Merge tag 'v3.14.20' into linux-linaro-lsk-v3.14

This is the 3.14.20 stable release

42 files changed, 513 insertions, 112 deletions

diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts
index 904dcf5973f3..9381754b35cc 100644
--- a/arch/arm/boot/dts/dra7-evm.dts
+++ b/arch/arm/boot/dts/dra7-evm.dts
@@ -50,13 +50,13 @@
 
 	mcspi1_pins: pinmux_mcspi1_pins {
 		pinctrl-single,pins = <
-			0x3a4 (PIN_INPUT | MUX_MODE0) /* spi2_clk */
-			0x3a8 (PIN_INPUT | MUX_MODE0) /* spi2_d1 */
-			0x3ac (PIN_INPUT | MUX_MODE0) /* spi2_d0 */
-			0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs0 */
-			0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi2_cs1 */
-			0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs2 */
-			0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi2_cs3 */
+			0x3a4 (PIN_INPUT | MUX_MODE0) /* spi1_sclk */
+			0x3a8 (PIN_INPUT | MUX_MODE0) /* spi1_d1 */
+			0x3ac (PIN_INPUT | MUX_MODE0) /* spi1_d0 */
+			0x3b0 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs0 */
+			0x3b4 (PIN_INPUT_SLEW | MUX_MODE0) /* spi1_cs1 */
+			0x3b8 (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs2.hdmi1_hpd */
+			0x3bc (PIN_INPUT_SLEW | MUX_MODE6) /* spi1_cs3.hdmi1_cec */
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 1fd75aa4639d..767f0e376f4d 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -178,7 +178,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio2: gpio@48055000 {
@@ -189,7 +189,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio3: gpio@48057000 {
@@ -200,7 +200,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio4: gpio@48059000 {
@@ -211,7 +211,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio5: gpio@4805b000 {
@@ -222,7 +222,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio6: gpio@4805d000 {
@@ -233,7 +233,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio7: gpio@48051000 {
@@ -244,7 +244,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		gpio8: gpio@48053000 {
@@ -255,7 +255,7 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			interrupt-controller;
-			#interrupt-cells = <1>;
+			#interrupt-cells = <2>;
 		};
 
 		uart1: serial@4806a000 {
diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h
index 83259b873333..5f833f7adba1 100644
--- a/arch/arm/include/asm/tls.h
+++ b/arch/arm/include/asm/tls.h
@@ -1,6 +1,9 @@
 #ifndef __ASMARM_TLS_H
 #define __ASMARM_TLS_H
 
+#include <linux/compiler.h>
+#include <asm/thread_info.h>
+
 #ifdef __ASSEMBLY__
 #include <asm/asm-offsets.h>
 	.macro switch_tls_none, base, tp, tpuser, tmp1, tmp2
@@ -50,6 +53,49 @@
 #endif
 
 #ifndef __ASSEMBLY__
+
+static inline void set_tls(unsigned long val)
+{
+	struct thread_info *thread;
+
+	thread = current_thread_info();
+
+	thread->tp_value[0] = val;
+
+	/*
+	 * This code runs with preemption enabled and therefore must
+	 * be reentrant with respect to switch_tls.
+	 *
+	 * We need to ensure ordering between the shadow state and the
+	 * hardware state, so that we don't corrupt the hardware state
+	 * with a stale shadow state during context switch.
+	 *
+	 * If we're preempted here, switch_tls will load TPIDRURO from
+	 * thread_info upon resuming execution and the following mcr
+	 * is merely redundant.
+	 */
+	barrier();
+
+	if (!tls_emu) {
+		if (has_tls_reg) {
+			asm("mcr p15, 0, %0, c13, c0, 3"
+			    : : "r" (val));
+		} else {
+#ifdef CONFIG_KUSER_HELPERS
+			/*
+			 * User space must never try to access this
+			 * directly.  Expect your app to break
+			 * eventually if you do so.  The user helper
+			 * at 0xffff0fe0 must be used instead.  (see
+			 * entry-armv.S for details)
+			 */
+			*((unsigned int *)0xffff0ff0) = val;
+#endif
+		}
+
+	}
+}
+
 static inline unsigned long get_tpuser(void)
 {
 	unsigned long reg = 0;
@@ -59,5 +105,23 @@ static inline unsigned long get_tpuser(void)
 
