Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

A function in kernel/bpf/syscall.c which got a bug fix in 'net'
was moved to kernel/bpf/verifier.c in 'net-next'.

Signed-off-by: David S. Miller <davem@davemloft.net>

19 files changed, 241 insertions, 83 deletions

diff --git a/arch/arm/boot/dts/am335x-baltos.dtsi b/arch/arm/boot/dts/am335x-baltos.dtsi
index efb5eae290a8..d42b98f15e8b 100644
--- a/arch/arm/boot/dts/am335x-baltos.dtsi
+++ b/arch/arm/boot/dts/am335x-baltos.dtsi
@@ -371,6 +371,8 @@
 
 	phy1: ethernet-phy@1 {
 		reg = <7>;
+		eee-broken-100tx;
+		eee-broken-1000t;
 	};
 };
 
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 9e43c443738a..9ba4b18c0cb2 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -672,6 +672,7 @@
 	ti,non-removable;
 	bus-width = <4>;
 	cap-power-off-card;
+	keep-power-in-suspend;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc2_pins>;
 
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 2c9e56f4aac5..bbfb9d5a70a9 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -283,6 +283,7 @@
 				device_type = "pci";
 				ranges = <0x81000000 0 0          0x03000 0 0x00010000
 					  0x82000000 0 0x20013000 0x13000 0 0xffed000>;
+				bus-range = <0x00 0xff>;
 				#interrupt-cells = <1>;
 				num-lanes = <1>;
 				linux,pci-domain = <0>;
@@ -319,6 +320,7 @@
 				device_type = "pci";
 				ranges = <0x81000000 0 0          0x03000 0 0x00010000
 					  0x82000000 0 0x30013000 0x13000 0 0xffed000>;
+				bus-range = <0x00 0xff>;
 				#interrupt-cells = <1>;
 				num-lanes = <1>;
 				linux,pci-domain = <1>;
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 8f9a69ca818c..efe53998c961 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -121,7 +121,7 @@
 &i2c3 {
 	clock-frequency = <400000>;
 	at24@50 {
-		compatible = "at24,24c02";
+		compatible = "atmel,24c64";
 		readonly;
 		reg = <0x50>;
 	};
diff --git a/arch/arm/boot/dts/sun8i-a33.dtsi b/arch/arm/boot/dts/sun8i-a33.dtsi
index 0467fb365bfc..306af6cadf26 100644
--- a/arch/arm/boot/dts/sun8i-a33.dtsi
+++ b/arch/arm/boot/dts/sun8i-a33.dtsi
@@ -66,12 +66,6 @@
 			opp-microvolt = <1200000>;
 			clock-latency-ns = <244144>; /* 8 32k periods */
 		};
-
-		opp@1200000000 {
-			opp-hz = /bits/ 64 <1200000000>;
-			opp-microvolt = <1320000>;
-			clock-latency-ns = <244144>; /* 8 32k periods */
-		};
 	};
 
 	cpus {
@@ -81,16 +75,22 @@
 			operating-points-v2 = <&cpu0_opp_table>;
 		};
 
+		cpu@1 {
+			operating-points-v2 = <&cpu0_opp_table>;
+		};
+
 		cpu@2 {
 			compatible = "arm,cortex-a7";
 			device_type = "cpu";
 			reg = <2>;
+			operating-points-v2 = <&cpu0_opp_table>;
 		};
 
 		cpu@3 {
 			compatible = "arm,cortex-a7";
 			device_type = "cpu";
 			reg = <3>;
+			operating-points-v2 = <&cpu0_opp_table>;
 		};
 	};
 
