		return QSLT_VO;
 	return skb->priority;
 }
 
diff --git a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
index c333dfd116b8..99f6bc5fa986 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723ae/hw.c
@@ -880,14 +880,25 @@ int rtl8723ae_hw_init(struct ieee80211_hw *hw)
 	bool rtstatus = true;
 	int err;
 	u8 tmp_u1b;
+	unsigned long flags;
 
 	rtlpriv->rtlhal.being_init_adapter = true;
+	/* As this function can take a very long time (up to 350 ms)
+	 * and can be called with irqs disabled, reenable the irqs
+	 * to let the other devices continue being serviced.
+	 *
+	 * It is safe doing so since our own interrupts will only be enabled
+	 * in a subsequent step.
+	 */
+	local_save_flags(flags);
+	local_irq_enable();
+
 	rtlpriv->intf_ops->disable_aspm(hw);
 	rtstatus = _rtl8712e_init_mac(hw);
 	if (rtstatus != true) {
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_EMERG, "Init MAC failed\n");
 		err = 1;
-		return err;
+		goto exit;
 	}
 
 	err = rtl8723ae_download_fw(hw);
@@ -895,8 +906,7 @@ int rtl8723ae_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_ERR, DBG_WARNING,
 			 "Failed to download FW. Init HW without FW now..\n");
 		err = 1;
-		rtlhal->fw_ready = false;
-		return err;
+		goto exit;
 	} else {
 		rtlhal->fw_ready = true;
 	}
@@ -971,6 +981,8 @@ int rtl8723ae_hw_init(struct ieee80211_hw *hw)
 		RT_TRACE(rtlpriv, COMP_INIT, DBG_TRACE, "under 1.5V\n");
 	}
 	rtl8723ae_dm_init(hw);
+exit:
+	local_irq_restore(flags);
 	rtlpriv->rtlhal.being_init_adapter = false;
 	return err;
 }
diff --git a/drivers/pinctrl/pinctrl-as3722.c b/drivers/pinctrl/pinctrl-as3722.c
index 92ed4b2e3c07..c862f9c0e9ce 100644
--- a/drivers/pinctrl/pinctrl-as3722.c
+++ b/drivers/pinctrl/pinctrl-as3722.c
@@ -64,7 +64,6 @@ struct as3722_pin_function {
 };
 
 struct as3722_gpio_pin_control {
-	bool enable_gpio_invert;
 	unsigned mode_prop;
 	int io_function;
 };
@@ -320,10 +319,8 @@ static int as3722_pinctrl_gpio_set_direction(struct pinctrl_dev *pctldev,
 		return mode;
 	}
 
-	if (as_pci->gpio_control[offset].enable_gpio_invert)
-		mode |= AS3722_GPIO_INV;
-
-	return as3722_write(as3722, AS3722_GPIOn_CONTROL_REG(offset), mode);
+	return as3722_update_bits(as3722, AS3722_GPIOn_CONTROL_REG(offset),
+				AS3722_GPIO_MODE_MASK, mode);
 }
 
 static const struct pinmux_ops as3722_pinmux_ops = {
@@ -496,10 +493,18 @@ static void as3722_gpio_set(struct gpio_chip *chip, unsigned offset,
 {
 	struct as3722_pctrl_info *as_pci = to_as_pci(chip);
 	struct as3722 *as3722 = as_pci->as3722;
-	int en_invert = as_pci->gpio_control[offset].enable_gpio_invert;
+	int en_invert;
 	u32 val;
 	int ret;
 
+	ret = as3722_read(as3722, AS3722_GPIOn_CONTROL_REG(offset), &val);
+	if (ret < 0) {
+		dev_err(as_pci->dev,
+			"GPIO_CONTROL%d_REG read failed: %d\n", offset, ret);
+		return;
+	}
+	en_invert = !!(val & AS3722_GPIO_INV);
+
 	if (value)
 		val = (en_invert) ? 0 : AS3722_GPIOn_SIGNAL(offset);
 	else
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index defb6afc1409..e2a91c845ac9 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -8447,9 +8447,21 @@ static void mute_led_exit(void)
 		tpacpi_led_set(i, false);
 }
 
+static void mute_led_resume(void)
+{
+	int i;
+
+	for (i = 0; i < TPACPI_LED_MAX; i++) {
+		struct tp_led_table *t = &led_tables[i];
+		if (t->state >= 0)
+			mute_led_on_off(t, t->state);
+	}
+}
+
 static struct ibm_struct mute_led_driver_data = {
 	.name = "mute_led",
 	.exit = mute_led_exit,
+	.resume = mute_led_resume,
 };
 
 /****************************************************************************
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 9f0ea6cb6922..e3bf885f4a6c 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -541,18 +541,27 @@ static void chsc_process_sei_nt0(struct chsc_sei_nt0_area *sei_area)
 
 static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm)
 {
-	do {
+	static int ntsm_unsupported;
+
+	while (true) {
 		memset(sei, 0, sizeof(*sei));
 		sei->request.length = 0x0010;
 		sei->request.code = 0x000e;
-		sei->ntsm = ntsm;
+		if (!ntsm_unsupported)
+			sei->ntsm = ntsm;
 
 		if (chsc(sei))
 			break;
 
 		if (sei->response.code != 0x0001) {
-			CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x)\n",
-				      sei->response.code);
+			CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x, ntsm=%llx)\n",
+				      sei->response.code, sei->ntsm);
+
+			if (sei->response.code == 3 && sei->ntsm) {
+				/* Fallback for old firmware. */
+				ntsm_unsupported = 1;
+				continue;
+			}
 			break;
 		}
 
@@ -568,7 +577,10 @@ static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm)
 			CIO_CRW_EVENT(2, "chsc: unhandled nt: %d\n", sei->nt);
 			break;
 		}
-	} while (sei->u.nt0_area.flags & 0x80);
+
+		if (!(sei->u.nt0_area.flags & 0x80))
+			break;
+	}
 }
 
 /*
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 7f0af4fcc001..6fd7d40b2c4d 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -8293,7 +8293,6 @@ _scsih_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	mpt2sas_base_free_resources(ioc);
 	pci_save_state(pdev);
-	pci_disable_device(pdev);
 	pci_set_power_state(pdev, device_state);
 	return 0;
 }
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 16bfd50cd3fe..db3b494e5926 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -750,8 +750,12 @@ static void __virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity)
 
 		vscsi->affinity_hint_set = true;
 	} else {
-		for (i = 0; i < vscsi->num_queues; i++)
+		for (i = 0; i < vscsi->num_queues; i++) {
+			if (!vscsi->req_vqs[i].vq)
+				continue;
+
 			virtqueue_set_affinity(vscsi->req_vqs[i].vq, -1);
+		}
 
 		vscsi->affinity_hint_set = false;
 	}
diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c
index 94f9e3a38412..0ff7fda0742f 100644
--- a/drivers/tty/hvc/hvc_console.c
+++ b/drivers/tty/hvc/hvc_console.c
@@ -190,7 +190,7 @@ static struct tty_driver *hvc_console_device(struct console *c, int *index)
 	return hvc_driver;
 }
 
-static int __init hvc_console_setup(struct console *co, char *options)
+static int hvc_console_setup(struct console *co, char *options)
 {	
 	if (co->index < 0 || co->index >= MAX_NR_HVC_CONSOLES)
 		return -ENODEV;
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index d15624c1b751..e36d1f5ca191 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -2356,8 +2356,12 @@ static ssize_t n_tty_write(struct tty_struct *tty, struct file *file,
 			if (tty->ops->flush_chars)
 				tty->ops->flush_chars(tty);
 		} else {
+			struct n_tty_data *ldata = tty->disc_data;
+
 			while (nr > 0) {
+				mutex_lock(&ldata->output_lock);
 				c = tty->ops->write(tty, b, nr);
+				mutex_unlock(&ldata->output_lock);
 				if (c < 0) {
 					retval = c;
 					goto break_out;
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 69932b7556cf..2798a23a0834 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -555,7 +555,7 @@ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep)
 	 */
 	if ((p->port.type == PORT_XR17V35X) ||
 	   (p->port.type == PORT_XR17D15X)) {
-		serial_out(p, UART_EXAR_SLEEP, 0xff);
+		serial_out(p, UART_EXAR_SLEEP, sleep ? 0xff : 0);
 		return;
 	}
 
