Merge tag 'v4.1.44' into 4.1-2.0.x-imx

Linux 4.1.44

* tag 'v4.1.44': (180 commits)
  Linux 4.1.44
  mtd: fsl-quadspi: fix macro collision problems with READ/WRITE
  pinctrl: samsung: Remove bogus irq_[un]mask from resource management
  pinctrl: sunxi: add a missing function of A10/A20 pinctrl driver
  pnfs/blocklayout: require 64-bit sector_t
  iio: adc: vf610_adc: Fix VALT selection value for REFSEL bits
  usb:xhci:Add quirk for Certain failing HP keyboard on reset after resume
  usb: quirks: Add no-lpm quirk for Moshi USB to Ethernet Adapter
  USB: Check for dropped connection before switching to full speed
  uas: Add US_FL_IGNORE_RESIDUE for Initio Corporation INIC-3069
  iio: light: tsl2563: use correct event code
  staging:iio:resolver:ad2s1210 fix negative IIO_ANGL_VEL read
  USB: hcd: Mark secondary HCD as dead if the primary one died
  USB: serial: pl2303: add new ATEN device id
  USB: serial: cp210x: add support for Qivicon USB ZigBee dongle
  USB: serial: option: add D-Link DWM-222 device ID
  nfs/flexfiles: fix leak of nfs4_ff_ds_version arrays
  fuse: initialize the flock flag in fuse_file on allocation
  iscsi-target: Fix iscsi_np reset hung task during parallel delete
  iscsi-target: fix memory leak in iscsit_setup_text_cmd()
  ...

Signed-off-by: Otavio Salvador <otavio@ossystems.com.br>

40 files changed, 370 insertions, 122 deletions

diff --git a/arch/arm/boot/dts/armada-388-gp.dts b/arch/arm/boot/dts/armada-388-gp.dts
index 757ac079e7f2..bcf4f1b6b2bc 100644
--- a/arch/arm/boot/dts/armada-388-gp.dts
+++ b/arch/arm/boot/dts/armada-388-gp.dts
@@ -91,7 +91,7 @@
 					pinctrl-names = "default";
 					pinctrl-0 = <&pca0_pins>;
 					interrupt-parent = <&gpio0>;
-					interrupts = <18 IRQ_TYPE_EDGE_FALLING>;
+					interrupts = <18 IRQ_TYPE_LEVEL_LOW>;
 					gpio-controller;
 					#gpio-cells = <2>;
 					interrupt-controller;
@@ -103,7 +103,7 @@
 					compatible = "nxp,pca9555";
 					pinctrl-names = "default";
 					interrupt-parent = <&gpio0>;
-					interrupts = <18 IRQ_TYPE_EDGE_FALLING>;
+					interrupts = <18 IRQ_TYPE_LEVEL_LOW>;
 					gpio-controller;
 					#gpio-cells = <2>;
 					interrupt-controller;
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 5f5e0f3d5b64..27cd4abfc74d 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -697,6 +697,8 @@
 	vmmc_aux-supply = <&vsim>;
 	bus-width = <8>;
 	non-removable;
+	no-sdio;
+	no-sd;
 };
 
 &mmc3 {
diff --git a/arch/arm/configs/s3c2410_defconfig b/arch/arm/configs/s3c2410_defconfig
index f3142369f594..01116ee1284b 100644
--- a/arch/arm/configs/s3c2410_defconfig
+++ b/arch/arm/configs/s3c2410_defconfig
@@ -87,9 +87,9 @@ CONFIG_IPV6_TUNNEL=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_DCCP=m
-CONFIG_NF_CT_PROTO_SCTP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_DCCP=y
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index bfe2a2f5a644..22b73112b75f 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -54,6 +54,24 @@ static inline void *return_address(unsigned int level)
 
 #define ftrace_return_address(n) return_address(n)
 
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+
+static inline bool arch_syscall_match_sym_name(const char *sym,
+					       const char *name)
+{
+	if (!strcmp(sym, "sys_mmap2"))
+		sym = "sys_mmap_pgoff";
+	else if (!strcmp(sym, "sys_statfs64_wrapper"))
+		sym = "sys_statfs64";
+	else if (!strcmp(sym, "sys_fstatfs64_wrapper"))
+		sym = "sys_fstatfs64";
+	else if (!strcmp(sym, "sys_arm_fadvise64_64"))
+		sym = "sys_fadvise64_64";
+
+	/* Ignore case since sym may start with "SyS" instead of "sys" */
+	return !strcasecmp(sym, name);
+}
+
 #endif /* ifndef __ASSEMBLY__ */
 
 #endif /* _ASM_ARM_FTRACE */
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 4e15eed87074..3ca19cdb0eac 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1611,12 +1611,16 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
 
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
+	if (!kvm->arch.pgd)
+		return 0;
 	trace_kvm_age_hva(start, end);
 	return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
 {
+	if (!kvm->arch.pgd)
+		return 0;
 	trace_kvm_test_age_hva(hva);
 	return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL);
 }
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts b/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts
index 0a3f40ecd06d..96235d2b135d 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts
+++ b/arch/arm64/boot/dts/xilinx/zynqmp-ep108.dts
@@ -26,7 +26,7 @@
 		stdout-path = "serial0:115200n8";
 	};
 
-	memory {
+	memory@0 {
 		device_type = "memory";
 		reg = <0x0 0x0 0x40000000>;
 	};
diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
index 11e0b00045cf..0cb2cdfd7309 100644
--- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
+++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi
@@ -71,7 +71,7 @@
 			     <1 10 0xf01>;
 	};
 
