loongson-sources/patches/0001-genpatches/base/1001_linux-3.16.2.patch

diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt
index 7ccf933bfbe0..48148d6d9307 100644
--- a/Documentation/sound/alsa/ALSA-Configuration.txt
+++ b/Documentation/sound/alsa/ALSA-Configuration.txt
@@ -2026,8 +2026,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed.
   -------------------
 
     Module for sound cards based on the Asus AV66/AV100/AV200 chips,
-    i.e., Xonar D1, DX, D2, D2X, DS, Essence ST (Deluxe), Essence STX,
-    HDAV1.3 (Deluxe), and HDAV1.3 Slim.
+    i.e., Xonar D1, DX, D2, D2X, DS, DSX, Essence ST (Deluxe),
+    Essence STX (II), HDAV1.3 (Deluxe), and HDAV1.3 Slim.
 
     This module supports autoprobe and multiple cards.
 
diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt
index cbc2f03056bd..aee73e78c7d4 100644
--- a/Documentation/stable_kernel_rules.txt
+++ b/Documentation/stable_kernel_rules.txt
@@ -29,6 +29,9 @@ Rules on what kind of patches are accepted, and which ones are not, into the
 
 Procedure for submitting patches to the -stable tree:
 
+ - If the patch covers files in net/ or drivers/net please follow netdev stable
+   submission guidelines as described in
+   Documentation/networking/netdev-FAQ.txt
  - Send the patch, after verifying that it follows the above rules, to
    stable@vger.kernel.org.  You must note the upstream commit ID in the
    changelog of your submission, as well as the kernel version you wish
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 0fe36497642c..612e6e99d1e5 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1869,7 +1869,8 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_PID	| 64
   PPC   | KVM_REG_PPC_ACOP	| 64
   PPC   | KVM_REG_PPC_VRSAVE	| 32
-  PPC   | KVM_REG_PPC_LPCR	| 64
+  PPC   | KVM_REG_PPC_LPCR	| 32
+  PPC   | KVM_REG_PPC_LPCR_64	| 64
   PPC   | KVM_REG_PPC_PPR	| 64
   PPC   | KVM_REG_PPC_ARCH_COMPAT 32
   PPC   | KVM_REG_PPC_DABRX     | 32
diff --git a/Makefile b/Makefile
index 87663a2d1d10..c2617526e605 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 16
-SUBLEVEL = 1
+SUBLEVEL = 2
 EXTRAVERSION =
 NAME = Museum of Fishiegoodies
 
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index 49fa59622254..c9aee0e799bb 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -168,9 +168,6 @@
 			ti,hwmods = "mailbox";
 			ti,mbox-num-users = <4>;
 			ti,mbox-num-fifos = <8>;
-			ti,mbox-names = "wkup_m3";
-			ti,mbox-data = <0 0 0 0>;
-			status = "disabled";
 		};
 
 		timer1: timer@44e31000 {
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 43876245fc57..21ca0cebcab0 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -15,7 +15,17 @@
 
 #include <uapi/asm/unistd.h>
 
+/*
+ * This may need to be greater than __NR_last_syscall+1 in order to
+ * account for the padding in the syscall table
+ */
 #define __NR_syscalls  (384)
+
+/*
+ * *NOTE*: This is a ghost syscall private to the kernel.  Only the
+ * __kuser_cmpxchg code in entry-armv.S should be aware of its
+ * existence.  Don't ever use this from user code.
+ */
 #define __ARM_NR_cmpxchg		(__ARM_NR_BASE+0x00fff0)
 
 #define __ARCH_WANT_STAT64
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index ba94446c72d9..acd5b66ea3aa 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -411,11 +411,6 @@
 #define __NR_renameat2			(__NR_SYSCALL_BASE+382)
 
 /*
- * This may need to be greater than __NR_last_syscall+1 in order to
- * account for the padding in the syscall table
- */
-
-/*
  * The following SWIs are ARM private.
  */
 #define __ARM_NR_BASE			(__NR_SYSCALL_BASE+0x0f0000)
@@ -426,12 +421,6 @@
 #define __ARM_NR_set_tls		(__ARM_NR_BASE+5)
 
 /*
- * *NOTE*: This is a ghost syscall private to the kernel.  Only the
- * __kuser_cmpxchg code in entry-armv.S should be aware of its
- * existence.  Don't ever use this from user code.
- */
-
-/*
  * The following syscalls are obsolete and no longer available for EABI.
  */
 #if !defined(__KERNEL__)
diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c
index 751f3549bf6f..acadac0992b6 100644
--- a/arch/arm/mach-omap2/control.c
+++ b/arch/arm/mach-omap2/control.c
@@ -314,7 +314,8 @@ void omap3_save_scratchpad_contents(void)
 		scratchpad_contents.public_restore_ptr =
 			virt_to_phys(omap3_restore_3630);
 	else if (omap_rev() != OMAP3430_REV_ES3_0 &&
-					omap_rev() != OMAP3430_REV_ES3_1)
+					omap_rev() != OMAP3430_REV_ES3_1 &&
+					omap_rev() != OMAP3430_REV_ES3_1_2)
 		scratchpad_contents.public_restore_ptr =
 			virt_to_phys(omap3_restore);
 	else
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 6c074f37cdd2..da1b256caccc 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2185,6 +2185,8 @@ static int _enable(struct omap_hwmod *oh)
 			 oh->mux->pads_dynamic))) {
 		omap_hwmod_mux(oh->mux, _HWMOD_STATE_ENABLED);
 		_reconfigure_io_chain();
+	} else if (oh->flags & HWMOD_FORCE_MSTANDBY) {
+		_reconfigure_io_chain();
 	}
 
 	_add_initiator_dep(oh, mpu_oh);
@@ -2291,6 +2293,8 @@ static int _idle(struct omap_hwmod *oh)
 	if (oh->mux && oh->mux->pads_dynamic) {
 		omap_hwmod_mux(oh->mux, _HWMOD_STATE_IDLE);
 		_reconfigure_io_chain();
+	} else if (oh->flags & HWMOD_FORCE_MSTANDBY) {
+		_reconfigure_io_chain();
 	}
 
 	oh->_state = _HWMOD_STATE_IDLE;
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index a5176cf32dad..f2defe1c380c 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -138,19 +138,10 @@ static inline void __flush_icache_all(void)
 #define flush_icache_page(vma,page)	do { } while (0)
 
 /*
- * flush_cache_vmap() is used when creating mappings (eg, via vmap,
- * vmalloc, ioremap etc) in kernel space for pages.  On non-VIPT
- * caches, since the direct-mappings of these pages may contain cached
- * data, we need to do a full cache flush to ensure that writebacks
- * don't corrupt data placed into these pages via the new mappings.
+ * Not required on AArch64 (PIPT or VIPT non-aliasing D-cache).
  */
 static inline void flush_cache_vmap(unsigned long start, unsigned long end)
 {
-	/*
-	 * set_pte_at() called from vmap_pte_range() does not
-	 * have a DSB after cleaning the cache line.
-	 */
-	dsb(ish);
 }
 
 static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index e0ccceb317d9..2a1508cdead0 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -138,6 +138,8 @@ extern struct page *empty_zero_page;
 
 #define pte_valid_user(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
+#define pte_valid_not_user(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
 
 static inline pte_t pte_wrprotect(pte_t pte)
 {
@@ -184,6 +186,15 @@ static inline pte_t pte_mkspecial(pte_t pte)
 static inline void set_pte(pte_t *ptep, pte_t pte)
 {
 	*ptep = pte;
+
+	/*
+	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
+	 * or update_mmu_cache() have the necessary barriers.
+	 */
+	if (pte_valid_not_user(pte)) {
+		dsb(ishst);
+		isb();
+	}
 }
 
 extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
@@ -303,6 +314,7 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
 	*pmdp = pmd;
 	dsb(ishst);
+	isb();
 }
 
 static inline void pmd_clear(pmd_t *pmdp)
@@ -333,6 +345,7 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
 {
 	*pudp = pud;
 	dsb(ishst);
+	isb();
 }
 
 static inline void pud_clear(pud_t *pudp)
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index b9349c4513ea..3796ea6bb734 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -122,6 +122,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
 		asm("tlbi vaae1is, %0" : : "r"(addr));
 	dsb(ish);
+	isb();
 }
 
 /*
@@ -131,8 +132,8 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
 				    unsigned long addr, pte_t *ptep)
 {
 	/*
-	 * set_pte() does not have a DSB, so make sure that the page table
-	 * write is visible.
+	 * set_pte() does not have a DSB for user mappings, so make sure that
+	 * the page table write is visible.
 	 */
 	dsb(ishst);
 }
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index a7fb874b595e..fe5b94078d82 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -315,20 +315,20 @@ static int brk_handler(unsigned long addr, unsigned int esr,
 {
 	siginfo_t info;
 
-	if (call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
-		return 0;
+	if (user_mode(regs)) {
+		info = (siginfo_t) {
+			.si_signo = SIGTRAP,
+			.si_errno = 0,
+			.si_code  = TRAP_BRKPT,
+			.si_addr  = (void __user *)instruction_pointer(regs),
+		};
 
-	if (!user_mode(regs))
+		force_sig_info(SIGTRAP, &info, current);
+	} else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
+		pr_warning("Unexpected kernel BRK exception at EL1\n");
 		return -EFAULT;
+	}
 
-	info = (siginfo_t) {
-		.si_signo = SIGTRAP,
-		.si_errno = 0,
-		.si_code  = TRAP_BRKPT,
-		.si_addr  = (void __user *)instruction_pointer(regs),
-	};
-
-	force_sig_info(SIGTRAP, &info, current);
 	return 0;
 }
 
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 14db1f6e8d7f..c0aead7d1a72 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -464,6 +464,8 @@ static int __init arm64_enter_virtual_mode(void)
 
 	set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 
+	efi.runtime_version = efi.systab->hdr.revision;
+
 	return 0;
 }
 early_initcall(arm64_enter_virtual_mode);
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 736c17a226e9..bf0fc6b16ad9 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -1827,7 +1827,7 @@ dcopuop:
 	case -1:
 
 		if (cpu_has_mips_4_5_r)
-			cbit = fpucondbit[MIPSInst_RT(ir) >> 2];
+			cbit = fpucondbit[MIPSInst_FD(ir) >> 2];
 		else
 			cbit = FPU_CSR_COND;
 		if (rv.w)
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 2bc4a9409a93..de7d426a9b0c 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -548,6 +548,7 @@ struct kvm_get_htab_header {
 
 #define KVM_REG_PPC_VRSAVE	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb4)
 #define KVM_REG_PPC_LPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb5)
+#define KVM_REG_PPC_LPCR_64	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb5)
 #define KVM_REG_PPC_PPR		(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb6)
 
 /* Architecture compatibility level */
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index fbd01eba4473..94802d267022 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -802,53 +802,33 @@ void eeh_pe_restore_bars(struct eeh_pe *pe)
  */
 const char *eeh_pe_loc_get(struct eeh_pe *pe)
 {
-	struct pci_controller *hose;
 	struct pci_bus *bus = eeh_pe_bus_get(pe);
-	struct pci_dev *pdev;
-	struct device_node *dn;
-	const char *loc;
+	struct device_node *dn = pci_bus_to_OF_node(bus);
+	const char *loc = NULL;
 
-	if (!bus)
-		return "N/A";
+	if (!dn)
+		goto out;
 
 	/* PHB PE or root PE ? */
 	if (pci_is_root_bus(bus)) {
-		hose = pci_bus_to_host(bus);
-		loc = of_get_property(hose->dn,
-				"ibm,loc-code", NULL);
-		if (loc)
-			return loc;
-		loc = of_get_property(hose->dn,
-				"ibm,io-base-loc-code", NULL);
+		loc = of_get_property(dn, "ibm,loc-code", NULL);
+		if (!loc)
+			loc = of_get_property(dn, "ibm,io-base-loc-code", NULL);
 		if (loc)
-			return loc;
-
-		pdev = pci_get_slot(bus, 0x0);
-	} else {
-		pdev = bus->self;
-	}
-
-	if (!pdev) {
-		loc = "N/A";
-		goto out;
-	}
+			goto out;
 
-	dn = pci_device_to_OF_node(pdev);
-	if (!dn) {
-		loc = "N/A";
-		goto out;
+		/* Check the root port */
+		dn = dn->child;
+		if (!dn)
+			goto out;
 	}
 
 	loc = of_get_property(dn, "ibm,loc-code", NULL);
 	if (!loc)
 		loc = of_get_property(dn, "ibm,slot-location-code", NULL);
-	if (!loc)
-		loc = "N/A";
 
 out:
-	if (pci_is_root_bus(bus) && pdev)
-		pci_dev_put(pdev);
-	return loc;
+	return loc ? loc : "N/A";
 }
 
 /**
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7a12edbb61e7..0f3a19237444 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -785,7 +785,8 @@ static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr)
+static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr,
+		bool preserve_top32)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	u64 mask;
@@ -820,6 +821,10 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr)
 	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC;
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		mask |= LPCR_AIL;
+
+	/* Broken 32-bit version of LPCR must not clear top bits */
+	if (preserve_top32)
+		mask &= 0xFFFFFFFF;
 	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
 	spin_unlock(&vc->lock);
 }
@@ -939,6 +944,7 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
 		break;
 	case KVM_REG_PPC_LPCR:
+	case KVM_REG_PPC_LPCR_64:
 		*val = get_reg_val(id, vcpu->arch.vcore->lpcr);
 		break;
 	case KVM_REG_PPC_PPR:
@@ -1150,7 +1156,10 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 			ALIGN(set_reg_val(id, *val), 1UL << 24);
 		break;
 	case KVM_REG_PPC_LPCR:
-		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val));
+		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), true);
+		break;
+	case KVM_REG_PPC_LPCR_64:
+		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val), false);
 		break;
 	case KVM_REG_PPC_PPR:
 		vcpu->arch.ppr = set_reg_val(id, *val);
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 8eef1e519077..66b7afec250f 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1233,6 +1233,7 @@ static int kvmppc_get_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
 		*val = get_reg_val(id, to_book3s(vcpu)->hior);
 		break;
 	case KVM_REG_PPC_LPCR:
+	case KVM_REG_PPC_LPCR_64:
 		/*
 		 * We are only interested in the LPCR_ILE bit
 		 */
@@ -1268,6 +1269,7 @@ static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
 		to_book3s(vcpu)->hior_explicit = true;
 		break;
 	case KVM_REG_PPC_LPCR:
+	case KVM_REG_PPC_LPCR_64:
 		kvmppc_set_lpcr_pr(vcpu, set_reg_val(id, *val));
 		break;
 	default:
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index de19edeaa7a7..3136ae2f75af 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -491,6 +491,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
 		set_dma_ops(&pdev->dev, &dma_iommu_ops);
 		set_iommu_table_base(&pdev->dev, &pe->tce32_table);
 	}
+	*pdev->dev.dma_mask = dma_mask;
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 203cbf0dc101..89e23811199c 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -118,10 +118,10 @@ int remove_phb_dynamic(struct pci_controller *phb)
 		}
 	}
 
-	/* Unregister the bridge device from sysfs and remove the PCI bus */
-	device_unregister(b->bridge);
+	/* Remove the PCI bus and unregister the bridge device from sysfs */
 	phb->bus = NULL;
 	pci_remove_bus(b);
+	device_unregister(b->bridge);
 
 	/* Now release the IO resource */
 	if (res->flags & IORESOURCE_IO)
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 37b8241ec784..f90ad8592b36 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -1279,6 +1279,7 @@ static unsigned long page_table_realloc_pmd(struct mmu_gather *tlb,
 {
 	unsigned long next, *table, *new;
 	struct page *page;
+	spinlock_t *ptl;
 	pmd_t *pmd;
 
 	pmd = pmd_offset(pud, addr);
@@ -1296,7 +1297,7 @@ again:
 		if (!new)
 			return -ENOMEM;
 
-		spin_lock(&mm->page_table_lock);
+		ptl = pmd_lock(mm, pmd);
 		if (likely((unsigned long *) pmd_deref(*pmd) == table)) {
 			/* Nuke pmd entry pointing to the "short" page table */
 			pmdp_flush_lazy(mm, addr, pmd);
@@ -1310,7 +1311,7 @@ again:
 			page_table_free_rcu(tlb, table);
 			new = NULL;
 		}
-		spin_unlock(&mm->page_table_lock);
+		spin_unlock(ptl);
 		if (new) {
 			page_table_free_pgste(new);
 			goto again;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d24887b645dc..27adfd902c6f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1537,6 +1537,7 @@ config EFI
 config EFI_STUB
        bool "EFI stub support"
        depends on EFI
+       select RELOCATABLE
        ---help---
           This kernel feature allows a bzImage to be loaded directly
 	  by EFI firmware without the use of a bootloader.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 49205d01b9ad..9f83c171ac18 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -95,7 +95,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
 #define KVM_REFILL_PAGES 25
 #define KVM_MAX_CPUID_ENTRIES 80
 #define KVM_NR_FIXED_MTRR_REGION 88
-#define KVM_NR_VAR_MTRR 10
+#define KVM_NR_VAR_MTRR 8
 
 #define ASYNC_PF_PER_VCPU 64
 
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0ec056012618..aa97a070f09f 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -131,8 +131,13 @@ static inline int pte_exec(pte_t pte)
 
 static inline int pte_special(pte_t pte)
 {
-	return (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_SPECIAL)) ==
-				 (_PAGE_PRESENT|_PAGE_SPECIAL);
+	/*
+	 * See CONFIG_NUMA_BALANCING pte_numa in include/asm-generic/pgtable.h.
+	 * On x86 we have _PAGE_BIT_NUMA == _PAGE_BIT_GLOBAL+1 ==
+	 * __PAGE_BIT_SOFTW1 == _PAGE_BIT_SPECIAL.
+	 */
+	return (pte_flags(pte) & _PAGE_SPECIAL) &&
+		(pte_flags(pte) & (_PAGE_PRESENT|_PAGE_PROTNONE));
 }
 
 static inline unsigned long pte_pfn(pte_t pte)
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 9a316b21df8b..3bdb95ae8c43 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -42,7 +42,7 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
  * cmci_discover_lock protects against parallel discovery attempts
  * which could race against each other.
  */
-static DEFINE_SPINLOCK(cmci_discover_lock);
+static DEFINE_RAW_SPINLOCK(cmci_discover_lock);
 
 #define CMCI_THRESHOLD		1
 #define CMCI_POLL_INTERVAL	(30 * HZ)
@@ -144,14 +144,14 @@ static void cmci_storm_disable_banks(void)
 	int bank;
 	u64 val;
 
-	spin_lock_irqsave(&cmci_discover_lock, flags);
+	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
 	owned = __get_cpu_var(mce_banks_owned);
 	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
 		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
 		val &= ~MCI_CTL2_CMCI_EN;
 		wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
 	}
-	spin_unlock_irqrestore(&cmci_discover_lock, flags);
+	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
 static bool cmci_storm_detect(void)
@@ -211,7 +211,7 @@ static void cmci_discover(int banks)
 	int i;
 	int bios_wrong_thresh = 0;
 
-	spin_lock_irqsave(&cmci_discover_lock, flags);
+	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
 	for (i = 0; i < banks; i++) {
 		u64 val;
 		int bios_zero_thresh = 0;
@@ -266,7 +266,7 @@ static void cmci_discover(int banks)
 			WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
 		}
 	}
-	spin_unlock_irqrestore(&cmci_discover_lock, flags);
+	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 	if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) {
 		pr_info_once(
 			"bios_cmci_threshold: Some banks do not have valid thresholds set\n");
@@ -316,10 +316,10 @@ void cmci_clear(void)
 
 	if (!cmci_supported(&banks))
 		return;
-	spin_lock_irqsave(&cmci_discover_lock, flags);
+	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
 	for (i = 0; i < banks; i++)
 		__cmci_disable_bank(i);
-	spin_unlock_irqrestore(&cmci_discover_lock, flags);
+	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
 static void cmci_rediscover_work_func(void *arg)
@@ -360,9 +360,9 @@ void cmci_disable_bank(int bank)
 	if (!cmci_supported(&banks))
 		return;
 
-	spin_lock_irqsave(&cmci_discover_lock, flags);
+	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
 	__cmci_disable_bank(bank);
-	spin_unlock_irqrestore(&cmci_discover_lock, flags);
+	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
 }
 
 static void intel_init_cmci(void)
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
index 2a26819bb6a8..80eab01c1a68 100644
--- a/arch/x86/kernel/resource.c
+++ b/arch/x86/kernel/resource.c
@@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail)
 
 void arch_remove_reservations(struct resource *avail)
 {
-	/* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */
+	/*
+	 * Trim out BIOS area (high 2MB) and E820 regions. We do not remove
+	 * the low 1MB unconditionally, as this area is needed for some ISA
+	 * cards requiring a memory range, e.g. the i82365 PCMCIA controller.
+	 */
 	if (avail->flags & IORESOURCE_MEM) {
-		if (avail->start < BIOS_END)
-			avail->start = BIOS_END;
 		resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);
 
 		remove_e820_regions(avail);
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index ea5b5709aa76..e1e1e80fc6a6 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -81,10 +81,10 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
 	if (!show_unhandled_signals)
 		return;
 
-	pr_notice_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
-			      level, current->comm, task_pid_nr(current),
-			      message, regs->ip, regs->cs,
-			      regs->sp, regs->ax, regs->si, regs->di);
+	printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+			   level, current->comm, task_pid_nr(current),
+			   message, regs->ip, regs->cs,
+			   regs->sp, regs->ax, regs->si, regs->di);
 }
 
 static int addr_to_vsyscall_nr(unsigned long addr)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e4e833d3d7d7..2d3b8d0efa0f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2017,6 +2017,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 	unsigned long cs;
+	int cpl = ctxt->ops->cpl(ctxt);
 
 	rc = emulate_pop(ctxt, &ctxt->_eip, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
@@ -2026,6 +2027,9 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 	rc = emulate_pop(ctxt, &cs, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
+	/* Outer-privilege level return is not implemented */
+	if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl)
+		return X86EMUL_UNHANDLEABLE;
 	rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS);
 	return rc;
 }
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index bd0da433e6d7..a1ec6a50a05a 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -108,7 +108,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 
 	vector = kvm_cpu_get_extint(v);
 
-	if (kvm_apic_vid_enabled(v->kvm) || vector != -1)
+	if (vector != -1)
 		return vector;			/* PIC */
 
 	return kvm_get_apic_interrupt(v);	/* APIC */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 006911858174..453e5fbbb7ae 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -352,25 +352,46 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic)
 
 static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
 {
-	apic->irr_pending = false;
+	struct kvm_vcpu *vcpu;
+
+	vcpu = apic->vcpu;
+
 	apic_clear_vector(vec, apic->regs + APIC_IRR);
-	if (apic_search_irr(apic) != -1)
-		apic->irr_pending = true;
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		/* try to update RVI */
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+	else {
+		vec = apic_search_irr(apic);
+		apic->irr_pending = (vec != -1);
+	}
 }
 
 static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 {
-	/* Note that we never get here with APIC virtualization enabled.  */
+	struct kvm_vcpu *vcpu;
+
+	if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
+		return;
+
+	vcpu = apic->vcpu;
 
-	if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
-		++apic->isr_count;
-	BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
 	/*
-	 * ISR (in service register) bit is set when injecting an interrupt.
-	 * The highest vector is injected. Thus the latest bit set matches
-	 * the highest bit in ISR.
+	 * With APIC virtualization enabled, all caching is disabled
+	 * because the processor can modify ISR under the hood.  Instead
+	 * just set SVI.
 	 */
-	apic->highest_isr_cache = vec;
+	if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+		kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec);
+	else {
+		++apic->isr_count;
+		BUG_ON(apic->isr_count > MAX_APIC_VECTOR);
+		/*
+		 * ISR (in service register) bit is set when injecting an interrupt.
+		 * The highest vector is injected. Thus the latest bit set matches
+		 * the highest bit in ISR.
+		 */
+		apic->highest_isr_cache = vec;
+	}
 }
 
 static inline int apic_find_highest_isr(struct kvm_lapic *apic)
@@ -1627,11 +1648,16 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 	int vector = kvm_apic_has_interrupt(vcpu);
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	/* Note that we never get here with APIC virtualization enabled.  */
-
 	if (vector == -1)
 		return -1;
 
+	/*
+	 * We get here even with APIC virtualization enabled, if doing
+	 * nested virtualization and L1 runs with the "acknowledge interrupt
+	 * on exit" mode.  Then we cannot inject the interrupt via RVI,
+	 * because the process would deliver it through the IDT.
+	 */
+
 	apic_set_isr(vector, apic);
 	apic_update_ppr(apic);
 	apic_clear_irr(vector, apic);
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index a19ed92e74e4..2ae525e0d8ba 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -162,6 +162,10 @@ pcibios_align_resource(void *data, const struct resource *res,
 			return start;
 		if (start & 0x300)
 			start = (start + 0x3ff) & ~0x3ff;
+	} else if (res->flags & IORESOURCE_MEM) {
+		/* The low 1MB range is reserved for ISA cards */
+		if (start < BIOS_END)
+			start = BIOS_END;
 	}
 	return start;
 }
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index ebfa9b2c871d..767c9cbb869f 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -168,6 +168,7 @@ static int __init xlated_setup_gnttab_pages(void)
 {
 	struct page **pages;
 	xen_pfn_t *pfns;
+	void *vaddr;
 	int rc;
 	unsigned int i;
 	unsigned long nr_grant_frames = gnttab_max_grant_frames();
@@ -193,21 +194,20 @@ static int __init xlated_setup_gnttab_pages(void)
 	for (i = 0; i < nr_grant_frames; i++)
 		pfns[i] = page_to_pfn(pages[i]);
 