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index 8ebd9f88a6f6..cf78d1985cd8 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -258,7 +258,11 @@ static int __tty_buffer_request_room(struct tty_port *port, size_t size,
 			n->flags = flags;
 			buf->tail = n;
 			b->commit = b->used;
-			smp_mb();
+			/* paired w/ barrier in flush_to_ldisc(); ensures the
+			 * latest commit value can be read before the head is
+			 * advanced to the next buffer
+			 */
+			smp_wmb();
 			b->next = n;
 		} else if (change)
 			size = 0;
@@ -444,17 +448,24 @@ static void flush_to_ldisc(struct work_struct *work)
 
 	while (1) {
 		struct tty_buffer *head = buf->head;
+		struct tty_buffer *next;
 		int count;
 
 		/* Ldisc or user is trying to gain exclusive access */
 		if (atomic_read(&buf->priority))
 			break;
 
+		next = head->next;
+		/* paired w/ barrier in __tty_buffer_request_room();
+		 * ensures commit value read is not stale if the head
+		 * is advancing to the next buffer
+		 */
+		smp_rmb();
 		count = head->commit - head->read;
 		if (!count) {
-			if (head->next == NULL)
+			if (next == NULL)
 				break;
-			buf->head = head->next;
+			buf->head = next;
 			tty_buffer_free(port, head);
 			continue;
 		}
diff --git a/drivers/video/aty/mach64_accel.c b/drivers/video/aty/mach64_accel.c
index e45833ce975b..182bd680141f 100644
--- a/drivers/video/aty/mach64_accel.c
+++ b/drivers/video/aty/mach64_accel.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/delay.h>
+#include <asm/unaligned.h>
 #include <linux/fb.h>
 #include <video/mach64.h>
 #include "atyfb.h"
@@ -419,7 +420,7 @@ void atyfb_imageblit(struct fb_info *info, const struct fb_image *image)
 		u32 *pbitmap, dwords = (src_bytes + 3) / 4;
 		for (pbitmap = (u32*)(image->data); dwords; dwords--, pbitmap++) {
 			wait_for_fifo(1, par);
-			aty_st_le32(HOST_DATA0, le32_to_cpup(pbitmap), par);
+			aty_st_le32(HOST_DATA0, get_unaligned_le32(pbitmap), par);
 		}
 	}
 
diff --git a/drivers/video/aty/mach64_cursor.c b/drivers/video/aty/mach64_cursor.c
index 95ec042ddbf8..0fe02e22d9a4 100644
--- a/drivers/video/aty/mach64_cursor.c
+++ b/drivers/video/aty/mach64_cursor.c
@@ -5,6 +5,7 @@
 #include <linux/fb.h>
 #include <linux/init.h>
 #include <linux/string.h>
+#include "../fb_draw.h"
 
 #include <asm/io.h>
 
@@ -157,24 +158,33 @@ static int atyfb_cursor(struct fb_info *info, struct fb_cursor *cursor)
 
 	    for (i = 0; i < height; i++) {
 		for (j = 0; j < width; j++) {
+			u16 l = 0xaaaa;
 			b = *src++;
 			m = *msk++;
 			switch (cursor->rop) {
 			case ROP_XOR:
 			    // Upper 4 bits of mask data
-			    fb_writeb(cursor_bits_lookup[(b ^ m) >> 4], dst++);
+			    l = cursor_bits_lookup[(b ^ m) >> 4] |
 			    // Lower 4 bits of mask
-			    fb_writeb(cursor_bits_lookup[(b ^ m) & 0x0f],
-				      dst++);
+				    (cursor_bits_lookup[(b ^ m) & 0x0f] << 8);
 			    break;
 			case ROP_COPY:
 			    // Upper 4 bits of mask data
-			    fb_writeb(cursor_bits_lookup[(b & m) >> 4], dst++);
+			    l = cursor_bits_lookup[(b & m) >> 4] |
 			    // Lower 4 bits of mask
-			    fb_writeb(cursor_bits_lookup[(b & m) & 0x0f],
-				      dst++);
+				    (cursor_bits_lookup[(b & m) & 0x0f] << 8);
 			    break;
 			}
+			/*
+			 * If cursor size is not a multiple of 8 characters
+			 * we must pad it with transparent pattern (0xaaaa).
+			 */
+			if ((j + 1) * 8 > cursor->image.width) {
+				l = comp(l, 0xaaaa,
+				    (1 << ((cursor->image.width & 7) * 2)) - 1);
+			}
+			fb_writeb(l & 0xff, dst++);
+			fb_writeb(l >> 8, dst++);
 		}
 		dst += offset;
 	    }
diff --git a/drivers/video/cfbcopyarea.c b/drivers/video/cfbcopyarea.c
index bb5a96b1645d..bcb57235fcc7 100644
--- a/drivers/video/cfbcopyarea.c
+++ b/drivers/video/cfbcopyarea.c
@@ -43,13 +43,22 @@
      */
 
 static void
-bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
-		const unsigned long __iomem *src, int src_idx, int bits,
+bitcpy(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
+		const unsigned long __iomem *src, unsigned src_idx, int bits,
 		unsigned n, u32 bswapmask)
 {
 	unsigned long first, last;
 	int const shift = dst_idx-src_idx;
-	int left, right;
+
+#if 0
+	/*
+	 * If you suspect bug in this function, compare it with this simple
+	 * memmove implementation.
+	 */
+	fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
+		   (char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
+	return;
+#endif
 
 	first = fb_shifted_pixels_mask_long(p, dst_idx, bswapmask);
 	last = ~fb_shifted_pixels_mask_long(p, (dst_idx+n) % bits, bswapmask);
@@ -98,9 +107,8 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 		unsigned long d0, d1;
 		int m;
 
-		right = shift & (bits - 1);
-		left = -shift & (bits - 1);
-		bswapmask &= shift;
+		int const left = shift & (bits - 1);
+		int const right = -shift & (bits - 1);
 
 		if (dst_idx+n <= bits) {
 			// Single destination word
@@ -110,15 +118,15 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			if (shift > 0) {
 				// Single source word
-				d0 >>= right;
+				d0 <<= left;
 			} else if (src_idx+n <= bits) {
 				// Single source word
-				d0 <<= left;
+				d0 >>= right;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src + 1);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0<<left | d1>>right;
+				d0 = d0 >> right | d1 << left;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
@@ -135,60 +143,59 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 			if (shift > 0) {
 				// Single source word
 				d1 = d0;
-				d0 >>= right;
-				dst++;
+				d0 <<= left;
 				n -= bits - dst_idx;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src++);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
 
-				d0 = d0<<left | d1>>right;
-				dst++;
+				d0 = d0 >> right | d1 << left;
 				n -= bits - dst_idx;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
 			d0 = d1;
+			dst++;
 
 			// Main chunk
 			m = n % bits;
 			n /= bits;
 			while ((n >= 4) && !bswapmask) {
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				d1 = FB_READL(src++);
-				FB_WRITEL(d0 << left | d1 >> right, dst++);
+				FB_WRITEL(d0 >> right | d1 << left, dst++);
 				d0 = d1;
 				n -= 4;
 			}
 			while (n--) {
 				d1 = FB_READL(src++);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0 << left | d1 >> right;
+				d0 = d0 >> right | d1 << left;
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(d0, dst++);
 				d0 = d1;
 			}
 
 			// Trailing bits
-			if (last) {
-				if (m <= right) {
+			if (m) {
+				if (m <= bits - right) {
 					// Single source word
-					d0 <<= left;
+					d0 >>= right;
 				} else {
 					// 2 source words
 					d1 = FB_READL(src);
 					d1 = fb_rev_pixels_in_long(d1,
 								bswapmask);
-					d0 = d0<<left | d1>>right;
+					d0 = d0 >> right | d1 << left;
 				}
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
@@ -202,43 +209,46 @@ bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
      */
 
 static void
-bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
-		const unsigned long __iomem *src, int src_idx, int bits,
+bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, unsigned dst_idx,
+		const unsigned long __iomem *src, unsigned src_idx, int bits,
 		unsigned n, u32 bswapmask)
 {
 	unsigned long first, last;
 	int shift;
 