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index c4f2ace91ea2..3089d3bfa19b 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -270,6 +270,7 @@ extern const struct smp_operations omap4_smp_ops;
 extern int omap4_mpuss_init(void);
 extern int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state);
 extern int omap4_hotplug_cpu(unsigned int cpu, unsigned int power_state);
+extern u32 omap4_get_cpu1_ns_pa_addr(void);
 #else
 static inline int omap4_enter_lowpower(unsigned int cpu,
 					unsigned int power_state)
diff --git a/arch/arm/mach-omap2/omap-hotplug.c b/arch/arm/mach-omap2/omap-hotplug.c
index d3fb5661bb5d..433db6d0b073 100644
--- a/arch/arm/mach-omap2/omap-hotplug.c
+++ b/arch/arm/mach-omap2/omap-hotplug.c
@@ -50,7 +50,7 @@ void omap4_cpu_die(unsigned int cpu)
 		omap4_hotplug_cpu(cpu, PWRDM_POWER_OFF);
 
 		if (omap_secure_apis_support())
-			boot_cpu = omap_read_auxcoreboot0();
+			boot_cpu = omap_read_auxcoreboot0() >> 9;
 		else
 			boot_cpu =
 				readl_relaxed(base + OMAP_AUX_CORE_BOOT_0) >> 5;
diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
index 113ab2dd2ee9..03ec6d307c82 100644
--- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c
+++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
@@ -64,6 +64,7 @@
 #include "prm-regbits-44xx.h"
 
 static void __iomem *sar_base;
+static u32 old_cpu1_ns_pa_addr;
 
 #if defined(CONFIG_PM) && defined(CONFIG_SMP)
 
@@ -212,6 +213,11 @@ static void __init save_l2x0_context(void)
 {}
 #endif
 
+u32 omap4_get_cpu1_ns_pa_addr(void)
+{
+	return old_cpu1_ns_pa_addr;
+}
+
 /**
  * omap4_enter_lowpower: OMAP4 MPUSS Low Power Entry Function
  * The purpose of this function is to manage low power programming
@@ -460,22 +466,30 @@ int __init omap4_mpuss_init(void)
 void __init omap4_mpuss_early_init(void)
 {
 	unsigned long startup_pa;
+	void __iomem *ns_pa_addr;
 
-	if (!(cpu_is_omap44xx() || soc_is_omap54xx()))
+	if (!(soc_is_omap44xx() || soc_is_omap54xx()))
 		return;
 
 	sar_base = omap4_get_sar_ram_base();
 
-	if (cpu_is_omap443x())
+	/* Save old NS_PA_ADDR for validity checks later on */
+	if (soc_is_omap44xx())
+		ns_pa_addr = sar_base + CPU1_WAKEUP_NS_PA_ADDR_OFFSET;
+	else
+		ns_pa_addr = sar_base + OMAP5_CPU1_WAKEUP_NS_PA_ADDR_OFFSET;
+	old_cpu1_ns_pa_addr = readl_relaxed(ns_pa_addr);
+
+	if (soc_is_omap443x())
 		startup_pa = __pa_symbol(omap4_secondary_startup);
-	else if (cpu_is_omap446x())
+	else if (soc_is_omap446x())
 		startup_pa = __pa_symbol(omap4460_secondary_startup);
 	else if ((__boot_cpu_mode & MODE_MASK) == HYP_MODE)
 		startup_pa = __pa_symbol(omap5_secondary_hyp_startup);
 	else
 		startup_pa = __pa_symbol(omap5_secondary_startup);
 
-	if (cpu_is_omap44xx())
+	if (soc_is_omap44xx())
 		writel_relaxed(startup_pa, sar_base +
 			       CPU1_WAKEUP_NS_PA_ADDR_OFFSET);
 	else
diff --git a/arch/arm/mach-omap2/omap-smc.S b/arch/arm/mach-omap2/omap-smc.S
index fd90125bffc7..72506e6cf9e7 100644
--- a/arch/arm/mach-omap2/omap-smc.S
+++ b/arch/arm/mach-omap2/omap-smc.S
@@ -94,6 +94,5 @@ ENTRY(omap_read_auxcoreboot0)
 	ldr	r12, =0x103
 	dsb
 	smc	#0
-	mov	r0, r0, lsr #9
 	ldmfd   sp!, {r2-r12, pc}
 ENDPROC(omap_read_auxcoreboot0)
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 003353b0b794..3faf454ba487 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -21,6 +21,7 @@
 #include <linux/io.h>
 #include <linux/irqchip/arm-gic.h>
 