-	rc = arch_gnttab_map_shared(pfns, nr_grant_frames, nr_grant_frames,
-				    &xen_auto_xlat_grant_frames.vaddr);
-
-	if (rc) {
+	vaddr = vmap(pages, nr_grant_frames, 0, PAGE_KERNEL);
+	if (!vaddr) {
 		pr_warn("%s Couldn't map %ld pfns rc:%d\n", __func__,
 			nr_grant_frames, rc);
 		free_xenballooned_pages(nr_grant_frames, pages);
 		kfree(pages);
 		kfree(pfns);
-		return rc;
+		return -ENOMEM;
 	}
 	kfree(pages);
 
 	xen_auto_xlat_grant_frames.pfn = pfns;
 	xen_auto_xlat_grant_frames.count = nr_grant_frames;
+	xen_auto_xlat_grant_frames.vaddr = vaddr;
 
 	return 0;
 }
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 7b78f88c1707..5718b0b58b60 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -444,7 +444,7 @@ void xen_setup_timer(int cpu)
 
 	irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt,
 				      IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER|
-				      IRQF_FORCE_RESUME,
+				      IRQF_FORCE_RESUME|IRQF_EARLY_RESUME,
 				      name, NULL);
 	(void)xen_set_irq_priority(irq, XEN_IRQ_PRIORITY_MAX);
 
diff --git a/drivers/char/tpm/tpm_i2c_stm_st33.c b/drivers/char/tpm/tpm_i2c_stm_st33.c
index 3b7bf2162898..4669e3713428 100644
--- a/drivers/char/tpm/tpm_i2c_stm_st33.c
+++ b/drivers/char/tpm/tpm_i2c_stm_st33.c
@@ -714,6 +714,7 @@ tpm_st33_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	}
 
 	tpm_get_timeouts(chip);
+	tpm_do_selftest(chip);
 
 	dev_info(chip->dev, "TPM I2C Initialized\n");
 	return 0;
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index a999f537228f..92105f3dc8e0 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -190,7 +190,7 @@ static void add_session_id(struct cryp_ctx *ctx)
 static irqreturn_t cryp_interrupt_handler(int irq, void *param)
 {
 	struct cryp_ctx *ctx;
-	int i;
+	int count;
 	struct cryp_device_data *device_data;
 
 	if (param == NULL) {
@@ -215,12 +215,11 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param)
 	if (cryp_pending_irq_src(device_data,
 				 CRYP_IRQ_SRC_OUTPUT_FIFO)) {
 		if (ctx->outlen / ctx->blocksize > 0) {
-			for (i = 0; i < ctx->blocksize / 4; i++) {
-				*(ctx->outdata) = readl_relaxed(
-						&device_data->base->dout);
-				ctx->outdata += 4;
-				ctx->outlen -= 4;
-			}
+			count = ctx->blocksize / 4;
+
+			readsl(&device_data->base->dout, ctx->outdata, count);
+			ctx->outdata += count;
+			ctx->outlen -= count;
 
 			if (ctx->outlen == 0) {
 				cryp_disable_irq_src(device_data,
@@ -230,12 +229,12 @@ static irqreturn_t cryp_interrupt_handler(int irq, void *param)
 	} else if (cryp_pending_irq_src(device_data,
 					CRYP_IRQ_SRC_INPUT_FIFO)) {
 		if (ctx->datalen / ctx->blocksize > 0) {
-			for (i = 0 ; i < ctx->blocksize / 4; i++) {
-				writel_relaxed(ctx->indata,
-						&device_data->base->din);
-				ctx->indata += 4;
-				ctx->datalen -= 4;
-			}
+			count = ctx->blocksize / 4;
+
+			writesl(&device_data->base->din, ctx->indata, count);
+
+			ctx->indata += count;
+			ctx->datalen -= count;
 
 			if (ctx->datalen == 0)
 				cryp_disable_irq_src(device_data,
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index f926b4caf449..56c60552abba 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -199,7 +199,7 @@ static struct dmm_txn *dmm_txn_init(struct dmm *dmm, struct tcm *tcm)
 static void dmm_txn_append(struct dmm_txn *txn, struct pat_area *area,
 		struct page **pages, uint32_t npages, uint32_t roll)
 {
-	dma_addr_t pat_pa = 0;
+	dma_addr_t pat_pa = 0, data_pa = 0;
 	uint32_t *data;
 	struct pat *pat;
 	struct refill_engine *engine = txn->engine_handle;
@@ -223,7 +223,9 @@ static void dmm_txn_append(struct dmm_txn *txn, struct pat_area *area,
 			.lut_id = engine->tcm->lut_id,
 		};
 
-	data = alloc_dma(txn, 4*i, &pat->data_pa);
+	data = alloc_dma(txn, 4*i, &data_pa);
+	/* FIXME: what if data_pa is more than 32-bit ? */
+	pat->data_pa = data_pa;
 
 	while (i--) {
 		int n = i + roll;
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 95dbce286a41..d9f5e5241af4 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -791,7 +791,7 @@ int omap_gem_get_paddr(struct drm_gem_object *obj,
 			omap_obj->paddr = tiler_ssptr(block);
 			omap_obj->block = block;
 
-			DBG("got paddr: %08x", omap_obj->paddr);
+			DBG("got paddr: %pad", &omap_obj->paddr);
 		}
 
 		omap_obj->paddr_cnt++;
@@ -985,9 +985,9 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 
 	off = drm_vma_node_start(&obj->vma_node);
 
-	seq_printf(m, "%08x: %2d (%2d) %08llx %08Zx (%2d) %p %4d",
+	seq_printf(m, "%08x: %2d (%2d) %08llx %pad (%2d) %p %4d",
 			omap_obj->flags, obj->name, obj->refcount.refcount.counter,
-			off, omap_obj->paddr, omap_obj->paddr_cnt,
+			off, &omap_obj->paddr, omap_obj->paddr_cnt,
 			omap_obj->vaddr, omap_obj->roll);
 
 	if (omap_obj->flags & OMAP_BO_TILED) {
@@ -1467,8 +1467,8 @@ void omap_gem_init(struct drm_device *dev)
 			entry->paddr = tiler_ssptr(block);
 			entry->block = block;
 
-			DBG("%d:%d: %dx%d: paddr=%08x stride=%d", i, j, w, h,
-					entry->paddr,
+			DBG("%d:%d: %dx%d: paddr=%pad stride=%d", i, j, w, h,
+					&entry->paddr,
 					usergart[i].stride_pfn << PAGE_SHIFT);
 		}
 	}
diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c
index 3cf31ee59aac..6af3398b5278 100644
--- a/drivers/gpu/drm/omapdrm/omap_plane.c
+++ b/drivers/gpu/drm/omapdrm/omap_plane.c
@@ -142,8 +142,8 @@ static void omap_plane_pre_apply(struct omap_drm_apply *apply)
 	DBG("%dx%d -> %dx%d (%d)", info->width, info->height,
 			info->out_width, info->out_height,
 			info->screen_width);
-	DBG("%d,%d %08x %08x", info->pos_x, info->pos_y,
-			info->paddr, info->p_uv_addr);
+	DBG("%d,%d %pad %pad", info->pos_x, info->pos_y,
+			&info->paddr, &info->p_uv_addr);
 
 	/* TODO: */
 	ilace = false;
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index c0ea66192fe0..767f2cc44bd8 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -3320,6 +3320,7 @@ static void cik_gpu_init(struct radeon_device *rdev)
 			   (rdev->pdev->device == 0x130B) ||
 			   (rdev->pdev->device == 0x130E) ||
 			   (rdev->pdev->device == 0x1315) ||
+			   (rdev->pdev->device == 0x1318) ||
 			   (rdev->pdev->device == 0x131B)) {
 			rdev->config.cik.max_cu_per_sh = 4;
 			rdev->config.cik.max_backends_per_se = 1;
diff --git a/drivers/hid/hid-cherry.c b/drivers/hid/hid-cherry.c
index 1bdcccc54a1d..f745d2c1325e 100644
--- a/drivers/hid/hid-cherry.c
+++ b/drivers/hid/hid-cherry.c
@@ -28,7 +28,7 @@
 static __u8 *ch_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	if (*rsize >= 17 && rdesc[11] == 0x3c && rdesc[12] == 0x02) {
+	if (*rsize >= 18 && rdesc[11] == 0x3c && rdesc[12] == 0x02) {
 		hid_info(hdev, "fixing up Cherry Cymotion report descriptor\n");
 		rdesc[11] = rdesc[16] = 0xff;
 		rdesc[12] = rdesc[17] = 0x03;
diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c
index e77696367591..b92bf01a1ae8 100644
--- a/drivers/hid/hid-kye.c
+++ b/drivers/hid/hid-kye.c
@@ -300,7 +300,7 @@ static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		 *   - change the button usage range to 4-7 for the extra
 		 *     buttons
 		 */
-		if (*rsize >= 74 &&
+		if (*rsize >= 75 &&
 			rdesc[61] == 0x05 && rdesc[62] == 0x08 &&
 			rdesc[63] == 0x19 && rdesc[64] == 0x08 &&
 			rdesc[65] == 0x29 && rdesc[66] == 0x0f &&
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index a976f48263f6..f91ff145db9a 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -345,14 +345,14 @@ static __u8 *lg_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	struct usb_device_descriptor *udesc;
 	__u16 bcdDevice, rev_maj, rev_min;
 
-	if ((drv_data->quirks & LG_RDESC) && *rsize >= 90 && rdesc[83] == 0x26 &&
+	if ((drv_data->quirks & LG_RDESC) && *rsize >= 91 && rdesc[83] == 0x26 &&
 			rdesc[84] == 0x8c && rdesc[85] == 0x02) {
 		hid_info(hdev,
 			 "fixing up Logitech keyboard report descriptor\n");
 		rdesc[84] = rdesc[89] = 0x4d;
 		rdesc[85] = rdesc[90] = 0x10;
 	}
-	if ((drv_data->quirks & LG_RDESC_REL_ABS) && *rsize >= 50 &&
+	if ((drv_data->quirks & LG_RDESC_REL_ABS) && *rsize >= 51 &&
 			rdesc[32] == 0x81 && rdesc[33] == 0x06 &&
 			rdesc[49] == 0x81 && rdesc[50] == 0x06) {
 		hid_info(hdev,
diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c
index 486dbde2ba2d..b7ba82960c79 100644
--- a/drivers/hid/hid-logitech-dj.c
+++ b/drivers/hid/hid-logitech-dj.c
@@ -238,13 +238,6 @@ static void logi_dj_recv_add_djhid_device(struct dj_receiver_dev *djrcv_dev,
 		return;
 	}
 
-	if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) ||
-	    (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) {
-		dev_err(&djrcv_hdev->dev, "%s: invalid device index:%d\n",
-			__func__, dj_report->device_index);
-		return;
-	}
-
 	if (djrcv_dev->paired_dj_devices[dj_report->device_index]) {
 		/* The device is already known. No need to reallocate it. */
 		dbg_hid("%s: device is already known\n", __func__);
@@ -557,7 +550,7 @@ static int logi_dj_ll_raw_request(struct hid_device *hid,
 	if (!out_buf)
 		return -ENOMEM;
 
-	if (count < DJREPORT_SHORT_LENGTH - 2)
+	if (count > DJREPORT_SHORT_LENGTH - 2)
 		count = DJREPORT_SHORT_LENGTH - 2;
 
 	out_buf[0] = REPORT_ID_DJ_SHORT;
@@ -690,6 +683,12 @@ static int logi_dj_raw_event(struct hid_device *hdev,
 	 * device (via hid_input_report() ) and return 1 so hid-core does not do
 	 * anything else with it.
 	 */
+	if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) ||
+	    (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) {
+		dev_err(&hdev->dev, "%s: invalid device index:%d\n",
+				__func__, dj_report->device_index);
+		return false;
+	}
 
 	spin_lock_irqsave(&djrcv_dev->lock, flags);
 	if (dj_report->report_id == REPORT_ID_DJ_SHORT) {
diff --git a/drivers/hid/hid-monterey.c b/drivers/hid/hid-monterey.c
index 9e14c00eb1b6..25daf28b26bd 100644
--- a/drivers/hid/hid-monterey.c
+++ b/drivers/hid/hid-monterey.c
@@ -24,7 +24,7 @@
 static __u8 *mr_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	if (*rsize >= 30 && rdesc[29] == 0x05 && rdesc[30] == 0x09) {
+	if (*rsize >= 31 && rdesc[29] == 0x05 && rdesc[30] == 0x09) {
 		hid_info(hdev, "fixing up button/consumer in HID report descriptor\n");
 		rdesc[30] = 0x0c;
 	}
diff --git a/drivers/hid/hid-petalynx.c b/drivers/hid/hid-petalynx.c
index 736b2502df4f..6aca4f2554bf 100644
--- a/drivers/hid/hid-petalynx.c
+++ b/drivers/hid/hid-petalynx.c
@@ -25,7 +25,7 @@
 static __u8 *pl_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	if (*rsize >= 60 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 &&
+	if (*rsize >= 62 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 &&
 			rdesc[41] == 0x00 && rdesc[59] == 0x26 &&
 			rdesc[60] == 0xf9 && rdesc[61] == 0x00) {
 		hid_info(hdev, "fixing up Petalynx Maxter Remote report descriptor\n");
diff --git a/drivers/hid/hid-sunplus.c b/drivers/hid/hid-sunplus.c
index 87fc91e1c8de..91072fa54663 100644
--- a/drivers/hid/hid-sunplus.c
+++ b/drivers/hid/hid-sunplus.c
@@ -24,7 +24,7 @@
 static __u8 *sp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	if (*rsize >= 107 && rdesc[104] == 0x26 && rdesc[105] == 0x80 &&
+	if (*rsize >= 112 && rdesc[104] == 0x26 && rdesc[105] == 0x80 &&
 			rdesc[106] == 0x03) {
 		hid_info(hdev, "fixing up Sunplus Wireless Desktop report descriptor\n");
 		rdesc[105] = rdesc[110] = 0x03;
diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c
index 7f9dc2f86b63..126516414c11 100644
--- a/drivers/hwmon/ads1015.c
+++ b/drivers/hwmon/ads1015.c
@@ -198,7 +198,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
 		}
 
 		channel = be32_to_cpup(property);
-		if (channel > ADS1015_CHANNELS) {
+		if (channel >= ADS1015_CHANNELS) {
 			dev_err(&client->dev,
 				"invalid channel index %d on %s\n",
 				channel, node->full_name);
@@ -212,6 +212,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
 				dev_err(&client->dev,
 					"invalid gain on %s\n",
 					node->full_name);
+				return -EINVAL;
 			}
 		}
 
@@ -222,6 +223,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client)
 				dev_err(&client->dev,
 					"invalid data_rate on %s\n",
 					node->full_name);
+				return -EINVAL;
 			}
 		}
 
diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c
index 9f2be3dd28f3..8a67ec6279a4 100644
--- a/drivers/hwmon/amc6821.c
+++ b/drivers/hwmon/amc6821.c
@@ -360,11 +360,13 @@ static ssize_t set_pwm1_enable(
 	if (config)
 		return config;
 
+	mutex_lock(&data->update_lock);
 	config = i2c_smbus_read_byte_data(client, AMC6821_REG_CONF1);
 	if (config < 0) {
 			dev_err(&client->dev,
 			"Error reading configuration register, aborting.\n");
-			return config;
+			count = config;
+			goto unlock;
 	}
 
 	switch (val) {
@@ -381,14 +383,15 @@ static ssize_t set_pwm1_enable(
 		config |= AMC6821_CONF1_FDRC1;
 		break;
 	default:
-		return -EINVAL;
+		count = -EINVAL;
+		goto unlock;
 	}
-	mutex_lock(&data->update_lock);
 	if (i2c_smbus_write_byte_data(client, AMC6821_REG_CONF1, config)) {
 			dev_err(&client->dev,
 			"Configuration register write error, aborting.\n");
 			count = -EIO;
 	}
+unlock:
 	mutex_unlock(&data->update_lock);
 	return count;
 }
@@ -493,8 +496,9 @@ static ssize_t set_temp_auto_point_temp(
 		return -EINVAL;
 	}
 
-	data->valid = 0;
 	mutex_lock(&data->update_lock);
+	data->valid = 0;
+
 	switch (ix) {
 	case 0:
 		ptemp[0] = clamp_val(val / 1000, 0,
@@ -658,13 +662,14 @@ static ssize_t set_fan1_div(
 	if (config)
 		return config;
 
+	mutex_lock(&data->update_lock);
 	config = i2c_smbus_read_byte_data(client, AMC6821_REG_CONF4);
 	if (config < 0) {
 		dev_err(&client->dev,
 			"Error reading configuration register, aborting.\n");
-		return config;
+		count = config;
+		goto EXIT;
 	}
-	mutex_lock(&data->update_lock);
 	switch (val) {
 	case 2:
 		config &= ~AMC6821_CONF4_PSPR;
diff --git a/drivers/hwmon/dme1737.c b/drivers/hwmon/dme1737.c
index 4ae3fff13f44..bea0a344fab5 100644
--- a/drivers/hwmon/dme1737.c
+++ b/drivers/hwmon/dme1737.c
@@ -247,8 +247,8 @@ struct dme1737_data {
 	u8  pwm_acz[3];
 	u8  pwm_freq[6];
 	u8  pwm_rr[2];
-	u8  zone_low[3];
-	u8  zone_abs[3];
+	s8  zone_low[3];
+	s8  zone_abs[3];
 	u8  zone_hyst[2];
 	u32 alarms;
 };
@@ -277,7 +277,7 @@ static inline int IN_FROM_REG(int reg, int nominal, int res)
 	return (reg * nominal + (3 << (res - 3))) / (3 << (res - 2));
 }
 
-static inline int IN_TO_REG(int val, int nominal)
+static inline int IN_TO_REG(long val, int nominal)
 {
 	return clamp_val((val * 192 + nominal / 2) / nominal, 0, 255);
 }
@@ -293,7 +293,7 @@ static inline int TEMP_FROM_REG(int reg, int res)
 	return (reg * 1000) >> (res - 8);
 }
 
-static inline int TEMP_TO_REG(int val)
+static inline int TEMP_TO_REG(long val)
 {
 	return clamp_val((val < 0 ? val - 500 : val + 500) / 1000, -128, 127);
 }
@@ -308,7 +308,7 @@ static inline int TEMP_RANGE_FROM_REG(int reg)
 	return TEMP_RANGE[(reg >> 4) & 0x0f];
 }
 
-static int TEMP_RANGE_TO_REG(int val, int reg)
+static int TEMP_RANGE_TO_REG(long val, int reg)
 {
 	int i;
 
@@ -331,7 +331,7 @@ static inline int TEMP_HYST_FROM_REG(int reg, int ix)
 	return (((ix == 1) ? reg : reg >> 4) & 0x0f) * 1000;
 }
 
-static inline int TEMP_HYST_TO_REG(int val, int ix, int reg)
+static inline int TEMP_HYST_TO_REG(long val, int ix, int reg)
 {
 	int hyst = clamp_val((val + 500) / 1000, 0, 15);
 
@@ -347,7 +347,7 @@ static inline int FAN_FROM_REG(int reg, int tpc)
 		return (reg == 0 || reg == 0xffff) ? 0 : 90000 * 60 / reg;
 }
 
-static inline int FAN_TO_REG(int val, int tpc)
+static inline int FAN_TO_REG(long val, int tpc)
 {
 	if (tpc) {
 		return clamp_val(val / tpc, 0, 0xffff);
@@ -379,7 +379,7 @@ static inline int FAN_TYPE_FROM_REG(int reg)
 	return (edge > 0) ? 1 << (edge - 1) : 0;
 }
 
-static inline int FAN_TYPE_TO_REG(int val, int reg)
+static inline int FAN_TYPE_TO_REG(long val, int reg)
 {
 	int edge = (val == 4) ? 3 : val;
 
@@ -402,7 +402,7 @@ static int FAN_MAX_FROM_REG(int reg)
 	return 1000 + i * 500;
 }
 
-static int FAN_MAX_TO_REG(int val)
+static int FAN_MAX_TO_REG(long val)
 {
 	int i;
 
@@ -460,7 +460,7 @@ static inline int PWM_ACZ_FROM_REG(int reg)
 	return acz[(reg >> 5) & 0x07];
 }
 
-static inline int PWM_ACZ_TO_REG(int val, int reg)
+static inline int PWM_ACZ_TO_REG(long val, int reg)
 {
 	int acz = (val == 4) ? 2 : val - 1;
 
@@ -476,7 +476,7 @@ static inline int PWM_FREQ_FROM_REG(int reg)
 	return PWM_FREQ[reg & 0x0f];
 }
 
-static int PWM_FREQ_TO_REG(int val, int reg)
+static int PWM_FREQ_TO_REG(long val, int reg)
 {
 	int i;
 
@@ -510,7 +510,7 @@ static inline int PWM_RR_FROM_REG(int reg, int ix)
 	return (rr & 0x08) ? PWM_RR[rr & 0x07] : 0;
 }
 
-static int PWM_RR_TO_REG(int val, int ix, int reg)
+static int PWM_RR_TO_REG(long val, int ix, int reg)
 {
 	int i;
 
@@ -528,7 +528,7 @@ static inline int PWM_RR_EN_FROM_REG(int reg, int ix)
 	return PWM_RR_FROM_REG(reg, ix) ? 1 : 0;
 }
 
-static inline int PWM_RR_EN_TO_REG(int val, int ix, int reg)
+static inline int PWM_RR_EN_TO_REG(long val, int ix, int reg)
 {
 	int en = (ix == 1) ? 0x80 : 0x08;
 
@@ -1481,13 +1481,16 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
 		       const char *buf, size_t count)
 {
 	struct dme1737_data *data = dev_get_drvdata(dev);
-	long val;
+	unsigned long val;
 	int err;
 
-	err = kstrtol(buf, 10, &val);
+	err = kstrtoul(buf, 10, &val);
 	if (err)
 		return err;
 
+	if (val > 255)
+		return -EINVAL;
+
 	data->vrm = val;
 	return count;
 }
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index 2566c43dd1e9..d10aa7b46cca 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -173,7 +173,7 @@ static int get_fan_speed_index(struct gpio_fan_data *fan_data)
 	return -ENODEV;
 }
 
-static int rpm_to_speed_index(struct gpio_fan_data *fan_data, int rpm)
+static int rpm_to_speed_index(struct gpio_fan_data *fan_data, unsigned long rpm)
 {
 	struct gpio_fan_speed *speed = fan_data->speed;
 	int i;
diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c
index 9efadfc851bc..c1eb464f0fd0 100644
--- a/drivers/hwmon/lm78.c
+++ b/drivers/hwmon/lm78.c
@@ -108,7 +108,7 @@ static inline int FAN_FROM_REG(u8 val, int div)
  * TEMP: mC (-128C to +127C)
  * REG: 1C/bit, two's complement
  */
-static inline s8 TEMP_TO_REG(int val)
+static inline s8 TEMP_TO_REG(long val)
 {
 	int nval = clamp_val(val, -128000, 127000) ;
 	return nval < 0 ? (nval - 500) / 1000 : (nval + 500) / 1000;
diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c
index b0129a54e1a6..ef627ea71cc8 100644
--- a/drivers/hwmon/lm85.c
+++ b/drivers/hwmon/lm85.c
@@ -155,7 +155,7 @@ static inline u16 FAN_TO_REG(unsigned long val)
 
 /* Temperature is reported in .001 degC increments */
 #define TEMP_TO_REG(val)	\
-		clamp_val(SCALE(val, 1000, 1), -127, 127)
+		DIV_ROUND_CLOSEST(clamp_val((val), -127000, 127000), 1000)
 #define TEMPEXT_FROM_REG(val, ext)	\
 		SCALE(((val) << 4) + (ext), 16, 1000)
 #define TEMP_FROM_REG(val)	((val) * 1000)
@@ -189,7 +189,7 @@ static const int lm85_range_map[] = {
 	13300, 16000, 20000, 26600, 32000, 40000, 53300, 80000
 };
 
-static int RANGE_TO_REG(int range)
+static int RANGE_TO_REG(long range)
 {
 	int i;
 
@@ -211,7 +211,7 @@ static const int adm1027_freq_map[8] = { /* 1 Hz */
 	11, 15, 22, 29, 35, 44, 59, 88
 };
 
-static int FREQ_TO_REG(const int *map, int freq)
+static int FREQ_TO_REG(const int *map, unsigned long freq)
 {
 	int i;
 
@@ -460,6 +460,9 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
 	if (err)
 		return err;
 
+	if (val > 255)
+		return -EINVAL;
+
 	data->vrm = val;
 	return count;
 }
diff --git a/drivers/hwmon/lm92.c b/drivers/hwmon/lm92.c
index d2060e245ff5..cfaf70b9cba7 100644
--- a/drivers/hwmon/lm92.c
+++ b/drivers/hwmon/lm92.c
@@ -74,12 +74,9 @@ static inline int TEMP_FROM_REG(s16 reg)
 	return reg / 8 * 625 / 10;
 }
 
-static inline s16 TEMP_TO_REG(int val)
+static inline s16 TEMP_TO_REG(long val)
 {
-	if (val <= -60000)
-		return -60000 * 10 / 625 * 8;
-	if (val >= 160000)
-		return 160000 * 10 / 625 * 8;
+	val = clamp_val(val, -60000, 160000);
 	return val * 10 / 625 * 8;
 }
 
@@ -206,10 +203,12 @@ static ssize_t set_temp_hyst(struct device *dev,
 	if (err)
 		return err;
 
+	val = clamp_val(val, -120000, 220000);
 	mutex_lock(&data->update_lock);
-	data->temp[t_hyst] = TEMP_FROM_REG(data->temp[attr->index]) - val;
+	 data->temp[t_hyst] =
+		TEMP_TO_REG(TEMP_FROM_REG(data->temp[attr->index]) - val);
 	i2c_smbus_write_word_swapped(client, LM92_REG_TEMP_HYST,
-				     TEMP_TO_REG(data->temp[t_hyst]));
+				     data->temp[t_hyst]);
 	mutex_unlock(&data->update_lock);
 	return count;
 }
diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c
index 3532026e25da..bf1d7893d51c 100644
--- a/drivers/hwmon/sis5595.c
+++ b/drivers/hwmon/sis5595.c
@@ -159,7 +159,7 @@ static inline int TEMP_FROM_REG(s8 val)
 {
 	return val * 830 + 52120;
 }
-static inline s8 TEMP_TO_REG(int val)
+static inline s8 TEMP_TO_REG(long val)
 {
 	int nval = clamp_val(val, -54120, 157530) ;
 	return nval < 0 ? (nval - 5212 - 415) / 830 : (nval - 5212 + 415) / 830;
diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c
index e95f9ba96790..83c989382be9 100644
--- a/drivers/i2c/busses/i2c-at91.c
+++ b/drivers/i2c/busses/i2c-at91.c
@@ -210,7 +210,7 @@ static void at91_twi_write_data_dma_callback(void *data)
 	struct at91_twi_dev *dev = (struct at91_twi_dev *)data;
 
 	dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg),
-			 dev->buf_len, DMA_MEM_TO_DEV);
+			 dev->buf_len, DMA_TO_DEVICE);
 
 	at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP);
 }
@@ -289,7 +289,7 @@ static void at91_twi_read_data_dma_callback(void *data)
 	struct at91_twi_dev *dev = (struct at91_twi_dev *)data;
 
 	dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg),
-			 dev->buf_len, DMA_DEV_TO_MEM);
+			 dev->buf_len, DMA_FROM_DEVICE);
 
 	/* The last two bytes have to be read without using dma */
 	dev->buf += dev->buf_len - 2;
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c
index a9791509966a..69e11853e8bf 100644
--- a/drivers/i2c/busses/i2c-rk3x.c
+++ b/drivers/i2c/busses/i2c-rk3x.c
@@ -399,7 +399,7 @@ static irqreturn_t rk3x_i2c_irq(int irqno, void *dev_id)
 	}
 