 	return reg;
 }
+
+static inline void set_tpuser(unsigned long val)
+{
+	/* Since TPIDRURW is fully context-switched (unlike TPIDRURO),
+	 * we need not update thread_info.
+	 */
+	if (has_tls_reg && !tls_emu) {
+		asm("mcr p15, 0, %0, c13, c0, 2"
+		    : : "r" (val));
+	}
+}
+
+static inline void flush_tls(void)
+{
+	set_tls(0);
+	set_tpuser(0);
+}
+
 #endif
 #endif	/* __ASMARM_TLS_H */
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 9723d17b8f38..1e782bdeee49 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -163,7 +163,7 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	c = irq_data_get_irq_chip(d);
 	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
-	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
 		cpumask_copy(d->affinity, affinity);
 
 	return ret;
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 92f7b15dd221..5f6e650ec9ab 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -334,6 +334,8 @@ void flush_thread(void)
 	memset(&tsk->thread.debug, 0, sizeof(struct debug_info));
 	memset(&thread->fpstate, 0, sizeof(union fp_state));
 
+	flush_tls();
+
 	thread_notify(THREAD_NOTIFY_FLUSH, thread);
 }
 
diff --git a/arch/arm/kernel/thumbee.c b/arch/arm/kernel/thumbee.c
index 7b8403b76666..80f0d69205e7 100644
--- a/arch/arm/kernel/thumbee.c
+++ b/arch/arm/kernel/thumbee.c
@@ -45,7 +45,7 @@ static int thumbee_notifier(struct notifier_block *self, unsigned long cmd, void
 
 	switch (cmd) {
 	case THREAD_NOTIFY_FLUSH:
-		thread->thumbee_state = 0;
+		teehbr_write(0);
 		break;
 	case THREAD_NOTIFY_SWITCH:
 		current_thread_info()->thumbee_state = teehbr_read();
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 172ee18ff124..9265b8bb529a 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -578,7 +578,6 @@ do_cache_op(unsigned long start, unsigned long end, int flags)
 #define NR(x) ((__ARM_NR_##x) - __ARM_NR_BASE)
 asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 {
-	struct thread_info *thread = current_thread_info();
 	siginfo_t info;
 
 	if ((no >> 16) != (__ARM_NR_BASE>> 16))
@@ -629,21 +628,7 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 		return regs->ARM_r0;
 
 	case NR(set_tls):
-		thread->tp_value[0] = regs->ARM_r0;
-		if (tls_emu)
-			return 0;
-		if (has_tls_reg) {
-			asm ("mcr p15, 0, %0, c13, c0, 3"
-				: : "r" (regs->ARM_r0));
-		} else {
-			/*
-			 * User space must never try to access this directly.
-			 * Expect your app to break eventually if you do so.
-			 * The user helper at 0xffff0fe0 must be used instead.
-			 * (see entry-armv.S for details)
-			 */
-			*((unsigned int *)0xffff0ff0) = regs->ARM_r0;
-		}
+		set_tls(regs->ARM_r0);
 		return 0;
 
 #ifdef CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 0de91fc6de0f..ec4fa868a7ba 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -89,6 +89,8 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	else
 		kvm_vcpu_block(vcpu);
 
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+
 	return 1;
 }
 
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 1b9844d369cc..ee4f7447a1d3 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -98,6 +98,10 @@ __do_hyp_init:
 	mrc	p15, 0, r0, c10, c2, 1
 	mcr	p15, 4, r0, c10, c2, 1
 