+#include <asm/sections.h>
 #include <asm/smp_scu.h>
 #include <asm/virt.h>
 
@@ -40,10 +41,14 @@
 
 #define OMAP5_CORE_COUNT	0x2
 
+#define AUX_CORE_BOOT0_GP_RELEASE	0x020
+#define AUX_CORE_BOOT0_HS_RELEASE	0x200
+
 struct omap_smp_config {
 	unsigned long cpu1_rstctrl_pa;
 	void __iomem *cpu1_rstctrl_va;
 	void __iomem *scu_base;
+	void __iomem *wakeupgen_base;
 	void *startup_addr;
 };
 
@@ -140,7 +145,6 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	static struct clockdomain *cpu1_clkdm;
 	static bool booted;
 	static struct powerdomain *cpu1_pwrdm;
-	void __iomem *base = omap_get_wakeupgen_base();
 
 	/*
 	 * Set synchronisation state between this boot processor
@@ -155,9 +159,11 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * A barrier is added to ensure that write buffer is drained
 	 */
 	if (omap_secure_apis_support())
-		omap_modify_auxcoreboot0(0x200, 0xfffffdff);
+		omap_modify_auxcoreboot0(AUX_CORE_BOOT0_HS_RELEASE,
+					 0xfffffdff);
 	else
-		writel_relaxed(0x20, base + OMAP_AUX_CORE_BOOT_0);
+		writel_relaxed(AUX_CORE_BOOT0_GP_RELEASE,
+			       cfg.wakeupgen_base + OMAP_AUX_CORE_BOOT_0);
 
 	if (!cpu1_clkdm && !cpu1_pwrdm) {
 		cpu1_clkdm = clkdm_lookup("mpu1_clkdm");
@@ -261,9 +267,72 @@ static void __init omap4_smp_init_cpus(void)
 		set_cpu_possible(i, true);
 }
 
+/*
+ * For now, just make sure the start-up address is not within the booting
+ * kernel space as that means we just overwrote whatever secondary_startup()
+ * code there was.
+ */
+static bool __init omap4_smp_cpu1_startup_valid(unsigned long addr)
+{
+	if ((addr >= __pa(PAGE_OFFSET)) && (addr <= __pa(__bss_start)))
+		return false;
+
+	return true;
+}
+
+/*
+ * We may need to reset CPU1 before configuring, otherwise kexec boot can end
+ * up trying to use old kernel startup address or suspend-resume will
+ * occasionally fail to bring up CPU1 on 4430 if CPU1 fails to enter deeper
+ * idle states.
+ */
+static void __init omap4_smp_maybe_reset_cpu1(struct omap_smp_config *c)
+{
+	unsigned long cpu1_startup_pa, cpu1_ns_pa_addr;
+	bool needs_reset = false;
+	u32 released;
+
+	if (omap_secure_apis_support())
+		released = omap_read_auxcoreboot0() & AUX_CORE_BOOT0_HS_RELEASE;
+	else
+		released = readl_relaxed(cfg.wakeupgen_base +
+					 OMAP_AUX_CORE_BOOT_0) &
+						AUX_CORE_BOOT0_GP_RELEASE;
+	if (released) {
+		pr_warn("smp: CPU1 not parked?\n");
+
+		return;
+	}
+
+	cpu1_startup_pa = readl_relaxed(cfg.wakeupgen_base +
+					OMAP_AUX_CORE_BOOT_1);
+	cpu1_ns_pa_addr = omap4_get_cpu1_ns_pa_addr();
+
+	/* Did the configured secondary_startup() get overwritten? */
+	if (!omap4_smp_cpu1_startup_valid(cpu1_startup_pa))
+		needs_reset = true;
+
+	/*
+	 * If omap4 or 5 has NS_PA_ADDR configured, CPU1 may be in a
+	 * deeper idle state in WFI and will wake to an invalid address.
+	 */
+	if ((soc_is_omap44xx() || soc_is_omap54xx()) &&
+	    !omap4_smp_cpu1_startup_valid(cpu1_ns_pa_addr))
+		needs_reset = true;
+
+	if (!needs_reset || !c->cpu1_rstctrl_va)
+		return;
+
+	pr_info("smp: CPU1 parked within kernel, needs reset (0x%lx 0x%lx)\n",
+		cpu1_startup_pa, cpu1_ns_pa_addr);
+
+	writel_relaxed(1, c->cpu1_rstctrl_va);
+	readl_relaxed(c->cpu1_rstctrl_va);
+	writel_relaxed(0, c->cpu1_rstctrl_va);
+}
+
 static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
 {
-	void __iomem *base = omap_get_wakeupgen_base();
 	const struct omap_smp_config *c = NULL;
 