 	/* is there anything left to handle? */
-	if (unlikely(ipd == 0))
+	if (unlikely((ipd & REG_INT_ALL) == 0))
 		goto out;
 
 	switch (i2c->state) {
diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c
index 59d20c599b16..2da05c0e113d 100644
--- a/drivers/misc/mei/client.c
+++ b/drivers/misc/mei/client.c
@@ -459,7 +459,7 @@ int mei_cl_disconnect(struct mei_cl *cl)
 {
 	struct mei_device *dev;
 	struct mei_cl_cb *cb;
-	int rets, err;
+	int rets;
 
 	if (WARN_ON(!cl || !cl->dev))
 		return -ENODEV;
@@ -491,6 +491,7 @@ int mei_cl_disconnect(struct mei_cl *cl)
 			cl_err(dev, cl, "failed to disconnect.\n");
 			goto free;
 		}
+		cl->timer_count = MEI_CONNECT_TIMEOUT;
 		mdelay(10); /* Wait for hardware disconnection ready */
 		list_add_tail(&cb->list, &dev->ctrl_rd_list.list);
 	} else {
@@ -500,23 +501,18 @@ int mei_cl_disconnect(struct mei_cl *cl)
 	}
 	mutex_unlock(&dev->device_lock);
 
-	err = wait_event_timeout(dev->wait_recvd_msg,
+	wait_event_timeout(dev->wait_recvd_msg,
 			MEI_FILE_DISCONNECTED == cl->state,
 			mei_secs_to_jiffies(MEI_CL_CONNECT_TIMEOUT));
 
 	mutex_lock(&dev->device_lock);
+
 	if (MEI_FILE_DISCONNECTED == cl->state) {
 		rets = 0;
 		cl_dbg(dev, cl, "successfully disconnected from FW client.\n");
 	} else {
-		rets = -ENODEV;
-		if (MEI_FILE_DISCONNECTED != cl->state)
-			cl_err(dev, cl, "wrong status client disconnect.\n");
-
-		if (err)
-			cl_dbg(dev, cl, "wait failed disconnect err=%d\n", err);
-
-		cl_err(dev, cl, "failed to disconnect from FW client.\n");
+		cl_dbg(dev, cl, "timeout on disconnect from FW client.\n");
+		rets = -ETIME;
 	}
 
 	mei_io_list_flush(&dev->ctrl_rd_list, cl);
@@ -605,6 +601,7 @@ int mei_cl_connect(struct mei_cl *cl, struct file *file)
 		cl->timer_count = MEI_CONNECT_TIMEOUT;
 		list_add_tail(&cb->list, &dev->ctrl_rd_list.list);
 	} else {
+		cl->state = MEI_FILE_INITIALIZING;
 		list_add_tail(&cb->list, &dev->ctrl_wr_list.list);
 	}
 
@@ -616,6 +613,7 @@ int mei_cl_connect(struct mei_cl *cl, struct file *file)
 	mutex_lock(&dev->device_lock);
 
 	if (cl->state != MEI_FILE_CONNECTED) {
+		cl->state = MEI_FILE_DISCONNECTED;
 		/* something went really wrong */
 		if (!cl->status)
 			cl->status = -EFAULT;
diff --git a/drivers/misc/mei/nfc.c b/drivers/misc/mei/nfc.c
index 3095fc514a65..5ccc23bc7690 100644
--- a/drivers/misc/mei/nfc.c
+++ b/drivers/misc/mei/nfc.c
@@ -342,9 +342,10 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length)
 	ndev = (struct mei_nfc_dev *) cldev->priv_data;
 	dev = ndev->cl->dev;
 
+	err = -ENOMEM;
 	mei_buf = kzalloc(length + MEI_NFC_HEADER_SIZE, GFP_KERNEL);
 	if (!mei_buf)
-		return -ENOMEM;
+		goto out;
 
 	hdr = (struct mei_nfc_hci_hdr *) mei_buf;
 	hdr->cmd = MEI_NFC_CMD_HCI_SEND;
@@ -354,12 +355,9 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length)
 	hdr->data_size = length;
 
 	memcpy(mei_buf + MEI_NFC_HEADER_SIZE, buf, length);
-
 	err = __mei_cl_send(ndev->cl, mei_buf, length + MEI_NFC_HEADER_SIZE);
 	if (err < 0)
-		return err;
-
-	kfree(mei_buf);
+		goto out;
 
 	if (!wait_event_interruptible_timeout(ndev->send_wq,
 				ndev->recv_req_id == ndev->req_id, HZ)) {
@@ -368,7 +366,8 @@ static int mei_nfc_send(struct mei_cl_device *cldev, u8 *buf, size_t length)
 	} else {
 		ndev->req_id++;
 	}
-
+out:
+	kfree(mei_buf);
 	return err;
 }
 
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 1b46c64a649f..4b821b4360e1 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -369,7 +369,7 @@ static int mei_me_pm_runtime_idle(struct device *device)
 	if (!dev)
 		return -ENODEV;
 	if (mei_write_is_idle(dev))
-		pm_schedule_suspend(device, MEI_ME_RPM_TIMEOUT * 2);
+		pm_runtime_autosuspend(device);
 
 	return -EBUSY;
 }
diff --git a/drivers/misc/mei/pci-txe.c b/drivers/misc/mei/pci-txe.c
index 2343c6236df9..32fef4d5b0b6 100644
--- a/drivers/misc/mei/pci-txe.c
+++ b/drivers/misc/mei/pci-txe.c
@@ -306,7 +306,7 @@ static int mei_txe_pm_runtime_idle(struct device *device)
 	if (!dev)
 		return -ENODEV;
 	if (mei_write_is_idle(dev))
-		pm_schedule_suspend(device, MEI_TXI_RPM_TIMEOUT * 2);
+		pm_runtime_autosuspend(device);
 
 	return -EBUSY;
 }
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 7ad463e9741c..249ab80cbb45 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -834,6 +834,10 @@ static void
 mmci_data_irq(struct mmci_host *host, struct mmc_data *data,
 	      unsigned int status)
 {
+	/* Make sure we have data to handle */
+	if (!data)
+		return;
+
 	/* First check for errors */
 	if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_STARTBITERR|
 		      MCI_TXUNDERRUN|MCI_RXOVERRUN)) {
@@ -902,9 +906,17 @@ mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd,
 	     unsigned int status)
 {
 	void __iomem *base = host->base;
-	bool sbc = (cmd == host->mrq->sbc);
-	bool busy_resp = host->variant->busy_detect &&
-			(cmd->flags & MMC_RSP_BUSY);
+	bool sbc, busy_resp;
+
+	if (!cmd)
+		return;
+
+	sbc = (cmd == host->mrq->sbc);
+	busy_resp = host->variant->busy_detect && (cmd->flags & MMC_RSP_BUSY);
+
+	if (!((status|host->busy_status) & (MCI_CMDCRCFAIL|MCI_CMDTIMEOUT|
+		MCI_CMDSENT|MCI_CMDRESPEND)))
+		return;
 
 	/* Check if we need to wait for busy completion. */
 	if (host->busy_status && (status & MCI_ST_CARDBUSY))
@@ -1132,9 +1144,6 @@ static irqreturn_t mmci_irq(int irq, void *dev_id)
 	spin_lock(&host->lock);
 
 	do {
-		struct mmc_command *cmd;
-		struct mmc_data *data;
-
 		status = readl(host->base + MMCISTATUS);
 
 		if (host->singleirq) {
@@ -1154,16 +1163,8 @@ static irqreturn_t mmci_irq(int irq, void *dev_id)
 
 		dev_dbg(mmc_dev(host->mmc), "irq0 (data+cmd) %08x\n", status);
 
-		cmd = host->cmd;
-		if ((status|host->busy_status) & (MCI_CMDCRCFAIL|MCI_CMDTIMEOUT|
-			MCI_CMDSENT|MCI_CMDRESPEND) && cmd)
-			mmci_cmd_irq(host, cmd, status);
-
-		data = host->data;
-		if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_STARTBITERR|
-			      MCI_TXUNDERRUN|MCI_RXOVERRUN|MCI_DATAEND|
-			      MCI_DATABLOCKEND) && data)
-			mmci_data_irq(host, data, status);
+		mmci_cmd_irq(host, host->cmd, status);
+		mmci_data_irq(host, host->data, status);
 
 		/* Don't poll for busy completion in irq context. */
 		if (host->busy_status)
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 42914e04d110..056841651a80 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -794,7 +794,7 @@ struct controller *pcie_init(struct pcie_device *dev)
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA,
 		PCI_EXP_SLTSTA_ABP | PCI_EXP_SLTSTA_PFD |
 		PCI_EXP_SLTSTA_MRLSC | PCI_EXP_SLTSTA_PDC |
-		PCI_EXP_SLTSTA_CC);
+		PCI_EXP_SLTSTA_CC | PCI_EXP_SLTSTA_DLLSC);
 
 	/* Disable software notification */
 	pcie_disable_notification(ctrl);
diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c
index a3fbe2012ea3..2ab1b47c7651 100644
--- a/drivers/pci/pci-label.c
+++ b/drivers/pci/pci-label.c
@@ -161,8 +161,8 @@ enum acpi_attr_enum {
 static void dsm_label_utf16s_to_utf8s(union acpi_object *obj, char *buf)
 {
 	int len;
-	len = utf16s_to_utf8s((const wchar_t *)obj->string.pointer,
-			      obj->string.length,
+	len = utf16s_to_utf8s((const wchar_t *)obj->buffer.pointer,
+			      obj->buffer.length,
 			      UTF16_LITTLE_ENDIAN,
 			      buf, PAGE_SIZE);
 	buf[len] = '\n';
@@ -187,16 +187,22 @@ static int dsm_get_label(struct device *dev, char *buf,
 	tmp = obj->package.elements;
 	if (obj->type == ACPI_TYPE_PACKAGE && obj->package.count == 2 &&
 	    tmp[0].type == ACPI_TYPE_INTEGER &&
-	    tmp[1].type == ACPI_TYPE_STRING) {
+	    (tmp[1].type == ACPI_TYPE_STRING ||
+	     tmp[1].type == ACPI_TYPE_BUFFER)) {
 		/*
 		 * The second string element is optional even when
 		 * this _DSM is implemented; when not implemented,
 		 * this entry must return a null string.
 		 */
-		if (attr == ACPI_ATTR_INDEX_SHOW)
+		if (attr == ACPI_ATTR_INDEX_SHOW) {
 			scnprintf(buf, PAGE_SIZE, "%llu\n", tmp->integer.value);
-		else if (attr == ACPI_ATTR_LABEL_SHOW)
-			dsm_label_utf16s_to_utf8s(tmp + 1, buf);
+		} else if (attr == ACPI_ATTR_LABEL_SHOW) {
+			if (tmp[1].type == ACPI_TYPE_STRING)
+				scnprintf(buf, PAGE_SIZE, "%s\n",
+					  tmp[1].string.pointer);
+			else if (tmp[1].type == ACPI_TYPE_BUFFER)
+				dsm_label_utf16s_to_utf8s(tmp + 1, buf);
+		}
 		len = strlen(buf) > 0 ? strlen(buf) : -1;
 	}
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 1c8592b0e146..81d49d3ab221 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -839,12 +839,6 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 
 	if (!__pci_complete_power_transition(dev, state))
 		error = 0;
-	/*
-	 * When aspm_policy is "powersave" this call ensures
-	 * that ASPM is configured.
-	 */
-	if (!error && dev->bus->self)
-		pcie_aspm_powersave_config_link(dev->bus->self);
 
 	return error;
 }
@@ -1195,12 +1189,18 @@ int __weak pcibios_enable_device(struct pci_dev *dev, int bars)
 static int do_pci_enable_device(struct pci_dev *dev, int bars)
 {
 	int err;
+	struct pci_dev *bridge;
 	u16 cmd;
 	u8 pin;
 
 	err = pci_set_power_state(dev, PCI_D0);
 	if (err < 0 && err != -EIO)
 		return err;
+
+	bridge = pci_upstream_bridge(dev);
+	if (bridge)
+		pcie_aspm_powersave_config_link(bridge);
+
 	err = pcibios_enable_device(dev, bars);
 	if (err < 0)
 		return err;
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index caed1ce6facd..481c4e18693a 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -320,9 +320,11 @@ int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsiz
 			resource_size_t min_align)
 {
 	struct resource *res = dev->resource + resno;
+	unsigned long flags;
 	resource_size_t new_size;
 	int ret;
 
+	flags = res->flags;
 	res->flags |= IORESOURCE_UNSET;
 	if (!res->parent) {
 		dev_info(&dev->dev, "BAR %d: can't reassign an unassigned resource %pR\n",
@@ -339,7 +341,12 @@ int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsiz
 		dev_info(&dev->dev, "BAR %d: reassigned %pR\n", resno, res);
 		if (resno < PCI_BRIDGE_RESOURCES)
 			pci_update_resource(dev, resno);
+	} else {
+		res->flags = flags;
+		dev_info(&dev->dev, "BAR %d: %pR (failed to expand by %#llx)\n",
+			 resno, res, (unsigned long long) addsize);
 	}
+
 	return ret;
 }
 
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 31184b35370f..489e83b6b5e1 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -5092,7 +5092,7 @@ static int hpsa_big_passthru_ioctl(struct ctlr_info *h, void __user *argp)
 		}
 		if (ioc->Request.Type.Direction & XFER_WRITE) {
 			if (copy_from_user(buff[sg_used], data_ptr, sz)) {
-				status = -ENOMEM;
+				status = -EFAULT;
 				goto cleanup1;
 			}
 		} else
@@ -6365,9 +6365,9 @@ static inline void hpsa_set_driver_support_bits(struct ctlr_info *h)
 {
 	u32 driver_support;
 
-#ifdef CONFIG_X86
-	/* Need to enable prefetch in the SCSI core for 6400 in x86 */
 	driver_support = readl(&(h->cfgtable->driver_support));
+	/* Need to enable prefetch in the SCSI core for 6400 in x86 */
+#ifdef CONFIG_X86
 	driver_support |= ENABLE_SCSI_PREFETCH;
 #endif
 	driver_support |= ENABLE_UNIT_ATTN;
diff --git a/drivers/staging/et131x/et131x.c b/drivers/staging/et131x/et131x.c
index 08356b6955a4..2d36eac6889c 100644
--- a/drivers/staging/et131x/et131x.c
+++ b/drivers/staging/et131x/et131x.c
@@ -1423,22 +1423,16 @@ static int et131x_mii_read(struct et131x_adapter *adapter, u8 reg, u16 *value)
  * @reg: the register to read
  * @value: 16-bit value to write
  */
-static int et131x_mii_write(struct et131x_adapter *adapter, u8 reg, u16 value)
+static int et131x_mii_write(struct et131x_adapter *adapter, u8 addr, u8 reg,
+			    u16 value)
 {
 	struct mac_regs __iomem *mac = &adapter->regs->mac;
-	struct phy_device *phydev = adapter->phydev;
 	int status = 0;
-	u8 addr;
 	u32 delay = 0;
 	u32 mii_addr;
 	u32 mii_cmd;
 	u32 mii_indicator;
 
-	if (!phydev)
-		return -EIO;
-
-	addr = phydev->addr;
-
 	/* Save a local copy of the registers we are dealing with so we can
 	 * set them back
 	 */
@@ -1633,17 +1627,7 @@ static int et131x_mdio_write(struct mii_bus *bus, int phy_addr,
 	struct net_device *netdev = bus->priv;
 	struct et131x_adapter *adapter = netdev_priv(netdev);
 
-	return et131x_mii_write(adapter, reg, value);
-}
-
-static int et131x_mdio_reset(struct mii_bus *bus)
-{
-	struct net_device *netdev = bus->priv;
-	struct et131x_adapter *adapter = netdev_priv(netdev);
-
-	et131x_mii_write(adapter, MII_BMCR, BMCR_RESET);
-
-	return 0;
+	return et131x_mii_write(adapter, phy_addr, reg, value);
 }
 
 /*	et1310_phy_power_switch	-	PHY power control
@@ -1658,18 +1642,20 @@ static int et131x_mdio_reset(struct mii_bus *bus)
 static void et1310_phy_power_switch(struct et131x_adapter *adapter, bool down)
 {
 	u16 data;
+	struct  phy_device *phydev = adapter->phydev;
 
 	et131x_mii_read(adapter, MII_BMCR, &data);
 	data &= ~BMCR_PDOWN;
 	if (down)
 		data |= BMCR_PDOWN;
-	et131x_mii_write(adapter, MII_BMCR, data);
+	et131x_mii_write(adapter, phydev->addr, MII_BMCR, data);
 }
 
 /* et131x_xcvr_init - Init the phy if we are setting it into force mode */
 static void et131x_xcvr_init(struct et131x_adapter *adapter)
 {
 	u16 lcr2;
+	struct  phy_device *phydev = adapter->phydev;
 
 	/* Set the LED behavior such that LED 1 indicates speed (off =
 	 * 10Mbits, blink = 100Mbits, on = 1000Mbits) and LED 2 indicates
@@ -1690,7 +1676,7 @@ static void et131x_xcvr_init(struct et131x_adapter *adapter)
 		else
 			lcr2 |= (LED_VAL_LINKON << LED_TXRX_SHIFT);
 
-		et131x_mii_write(adapter, PHY_LED_2, lcr2);
+		et131x_mii_write(adapter, phydev->addr, PHY_LED_2, lcr2);
 	}
 }
 
@@ -3645,14 +3631,14 @@ static void et131x_adjust_link(struct net_device *netdev)
 
 			et131x_mii_read(adapter, PHY_MPHY_CONTROL_REG,
 					 &register18);
-			et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG,
-					 register18 | 0x4);
-			et131x_mii_write(adapter, PHY_INDEX_REG,
+			et131x_mii_write(adapter, phydev->addr,
+					 PHY_MPHY_CONTROL_REG, register18 | 0x4);
+			et131x_mii_write(adapter, phydev->addr, PHY_INDEX_REG,
 					 register18 | 0x8402);
-			et131x_mii_write(adapter, PHY_DATA_REG,
+			et131x_mii_write(adapter, phydev->addr, PHY_DATA_REG,
 					 register18 | 511);
-			et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG,
-					 register18);
+			et131x_mii_write(adapter, phydev->addr,
+					 PHY_MPHY_CONTROL_REG, register18);
 		}
 
 		et1310_config_flow_control(adapter);
@@ -3664,7 +3650,8 @@ static void et131x_adjust_link(struct net_device *netdev)
 			et131x_mii_read(adapter, PHY_CONFIG, &reg);
 			reg &= ~ET_PHY_CONFIG_TX_FIFO_DEPTH;
 			reg |= ET_PHY_CONFIG_FIFO_DEPTH_32;
-			et131x_mii_write(adapter, PHY_CONFIG, reg);
+			et131x_mii_write(adapter, phydev->addr, PHY_CONFIG,
+					 reg);
 		}
 
 		et131x_set_rx_dma_timer(adapter);
@@ -3677,14 +3664,14 @@ static void et131x_adjust_link(struct net_device *netdev)
 
 			et131x_mii_read(adapter, PHY_MPHY_CONTROL_REG,
 					 &register18);
-			et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG,
-					 register18 | 0x4);
-			et131x_mii_write(adapter, PHY_INDEX_REG,
-					 register18 | 0x8402);
-			et131x_mii_write(adapter, PHY_DATA_REG,
-					 register18 | 511);
-			et131x_mii_write(adapter, PHY_MPHY_CONTROL_REG,
-					 register18);
+			et131x_mii_write(adapter, phydev->addr,
+					PHY_MPHY_CONTROL_REG, register18 | 0x4);
+			et131x_mii_write(adapter, phydev->addr,
+					PHY_INDEX_REG, register18 | 0x8402);
+			et131x_mii_write(adapter, phydev->addr,
+					PHY_DATA_REG, register18 | 511);
+			et131x_mii_write(adapter, phydev->addr,
+					PHY_MPHY_CONTROL_REG, register18);
 		}
 
 		/* Free the packets being actively sent & stopped */
@@ -4646,10 +4633,6 @@ static int et131x_pci_setup(struct pci_dev *pdev,
 	/* Copy address into the net_device struct */
 	memcpy(netdev->dev_addr, adapter->addr, ETH_ALEN);
 
-	/* Init variable for counting how long we do not have link status */
-	adapter->boot_coma = 0;
-	et1310_disable_phy_coma(adapter);
-
 	rc = -ENOMEM;
 
 	/* Setup the mii_bus struct */
@@ -4665,7 +4648,6 @@ static int et131x_pci_setup(struct pci_dev *pdev,
 	adapter->mii_bus->priv = netdev;
 	adapter->mii_bus->read = et131x_mdio_read;
 	adapter->mii_bus->write = et131x_mdio_write;
-	adapter->mii_bus->reset = et131x_mdio_reset;
 	adapter->mii_bus->irq = kmalloc_array(PHY_MAX_ADDR, sizeof(int),
 					      GFP_KERNEL);
 	if (!adapter->mii_bus->irq)
@@ -4689,6 +4671,10 @@ static int et131x_pci_setup(struct pci_dev *pdev,
 	/* Setup et1310 as per the documentation */
 	et131x_adapter_setup(adapter);
 
+	/* Init variable for counting how long we do not have link status */
+	adapter->boot_coma = 0;
+	et1310_disable_phy_coma(adapter);
+
 	/* We can enable interrupts now
 	 *
 	 *  NOTE - Because registration of interrupt handler is done in the
diff --git a/drivers/staging/lustre/lustre/obdclass/class_obd.c b/drivers/staging/lustre/lustre/obdclass/class_obd.c
index dde04b767a6d..b16687625c44 100644
--- a/drivers/staging/lustre/lustre/obdclass/class_obd.c
+++ b/drivers/staging/lustre/lustre/obdclass/class_obd.c
@@ -35,7 +35,7 @@
  */
 
 #define DEBUG_SUBSYSTEM S_CLASS
-# include <asm/atomic.h>
+# include <linux/atomic.h>
 
 #include <obd_support.h>
 #include <obd_class.h>
diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
index 7526b989dcbf..c4273cd5f7ed 100644
--- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c
+++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c
@@ -54,9 +54,11 @@ static struct usb_device_id rtw_usb_id_tbl[] = {
 	{USB_DEVICE(USB_VENDER_ID_REALTEK, 0x0179)}, /* 8188ETV */
 	/*=== Customer ID ===*/
 	/****** 8188EUS ********/
+	{USB_DEVICE(0x056e, 0x4008)}, /* Elecom WDC-150SU2M */
 	{USB_DEVICE(0x07b8, 0x8179)}, /* Abocom - Abocom */
 	{USB_DEVICE(0x2001, 0x330F)}, /* DLink DWA-125 REV D1 */
 	{USB_DEVICE(0x2001, 0x3310)}, /* Dlink DWA-123 REV D1 */
+	{USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */
 	{}	/* Terminating entry */
 };
 
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index fbf6c5ad222f..ef2fb367d179 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -243,6 +243,9 @@ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state)
 		/*
 		 * Turn off DTR and RTS early.
 		 */
+		if (uart_console(uport) && tty)
+			uport->cons->cflag = tty->termios.c_cflag;
+
 		if (!tty || (tty->termios.c_cflag & HUPCL))
 			uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS);
 
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 257876ea03a1..0b59731c3021 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -1509,7 +1509,7 @@ static int proc_do_submiturb(struct usb_dev_state *ps, struct usbdevfs_urb *uurb
 	u = (is_in ? URB_DIR_IN : URB_DIR_OUT);
 	if (uurb->flags & USBDEVFS_URB_ISO_ASAP)
 		u |= URB_ISO_ASAP;
-	if (uurb->flags & USBDEVFS_URB_SHORT_NOT_OK)
+	if (uurb->flags & USBDEVFS_URB_SHORT_NOT_OK && is_in)
 		u |= URB_SHORT_NOT_OK;
 	if (uurb->flags & USBDEVFS_URB_NO_FSBR)
 		u |= URB_NO_FSBR;
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 0e950ad8cb25..27f217107ef1 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1728,8 +1728,14 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id)
 	 * - Change autosuspend delay of hub can avoid unnecessary auto
 	 *   suspend timer for hub, also may decrease power consumption
 	 *   of USB bus.
+	 *
+	 * - If user has indicated to prevent autosuspend by passing
+	 *   usbcore.autosuspend = -1 then keep autosuspend disabled.
 	 */
-	pm_runtime_set_autosuspend_delay(&hdev->dev, 0);
+#ifdef CONFIG_PM_RUNTIME
+	if (hdev->dev.power.autosuspend_delay >= 0)
+		pm_runtime_set_autosuspend_delay(&hdev->dev, 0);
+#endif
 
 	/*
 	 * Hubs have proper suspend/resume support, except for root hubs
@@ -3264,6 +3270,43 @@ static int finish_port_resume(struct usb_device *udev)
 }
 
 /*
+ * There are some SS USB devices which take longer time for link training.
+ * XHCI specs 4.19.4 says that when Link training is successful, port
+ * sets CSC bit to 1. So if SW reads port status before successful link
+ * training, then it will not find device to be present.
+ * USB Analyzer log with such buggy devices show that in some cases
+ * device switch on the RX termination after long delay of host enabling
+ * the VBUS. In few other cases it has been seen that device fails to
+ * negotiate link training in first attempt. It has been
+ * reported till now that few devices take as long as 2000 ms to train
+ * the link after host enabling its VBUS and termination. Following
+ * routine implements a 2000 ms timeout for link training. If in a case
+ * link trains before timeout, loop will exit earlier.
+ *
+ * FIXME: If a device was connected before suspend, but was removed
+ * while system was asleep, then the loop in the following routine will
+ * only exit at timeout.
+ *
+ * This routine should only be called when persist is enabled for a SS
+ * device.
+ */
+static int wait_for_ss_port_enable(struct usb_device *udev,
+		struct usb_hub *hub, int *port1,
+		u16 *portchange, u16 *portstatus)
+{
+	int status = 0, delay_ms = 0;
+
+	while (delay_ms < 2000) {
+		if (status || *portstatus & USB_PORT_STAT_CONNECTION)
+			break;
+		msleep(20);
+		delay_ms += 20;
+		status = hub_port_status(hub, *port1, portstatus, portchange);
+	}
+	return status;
+}
+
+/*
  * usb_port_resume - re-activate a suspended usb device's upstream port
  * @udev: device to re-activate, not a root hub
  * Context: must be able to sleep; device not locked; pm locks held
@@ -3359,6 +3402,10 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg)
 		}
 	}
 