-	dst += (n-1)/bits;
-	src += (n-1)/bits;
-	if ((n-1) % bits) {
-		dst_idx += (n-1) % bits;
-		dst += dst_idx >> (ffs(bits) - 1);
-		dst_idx &= bits - 1;
-		src_idx += (n-1) % bits;
-		src += src_idx >> (ffs(bits) - 1);
-		src_idx &= bits - 1;
-	}
+#if 0
+	/*
+	 * If you suspect bug in this function, compare it with this simple
+	 * memmove implementation.
+	 */
+	fb_memmove((char *)dst + ((dst_idx & (bits - 1))) / 8,
+		   (char *)src + ((src_idx & (bits - 1))) / 8, n / 8);
+	return;
+#endif
+
+	dst += (dst_idx + n - 1) / bits;
+	src += (src_idx + n - 1) / bits;
+	dst_idx = (dst_idx + n - 1) % bits;
+	src_idx = (src_idx + n - 1) % bits;
 
 	shift = dst_idx-src_idx;
 
-	first = fb_shifted_pixels_mask_long(p, bits - 1 - dst_idx, bswapmask);
-	last = ~fb_shifted_pixels_mask_long(p, bits - 1 - ((dst_idx-n) % bits),
-					    bswapmask);
+	first = ~fb_shifted_pixels_mask_long(p, (dst_idx + 1) % bits, bswapmask);
+	last = fb_shifted_pixels_mask_long(p, (bits + dst_idx + 1 - n) % bits, bswapmask);
 
 	if (!shift) {
 		// Same alignment for source and dest
 
 		if ((unsigned long)dst_idx+1 >= n) {
 			// Single word
-			if (last)
-				first &= last;
-			FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
+			if (first)
+				last &= first;
+			FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
 		} else {
 			// Multiple destination words
 
 			// Leading bits
-			if (first != ~0UL) {
+			if (first) {
 				FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
 				dst--;
 				src--;
@@ -262,7 +272,7 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 				FB_WRITEL(FB_READL(src--), dst--);
 
 			// Trailing bits
-			if (last)
+			if (last != -1UL)
 				FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
 		}
 	} else {
@@ -270,29 +280,28 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 		unsigned long d0, d1;
 		int m;
 
-		int const left = -shift & (bits-1);
-		int const right = shift & (bits-1);
-		bswapmask &= shift;
+		int const left = shift & (bits-1);
+		int const right = -shift & (bits-1);
 
 		if ((unsigned long)dst_idx+1 >= n) {
 			// Single destination word
-			if (last)
-				first &= last;
+			if (first)
+				last &= first;
 			d0 = FB_READL(src);
 			if (shift < 0) {
 				// Single source word
-				d0 <<= left;
+				d0 >>= right;
 			} else if (1+(unsigned long)src_idx >= n) {
 				// Single source word
-				d0 >>= right;
+				d0 <<= left;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src - 1);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0>>right | d1<<left;
+				d0 = d0 << left | d1 >> right;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
-			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
+			FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
 		} else {
 			// Multiple destination words
 			/** We must always remember the last value read, because in case
@@ -307,12 +316,12 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 			if (shift < 0) {
 				// Single source word
 				d1 = d0;
-				d0 <<= left;
+				d0 >>= right;
 			} else {
 				// 2 source words
 				d1 = FB_READL(src--);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0>>right | d1<<left;
+				d0 = d0 << left | d1 >> right;
 			}
 			d0 = fb_rev_pixels_in_long(d0, bswapmask);
 			FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
@@ -325,39 +334,39 @@ bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
 			n /= bits;
 			while ((n >= 4) && !bswapmask) {
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				d1 = FB_READL(src--);
-				FB_WRITEL(d0 >> right | d1 << left, dst--);
+				FB_WRITEL(d0 << left | d1 >> right, dst--);
 				d0 = d1;
 				n -= 4;
 			}
 			while (n--) {
 				d1 = FB_READL(src--);
 				d1 = fb_rev_pixels_in_long(d1, bswapmask);
-				d0 = d0 >> right | d1 << left;
+				d0 = d0 << left | d1 >> right;
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(d0, dst--);
 				d0 = d1;
 			}
 
 			// Trailing bits
-			if (last) {
-				if (m <= left) {
+			if (m) {
+				if (m <= bits - left) {
 					// Single source word
-					d0 >>= right;
+					d0 <<= left;
 				} else {
 					// 2 source words
 					d1 = FB_READL(src);
 					d1 = fb_rev_pixels_in_long(d1,
 								bswapmask);
-					d0 = d0>>right | d1<<left;
+					d0 = d0 << left | d1 >> right;
 				}
 				d0 = fb_rev_pixels_in_long(d0, bswapmask);
 				FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
@@ -371,9 +380,9 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 	u32 dx = area->dx, dy = area->dy, sx = area->sx, sy = area->sy;
 	u32 height = area->height, width = area->width;
 	unsigned long const bits_per_line = p->fix.line_length*8u;
-	unsigned long __iomem *dst = NULL, *src = NULL;
+	unsigned long __iomem *base = NULL;
 	int bits = BITS_PER_LONG, bytes = bits >> 3;
-	int dst_idx = 0, src_idx = 0, rev_copy = 0;
+	unsigned dst_idx = 0, src_idx = 0, rev_copy = 0;
 	u32 bswapmask = fb_compute_bswapmask(p);
 
 	if (p->state != FBINFO_STATE_RUNNING)
@@ -389,7 +398,7 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 
 	// split the base of the framebuffer into a long-aligned address and the
 	// index of the first bit
-	dst = src = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1));
+	base = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1));
 	dst_idx = src_idx = 8*((unsigned long)p->screen_base & (bytes-1));
 	// add offset of source and target area
 	dst_idx += dy*bits_per_line + dx*p->var.bits_per_pixel;
@@ -402,20 +411,14 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
 		while (height--) {
 			dst_idx -= bits_per_line;
 			src_idx -= bits_per_line;
-			dst += dst_idx >> (ffs(bits) - 1);
-			dst_idx &= (bytes - 1);
-			src += src_idx >> (ffs(bits) - 1);
-			src_idx &= (bytes - 1);
-			bitcpy_rev(p, dst, dst_idx, src, src_idx, bits,
+			bitcpy_rev(p, base + (dst_idx / bits), dst_idx % bits,
+				base + (src_idx / bits), src_idx % bits, bits,
 				width*p->var.bits_per_pixel, bswapmask);
 		}
 	} else {
 		while (height--) {
-			dst += dst_idx >> (ffs(bits) - 1);
-			dst_idx &= (bytes - 1);
-			src += src_idx >> (ffs(bits) - 1);
-			src_idx &= (bytes - 1);
-			bitcpy(p, dst, dst_idx, src, src_idx, bits,
+			bitcpy(p, base + (dst_idx / bits), dst_idx % bits,
+				base + (src_idx / bits), src_idx % bits, bits,
 				width*p->var.bits_per_pixel, bswapmask);
 			dst_idx += bits_per_line;
 			src_idx += bits_per_line;
diff --git a/drivers/video/matrox/matroxfb_accel.c b/drivers/video/matrox/matroxfb_accel.c
index 8335a6fe303e..0d5cb85d071a 100644
--- a/drivers/video/matrox/matroxfb_accel.c
+++ b/drivers/video/matrox/matroxfb_accel.c
@@ -192,10 +192,18 @@ void matrox_cfbX_init(struct matrox_fb_info *minfo)
 	minfo->accel.m_dwg_rect = M_DWG_TRAP | M_DWG_SOLID | M_DWG_ARZERO | M_DWG_SGNZERO | M_DWG_SHIFTZERO;
 	if (isMilleniumII(minfo)) minfo->accel.m_dwg_rect |= M_DWG_TRANSC;
 	minfo->accel.m_opmode = mopmode;
+	minfo->accel.m_access = maccess;
+	minfo->accel.m_pitch = mpitch;
 }
 
 EXPORT_SYMBOL(matrox_cfbX_init);
 