-	amba_apu {
+	amba_apu: amba_apu@0 {
 		compatible = "simple-bus";
 		#address-cells = <2>;
 		#size-cells = <1>;
@@ -251,7 +251,7 @@
 		};
 
 		i2c0: i2c@ff020000 {
-			compatible = "cdns,i2c-r1p10";
+			compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10";
 			status = "disabled";
 			interrupt-parent = <&gic>;
 			interrupts = <0 17 4>;
@@ -262,7 +262,7 @@
 		};
 
 		i2c1: i2c@ff030000 {
-			compatible = "cdns,i2c-r1p10";
+			compatible = "cdns,i2c-r1p14", "cdns,i2c-r1p10";
 			status = "disabled";
 			interrupt-parent = <&gic>;
 			interrupts = <0 18 4>;
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index fa5efaa5c3ac..16523fbd9671 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -62,21 +62,21 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 			break;
 
 		pud = pud_offset(pgd, addr);
-		printk(", *pud=%016llx", pud_val(*pud));
+		pr_cont(", *pud=%016llx", pud_val(*pud));
 		if (pud_none(*pud) || pud_bad(*pud))
 			break;
 
 		pmd = pmd_offset(pud, addr);
-		printk(", *pmd=%016llx", pmd_val(*pmd));
+		pr_cont(", *pmd=%016llx", pmd_val(*pmd));
 		if (pmd_none(*pmd) || pmd_bad(*pmd))
 			break;
 
 		pte = pte_offset_map(pmd, addr);
-		printk(", *pte=%016llx", pte_val(*pte));
+		pr_cont(", *pte=%016llx", pte_val(*pte));
 		pte_unmap(pte);
 	} while(0);
 
-	printk("\n");
+	pr_cont("\n");
 }
 
 /*
diff --git a/arch/mips/include/asm/branch.h b/arch/mips/include/asm/branch.h
index de781cf54bc7..da80878f2c0d 100644
--- a/arch/mips/include/asm/branch.h
+++ b/arch/mips/include/asm/branch.h
@@ -74,10 +74,7 @@ static inline int compute_return_epc(struct pt_regs *regs)
 			return __microMIPS_compute_return_epc(regs);
 		if (cpu_has_mips16)
 			return __MIPS16e_compute_return_epc(regs);
-		return regs->cp0_epc;
-	}
-
-	if (!delay_slot(regs)) {
+	} else if (!delay_slot(regs)) {
 		regs->cp0_epc += 4;
 		return 0;
 	}
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index fe376aa705c5..13254da66ce8 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -399,7 +399,7 @@ int __MIPS16e_compute_return_epc(struct pt_regs *regs)
  *
  * @regs:	Pointer to pt_regs
  * @insn:	branch instruction to decode
- * @returns:	-EFAULT on error and forces SIGBUS, and on success
+ * @returns:	-EFAULT on error and forces SIGILL, and on success
  *		returns 0 or BRANCH_LIKELY_TAKEN as appropriate after
  *		evaluating the branch.
  *
@@ -556,6 +556,7 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 	/*
 	 * These are unconditional and in j_format.
 	 */
+	case jalx_op:
 	case jal_op:
 		regs->regs[31] = regs->cp0_epc + 8;
 	case j_op:
@@ -843,8 +844,9 @@ int __compute_return_epc_for_insn(struct pt_regs *regs,
 	return ret;
 
 sigill_dsp:
-	printk("%s: DSP branch but not DSP ASE - sending SIGBUS.\n", current->comm);
-	force_sig(SIGBUS, current);
+	pr_info("%s: DSP branch but not DSP ASE - sending SIGILL.\n",
+		current->comm);
+	force_sig(SIGILL, current);
 	return -EFAULT;
 sigill_r6:
 	pr_info("%s: R2 branch but r2-to-r6 emulator is not preset - sending SIGILL.\n",
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index 298b2b773d12..f1fab6ff53e6 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -83,7 +83,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	}
 
 	seq_printf(m, "isa\t\t\t:"); 
-	if (cpu_has_mips_r1)
+	if (cpu_has_mips_1)
 		seq_printf(m, " mips1");
 	if (cpu_has_mips_2)
 		seq_printf(m, "%s", " mips2");
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index f7968b5149b0..5c3aa41a162f 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -838,7 +838,7 @@ asmlinkage void syscall_trace_leave(struct pt_regs *regs)
 	audit_syscall_exit(regs);
 
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
-		trace_sys_exit(regs, regs->regs[2]);
+		trace_sys_exit(regs, regs_return_value(regs));
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, 0);
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 6e8de80bb446..d516765ce320 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -362,7 +362,7 @@ EXPORT(sys_call_table)
 	PTR	sys_writev
 	PTR	sys_cacheflush
 	PTR	sys_cachectl
-	PTR	sys_sysmips
+	PTR	__sys_sysmips
 	PTR	sys_ni_syscall			/* 4150 */
 	PTR	sys_getsid
 	PTR	sys_fdatasync
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index a6f6b762c47a..a60edb497da3 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -318,7 +318,7 @@ EXPORT(sys_call_table)
 	PTR	sys_sched_getaffinity
 	PTR	sys_cacheflush
 	PTR	sys_cachectl
-	PTR	sys_sysmips
+	PTR	__sys_sysmips
 	PTR	sys_io_setup			/* 5200 */
 	PTR	sys_io_destroy
 	PTR	sys_io_getevents
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 97fa4c7b9a5e..5de53e4b9607 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -307,7 +307,7 @@ EXPORT(sysn32_call_table)
 	PTR	compat_sys_sched_getaffinity
 	PTR	sys_cacheflush
 	PTR	sys_cachectl
-	PTR	sys_sysmips
+	PTR	__sys_sysmips
 	PTR	compat_sys_io_setup			/* 6200 */
 	PTR	sys_io_destroy
 	PTR	compat_sys_io_getevents
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 80e39776e377..185092b9ecc1 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -359,7 +359,7 @@ EXPORT(sys32_call_table)
 	PTR	compat_sys_writev
 	PTR	sys_cacheflush
 	PTR	sys_cachectl
-	PTR	sys_sysmips
+	PTR	__sys_sysmips
 	PTR	sys_ni_syscall			/* 4150 */
 	PTR	sys_getsid
 	PTR	sys_fdatasync
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index 53a7ef9a8f32..4234b2d726c5 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -28,6 +28,7 @@
 #include <linux/elf.h>
 