+	if (udev->persist_enabled && hub_is_superspeed(hub->hdev))
+		status = wait_for_ss_port_enable(udev, hub, &port1, &portchange,
+				&portstatus);
+
 	status = check_port_resume_type(udev,
 			hub, port1, status, portchange, portstatus);
 	if (status == 0)
@@ -4550,6 +4597,7 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 	struct usb_hcd *hcd = bus_to_hcd(hdev->bus);
 	struct usb_port *port_dev = hub->ports[port1 - 1];
 	struct usb_device *udev = port_dev->child;
+	static int unreliable_port = -1;
 
 	/* Disconnect any existing devices under this port */
 	if (udev) {
@@ -4570,10 +4618,12 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus,
 				USB_PORT_STAT_C_ENABLE)) {
 		status = hub_port_debounce_be_stable(hub, port1);
 		if (status < 0) {
-			if (status != -ENODEV && printk_ratelimit())
-				dev_err(&port_dev->dev,
-						"connect-debounce failed\n");
+			if (status != -ENODEV &&
+				port1 != unreliable_port &&
+				printk_ratelimit())
+				dev_err(&port_dev->dev, "connect-debounce failed\n");
 			portstatus &= ~USB_PORT_STAT_CONNECTION;
+			unreliable_port = port1;
 		} else {
 			portstatus = status;
 		}
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index cc305c71ac3d..6130b7574908 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -1230,7 +1230,7 @@ int ehci_hub_control(
 			if (selector == EHSET_TEST_SINGLE_STEP_SET_FEATURE) {
 				spin_unlock_irqrestore(&ehci->lock, flags);
 				retval = ehset_single_step_set_feature(hcd,
-									wIndex);
+								wIndex + 1);
 				spin_lock_irqsave(&ehci->lock, flags);
 				break;
 			}
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index 3e86bf4371b3..ca7b964124af 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -35,6 +35,21 @@ static const char hcd_name[] = "ehci-pci";
 #define PCI_DEVICE_ID_INTEL_CE4100_USB	0x2e70
 
 /*-------------------------------------------------------------------------*/
+#define PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC		0x0939
+static inline bool is_intel_quark_x1000(struct pci_dev *pdev)
+{
+	return pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		pdev->device == PCI_DEVICE_ID_INTEL_QUARK_X1000_SOC;
+}
+
+/*
+ * 0x84 is the offset of in/out threshold register,
+ * and it is the same offset as the register of 'hostpc'.
+ */
+#define	intel_quark_x1000_insnreg01	hostpc
+
+/* Maximum usable threshold value is 0x7f dwords for both IN and OUT */
+#define INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD	0x007f007f
 
 /* called after powerup, by probe or system-pm "wakeup" */
 static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev)
@@ -50,6 +65,16 @@ static int ehci_pci_reinit(struct ehci_hcd *ehci, struct pci_dev *pdev)
 	if (!retval)
 		ehci_dbg(ehci, "MWI active\n");
 
+	/* Reset the threshold limit */
+	if (is_intel_quark_x1000(pdev)) {
+		/*
+		 * For the Intel QUARK X1000, raise the I/O threshold to the
+		 * maximum usable value in order to improve performance.
+		 */
+		ehci_writel(ehci, INTEL_QUARK_X1000_EHCI_MAX_THRESHOLD,
+			ehci->regs->intel_quark_x1000_insnreg01);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/usb/host/ohci-dbg.c b/drivers/usb/host/ohci-dbg.c
index 45032e933e18..04f2186939d2 100644
--- a/drivers/usb/host/ohci-dbg.c
+++ b/drivers/usb/host/ohci-dbg.c
@@ -236,7 +236,7 @@ ohci_dump_roothub (
 	}
 }
 
-static void ohci_dump (struct ohci_hcd *controller, int verbose)
+static void ohci_dump(struct ohci_hcd *controller)
 {
 	ohci_dbg (controller, "OHCI controller state\n");
 
@@ -464,15 +464,16 @@ show_list (struct ohci_hcd *ohci, char *buf, size_t count, struct ed *ed)
 static ssize_t fill_async_buffer(struct debug_buffer *buf)
 {
 	struct ohci_hcd		*ohci;
-	size_t			temp;
+	size_t			temp, size;
 	unsigned long		flags;
 
 	ohci = buf->ohci;
+	size = PAGE_SIZE;
 
 	/* display control and bulk lists together, for simplicity */
 	spin_lock_irqsave (&ohci->lock, flags);
-	temp = show_list(ohci, buf->page, buf->count, ohci->ed_controltail);
-	temp += show_list(ohci, buf->page + temp, buf->count - temp,
+	temp = show_list(ohci, buf->page, size, ohci->ed_controltail);
+	temp += show_list(ohci, buf->page + temp, size - temp,
 			  ohci->ed_bulktail);
 	spin_unlock_irqrestore (&ohci->lock, flags);
 
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index f98d03f3144c..a21a36500fd7 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -76,8 +76,8 @@ static const char	hcd_name [] = "ohci_hcd";
 #include "ohci.h"
 #include "pci-quirks.h"
 
-static void ohci_dump (struct ohci_hcd *ohci, int verbose);
-static void ohci_stop (struct usb_hcd *hcd);
+static void ohci_dump(struct ohci_hcd *ohci);
+static void ohci_stop(struct usb_hcd *hcd);
 
 #include "ohci-hub.c"
 #include "ohci-dbg.c"
@@ -744,7 +744,7 @@ retry:
 		ohci->ed_to_check = NULL;
 	}
 
-	ohci_dump (ohci, 1);
+	ohci_dump(ohci);
 
 	return 0;
 }
@@ -825,7 +825,7 @@ static irqreturn_t ohci_irq (struct usb_hcd *hcd)
 			usb_hc_died(hcd);
 		}
 
-		ohci_dump (ohci, 1);
+		ohci_dump(ohci);
 		ohci_usb_reset (ohci);
 	}
 
@@ -925,7 +925,7 @@ static void ohci_stop (struct usb_hcd *hcd)
 {
 	struct ohci_hcd		*ohci = hcd_to_ohci (hcd);
 
-	ohci_dump (ohci, 1);
+	ohci_dump(ohci);
 
 	if (quirk_nec(ohci))
 		flush_work(&ohci->nec_work);
diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c
index d4253e319428..a8bde5b8cbdd 100644
--- a/drivers/usb/host/ohci-q.c
+++ b/drivers/usb/host/ohci-q.c
@@ -311,8 +311,7 @@ static void periodic_unlink (struct ohci_hcd *ohci, struct ed *ed)
  *  - ED_OPER: when there's any request queued, the ED gets rescheduled
  *    immediately.  HC should be working on them.
  *
- *  - ED_IDLE:  when there's no TD queue. there's no reason for the HC
- *    to care about this ED; safe to disable the endpoint.
+ *  - ED_IDLE: when there's no TD queue or the HC isn't running.
  *
  * When finish_unlinks() runs later, after SOF interrupt, it will often
  * complete one or more URB unlinks before making that state change.
@@ -926,6 +925,10 @@ rescan_all:
 		int			completed, modified;
 		__hc32			*prev;
 
+		/* Is this ED already invisible to the hardware? */
+		if (ed->state == ED_IDLE)
+			goto ed_idle;
+
 		/* only take off EDs that the HC isn't using, accounting for
 		 * frame counter wraps and EDs with partially retired TDs
 		 */
@@ -955,12 +958,20 @@ skip_ed:
 			}
 		}
 
+		/* ED's now officially unlinked, hc doesn't see */
+		ed->state = ED_IDLE;
+		if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT)
+			ohci->eds_scheduled--;
+		ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H);
+		ed->hwNextED = 0;
+		wmb();
+		ed->hwINFO &= ~cpu_to_hc32(ohci, ED_SKIP | ED_DEQUEUE);
+ed_idle:
+
 		/* reentrancy:  if we drop the schedule lock, someone might
 		 * have modified this list.  normally it's just prepending
 		 * entries (which we'd ignore), but paranoia won't hurt.
 		 */
-		*last = ed->ed_next;
-		ed->ed_next = NULL;
 		modified = 0;
 
 		/* unlink urbs as requested, but rescan the list after
@@ -1018,19 +1029,20 @@ rescan_this:
 		if (completed && !list_empty (&ed->td_list))
 			goto rescan_this;
 
-		/* ED's now officially unlinked, hc doesn't see */
-		ed->state = ED_IDLE;
-		if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT)
-			ohci->eds_scheduled--;
-		ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H);
-		ed->hwNextED = 0;
-		wmb ();
-		ed->hwINFO &= ~cpu_to_hc32 (ohci, ED_SKIP | ED_DEQUEUE);
-
-		/* but if there's work queued, reschedule */
-		if (!list_empty (&ed->td_list)) {
-			if (ohci->rh_state == OHCI_RH_RUNNING)
-				ed_schedule (ohci, ed);
+		/*
+		 * If no TDs are queued, take ED off the ed_rm_list.
+		 * Otherwise, if the HC is running, reschedule.
+		 * If not, leave it on the list for further dequeues.
+		 */
+		if (list_empty(&ed->td_list)) {
+			*last = ed->ed_next;
+			ed->ed_next = NULL;
+		} else if (ohci->rh_state == OHCI_RH_RUNNING) {
+			*last = ed->ed_next;
+			ed->ed_next = NULL;
+			ed_schedule(ohci, ed);
+		} else {
+			last = &ed->ed_next;
 		}
 
 		if (modified)
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index e20520f42753..994a36e582ca 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -101,6 +101,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	/* AMD PLL quirk */
 	if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info())
 		xhci->quirks |= XHCI_AMD_PLL_FIX;
+
+	if (pdev->vendor == PCI_VENDOR_ID_AMD)
+		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL) {
 		xhci->quirks |= XHCI_LPM_SUPPORT;
 		xhci->quirks |= XHCI_INTEL_HOST;
@@ -143,6 +147,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 			pdev->device == PCI_DEVICE_ID_ASROCK_P67) {
 		xhci->quirks |= XHCI_RESET_ON_RESUME;
 		xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+		xhci->quirks |= XHCI_BROKEN_STREAMS;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
 			pdev->device == 0x0015)
@@ -150,6 +155,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 	if (pdev->vendor == PCI_VENDOR_ID_VIA)
 		xhci->quirks |= XHCI_RESET_ON_RESUME;
 
+	/* See https://bugzilla.kernel.org/show_bug.cgi?id=79511 */
+	if (pdev->vendor == PCI_VENDOR_ID_VIA &&
+			pdev->device == 0x3432)
+		xhci->quirks |= XHCI_BROKEN_STREAMS;
+
 	if (xhci->quirks & XHCI_RESET_ON_RESUME)
 		xhci_dbg_trace(xhci, trace_xhci_dbg_quirks,
 				"QUIRK: Resetting on resume");
@@ -230,7 +240,8 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		goto put_usb3_hcd;
 	/* Roothub already marked as USB 3.0 speed */
 
-	if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
+	if (!(xhci->quirks & XHCI_BROKEN_STREAMS) &&
+			HCC_MAX_PSA(xhci->hcc_params) >= 4)
 		xhci->shared_hcd->can_do_streams = 1;
 
 	/* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 749fc68eb5c1..28a929d45cfe 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -364,32 +364,6 @@ static void ring_doorbell_for_active_rings(struct xhci_hcd *xhci,
 	}
 }
 
-/*
- * Find the segment that trb is in.  Start searching in start_seg.
- * If we must move past a segment that has a link TRB with a toggle cycle state
- * bit set, then we will toggle the value pointed at by cycle_state.
- */
-static struct xhci_segment *find_trb_seg(
-		struct xhci_segment *start_seg,
-		union xhci_trb	*trb, int *cycle_state)
-{
-	struct xhci_segment *cur_seg = start_seg;
-	struct xhci_generic_trb *generic_trb;
-
-	while (cur_seg->trbs > trb ||
-			&cur_seg->trbs[TRBS_PER_SEGMENT - 1] < trb) {
-		generic_trb = &cur_seg->trbs[TRBS_PER_SEGMENT - 1].generic;
-		if (generic_trb->field[3] & cpu_to_le32(LINK_TOGGLE))
-			*cycle_state ^= 0x1;
-		cur_seg = cur_seg->next;
-		if (cur_seg == start_seg)
-			/* Looped over the entire list.  Oops! */
-			return NULL;
-	}
-	return cur_seg;
-}
-
-
 static struct xhci_ring *xhci_triad_to_transfer_ring(struct xhci_hcd *xhci,
 		unsigned int slot_id, unsigned int ep_index,
 		unsigned int stream_id)
@@ -459,9 +433,12 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 	struct xhci_virt_device *dev = xhci->devs[slot_id];
 	struct xhci_virt_ep *ep = &dev->eps[ep_index];
 	struct xhci_ring *ep_ring;
-	struct xhci_generic_trb *trb;
+	struct xhci_segment *new_seg;
+	union xhci_trb *new_deq;
 	dma_addr_t addr;
 	u64 hw_dequeue;
+	bool cycle_found = false;
+	bool td_last_trb_found = false;
 
 	ep_ring = xhci_triad_to_transfer_ring(xhci, slot_id,
 			ep_index, stream_id);
@@ -486,45 +463,45 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci,
 		hw_dequeue = le64_to_cpu(ep_ctx->deq);
 	}
 
-	/* Find virtual address and segment of hardware dequeue pointer */
-	state->new_deq_seg = ep_ring->deq_seg;
-	state->new_deq_ptr = ep_ring->dequeue;
-	while (xhci_trb_virt_to_dma(state->new_deq_seg, state->new_deq_ptr)
-			!= (dma_addr_t)(hw_dequeue & ~0xf)) {
-		next_trb(xhci, ep_ring, &state->new_deq_seg,
-					&state->new_deq_ptr);
-		if (state->new_deq_ptr == ep_ring->dequeue) {
-			WARN_ON(1);
-			return;
-		}
-	}
+	new_seg = ep_ring->deq_seg;
+	new_deq = ep_ring->dequeue;
+	state->new_cycle_state = hw_dequeue & 0x1;
+
 	/*
-	 * Find cycle state for last_trb, starting at old cycle state of
-	 * hw_dequeue. If there is only one segment ring, find_trb_seg() will
-	 * return immediately and cannot toggle the cycle state if this search
-	 * wraps around, so add one more toggle manually in that case.
+	 * We want to find the pointer, segment and cycle state of the new trb
+	 * (the one after current TD's last_trb). We know the cycle state at
+	 * hw_dequeue, so walk the ring until both hw_dequeue and last_trb are
+	 * found.
 	 */
-	state->new_cycle_state = hw_dequeue & 0x1;
-	if (ep_ring->first_seg == ep_ring->first_seg->next &&
-			cur_td->last_trb < state->new_deq_ptr)
-		state->new_cycle_state ^= 0x1;
+	do {
+		if (!cycle_found && xhci_trb_virt_to_dma(new_seg, new_deq)
+		    == (dma_addr_t)(hw_dequeue & ~0xf)) {
+			cycle_found = true;
+			if (td_last_trb_found)
+				break;
+		}
+		if (new_deq == cur_td->last_trb)
+			td_last_trb_found = true;
 
-	state->new_deq_ptr = cur_td->last_trb;
-	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
-			"Finding segment containing last TRB in TD.");
-	state->new_deq_seg = find_trb_seg(state->new_deq_seg,
-			state->new_deq_ptr, &state->new_cycle_state);
-	if (!state->new_deq_seg) {
-		WARN_ON(1);
-		return;
-	}
+		if (cycle_found &&
+		    TRB_TYPE_LINK_LE32(new_deq->generic.field[3]) &&
+		    new_deq->generic.field[3] & cpu_to_le32(LINK_TOGGLE))
+			state->new_cycle_state ^= 0x1;
+
+		next_trb(xhci, ep_ring, &new_seg, &new_deq);
+
+		/* Search wrapped around, bail out */
+		if (new_deq == ep->ring->dequeue) {
+			xhci_err(xhci, "Error: Failed finding new dequeue state\n");
+			state->new_deq_seg = NULL;
+			state->new_deq_ptr = NULL;
+			return;
+		}
+
+	} while (!cycle_found || !td_last_trb_found);
 
-	/* Increment to find next TRB after last_trb. Cycle if appropriate. */
-	trb = &state->new_deq_ptr->generic;
-	if (TRB_TYPE_LINK_LE32(trb->field[3]) &&
-	    (trb->field[3] & cpu_to_le32(LINK_TOGGLE)))
-		state->new_cycle_state ^= 0x1;
-	next_trb(xhci, ep_ring, &state->new_deq_seg, &state->new_deq_ptr);
+	state->new_deq_seg = new_seg;
+	state->new_deq_ptr = new_deq;
 
 	/* Don't update the ring cycle state for the producer (us). */
 	xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
@@ -2483,7 +2460,8 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 		 * last TRB of the previous TD. The command completion handle
 		 * will take care the rest.
 		 */
-		if (!event_seg && trb_comp_code == COMP_STOP_INVAL) {
+		if (!event_seg && (trb_comp_code == COMP_STOP ||
+				   trb_comp_code == COMP_STOP_INVAL)) {
 			ret = 0;
 			goto cleanup;
 		}
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 7436d5f5e67a..e32cc6cf86dc 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -2891,6 +2891,9 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci,
 			ep_index, ep->stopped_stream, ep->stopped_td,
 			&deq_state);
 
+	if (!deq_state.new_deq_ptr || !deq_state.new_deq_seg)
+		return;
+
 	/* HW with the reset endpoint quirk will use the saved dequeue state to
 	 * issue a configure endpoint command later.
 	 */
@@ -3163,7 +3166,8 @@ int xhci_alloc_streams(struct usb_hcd *hcd, struct usb_device *udev,
 			num_streams);
 
 	/* MaxPSASize value 0 (2 streams) means streams are not supported */
-	if (HCC_MAX_PSA(xhci->hcc_params) < 4) {
+	if ((xhci->quirks & XHCI_BROKEN_STREAMS) ||
+			HCC_MAX_PSA(xhci->hcc_params) < 4) {
 		xhci_dbg(xhci, "xHCI controller does not support streams.\n");
 		return -ENOSYS;
 	}
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 9ffecd56600d..dace5152e179 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1558,6 +1558,8 @@ struct xhci_hcd {
 #define XHCI_PLAT		(1 << 16)
 #define XHCI_SLOW_SUSPEND	(1 << 17)
 #define XHCI_SPURIOUS_WAKEUP	(1 << 18)
+/* For controllers with a broken beyond repair streams implementation */
+#define XHCI_BROKEN_STREAMS	(1 << 19)
 	unsigned int		num_active_eps;
 	unsigned int		limit_active_eps;
 	/* There are two roothubs to keep track of bus suspend info for */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 8a3813be1b28..8b0f517abb6b 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -151,6 +151,7 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_AMC232_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CANUSB_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CANDAPTER_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_BM_ATOM_NANO_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_NXTCAM_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_EV3CON_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_0_PID) },
@@ -673,6 +674,8 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_5_PID) },
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_6_PID) },
 	{ USB_DEVICE(FTDI_VID, XSENS_CONVERTER_7_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) },
+	{ USB_DEVICE(XSENS_VID, XSENS_MTW_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_OMNI1509) },
 	{ USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ACTIVE_ROBOTS_PID) },
@@ -945,6 +948,8 @@ static const struct usb_device_id id_table_combined[] = {
 	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_2_PID) },
 	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_3_PID) },
 	{ USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_4_PID) },
+	/* ekey Devices */
+	{ USB_DEVICE(FTDI_VID, FTDI_EKEY_CONV_USB_PID) },
 	/* Infineon Devices */
 	{ USB_DEVICE_INTERFACE_NUMBER(INFINEON_VID, INFINEON_TRIBOARD_PID, 1) },
 	{ }					/* Terminating entry */
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index c4777bc6aee0..70b0b1d88ae9 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -42,6 +42,8 @@
 /* www.candapter.com Ewert Energy Systems CANdapter device */
 #define FTDI_CANDAPTER_PID 0x9F80 /* Product Id */
 
+#define FTDI_BM_ATOM_NANO_PID	0xa559	/* Basic Micro ATOM Nano USB2Serial */
+
 /*
  * Texas Instruments XDS100v2 JTAG / BeagleBone A3
  * http://processors.wiki.ti.com/index.php/XDS100
@@ -140,12 +142,15 @@
 /*
  * Xsens Technologies BV products (http://www.xsens.com).
  */
-#define XSENS_CONVERTER_0_PID	0xD388
-#define XSENS_CONVERTER_1_PID	0xD389
+#define XSENS_VID		0x2639
+#define XSENS_CONVERTER_PID	0xD00D	/* Xsens USB-serial converter */
+#define XSENS_MTW_PID		0x0200	/* Xsens MTw */
+#define XSENS_CONVERTER_0_PID	0xD388	/* Xsens USB converter */
+#define XSENS_CONVERTER_1_PID	0xD389	/* Xsens Wireless Receiver */
 #define XSENS_CONVERTER_2_PID	0xD38A
-#define XSENS_CONVERTER_3_PID	0xD38B
-#define XSENS_CONVERTER_4_PID	0xD38C
-#define XSENS_CONVERTER_5_PID	0xD38D
+#define XSENS_CONVERTER_3_PID	0xD38B	/* Xsens USB-serial converter */
+#define XSENS_CONVERTER_4_PID	0xD38C	/* Xsens Wireless Receiver */
+#define XSENS_CONVERTER_5_PID	0xD38D	/* Xsens Awinda Station */
 #define XSENS_CONVERTER_6_PID	0xD38E
 #define XSENS_CONVERTER_7_PID	0xD38F
 
@@ -1375,3 +1380,8 @@
 #define BRAINBOXES_US_160_6_PID		0x9006 /* US-160 16xRS232 1Mbaud Port 11 and 12 */
 #define BRAINBOXES_US_160_7_PID		0x9007 /* US-160 16xRS232 1Mbaud Port 13 and 14 */
 #define BRAINBOXES_US_160_8_PID		0x9008 /* US-160 16xRS232 1Mbaud Port 15 and 16 */
+
+/*
+ * ekey biometric systems GmbH (http://ekey.net/)
+ */
+#define FTDI_EKEY_CONV_USB_PID		0xCB08	/* Converter USB */
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index e62f2dff8b7d..6c3734d2b45a 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -514,6 +514,10 @@ static void command_port_read_callback(struct urb *urb)
 		dev_dbg(&urb->dev->dev, "%s - command_info is NULL, exiting.\n", __func__);
 		return;
 	}
+	if (!urb->actual_length) {
+		dev_dbg(&urb->dev->dev, "%s - empty response, exiting.\n", __func__);
+		return;
+	}
 	if (status) {
 		dev_dbg(&urb->dev->dev, "%s - nonzero urb status: %d\n", __func__, status);
 		if (status != -ENOENT)
@@ -534,7 +538,8 @@ static void command_port_read_callback(struct urb *urb)
 		/* These are unsolicited reports from the firmware, hence no
 		   waiting command to wakeup */
 		dev_dbg(&urb->dev->dev, "%s - event received\n", __func__);
-	} else if (data[0] == WHITEHEAT_GET_DTR_RTS) {
+	} else if ((data[0] == WHITEHEAT_GET_DTR_RTS) &&
+		(urb->actual_length - 1 <= sizeof(command_info->result_buffer))) {
 		memcpy(command_info->result_buffer, &data[1],
 						urb->actual_length - 1);
 		command_info->command_finished = WHITEHEAT_CMD_COMPLETE;
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index 511b22953167..3f42785f653c 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -1026,7 +1026,7 @@ static int uas_configure_endpoints(struct uas_dev_info *devinfo)
 					    usb_endpoint_num(&eps[3]->desc));
 
 	if (udev->speed != USB_SPEED_SUPER) {
-		devinfo->qdepth = 256;
+		devinfo->qdepth = 32;
 		devinfo->use_streams = 0;
 	} else {
 		devinfo->qdepth = usb_alloc_streams(devinfo->intf, eps + 1,
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index 84b4bfb84344..500713882ad5 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -67,10 +67,9 @@ static event_word_t *event_array[MAX_EVENT_ARRAY_PAGES] __read_mostly;
 static unsigned event_array_pages __read_mostly;
 
 /*
- * sync_set_bit() and friends must be unsigned long aligned on non-x86
- * platforms.
+ * sync_set_bit() and friends must be unsigned long aligned.
  */
-#if !defined(CONFIG_X86) && BITS_PER_LONG > 32
+#if BITS_PER_LONG > 32
 
 #define BM(w) (unsigned long *)((unsigned long)w & ~0x7UL)
 #define EVTCHN_FIFO_BIT(b, w) \
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 5a201d81049c..fbd76ded9a34 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -22,7 +22,6 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/freezer.h>
-#include <linux/workqueue.h>
 #include "async-thread.h"
 #include "ctree.h"
 
@@ -55,8 +54,39 @@ struct btrfs_workqueue {
 	struct __btrfs_workqueue *high;
 };
 
-static inline struct __btrfs_workqueue
-*__btrfs_alloc_workqueue(const char *name, int flags, int max_active,
+static void normal_work_helper(struct btrfs_work *work);
+
+#define BTRFS_WORK_HELPER(name)					\
+void btrfs_##name(struct work_struct *arg)				\
+{									\
+	struct btrfs_work *work = container_of(arg, struct btrfs_work,	\
+					       normal_work);		\
+	normal_work_helper(work);					\
+}
+
+BTRFS_WORK_HELPER(worker_helper);
+BTRFS_WORK_HELPER(delalloc_helper);
+BTRFS_WORK_HELPER(flush_delalloc_helper);
+BTRFS_WORK_HELPER(cache_helper);
+BTRFS_WORK_HELPER(submit_helper);
+BTRFS_WORK_HELPER(fixup_helper);
+BTRFS_WORK_HELPER(endio_helper);
+BTRFS_WORK_HELPER(endio_meta_helper);
+BTRFS_WORK_HELPER(endio_meta_write_helper);
+BTRFS_WORK_HELPER(endio_raid56_helper);
+BTRFS_WORK_HELPER(rmw_helper);
+BTRFS_WORK_HELPER(endio_write_helper);
+BTRFS_WORK_HELPER(freespace_write_helper);
+BTRFS_WORK_HELPER(delayed_meta_helper);
+BTRFS_WORK_HELPER(readahead_helper);
+BTRFS_WORK_HELPER(qgroup_rescan_helper);
+BTRFS_WORK_HELPER(extent_refs_helper);
+BTRFS_WORK_HELPER(scrub_helper);
+BTRFS_WORK_HELPER(scrubwrc_helper);
+BTRFS_WORK_HELPER(scrubnc_helper);
+
+static struct __btrfs_workqueue *
+__btrfs_alloc_workqueue(const char *name, int flags, int max_active,
 			 int thresh)
 {
 	struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
@@ -232,13 +262,11 @@ static void run_ordered_work(struct __btrfs_workqueue *wq)
 	spin_unlock_irqrestore(lock, flags);
 }
 
