Merge tag 'v4.9.62' into linux-linaro-lsk-v4.9

 This is the 4.9.62 stable release

24 files changed, 129 insertions, 83 deletions

diff --git a/arch/arm/boot/dts/imx53-qsb-common.dtsi b/arch/arm/boot/dts/imx53-qsb-common.dtsi
index c05e7cf..40b3e31 100644
--- a/arch/arm/boot/dts/imx53-qsb-common.dtsi
+++ b/arch/arm/boot/dts/imx53-qsb-common.dtsi
@@ -215,16 +215,16 @@
 
 		pinctrl_fec: fecgrp {
 			fsl,pins = <
-				MX53_PAD_FEC_MDC__FEC_MDC		0x80000000
-				MX53_PAD_FEC_MDIO__FEC_MDIO		0x80000000
-				MX53_PAD_FEC_REF_CLK__FEC_TX_CLK	0x80000000
-				MX53_PAD_FEC_RX_ER__FEC_RX_ER		0x80000000
-				MX53_PAD_FEC_CRS_DV__FEC_RX_DV		0x80000000
-				MX53_PAD_FEC_RXD1__FEC_RDATA_1		0x80000000
-				MX53_PAD_FEC_RXD0__FEC_RDATA_0		0x80000000
-				MX53_PAD_FEC_TX_EN__FEC_TX_EN		0x80000000
-				MX53_PAD_FEC_TXD1__FEC_TDATA_1		0x80000000
-				MX53_PAD_FEC_TXD0__FEC_TDATA_0		0x80000000
+				MX53_PAD_FEC_MDC__FEC_MDC		0x4
+				MX53_PAD_FEC_MDIO__FEC_MDIO		0x1fc
+				MX53_PAD_FEC_REF_CLK__FEC_TX_CLK	0x180
+				MX53_PAD_FEC_RX_ER__FEC_RX_ER		0x180
+				MX53_PAD_FEC_CRS_DV__FEC_RX_DV		0x180
+				MX53_PAD_FEC_RXD1__FEC_RDATA_1		0x180
+				MX53_PAD_FEC_RXD0__FEC_RDATA_0		0x180
+				MX53_PAD_FEC_TX_EN__FEC_TX_EN		0x4
+				MX53_PAD_FEC_TXD1__FEC_TDATA_1		0x4
+				MX53_PAD_FEC_TXD0__FEC_TDATA_0		0x4
 			>;
 		};
 
diff --git a/arch/arm/boot/dts/stih410.dtsi b/arch/arm/boot/dts/stih410.dtsi
index a3ef734..4d329b2 100644
--- a/arch/arm/boot/dts/stih410.dtsi
+++ b/arch/arm/boot/dts/stih410.dtsi
@@ -131,7 +131,7 @@
 						 <&clk_s_d2_quadfs 0>;
 
 			assigned-clock-rates = <297000000>,
-					       <108000000>,
+					       <297000000>,
 					       <0>,
 					       <400000000>,
 					       <400000000>;
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 53e1a88..66d7196 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -216,6 +216,7 @@ CONFIG_SERIO=m
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_8250_NR_UARTS=32
+CONFIG_SERIAL_8250_RUNTIME_UARTS=6
 CONFIG_SERIAL_8250_EXTENDED=y
 CONFIG_SERIAL_8250_MANY_PORTS=y
 CONFIG_SERIAL_8250_SHARE_IRQ=y
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 9688ec0..1b30489 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -152,30 +152,26 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
 	set_fs(fs);
 }
 
-static void dump_instr(const char *lvl, struct pt_regs *regs)
+static void __dump_instr(const char *lvl, struct pt_regs *regs)
 {
 	unsigned long addr = instruction_pointer(regs);
 	const int thumb = thumb_mode(regs);
 	const int width = thumb ? 4 : 8;
-	mm_segment_t fs;
 	char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
 	int i;
 