+static void matrox_accel_restore_maccess(struct matrox_fb_info *minfo)
+{
+	mga_outl(M_MACCESS, minfo->accel.m_access);
+	mga_outl(M_PITCH, minfo->accel.m_pitch);
+}
+
 static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 			       int sx, int dy, int dx, int height, int width)
 {
@@ -207,7 +215,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 	CRITBEGIN
 
 	if ((dy < sy) || ((dy == sy) && (dx <= sx))) {
-		mga_fifo(2);
+		mga_fifo(4);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO |
 			 M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_AR5, vxres);
@@ -215,7 +224,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 		start = sy*vxres+sx+curr_ydstorg(minfo);
 		end = start+width;
 	} else {
-		mga_fifo(3);
+		mga_fifo(5);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_SGN, 5);
 		mga_outl(M_AR5, -vxres);
@@ -224,7 +234,8 @@ static void matrox_accel_bmove(struct matrox_fb_info *minfo, int vxres, int sy,
 		start = end+width;
 		dy += height-1;
 	}
-	mga_fifo(4);
+	mga_fifo(6);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_AR0, end);
 	mga_outl(M_AR3, start);
 	mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx);
@@ -246,7 +257,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres,
 	CRITBEGIN
 
 	if ((dy < sy) || ((dy == sy) && (dx <= sx))) {
-		mga_fifo(2);
+		mga_fifo(4);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_SGNZERO |
 			M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_AR5, vxres);
@@ -254,7 +266,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres,
 		start = sy*vxres+sx+curr_ydstorg(minfo);
 		end = start+width;
 	} else {
-		mga_fifo(3);
+		mga_fifo(5);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, M_DWG_BITBLT | M_DWG_SHIFTZERO | M_DWG_BFCOL | M_DWG_REPLACE);
 		mga_outl(M_SGN, 5);
 		mga_outl(M_AR5, -vxres);
@@ -263,7 +276,8 @@ static void matrox_accel_bmove_lin(struct matrox_fb_info *minfo, int vxres,
 		start = end+width;
 		dy += height-1;
 	}
-	mga_fifo(5);
+	mga_fifo(7);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_AR0, end);
 	mga_outl(M_AR3, start);
 	mga_outl(M_FXBNDRY, ((dx+width)<<16) | dx);
@@ -298,7 +312,8 @@ static void matroxfb_accel_clear(struct matrox_fb_info *minfo, u_int32_t color,
 
 	CRITBEGIN
 
-	mga_fifo(5);
+	mga_fifo(7);
+	matrox_accel_restore_maccess(minfo);
 	mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE);
 	mga_outl(M_FCOL, color);
 	mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx);
@@ -341,7 +356,8 @@ static void matroxfb_cfb4_clear(struct matrox_fb_info *minfo, u_int32_t bgx,
 	width >>= 1;
 	sx >>= 1;
 	if (width) {
-		mga_fifo(5);
+		mga_fifo(7);
+		matrox_accel_restore_maccess(minfo);
 		mga_outl(M_DWGCTL, minfo->accel.m_dwg_rect | M_DWG_REPLACE2);
 		mga_outl(M_FCOL, bgx);
 		mga_outl(M_FXBNDRY, ((sx + width) << 16) | sx);
@@ -415,7 +431,8 @@ static void matroxfb_1bpp_imageblit(struct matrox_fb_info *minfo, u_int32_t fgx,
 
 	CRITBEGIN
 
-	mga_fifo(3);
+	mga_fifo(5);
+	matrox_accel_restore_maccess(minfo);
 	if (easy)
 		mga_outl(M_DWGCTL, M_DWG_ILOAD | M_DWG_SGNZERO | M_DWG_SHIFTZERO | M_DWG_BMONOWF | M_DWG_LINEAR | M_DWG_REPLACE);
 	else
@@ -425,7 +442,8 @@ static void matroxfb_1bpp_imageblit(struct matrox_fb_info *minfo, u_int32_t fgx,
 	fxbndry = ((xx + width - 1) << 16) | xx;
 	mmio = minfo->mmio.vbase;
 
-	mga_fifo(6);
+	mga_fifo(8);
+	matrox_accel_restore_maccess(minfo);
 	mga_writel(mmio, M_FXBNDRY, fxbndry);
 	mga_writel(mmio, M_AR0, ar0);
 	mga_writel(mmio, M_AR3, 0);
diff --git a/drivers/video/matrox/matroxfb_base.h b/drivers/video/matrox/matroxfb_base.h
index 11ed57bb704e..556d96ce40bf 100644
--- a/drivers/video/matrox/matroxfb_base.h
+++ b/drivers/video/matrox/matroxfb_base.h
@@ -307,6 +307,8 @@ struct matrox_accel_data {
 #endif
 	u_int32_t	m_dwg_rect;
 	u_int32_t	m_opmode;
+	u_int32_t	m_access;
+	u_int32_t	m_pitch;
 };
 
 struct v4l2_queryctrl;
diff --git a/drivers/video/tgafb.c b/drivers/video/tgafb.c
index 07c7df9ee77b..3d5bce517d8e 100644
--- a/drivers/video/tgafb.c
+++ b/drivers/video/tgafb.c
@@ -182,6 +182,8 @@ tgafb_check_var(struct fb_var_screeninfo *var, struct fb_info *info)
 
 	if (var->xres_virtual != var->xres || var->yres_virtual != var->yres)
 		return -EINVAL;
+	if (var->xres * var->yres * (var->bits_per_pixel >> 3) > info->fix.smem_len)
+		return -EINVAL;
 	if (var->nonstd)
 		return -EINVAL;
 	if (1000000000 / var->pixclock > TGA_PLL_MAX_FREQ)
@@ -262,6 +264,7 @@ tgafb_set_par(struct fb_info *info)
 	par->yres = info->var.yres;
 	par->pll_freq = pll_freq = 1000000000 / info->var.pixclock;
 	par->bits_per_pixel = info->var.bits_per_pixel;
+	info->fix.line_length = par->xres * (par->bits_per_pixel >> 3);
 
 	tga_type = par->tga_type;
 
@@ -1136,222 +1139,57 @@ copyarea_line_32bpp(struct fb_info *info, u32 dy, u32 sy,
 	__raw_writel(TGA_MODE_SBM_24BPP|TGA_MODE_SIMPLE, tga_regs+TGA_MODE_REG);
 }
 
-/* The general case of forward copy in 8bpp mode.  */
+/* The (almost) general case of backward copy in 8bpp mode.  */
 static inline void
-copyarea_foreward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
-		       u32 height, u32 width, u32 line_length)
+copyarea_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
+	      u32 height, u32 width, u32 line_length,
+	      const struct fb_copyarea *area)
 {
 	struct tga_par *par = (struct tga_par *) info->par;
-	unsigned long i, copied, left;
-	unsigned long dpos, spos, dalign, salign, yincr;
-	u32 smask_first, dmask_first, dmask_last;
-	int pixel_shift, need_prime, need_second;
-	unsigned long n64, n32, xincr_first;
+	unsigned i, yincr;
+	int depos, sepos, backward, last_step, step;
+	u32 mask_last;
+	unsigned n32;
 	void __iomem *tga_regs;
 	void __iomem *tga_fb;
 