+	@ Invalidate the stale TLBs from Bootloader
+	mcr	p15, 4, r0, c8, c7, 0	@ TLBIALLH
+	dsb	ish
+
 	@ Set the HSCTLR to:
 	@  - ARM/THUMB exceptions: Kernel config (Thumb-2 kernel)
 	@  - Endianness: Kernel config
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index c914b0052fb9..4551efd28f8d 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -3349,6 +3349,9 @@ int __init omap_hwmod_register_links(struct omap_hwmod_ocp_if **ois)
 	if (!ois)
 		return 0;
 
+	if (ois[0] == NULL) /* Empty list */
+		return 0;
+
 	if (!linkspace) {
 		if (_alloc_linkspace(ois)) {
 			pr_err("omap_hwmod: could not allocate link space\n");
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 810c205d668b..2e35ff99f60e 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -35,6 +35,7 @@
 #include "i2c.h"
 #include "mmc.h"
 #include "wd_timer.h"
+#include "soc.h"
 
 /* Base offset for all DRA7XX interrupts external to MPUSS */
 #define DRA7XX_IRQ_GIC_START	32
@@ -2707,7 +2708,6 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = {
 	&dra7xx_l4_per3__usb_otg_ss1,
 	&dra7xx_l4_per3__usb_otg_ss2,
 	&dra7xx_l4_per3__usb_otg_ss3,
-	&dra7xx_l4_per3__usb_otg_ss4,
 	&dra7xx_l3_main_1__vcp1,
 	&dra7xx_l4_per2__vcp1,
 	&dra7xx_l3_main_1__vcp2,
@@ -2716,8 +2716,26 @@ static struct omap_hwmod_ocp_if *dra7xx_hwmod_ocp_ifs[] __initdata = {
 	NULL,
 };
 
+static struct omap_hwmod_ocp_if *dra74x_hwmod_ocp_ifs[] __initdata = {
+	&dra7xx_l4_per3__usb_otg_ss4,
+	NULL,
+};
+
+static struct omap_hwmod_ocp_if *dra72x_hwmod_ocp_ifs[] __initdata = {
+	NULL,
+};
+
 int __init dra7xx_hwmod_init(void)
 {
+	int ret;
+
 	omap_hwmod_init();
-	return omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs);
+	ret = omap_hwmod_register_links(dra7xx_hwmod_ocp_ifs);
+
+	if (!ret && soc_is_dra74x())
+		return omap_hwmod_register_links(dra74x_hwmod_ocp_ifs);
+	else if (!ret && soc_is_dra72x())
+		return omap_hwmod_register_links(dra72x_hwmod_ocp_ifs);
+
+	return ret;
 }
diff --git a/arch/arm/mach-omap2/soc.h b/arch/arm/mach-omap2/soc.h
index 076bd90a6ce0..8a9be09d9f38 100644
--- a/arch/arm/mach-omap2/soc.h
+++ b/arch/arm/mach-omap2/soc.h
@@ -245,6 +245,8 @@ IS_AM_SUBCLASS(437x, 0x437)
 #define soc_is_omap54xx()		0
 #define soc_is_omap543x()		0
 #define soc_is_dra7xx()			0
+#define soc_is_dra74x()			0
+#define soc_is_dra72x()			0
 
 #if defined(MULTI_OMAP2)
 # if defined(CONFIG_ARCH_OMAP2)
@@ -393,7 +395,11 @@ IS_OMAP_TYPE(3430, 0x3430)
 
 #if defined(CONFIG_SOC_DRA7XX)
 #undef soc_is_dra7xx
+#undef soc_is_dra74x
+#undef soc_is_dra72x
 #define soc_is_dra7xx()	(of_machine_is_compatible("ti,dra7"))
+#define soc_is_dra74x()	(of_machine_is_compatible("ti,dra74"))
+#define soc_is_dra72x()	(of_machine_is_compatible("ti,dra72"))
 #endif
 