 	/*
-	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.  Note that we now dump the
-	 * code first, just in case the backtrace kills us.
+	 * Note that we now dump the code first, just in case the backtrace
+	 * kills us.
 	 */
-	fs = get_fs();
-	set_fs(KERNEL_DS);
 
 	for (i = -4; i < 1 + !!thumb; i++) {
 		unsigned int val, bad;
 
 		if (thumb)
-			bad = __get_user(val, &((u16 *)addr)[i]);
+			bad = get_user(val, &((u16 *)addr)[i]);
 		else
-			bad = __get_user(val, &((u32 *)addr)[i]);
+			bad = get_user(val, &((u32 *)addr)[i]);
 
 		if (!bad)
 			p += sprintf(p, i == 0 ? "(%0*x) " : "%0*x ",
@@ -186,8 +182,20 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 		}
 	}
 	printk("%sCode: %s\n", lvl, str);
+}
 
-	set_fs(fs);
+static void dump_instr(const char *lvl, struct pt_regs *regs)
+{
+	mm_segment_t fs;
+
+	if (!user_mode(regs)) {
+		fs = get_fs();
+		set_fs(KERNEL_DS);
+		__dump_instr(lvl, regs);
+		set_fs(fs);
+	} else {
+		__dump_instr(lvl, regs);
+	}
 }
 
 #ifdef CONFIG_ARM_UNWIND
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index b5bf46c..cab3574 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -836,14 +836,21 @@ static bool do_iommu_attach(struct device *dev, const struct iommu_ops *ops,
 	 * then the IOMMU core will have already configured a group for this
 	 * device, and allocated the default domain for that group.
 	 */
-	if (!domain || iommu_dma_init_domain(domain, dma_base, size, dev)) {
-		pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
-			dev_name(dev));
-		return false;
+	if (!domain)
+		goto out_err;
+
+	if (domain->type == IOMMU_DOMAIN_DMA) {
+		if (iommu_dma_init_domain(domain, dma_base, size, dev))
+			goto out_err;
+
+		dev->archdata.dma_ops = &iommu_dma_ops;
 	}
 
-	dev->archdata.dma_ops = &iommu_dma_ops;
 	return true;
+out_err:
+	pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
+		 dev_name(dev));
+	return false;
 }
 
 static void queue_iommu_attach(struct device *dev, const struct iommu_ops *ops,
diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c
index 58fca9a..3446b6f 100644
--- a/arch/mips/ar7/platform.c
+++ b/arch/mips/ar7/platform.c
@@ -576,6 +576,7 @@ static int __init ar7_register_uarts(void)
 	uart_port.type		= PORT_AR7;
 	uart_port.uartclk	= clk_get_rate(bus_clk) / 2;
 	uart_port.iotype	= UPIO_MEM32;
+	uart_port.flags		= UPF_FIXED_TYPE;
 	uart_port.regshift	= 2;
 
 	uart_port.line		= 0;
@@ -654,6 +655,10 @@ static int __init ar7_register_devices(void)
 	u32 val;
 	int res;
 
+	res = ar7_gpio_init();
+	if (res)
+		pr_warn("unable to register gpios: %d\n", res);
+
 	res = ar7_register_uarts();
 	if (res)
 		pr_err("unable to setup uart(s): %d\n", res);
diff --git a/arch/mips/ar7/prom.c b/arch/mips/ar7/prom.c
index a23adc4..36aabee 100644
--- a/arch/mips/ar7/prom.c
+++ b/arch/mips/ar7/prom.c
@@ -246,8 +246,6 @@ void __init prom_init(void)
 	ar7_init_cmdline(fw_arg0, (char **)fw_arg1);
 	ar7_init_env((struct env_var *)fw_arg2);
 	console_config();
-
-	ar7_gpio_init();
 }
 