 	if (soc_is_omap443x())
@@ -281,6 +350,7 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
 	/* Must preserve cfg.scu_base set earlier */
 	cfg.cpu1_rstctrl_pa = c->cpu1_rstctrl_pa;
 	cfg.startup_addr = c->startup_addr;
+	cfg.wakeupgen_base = omap_get_wakeupgen_base();
 
 	if (soc_is_dra74x() || soc_is_omap54xx()) {
 		if ((__boot_cpu_mode & MODE_MASK) == HYP_MODE)
@@ -299,15 +369,7 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
 	if (cfg.scu_base)
 		scu_enable(cfg.scu_base);
 
-	/*
-	 * Reset CPU1 before configuring, otherwise kexec will
-	 * end up trying to use old kernel startup address.
-	 */
-	if (cfg.cpu1_rstctrl_va) {
-		writel_relaxed(1, cfg.cpu1_rstctrl_va);
-		readl_relaxed(cfg.cpu1_rstctrl_va);
-		writel_relaxed(0, cfg.cpu1_rstctrl_va);
-	}
+	omap4_smp_maybe_reset_cpu1(&cfg);
 
 	/*
 	 * Write the address of secondary startup routine into the
@@ -319,7 +381,7 @@ static void __init omap4_smp_prepare_cpus(unsigned int max_cpus)
 		omap_auxcoreboot_addr(__pa_symbol(cfg.startup_addr));
 	else
 		writel_relaxed(__pa_symbol(cfg.startup_addr),
-			       base + OMAP_AUX_CORE_BOOT_1);
+			       cfg.wakeupgen_base + OMAP_AUX_CORE_BOOT_1);
 }
 
 const struct smp_operations omap4_smp_ops __initconst = {
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index e920dd83e443..f989145480c8 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -222,6 +222,14 @@ static int _omap_device_notifier_call(struct notifier_block *nb,
 				dev_err(dev, "failed to idle\n");
 		}
 		break;
+	case BUS_NOTIFY_BIND_DRIVER:
+		od = to_omap_device(pdev);
+		if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED) &&
+		    pm_runtime_status_suspended(dev)) {
+			od->_driver_status = BUS_NOTIFY_BIND_DRIVER;
+			pm_runtime_set_active(dev);
+		}
+		break;
 	case BUS_NOTIFY_ADD_DEVICE:
 		if (pdev->dev.of_node)
 			omap_device_build_from_dt(pdev);
diff --git a/arch/arm/mach-orion5x/Kconfig b/arch/arm/mach-orion5x/Kconfig
index 633442ad4e4c..2a7bb6ccdcb7 100644
--- a/arch/arm/mach-orion5x/Kconfig
+++ b/arch/arm/mach-orion5x/Kconfig
@@ -6,6 +6,7 @@ menuconfig ARCH_ORION5X
 	select GPIOLIB
 	select MVEBU_MBUS
 	select PCI
+	select PHYLIB if NETDEVICES
 	select PLAT_ORION_LEGACY
 	help
 	  Support for the following Marvell Orion 5x series SoCs:
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index 9255b6d67ba5..aff6994950ba 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -468,6 +468,7 @@ void __init orion_ge11_init(struct mv643xx_eth_platform_data *eth_data,
 		    eth_data, &orion_ge11);
 }
 