 /* Various silicon revisions for omap2 */
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 3815a8262af0..8c48c5c22a33 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -17,12 +17,6 @@
  */
 	.align	5
 ENTRY(v6_early_abort)
-#ifdef CONFIG_CPU_V6
-	sub	r1, sp, #4			@ Get unused stack location
-	strex	r0, r1, [r1]			@ Clear the exclusive monitor
-#elif defined(CONFIG_CPU_32v6K)
-	clrex
-#endif
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 /*
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index 703375277ba6..4812ad054214 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -13,12 +13,6 @@
  */
 	.align	5
 ENTRY(v7_early_abort)
-	/*
-	 * The effect of data aborts on on the exclusive access monitor are
-	 * UNPREDICTABLE. Do a CLREX to clear the state
-	 */
-	clrex
-
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 924036473b16..d301662b7b32 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -40,6 +40,7 @@
  * This code is not portable to processors with late data abort handling.
  */
 #define CODING_BITS(i)	(i & 0x0e000000)
+#define COND_BITS(i)	(i & 0xf0000000)
 
 #define LDST_I_BIT(i)	(i & (1 << 26))		/* Immediate constant	*/
 #define LDST_P_BIT(i)	(i & (1 << 24))		/* Preindex		*/
@@ -817,6 +818,8 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		break;
 
 	case 0x04000000:	/* ldr or str immediate */
+		if (COND_BITS(instr) == 0xf0000000) /* NEON VLDn, VSTn */
+			goto bad;
 		offset.un = OFFSET_BITS(instr);
 		handler = do_alignment_ldrstr;
 		break;
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index d064047612b1..52b484b6aa1a 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -79,7 +79,6 @@ static inline void decode_ctrl_reg(u32 reg,
  */
 #define ARM_MAX_BRP		16
 #define ARM_MAX_WRP		16
-#define ARM_MAX_HBP_SLOTS	(ARM_MAX_BRP + ARM_MAX_WRP)
 
 /* Virtual debug register bases. */
 #define AARCH64_DBG_REG_BVR	0
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 0f08dfd69ebc..dfa6e3e74fdd 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -97,19 +97,15 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
 		return false;
 
-	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids)
+	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
+		affinity = cpu_online_mask;
 		ret = true;
+	}
 
-	/*
-	 * when using forced irq_set_affinity we must ensure that the cpu
-	 * being offlined is not present in the affinity mask, it may be
-	 * selected as the target CPU otherwise
-	 */
-	affinity = cpu_online_mask;
 	c = irq_data_get_irq_chip(d);
 	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
-	else if (c->irq_set_affinity(d, affinity, true) == IRQ_SET_MASK_OK && ret)
+	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
 		cpumask_copy(d->affinity, affinity);
 
 	return ret;
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 0e9ce28145d9..b1cd364d1364 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -188,9 +188,27 @@ void exit_thread(void)
 {
 }
 
+static void tls_thread_flush(void)
+{
+	asm ("msr tpidr_el0, xzr");
+
+	if (is_compat_task()) {
+		current->thread.tp_value = 0;
+
+		/*
+		 * We need to ensure ordering between the shadow state and the
+		 * hardware state, so that we don't corrupt the hardware state
+		 * with a stale shadow state during context switch.
+		 */
+		barrier();
+		asm ("msr tpidrro_el0, xzr");
+	}
+}
+
 void flush_thread(void)
 {
 	fpsimd_flush_thread();
+	tls_thread_flush();
 	flush_ptrace_hw_breakpoint(current);
 }
 
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 7c8e809bdbde..8ba6b0fa1753 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -85,7 +85,8 @@ static void ptrace_hbptriggered(struct perf_event *bp,
 			break;
 		}
 	}
-	for (i = ARM_MAX_BRP; i < ARM_MAX_HBP_SLOTS && !bp; ++i) {
+
+	for (i = 0; i < ARM_MAX_WRP; ++i) {
 		if (current->thread.debug.hbp_watch[i] == bp) {
 			info.si_errno = -((i << 1) + 1);
 			break;
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 26e9c4eeaba8..78039927c807 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -79,6 +79,12 @@ long compat_arm_syscall(struct pt_regs *regs)
 
 	case __ARM_NR_compat_set_tls:
 		current->thread.tp_value = regs->regs[0];
+
+		/*
+		 * Protect against register corruption from context switch.
+		 * See comment in tls_thread_flush.
+		 */
+		barrier();
 		asm ("msr tpidrro_el0, %0" : : "r" (regs->regs[0]));
 		return 0;
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 7bc41eab4c64..fd9aeba99683 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -62,6 +62,8 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	else
 		kvm_vcpu_block(vcpu);
 