 #define PORT(offset) (KSEG1ADDR(AR7_REGS_UART0 + (offset * 4)))
diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index 2e41807..b6845db 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -239,8 +239,8 @@ BUILD_CM_Cx_R_(tcid_8_priority,	0x80)
 #define CM_GCR_BASE_GCRBASE_MSK			(_ULCAST_(0x1ffff) << 15)
 #define CM_GCR_BASE_CMDEFTGT_SHF		0
 #define CM_GCR_BASE_CMDEFTGT_MSK		(_ULCAST_(0x3) << 0)
-#define  CM_GCR_BASE_CMDEFTGT_DISABLED		0
-#define  CM_GCR_BASE_CMDEFTGT_MEM		1
+#define  CM_GCR_BASE_CMDEFTGT_MEM		0
+#define  CM_GCR_BASE_CMDEFTGT_RESERVED		1
 #define  CM_GCR_BASE_CMDEFTGT_IOCU0		2
 #define  CM_GCR_BASE_CMDEFTGT_IOCU1		3
 
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 1b50958..c558bce 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -50,9 +50,7 @@
 #ifdef CONFIG_HOTPLUG_CPU
 void arch_cpu_idle_dead(void)
 {
-	/* What the heck is this check doing ? */
-	if (!cpumask_test_cpu(smp_processor_id(), &cpu_callin_map))
-		play_dead();
+	play_dead();
 }
 #endif
 
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 6d0f132..47c9646 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -587,11 +587,11 @@ void __init bmips_cpu_setup(void)
 
 		/* Flush and enable RAC */
 		cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG);
-		__raw_writel(cfg | 0x100, BMIPS_RAC_CONFIG);
+		__raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG);
 		__raw_readl(cbr + BMIPS_RAC_CONFIG);
 
 		cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG);
-		__raw_writel(cfg | 0xf, BMIPS_RAC_CONFIG);
+		__raw_writel(cfg | 0xf, cbr + BMIPS_RAC_CONFIG);
 		__raw_readl(cbr + BMIPS_RAC_CONFIG);
 
 		cfg = __raw_readl(cbr + BMIPS_RAC_ADDRESS_RANGE);
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 7ebb191..95ba427 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -68,6 +68,9 @@ EXPORT_SYMBOL(cpu_sibling_map);
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_core_map);
 
+static DECLARE_COMPLETION(cpu_starting);
+static DECLARE_COMPLETION(cpu_running);
+
 /*
  * A logcal cpu mask containing only one VPE per core to
  * reduce the number of IPIs on large MT systems.
@@ -369,9 +372,12 @@ asmlinkage void start_secondary(void)
 	cpumask_set_cpu(cpu, &cpu_coherent_mask);
 	notify_cpu_starting(cpu);
 
-	cpumask_set_cpu(cpu, &cpu_callin_map);
+	/* Notify boot CPU that we're starting & ready to sync counters */
+	complete(&cpu_starting);
+
 	synchronise_count_slave(cpu);
 
+	/* The CPU is running and counters synchronised, now mark it online */
 	set_cpu_online(cpu, true);
 
 	set_cpu_sibling_map(cpu);
@@ -380,6 +386,12 @@ asmlinkage void start_secondary(void)
 	calculate_cpu_foreign_map();
 
 	/*
+	 * Notify boot CPU that we're up & online and it can safely return
+	 * from __cpu_up
+	 */
+	complete(&cpu_running);
+
+	/*
 	 * irq will be enabled in ->smp_finish(), enabling it too early
 	 * is dangerous.
 	 */
@@ -430,22 +442,23 @@ void smp_prepare_boot_cpu(void)
 {
 	set_cpu_possible(0, true);
 	set_cpu_online(0, true);
-	cpumask_set_cpu(0, &cpu_callin_map);
 }
 
 int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	mp_ops->boot_secondary(cpu, tidle);
 