-static void normal_work_helper(struct work_struct *arg)
+static void normal_work_helper(struct btrfs_work *work)
 {
-	struct btrfs_work *work;
 	struct __btrfs_workqueue *wq;
 	int need_order = 0;
 
-	work = container_of(arg, struct btrfs_work, normal_work);
 	/*
 	 * We should not touch things inside work in the following cases:
 	 * 1) after work->func() if it has no ordered_free
@@ -262,7 +290,7 @@ static void normal_work_helper(struct work_struct *arg)
 		trace_btrfs_all_work_done(work);
 }
 
-void btrfs_init_work(struct btrfs_work *work,
+void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
 		     btrfs_func_t func,
 		     btrfs_func_t ordered_func,
 		     btrfs_func_t ordered_free)
@@ -270,7 +298,7 @@ void btrfs_init_work(struct btrfs_work *work,
 	work->func = func;
 	work->ordered_func = ordered_func;
 	work->ordered_free = ordered_free;
-	INIT_WORK(&work->normal_work, normal_work_helper);
+	INIT_WORK(&work->normal_work, uniq_func);
 	INIT_LIST_HEAD(&work->ordered_list);
 	work->flags = 0;
 }
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 9c6b66d15fb0..e9e31c94758f 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -19,12 +19,14 @@
 
 #ifndef __BTRFS_ASYNC_THREAD_
 #define __BTRFS_ASYNC_THREAD_
+#include <linux/workqueue.h>
 
 struct btrfs_workqueue;
 /* Internal use only */
 struct __btrfs_workqueue;
 struct btrfs_work;
 typedef void (*btrfs_func_t)(struct btrfs_work *arg);
+typedef void (*btrfs_work_func_t)(struct work_struct *arg);
 
 struct btrfs_work {
 	btrfs_func_t func;
@@ -38,11 +40,35 @@ struct btrfs_work {
 	unsigned long flags;
 };
 
+#define BTRFS_WORK_HELPER_PROTO(name)					\
+void btrfs_##name(struct work_struct *arg)
+
+BTRFS_WORK_HELPER_PROTO(worker_helper);
+BTRFS_WORK_HELPER_PROTO(delalloc_helper);
+BTRFS_WORK_HELPER_PROTO(flush_delalloc_helper);
+BTRFS_WORK_HELPER_PROTO(cache_helper);
+BTRFS_WORK_HELPER_PROTO(submit_helper);
+BTRFS_WORK_HELPER_PROTO(fixup_helper);
+BTRFS_WORK_HELPER_PROTO(endio_helper);
+BTRFS_WORK_HELPER_PROTO(endio_meta_helper);
+BTRFS_WORK_HELPER_PROTO(endio_meta_write_helper);
+BTRFS_WORK_HELPER_PROTO(endio_raid56_helper);
+BTRFS_WORK_HELPER_PROTO(rmw_helper);
+BTRFS_WORK_HELPER_PROTO(endio_write_helper);
+BTRFS_WORK_HELPER_PROTO(freespace_write_helper);
+BTRFS_WORK_HELPER_PROTO(delayed_meta_helper);
+BTRFS_WORK_HELPER_PROTO(readahead_helper);
+BTRFS_WORK_HELPER_PROTO(qgroup_rescan_helper);
+BTRFS_WORK_HELPER_PROTO(extent_refs_helper);
+BTRFS_WORK_HELPER_PROTO(scrub_helper);
+BTRFS_WORK_HELPER_PROTO(scrubwrc_helper);
+BTRFS_WORK_HELPER_PROTO(scrubnc_helper);
+
 struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name,
 					      int flags,
 					      int max_active,
 					      int thresh);
-void btrfs_init_work(struct btrfs_work *work,
+void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper,
 		     btrfs_func_t func,
 		     btrfs_func_t ordered_func,
 		     btrfs_func_t ordered_free);
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index e25564bfcb46..54a201dac7f9 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -276,9 +276,8 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 			}
 			if (ret > 0)
 				goto next;
-			ret = ulist_add_merge(parents, eb->start,
-					      (uintptr_t)eie,
-					      (u64 *)&old, GFP_NOFS);
+			ret = ulist_add_merge_ptr(parents, eb->start,
+						  eie, (void **)&old, GFP_NOFS);
 			if (ret < 0)
 				break;
 			if (!ret && extent_item_pos) {
@@ -1001,16 +1000,19 @@ again:
 					ret = -EIO;
 					goto out;
 				}
+				btrfs_tree_read_lock(eb);
+				btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
 				ret = find_extent_in_eb(eb, bytenr,
 							*extent_item_pos, &eie);
+				btrfs_tree_read_unlock_blocking(eb);
 				free_extent_buffer(eb);
 				if (ret < 0)
 					goto out;
 				ref->inode_list = eie;
 			}
-			ret = ulist_add_merge(refs, ref->parent,
-					      (uintptr_t)ref->inode_list,
-					      (u64 *)&eie, GFP_NOFS);
+			ret = ulist_add_merge_ptr(refs, ref->parent,
+						  ref->inode_list,
+						  (void **)&eie, GFP_NOFS);
 			if (ret < 0)
 				goto out;
 			if (!ret && extent_item_pos) {
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 4794923c410c..43527fd78825 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -84,12 +84,6 @@ struct btrfs_inode {
 	 */
 	struct list_head delalloc_inodes;
 
-	/*
-	 * list for tracking inodes that must be sent to disk before a
-	 * rename or truncate commit
-	 */
-	struct list_head ordered_operations;
-
 	/* node for the red-black tree that links inodes in subvolume root */
 	struct rb_node rb_node;
 
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index da775bfdebc9..a2e90f855d7d 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1395,8 +1395,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 		return -ENOMEM;
 
 	async_work->delayed_root = delayed_root;
-	btrfs_init_work(&async_work->work, btrfs_async_run_delayed_root,
-			NULL, NULL);
+	btrfs_init_work(&async_work->work, btrfs_delayed_meta_helper,
+			btrfs_async_run_delayed_root, NULL, NULL);
 	async_work->nr = nr;
 
 	btrfs_queue_work(root->fs_info->delayed_workers, &async_work->work);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 08e65e9cf2aa..0229c3720b30 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -39,7 +39,6 @@
 #include "btrfs_inode.h"
 #include "volumes.h"
 #include "print-tree.h"
-#include "async-thread.h"
 #include "locking.h"
 #include "tree-log.h"
 #include "free-space-cache.h"
@@ -60,8 +59,6 @@ static void end_workqueue_fn(struct btrfs_work *work);
 static void free_fs_root(struct btrfs_root *root);
 static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 				    int read_only);
-static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
-					     struct btrfs_root *root);
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				      struct btrfs_root *root);
@@ -695,35 +692,41 @@ static void end_workqueue_bio(struct bio *bio, int err)
 {
 	struct end_io_wq *end_io_wq = bio->bi_private;
 	struct btrfs_fs_info *fs_info;
+	struct btrfs_workqueue *wq;
+	btrfs_work_func_t func;
 
 	fs_info = end_io_wq->info;
 	end_io_wq->error = err;
-	btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
 
 	if (bio->bi_rw & REQ_WRITE) {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
-			btrfs_queue_work(fs_info->endio_meta_write_workers,
-					 &end_io_wq->work);
-		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
-			btrfs_queue_work(fs_info->endio_freespace_worker,
-					 &end_io_wq->work);
-		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
-			btrfs_queue_work(fs_info->endio_raid56_workers,
-					 &end_io_wq->work);
-		else
-			btrfs_queue_work(fs_info->endio_write_workers,
-					 &end_io_wq->work);
+		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
+			wq = fs_info->endio_meta_write_workers;
+			func = btrfs_endio_meta_write_helper;
+		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE) {
+			wq = fs_info->endio_freespace_worker;
+			func = btrfs_freespace_write_helper;
+		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+			wq = fs_info->endio_raid56_workers;
+			func = btrfs_endio_raid56_helper;
+		} else {
+			wq = fs_info->endio_write_workers;
+			func = btrfs_endio_write_helper;
+		}
 	} else {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
-			btrfs_queue_work(fs_info->endio_raid56_workers,
-					 &end_io_wq->work);
-		else if (end_io_wq->metadata)
-			btrfs_queue_work(fs_info->endio_meta_workers,
-					 &end_io_wq->work);
-		else
-			btrfs_queue_work(fs_info->endio_workers,
-					 &end_io_wq->work);
+		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+			wq = fs_info->endio_raid56_workers;
+			func = btrfs_endio_raid56_helper;
+		} else if (end_io_wq->metadata) {
+			wq = fs_info->endio_meta_workers;
+			func = btrfs_endio_meta_helper;
+		} else {
+			wq = fs_info->endio_workers;
+			func = btrfs_endio_helper;
+		}
 	}
+
+	btrfs_init_work(&end_io_wq->work, func, end_workqueue_fn, NULL, NULL);
+	btrfs_queue_work(wq, &end_io_wq->work);
 }
 
 /*
@@ -830,7 +833,7 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
 	async->submit_bio_start = submit_bio_start;
 	async->submit_bio_done = submit_bio_done;
 
-	btrfs_init_work(&async->work, run_one_async_start,
+	btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
 			run_one_async_done, run_one_async_free);
 
 	async->bio_flags = bio_flags;
@@ -3829,34 +3832,6 @@ static void btrfs_error_commit_super(struct btrfs_root *root)
 	btrfs_cleanup_transaction(root);
 }
 
-static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
-					     struct btrfs_root *root)
-{
-	struct btrfs_inode *btrfs_inode;
-	struct list_head splice;
-
-	INIT_LIST_HEAD(&splice);
-
-	mutex_lock(&root->fs_info->ordered_operations_mutex);
-	spin_lock(&root->fs_info->ordered_root_lock);
-
-	list_splice_init(&t->ordered_operations, &splice);
-	while (!list_empty(&splice)) {
-		btrfs_inode = list_entry(splice.next, struct btrfs_inode,
-					 ordered_operations);
-
-		list_del_init(&btrfs_inode->ordered_operations);
-		spin_unlock(&root->fs_info->ordered_root_lock);
-
-		btrfs_invalidate_inodes(btrfs_inode->root);
-
-		spin_lock(&root->fs_info->ordered_root_lock);
-	}
-
-	spin_unlock(&root->fs_info->ordered_root_lock);
-	mutex_unlock(&root->fs_info->ordered_operations_mutex);
-}
-
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
 {
 	struct btrfs_ordered_extent *ordered;
@@ -4093,8 +4068,6 @@ again:
 void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 				   struct btrfs_root *root)
 {
-	btrfs_destroy_ordered_operations(cur_trans, root);
-
 	btrfs_destroy_delayed_refs(cur_trans, root);
 
 	cur_trans->state = TRANS_STATE_COMMIT_START;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 813537f362f9..8edb9fcc38d5 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -552,7 +552,8 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 	caching_ctl->block_group = cache;
 	caching_ctl->progress = cache->key.objectid;
 	atomic_set(&caching_ctl->count, 1);
-	btrfs_init_work(&caching_ctl->work, caching_thread, NULL, NULL);
+	btrfs_init_work(&caching_ctl->work, btrfs_cache_helper,
+			caching_thread, NULL, NULL);
 
 	spin_lock(&cache->lock);
 	/*
@@ -2749,8 +2750,8 @@ int btrfs_async_run_delayed_refs(struct btrfs_root *root,
 		async->sync = 0;
 	init_completion(&async->wait);
 
-	btrfs_init_work(&async->work, delayed_ref_async_start,
-			NULL, NULL);
+	btrfs_init_work(&async->work, btrfs_extent_refs_helper,
+			delayed_ref_async_start, NULL, NULL);
 
 	btrfs_queue_work(root->fs_info->extent_workers, &async->work);
 
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index a389820d158b..09b4e3165e2c 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2532,6 +2532,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 					test_bit(BIO_UPTODATE, &bio->bi_flags);
 				if (err)
 					uptodate = 0;
+				offset += len;
 				continue;
 			}
 		}
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index f46cfe45d686..54c84daec9b5 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -756,7 +756,7 @@ again:
 				found_next = 1;
 			if (ret != 0)
 				goto insert;
-			slot = 0;
+			slot = path->slots[0];
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot);
 		if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID ||
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 1f2b99cb55ea..ab1fd668020d 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1838,6 +1838,8 @@ out:
 
 int btrfs_release_file(struct inode *inode, struct file *filp)
 {
+	if (filp->private_data)
+		btrfs_ioctl_trans_end(filp);
 	/*
 	 * ordered_data_close is set by settattr when we are about to truncate
 	 * a file from a non-zero size to a zero size.  This tries to
@@ -1845,26 +1847,8 @@ int btrfs_release_file(struct inode *inode, struct file *filp)
 	 * application were using truncate to replace a file in place.
 	 */
 	if (test_and_clear_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
-			       &BTRFS_I(inode)->runtime_flags)) {
-		struct btrfs_trans_handle *trans;
-		struct btrfs_root *root = BTRFS_I(inode)->root;
-
-		/*
-		 * We need to block on a committing transaction to keep us from
-		 * throwing a ordered operation on to the list and causing
-		 * something like sync to deadlock trying to flush out this
-		 * inode.
-		 */
-		trans = btrfs_start_transaction(root, 0);
-		if (IS_ERR(trans))
-			return PTR_ERR(trans);
-		btrfs_add_ordered_operation(trans, BTRFS_I(inode)->root, inode);
-		btrfs_end_transaction(trans, root);
-		if (inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT)
+			       &BTRFS_I(inode)->runtime_flags))
 			filemap_flush(inode->i_mapping);
-	}
-	if (filp->private_data)
-		btrfs_ioctl_trans_end(filp);
 	return 0;
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 3668048e16f8..c6cd34e699d0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -709,6 +709,18 @@ retry:
 				unlock_extent(io_tree, async_extent->start,
 					      async_extent->start +
 					      async_extent->ram_size - 1);
+
+				/*
+				 * we need to redirty the pages if we decide to
+				 * fallback to uncompressed IO, otherwise we
+				 * will not submit these pages down to lower
+				 * layers.
+				 */
+				extent_range_redirty_for_io(inode,
+						async_extent->start,
+						async_extent->start +
+						async_extent->ram_size - 1);
+
 				goto retry;
 			}
 			goto out_free;
@@ -1084,8 +1096,10 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 		async_cow->end = cur_end;
 		INIT_LIST_HEAD(&async_cow->extents);
 
-		btrfs_init_work(&async_cow->work, async_cow_start,
-				async_cow_submit, async_cow_free);
+		btrfs_init_work(&async_cow->work,
+				btrfs_delalloc_helper,
+				async_cow_start, async_cow_submit,
+				async_cow_free);
 
 		nr_pages = (cur_end - start + PAGE_CACHE_SIZE) >>
 			PAGE_CACHE_SHIFT;
@@ -1869,7 +1883,8 @@ static int btrfs_writepage_start_hook(struct page *page, u64 start, u64 end)
 
 	SetPageChecked(page);
 	page_cache_get(page);
-	btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
+	btrfs_init_work(&fixup->work, btrfs_fixup_helper,
+			btrfs_writepage_fixup_worker, NULL, NULL);
 	fixup->page = page;
 	btrfs_queue_work(root->fs_info->fixup_workers, &fixup->work);
 	return -EBUSY;
@@ -2810,7 +2825,8 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 	struct inode *inode = page->mapping->host;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_ordered_extent *ordered_extent = NULL;
-	struct btrfs_workqueue *workers;
+	struct btrfs_workqueue *wq;
+	btrfs_work_func_t func;
 
 	trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
 
@@ -2819,13 +2835,17 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 					    end - start + 1, uptodate))
 		return 0;
 
-	btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
+	if (btrfs_is_free_space_inode(inode)) {
+		wq = root->fs_info->endio_freespace_worker;
+		func = btrfs_freespace_write_helper;
+	} else {
+		wq = root->fs_info->endio_write_workers;
+		func = btrfs_endio_write_helper;
+	}
 
-	if (btrfs_is_free_space_inode(inode))
-		workers = root->fs_info->endio_freespace_worker;
-	else
-		workers = root->fs_info->endio_write_workers;
-	btrfs_queue_work(workers, &ordered_extent->work);
+	btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
+			NULL);
+	btrfs_queue_work(wq, &ordered_extent->work);
 
 	return 0;
 }
@@ -7146,7 +7166,8 @@ again:
 	if (!ret)
 		goto out_test;
 
-	btrfs_init_work(&ordered->work, finish_ordered_fn, NULL, NULL);
+	btrfs_init_work(&ordered->work, btrfs_endio_write_helper,
+			finish_ordered_fn, NULL, NULL);
 	btrfs_queue_work(root->fs_info->endio_write_workers,
 			 &ordered->work);
 out_test:
@@ -7939,27 +7960,6 @@ static int btrfs_truncate(struct inode *inode)
 	BUG_ON(ret);
 
 	/*
-	 * setattr is responsible for setting the ordered_data_close flag,
-	 * but that is only tested during the last file release.  That
-	 * could happen well after the next commit, leaving a great big
-	 * window where new writes may get lost if someone chooses to write
-	 * to this file after truncating to zero
-	 *
-	 * The inode doesn't have any dirty data here, and so if we commit
-	 * this is a noop.  If someone immediately starts writing to the inode
-	 * it is very likely we'll catch some of their writes in this
-	 * transaction, and the commit will find this file on the ordered
-	 * data list with good things to send down.
-	 *
-	 * This is a best effort solution, there is still a window where
-	 * using truncate to replace the contents of the file will
-	 * end up with a zero length file after a crash.
-	 */
-	if (inode->i_size == 0 && test_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
-					   &BTRFS_I(inode)->runtime_flags))
-		btrfs_add_ordered_operation(trans, root, inode);
-
-	/*
 	 * So if we truncate and then write and fsync we normally would just
 	 * write the extents that changed, which is a problem if we need to
 	 * first truncate that entire inode.  So set this flag so we write out
@@ -8106,7 +8106,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	mutex_init(&ei->delalloc_mutex);
 	btrfs_ordered_inode_tree_init(&ei->ordered_tree);
 	INIT_LIST_HEAD(&ei->delalloc_inodes);
-	INIT_LIST_HEAD(&ei->ordered_operations);
 	RB_CLEAR_NODE(&ei->rb_node);
 
 	return inode;
@@ -8146,17 +8145,6 @@ void btrfs_destroy_inode(struct inode *inode)
 	if (!root)
 		goto free;
 
-	/*
-	 * Make sure we're properly removed from the ordered operation
-	 * lists.
-	 */
-	smp_mb();
-	if (!list_empty(&BTRFS_I(inode)->ordered_operations)) {
-		spin_lock(&root->fs_info->ordered_root_lock);
-		list_del_init(&BTRFS_I(inode)->ordered_operations);
-		spin_unlock(&root->fs_info->ordered_root_lock);
-	}
-
 	if (test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
 		     &BTRFS_I(inode)->runtime_flags)) {
 		btrfs_info(root->fs_info, "inode %llu still on the orphan list",
@@ -8338,12 +8326,10 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	ret = 0;
 
 	/*
-	 * we're using rename to replace one file with another.
-	 * and the replacement file is large.  Start IO on it now so
-	 * we don't add too much work to the end of the transaction
+	 * we're using rename to replace one file with another.  Start IO on it
+	 * now so  we don't add too much work to the end of the transaction
 	 */
-	if (new_inode && S_ISREG(old_inode->i_mode) && new_inode->i_size &&
-	    old_inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT)
+	if (new_inode && S_ISREG(old_inode->i_mode) && new_inode->i_size)
 		filemap_flush(old_inode->i_mapping);
 
 	/* close the racy window with snapshot create/destroy ioctl */
@@ -8391,12 +8377,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		 */
 		btrfs_pin_log_trans(root);
 	}
-	/*
-	 * make sure the inode gets flushed if it is replacing
-	 * something.
-	 */
-	if (new_inode && new_inode->i_size && S_ISREG(old_inode->i_mode))
-		btrfs_add_ordered_operation(trans, root, old_inode);
 
 	inode_inc_iversion(old_dir);
 	inode_inc_iversion(new_dir);
@@ -8514,7 +8494,9 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
 	work->inode = inode;
 	work->wait = wait;
 	work->delay_iput = delay_iput;
-	btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
+	WARN_ON_ONCE(!inode);
+	btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
+			btrfs_run_delalloc_work, NULL, NULL);
 
 	return work;
 }
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 7187b14faa6c..ac734ec4cc20 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -571,18 +571,6 @@ void btrfs_remove_ordered_extent(struct inode *inode,
 
 	trace_btrfs_ordered_extent_remove(inode, entry);
 
-	/*
-	 * we have no more ordered extents for this inode and
-	 * no dirty pages.  We can safely remove it from the
-	 * list of ordered extents
-	 */
-	if (RB_EMPTY_ROOT(&tree->tree) &&
-	    !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) {
-		spin_lock(&root->fs_info->ordered_root_lock);
-		list_del_init(&BTRFS_I(inode)->ordered_operations);
-		spin_unlock(&root->fs_info->ordered_root_lock);
-	}
-
 	if (!root->nr_ordered_extents) {
 		spin_lock(&root->fs_info->ordered_root_lock);
 		BUG_ON(list_empty(&root->ordered_root));
@@ -627,6 +615,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr)
 		spin_unlock(&root->ordered_extent_lock);
 
 		btrfs_init_work(&ordered->flush_work,
+				btrfs_flush_delalloc_helper,
 				btrfs_run_ordered_extent_work, NULL, NULL);
 		list_add_tail(&ordered->work_list, &works);
 		btrfs_queue_work(root->fs_info->flush_workers,
@@ -687,81 +676,6 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr)
 }
 
 /*
- * this is used during transaction commit to write all the inodes
- * added to the ordered operation list.  These files must be fully on
- * disk before the transaction commits.
- *
- * we have two modes here, one is to just start the IO via filemap_flush
- * and the other is to wait for all the io.  When we wait, we have an
- * extra check to make sure the ordered operation list really is empty
- * before we return
- */
-int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans,
-				 struct btrfs_root *root, int wait)
-{
-	struct btrfs_inode *btrfs_inode;
-	struct inode *inode;
-	struct btrfs_transaction *cur_trans = trans->transaction;
-	struct list_head splice;
-	struct list_head works;
-	struct btrfs_delalloc_work *work, *next;
-	int ret = 0;
-
-	INIT_LIST_HEAD(&splice);
-	INIT_LIST_HEAD(&works);
-
-	mutex_lock(&root->fs_info->ordered_extent_flush_mutex);
-	spin_lock(&root->fs_info->ordered_root_lock);
-	list_splice_init(&cur_trans->ordered_operations, &splice);
-	while (!list_empty(&splice)) {
-		btrfs_inode = list_entry(splice.next, struct btrfs_inode,
-				   ordered_operations);
-		inode = &btrfs_inode->vfs_inode;
-
-		list_del_init(&btrfs_inode->ordered_operations);
-
-		/*
-		 * the inode may be getting freed (in sys_unlink path).
-		 */
-		inode = igrab(inode);
-		if (!inode)
-			continue;
-
-		if (!wait)
-			list_add_tail(&BTRFS_I(inode)->ordered_operations,
-				      &cur_trans->ordered_operations);
-		spin_unlock(&root->fs_info->ordered_root_lock);
-
-		work = btrfs_alloc_delalloc_work(inode, wait, 1);
-		if (!work) {
-			spin_lock(&root->fs_info->ordered_root_lock);
-			if (list_empty(&BTRFS_I(inode)->ordered_operations))
-				list_add_tail(&btrfs_inode->ordered_operations,
-					      &splice);
-			list_splice_tail(&splice,
-					 &cur_trans->ordered_operations);
-			spin_unlock(&root->fs_info->ordered_root_lock);
-			ret = -ENOMEM;
-			goto out;
-		}
-		list_add_tail(&work->list, &works);
-		btrfs_queue_work(root->fs_info->flush_workers,
-				 &work->work);
-
-		cond_resched();
-		spin_lock(&root->fs_info->ordered_root_lock);
-	}
-	spin_unlock(&root->fs_info->ordered_root_lock);
-out:
-	list_for_each_entry_safe(work, next, &works, list) {
-		list_del_init(&work->list);
-		btrfs_wait_and_free_delalloc_work(work);
-	}
-	mutex_unlock(&root->fs_info->ordered_extent_flush_mutex);
-	return ret;
-}
-
-/*
  * Used to start IO or wait for a given ordered extent to finish.
  *
  * If wait is one, this effectively waits on page writeback for all the pages
@@ -1120,42 +1034,6 @@ out:
 	return index;
 }
 