+	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+
 	return 1;
 }
 
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 2b0244d65c16..12e26f358c31 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -74,6 +74,10 @@ __do_hyp_init:
 	msr	mair_el2, x4
 	isb
 
+	/* Invalidate the stale TLBs from Bootloader */
+	tlbi	alle2
+	dsb	sy
+
 	mrs	x4, sctlr_el2
 	and	x4, x4, #SCTLR_EL2_EE	// preserve endianness of EL2
 	ldr	x5, =SCTLR_EL2_FLAGS
diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c
index c00c4ddf4514..5244cecf1e45 100644
--- a/arch/mips/boot/compressed/decompress.c
+++ b/arch/mips/boot/compressed/decompress.c
@@ -13,6 +13,7 @@
 
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/string.h>
 
 #include <asm/addrspace.h>
 
diff --git a/arch/mips/kernel/mcount.S b/arch/mips/kernel/mcount.S
index 539b6294b613..8f89ff4ed524 100644
--- a/arch/mips/kernel/mcount.S
+++ b/arch/mips/kernel/mcount.S
@@ -123,7 +123,11 @@ NESTED(_mcount, PT_SIZE, ra)
 	 nop
 #endif
 	b	ftrace_stub
+#ifdef CONFIG_32BIT
+	 addiu sp, sp, 8
+#else
 	 nop
+#endif
 
 static_trace:
 	MCOUNT_SAVE_REGS
@@ -133,6 +137,9 @@ static_trace:
 	 move	a1, AT		/* arg2: parent's return address */
 
 	MCOUNT_RESTORE_REGS
+#ifdef CONFIG_32BIT
+	addiu sp, sp, 8
+#endif
 	.globl ftrace_stub
 ftrace_stub:
 	RETURN_BACK
@@ -177,6 +184,11 @@ NESTED(ftrace_graph_caller, PT_SIZE, ra)
 	jal	prepare_ftrace_return
 	 nop
 	MCOUNT_RESTORE_REGS
+#ifndef CONFIG_DYNAMIC_FTRACE
+#ifdef CONFIG_32BIT
+	addiu sp, sp, 8
+#endif
+#endif
 	RETURN_BACK
 	END(ftrace_graph_caller)
 
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 7187664034c3..5db8882f732c 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -48,7 +48,12 @@ cflags-y	:= -pipe
 
 # These flags should be implied by an hppa-linux configuration, but they
 # are not in gcc 3.2.
-cflags-y	+= -mno-space-regs -mfast-indirect-calls
+cflags-y	+= -mno-space-regs
+
+# -mfast-indirect-calls is only relevant for 32-bit kernels.
+ifndef CONFIG_64BIT
+cflags-y	+= -mfast-indirect-calls
+endif
 
 # Currently we save and restore fpregs on all kernel entry/interruption paths.
 # If that gets optimized, we might need to disable the use of fpregs in the
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 838786011037..7ef22e3387e0 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -74,7 +74,7 @@ ENTRY(linux_gateway_page)
 	/* ADDRESS 0xb0 to 0xb8, lws uses two insns for entry */
 	/* Light-weight-syscall entry must always be located at 0xb0 */
 	/* WARNING: Keep this number updated with table size changes */
-#define __NR_lws_entries (2)
+#define __NR_lws_entries (3)
 
 lws_entry:
 	gate	lws_start, %r0		/* increase privilege */
@@ -502,7 +502,7 @@ lws_exit:
 