-	/*
-	 * Trust is futile.  We should really have timeouts ...
-	 */
-	while (!cpumask_test_cpu(cpu, &cpu_callin_map)) {
-		udelay(100);
-		schedule();
+	/* Wait for CPU to start and be ready to sync counters */
+	if (!wait_for_completion_timeout(&cpu_starting,
+					 msecs_to_jiffies(1000))) {
+		pr_crit("CPU%u: failed to start\n", cpu);
+		return -EIO;
 	}
 
 	synchronise_count_master(cpu);
+
+	/* Wait for CPU to finish startup & mark itself online before return */
+	wait_for_completion(&cpu_running);
 	return 0;
 }
 
diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index 277cf52..6c17cba 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -80,7 +80,7 @@ static struct insn insn_table_MM[] = {
 	{ insn_jr, M(mm_pool32a_op, 0, 0, 0, mm_jalr_op, mm_pool32axf_op), RS },
 	{ insn_lb, M(mm_lb32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
 	{ insn_ld, 0, 0 },
-	{ insn_lh, M(mm_lh32_op, 0, 0, 0, 0, 0), RS | RS | SIMM },
+	{ insn_lh, M(mm_lh32_op, 0, 0, 0, 0, 0), RT | RS | SIMM },
 	{ insn_ll, M(mm_pool32c_op, 0, 0, (mm_ll_func << 1), 0, 0), RS | RT | SIMM },
 	{ insn_lld, 0, 0 },
 	{ insn_lui, M(mm_pool32i_op, mm_lui_op, 0, 0, 0, 0), RS | SIMM },
diff --git a/arch/powerpc/boot/dts/fsl/kmcoge4.dts b/arch/powerpc/boot/dts/fsl/kmcoge4.dts
index ae70a24..e103c0f 100644
--- a/arch/powerpc/boot/dts/fsl/kmcoge4.dts
+++ b/arch/powerpc/boot/dts/fsl/kmcoge4.dts
@@ -83,6 +83,10 @@
 			};
 		};
 
+		sdhc@114000 {
+			status = "disabled";
+		};
+
 		i2c@119000 {
 			status = "disabled";
 		};
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index bc3f7d0..f1d7e99 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -407,6 +407,7 @@ void arch_vtime_task_switch(struct task_struct *prev)
 	struct cpu_accounting_data *acct = get_accounting(current);
 
 	acct->starttime = get_accounting(prev)->starttime;
+	acct->startspurr = get_accounting(prev)->startspurr;
 	acct->system_time = 0;
 	acct->user_time = 0;
 }
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index a0ea63a..a8e3498 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -376,6 +376,7 @@ static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 		 */
 		if (reject && reject != XICS_IPI) {
 			arch_spin_unlock(&ics->lock);
+			icp->n_reject++;
 			new_irq = reject;
 			goto again;
 		}
@@ -707,10 +708,8 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
 	state = &ics->irq_state[src];
 
 	/* Still asserted, resend it */
-	if (state->asserted) {
-		icp->n_reject++;
+	if (state->asserted)
 		icp_rm_deliver_irq(xics, icp, irq);
-	}
 
 	if (!hlist_empty(&vcpu->kvm->irq_ack_notifier_list)) {
 		icp->rm_action |= XICS_RM_NOTIFY_EOI;
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 2374c5b..0c19686 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -363,6 +363,18 @@ static inline void save_vector_registers(void)
 #endif
 }
 
+static int __init topology_setup(char *str)
+{
+	bool enabled;
+	int rc;
+
+	rc = kstrtobool(str, &enabled);
+	if (!rc && !enabled)
+		S390_lowcore.machine_flags &= ~MACHINE_HAS_TOPOLOGY;
+	return rc;
+}
+early_param("topology", topology_setup);
+
 static int __init disable_vector_extension(char *str)
 {
 	S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 8705ee6..239f295 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -37,7 +37,6 @@ static void set_topology_timer(void);
 static void topology_work_fn(struct work_struct *work);
 static struct sysinfo_15_1_x *tl_info;
 
-static bool topology_enabled = true;
 static DECLARE_WORK(topology_work, topology_work_fn);
 