 #include <asm/asm.h>
+#include <asm/asm-eva.h>
 #include <asm/branch.h>
 #include <asm/cachectl.h>
 #include <asm/cacheflush.h>
@@ -138,10 +139,12 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new)
 		__asm__ __volatile__ (
 		"	.set	"MIPS_ISA_ARCH_LEVEL"			\n"
 		"	li	%[err], 0				\n"
-		"1:	ll	%[old], (%[addr])			\n"
+		"1:							\n"
+		user_ll("%[old]", "(%[addr])")
 		"	move	%[tmp], %[new]				\n"
-		"2:	sc	%[tmp], (%[addr])			\n"
-		"	bnez	%[tmp], 4f				\n"
+		"2:							\n"
+		user_sc("%[tmp]", "(%[addr])")
+		"	beqz	%[tmp], 4f				\n"
 		"3:							\n"
 		"	.insn						\n"
 		"	.subsection 2					\n"
@@ -199,6 +202,12 @@ static inline int mips_atomic_set(unsigned long addr, unsigned long new)
 	unreachable();
 }
 
+/*
+ * mips_atomic_set() normally returns directly via syscall_exit potentially
+ * clobbering static registers, so be sure to preserve them.
+ */
+save_static_function(sys_sysmips);
+
 SYSCALL_DEFINE3(sysmips, long, cmd, long, arg1, long, arg2)
 {
 	switch (cmd) {
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 81f645973eb3..62ad117675b3 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -2140,6 +2140,35 @@ dcopuop:
 	return 0;
 }
 
+/*
+ * Emulate FPU instructions.
+ *
+ * If we use FPU hardware, then we have been typically called to handle
+ * an unimplemented operation, such as where an operand is a NaN or
+ * denormalized.  In that case exit the emulation loop after a single
+ * iteration so as to let hardware execute any subsequent instructions.
+ *
+ * If we have no FPU hardware or it has been disabled, then continue
+ * emulating floating-point instructions until one of these conditions
+ * has occurred:
+ *
+ * - a non-FPU instruction has been encountered,
+ *
+ * - an attempt to emulate has ended with a signal,
+ *
+ * - the ISA mode has been switched.
+ *
+ * We need to terminate the emulation loop if we got switched to the
+ * MIPS16 mode, whether supported or not, so that we do not attempt
+ * to emulate a MIPS16 instruction as a regular MIPS FPU instruction.
+ * Similarly if we got switched to the microMIPS mode and only the
+ * regular MIPS mode is supported, so that we do not attempt to emulate
+ * a microMIPS instruction as a regular MIPS FPU instruction.  Or if
+ * we got switched to the regular MIPS mode and only the microMIPS mode
+ * is supported, so that we do not attempt to emulate a regular MIPS
+ * instruction that should cause an Address Error exception instead.
+ * For simplicity we always terminate upon an ISA mode switch.
+ */
 int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 	int has_fpu, void *__user *fault_addr)
 {
@@ -2225,6 +2254,15 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			break;
 		if (sig)
 			break;
+		/*
+		 * We have to check for the ISA bit explicitly here,
+		 * because `get_isa16_mode' may return 0 if support
+		 * for code compression has been globally disabled,
+		 * or otherwise we may produce the wrong signal or
+		 * even proceed successfully where we must not.
+		 */
+		if ((xcp->cp0_epc ^ prevepc) & 0x1)
+			break;
 
 		cond_resched();
 	} while (xcp->cp0_epc > prevepc);
diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S
index 2d69a853b742..3a08b55609b6 100644
--- a/arch/openrisc/kernel/vmlinux.lds.S
+++ b/arch/openrisc/kernel/vmlinux.lds.S
@@ -38,6 +38,8 @@ SECTIONS
         /* Read-only sections, merged into text segment: */
         . = LOAD_BASE ;
 
+	_text = .;
+
 	/* _s_kernel_ro must be page aligned */
 	. = ALIGN(PAGE_SIZE);
 	_s_kernel_ro = .;
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 512d2782b043..0d6670056cd2 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -453,7 +453,7 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
  * Atomically increments @v by 1, so long as @v is non-zero.
  * Returns non-zero if @v was non-zero, and zero otherwise.
  */
-static __inline__ long atomic64_inc_not_zero(atomic64_t *v)
+static __inline__ int atomic64_inc_not_zero(atomic64_t *v)
 {
 	long t1, t2;
 
@@ -472,7 +472,7 @@ static __inline__ long atomic64_inc_not_zero(atomic64_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer", "memory");
 