-
-/*
- * add a given inode to the list of inodes that must be fully on
- * disk before a transaction commit finishes.
- *
- * This basically gives us the ext3 style data=ordered mode, and it is mostly
- * used to make sure renamed files are fully on disk.
- *
- * It is a noop if the inode is already fully on disk.
- *
- * If trans is not null, we'll do a friendly check for a transaction that
- * is already flushing things and force the IO down ourselves.
- */
-void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
-				 struct btrfs_root *root, struct inode *inode)
-{
-	struct btrfs_transaction *cur_trans = trans->transaction;
-	u64 last_mod;
-
-	last_mod = max(BTRFS_I(inode)->generation, BTRFS_I(inode)->last_trans);
-
-	/*
-	 * if this file hasn't been changed since the last transaction
-	 * commit, we can safely return without doing anything
-	 */
-	if (last_mod <= root->fs_info->last_trans_committed)
-		return;
-
-	spin_lock(&root->fs_info->ordered_root_lock);
-	if (list_empty(&BTRFS_I(inode)->ordered_operations)) {
-		list_add_tail(&BTRFS_I(inode)->ordered_operations,
-			      &cur_trans->ordered_operations);
-	}
-	spin_unlock(&root->fs_info->ordered_root_lock);
-}
-
 int __init ordered_data_init(void)
 {
 	btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent",
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 246897058efb..d81a274d621e 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -190,11 +190,6 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 				struct btrfs_ordered_extent *ordered);
 int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
 			   u32 *sum, int len);
-int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans,
-				 struct btrfs_root *root, int wait);
-void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans,
-				 struct btrfs_root *root,
-				 struct inode *inode);
 int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr);
 void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr);
 void btrfs_get_logged_extents(struct inode *inode,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 98cb6b2630f9..3eec914710b2 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2551,6 +2551,7 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 	memset(&fs_info->qgroup_rescan_work, 0,
 	       sizeof(fs_info->qgroup_rescan_work));
 	btrfs_init_work(&fs_info->qgroup_rescan_work,
+			btrfs_qgroup_rescan_helper,
 			btrfs_qgroup_rescan_worker, NULL, NULL);
 
 	if (ret) {
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 4a88f073fdd7..0a6b6e4bcbb9 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1416,7 +1416,8 @@ cleanup:
 
 static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
 {
-	btrfs_init_work(&rbio->work, rmw_work, NULL, NULL);
+	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
+			rmw_work, NULL, NULL);
 
 	btrfs_queue_work(rbio->fs_info->rmw_workers,
 			 &rbio->work);
@@ -1424,7 +1425,8 @@ static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
 
 static void async_read_rebuild(struct btrfs_raid_bio *rbio)
 {
-	btrfs_init_work(&rbio->work, read_rebuild_work, NULL, NULL);
+	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
+			read_rebuild_work, NULL, NULL);
 
 	btrfs_queue_work(rbio->fs_info->rmw_workers,
 			 &rbio->work);
@@ -1665,7 +1667,8 @@ static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
 	plug = container_of(cb, struct btrfs_plug_cb, cb);
 
 	if (from_schedule) {
-		btrfs_init_work(&plug->work, unplug_work, NULL, NULL);
+		btrfs_init_work(&plug->work, btrfs_rmw_helper,
+				unplug_work, NULL, NULL);
 		btrfs_queue_work(plug->info->rmw_workers,
 				 &plug->work);
 		return;
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 09230cf3a244..20408c6b665a 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -798,7 +798,8 @@ static void reada_start_machine(struct btrfs_fs_info *fs_info)
 		/* FIXME we cannot handle this properly right now */
 		BUG();
 	}
-	btrfs_init_work(&rmw->work, reada_start_machine_worker, NULL, NULL);
+	btrfs_init_work(&rmw->work, btrfs_readahead_helper,
+			reada_start_machine_worker, NULL, NULL);
 	rmw->fs_info = fs_info;
 
 	btrfs_queue_work(fs_info->readahead_workers, &rmw->work);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index b6d198f5181e..8dddedcfa961 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -428,8 +428,8 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 		sbio->index = i;
 		sbio->sctx = sctx;
 		sbio->page_count = 0;
-		btrfs_init_work(&sbio->work, scrub_bio_end_io_worker,
-				NULL, NULL);
+		btrfs_init_work(&sbio->work, btrfs_scrub_helper,
+				scrub_bio_end_io_worker, NULL, NULL);
 
 		if (i != SCRUB_BIOS_PER_SCTX - 1)
 			sctx->bios[i]->next_free = i + 1;
@@ -999,8 +999,8 @@ nodatasum_case:
 		fixup_nodatasum->root = fs_info->extent_root;
 		fixup_nodatasum->mirror_num = failed_mirror_index + 1;
 		scrub_pending_trans_workers_inc(sctx);
-		btrfs_init_work(&fixup_nodatasum->work, scrub_fixup_nodatasum,
-				NULL, NULL);
+		btrfs_init_work(&fixup_nodatasum->work, btrfs_scrub_helper,
+				scrub_fixup_nodatasum, NULL, NULL);
 		btrfs_queue_work(fs_info->scrub_workers,
 				 &fixup_nodatasum->work);
 		goto out;
@@ -1616,7 +1616,8 @@ static void scrub_wr_bio_end_io(struct bio *bio, int err)
 	sbio->err = err;
 	sbio->bio = bio;
 
-	btrfs_init_work(&sbio->work, scrub_wr_bio_end_io_worker, NULL, NULL);
+	btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper,
+			 scrub_wr_bio_end_io_worker, NULL, NULL);
 	btrfs_queue_work(fs_info->scrub_wr_completion_workers, &sbio->work);
 }
 
@@ -3203,7 +3204,8 @@ static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 	nocow_ctx->len = len;
 	nocow_ctx->mirror_num = mirror_num;
 	nocow_ctx->physical_for_dev_replace = physical_for_dev_replace;
-	btrfs_init_work(&nocow_ctx->work, copy_nocow_pages_worker, NULL, NULL);
+	btrfs_init_work(&nocow_ctx->work, btrfs_scrubnc_helper,
+			copy_nocow_pages_worker, NULL, NULL);
 	INIT_LIST_HEAD(&nocow_ctx->inodes);
 	btrfs_queue_work(fs_info->scrub_nocow_workers,
 			 &nocow_ctx->work);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 5f379affdf23..d89c6d3542ca 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -218,7 +218,6 @@ loop:
 	spin_lock_init(&cur_trans->delayed_refs.lock);
 
 	INIT_LIST_HEAD(&cur_trans->pending_snapshots);
-	INIT_LIST_HEAD(&cur_trans->ordered_operations);
 	INIT_LIST_HEAD(&cur_trans->pending_chunks);
 	INIT_LIST_HEAD(&cur_trans->switch_commits);
 	list_add_tail(&cur_trans->list, &fs_info->trans_list);
@@ -1612,27 +1611,6 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans,
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
 }
 
-static int btrfs_flush_all_pending_stuffs(struct btrfs_trans_handle *trans,
-					  struct btrfs_root *root)
-{
-	int ret;
-
-	ret = btrfs_run_delayed_items(trans, root);
-	if (ret)
-		return ret;
-
-	/*
-	 * rename don't use btrfs_join_transaction, so, once we
-	 * set the transaction to blocked above, we aren't going
-	 * to get any new ordered operations.  We can safely run
-	 * it here and no for sure that nothing new will be added
-	 * to the list
-	 */
-	ret = btrfs_run_ordered_operations(trans, root, 1);
-
-	return ret;
-}
-
 static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
 {
 	if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT))
@@ -1653,13 +1631,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	struct btrfs_transaction *prev_trans = NULL;
 	int ret;
 
-	ret = btrfs_run_ordered_operations(trans, root, 0);
-	if (ret) {
-		btrfs_abort_transaction(trans, root, ret);
-		btrfs_end_transaction(trans, root);
-		return ret;
-	}
-
 	/* Stop the commit early if ->aborted is set */
 	if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
 		ret = cur_trans->aborted;
@@ -1740,7 +1711,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto cleanup_transaction;
 
-	ret = btrfs_flush_all_pending_stuffs(trans, root);
+	ret = btrfs_run_delayed_items(trans, root);
 	if (ret)
 		goto cleanup_transaction;
 
@@ -1748,7 +1719,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 		   extwriter_counter_read(cur_trans) == 0);
 
 	/* some pending stuffs might be added after the previous flush. */
-	ret = btrfs_flush_all_pending_stuffs(trans, root);
+	ret = btrfs_run_delayed_items(trans, root);
 	if (ret)
 		goto cleanup_transaction;
 
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 7dd558ed0716..579be51b27e5 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -55,7 +55,6 @@ struct btrfs_transaction {
 	wait_queue_head_t writer_wait;
 	wait_queue_head_t commit_wait;
 	struct list_head pending_snapshots;
-	struct list_head ordered_operations;
 	struct list_head pending_chunks;
 	struct list_head switch_commits;
 	struct btrfs_delayed_ref_root delayed_refs;
diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h
index 7f78cbf5cf41..4c29db604bbe 100644
--- a/fs/btrfs/ulist.h
+++ b/fs/btrfs/ulist.h
@@ -57,6 +57,21 @@ void ulist_free(struct ulist *ulist);
 int ulist_add(struct ulist *ulist, u64 val, u64 aux, gfp_t gfp_mask);
 int ulist_add_merge(struct ulist *ulist, u64 val, u64 aux,
 		    u64 *old_aux, gfp_t gfp_mask);
+
+/* just like ulist_add_merge() but take a pointer for the aux data */
+static inline int ulist_add_merge_ptr(struct ulist *ulist, u64 val, void *aux,
+				      void **old_aux, gfp_t gfp_mask)
+{
+#if BITS_PER_LONG == 32
+	u64 old64 = (uintptr_t)*old_aux;
+	int ret = ulist_add_merge(ulist, val, (uintptr_t)aux, &old64, gfp_mask);
+	*old_aux = (void *)((uintptr_t)old64);
+	return ret;
+#else
+	return ulist_add_merge(ulist, val, (u64)aux, (u64 *)old_aux, gfp_mask);
+#endif
+}
+
 struct ulist_node *ulist_next(struct ulist *ulist,
 			      struct ulist_iterator *uiter);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6cb82f62cb7c..81bec9fd8f19 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5800,7 +5800,8 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 	else
 		generate_random_uuid(dev->uuid);
 
-	btrfs_init_work(&dev->work, pending_bios_fn, NULL, NULL);
+	btrfs_init_work(&dev->work, btrfs_submit_helper,
+			pending_bios_fn, NULL, NULL);
 
 	return dev;
 }
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 8c41b52da358..16a46b6a6fee 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -534,7 +534,7 @@ EXPORT_SYMBOL_GPL(debugfs_remove);
  */
 void debugfs_remove_recursive(struct dentry *dentry)
 {
-	struct dentry *child, *next, *parent;
+	struct dentry *child, *parent;
 
 	if (IS_ERR_OR_NULL(dentry))
 		return;
@@ -546,30 +546,49 @@ void debugfs_remove_recursive(struct dentry *dentry)
 	parent = dentry;
  down:
 	mutex_lock(&parent->d_inode->i_mutex);
-	list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) {
+ loop:
+	/*
+	 * The parent->d_subdirs is protected by the d_lock. Outside that
+	 * lock, the child can be unlinked and set to be freed which can
+	 * use the d_u.d_child as the rcu head and corrupt this list.
+	 */
+	spin_lock(&parent->d_lock);
+	list_for_each_entry(child, &parent->d_subdirs, d_u.d_child) {
 		if (!debugfs_positive(child))
 			continue;
 
 		/* perhaps simple_empty(child) makes more sense */
 		if (!list_empty(&child->d_subdirs)) {
+			spin_unlock(&parent->d_lock);
 			mutex_unlock(&parent->d_inode->i_mutex);
 			parent = child;
 			goto down;
 		}
- up:
+
+		spin_unlock(&parent->d_lock);
+
 		if (!__debugfs_remove(child, parent))
 			simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+
+		/*
+		 * The parent->d_lock protects agaist child from unlinking
+		 * from d_subdirs. When releasing the parent->d_lock we can
+		 * no longer trust that the next pointer is valid.
+		 * Restart the loop. We'll skip this one with the
+		 * debugfs_positive() check.
+		 */
+		goto loop;
 	}
+	spin_unlock(&parent->d_lock);
 
 	mutex_unlock(&parent->d_inode->i_mutex);
 	child = parent;
 	parent = parent->d_parent;
 	mutex_lock(&parent->d_inode->i_mutex);
 
-	if (child != dentry) {
-		next = list_next_entry(child, d_u.d_child);
-		goto up;
-	}
+	if (child != dentry)
+		/* go up */
+		goto loop;
 
 	if (!__debugfs_remove(child, parent))
 		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 7cc5a0e23688..1bbe7c315138 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2144,8 +2144,8 @@ extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
 extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
 extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
 extern void ext4_ind_truncate(handle_t *, struct inode *inode);
-extern int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
-				 ext4_lblk_t first, ext4_lblk_t stop);
+extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
+				 ext4_lblk_t start, ext4_lblk_t end);
 
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
@@ -2453,6 +2453,22 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
 	up_write(&EXT4_I(inode)->i_data_sem);
 }
 
+/* Update i_size, i_disksize. Requires i_mutex to avoid races with truncate */
+static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize)
+{
+	int changed = 0;
+
+	if (newsize > inode->i_size) {
+		i_size_write(inode, newsize);
+		changed = 1;
+	}
+	if (newsize > EXT4_I(inode)->i_disksize) {
+		ext4_update_i_disksize(inode, newsize);
+		changed |= 2;
+	}
+	return changed;
+}
+
 struct ext4_group_info {
 	unsigned long   bb_state;
 	struct rb_root  bb_free_root;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 4da228a0e6d0..7dfd6300e1c2 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4664,7 +4664,8 @@ retry:
 }
 
 static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
-				  ext4_lblk_t len, int flags, int mode)
+				  ext4_lblk_t len, loff_t new_size,
+				  int flags, int mode)
 {
 	struct inode *inode = file_inode(file);
 	handle_t *handle;
@@ -4673,8 +4674,10 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 	int retries = 0;
 	struct ext4_map_blocks map;
 	unsigned int credits;
+	loff_t epos;
 
 	map.m_lblk = offset;
+	map.m_len = len;
 	/*
 	 * Don't normalize the request if it can fit in one extent so
 	 * that it doesn't get unnecessarily split into multiple
@@ -4689,9 +4692,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 	credits = ext4_chunk_trans_blocks(inode, len);
 
 retry:
-	while (ret >= 0 && ret < len) {
-		map.m_lblk = map.m_lblk + ret;
-		map.m_len = len = len - ret;
+	while (ret >= 0 && len) {
 		handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
 					    credits);
 		if (IS_ERR(handle)) {
@@ -4708,6 +4709,21 @@ retry:
 			ret2 = ext4_journal_stop(handle);
 			break;
 		}
+		map.m_lblk += ret;
+		map.m_len = len = len - ret;
+		epos = (loff_t)map.m_lblk << inode->i_blkbits;
+		inode->i_ctime = ext4_current_time(inode);
+		if (new_size) {
+			if (epos > new_size)
+				epos = new_size;
+			if (ext4_update_inode_size(inode, epos) & 0x1)
+				inode->i_mtime = inode->i_ctime;
+		} else {
+			if (epos > inode->i_size)
+				ext4_set_inode_flag(inode,
+						    EXT4_INODE_EOFBLOCKS);
+		}
+		ext4_mark_inode_dirty(handle, inode);
 		ret2 = ext4_journal_stop(handle);
 		if (ret2)
 			break;
@@ -4730,7 +4746,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	loff_t new_size = 0;
 	int ret = 0;
 	int flags;
-	int partial;
+	int credits;
+	int partial_begin, partial_end;
 	loff_t start, end;
 	ext4_lblk_t lblk;
 	struct address_space *mapping = inode->i_mapping;
@@ -4770,7 +4787,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 	if (start < offset || end > offset + len)
 		return -EINVAL;
-	partial = (offset + len) & ((1 << blkbits) - 1);
+	partial_begin = offset & ((1 << blkbits) - 1);
+	partial_end = (offset + len) & ((1 << blkbits) - 1);
 
 	lblk = start >> blkbits;
 	max_blocks = (end >> blkbits);
@@ -4804,7 +4822,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		 * If we have a partial block after EOF we have to allocate
 		 * the entire block.
 		 */
-		if (partial)
+		if (partial_end)
 			max_blocks += 1;
 	}
 
@@ -4812,6 +4830,7 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 		/* Now release the pages and zero block aligned part of pages*/
 		truncate_pagecache_range(inode, start, end - 1);
+		inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
 
 		/* Wait all existing dio workers, newcomers will block on i_mutex */
 		ext4_inode_block_unlocked_dio(inode);
@@ -4824,13 +4843,22 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		if (ret)
 			goto out_dio;
 
-		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags,
-					     mode);
+		ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
+					     flags, mode);
 		if (ret)
 			goto out_dio;
 	}
+	if (!partial_begin && !partial_end)
+		goto out_dio;
 
-	handle = ext4_journal_start(inode, EXT4_HT_MISC, 4);
+	/*
+	 * In worst case we have to writeout two nonadjacent unwritten
+	 * blocks and update the inode
+	 */
+	credits = (2 * ext4_ext_index_trans_blocks(inode, 2)) + 1;
+	if (ext4_should_journal_data(inode))
+		credits += 2;
+	handle = ext4_journal_start(inode, EXT4_HT_MISC, credits);
 	if (IS_ERR(handle)) {
 		ret = PTR_ERR(handle);
 		ext4_std_error(inode->i_sb, ret);
@@ -4838,12 +4866,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 	}
 
 	inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
-
 	if (new_size) {
-		if (new_size > i_size_read(inode))
-			i_size_write(inode, new_size);
-		if (new_size > EXT4_I(inode)->i_disksize)
-			ext4_update_i_disksize(inode, new_size);
+		ext4_update_inode_size(inode, new_size);
 	} else {
 		/*
 		* Mark that we allocate beyond EOF so the subsequent truncate
@@ -4852,7 +4876,6 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		if ((offset + len) > i_size_read(inode))
 			ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
 	}
-
 	ext4_mark_inode_dirty(handle, inode);
 
 	/* Zero out partial block at the edges of the range */
@@ -4879,13 +4902,11 @@ out_mutex:
 long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(file);
-	handle_t *handle;
 	loff_t new_size = 0;
 	unsigned int max_blocks;
 	int ret = 0;
 	int flags;
 	ext4_lblk_t lblk;
-	struct timespec tv;
 	unsigned int blkbits = inode->i_blkbits;
 
 	/* Return error if mode is not supported */
@@ -4936,36 +4957,15 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 			goto out;
 	}
 
-	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, flags, mode);
+	ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size,
+				     flags, mode);
 	if (ret)
 		goto out;
 
-	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
-	if (IS_ERR(handle))
-		goto out;
-
-	tv = inode->i_ctime = ext4_current_time(inode);
-
-	if (new_size) {
-		if (new_size > i_size_read(inode)) {
-			i_size_write(inode, new_size);
-			inode->i_mtime = tv;
-		}
-		if (new_size > EXT4_I(inode)->i_disksize)
-			ext4_update_i_disksize(inode, new_size);
-	} else {
-		/*
-		* Mark that we allocate beyond EOF so the subsequent truncate
-		* can proceed even if the new size is the same as i_size.
-		*/
-		if ((offset + len) > i_size_read(inode))
-			ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
+	if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) {
+		ret = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
+						EXT4_I(inode)->i_sync_tid);
 	}
-	ext4_mark_inode_dirty(handle, inode);
-	if (file->f_flags & O_SYNC)
-		ext4_handle_sync(handle);
-
-	ext4_journal_stop(handle);
 out:
 	mutex_unlock(&inode->i_mutex);
 	trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index fd69da194826..e75f840000a0 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -1295,97 +1295,220 @@ do_indirects:
 	}
 }
 
-static int free_hole_blocks(handle_t *handle, struct inode *inode,
-			    struct buffer_head *parent_bh, __le32 *i_data,
-			    int level, ext4_lblk_t first,
-			    ext4_lblk_t count, int max)
+/**
+ *	ext4_ind_remove_space - remove space from the range
+ *	@handle: JBD handle for this transaction
+ *	@inode:	inode we are dealing with
+ *	@start:	First block to remove
+ *	@end:	One block after the last block to remove (exclusive)
+ *
+ *	Free the blocks in the defined range (end is exclusive endpoint of
+ *	range). This is used by ext4_punch_hole().
+ */
+int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
+			  ext4_lblk_t start, ext4_lblk_t end)
 {
-	struct buffer_head *bh = NULL;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	__le32 *i_data = ei->i_data;
 	int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
-	int ret = 0;
-	int i, inc;
-	ext4_lblk_t offset;
-	__le32 blk;
-
-	inc = 1 << ((EXT4_BLOCK_SIZE_BITS(inode->i_sb) - 2) * level);
-	for (i = 0, offset = 0; i < max; i++, i_data++, offset += inc) {
-		if (offset >= count + first)
-			break;
-		if (*i_data == 0 || (offset + inc) <= first)
-			continue;
-		blk = *i_data;
-		if (level > 0) {
-			ext4_lblk_t first2;
-			ext4_lblk_t count2;
+	ext4_lblk_t offsets[4], offsets2[4];
+	Indirect chain[4], chain2[4];
+	Indirect *partial, *partial2;
+	ext4_lblk_t max_block;
+	__le32 nr = 0, nr2 = 0;
+	int n = 0, n2 = 0;
+	unsigned blocksize = inode->i_sb->s_blocksize;
 
-			bh = sb_bread(inode->i_sb, le32_to_cpu(blk));
-			if (!bh) {
-				EXT4_ERROR_INODE_BLOCK(inode, le32_to_cpu(blk),
-						       "Read failure");
-				return -EIO;
-			}
-			if (first > offset) {
-				first2 = first - offset;
-				count2 = count;
+	max_block = (EXT4_SB(inode->i_sb)->s_bitmap_maxbytes + blocksize-1)
+					>> EXT4_BLOCK_SIZE_BITS(inode->i_sb);
+	if (end >= max_block)
+		end = max_block;
+	if ((start >= end) || (start > max_block))
+		return 0;
+
+	n = ext4_block_to_path(inode, start, offsets, NULL);
+	n2 = ext4_block_to_path(inode, end, offsets2, NULL);
+
+	BUG_ON(n > n2);
+
+	if ((n == 1) && (n == n2)) {
+		/* We're punching only within direct block range */
+		ext4_free_data(handle, inode, NULL, i_data + offsets[0],
+			       i_data + offsets2[0]);
+		return 0;
+	} else if (n2 > n) {
+		/*
+		 * Start and end are on a different levels so we're going to
+		 * free partial block at start, and partial block at end of
+		 * the range. If there are some levels in between then
+		 * do_indirects label will take care of that.
+		 */
+
+		if (n == 1) {
+			/*
+			 * Start is at the direct block level, free
+			 * everything to the end of the level.
+			 */
+			ext4_free_data(handle, inode, NULL, i_data + offsets[0],
+				       i_data + EXT4_NDIR_BLOCKS);
+			goto end_range;
+		}
+
+
+		partial = ext4_find_shared(inode, n, offsets, chain, &nr);
+		if (nr) {
+			if (partial == chain) {
+				/* Shared branch grows from the inode */
+				ext4_free_branches(handle, inode, NULL,
+					   &nr, &nr+1, (chain+n-1) - partial);
+				*partial->p = 0;
 			} else {
-				first2 = 0;
-				count2 = count - (offset - first);
+				/* Shared branch grows from an indirect block */
+				BUFFER_TRACE(partial->bh, "get_write_access");
+				ext4_free_branches(handle, inode, partial->bh,
+					partial->p,
+					partial->p+1, (chain+n-1) - partial);
 			}
-			ret = free_hole_blocks(handle, inode, bh,
-					       (__le32 *)bh->b_data, level - 1,
-					       first2, count2,
-					       inode->i_sb->s_blocksize >> 2);
-			if (ret) {
-				brelse(bh);
-				goto err;
+		}
+
+		/*
+		 * Clear the ends of indirect blocks on the shared branch
+		 * at the start of the range
+		 */
+		while (partial > chain) {
+			ext4_free_branches(handle, inode, partial->bh,
+				partial->p + 1,
+				(__le32 *)partial->bh->b_data+addr_per_block,
+				(chain+n-1) - partial);
+			BUFFER_TRACE(partial->bh, "call brelse");
+			brelse(partial->bh);
+			partial--;
+		}
+
+end_range:
+		partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
+		if (nr2) {
+			if (partial2 == chain2) {
+				/*
+				 * Remember, end is exclusive so here we're at
+				 * the start of the next level we're not going
+				 * to free. Everything was covered by the start
+				 * of the range.
+				 */
+				return 0;
+			} else {
+				/* Shared branch grows from an indirect block */
+				partial2--;
 			}
+		} else {
+			/*
+			 * ext4_find_shared returns Indirect structure which
+			 * points to the last element which should not be
+			 * removed by truncate. But this is end of the range
+			 * in punch_hole so we need to point to the next element
+			 */
+			partial2->p++;
 		}
-		if (level == 0 ||
-		    (bh && all_zeroes((__le32 *)bh->b_data,
-				      (__le32 *)bh->b_data + addr_per_block))) {
-			ext4_free_data(handle, inode, parent_bh,
-				       i_data, i_data + 1);
+
+		/*
+		 * Clear the ends of indirect blocks on the shared branch
+		 * at the end of the range
+		 */
+		while (partial2 > chain2) {
+			ext4_free_branches(handle, inode, partial2->bh,
+					   (__le32 *)partial2->bh->b_data,
+					   partial2->p,
+					   (chain2+n2-1) - partial2);
+			BUFFER_TRACE(partial2->bh, "call brelse");
+			brelse(partial2->bh);
+			partial2--;
 		}
-		brelse(bh);
-		bh = NULL;
+		goto do_indirects;
 	}
 
-err:
-	return ret;
-}
-
-int ext4_free_hole_blocks(handle_t *handle, struct inode *inode,
-			  ext4_lblk_t first, ext4_lblk_t stop)
-{
-	int addr_per_block = EXT4_ADDR_PER_BLOCK(inode->i_sb);
-	int level, ret = 0;
-	int num = EXT4_NDIR_BLOCKS;
-	ext4_lblk_t count, max = EXT4_NDIR_BLOCKS;
-	__le32 *i_data = EXT4_I(inode)->i_data;
-
-	count = stop - first;
-	for (level = 0; level < 4; level++, max *= addr_per_block) {
-		if (first < max) {
-			ret = free_hole_blocks(handle, inode, NULL, i_data,
-					       level, first, count, num);
-			if (ret)
-				goto err;
-			if (count > max - first)
-				count -= max - first;
-			else
-				break;
-			first = 0;
-		} else {
-			first -= max;
+	/* Punch happened within the same level (n == n2) */
+	partial = ext4_find_shared(inode, n, offsets, chain, &nr);
+	partial2 = ext4_find_shared(inode, n2, offsets2, chain2, &nr2);
+	/*
+	 * ext4_find_shared returns Indirect structure which
+	 * points to the last element which should not be
+	 * removed by truncate. But this is end of the range
+	 * in punch_hole so we need to point to the next element
+	 */
+	partial2->p++;
+	while ((partial > chain) || (partial2 > chain2)) {
+		/* We're at the same block, so we're almost finished */
+		if ((partial->bh && partial2->bh) &&
+		    (partial->bh->b_blocknr == partial2->bh->b_blocknr)) {
+			if ((partial > chain) && (partial2 > chain2)) {
+				ext4_free_branches(handle, inode, partial->bh,
+						   partial->p + 1,
+						   partial2->p,
+						   (chain+n-1) - partial);
+				BUFFER_TRACE(partial->bh, "call brelse");
+				brelse(partial->bh);
+				BUFFER_TRACE(partial2->bh, "call brelse");
+				brelse(partial2->bh);
+			}
+			return 0;
 		}
-		i_data += num;
-		if (level == 0) {
-			num = 1;
-			max = 1;
+		/*
+		 * Clear the ends of indirect blocks on the shared branch
+		 * at the start of the range
+		 */
+		if (partial > chain) {
+			ext4_free_branches(handle, inode, partial->bh,
+				   partial->p + 1,
+				   (__le32 *)partial->bh->b_data+addr_per_block,
+				   (chain+n-1) - partial);
+			BUFFER_TRACE(partial->bh, "call brelse");
+			brelse(partial->bh);
+			partial--;
+		}
+		/*
+		 * Clear the ends of indirect blocks on the shared branch
+		 * at the end of the range
+		 */
+		if (partial2 > chain2) {
+			ext4_free_branches(handle, inode, partial2->bh,
+					   (__le32 *)partial2->bh->b_data,
+					   partial2->p,
+					   (chain2+n-1) - partial2);
+			BUFFER_TRACE(partial2->bh, "call brelse");
+			brelse(partial2->bh);
+			partial2--;
 		}
 	}
 