 /*
@@ -56,7 +55,7 @@ static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 	cpumask_t mask;
 
 	cpumask_copy(&mask, cpumask_of(cpu));
-	if (!topology_enabled || !MACHINE_HAS_TOPOLOGY)
+	if (!MACHINE_HAS_TOPOLOGY)
 		return mask;
 	for (; info; info = info->next) {
 		if (cpumask_test_cpu(cpu, &info->mask))
@@ -71,7 +70,7 @@ static cpumask_t cpu_thread_map(unsigned int cpu)
 	int i;
 
 	cpumask_copy(&mask, cpumask_of(cpu));
-	if (!topology_enabled || !MACHINE_HAS_TOPOLOGY)
+	if (!MACHINE_HAS_TOPOLOGY)
 		return mask;
 	cpu -= cpu % (smp_cpu_mtid + 1);
 	for (i = 0; i <= smp_cpu_mtid; i++)
@@ -413,12 +412,6 @@ static const struct cpumask *cpu_drawer_mask(int cpu)
 	return &per_cpu(cpu_topology, cpu).drawer_mask;
 }
 
-static int __init early_parse_topology(char *p)
-{
-	return kstrtobool(p, &topology_enabled);
-}
-early_param("topology", early_parse_topology);
-
 static struct sched_domain_topology_level s390_topology[] = {
 	{ cpu_thread_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
 	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
diff --git a/arch/sh/kernel/cpu/sh3/setup-sh770x.c b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
index 538c10d..8dc315b 100644
--- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
@@ -165,7 +165,6 @@ static struct plat_sci_port scif2_platform_data = {
 	.scscr		= SCSCR_TE | SCSCR_RE,
 	.type		= PORT_IRDA,
 	.ops		= &sh770x_sci_port_ops,
-	.regshift	= 1,
 };
 
 static struct resource scif2_resources[] = {
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S
index 96df6a3..a2ae689 100644
--- a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S
+++ b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S
@@ -157,8 +157,8 @@ LABEL skip_ %I
 .endr
 
 	# Find min length
-	vmovdqa _lens+0*16(state), %xmm0
-	vmovdqa _lens+1*16(state), %xmm1
+	vmovdqu _lens+0*16(state), %xmm0
+	vmovdqu _lens+1*16(state), %xmm1
 
 	vpminud %xmm1, %xmm0, %xmm2     # xmm2 has {D,C,B,A}
 	vpalignr $8, %xmm2, %xmm3, %xmm3   # xmm3 has {x,x,D,C}
@@ -178,8 +178,8 @@ LABEL skip_ %I
 	vpsubd  %xmm2, %xmm0, %xmm0
 	vpsubd  %xmm2, %xmm1, %xmm1
 
-	vmovdqa %xmm0, _lens+0*16(state)
-	vmovdqa %xmm1, _lens+1*16(state)
+	vmovdqu %xmm0, _lens+0*16(state)
+	vmovdqu %xmm1, _lens+1*16(state)
 
 	# "state" and "args" are the same address, arg1
 	# len is arg2
@@ -235,8 +235,8 @@ ENTRY(sha1_mb_mgr_get_comp_job_avx2)
 	jc      .return_null
 
 	# Find min length
-	vmovdqa _lens(state), %xmm0
-	vmovdqa _lens+1*16(state), %xmm1
+	vmovdqu _lens(state), %xmm0
+	vmovdqu _lens+1*16(state), %xmm1
 
 	vpminud %xmm1, %xmm0, %xmm2        # xmm2 has {D,C,B,A}
 	vpalignr $8, %xmm2, %xmm3, %xmm3   # xmm3 has {x,x,D,C}
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
index a78a069..ec9bee6 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
@@ -155,8 +155,8 @@ LABEL skip_ %I
 .endr
 
 	# Find min length
-	vmovdqa _lens+0*16(state), %xmm0
-	vmovdqa _lens+1*16(state), %xmm1
+	vmovdqu _lens+0*16(state), %xmm0
+	vmovdqu _lens+1*16(state), %xmm1
 
 	vpminud %xmm1, %xmm0, %xmm2		# xmm2 has {D,C,B,A}
 	vpalignr $8, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,D,C}
@@ -176,8 +176,8 @@ LABEL skip_ %I
 	vpsubd	%xmm2, %xmm0, %xmm0
 	vpsubd	%xmm2, %xmm1, %xmm1
 