-	return t1;
+	return t1 != 0;
 }
 
 #endif /* __powerpc64__ */
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index a4bf6e0eb813..e97e58e28668 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1237,7 +1237,7 @@ static inline unsigned long mfvtb (void)
 				"	.llong 0\n"			\
 				".previous"				\
 			: "=r" (rval) \
-			: "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL)); \
+			: "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \
 			rval;})
 #else
 #define mftb()		({unsigned long rval;	\
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index c1e10ffadd17..8e7a6c8efd27 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2232,6 +2232,10 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int r;
 	int srcu_idx;
+	unsigned long ebb_regs[3] = {};	/* shut up GCC */
+	unsigned long user_tar = 0;
+	unsigned long proc_fscr = 0;
+	unsigned int user_vrsave;
 
 	if (!vcpu->arch.sane) {
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
@@ -2281,6 +2285,17 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	flush_fp_to_thread(current);
 	flush_altivec_to_thread(current);
 	flush_vsx_to_thread(current);
+
+	/* Save userspace EBB and other register values */
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		ebb_regs[0] = mfspr(SPRN_EBBHR);
+		ebb_regs[1] = mfspr(SPRN_EBBRR);
+		ebb_regs[2] = mfspr(SPRN_BESCR);
+		user_tar = mfspr(SPRN_TAR);
+		proc_fscr = mfspr(SPRN_FSCR);
+	}
+	user_vrsave = mfspr(SPRN_VRSAVE);
+
 	vcpu->arch.wqp = &vcpu->arch.vcore->wq;
 	vcpu->arch.pgdir = current->mm->pgd;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
@@ -2302,6 +2317,16 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		}
 	} while (is_kvmppc_resume_guest(r));
 
+	/* Restore userspace EBB and other register values */
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		mtspr(SPRN_EBBHR, ebb_regs[0]);
+		mtspr(SPRN_EBBRR, ebb_regs[1]);
+		mtspr(SPRN_BESCR, ebb_regs[2]);
+		mtspr(SPRN_TAR, user_tar);
+		mtspr(SPRN_FSCR, proc_fscr);
+	}
+	mtspr(SPRN_VRSAVE, user_vrsave);
+
  out:
 	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
 	atomic_dec(&vcpu->kvm->arch.vcpus_running);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 70eaf547703e..a3018f109cd3 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -36,6 +36,13 @@
 #define NAPPING_CEDE	1
 #define NAPPING_NOVCPU	2
 
+/* Stack frame offsets for kvmppc_hv_entry */
+#define SFS			112
+#define STACK_SLOT_TRAP		(SFS-4)
+#define STACK_SLOT_CIABR	(SFS-16)
+#define STACK_SLOT_DAWR		(SFS-24)
+#define STACK_SLOT_DAWRX	(SFS-32)
+
 /*
  * Call kvmppc_hv_entry in real mode.
  * Must be called with interrupts hard-disabled.
@@ -265,10 +272,10 @@ kvm_novcpu_exit:
 	bl	kvmhv_accumulate_time
 #endif
 13:	mr	r3, r12
-	stw	r12, 112-4(r1)
+	stw	r12, STACK_SLOT_TRAP(r1)
 	bl	kvmhv_commence_exit
 	nop
-	lwz	r12, 112-4(r1)
+	lwz	r12, STACK_SLOT_TRAP(r1)
 	b	kvmhv_switch_to_host
 
 /*
@@ -404,7 +411,7 @@ kvmppc_hv_entry:
 	 */
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
-	stdu	r1, -112(r1)
+	stdu	r1, -SFS(r1)
 
 	/* Save R1 in the PACA */
 	std	r1, HSTATE_HOST_R1(r13)
@@ -558,6 +565,16 @@ kvmppc_got_guest:
 	mtspr	SPRN_PURR,r7
 	mtspr	SPRN_SPURR,r8
 
+	/* Save host values of some registers */
+BEGIN_FTR_SECTION
+	mfspr	r5, SPRN_CIABR
+	mfspr	r6, SPRN_DAWR
+	mfspr	r7, SPRN_DAWRX
+	std	r5, STACK_SLOT_CIABR(r1)
+	std	r6, STACK_SLOT_DAWR(r1)
+	std	r7, STACK_SLOT_DAWRX(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
 BEGIN_FTR_SECTION
 	/* Set partition DABR */
 	/* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
@@ -1169,8 +1186,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	 */
 	li	r0, 0
 	mtspr	SPRN_IAMR, r0
-	mtspr	SPRN_CIABR, r0
-	mtspr	SPRN_DAWRX, r0
+	mtspr	SPRN_PSPB, r0
 	mtspr	SPRN_TCSCR, r0
 	mtspr	SPRN_WORT, r0
 	/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
@@ -1186,6 +1202,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	std	r6,VCPU_UAMOR(r9)
 	li	r6,0
 	mtspr	SPRN_AMR,r6
+	mtspr	SPRN_UAMOR, r6
 
 	/* Switch DSCR back to host value */
 	mfspr	r8, SPRN_DSCR
@@ -1327,6 +1344,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	slbia
 	ptesync
 
+	/* Restore host values of some registers */
+BEGIN_FTR_SECTION
+	ld	r5, STACK_SLOT_CIABR(r1)
+	ld	r6, STACK_SLOT_DAWR(r1)
+	ld	r7, STACK_SLOT_DAWRX(r1)
+	mtspr	SPRN_CIABR, r5
+	mtspr	SPRN_DAWR, r6
+	mtspr	SPRN_DAWRX, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+
 	/*
 	 * POWER7/POWER8 guest -> host partition switch code.
 	 * We don't have to lock against tlbies but we do
@@ -1431,8 +1458,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	li	r0, KVM_GUEST_MODE_NONE
 	stb	r0, HSTATE_IN_GUEST(r13)
 