-	yincr = line_length;
-	if (dy > sy) {
-		dy += height - 1;
-		sy += height - 1;
-		yincr = -yincr;
-	}
-
-	/* Compute the offsets and alignments in the frame buffer.
-	   More than anything else, these control how we do copies.  */
-	dpos = dy * line_length + dx;
-	spos = sy * line_length + sx;
-	dalign = dpos & 7;
-	salign = spos & 7;
-	dpos &= -8;
-	spos &= -8;
-
-	/* Compute the value for the PIXELSHIFT register.  This controls
-	   both non-co-aligned source and destination and copy direction.  */
-	if (dalign >= salign)
-		pixel_shift = dalign - salign;
-	else
-		pixel_shift = 8 - (salign - dalign);
-
-	/* Figure out if we need an additional priming step for the
-	   residue register.  */
-	need_prime = (salign > dalign);
-	if (need_prime)
-		dpos -= 8;
-
-	/* Begin by copying the leading unaligned destination.  Copy enough
-	   to make the next destination address 32-byte aligned.  */
-	copied = 32 - (dalign + (dpos & 31));
-	if (copied == 32)
-		copied = 0;
-	xincr_first = (copied + 7) & -8;
-	smask_first = dmask_first = (1ul << copied) - 1;
-	smask_first <<= salign;
-	dmask_first <<= dalign + need_prime*8;
-	if (need_prime && copied > 24)
-		copied -= 8;
-	left = width - copied;
-
-	/* Care for small copies.  */
-	if (copied > width) {
-		u32 t;
-		t = (1ul << width) - 1;
-		t <<= dalign + need_prime*8;
-		dmask_first &= t;
-		left = 0;
-	}
-
-	/* Attempt to use 64-byte copies.  This is only possible if the
-	   source and destination are co-aligned at 64 bytes.  */
-	n64 = need_second = 0;
-	if ((dpos & 63) == (spos & 63)
-	    && (height == 1 || line_length % 64 == 0)) {
-		/* We may need a 32-byte copy to ensure 64 byte alignment.  */
-		need_second = (dpos + xincr_first) & 63;
-		if ((need_second & 32) != need_second)
-			printk(KERN_ERR "tgafb: need_second wrong\n");
-		if (left >= need_second + 64) {
-			left -= need_second;
-			n64 = left / 64;
-			left %= 64;
-		} else
-			need_second = 0;
-	}
-
-	/* Copy trailing full 32-byte sections.  This will be the main
-	   loop if the 64 byte loop can't be used.  */
-	n32 = left / 32;
-	left %= 32;
-
-	/* Copy the trailing unaligned destination.  */
-	dmask_last = (1ul << left) - 1;
-
-	tga_regs = par->tga_regs_base;
-	tga_fb = par->tga_fb_base;
-
-	/* Set up the MODE and PIXELSHIFT registers.  */
-	__raw_writel(TGA_MODE_SBM_8BPP|TGA_MODE_COPY, tga_regs+TGA_MODE_REG);
-	__raw_writel(pixel_shift, tga_regs+TGA_PIXELSHIFT_REG);
-	wmb();
-
-	for (i = 0; i < height; ++i) {
-		unsigned long j;
-		void __iomem *sfb;
-		void __iomem *dfb;
-
-		sfb = tga_fb + spos;
-		dfb = tga_fb + dpos;
-		if (dmask_first) {
-			__raw_writel(smask_first, sfb);
-			wmb();
-			__raw_writel(dmask_first, dfb);
-			wmb();
-			sfb += xincr_first;
-			dfb += xincr_first;
-		}
-
-		if (need_second) {
-			__raw_writel(0xffffffff, sfb);
-			wmb();
-			__raw_writel(0xffffffff, dfb);
-			wmb();
-			sfb += 32;
-			dfb += 32;
-		}
-
-		if (n64 && (((unsigned long)sfb | (unsigned long)dfb) & 63))
-			printk(KERN_ERR
-			       "tgafb: misaligned copy64 (s:%p, d:%p)\n",
-			       sfb, dfb);
-
-		for (j = 0; j < n64; ++j) {
-			__raw_writel(sfb - tga_fb, tga_regs+TGA_COPY64_SRC);
-			wmb();
-			__raw_writel(dfb - tga_fb, tga_regs+TGA_COPY64_DST);
-			wmb();
-			sfb += 64;
-			dfb += 64;
-		}
-
-		for (j = 0; j < n32; ++j) {
-			__raw_writel(0xffffffff, sfb);
-			wmb();
-			__raw_writel(0xffffffff, dfb);
-			wmb();
-			sfb += 32;
-			dfb += 32;
-		}
-
-		if (dmask_last) {
-			__raw_writel(0xffffffff, sfb);
-			wmb();
-			__raw_writel(dmask_last, dfb);
-			wmb();
-		}
-
-		spos += yincr;
-		dpos += yincr;
+	/* Do acceleration only if we are aligned on 8 pixels */
+	if ((dx | sx | width) & 7) {
+		cfb_copyarea(info, area);
+		return;
 	}
 
-	/* Reset the MODE register to normal.  */
-	__raw_writel(TGA_MODE_SBM_8BPP|TGA_MODE_SIMPLE, tga_regs+TGA_MODE_REG);
-}
-
-/* The (almost) general case of backward copy in 8bpp mode.  */
-static inline void
-copyarea_backward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
-		       u32 height, u32 width, u32 line_length,
-		       const struct fb_copyarea *area)
-{
-	struct tga_par *par = (struct tga_par *) info->par;
-	unsigned long i, left, yincr;
-	unsigned long depos, sepos, dealign, sealign;
-	u32 mask_first, mask_last;
-	unsigned long n32;
-	void __iomem *tga_regs;
-	void __iomem *tga_fb;
-
 	yincr = line_length;
 	if (dy > sy) {
 		dy += height - 1;
 		sy += height - 1;
 		yincr = -yincr;
 	}
+	backward = dy == sy && dx > sx && dx < sx + width;
 
 	/* Compute the offsets and alignments in the frame buffer.
 	   More than anything else, these control how we do copies.  */
-	depos = dy * line_length + dx + width;
-	sepos = sy * line_length + sx + width;
-	dealign = depos & 7;
-	sealign = sepos & 7;
-
-	/* ??? The documentation appears to be incorrect (or very
-	   misleading) wrt how pixel shifting works in backward copy
-	   mode, i.e. when PIXELSHIFT is negative.  I give up for now.
-	   Do handle the common case of co-aligned backward copies,
-	   but frob everything else back on generic code.  */
-	if (dealign != sealign) {
-		cfb_copyarea(info, area);
-		return;
-	}
-
-	/* We begin the copy with the trailing pixels of the
-	   unaligned destination.  */
-	mask_first = (1ul << dealign) - 1;
-	left = width - dealign;
-
-	/* Care for small copies.  */
-	if (dealign > width) {
-		mask_first ^= (1ul << (dealign - width)) - 1;
-		left = 0;
-	}
+	depos = dy * line_length + dx;
+	sepos = sy * line_length + sx;
+	if (backward)
+		depos += width, sepos += width;
 
 	/* Next copy full words at a time.  */
-	n32 = left / 32;
-	left %= 32;
+	n32 = width / 32;
+	last_step = width % 32;
 
 	/* Finally copy the unaligned head of the span.  */
-	mask_last = -1 << (32 - left);
+	mask_last = (1ul << last_step) - 1;
+
+	if (!backward) {
+		step = 32;
+		last_step = 32;
+	} else {
+		step = -32;
+		last_step = -last_step;
+		sepos -= 32;
+		depos -= 32;
+	}
 
 	tga_regs = par->tga_regs_base;
 	tga_fb = par->tga_fb_base;
@@ -1368,25 +1206,33 @@ copyarea_backward_8bpp(struct fb_info *info, u32 dx, u32 dy, u32 sx, u32 sy,
 
 		sfb = tga_fb + sepos;
 		dfb = tga_fb + depos;
-		if (mask_first) {
-			__raw_writel(mask_first, sfb);
-			wmb();
-			__raw_writel(mask_first, dfb);
-			wmb();
-		}
 
-		for (j = 0; j < n32; ++j) {
-			sfb -= 32;
-			dfb -= 32;
+		for (j = 0; j < n32; j++) {
+			if (j < 2 && j + 1 < n32 && !backward &&
+			    !(((unsigned long)sfb | (unsigned long)dfb) & 63)) {
+				do {
+					__raw_writel(sfb - tga_fb, tga_regs+TGA_COPY64_SRC);
+					wmb();
+					__raw_writel(dfb - tga_fb, tga_regs+TGA_COPY64_DST);
+					wmb();
+					sfb += 64;
+					dfb += 64;
+					j += 2;
+				} while (j + 1 < n32);
+				j--;
+				continue;
+			}
 			__raw_writel(0xffffffff, sfb);
 			wmb();
 			__raw_writel(0xffffffff, dfb);
 			wmb();
+			sfb += step;
+			dfb += step;
 		}
 
 		if (mask_last) {
-			sfb -= 32;
-			dfb -= 32;
+			sfb += last_step - step;
+			dfb += last_step - step;
 			__raw_writel(mask_last, sfb);
 			wmb();
 			__raw_writel(mask_last, dfb);
@@ -1447,14 +1293,9 @@ tgafb_copyarea(struct fb_info *info, const struct fb_copyarea *area)
 	else if (bpp == 32)
 		cfb_copyarea(info, area);
 
-	/* Detect overlapping source and destination that requires
-	   a backward copy.  */
-	else if (dy == sy && dx > sx && dx < sx + width)
-		copyarea_backward_8bpp(info, dx, dy, sx, sy, height,
-				       width, line_length, area);
 	else
-		copyarea_foreward_8bpp(info, dx, dy, sx, sy, height,
-				       width, line_length);
+		copyarea_8bpp(info, dx, dy, sx, sy, height,
+			      width, line_length, area);
 }
 