 	
 	/***************************************************
-		Implementing CAS as an atomic operation:
+		Implementing 32bit CAS as an atomic operation:
 
 		%r26 - Address to examine
 		%r25 - Old value to check (old)
@@ -659,6 +659,230 @@ cas_action:
 	ASM_EXCEPTIONTABLE_ENTRY(2b-linux_gateway_page, 3b-linux_gateway_page)
 
 
+	/***************************************************
+		New CAS implementation which uses pointers and variable size
+		information. The value pointed by old and new MUST NOT change
+		while performing CAS. The lock only protect the value at %r26.
+
+		%r26 - Address to examine
+		%r25 - Pointer to the value to check (old)
+		%r24 - Pointer to the value to set (new)
+		%r23 - Size of the variable (0/1/2/3 for 8/16/32/64 bit)
+		%r28 - Return non-zero on failure
+		%r21 - Kernel error code
+
+		%r21 has the following meanings:
+
+		EAGAIN - CAS is busy, ldcw failed, try again.
+		EFAULT - Read or write failed.
+
+		Scratch: r20, r22, r28, r29, r1, fr4 (32bit for 64bit CAS only)
+
+	****************************************************/
+
+	/* ELF32 Process entry path */
+lws_compare_and_swap_2:
+#ifdef CONFIG_64BIT
+	/* Clip the input registers */
+	depdi	0, 31, 32, %r26
+	depdi	0, 31, 32, %r25
+	depdi	0, 31, 32, %r24
+	depdi	0, 31, 32, %r23
+#endif
+
+	/* Check the validity of the size pointer */
+	subi,>>= 4, %r23, %r0
+	b,n	lws_exit_nosys
+
+	/* Jump to the functions which will load the old and new values into
+	   registers depending on the their size */
+	shlw	%r23, 2, %r29
+	blr	%r29, %r0
+	nop
+
+	/* 8bit load */
+4:	ldb	0(%sr3,%r25), %r25
+	b	cas2_lock_start
+5:	ldb	0(%sr3,%r24), %r24
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* 16bit load */
+6:	ldh	0(%sr3,%r25), %r25
+	b	cas2_lock_start
+7:	ldh	0(%sr3,%r24), %r24
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* 32bit load */
+8:	ldw	0(%sr3,%r25), %r25
+	b	cas2_lock_start
+9:	ldw	0(%sr3,%r24), %r24
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* 64bit load */
+#ifdef CONFIG_64BIT
+10:	ldd	0(%sr3,%r25), %r25
+11:	ldd	0(%sr3,%r24), %r24
+#else
+	/* Load new value into r22/r23 - high/low */
+10:	ldw	0(%sr3,%r25), %r22
+11:	ldw	4(%sr3,%r25), %r23
+	/* Load new value into fr4 for atomic store later */
+12:	flddx	0(%sr3,%r24), %fr4
+#endif
+
+cas2_lock_start:
+	/* Load start of lock table */
+	ldil	L%lws_lock_start, %r20
+	ldo	R%lws_lock_start(%r20), %r28
+
+	/* Extract four bits from r26 and hash lock (Bits 4-7) */
+	extru  %r26, 27, 4, %r20
+
+	/* Find lock to use, the hash is either one of 0 to
+	   15, multiplied by 16 (keep it 16-byte aligned)
+	   and add to the lock table offset. */
+	shlw	%r20, 4, %r20
+	add	%r20, %r28, %r20
+
+	rsm	PSW_SM_I, %r0			/* Disable interrupts */
+	/* COW breaks can cause contention on UP systems */
+	LDCW	0(%sr2,%r20), %r28		/* Try to acquire the lock */
+	cmpb,<>,n	%r0, %r28, cas2_action	/* Did we get it? */
+cas2_wouldblock:
+	ldo	2(%r0), %r28			/* 2nd case */
+	ssm	PSW_SM_I, %r0
+	b	lws_exit			/* Contended... */
+	ldo	-EAGAIN(%r0), %r21		/* Spin in userspace */
+
+	/*
+		prev = *addr;
+		if ( prev == old )
+		  *addr = new;
+		return prev;
+	*/
+
+	/* NOTES:
+		This all works becuse intr_do_signal
+		and schedule both check the return iasq
+		and see that we are on the kernel page