+#ifdef CONFIG_ARCH_ORION5X
 /*****************************************************************************
  * Ethernet switch
  ****************************************************************************/
@@ -480,6 +481,9 @@ void __init orion_ge00_switch_init(struct dsa_chip_data *d)
 	struct mdio_board_info *bd;
 	unsigned int i;
 
+	if (!IS_BUILTIN(CONFIG_PHYLIB))
+		return;
+
 	for (i = 0; i < ARRAY_SIZE(d->port_names); i++)
 		if (!strcmp(d->port_names[i], "cpu"))
 			break;
@@ -493,6 +497,7 @@ void __init orion_ge00_switch_init(struct dsa_chip_data *d)
 
 	mdiobus_register_board_info(&orion_ge00_switch_board_info, 1);
 }
+#endif
 
 /*****************************************************************************
  * I2C
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
index 1c64ea2d23f9..0565779e66fa 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
@@ -179,8 +179,10 @@
 		usbphy: phy@01c19400 {
 			compatible = "allwinner,sun50i-a64-usb-phy";
 			reg = <0x01c19400 0x14>,
+			      <0x01c1a800 0x4>,
 			      <0x01c1b800 0x4>;
 			reg-names = "phy_ctrl",
+				    "pmu0",
 				    "pmu1";
 			clocks = <&ccu CLK_USB_PHY0>,
 				 <&ccu CLK_USB_PHY1>;
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 8442727f28d2..cbd4f4af8108 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -39,10 +39,10 @@
 #define get_user __get_user
 
 #if !defined(CONFIG_64BIT)
-#define LDD_USER(ptr)		__get_user_asm64(ptr)
+#define LDD_USER(val, ptr)	__get_user_asm64(val, ptr)
 #define STD_USER(x, ptr)	__put_user_asm64(x, ptr)
 #else
-#define LDD_USER(ptr)		__get_user_asm("ldd", ptr)
+#define LDD_USER(val, ptr)	__get_user_asm(val, "ldd", ptr)
 #define STD_USER(x, ptr)	__put_user_asm("std", x, ptr)
 #endif
 
@@ -97,63 +97,87 @@ struct exception_data {
 		" mtsp %0,%%sr2\n\t"		\
 		: : "r"(get_fs()) : )
 
-#define __get_user(x, ptr)                               \
-({                                                       \
-	register long __gu_err __asm__ ("r8") = 0;       \
-	register long __gu_val;				 \
-							 \
-	load_sr2();					 \
-	switch (sizeof(*(ptr))) {			 \
-	    case 1: __get_user_asm("ldb", ptr); break;   \
-	    case 2: __get_user_asm("ldh", ptr); break;   \
-	    case 4: __get_user_asm("ldw", ptr); break;   \
-	    case 8: LDD_USER(ptr);  break;		 \
-	    default: BUILD_BUG(); break;		 \
-	}                                                \
-							 \
-	(x) = (__force __typeof__(*(ptr))) __gu_val;	 \
-	__gu_err;                                        \
+#define __get_user_internal(val, ptr)			\
+({							\
+	register long __gu_err __asm__ ("r8") = 0;	\
+							\
+	switch (sizeof(*(ptr))) {			\
+	case 1: __get_user_asm(val, "ldb", ptr); break;	\
+	case 2: __get_user_asm(val, "ldh", ptr); break; \
+	case 4: __get_user_asm(val, "ldw", ptr); break; \
+	case 8: LDD_USER(val, ptr); break;		\
+	default: BUILD_BUG();				\
+	}						\
+							\
+	__gu_err;					\
 })
 