 
@@ -1470,6 +1311,7 @@ tgafb_init_fix(struct fb_info *info)
 	int tga_bus_tc = TGA_BUS_TC(par->dev);
 	u8 tga_type = par->tga_type;
 	const char *tga_type_name = NULL;
+	unsigned memory_size;
 
 	switch (tga_type) {
 	case TGA_TYPE_8PLANE:
@@ -1477,22 +1319,27 @@ tgafb_init_fix(struct fb_info *info)
 			tga_type_name = "Digital ZLXp-E1";
 		if (tga_bus_tc)
 			tga_type_name = "Digital ZLX-E1";
+		memory_size = 2097152;
 		break;
 	case TGA_TYPE_24PLANE:
 		if (tga_bus_pci)
 			tga_type_name = "Digital ZLXp-E2";
 		if (tga_bus_tc)
 			tga_type_name = "Digital ZLX-E2";
+		memory_size = 8388608;
 		break;
 	case TGA_TYPE_24PLUSZ:
 		if (tga_bus_pci)
 			tga_type_name = "Digital ZLXp-E3";
 		if (tga_bus_tc)
 			tga_type_name = "Digital ZLX-E3";
+		memory_size = 16777216;
 		break;
 	}
-	if (!tga_type_name)
+	if (!tga_type_name) {
 		tga_type_name = "Unknown";
+		memory_size = 16777216;
+	}
 
 	strlcpy(info->fix.id, tga_type_name, sizeof(info->fix.id));
 
@@ -1502,9 +1349,8 @@ tgafb_init_fix(struct fb_info *info)
 			    ? FB_VISUAL_PSEUDOCOLOR
 			    : FB_VISUAL_DIRECTCOLOR);
 
-	info->fix.line_length = par->xres * (par->bits_per_pixel >> 3);
 	info->fix.smem_start = (size_t) par->tga_fb_base;
-	info->fix.smem_len = info->fix.line_length * par->yres;
+	info->fix.smem_len = memory_size;
 	info->fix.mmio_start = (size_t) par->tga_regs_base;
 	info->fix.mmio_len = 512;
 
@@ -1628,6 +1474,9 @@ static int tgafb_register(struct device *dev)
 		modedb_tga = &modedb_tc;
 		modedbsize_tga = 1;
 	}
+
+	tgafb_init_fix(info);
+
 	ret = fb_find_mode(&info->var, info,
 			   mode_option ? mode_option : mode_option_tga,
 			   modedb_tga, modedbsize_tga, NULL,
@@ -1645,7 +1494,6 @@ static int tgafb_register(struct device *dev)
 	}
 
 	tgafb_set_par(info);
-	tgafb_init_fix(info);
 
 	if (register_framebuffer(info) < 0) {
 		printk(KERN_ERR "tgafb: Could not register framebuffer\n");
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 34bdabaecbd6..36e7859a31aa 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -310,6 +310,12 @@ static int balloon(void *_vballoon)
 		else if (diff < 0)
 			leak_balloon(vb, -diff);
 		update_balloon_size(vb);
+
+		/*
+		 * For large balloon changes, we could spend a lot of time
+		 * and always have work to do.  Be nice if preempt disabled.
+		 */
+		cond_resched();
 	}
 	return 0;
 }
diff --git a/fs/aio.c b/fs/aio.c
index 062a5f6a1448..12a3de0ee6da 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -52,7 +52,8 @@
 struct aio_ring {
 	unsigned	id;	/* kernel internal index number */
 	unsigned	nr;	/* number of io_events */
-	unsigned	head;
+	unsigned	head;	/* Written to by userland or under ring_lock
+				 * mutex by aio_read_events_ring(). */
 	unsigned	tail;
 
 	unsigned	magic;
@@ -243,6 +244,11 @@ static void aio_free_ring(struct kioctx *ctx)
 {
 	int i;
 
+	/* Disconnect the kiotx from the ring file.  This prevents future
+	 * accesses to the kioctx from page migration.
+	 */
+	put_aio_ring_file(ctx);
+
 	for (i = 0; i < ctx->nr_pages; i++) {
 		struct page *page;
 		pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i,
@@ -254,8 +260,6 @@ static void aio_free_ring(struct kioctx *ctx)
 		put_page(page);
 	}
 
-	put_aio_ring_file(ctx);
-
 	if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) {
 		kfree(ctx->ring_pages);
 		ctx->ring_pages = NULL;
@@ -283,29 +287,38 @@ static int aio_migratepage(struct address_space *mapping, struct page *new,
 {
 	struct kioctx *ctx;
 	unsigned long flags;
+	pgoff_t idx;
 	int rc;
 
 	rc = 0;
 
-	/* Make sure the old page hasn't already been changed */
+	/* mapping->private_lock here protects against the kioctx teardown.  */
 	spin_lock(&mapping->private_lock);
 	ctx = mapping->private_data;
-	if (ctx) {
-		pgoff_t idx;
-		spin_lock_irqsave(&ctx->completion_lock, flags);
-		idx = old->index;
-		if (idx < (pgoff_t)ctx->nr_pages) {
-			if (ctx->ring_pages[idx] != old)
-				rc = -EAGAIN;
-		} else
-			rc = -EINVAL;
-		spin_unlock_irqrestore(&ctx->completion_lock, flags);
+	if (!ctx) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	/* The ring_lock mutex.  The prevents aio_read_events() from writing
+	 * to the ring's head, and prevents page migration from mucking in
+	 * a partially initialized kiotx.
+	 */
+	if (!mutex_trylock(&ctx->ring_lock)) {
+		rc = -EAGAIN;
+		goto out;
+	}
+
+	idx = old->index;
+	if (idx < (pgoff_t)ctx->nr_pages) {
+		/* Make sure the old page hasn't already been changed */
+		if (ctx->ring_pages[idx] != old)
+			rc = -EAGAIN;
 	} else
 		rc = -EINVAL;
-	spin_unlock(&mapping->private_lock);
 
 	if (rc != 0)
-		return rc;
+		goto out_unlock;
 
 	/* Writeback must be complete */
 	BUG_ON(PageWriteback(old));
@@ -314,38 +327,26 @@ static int aio_migratepage(struct address_space *mapping, struct page *new,
 	rc = migrate_page_move_mapping(mapping, new, old, NULL, mode, 1);
 	if (rc != MIGRATEPAGE_SUCCESS) {
 		put_page(new);
-		return rc;
+		goto out_unlock;
 	}
 
-	/* We can potentially race against kioctx teardown here.  Use the
-	 * address_space's private data lock to protect the mapping's
-	 * private_data.
+	/* Take completion_lock to prevent other writes to the ring buffer
+	 * while the old page is copied to the new.  This prevents new
+	 * events from being lost.
 	 */
-	spin_lock(&mapping->private_lock);
-	ctx = mapping->private_data;
-	if (ctx) {
-		pgoff_t idx;
-		spin_lock_irqsave(&ctx->completion_lock, flags);
-		migrate_page_copy(new, old);
-		idx = old->index;
-		if (idx < (pgoff_t)ctx->nr_pages) {
-			/* And only do the move if things haven't changed */
-			if (ctx->ring_pages[idx] == old)
-				ctx->ring_pages[idx] = new;
-			else
-				rc = -EAGAIN;
-		} else
-			rc = -EINVAL;
-		spin_unlock_irqrestore(&ctx->completion_lock, flags);
-	} else
-		rc = -EBUSY;
-	spin_unlock(&mapping->private_lock);
+	spin_lock_irqsave(&ctx->completion_lock, flags);
+	migrate_page_copy(new, old);
+	BUG_ON(ctx->ring_pages[idx] != old);
+	ctx->ring_pages[idx] = new;
+	spin_unlock_irqrestore(&ctx->completion_lock, flags);
 
-	if (rc == MIGRATEPAGE_SUCCESS)
-		put_page(old);
-	else
-		put_page(new);
+	/* The old page is no longer accessible. */
+	put_page(old);
 