-err:
-	return ret;
+do_indirects:
+	/* Kill the remaining (whole) subtrees */
+	switch (offsets[0]) {
+	default:
+		if (++n >= n2)
+			return 0;
+		nr = i_data[EXT4_IND_BLOCK];
+		if (nr) {
+			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1);
+			i_data[EXT4_IND_BLOCK] = 0;
+		}
+	case EXT4_IND_BLOCK:
+		if (++n >= n2)
+			return 0;
+		nr = i_data[EXT4_DIND_BLOCK];
+		if (nr) {
+			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2);
+			i_data[EXT4_DIND_BLOCK] = 0;
+		}
+	case EXT4_DIND_BLOCK:
+		if (++n >= n2)
+			return 0;
+		nr = i_data[EXT4_TIND_BLOCK];
+		if (nr) {
+			ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3);
+			i_data[EXT4_TIND_BLOCK] = 0;
+		}
+	case EXT4_TIND_BLOCK:
+		;
+	}
+	return 0;
 }
-
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 8a064734e6eb..e9c9b5bd906a 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1092,27 +1092,11 @@ static int ext4_write_end(struct file *file,
 	} else
 		copied = block_write_end(file, mapping, pos,
 					 len, copied, page, fsdata);
-
 	/*
-	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hole i_mutex.
-	 *
-	 * But it's important to update i_size while still holding page lock:
+	 * it's important to update i_size while still holding page lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
 	 */
-	if (pos + copied > inode->i_size) {
-		i_size_write(inode, pos + copied);
-		i_size_changed = 1;
-	}
-
-	if (pos + copied > EXT4_I(inode)->i_disksize) {
-		/* We need to mark inode dirty even if
-		 * new_i_size is less that inode->i_size
-		 * but greater than i_disksize. (hint delalloc)
-		 */
-		ext4_update_i_disksize(inode, (pos + copied));
-		i_size_changed = 1;
-	}
+	i_size_changed = ext4_update_inode_size(inode, pos + copied);
 	unlock_page(page);
 	page_cache_release(page);
 
@@ -1160,7 +1144,7 @@ static int ext4_journalled_write_end(struct file *file,
 	int ret = 0, ret2;
 	int partial = 0;
 	unsigned from, to;
-	loff_t new_i_size;
+	int size_changed = 0;
 
 	trace_ext4_journalled_write_end(inode, pos, len, copied);
 	from = pos & (PAGE_CACHE_SIZE - 1);
@@ -1183,20 +1167,18 @@ static int ext4_journalled_write_end(struct file *file,
 		if (!partial)
 			SetPageUptodate(page);
 	}
-	new_i_size = pos + copied;
-	if (new_i_size > inode->i_size)
-		i_size_write(inode, pos+copied);
+	size_changed = ext4_update_inode_size(inode, pos + copied);
 	ext4_set_inode_state(inode, EXT4_STATE_JDATA);
 	EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
-	if (new_i_size > EXT4_I(inode)->i_disksize) {
-		ext4_update_i_disksize(inode, new_i_size);
+	unlock_page(page);
+	page_cache_release(page);
+
+	if (size_changed) {
 		ret2 = ext4_mark_inode_dirty(handle, inode);
 		if (!ret)
 			ret = ret2;
 	}
 
-	unlock_page(page);
-	page_cache_release(page);
 	if (pos + len > inode->i_size && ext4_can_truncate(inode))
 		/* if we have allocated more blocks and copied
 		 * less. We will have blocks allocated outside
@@ -2212,6 +2194,7 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 	struct ext4_map_blocks *map = &mpd->map;
 	int err;
 	loff_t disksize;
+	int progress = 0;
 
 	mpd->io_submit.io_end->offset =
 				((loff_t)map->m_lblk) << inode->i_blkbits;
@@ -2228,8 +2211,11 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 			 * is non-zero, a commit should free up blocks.
 			 */
 			if ((err == -ENOMEM) ||
-			    (err == -ENOSPC && ext4_count_free_clusters(sb)))
+			    (err == -ENOSPC && ext4_count_free_clusters(sb))) {
+				if (progress)
+					goto update_disksize;
 				return err;
+			}
 			ext4_msg(sb, KERN_CRIT,
 				 "Delayed block allocation failed for "
 				 "inode %lu at logical offset %llu with"
@@ -2246,15 +2232,17 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 			*give_up_on_write = true;
 			return err;
 		}
+		progress = 1;
 		/*
 		 * Update buffer state, submit mapped pages, and get us new
 		 * extent to map
 		 */
 		err = mpage_map_and_submit_buffers(mpd);
 		if (err < 0)
-			return err;
+			goto update_disksize;
 	} while (map->m_len);
 
+update_disksize:
 	/*
 	 * Update on-disk size after IO is submitted.  Races with
 	 * truncate are avoided by checking i_size under i_data_sem.
@@ -3624,7 +3612,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 		ret = ext4_ext_remove_space(inode, first_block,
 					    stop_block - 1);
 	else
-		ret = ext4_free_hole_blocks(handle, inode, first_block,
+		ret = ext4_ind_remove_space(handle, inode, first_block,
 					    stop_block);
 
 	up_write(&EXT4_I(inode)->i_data_sem);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 2dcb936be90e..c3e7418a6811 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1412,6 +1412,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
 	int last = first + count - 1;
 	struct super_block *sb = e4b->bd_sb;
 
+	if (WARN_ON(count == 0))
+		return;
 	BUG_ON(last >= (sb->s_blocksize << 3));
 	assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
 	/* Don't bother if the block group is corrupt. */
@@ -3216,8 +3218,30 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac)
 static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
 {
 	struct ext4_prealloc_space *pa = ac->ac_pa;
+	struct ext4_buddy e4b;
+	int err;
 
-	if (pa && pa->pa_type == MB_INODE_PA)
+	if (pa == NULL) {
+		if (ac->ac_f_ex.fe_len == 0)
+			return;
+		err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b);
+		if (err) {
+			/*
+			 * This should never happen since we pin the
+			 * pages in the ext4_allocation_context so
+			 * ext4_mb_load_buddy() should never fail.
+			 */
+			WARN(1, "mb_load_buddy failed (%d)", err);
+			return;
+		}
+		ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
+		mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start,
+			       ac->ac_f_ex.fe_len);
+		ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group);
+		ext4_mb_unload_buddy(&e4b);
+		return;
+	}
+	if (pa->pa_type == MB_INODE_PA)
 		pa->pa_free += ac->ac_b_ex.fe_len;
 }
 
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 3520ab8a6639..9e6eced1605b 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -3128,7 +3128,8 @@ static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
 	return retval;
 }
 
-static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent)
+static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent,
+			       int force_reread)
 {
 	int retval;
 	/*
@@ -3140,7 +3141,8 @@ static void ext4_rename_delete(handle_t *handle, struct ext4_renament *ent)
 	if (le32_to_cpu(ent->de->inode) != ent->inode->i_ino ||
 	    ent->de->name_len != ent->dentry->d_name.len ||
 	    strncmp(ent->de->name, ent->dentry->d_name.name,
-		    ent->de->name_len)) {
+		    ent->de->name_len) ||
+	    force_reread) {
 		retval = ext4_find_delete_entry(handle, ent->dir,
 						&ent->dentry->d_name);
 	} else {
@@ -3191,6 +3193,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		.dentry = new_dentry,
 		.inode = new_dentry->d_inode,
 	};
+	int force_reread;
 	int retval;
 
 	dquot_initialize(old.dir);
@@ -3246,6 +3249,15 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (retval)
 			goto end_rename;
 	}
+	/*
+	 * If we're renaming a file within an inline_data dir and adding or
+	 * setting the new dirent causes a conversion from inline_data to
+	 * extents/blockmap, we need to force the dirent delete code to
+	 * re-read the directory, or else we end up trying to delete a dirent
+	 * from what is now the extent tree root (or a block map).
+	 */
+	force_reread = (new.dir->i_ino == old.dir->i_ino &&
+			ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA));
 	if (!new.bh) {
 		retval = ext4_add_entry(handle, new.dentry, old.inode);
 		if (retval)
@@ -3256,6 +3268,9 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (retval)
 			goto end_rename;
 	}
+	if (force_reread)
+		force_reread = !ext4_test_inode_flag(new.dir,
+						     EXT4_INODE_INLINE_DATA);
 
 	/*
 	 * Like most other Unix systems, set the ctime for inodes on a
@@ -3267,7 +3282,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 	/*
 	 * ok, that's it
 	 */
-	ext4_rename_delete(handle, &old);
+	ext4_rename_delete(handle, &old, force_reread);
 
 	if (new.inode) {
 		ext4_dec_count(handle, new.inode);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6df7bc611dbd..beeb5c4e1f9d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3185,9 +3185,9 @@ static int set_journal_csum_feature_set(struct super_block *sb)
 
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
 				       EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
-		/* journal checksum v2 */
+		/* journal checksum v3 */
 		compat = 0;
-		incompat = JBD2_FEATURE_INCOMPAT_CSUM_V2;
+		incompat = JBD2_FEATURE_INCOMPAT_CSUM_V3;
 	} else {
 		/* journal checksum v1 */
 		compat = JBD2_FEATURE_COMPAT_CHECKSUM;
@@ -3209,6 +3209,7 @@ static int set_journal_csum_feature_set(struct super_block *sb)
 		jbd2_journal_clear_features(sbi->s_journal,
 				JBD2_FEATURE_COMPAT_CHECKSUM, 0,
 				JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT |
+				JBD2_FEATURE_INCOMPAT_CSUM_V3 |
 				JBD2_FEATURE_INCOMPAT_CSUM_V2);
 	}
 
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 4556ce1af5b0..5ddaf8625d3b 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -61,7 +61,7 @@ static void isofs_put_super(struct super_block *sb)
 	return;
 }
 
-static int isofs_read_inode(struct inode *);
+static int isofs_read_inode(struct inode *, int relocated);
 static int isofs_statfs (struct dentry *, struct kstatfs *);
 
 static struct kmem_cache *isofs_inode_cachep;
@@ -1259,7 +1259,7 @@ out_toomany:
 	goto out;
 }
 
-static int isofs_read_inode(struct inode *inode)
+static int isofs_read_inode(struct inode *inode, int relocated)
 {
 	struct super_block *sb = inode->i_sb;
 	struct isofs_sb_info *sbi = ISOFS_SB(sb);
@@ -1404,7 +1404,7 @@ static int isofs_read_inode(struct inode *inode)
 	 */
 
 	if (!high_sierra) {
-		parse_rock_ridge_inode(de, inode);
+		parse_rock_ridge_inode(de, inode, relocated);
 		/* if we want uid/gid set, override the rock ridge setting */
 		if (sbi->s_uid_set)
 			inode->i_uid = sbi->s_uid;
@@ -1483,9 +1483,10 @@ static int isofs_iget5_set(struct inode *ino, void *data)
  * offset that point to the underlying meta-data for the inode.  The
  * code below is otherwise similar to the iget() code in
  * include/linux/fs.h */
-struct inode *isofs_iget(struct super_block *sb,
-			 unsigned long block,
-			 unsigned long offset)
+struct inode *__isofs_iget(struct super_block *sb,
+			   unsigned long block,
+			   unsigned long offset,
+			   int relocated)
 {
 	unsigned long hashval;
 	struct inode *inode;
@@ -1507,7 +1508,7 @@ struct inode *isofs_iget(struct super_block *sb,
 		return ERR_PTR(-ENOMEM);
 
 	if (inode->i_state & I_NEW) {
-		ret = isofs_read_inode(inode);
+		ret = isofs_read_inode(inode, relocated);
 		if (ret < 0) {
 			iget_failed(inode);
 			inode = ERR_PTR(ret);
diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h
index 99167238518d..0ac4c1f73fbd 100644
--- a/fs/isofs/isofs.h
+++ b/fs/isofs/isofs.h
@@ -107,7 +107,7 @@ extern int iso_date(char *, int);
 
 struct inode;		/* To make gcc happy */
 
-extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *);
+extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *, int relocated);
 extern int get_rock_ridge_filename(struct iso_directory_record *, char *, struct inode *);
 extern int isofs_name_translate(struct iso_directory_record *, char *, struct inode *);
 
@@ -118,9 +118,24 @@ extern struct dentry *isofs_lookup(struct inode *, struct dentry *, unsigned int
 extern struct buffer_head *isofs_bread(struct inode *, sector_t);
 extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long);
 
-extern struct inode *isofs_iget(struct super_block *sb,
-                                unsigned long block,
-                                unsigned long offset);
+struct inode *__isofs_iget(struct super_block *sb,
+			   unsigned long block,
+			   unsigned long offset,
+			   int relocated);
+
+static inline struct inode *isofs_iget(struct super_block *sb,
+				       unsigned long block,
+				       unsigned long offset)
+{
+	return __isofs_iget(sb, block, offset, 0);
+}
+
+static inline struct inode *isofs_iget_reloc(struct super_block *sb,
+					     unsigned long block,
+					     unsigned long offset)
+{
+	return __isofs_iget(sb, block, offset, 1);
+}
 
 /* Because the inode number is no longer relevant to finding the
  * underlying meta-data for an inode, we are free to choose a more
diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c
index c0bf42472e40..f488bbae541a 100644
--- a/fs/isofs/rock.c
+++ b/fs/isofs/rock.c
@@ -288,12 +288,16 @@ eio:
 	goto out;
 }
 
+#define RR_REGARD_XA 1
+#define RR_RELOC_DE 2
+
 static int
 parse_rock_ridge_inode_internal(struct iso_directory_record *de,
-				struct inode *inode, int regard_xa)
+				struct inode *inode, int flags)
 {
 	int symlink_len = 0;
 	int cnt, sig;
+	unsigned int reloc_block;
 	struct inode *reloc;
 	struct rock_ridge *rr;
 	int rootflag;
@@ -305,7 +309,7 @@ parse_rock_ridge_inode_internal(struct iso_directory_record *de,
 
 	init_rock_state(&rs, inode);
 	setup_rock_ridge(de, inode, &rs);
-	if (regard_xa) {
+	if (flags & RR_REGARD_XA) {
 		rs.chr += 14;
 		rs.len -= 14;
 		if (rs.len < 0)
@@ -485,12 +489,22 @@ repeat:
 					"relocated directory\n");
 			goto out;
 		case SIG('C', 'L'):
-			ISOFS_I(inode)->i_first_extent =
-			    isonum_733(rr->u.CL.location);
-			reloc =
-			    isofs_iget(inode->i_sb,
-				       ISOFS_I(inode)->i_first_extent,
-				       0);
+			if (flags & RR_RELOC_DE) {
+				printk(KERN_ERR
+				       "ISOFS: Recursive directory relocation "
+				       "is not supported\n");
+				goto eio;
+			}
+			reloc_block = isonum_733(rr->u.CL.location);
+			if (reloc_block == ISOFS_I(inode)->i_iget5_block &&
+			    ISOFS_I(inode)->i_iget5_offset == 0) {
+				printk(KERN_ERR
+				       "ISOFS: Directory relocation points to "
+				       "itself\n");
+				goto eio;
+			}
+			ISOFS_I(inode)->i_first_extent = reloc_block;
+			reloc = isofs_iget_reloc(inode->i_sb, reloc_block, 0);
 			if (IS_ERR(reloc)) {
 				ret = PTR_ERR(reloc);
 				goto out;
@@ -637,9 +651,11 @@ static char *get_symlink_chunk(char *rpnt, struct rock_ridge *rr, char *plimit)
 	return rpnt;
 }
 
-int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode)
+int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode,
+			   int relocated)
 {
-	int result = parse_rock_ridge_inode_internal(de, inode, 0);
+	int flags = relocated ? RR_RELOC_DE : 0;
+	int result = parse_rock_ridge_inode_internal(de, inode, flags);
 
 	/*
 	 * if rockridge flag was reset and we didn't look for attributes
@@ -647,7 +663,8 @@ int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode)
 	 */
 	if ((ISOFS_SB(inode->i_sb)->s_rock_offset == -1)
 	    && (ISOFS_SB(inode->i_sb)->s_rock == 2)) {
-		result = parse_rock_ridge_inode_internal(de, inode, 14);
+		result = parse_rock_ridge_inode_internal(de, inode,
+							 flags | RR_REGARD_XA);
 	}
 	return result;
 }
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6fac74349856..b73e0215baa7 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -97,7 +97,7 @@ static void jbd2_commit_block_csum_set(journal_t *j, struct buffer_head *bh)
 	struct commit_header *h;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	h = (struct commit_header *)(bh->b_data);
@@ -313,11 +313,11 @@ static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh)
 	return checksum;
 }
 
-static void write_tag_block(int tag_bytes, journal_block_tag_t *tag,
+static void write_tag_block(journal_t *j, journal_block_tag_t *tag,
 				   unsigned long long block)
 {
 	tag->t_blocknr = cpu_to_be32(block & (u32)~0);
-	if (tag_bytes > JBD2_TAG_SIZE32)
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_64BIT))
 		tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1);
 }
 
@@ -327,7 +327,7 @@ static void jbd2_descr_block_csum_set(journal_t *j,
 	struct jbd2_journal_block_tail *tail;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize -
@@ -340,12 +340,13 @@ static void jbd2_descr_block_csum_set(journal_t *j,
 static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 				    struct buffer_head *bh, __u32 sequence)
 {
+	journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
 	struct page *page = bh->b_page;
 	__u8 *addr;
 	__u32 csum32;
 	__be32 seq;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	seq = cpu_to_be32(sequence);
@@ -355,8 +356,10 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
 			     bh->b_size);
 	kunmap_atomic(addr);
 
-	/* We only have space to store the lower 16 bits of the crc32c. */
-	tag->t_checksum = cpu_to_be16(csum32);
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		tag3->t_checksum = cpu_to_be32(csum32);
+	else
+		tag->t_checksum = cpu_to_be16(csum32);
 }
 /*
  * jbd2_journal_commit_transaction
@@ -396,7 +399,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	LIST_HEAD(io_bufs);
 	LIST_HEAD(log_bufs);
 
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		csum_size = sizeof(struct jbd2_journal_block_tail);
 
 	/*
@@ -690,7 +693,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			tag_flag |= JBD2_FLAG_SAME_UUID;
 
 		tag = (journal_block_tag_t *) tagp;
-		write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr);
+		write_tag_block(journal, tag, jh2bh(jh)->b_blocknr);
 		tag->t_flags = cpu_to_be16(tag_flag);
 		jbd2_block_tag_csum_set(journal, tag, wbuf[bufs],
 					commit_transaction->t_tid);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 67b8e303946c..19d74d86d99c 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -124,7 +124,7 @@ EXPORT_SYMBOL(__jbd2_debug);
 /* Checksumming functions */
 static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	return sb->s_checksum_type == JBD2_CRC32C_CHKSUM;
@@ -145,7 +145,7 @@ static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb)
 
 static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	return sb->s_checksum == jbd2_superblock_csum(j, sb);
@@ -153,7 +153,7 @@ static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb)
 
 static void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb)
 {
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	sb->s_checksum = jbd2_superblock_csum(j, sb);
@@ -1522,21 +1522,29 @@ static int journal_get_superblock(journal_t *journal)
 		goto out;
 	}
 
-	if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) &&
-	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	if (jbd2_journal_has_csum_v2or3(journal) &&
+	    JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) {
 		/* Can't have checksum v1 and v2 on at the same time! */
 		printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 "
 		       "at the same time!\n");
 		goto out;
 	}
 
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) &&
+	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
+		/* Can't have checksum v2 and v3 at the same time! */
+		printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 "
+		       "at the same time!\n");
+		goto out;
+	}
+
 	if (!jbd2_verify_csum_type(journal, sb)) {
 		printk(KERN_ERR "JBD2: Unknown checksum type\n");
 		goto out;
 	}
 
 	/* Load the checksum driver */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	if (jbd2_journal_has_csum_v2or3(journal)) {
 		journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
 		if (IS_ERR(journal->j_chksum_driver)) {
 			printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n");
@@ -1553,7 +1561,7 @@ static int journal_get_superblock(journal_t *journal)
 	}
 
 	/* Precompute checksum seed for all metadata */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
 						   sizeof(sb->s_uuid));
 
@@ -1813,8 +1821,14 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 	if (!jbd2_journal_check_available_features(journal, compat, ro, incompat))
 		return 0;
 
-	/* Asking for checksumming v2 and v1?  Only give them v2. */
-	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2 &&
+	/* If enabling v2 checksums, turn on v3 instead */
+	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2) {
+		incompat &= ~JBD2_FEATURE_INCOMPAT_CSUM_V2;
+		incompat |= JBD2_FEATURE_INCOMPAT_CSUM_V3;
+	}
+
+	/* Asking for checksumming v3 and v1?  Only give them v3. */
+	if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V3 &&
 	    compat & JBD2_FEATURE_COMPAT_CHECKSUM)
 		compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM;
 
@@ -1823,8 +1837,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 
 	sb = journal->j_superblock;
 
-	/* If enabling v2 checksums, update superblock */
-	if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V2)) {
+	/* If enabling v3 checksums, update superblock */
+	if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
 		sb->s_checksum_type = JBD2_CRC32C_CHKSUM;
 		sb->s_feature_compat &=
 			~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM);
@@ -1842,8 +1856,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 		}
 
 		/* Precompute checksum seed for all metadata */
-		if (JBD2_HAS_INCOMPAT_FEATURE(journal,
-					      JBD2_FEATURE_INCOMPAT_CSUM_V2))
+		if (jbd2_journal_has_csum_v2or3(journal))
 			journal->j_csum_seed = jbd2_chksum(journal, ~0,
 							   sb->s_uuid,
 							   sizeof(sb->s_uuid));
@@ -1852,7 +1865,8 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
 	/* If enabling v1 checksums, downgrade superblock */
 	if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM))
 		sb->s_feature_incompat &=
-			~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2);
+			~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2 |
+				     JBD2_FEATURE_INCOMPAT_CSUM_V3);
 
 	sb->s_feature_compat    |= cpu_to_be32(compat);
 	sb->s_feature_ro_compat |= cpu_to_be32(ro);
@@ -2165,16 +2179,20 @@ int jbd2_journal_blocks_per_page(struct inode *inode)
  */
 size_t journal_tag_bytes(journal_t *journal)
 {
-	journal_block_tag_t tag;
-	size_t x = 0;
+	size_t sz;
+
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return sizeof(journal_block_tag3_t);
+
+	sz = sizeof(journal_block_tag_t);
 
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
-		x += sizeof(tag.t_checksum);
+		sz += sizeof(__u16);
 
 	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
-		return x + JBD2_TAG_SIZE64;
+		return sz;
 	else
-		return x + JBD2_TAG_SIZE32;
+		return sz - sizeof(__u32);
 }
 
 /*
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 3b6bb19d60b1..9b329b55ffe3 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -181,7 +181,7 @@ static int jbd2_descr_block_csum_verify(journal_t *j,
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	tail = (struct jbd2_journal_block_tail *)(buf + j->j_blocksize -
@@ -205,7 +205,7 @@ static int count_tags(journal_t *journal, struct buffer_head *bh)
 	int			nr = 0, size = journal->j_blocksize;
 	int			tag_bytes = journal_tag_bytes(journal);
 
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		size -= sizeof(struct jbd2_journal_block_tail);
 
 	tagp = &bh->b_data[sizeof(journal_header_t)];
@@ -338,10 +338,11 @@ int jbd2_journal_skip_recovery(journal_t *journal)
 	return err;
 }
 
-static inline unsigned long long read_tag_block(int tag_bytes, journal_block_tag_t *tag)
+static inline unsigned long long read_tag_block(journal_t *journal,
+						journal_block_tag_t *tag)
 {
 	unsigned long long block = be32_to_cpu(tag->t_blocknr);
-	if (tag_bytes > JBD2_TAG_SIZE32)
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
 		block |= (u64)be32_to_cpu(tag->t_blocknr_high) << 32;
 	return block;
 }
@@ -384,7 +385,7 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	h = buf;
@@ -399,17 +400,21 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
 static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
 				      void *buf, __u32 sequence)
 {
+	journal_block_tag3_t *tag3 = (journal_block_tag3_t *)tag;
 	__u32 csum32;
 	__be32 seq;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	seq = cpu_to_be32(sequence);
 	csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq));
 	csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize);
 
-	return tag->t_checksum == cpu_to_be16(csum32);
+	if (JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return tag3->t_checksum == cpu_to_be32(csum32);
+	else
+		return tag->t_checksum == cpu_to_be16(csum32);
 }
 
 static int do_one_pass(journal_t *journal,
@@ -426,6 +431,7 @@ static int do_one_pass(journal_t *journal,
 	int			tag_bytes = journal_tag_bytes(journal);
 	__u32			crc32_sum = ~0; /* Transactional Checksums */
 	int			descr_csum_size = 0;
+	int			block_error = 0;
 
 	/*
 	 * First thing is to establish what we expect to find in the log
@@ -512,8 +518,7 @@ static int do_one_pass(journal_t *journal,
 		switch(blocktype) {
 		case JBD2_DESCRIPTOR_BLOCK:
 			/* Verify checksum first */
-			if (JBD2_HAS_INCOMPAT_FEATURE(journal,
-					JBD2_FEATURE_INCOMPAT_CSUM_V2))
+			if (jbd2_journal_has_csum_v2or3(journal))
 				descr_csum_size =
 					sizeof(struct jbd2_journal_block_tail);
 			if (descr_csum_size > 0 &&
@@ -574,7 +579,7 @@ static int do_one_pass(journal_t *journal,
 					unsigned long long blocknr;
 
 					J_ASSERT(obh != NULL);
-					blocknr = read_tag_block(tag_bytes,
+					blocknr = read_tag_block(journal,
 								 tag);
 
 					/* If the block has been
@@ -598,7 +603,8 @@ static int do_one_pass(journal_t *journal,
 						       "checksum recovering "
 						       "block %llu in log\n",
 						       blocknr);
-						continue;
+						block_error = 1;
+						goto skip_write;
 					}
 
 					/* Find a buffer for the new
@@ -797,7 +803,8 @@ static int do_one_pass(journal_t *journal,
 				success = -EIO;
 		}
 	}
-
+	if (block_error && success == 0)
+		success = -EIO;
 	return success;
 
  failed:
@@ -811,7 +818,7 @@ static int jbd2_revoke_block_csum_verify(journal_t *j,
 	__be32 provided;
 	__u32 calculated;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return 1;
 
 	tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize -
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index 198c9c10276d..d5e95a175c92 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -91,8 +91,8 @@
 #include <linux/list.h>
 #include <linux/init.h>
 #include <linux/bio.h>
-#endif
 #include <linux/log2.h>
+#endif
 
 static struct kmem_cache *jbd2_revoke_record_cache;
 static struct kmem_cache *jbd2_revoke_table_cache;
@@ -597,7 +597,7 @@ static void write_one_revoke_record(journal_t *journal,
 	offset = *offsetp;
 