-	ld	r0, 112+PPC_LR_STKOFF(r1)
-	addi	r1, r1, 112
+	ld	r0, SFS+PPC_LR_STKOFF(r1)
+	addi	r1, r1, SFS
 	mtlr	r0
 	blr
 
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 4014881e9843..e37162d356d8 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -687,8 +687,10 @@ int __kprobes analyse_instr(struct instruction_op *op, struct pt_regs *regs,
 	case 19:
 		switch ((instr >> 1) & 0x3ff) {
 		case 0:		/* mcrf */
-			rd = (instr >> 21) & 0x1c;
-			ra = (instr >> 16) & 0x1c;
+			rd = 7 - ((instr >> 23) & 0x7);
+			ra = 7 - ((instr >> 18) & 0x7);
+			rd *= 4;
+			ra *= 4;
 			val = (regs->ccr >> ra) & 0xf;
 			regs->ccr = (regs->ccr & ~(0xfUL << rd)) | (val << rd);
 			goto instr_done;
@@ -967,6 +969,19 @@ int __kprobes analyse_instr(struct instruction_op *op, struct pt_regs *regs,
 #endif
 
 		case 19:	/* mfcr */
+			if ((instr >> 20) & 1) {
+				imm = 0xf0000000UL;
+				for (sh = 0; sh < 8; ++sh) {
+					if (instr & (0x80000 >> sh)) {
+						regs->gpr[rd] = regs->ccr & imm;
+						break;
+					}
+					imm >>= 4;
+				}
+
+				goto instr_done;
+			}
+
 			regs->gpr[rd] = regs->ccr;
 			regs->gpr[rd] &= 0xffffffffUL;
 			goto instr_done;
diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c
index 0f319521e002..14392b4e4693 100644
--- a/arch/powerpc/platforms/pseries/reconfig.c
+++ b/arch/powerpc/platforms/pseries/reconfig.c
@@ -112,7 +112,6 @@ static int pSeries_reconfig_remove_node(struct device_node *np)
 
 	of_detach_node(np);
 	of_node_put(parent);
-	of_node_put(np); /* Must decrement the refcount */
 	return 0;
 }
 
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 6ba0bf928909..6bc941be6921 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -64,6 +64,12 @@ static inline void syscall_get_arguments(struct task_struct *task,
 {
 	unsigned long mask = -1UL;
 
+	/*
+	 * No arguments for this syscall, there's nothing to do.
+	 */
+	if (!n)
+		return;
+
 	BUG_ON(i + n > 6);
 #ifdef CONFIG_COMPAT
 	if (test_tsk_thread_flag(task, TIF_31BIT))
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index dc2d7aa56440..a3b51d30e8d8 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -1139,7 +1139,8 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp)
 		insn_count = bpf_jit_insn(jit, fp, i);
 		if (insn_count < 0)
 			return -1;
-		jit->addrs[i + 1] = jit->prg; /* Next instruction address */
+		/* Next instruction address */
+		jit->addrs[i + insn_count] = jit->prg;
 	}
 	bpf_jit_epilogue(jit);
 
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index 349dd23e2876..0cdeb2b483a0 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -25,9 +25,11 @@ void destroy_context(struct mm_struct *mm);
 void __tsb_context_switch(unsigned long pgd_pa,
 			  struct tsb_config *tsb_base,
 			  struct tsb_config *tsb_huge,
-			  unsigned long tsb_descr_pa);
+			  unsigned long tsb_descr_pa,
+			  unsigned long secondary_ctx);
 
-static inline void tsb_context_switch(struct mm_struct *mm)
+static inline void tsb_context_switch_ctx(struct mm_struct *mm,
+					  unsigned long ctx)
 {
 	__tsb_context_switch(__pa(mm->pgd),
 			     &mm->context.tsb_block[0],
@@ -38,9 +40,12 @@ static inline void tsb_context_switch(struct mm_struct *mm)
 #else
 			     NULL
 #endif
-			     , __pa(&mm->context.tsb_descr[0]));
+			     , __pa(&mm->context.tsb_descr[0]),
+			     ctx);
 }
 
+#define tsb_context_switch(X) tsb_context_switch_ctx(X, 0)
+
 void tsb_grow(struct mm_struct *mm,
 	      unsigned long tsb_index,
 	      unsigned long mm_rss);
@@ -110,8 +115,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 	 * cpu0 to update it's TSB because at that point the cpu_vm_mask
 	 * only had cpu1 set in it.
 	 */
-	load_secondary_context(mm);
-	tsb_context_switch(mm);
+	tsb_context_switch_ctx(mm, CTX_HWBITS(mm->context));
 
 	/* Any time a processor runs a context on an address space
 	 * for the first time, we must flush that context out of the
diff --git a/arch/sparc/include/asm/trap_block.h b/arch/sparc/include/asm/trap_block.h
index ec9c04de3664..ff05992dae7a 100644
--- a/arch/sparc/include/asm/trap_block.h
+++ b/arch/sparc/include/asm/trap_block.h
@@ -54,6 +54,7 @@ extern struct trap_per_cpu trap_block[NR_CPUS];
 void init_cur_cpu_trap(struct thread_info *);
 void setup_tba(void);
 extern int ncpus_probed;
+extern u64 cpu_mondo_counter[NR_CPUS];
 
 unsigned long real_hard_smp_processor_id(void);
 