+out_unlock:
+	mutex_unlock(&ctx->ring_lock);
+out:
+	spin_unlock(&mapping->private_lock);
 	return rc;
 }
 #endif
@@ -380,7 +381,7 @@ static int aio_setup_ring(struct kioctx *ctx)
 	file = aio_private_file(ctx, nr_pages);
 	if (IS_ERR(file)) {
 		ctx->aio_ring_file = NULL;
-		return -EAGAIN;
+		return -ENOMEM;
 	}
 
 	ctx->aio_ring_file = file;
@@ -415,7 +416,7 @@ static int aio_setup_ring(struct kioctx *ctx)
 
 	if (unlikely(i != nr_pages)) {
 		aio_free_ring(ctx);
-		return -EAGAIN;
+		return -ENOMEM;
 	}
 
 	ctx->mmap_size = nr_pages * PAGE_SIZE;
@@ -429,7 +430,7 @@ static int aio_setup_ring(struct kioctx *ctx)
 	if (IS_ERR((void *)ctx->mmap_base)) {
 		ctx->mmap_size = 0;
 		aio_free_ring(ctx);
-		return -EAGAIN;
+		return -ENOMEM;
 	}
 
 	pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base);
@@ -556,6 +557,10 @@ static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
 					rcu_read_unlock();
 					spin_unlock(&mm->ioctx_lock);
 
+					/* While kioctx setup is in progress,
+					 * we are protected from page migration
+					 * changes ring_pages by ->ring_lock.
+					 */
 					ring = kmap_atomic(ctx->ring_pages[0]);
 					ring->id = ctx->id;
 					kunmap_atomic(ring);
@@ -640,24 +645,28 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 
 	ctx->max_reqs = nr_events;
 
-	if (percpu_ref_init(&ctx->users, free_ioctx_users))
-		goto err;
-
-	if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs))
-		goto err;
-
 	spin_lock_init(&ctx->ctx_lock);
 	spin_lock_init(&ctx->completion_lock);
 	mutex_init(&ctx->ring_lock);
+	/* Protect against page migration throughout kiotx setup by keeping
+	 * the ring_lock mutex held until setup is complete. */
+	mutex_lock(&ctx->ring_lock);
 	init_waitqueue_head(&ctx->wait);
 
 	INIT_LIST_HEAD(&ctx->active_reqs);
 
+	if (percpu_ref_init(&ctx->users, free_ioctx_users))
+		goto err;
+
+	if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs))
+		goto err;
+
 	ctx->cpu = alloc_percpu(struct kioctx_cpu);
 	if (!ctx->cpu)
 		goto err;
 
-	if (aio_setup_ring(ctx) < 0)
+	err = aio_setup_ring(ctx);
+	if (err < 0)
 		goto err;
 
 	atomic_set(&ctx->reqs_available, ctx->nr_events - 1);
@@ -683,6 +692,9 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 	if (err)
 		goto err_cleanup;
 
+	/* Release the ring_lock mutex now that all setup is complete. */
+	mutex_unlock(&ctx->ring_lock);
+
 	pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n",
 		 ctx, ctx->user_id, mm, ctx->nr_events);
 	return ctx;
@@ -692,6 +704,7 @@ err_cleanup:
 err_ctx:
 	aio_free_ring(ctx);
 err:
+	mutex_unlock(&ctx->ring_lock);
 	free_percpu(ctx->cpu);
 	free_percpu(ctx->reqs.pcpu_count);
 	free_percpu(ctx->users.pcpu_count);
@@ -1024,6 +1037,7 @@ static long aio_read_events_ring(struct kioctx *ctx,
 
 	mutex_lock(&ctx->ring_lock);
 
+	/* Access to ->ring_pages here is protected by ctx->ring_lock. */
 	ring = kmap_atomic(ctx->ring_pages[0]);
 	head = ring->head;
 	tail = ring->tail;
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 10d6c41aecad..6bf06a07f3e0 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -235,6 +235,7 @@ out_err:
 	if (warned++ == 0)
 		printk(KERN_WARNING
 			"lockd_up: makesock failed, error=%d\n", err);
+	svc_shutdown_net(serv, net);
 	return err;
 }
 
diff --git a/fs/locks.c b/fs/locks.c
index 92a0f0a52b06..4dd39b98a6a3 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1376,11 +1376,10 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
 
 restart:
 	break_time = flock->fl_break_time;
-	if (break_time != 0) {
+	if (break_time != 0)
 		break_time -= jiffies;
-		if (break_time == 0)
-			break_time++;
-	}
+	if (break_time == 0)
+		break_time++;
 	locks_insert_block(flock, new_fl);
 	spin_unlock(&inode->i_lock);
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index bec6dbe939a0..3fee55e73e5e 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -822,6 +822,7 @@ struct ata_port {
 	unsigned long		qc_allocated;
 	unsigned int		qc_active;
 	int			nr_active_links; /* #links with active qcs */
+	unsigned int		last_tag;	/* track next tag hw expects */
 
 	struct ata_link		link;		/* host default link */
 	struct ata_link		*slave_link;	/* see ata_slave_link_init() */
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 8280a5dd1727..7dd33577b905 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -169,7 +169,7 @@ static int percpu_counter_hotcpu_callback(struct notifier_block *nb,
 	struct percpu_counter *fbc;
 
 	compute_batch_value();
-	if (action != CPU_DEAD)
+	if (action != CPU_DEAD && action != CPU_DEAD_FROZEN)
 		return NOTIFY_OK;
 
 	cpu = (unsigned long)hcpu;
diff --git a/net/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index b703790b4e44..074bb2a5e675 100644
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -292,8 +292,8 @@ static int is_out(const struct crush_map *map,
  * @outpos: our position in that vector
  * @tries: number of attempts to make
  * @recurse_tries: number of attempts to have recursive chooseleaf make
- * @local_tries: localized retries
- * @local_fallback_tries: localized fallback retries
+ * @local_retries: localized retries
+ * @local_fallback_retries: localized fallback retries
  * @recurse_to_leaf: true if we want one device under each item of given type (chooseleaf instead of choose)
  * @out2: second output vector for leaf items (if @recurse_to_leaf)
  */
@@ -304,8 +304,8 @@ static int crush_choose_firstn(const struct crush_map *map,
 			       int *out, int outpos,
 			       unsigned int tries,
 			       unsigned int recurse_tries,
-			       unsigned int local_tries,
-			       unsigned int local_fallback_tries,
+			       unsigned int local_retries,
+			       unsigned int local_fallback_retries,
 			       int recurse_to_leaf,
 			       int *out2)
 {
@@ -344,9 +344,9 @@ static int crush_choose_firstn(const struct crush_map *map,
 					reject = 1;
 					goto reject;
 				}
-				if (local_fallback_tries > 0 &&
+				if (local_fallback_retries > 0 &&
 				    flocal >= (in->size>>1) &&
-				    flocal > local_fallback_tries)
+				    flocal > local_fallback_retries)
 					item = bucket_perm_choose(in, x, r);
 				else
 					item = crush_bucket_choose(in, x, r);
@@ -393,8 +393,8 @@ static int crush_choose_firstn(const struct crush_map *map,
 							 x, outpos+1, 0,
 							 out2, outpos,
 							 recurse_tries, 0,
-							 local_tries,
-							 local_fallback_tries,
+							 local_retries,
+							 local_fallback_retries,
 							 0,
 							 NULL) <= outpos)
 							/* didn't get leaf */
@@ -420,14 +420,14 @@ reject:
 					ftotal++;
 					flocal++;
 