-	vmovdqa	%xmm0, _lens+0*16(state)
-	vmovdqa	%xmm1, _lens+1*16(state)
+	vmovdqu	%xmm0, _lens+0*16(state)
+	vmovdqu	%xmm1, _lens+1*16(state)
 
 	# "state" and "args" are the same address, arg1
 	# len is arg2
@@ -234,8 +234,8 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2)
 	jc	.return_null
 
 	# Find min length
-	vmovdqa	_lens(state), %xmm0
-	vmovdqa	_lens+1*16(state), %xmm1
+	vmovdqu	_lens(state), %xmm0
+	vmovdqu	_lens+1*16(state), %xmm1
 
 	vpminud	%xmm1, %xmm0, %xmm2		# xmm2 has {D,C,B,A}
 	vpalignr $8, %xmm2, %xmm3, %xmm3	# xmm3 has {x,x,D,C}
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index a300aa1..dead0f3 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -68,6 +68,12 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
 	__chk_range_not_ok((unsigned long __force)(addr), size, limit); \
 })
 
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+# define WARN_ON_IN_IRQ()	WARN_ON_ONCE(!in_task())
+#else
+# define WARN_ON_IN_IRQ()
+#endif
+
 /**
  * access_ok: - Checks if a user space pointer is valid
  * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE.  Note that
@@ -88,8 +94,11 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
  * checks that the pointer is in the user space range - after calling
  * this function, memory access functions may still return -EFAULT.
  */
-#define access_ok(type, addr, size) \
-	likely(!__range_not_ok(addr, size, user_addr_max()))
+#define access_ok(type, addr, size)					\
+({									\
+	WARN_ON_IN_IRQ();						\
+	likely(!__range_not_ok(addr, size, user_addr_max()));		\
+})
 
 /*
  * These are the main single-value transfer routines.  They automatically
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 36171bc..9fe7b9e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -181,6 +181,12 @@ static void smp_callin(void)
 	smp_store_cpu_info(cpuid);
 
 	/*
+	 * The topology information must be up to date before
+	 * calibrate_delay() and notify_cpu_starting().
+	 */
+	set_cpu_sibling_map(raw_smp_processor_id());
+
+	/*
 	 * Get our bogomips.
 	 * Update loops_per_jiffy in cpu_data. Previous call to
 	 * smp_store_cpu_info() stored a value that is close but not as
@@ -190,11 +196,6 @@ static void smp_callin(void)
 	cpu_data(cpuid).loops_per_jiffy = loops_per_jiffy;
 	pr_debug("Stack at about %p\n", &cpuid);
 
-	/*
-	 * This must be done before setting cpu_online_mask
-	 * or calling notify_cpu_starting.
-	 */
-	set_cpu_sibling_map(raw_smp_processor_id());
 	wmb();
 
 	notify_cpu_starting(cpuid);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 6e57edf..44bf5cf 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1382,12 +1382,10 @@ void __init tsc_init(void)
 unsigned long calibrate_delay_is_known(void)
 {
 	int sibling, cpu = smp_processor_id();
-	struct cpumask *mask = topology_core_cpumask(cpu);
+	int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC);
+	const struct cpumask *mask = topology_core_cpumask(cpu);
 
-	if (!tsc_disabled && !cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC))
-		return 0;
-
-	if (!mask)
+	if (tsc_disabled || !constant_tsc || !mask)
 		return 0;
 
 	sibling = cpumask_any_but(mask, cpu);
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 350f709..7913b69 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -212,8 +212,8 @@ static void arch_perfmon_setup_counters(void)
 	eax.full = cpuid_eax(0xa);
 
 	/* Workaround for BIOS bugs in 6/15. Taken from perfmon2 */
-	if (eax.split.version_id == 0 && __this_cpu_read(cpu_info.x86) == 6 &&
-		__this_cpu_read(cpu_info.x86_model) == 15) {
+	if (eax.split.version_id == 0 && boot_cpu_data.x86 == 6 &&
+	    boot_cpu_data.x86_model == 15) {
 		eax.split.version_id = 2;
 		eax.split.num_counters = 2;
 		eax.split.bit_width = 40;