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 95a9fa0d2195..4511caa3b7e9 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -617,22 +617,48 @@ retry:
 	}
 }
 
-/* Multi-cpu list version.  */
+#define	CPU_MONDO_COUNTER(cpuid)	(cpu_mondo_counter[cpuid])
+#define	MONDO_USEC_WAIT_MIN		2
+#define	MONDO_USEC_WAIT_MAX		100
+#define	MONDO_RETRY_LIMIT		500000
+
+/* Multi-cpu list version.
+ *
+ * Deliver xcalls to 'cnt' number of cpus in 'cpu_list'.
+ * Sometimes not all cpus receive the mondo, requiring us to re-send
+ * the mondo until all cpus have received, or cpus are truly stuck
+ * unable to receive mondo, and we timeout.
+ * Occasionally a target cpu strand is borrowed briefly by hypervisor to
+ * perform guest service, such as PCIe error handling. Consider the
+ * service time, 1 second overall wait is reasonable for 1 cpu.
+ * Here two in-between mondo check wait time are defined: 2 usec for
+ * single cpu quick turn around and up to 100usec for large cpu count.
+ * Deliver mondo to large number of cpus could take longer, we adjusts
+ * the retry count as long as target cpus are making forward progress.
+ */
 static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt)
 {
-	int retries, this_cpu, prev_sent, i, saw_cpu_error;
+	int this_cpu, tot_cpus, prev_sent, i, rem;
+	int usec_wait, retries, tot_retries;
+	u16 first_cpu = 0xffff;
+	unsigned long xc_rcvd = 0;
 	unsigned long status;
+	int ecpuerror_id = 0;
+	int enocpu_id = 0;
 	u16 *cpu_list;
+	u16 cpu;
 
 	this_cpu = smp_processor_id();
-
 	cpu_list = __va(tb->cpu_list_pa);
-
-	saw_cpu_error = 0;
-	retries = 0;
+	usec_wait = cnt * MONDO_USEC_WAIT_MIN;
+	if (usec_wait > MONDO_USEC_WAIT_MAX)
+		usec_wait = MONDO_USEC_WAIT_MAX;
+	retries = tot_retries = 0;
+	tot_cpus = cnt;
 	prev_sent = 0;
+
 	do {
-		int forward_progress, n_sent;
+		int n_sent, mondo_delivered, target_cpu_busy;
 
 		status = sun4v_cpu_mondo_send(cnt,
 					      tb->cpu_list_pa,
@@ -640,94 +666,113 @@ static void hypervisor_xcall_deliver(struct trap_per_cpu *tb, int cnt)
 
 		/* HV_EOK means all cpus received the xcall, we're done.  */
 		if (likely(status == HV_EOK))
-			break;
+			goto xcall_done;
+
+		/* If not these non-fatal errors, panic */
+		if (unlikely((status != HV_EWOULDBLOCK) &&
+			(status != HV_ECPUERROR) &&
+			(status != HV_ENOCPU)))
+			goto fatal_errors;
 
 		/* First, see if we made any forward progress.
 		 *
+		 * Go through the cpu_list, count the target cpus that have
+		 * received our mondo (n_sent), and those that did not (rem).
+		 * Re-pack cpu_list with the cpus remain to be retried in the
+		 * front - this simplifies tracking the truly stalled cpus.
+		 *
 		 * The hypervisor indicates successful sends by setting
 		 * cpu list entries to the value 0xffff.
+		 *
+		 * EWOULDBLOCK means some target cpus did not receive the
+		 * mondo and retry usually helps.
+		 *
+		 * ECPUERROR means at least one target cpu is in error state,
+		 * it's usually safe to skip the faulty cpu and retry.
+		 *
+		 * ENOCPU means one of the target cpu doesn't belong to the
+		 * domain, perhaps offlined which is unexpected, but not
+		 * fatal and it's okay to skip the offlined cpu.
 		 */
+		rem = 0;
 		n_sent = 0;
 		for (i = 0; i < cnt; i++) {
-			if (likely(cpu_list[i] == 0xffff))
+			cpu = cpu_list[i];
+			if (likely(cpu == 0xffff)) {
 				n_sent++;
+			} else if ((status == HV_ECPUERROR) &&
+				(sun4v_cpu_state(cpu) == HV_CPU_STATE_ERROR)) {
+				ecpuerror_id = cpu + 1;
+			} else if (status == HV_ENOCPU && !cpu_online(cpu)) {
+				enocpu_id = cpu + 1;
+			} else {
+				cpu_list[rem++] = cpu;
+			}
 		}
 
-		forward_progress = 0;
-		if (n_sent > prev_sent)
-			forward_progress = 1;
+		/* No cpu remained, we're done. */
+		if (rem == 0)
+			break;
 
-		prev_sent = n_sent;
+		/* Otherwise, update the cpu count for retry. */
+		cnt = rem;
 
-		/* If we get a HV_ECPUERROR, then one or more of the cpus
-		 * in the list are in error state.  Use the cpu_state()
-		 * hypervisor call to find out which cpus are in error state.
+		/* Record the overall number of mondos received by the
+		 * first of the remaining cpus.
 		 */
-		if (unlikely(status == HV_ECPUERROR)) {
-			for (i = 0; i < cnt; i++) {
-				long err;
-				u16 cpu;
+		if (first_cpu != cpu_list[0]) {
+			first_cpu = cpu_list[0];
+			xc_rcvd = CPU_MONDO_COUNTER(first_cpu);
+		}
 