-					if (collide && flocal <= local_tries)
+					if (collide && flocal <= local_retries)
 						/* retry locally a few times */
 						retry_bucket = 1;
-					else if (local_fallback_tries > 0 &&
-						 flocal <= in->size + local_fallback_tries)
+					else if (local_fallback_retries > 0 &&
+						 flocal <= in->size + local_fallback_retries)
 						/* exhaustive bucket search */
 						retry_bucket = 1;
-					else if (ftotal <= tries)
+					else if (ftotal < tries)
 						/* then retry descent */
 						retry_descent = 1;
 					else
@@ -640,10 +640,18 @@ int crush_do_rule(const struct crush_map *map,
 	__u32 step;
 	int i, j;
 	int numrep;
-	int choose_tries = map->choose_total_tries;
-	int choose_local_tries = map->choose_local_tries;
-	int choose_local_fallback_tries = map->choose_local_fallback_tries;
+	/*
+	 * the original choose_total_tries value was off by one (it
+	 * counted "retries" and not "tries").  add one.
+	 */
+	int choose_tries = map->choose_total_tries + 1;
 	int choose_leaf_tries = 0;
+	/*
+	 * the local tries values were counted as "retries", though,
+	 * and need no adjustment
+	 */
+	int choose_local_retries = map->choose_local_tries;
+	int choose_local_fallback_retries = map->choose_local_fallback_tries;
 
 	if ((__u32)ruleno >= map->max_rules) {
 		dprintk(" bad ruleno %d\n", ruleno);
@@ -677,12 +685,12 @@ int crush_do_rule(const struct crush_map *map,
 
 		case CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES:
 			if (curstep->arg1 > 0)
-				choose_local_tries = curstep->arg1;
+				choose_local_retries = curstep->arg1;
 			break;
 
 		case CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES:
 			if (curstep->arg1 > 0)
-				choose_local_fallback_tries = curstep->arg1;
+				choose_local_fallback_retries = curstep->arg1;
 			break;
 
 		case CRUSH_RULE_CHOOSELEAF_FIRSTN:
@@ -734,8 +742,8 @@ int crush_do_rule(const struct crush_map *map,
 						o+osize, j,
 						choose_tries,
 						recurse_tries,
-						choose_local_tries,
-						choose_local_fallback_tries,
+						choose_local_retries,
+						choose_local_fallback_retries,
 						recurse_to_leaf,
 						c+osize);
 				} else {
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 5e44e3179e02..6bd498470138 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1385,6 +1385,7 @@ void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mgd_conn_tx_status(struct ieee80211_sub_if_data *sdata,
 				  __le16 fc, bool acked);
+void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata);
 
 /* IBSS code */
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index d767cfb9b45f..c7a7a86afdb8 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -148,6 +148,8 @@ static u32 ieee80211_hw_conf_chan(struct ieee80211_local *local)
 	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
 		if (!rcu_access_pointer(sdata->vif.chanctx_conf))
 			continue;
+		if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+			continue;
 		power = min(power, sdata->vif.bss_conf.txpower);
 	}
 	rcu_read_unlock();
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 245dce969b31..47059ac44e24 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2708,8 +2708,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata,
 	bss = ieee80211_bss_info_update(local, rx_status, mgmt, len, elems,
 					channel);
 	if (bss) {
-		ieee80211_rx_bss_put(local, bss);
 		sdata->vif.bss_conf.beacon_rate = bss->beacon_rate;
+		ieee80211_rx_bss_put(local, bss);
 	}
 }
 
@@ -3504,6 +3504,32 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata)
 }
 
 #ifdef CONFIG_PM
+void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
+
+	sdata_lock(sdata);
+
+	if (ifmgd->auth_data) {
+		/*
+		 * If we are trying to authenticate while suspending, cfg80211
+		 * won't know and won't actually abort those attempts, thus we
+		 * need to do that ourselves.
+		 */
+		ieee80211_send_deauth_disassoc(sdata,
+					       ifmgd->auth_data->bss->bssid,
+					       IEEE80211_STYPE_DEAUTH,
+					       WLAN_REASON_DEAUTH_LEAVING,
+					       false, frame_buf);
+		ieee80211_destroy_auth_data(sdata, false);
+		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
+				      IEEE80211_DEAUTH_FRAME_LEN);
+	}
+
+	sdata_unlock(sdata);
+}
+
 void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index 0c2a29484c07..6fb38558a5e6 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -355,6 +355,7 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 		struct ieee80211_roc_work *dep;
 
 		/* start this ROC */
+		ieee80211_offchannel_stop_vifs(local);
 
 		/* switch channel etc */
 		ieee80211_recalc_idle(local);
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index af64fb8e8add..d478b880a0af 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -100,10 +100,18 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 
 	/* remove all interfaces that were created in the driver */
 	list_for_each_entry(sdata, &local->interfaces, list) {
-		if (!ieee80211_sdata_running(sdata) ||
-		    sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
-		    sdata->vif.type == NL80211_IFTYPE_MONITOR)
+		if (!ieee80211_sdata_running(sdata))
 			continue;
+		switch (sdata->vif.type) {
+		case NL80211_IFTYPE_AP_VLAN:
+		case NL80211_IFTYPE_MONITOR:
+			continue;
+		case NL80211_IFTYPE_STATION:
+			ieee80211_mgd_quiesce(sdata);
+			break;
+		default:
+			break;
+		}
 
 		drv_remove_interface(local, sdata);
 	}
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 4080c615636f..c14c16a6d62d 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -2909,7 +2909,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw,
 				cpu_to_le16(IEEE80211_FCTL_MOREDATA);
 		}
 
-		if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+		if (sdata->vif.type == NL80211_IFTYPE_AP)
 			sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev);
 		if (!ieee80211_tx_prepare(sdata, &tx, skb))
 			break;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 0edada973434..3ea5cda787c7 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1798,21 +1798,19 @@ call_connect_status(struct rpc_task *task)
 	trace_rpc_connect_status(task, status);
 	task->tk_status = 0;
 	switch (status) {
-		/* if soft mounted, test if we've timed out */
-	case -ETIMEDOUT:
-		task->tk_action = call_timeout;
-		return;
 	case -ECONNREFUSED:
 	case -ECONNRESET:
 	case -ECONNABORTED:
 	case -ENETUNREACH:
 	case -EHOSTUNREACH:
-		/* retry with existing socket, after a delay */
-		rpc_delay(task, 3*HZ);
 		if (RPC_IS_SOFTCONN(task))
 			break;
+		/* retry with existing socket, after a delay */
+		rpc_delay(task, 3*HZ);
 	case -EAGAIN:
-		task->tk_action = call_bind;
+		/* Check for timeouts before looping back to call_bind */
+	case -ETIMEDOUT:
+		task->tk_action = call_timeout;
 		return;
 	case 0:
 		clnt->cl_stats->netreconn++;
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index b9dc6acbba8c..910223782c5c 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -251,7 +251,6 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
 static void dapm_kcontrol_free(struct snd_kcontrol *kctl)
 {
 	struct dapm_kcontrol_data *data = snd_kcontrol_chip(kctl);
-	kfree(data->widget);
 	kfree(data->wlist);
 	kfree(data);
 }
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index bdb71a26ae35..00ea679b3826 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -172,7 +172,7 @@ static void run_test(struct vdev_info *dev, struct vq_info *vq,
 							 GFP_ATOMIC);
 				if (likely(r == 0)) {
 					++started;
-					if (unlikely(!virtqueue_kick(vq->vq))
+					if (unlikely(!virtqueue_kick(vq->vq)))
 						r = -1;
 				}
 			} else
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 8ca405cd7c1a..26954a7d9b03 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -916,6 +916,7 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
 	case 0:
 		if (!target_cpus)
 			return;
+		break;
 
 	case 1:
 		target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff;
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 8631d9c14320..f2c80d5451c3 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -85,7 +85,7 @@ static void async_pf_execute(struct work_struct *work)
 	if (waitqueue_active(&vcpu->wq))
 		wake_up_interruptible(&vcpu->wq);
 
-	mmdrop(mm);
+	mmput(mm);
 	kvm_put_kvm(vcpu->kvm);
 }
 
@@ -98,7 +98,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 				   typeof(*work), queue);
 		list_del(&work->queue);
 		if (cancel_work_sync(&work->work)) {
-			mmdrop(work->mm);
+			mmput(work->mm);
 			kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */
 			kmem_cache_free(async_pf_cache, work);
 		}
@@ -162,7 +162,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 	work->addr = gfn_to_hva(vcpu->kvm, gfn);
 	work->arch = *arch;
 	work->mm = current->mm;
-	atomic_inc(&work->mm->mm_count);
+	atomic_inc(&work->mm->mm_users);
 	kvm_get_kvm(work->vcpu->kvm);
 
 	/* this can't really happen otherwise gfn_to_pfn_async
@@ -180,7 +180,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 	return 1;
 retry_sync:
 	kvm_put_kvm(work->vcpu->kvm);
-	mmdrop(work->mm);
+	mmput(work->mm);
 	kmem_cache_free(async_pf_cache, work);
 	return 0;
 }
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index ce9ed99ad7dc..8c805a071507 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -306,7 +306,7 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq, bool line_status)
 		BUG_ON(ioapic->rtc_status.pending_eoi != 0);
 		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
 				ioapic->rtc_status.dest_map);
-		ioapic->rtc_status.pending_eoi = ret;
+		ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret);
 	} else
 		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
 