-#define __get_user_asm(ldx, ptr)                        \
+#define __get_user(val, ptr)				\
+({							\
+	load_sr2();					\
+	__get_user_internal(val, ptr);			\
+})
+
+#define __get_user_asm(val, ldx, ptr)			\
+{							\
+	register long __gu_val;				\
+							\
 	__asm__("1: " ldx " 0(%%sr2,%2),%0\n"		\
 		"9:\n"					\
 		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
 		: "=r"(__gu_val), "=r"(__gu_err)        \
-		: "r"(ptr), "1"(__gu_err));
+		: "r"(ptr), "1"(__gu_err));		\
+							\
+	(val) = (__force __typeof__(*(ptr))) __gu_val;	\
+}
 
 #if !defined(CONFIG_64BIT)
 
-#define __get_user_asm64(ptr) 				\
+#define __get_user_asm64(val, ptr)			\
+{							\
+	union {						\
+		unsigned long long	l;		\
+		__typeof__(*(ptr))	t;		\
+	} __gu_tmp;					\
+							\
 	__asm__("   copy %%r0,%R0\n"			\
 		"1: ldw 0(%%sr2,%2),%0\n"		\
 		"2: ldw 4(%%sr2,%2),%R0\n"		\
 		"9:\n"					\
 		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
 		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)	\
-		: "=r"(__gu_val), "=r"(__gu_err)	\
-		: "r"(ptr), "1"(__gu_err));
+		: "=&r"(__gu_tmp.l), "=r"(__gu_err)	\
+		: "r"(ptr), "1"(__gu_err));		\
+							\
+	(val) = __gu_tmp.t;				\
+}
 
 #endif /* !defined(CONFIG_64BIT) */
 
 
-#define __put_user(x, ptr)                                      \
+#define __put_user_internal(x, ptr)				\
 ({								\
 	register long __pu_err __asm__ ("r8") = 0;      	\
         __typeof__(*(ptr)) __x = (__typeof__(*(ptr)))(x);	\
 								\
-	load_sr2();						\
 	switch (sizeof(*(ptr))) {				\
-	    case 1: __put_user_asm("stb", __x, ptr); break;     \
-	    case 2: __put_user_asm("sth", __x, ptr); break;     \
-	    case 4: __put_user_asm("stw", __x, ptr); break;     \
-	    case 8: STD_USER(__x, ptr); break;			\
-	    default: BUILD_BUG(); break;			\
-	}                                                       \
+	case 1: __put_user_asm("stb", __x, ptr); break;		\
+	case 2: __put_user_asm("sth", __x, ptr); break;		\
+	case 4: __put_user_asm("stw", __x, ptr); break;		\
+	case 8: STD_USER(__x, ptr); break;			\
+	default: BUILD_BUG();					\
+	}							\
 								\
 	__pu_err;						\
 })
 
+#define __put_user(x, ptr)					\
+({								\
+	load_sr2();						\
+	__put_user_internal(x, ptr);				\
+})
+
+
 /*
  * The "__put_user/kernel_asm()" macros tell gcc they read from memory
  * instead of writing. This is because they do not write to any memory
diff --git a/arch/parisc/lib/lusercopy.S b/arch/parisc/lib/lusercopy.S
index f01188c044ee..85c28bb80fb7 100644
--- a/arch/parisc/lib/lusercopy.S
+++ b/arch/parisc/lib/lusercopy.S
@@ -201,7 +201,7 @@ ENTRY_CFI(pa_memcpy)
 	add	dst,len,end
 
 	/* short copy with less than 16 bytes? */
-	cmpib,>>=,n 15,len,.Lbyte_loop
+	cmpib,COND(>>=),n 15,len,.Lbyte_loop
 