 	/* Do we need to leave space at the end for a checksum? */
-	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (jbd2_journal_has_csum_v2or3(journal))
 		csum_size = sizeof(struct jbd2_journal_revoke_tail);
 
 	/* Make sure we have a descriptor with space left for the record */
@@ -644,7 +644,7 @@ static void jbd2_revoke_csum_set(journal_t *j, struct buffer_head *bh)
 	struct jbd2_journal_revoke_tail *tail;
 	__u32 csum;
 
-	if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
+	if (!jbd2_journal_has_csum_v2or3(j))
 		return;
 
 	tail = (struct jbd2_journal_revoke_tail *)(bh->b_data + j->j_blocksize -
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 8f854dde4150..24c6898159cc 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -129,7 +129,10 @@ static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 		.rpc_argp	= &args,
 		.rpc_resp	= &fattr,
 	};
-	int status;
+	int status = 0;
+
+	if (acl == NULL && (!S_ISDIR(inode->i_mode) || dfacl == NULL))
+		goto out;
 
 	status = -EOPNOTSUPP;
 	if (!nfs_server_capable(inode, NFS_CAP_ACLS))
@@ -256,7 +259,7 @@ nfs3_list_one_acl(struct inode *inode, int type, const char *name, void *data,
 	char *p = data + *result;
 
 	acl = get_acl(inode, type);
-	if (!acl)
+	if (IS_ERR_OR_NULL(acl))
 		return 0;
 
 	posix_acl_release(acl);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4bf3d97cc5a0..dac979866f83 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2545,6 +2545,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 	struct nfs4_closedata *calldata = data;
 	struct nfs4_state *state = calldata->state;
 	struct nfs_server *server = NFS_SERVER(calldata->inode);
+	nfs4_stateid *res_stateid = NULL;
 
 	dprintk("%s: begin!\n", __func__);
 	if (!nfs4_sequence_done(task, &calldata->res.seq_res))
@@ -2555,12 +2556,12 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 	 */
 	switch (task->tk_status) {
 		case 0:
-			if (calldata->roc)
+			res_stateid = &calldata->res.stateid;
+			if (calldata->arg.fmode == 0 && calldata->roc)
 				pnfs_roc_set_barrier(state->inode,
 						     calldata->roc_barrier);
-			nfs_clear_open_stateid(state, &calldata->res.stateid, 0);
 			renew_lease(server, calldata->timestamp);
-			goto out_release;
+			break;
 		case -NFS4ERR_ADMIN_REVOKED:
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_OLD_STATEID:
@@ -2574,7 +2575,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 				goto out_release;
 			}
 	}
-	nfs_clear_open_stateid(state, NULL, calldata->arg.fmode);
+	nfs_clear_open_stateid(state, res_stateid, calldata->arg.fmode);
 out_release:
 	nfs_release_seqid(calldata->arg.seqid);
 	nfs_refresh_inode(calldata->inode, calldata->res.fattr);
@@ -2586,6 +2587,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 	struct nfs4_closedata *calldata = data;
 	struct nfs4_state *state = calldata->state;
 	struct inode *inode = calldata->inode;
+	bool is_rdonly, is_wronly, is_rdwr;
 	int call_close = 0;
 
 	dprintk("%s: begin!\n", __func__);
@@ -2593,18 +2595,24 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 		goto out_wait;
 
 	task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE];
-	calldata->arg.fmode = FMODE_READ|FMODE_WRITE;
 	spin_lock(&state->owner->so_lock);
+	is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags);
+	is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags);
+	is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags);
+	/* Calculate the current open share mode */
+	calldata->arg.fmode = 0;
+	if (is_rdonly || is_rdwr)
+		calldata->arg.fmode |= FMODE_READ;
+	if (is_wronly || is_rdwr)
+		calldata->arg.fmode |= FMODE_WRITE;
 	/* Calculate the change in open mode */
 	if (state->n_rdwr == 0) {
 		if (state->n_rdonly == 0) {
-			call_close |= test_bit(NFS_O_RDONLY_STATE, &state->flags);
-			call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
+			call_close |= is_rdonly || is_rdwr;
 			calldata->arg.fmode &= ~FMODE_READ;
 		}
 		if (state->n_wronly == 0) {
-			call_close |= test_bit(NFS_O_WRONLY_STATE, &state->flags);
-			call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
+			call_close |= is_wronly || is_rdwr;
 			calldata->arg.fmode &= ~FMODE_WRITE;
 		}
 	}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 084af1060d79..3fd83327bbad 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2180,7 +2180,7 @@ out_no_address:
 	return -EINVAL;
 }
 
-#define NFS_MOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \
+#define NFS_REMOUNT_CMP_FLAGMASK ~(NFS_MOUNT_INTR \
 		| NFS_MOUNT_SECURE \
 		| NFS_MOUNT_TCP \
 		| NFS_MOUNT_VER3 \
@@ -2188,15 +2188,16 @@ out_no_address:
 		| NFS_MOUNT_NONLM \
 		| NFS_MOUNT_BROKEN_SUID \
 		| NFS_MOUNT_STRICTLOCK \
-		| NFS_MOUNT_UNSHARED \
-		| NFS_MOUNT_NORESVPORT \
 		| NFS_MOUNT_LEGACY_INTERFACE)
 
+#define NFS_MOUNT_CMP_FLAGMASK (NFS_REMOUNT_CMP_FLAGMASK & \
+		~(NFS_MOUNT_UNSHARED | NFS_MOUNT_NORESVPORT))
+
 static int
 nfs_compare_remount_data(struct nfs_server *nfss,
 			 struct nfs_parsed_mount_data *data)
 {
-	if ((data->flags ^ nfss->flags) & NFS_MOUNT_CMP_FLAGMASK ||
+	if ((data->flags ^ nfss->flags) & NFS_REMOUNT_CMP_FLAGMASK ||
 	    data->rsize != nfss->rsize ||
 	    data->wsize != nfss->wsize ||
 	    data->version != nfss->nfs_client->rpc_ops->version ||
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 2c73cae9899d..0f23ad005826 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -689,7 +689,8 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		clp->cl_cb_session = ses;
 		args.bc_xprt = conn->cb_xprt;
 		args.prognumber = clp->cl_cb_session->se_cb_prog;
-		args.protocol = XPRT_TRANSPORT_BC_TCP;
+		args.protocol = conn->cb_xprt->xpt_class->xcl_ident |
+				XPRT_TRANSPORT_BC;
 		args.authflavor = ses->se_cb_sec.flavor;
 	}
 	/* Create RPC client */
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 1879e43f2868..2f2edbb2a4a3 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -221,7 +221,8 @@ static int nfsd_startup_generic(int nrservs)
 	 */
 	ret = nfsd_racache_init(2*nrservs);
 	if (ret)
-		return ret;
+		goto dec_users;
+
 	ret = nfs4_state_start();
 	if (ret)
 		goto out_racache;
@@ -229,6 +230,8 @@ static int nfsd_startup_generic(int nrservs)
 
 out_racache:
 	nfsd_racache_shutdown();
+dec_users:
+	nfsd_users--;
 	return ret;
 }
 
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 6dfd64b3a604..e973540cd15b 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -17,6 +17,7 @@
 	{0x1002, 0x1315, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x1316, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x1317, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x1318, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x131B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x131C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x131D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KAVERI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
@@ -164,8 +165,11 @@
 	{0x1002, 0x6601, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6602, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6603, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6604, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6605, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6606, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6607, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6608, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6610, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6611, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6613, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
@@ -175,6 +179,8 @@
 	{0x1002, 0x6631, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6640, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6641, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6646, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6649, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6650, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6651, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BONAIRE|RADEON_NEW_MEMMAP}, \
@@ -297,6 +303,7 @@
 	{0x1002, 0x6829, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x682C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x682F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6830, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VERDE|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index d5b50a19463c..0dae71e9971c 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -159,7 +159,11 @@ typedef struct journal_header_s
  * journal_block_tag (in the descriptor).  The other h_chksum* fields are
  * not used.
  *
- * Checksum v1 and v2 are mutually exclusive features.
+ * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses
+ * journal_block_tag3_t to store a full 32-bit checksum.  Everything else
+ * is the same as v2.
+ *
+ * Checksum v1, v2, and v3 are mutually exclusive features.
  */
 struct commit_header {
 	__be32		h_magic;
@@ -179,6 +183,14 @@ struct commit_header {
  * raw struct shouldn't be used for pointer math or sizeof() - use
  * journal_tag_bytes(journal) instead to compute this.
  */
+typedef struct journal_block_tag3_s
+{
+	__be32		t_blocknr;	/* The on-disk block number */
+	__be32		t_flags;	/* See below */
+	__be32		t_blocknr_high; /* most-significant high 32bits. */
+	__be32		t_checksum;	/* crc32c(uuid+seq+block) */
+} journal_block_tag3_t;
+
 typedef struct journal_block_tag_s
 {
 	__be32		t_blocknr;	/* The on-disk block number */
@@ -187,9 +199,6 @@ typedef struct journal_block_tag_s
 	__be32		t_blocknr_high; /* most-significant high 32bits. */
 } journal_block_tag_t;
 
-#define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high))
-#define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t))
-
 /* Tail of descriptor block, for checksumming */
 struct jbd2_journal_block_tail {
 	__be32		t_checksum;	/* crc32c(uuid+descr_block) */
@@ -284,6 +293,7 @@ typedef struct journal_superblock_s
 #define JBD2_FEATURE_INCOMPAT_64BIT		0x00000002
 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT	0x00000004
 #define JBD2_FEATURE_INCOMPAT_CSUM_V2		0x00000008
+#define JBD2_FEATURE_INCOMPAT_CSUM_V3		0x00000010
 
 /* Features known to this kernel version: */
 #define JBD2_KNOWN_COMPAT_FEATURES	JBD2_FEATURE_COMPAT_CHECKSUM
@@ -291,7 +301,8 @@ typedef struct journal_superblock_s
 #define JBD2_KNOWN_INCOMPAT_FEATURES	(JBD2_FEATURE_INCOMPAT_REVOKE | \
 					JBD2_FEATURE_INCOMPAT_64BIT | \
 					JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
-					JBD2_FEATURE_INCOMPAT_CSUM_V2)
+					JBD2_FEATURE_INCOMPAT_CSUM_V2 | \
+					JBD2_FEATURE_INCOMPAT_CSUM_V3)
 
 #ifdef __KERNEL__
 
@@ -1296,6 +1307,15 @@ static inline int tid_geq(tid_t x, tid_t y)
 extern int jbd2_journal_blocks_per_page(struct inode *inode);
 extern size_t journal_tag_bytes(journal_t *journal);
 
+static inline int jbd2_journal_has_csum_v2or3(journal_t *journal)
+{
+	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2) ||
+	    JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V3))
+		return 1;
+
+	return 0;
+}
+
 /*
  * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for
  * transaction control blocks.
diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h
index 7235040a19b2..5d9d6f84b382 100644
--- a/include/linux/sunrpc/svc_xprt.h
+++ b/include/linux/sunrpc/svc_xprt.h
@@ -33,6 +33,7 @@ struct svc_xprt_class {
 	struct svc_xprt_ops	*xcl_ops;
 	struct list_head	xcl_list;
 	u32			xcl_max_payload;
+	int			xcl_ident;
 };
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bc1638b33449..0acf96b790c5 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3558,9 +3558,10 @@ static int _sched_setscheduler(struct task_struct *p, int policy,
 	};
 
 	/*
-	 * Fixup the legacy SCHED_RESET_ON_FORK hack
+	 * Fixup the legacy SCHED_RESET_ON_FORK hack, except if
+	 * the policy=-1 was passed by sched_setparam().
 	 */
-	if (policy & SCHED_RESET_ON_FORK) {
+	if ((policy != -1) && (policy & SCHED_RESET_ON_FORK)) {
 		attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
 		policy &= ~SCHED_RESET_ON_FORK;
 		attr.sched_policy = policy;
diff --git a/mm/memory.c b/mm/memory.c
index 8b44f765b645..0a21f3d162ae 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -751,7 +751,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 	unsigned long pfn = pte_pfn(pte);
 
 	if (HAVE_PTE_SPECIAL) {
-		if (likely(!pte_special(pte) || pte_numa(pte)))
+		if (likely(!pte_special(pte)))
 			goto check_pfn;
 		if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
 			return NULL;
@@ -777,15 +777,14 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 		}
 	}
 
+	if (is_zero_pfn(pfn))
+		return NULL;
 check_pfn:
 	if (unlikely(pfn > highest_memmap_pfn)) {
 		print_bad_pte(vma, addr, pte, NULL);
 		return NULL;
 	}
 
-	if (is_zero_pfn(pfn))
-		return NULL;
-
 	/*
 	 * NOTE! We still have PageReserved() pages in the page tables.
 	 * eg. VDSO mappings can cause them to exist.
diff --git a/mm/util.c b/mm/util.c
index d5ea733c5082..33e9f4455800 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -277,17 +277,14 @@ pid_t vm_is_stack(struct task_struct *task,
 
 	if (in_group) {
 		struct task_struct *t;
-		rcu_read_lock();
-		if (!pid_alive(task))
-			goto done;
 
-		t = task;
-		do {
+		rcu_read_lock();
+		for_each_thread(task, t) {
 			if (vm_is_stack_for_task(t, vma)) {
 				ret = t->pid;
 				goto done;
 			}
-		} while_each_thread(task, t);
+		}
 done:
 		rcu_read_unlock();
 	}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index b507cd327d9b..b2437ee93657 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -692,6 +692,7 @@ static struct svc_xprt_class svc_udp_class = {
 	.xcl_owner = THIS_MODULE,
 	.xcl_ops = &svc_udp_ops,
 	.xcl_max_payload = RPCSVC_MAXPAYLOAD_UDP,
+	.xcl_ident = XPRT_TRANSPORT_UDP,
 };
 
 static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv)
@@ -1292,6 +1293,7 @@ static struct svc_xprt_class svc_tcp_class = {
 	.xcl_owner = THIS_MODULE,
 	.xcl_ops = &svc_tcp_ops,
 	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
+	.xcl_ident = XPRT_TRANSPORT_TCP,
 };
 
 void svc_init_xprt_sock(void)
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index c3b2b3369e52..51c63165073c 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1306,7 +1306,7 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args)
 		}
 	}
 	spin_unlock(&xprt_list_lock);
-	printk(KERN_ERR "RPC: transport (%d) not supported\n", args->ident);
+	dprintk("RPC: transport (%d) not supported\n", args->ident);
 	return ERR_PTR(-EIO);
 
 found:
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index e7323fbbd348..06a5d9235107 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -92,6 +92,7 @@ struct svc_xprt_class svc_rdma_class = {
 	.xcl_owner = THIS_MODULE,
 	.xcl_ops = &svc_rdma_ops,
 	.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
+	.xcl_ident = XPRT_TRANSPORT_RDMA,
 };
 
 struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig
index 3a3a3a71088b..50dd0086cfb1 100644
--- a/sound/pci/Kconfig
+++ b/sound/pci/Kconfig
@@ -858,8 +858,8 @@ config SND_VIRTUOSO
 	select SND_JACK if INPUT=y || INPUT=SND
 	help
 	  Say Y here to include support for sound cards based on the
-	  Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS,
-	  Essence ST (Deluxe), and Essence STX.
+	  Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS, DSX,
+	  Essence ST (Deluxe), and Essence STX (II).
 	  Support for the HDAV1.3 (Deluxe) and HDAV1.3 Slim is experimental;
 	  for the Xense, missing.
 
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 092f2bd030bd..b686aca7f000 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -4376,6 +4376,9 @@ static void ca0132_download_dsp(struct hda_codec *codec)
 	return; /* NOP */
 #endif
 
+	if (spec->dsp_state == DSP_DOWNLOAD_FAILED)
+		return; /* don't retry failures */
+
 	chipio_enable_clocks(codec);
 	spec->dsp_state = DSP_DOWNLOADING;
 	if (!ca0132_download_dsp_images(codec))
@@ -4552,7 +4555,8 @@ static int ca0132_init(struct hda_codec *codec)
 	struct auto_pin_cfg *cfg = &spec->autocfg;
 	int i;
 
-	spec->dsp_state = DSP_DOWNLOAD_INIT;
+	if (spec->dsp_state != DSP_DOWNLOAD_FAILED)
+		spec->dsp_state = DSP_DOWNLOAD_INIT;
 	spec->curr_chip_addx = INVALID_CHIP_ADDRESS;
 
 	snd_hda_power_up(codec);
@@ -4663,6 +4667,7 @@ static int patch_ca0132(struct hda_codec *codec)
 	codec->spec = spec;
 	spec->codec = codec;
 
+	spec->dsp_state = DSP_DOWNLOAD_INIT;
 	spec->num_mixers = 1;
 	spec->mixers[0] = ca0132_mixer;
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index b60824e90408..25728aaacc26 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -180,6 +180,8 @@ static void alc_fix_pll(struct hda_codec *codec)
 			    spec->pll_coef_idx);
 	val = snd_hda_codec_read(codec, spec->pll_nid, 0,
 				 AC_VERB_GET_PROC_COEF, 0);
+	if (val == -1)
+		return;
 	snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_COEF_INDEX,
 			    spec->pll_coef_idx);
 	snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_PROC_COEF,
@@ -2784,6 +2786,8 @@ static int alc269_parse_auto_config(struct hda_codec *codec)
 static void alc269vb_toggle_power_output(struct hda_codec *codec, int power_up)
 {
 	int val = alc_read_coef_idx(codec, 0x04);
+	if (val == -1)
+		return;
 	if (power_up)
 		val |= 1 << 11;
 	else
@@ -3242,6 +3246,15 @@ static int alc269_resume(struct hda_codec *codec)
 	snd_hda_codec_resume_cache(codec);
 	alc_inv_dmic_sync(codec, true);
 	hda_call_check_power_status(codec, 0x01);
+
+	/* on some machine, the BIOS will clear the codec gpio data when enter
+	 * suspend, and won't restore the data after resume, so we restore it
+	 * in the driver.
+	 */
+	if (spec->gpio_led)
+		snd_hda_codec_write(codec, codec->afg, 0, AC_VERB_SET_GPIO_DATA,
+			    spec->gpio_led);
+
 	if (spec->has_alc5505_dsp)
 		alc5505_dsp_resume(codec);
 
@@ -4782,6 +4795,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x1983, "HP Pavilion", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x218b, "HP", ALC269_FIXUP_LIMIT_INT_MIC_BOOST_MUTE_LED),
 	/* ALC282 */
+	SND_PCI_QUIRK(0x103c, 0x2191, "HP Touchsmart 14", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x2192, "HP Touchsmart 15", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x220d, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x220e, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x220f, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
@@ -5122,27 +5137,30 @@ static void alc269_fill_coef(struct hda_codec *codec)
 	if ((alc_get_coef0(codec) & 0x00ff) == 0x017) {
 		val = alc_read_coef_idx(codec, 0x04);
 		/* Power up output pin */
-		alc_write_coef_idx(codec, 0x04, val | (1<<11));
+		if (val != -1)
+			alc_write_coef_idx(codec, 0x04, val | (1<<11));
 	}
 
 	if ((alc_get_coef0(codec) & 0x00ff) == 0x018) {
 		val = alc_read_coef_idx(codec, 0xd);
-		if ((val & 0x0c00) >> 10 != 0x1) {
+		if (val != -1 && (val & 0x0c00) >> 10 != 0x1) {
 			/* Capless ramp up clock control */
 			alc_write_coef_idx(codec, 0xd, val | (1<<10));
 		}
 		val = alc_read_coef_idx(codec, 0x17);
-		if ((val & 0x01c0) >> 6 != 0x4) {
+		if (val != -1 && (val & 0x01c0) >> 6 != 0x4) {
 			/* Class D power on reset */
 			alc_write_coef_idx(codec, 0x17, val | (1<<7));
 		}
 	}
 
 	val = alc_read_coef_idx(codec, 0xd); /* Class D */
-	alc_write_coef_idx(codec, 0xd, val | (1<<14));
+	if (val != -1)
+		alc_write_coef_idx(codec, 0xd, val | (1<<14));
 
 	val = alc_read_coef_idx(codec, 0x4); /* HP */
-	alc_write_coef_idx(codec, 0x4, val | (1<<11));
+	if (val != -1)
+		alc_write_coef_idx(codec, 0x4, val | (1<<11));
 }
 
 /*
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 3744ea4e843d..4d3a3b932690 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -84,6 +84,7 @@ enum {
 	STAC_DELL_EQ,
 	STAC_ALIENWARE_M17X,
 	STAC_92HD89XX_HP_FRONT_JACK,
+	STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK,
 	STAC_92HD73XX_MODELS
 };
 
@@ -1809,6 +1810,11 @@ static const struct hda_pintbl stac92hd89xx_hp_front_jack_pin_configs[] = {
 	{}
 };
 
+static const struct hda_pintbl stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs[] = {
+	{ 0x0e, 0x400000f0 },
+	{}
+};
+
 static void stac92hd73xx_fixup_ref(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
@@ -1931,6 +1937,10 @@ static const struct hda_fixup stac92hd73xx_fixups[] = {
 	[STAC_92HD89XX_HP_FRONT_JACK] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = stac92hd89xx_hp_front_jack_pin_configs,
+	},
+	[STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = stac92hd89xx_hp_z1_g2_right_mic_jack_pin_configs,
 	}
 };
 
@@ -1991,6 +2001,8 @@ static const struct snd_pci_quirk stac92hd73xx_fixup_tbl[] = {
 		      "Alienware M17x", STAC_ALIENWARE_M17X),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0490,
 		      "Alienware M17x R3", STAC_DELL_EQ),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x1927,
+				"HP Z1 G2", STAC_92HD89XX_HP_Z1_G2_RIGHT_MIC_JACK),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x2b17,
 				"unknown HP", STAC_92HD89XX_HP_FRONT_JACK),
 	{} /* terminator */
diff --git a/sound/pci/oxygen/virtuoso.c b/sound/pci/oxygen/virtuoso.c
index 64b9fda5f04a..dbbbacfd535e 100644
--- a/sound/pci/oxygen/virtuoso.c
+++ b/sound/pci/oxygen/virtuoso.c
@@ -53,6 +53,7 @@ static DEFINE_PCI_DEVICE_TABLE(xonar_ids) = {
 	{ OXYGEN_PCI_SUBID(0x1043, 0x835e) },
 	{ OXYGEN_PCI_SUBID(0x1043, 0x838e) },
 	{ OXYGEN_PCI_SUBID(0x1043, 0x8522) },
+	{ OXYGEN_PCI_SUBID(0x1043, 0x85f4) },
 	{ OXYGEN_PCI_SUBID_BROKEN_EEPROM },
 	{ }
 };
diff --git a/sound/pci/oxygen/xonar_pcm179x.c b/sound/pci/oxygen/xonar_pcm179x.c
index c8c7f2c9b355..e02605931669 100644
--- a/sound/pci/oxygen/xonar_pcm179x.c
+++ b/sound/pci/oxygen/xonar_pcm179x.c
@@ -100,8 +100,8 @@
  */
 
 /*
- * Xonar Essence ST (Deluxe)/STX
- * -----------------------------
+ * Xonar Essence ST (Deluxe)/STX (II)
+ * ----------------------------------
  *
  * CMI8788:
  *
@@ -1138,6 +1138,14 @@ int get_xonar_pcm179x_model(struct oxygen *chip,
 		chip->model.resume = xonar_stx_resume;
 		chip->model.set_dac_params = set_pcm1796_params;
 		break;
+	case 0x85f4:
+		chip->model = model_xonar_st;
+		/* TODO: daughterboard support */
+		chip->model.shortname = "Xonar STX II";
+		chip->model.init = xonar_stx_init;
+		chip->model.resume = xonar_stx_resume;
+		chip->model.set_dac_params = set_pcm1796_params;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index f652b10ce905..223c47b33ba3 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -1581,6 +1581,35 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 	}
 },
 {
+	/* BOSS ME-25 */
+	USB_DEVICE(0x0582, 0x0113),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_MIDI_FIXED_ENDPOINT,
+				.data = & (const struct snd_usb_midi_endpoint_info) {
+					.out_cables = 0x0001,
+					.in_cables  = 0x0001
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+{
 	/* only 44.1 kHz works at the moment */
 	USB_DEVICE(0x0582, 0x0120),
 	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 7c57f2268dd7..19a921eb75f1 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -670,7 +670,7 @@ static int snd_usb_gamecon780_boot_quirk(struct usb_device *dev)
 	/* set the initial volume and don't change; other values are either
 	 * too loud or silent due to firmware bug (bko#65251)
 	 */
-	u8 buf[2] = { 0x74, 0xdc };
+	u8 buf[2] = { 0x74, 0xe3 };
 	return snd_usb_ctl_msg(dev, usb_sndctrlpipe(dev, 0), UAC_SET_CUR,
 			USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_OUT,
 			UAC_FU_VOLUME << 8, 9 << 8, buf, 2);
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 2458a1dc2ba9..e8ce34c9db32 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -254,10 +254,9 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
 	spin_lock(&ioapic->lock);
 	for (index = 0; index < IOAPIC_NUM_PINS; index++) {
 		e = &ioapic->redirtbl[index];
-		if (!e->fields.mask &&
-			(e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
-			 kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC,
-				 index) || index == RTC_GSI)) {
+		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
+		    kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
+		    index == RTC_GSI) {
 			if (kvm_apic_match_dest(vcpu, NULL, 0,
 				e->fields.dest_id, e->fields.dest_mode)) {
 				__set_bit(e->fields.vector,
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 0df7d4b34dfe..714b94932312 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -61,6 +61,14 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
 	return pfn;
 }
 
+static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+{
+	unsigned long i;
+
+	for (i = 0; i < npages; ++i)
+		kvm_release_pfn_clean(pfn + i);
+}
+
 int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
 	gfn_t gfn, end_gfn;
@@ -123,6 +131,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 		if (r) {
 			printk(KERN_ERR "kvm_iommu_map_address:"
 			       "iommu failed to map pfn=%llx\n", pfn);
+			kvm_unpin_pages(kvm, pfn, page_size);
 			goto unmap_pages;
 		}
 
@@ -134,7 +143,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 	return 0;
 
 unmap_pages:
-	kvm_iommu_put_pages(kvm, slot->base_gfn, gfn);
+	kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn);
 	return r;
 }
 
@@ -266,14 +275,6 @@ out_unlock:
 	return r;
 }
 
-static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
-{
-	unsigned long i;
-
-	for (i = 0; i < npages; ++i)
-		kvm_release_pfn_clean(pfn + i);
-}
-
 static void kvm_iommu_put_pages(struct kvm *kvm,
 				gfn_t base_gfn, unsigned long npages)
 {