-				cpu = cpu_list[i];
-				if (cpu == 0xffff)
-					continue;
+		/* Was any mondo delivered successfully? */
+		mondo_delivered = (n_sent > prev_sent);
+		prev_sent = n_sent;
 
-				err = sun4v_cpu_state(cpu);
-				if (err == HV_CPU_STATE_ERROR) {
-					saw_cpu_error = (cpu + 1);
-					cpu_list[i] = 0xffff;
-				}
-			}
-		} else if (unlikely(status != HV_EWOULDBLOCK))
-			goto fatal_mondo_error;
+		/* or, was any target cpu busy processing other mondos? */
+		target_cpu_busy = (xc_rcvd < CPU_MONDO_COUNTER(first_cpu));
+		xc_rcvd = CPU_MONDO_COUNTER(first_cpu);
 
-		/* Don't bother rewriting the CPU list, just leave the
-		 * 0xffff and non-0xffff entries in there and the
-		 * hypervisor will do the right thing.
-		 *
-		 * Only advance timeout state if we didn't make any
-		 * forward progress.
+		/* Retry count is for no progress. If we're making progress,
+		 * reset the retry count.
 		 */
-		if (unlikely(!forward_progress)) {
-			if (unlikely(++retries > 10000))
-				goto fatal_mondo_timeout;
-
-			/* Delay a little bit to let other cpus catch up
-			 * on their cpu mondo queue work.
-			 */
-			udelay(2 * cnt);
+		if (likely(mondo_delivered || target_cpu_busy)) {
+			tot_retries += retries;
+			retries = 0;
+		} else if (unlikely(retries > MONDO_RETRY_LIMIT)) {
+			goto fatal_mondo_timeout;
 		}
-	} while (1);
 
-	if (unlikely(saw_cpu_error))
-		goto fatal_mondo_cpu_error;
+		/* Delay a little bit to let other cpus catch up on
+		 * their cpu mondo queue work.
+		 */
+		if (!mondo_delivered)
+			udelay(usec_wait);
 
-	return;
+		retries++;
+	} while (1);
 
-fatal_mondo_cpu_error:
-	printk(KERN_CRIT "CPU[%d]: SUN4V mondo cpu error, some target cpus "
-	       "(including %d) were in error state\n",
-	       this_cpu, saw_cpu_error - 1);
+xcall_done:
+	if (unlikely(ecpuerror_id > 0)) {
+		pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) was in error state\n",
+		       this_cpu, ecpuerror_id - 1);
+	} else if (unlikely(enocpu_id > 0)) {
+		pr_crit("CPU[%d]: SUN4V mondo cpu error, target cpu(%d) does not belong to the domain\n",
+		       this_cpu, enocpu_id - 1);
+	}
 	return;
 
+fatal_errors:
+	/* fatal errors include bad alignment, etc */
+	pr_crit("CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) mondo_block_pa(%lx)\n",
+	       this_cpu, tot_cpus, tb->cpu_list_pa, tb->cpu_mondo_block_pa);
+	panic("Unexpected SUN4V mondo error %lu\n", status);
+
 fatal_mondo_timeout:
-	printk(KERN_CRIT "CPU[%d]: SUN4V mondo timeout, no forward "
-	       " progress after %d retries.\n",
-	       this_cpu, retries);
-	goto dump_cpu_list_and_out;
-
-fatal_mondo_error:
-	printk(KERN_CRIT "CPU[%d]: Unexpected SUN4V mondo error %lu\n",
-	       this_cpu, status);
-	printk(KERN_CRIT "CPU[%d]: Args were cnt(%d) cpulist_pa(%lx) "
-	       "mondo_block_pa(%lx)\n",
-	       this_cpu, cnt, tb->cpu_list_pa, tb->cpu_mondo_block_pa);
-
-dump_cpu_list_and_out:
-	printk(KERN_CRIT "CPU[%d]: CPU list [ ", this_cpu);
-	for (i = 0; i < cnt; i++)
-		printk("%u ", cpu_list[i]);
-	printk("]\n");
+	/* some cpus being non-responsive to the cpu mondo */
+	pr_crit("CPU[%d]: SUN4V mondo timeout, cpu(%d) made no forward progress after %d retries. Total target cpus(%d).\n",
+	       this_cpu, first_cpu, (tot_retries + retries), tot_cpus);
+	panic("SUN4V mondo timeout panic\n");
 }
 
 static void (*xcall_deliver_impl)(struct trap_per_cpu *, int);
diff --git a/arch/sparc/kernel/sun4v_ivec.S b/arch/sparc/kernel/sun4v_ivec.S
index 559bc5e9c199..34631995859a 100644
--- a/arch/sparc/kernel/sun4v_ivec.S
+++ b/arch/sparc/kernel/sun4v_ivec.S
@@ -26,6 +26,21 @@ sun4v_cpu_mondo:
 	ldxa	[%g0] ASI_SCRATCHPAD, %g4
 	sub	%g4, TRAP_PER_CPU_FAULT_INFO, %g4
 
+	/* Get smp_processor_id() into %g3 */
+	sethi	%hi(trap_block), %g5
+	or	%g5, %lo(trap_block), %g5
+	sub	%g4, %g5, %g3
+	srlx	%g3, TRAP_BLOCK_SZ_SHIFT, %g3
+
+	/* Increment cpu_mondo_counter[smp_processor_id()] */
+	sethi	%hi(cpu_mondo_counter), %g5
+	or	%g5, %lo(cpu_mondo_counter), %g5
+	sllx	%g3, 3, %g3
+	add	%g5, %g3, %g5
+	ldx	[%g5], %g3
+	add	%g3, 1, %g3
+	stx	%g3, [%g5]
+
 	/* Get CPU mondo queue base phys address into %g7.  */
 	ldx	[%g4 + TRAP_PER_CPU_CPU_MONDO_PA], %g7
 