 	/* same alignment? */
 	xor	src,dst,t0
@@ -216,7 +216,7 @@ ENTRY_CFI(pa_memcpy)
 	/* loop until we are 64-bit aligned */
 .Lalign_loop64:
 	extru	dst,31,3,t1
-	cmpib,=,n	0,t1,.Lcopy_loop_16
+	cmpib,=,n	0,t1,.Lcopy_loop_16_start
 20:	ldb,ma	1(srcspc,src),t1
 21:	stb,ma	t1,1(dstspc,dst)
 	b	.Lalign_loop64
@@ -225,6 +225,7 @@ ENTRY_CFI(pa_memcpy)
 	ASM_EXCEPTIONTABLE_ENTRY(20b,.Lcopy_done)
 	ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
 
+.Lcopy_loop_16_start:
 	ldi	31,t0
 .Lcopy_loop_16:
 	cmpb,COND(>>=),n t0,len,.Lword_loop
@@ -267,7 +268,7 @@ ENTRY_CFI(pa_memcpy)
 	/* loop until we are 32-bit aligned */
 .Lalign_loop32:
 	extru	dst,31,2,t1
-	cmpib,=,n	0,t1,.Lcopy_loop_4
+	cmpib,=,n	0,t1,.Lcopy_loop_8
 20:	ldb,ma	1(srcspc,src),t1
 21:	stb,ma	t1,1(dstspc,dst)
 	b	.Lalign_loop32
@@ -277,7 +278,7 @@ ENTRY_CFI(pa_memcpy)
 	ASM_EXCEPTIONTABLE_ENTRY(21b,.Lcopy_done)
 
 
-.Lcopy_loop_4:
+.Lcopy_loop_8:
 	cmpib,COND(>>=),n 15,len,.Lbyte_loop
 
 10:	ldw	0(srcspc,src),t1
@@ -299,7 +300,7 @@ ENTRY_CFI(pa_memcpy)
 	ASM_EXCEPTIONTABLE_ENTRY(16b,.Lcopy_done)
 	ASM_EXCEPTIONTABLE_ENTRY(17b,.Lcopy_done)
 
-	b	.Lcopy_loop_4
+	b	.Lcopy_loop_8
 	ldo	-16(len),len
 
 .Lbyte_loop:
@@ -324,7 +325,7 @@ ENTRY_CFI(pa_memcpy)
 .Lunaligned_copy:
 	/* align until dst is 32bit-word-aligned */
 	extru	dst,31,2,t1
-	cmpib,COND(=),n	0,t1,.Lcopy_dstaligned
+	cmpib,=,n	0,t1,.Lcopy_dstaligned
 20:	ldb	0(srcspc,src),t1
 	ldo	1(src),src
 21:	stb,ma	t1,1(dstspc,dst)
@@ -362,7 +363,7 @@ ENTRY_CFI(pa_memcpy)
 	cmpiclr,<> 1,t0,%r0
 	b,n .Lcase1
 .Lcase0:
-	cmpb,= %r0,len,.Lcda_finish
+	cmpb,COND(=) %r0,len,.Lcda_finish
 	nop
 
 1:	ldw,ma 4(srcspc,src), a3
@@ -376,7 +377,7 @@ ENTRY_CFI(pa_memcpy)
 1:	ldw,ma 4(srcspc,src), a3
 	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
 	ldo -1(len),len
-	cmpb,=,n %r0,len,.Ldo0
+	cmpb,COND(=),n %r0,len,.Ldo0
 .Ldo4:
 1:	ldw,ma 4(srcspc,src), a0
 	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcda_rdfault)
@@ -402,7 +403,7 @@ ENTRY_CFI(pa_memcpy)
 1:	stw,ma t0, 4(dstspc,dst)
 	ASM_EXCEPTIONTABLE_ENTRY(1b,.Lcopy_done)
 	ldo -4(len),len
-	cmpb,<> %r0,len,.Ldo4
+	cmpb,COND(<>) %r0,len,.Ldo4
 	nop
 .Ldo0:
 	shrpw a2, a3, %sar, t0
@@ -436,14 +437,14 @@ ENTRY_CFI(pa_memcpy)
 	/* fault exception fixup handlers: */
 #ifdef CONFIG_64BIT
 .Lcopy16_fault:
-10:	b	.Lcopy_done
-	std,ma	t1,8(dstspc,dst)
+	b	.Lcopy_done
+10:	std,ma	t1,8(dstspc,dst)
 	ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
 #endif
 
 .Lcopy8_fault:
-10:	b	.Lcopy_done
-	stw,ma	t1,4(dstspc,dst)
+	b	.Lcopy_done
+10:	stw,ma	t1,4(dstspc,dst)
 	ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
 
 	.exit
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 68ac5c7cd982..a59deaef21e5 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -43,7 +43,7 @@ config SPARC
 	select ARCH_HAS_SG_CHAIN
 	select CPU_NO_EFFICIENT_FFS
 	select HAVE_ARCH_HARDENED_USERCOPY
-	select PROVE_LOCKING_SMALL if PROVE_LOCKING
+	select LOCKDEP_SMALL if LOCKDEP
 	select ARCH_WANT_RELAX_ORDER
 
 config SPARC32
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index ee5273ad918d..7c29d38e6b99 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -461,6 +461,22 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 	pgd_t *pgd;
 	unsigned long next;
 
+	addr &= PMD_MASK;
+	if (addr < floor) {
+		addr += PMD_SIZE;
+		if (!addr)
+			return;
+	}
+	if (ceiling) {
+		ceiling &= PMD_MASK;
+		if (!ceiling)
+			return;
+	}
+	if (end - 1 > ceiling - 1)
+		end -= PMD_SIZE;
+	if (addr > end - 1)
+		return;
+
 	pgd = pgd_offset(tlb->mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index 2c1ebeb4d737..529bb4a6487a 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -55,7 +55,8 @@ static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n)
  * @size:	number of bytes to write back
  *
  * Write back a cache range using the CLWB (cache line write back)
- * instruction.
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
  */
 static inline void arch_wb_cache_pmem(void *addr, size_t size)
 {
@@ -69,15 +70,6 @@ static inline void arch_wb_cache_pmem(void *addr, size_t size)
 		clwb(p);
 }
 
-/*
- * copy_from_iter_nocache() on x86 only uses non-temporal stores for iovec
- * iterators, so for other types (bvec & kvec) we must do a cache write-back.
- */
-static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
-{
-	return iter_is_iovec(i) == false;
-}
-
 /**
  * arch_copy_from_iter_pmem - copy data from an iterator to PMEM
  * @addr:	PMEM destination address
@@ -94,7 +86,35 @@ static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
 	/* TODO: skip the write-back by always using non-temporal stores */
 	len = copy_from_iter_nocache(addr, bytes, i);
 
-	if (__iter_needs_pmem_wb(i))
+	/*
+	 * In the iovec case on x86_64 copy_from_iter_nocache() uses
+	 * non-temporal stores for the bulk of the transfer, but we need
+	 * to manually flush if the transfer is unaligned. A cached
+	 * memory copy is used when destination or size is not naturally
+	 * aligned. That is:
+	 *   - Require 8-byte alignment when size is 8 bytes or larger.
+	 *   - Require 4-byte alignment when size is 4 bytes.
+	 *
+	 * In the non-iovec case the entire destination needs to be
+	 * flushed.
+	 */
+	if (iter_is_iovec(i)) {
+		unsigned long flushed, dest = (unsigned long) addr;
+
+		if (bytes < 8) {
+			if (!IS_ALIGNED(dest, 4) || (bytes != 4))
+				arch_wb_cache_pmem(addr, 1);
+		} else {
+			if (!IS_ALIGNED(dest, 8)) {
+				dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+				arch_wb_cache_pmem(addr, 1);
+			}
+
+			flushed = dest - (unsigned long) addr;
+			if (bytes > flushed && !IS_ALIGNED(bytes - flushed, 8))
+				arch_wb_cache_pmem(addr + bytes - 1, 1);
+		}
+	} else
 		arch_wb_cache_pmem(addr, bytes);
 
 	return len;