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index cc97a43268ee..d883c5951e8b 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2659,6 +2659,7 @@ void do_getpsr(struct pt_regs *regs)
 	}
 }
 
+u64 cpu_mondo_counter[NR_CPUS] = {0};
 struct trap_per_cpu trap_block[NR_CPUS];
 EXPORT_SYMBOL(trap_block);
 
diff --git a/arch/sparc/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index 8e920d152565..12fe20c9042c 100644
--- a/arch/sparc/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -367,6 +367,7 @@ tsb_flush:
 	 * %o1:	TSB base config pointer
 	 * %o2:	TSB huge config pointer, or NULL if none
 	 * %o3:	Hypervisor TSB descriptor physical address
+	 * %o4: Secondary context to load, if non-zero
 	 *
 	 * We have to run this whole thing with interrupts
 	 * disabled so that the current cpu doesn't change
@@ -379,6 +380,17 @@ __tsb_context_switch:
 	rdpr	%pstate, %g1
 	wrpr	%g1, PSTATE_IE, %pstate
 
+	brz,pn	%o4, 1f
+	 mov	SECONDARY_CONTEXT, %o5
+
+661:	stxa	%o4, [%o5] ASI_DMMU
+	.section .sun4v_1insn_patch, "ax"
+	.word	661b
+	stxa	%o4, [%o5] ASI_MMU
+	.previous
+	flush	%g6
+
+1:
 	TRAP_LOAD_TRAP_BLOCK(%g2, %g3)
 
 	stx	%o0, [%g2 + TRAP_PER_CPU_PGD_PADDR]
diff --git a/arch/sparc/power/hibernate.c b/arch/sparc/power/hibernate.c
index 17bd2e167e07..df707a8ad311 100644
--- a/arch/sparc/power/hibernate.c
+++ b/arch/sparc/power/hibernate.c
@@ -35,6 +35,5 @@ void restore_processor_state(void)
 {
 	struct mm_struct *mm = current->active_mm;
 
-	load_secondary_context(mm);
-	tsb_context_switch(mm);
+	tsb_context_switch_ctx(mm, CTX_HWBITS(mm->context));
 }
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 318b8465d302..06ceddb3a22e 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -14,6 +14,7 @@
 
 #include <linux/types.h>
 #include "ctype.h"
+#include "string.h"
 
 int memcmp(const void *s1, const void *s2, size_t len)
 {
diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h
index 725e820602b1..113588ddb43f 100644
--- a/arch/x86/boot/string.h
+++ b/arch/x86/boot/string.h
@@ -18,4 +18,13 @@ int memcmp(const void *s1, const void *s2, size_t len);
 #define memset(d,c,l) __builtin_memset(d,c,l)
 #define memcmp	__builtin_memcmp
 
+extern int strcmp(const char *str1, const char *str2);
+extern int strncmp(const char *cs, const char *ct, size_t count);
+extern size_t strlen(const char *s);
+extern char *strstr(const char *s1, const char *s2);
+extern size_t strnlen(const char *s, size_t maxlen);
+extern unsigned int atou(const char *s);
+extern unsigned long long simple_strtoull(const char *cp, char **endp,
+					  unsigned int base);
+
 #endif /* BOOT_STRING_H */
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index ca08a27b90b3..4ad5a91aea79 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -43,6 +43,7 @@
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
+#include <asm/smap.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
@@ -213,10 +214,12 @@ privcmd_call(unsigned call,
 	__HYPERCALL_DECLS;
 	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
 
+	stac();
 	asm volatile("call *%[call]"
 		     : __HYPERCALL_5PARAM
 		     : [call] "a" (&hypercall_page[call])
 		     : __HYPERCALL_CLOBBER5);
+	clac();
 
 	return (long)__res;
 }
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 07bea80223f6..60aa02503b48 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -329,6 +329,14 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 	struct mpc_intsrc mp_irq;
 
 	/*
+	 * Check bus_irq boundary.
+	 */
+	if (bus_irq >= NR_IRQS_LEGACY) {
+		pr_warn("Invalid bus_irq %u for legacy override\n", bus_irq);
+		return;
+	}
+
+	/*
 	 * Convert 'gsi' to 'ioapic.pin'.
 	 */
 	ioapic = mp_find_ioapic(gsi);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index df61c2d0cb56..bd7e7d6c29c5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -581,6 +581,9 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	const char *name = th_names[bank];
 	int err = 0;
 
+	if (!dev)
+		return -ENODEV;
+
 	if (is_shared_bank(bank)) {
 		nb = node_to_amd_nb(amd_get_nb_id(cpu));
 
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 27e63c1770e6..916e84aa5447 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -151,6 +151,8 @@ void kvm_async_pf_task_wait(u32 token)
 		if (hlist_unhashed(&n.link))
 			break;
 
+		rcu_irq_exit();
+
 		if (!n.halted) {
 			local_irq_enable();
 			schedule();
@@ -159,11 +161,11 @@ void kvm_async_pf_task_wait(u32 token)
 			/*
 			 * We cannot reschedule. So halt.
 			 */
-			rcu_irq_exit();
 			native_safe_halt();
 			local_irq_disable();
-			rcu_irq_enter();
 		}
+
+		rcu_irq_enter();
 	}
 	if (!n.halted)
 		finish_wait(&n.wq, &wait);