+		so this process is never scheduled off
+		or is ever sent any signal of any sort,
+		thus it is wholly atomic from usrspaces
+		perspective
+	*/
+cas2_action:
+	/* Jump to the correct function */
+	blr	%r29, %r0
+	/* Set %r28 as non-zero for now */
+	ldo	1(%r0),%r28
+
+	/* 8bit CAS */
+13:	ldb,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+14:	stb,ma	%r24, 0(%sr3,%r26)
+	b	cas2_end
+	copy	%r0, %r28
+	nop
+	nop
+
+	/* 16bit CAS */
+15:	ldh,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+16:	sth,ma	%r24, 0(%sr3,%r26)
+	b	cas2_end
+	copy	%r0, %r28
+	nop
+	nop
+
+	/* 32bit CAS */
+17:	ldw,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+18:	stw,ma	%r24, 0(%sr3,%r26)
+	b	cas2_end
+	copy	%r0, %r28
+	nop
+	nop
+
+	/* 64bit CAS */
+#ifdef CONFIG_64BIT
+19:	ldd,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+20:	std,ma	%r24, 0(%sr3,%r26)
+	copy	%r0, %r28
+#else
+	/* Compare first word */
+19:	ldw,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r22, %r0
+	b,n	cas2_end
+	/* Compare second word */
+20:	ldw,ma	4(%sr3,%r26), %r29
+	sub,=	%r29, %r23, %r0
+	b,n	cas2_end
+	/* Perform the store */
+21:	fstdx	%fr4, 0(%sr3,%r26)
+	copy	%r0, %r28
+#endif
+
+cas2_end:
+	/* Free lock */
+	stw,ma	%r20, 0(%sr2,%r20)
+	/* Enable interrupts */
+	ssm	PSW_SM_I, %r0
+	/* Return to userspace, set no error */
+	b	lws_exit
+	copy	%r0, %r21
+
+22:
+	/* Error occurred on load or store */
+	/* Free lock */
+	stw	%r20, 0(%sr2,%r20)
+	ssm	PSW_SM_I, %r0
+	ldo	1(%r0),%r28
+	b	lws_exit
+	ldo	-EFAULT(%r0),%r21	/* set errno */
+	nop
+	nop
+	nop
+
+	/* Exception table entries, for the load and store, return EFAULT.
+	   Each of the entries must be relocated. */
+	ASM_EXCEPTIONTABLE_ENTRY(4b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(5b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(6b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(7b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(8b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(9b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(10b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(11b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(13b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(14b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(15b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(16b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(17b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(18b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(19b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(20b-linux_gateway_page, 22b-linux_gateway_page)
+#ifndef CONFIG_64BIT
+	ASM_EXCEPTIONTABLE_ENTRY(12b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(21b-linux_gateway_page, 22b-linux_gateway_page)
+#endif
+
 	/* Make sure nothing else is placed on this page */
 	.align PAGE_SIZE
 END(linux_gateway_page)
@@ -675,8 +899,9 @@ ENTRY(end_linux_gateway_page)
 	/* Light-weight-syscall table */
 	/* Start of lws table. */
 ENTRY(lws_table)
-	LWS_ENTRY(compare_and_swap32)	/* 0 - ELF32 Atomic compare and swap */
-	LWS_ENTRY(compare_and_swap64)	/* 1 - ELF64 Atomic compare and swap */
+	LWS_ENTRY(compare_and_swap32)		/* 0 - ELF32 Atomic 32bit CAS */
+	LWS_ENTRY(compare_and_swap64)		/* 1 - ELF64 Atomic 32bit CAS */
+	LWS_ENTRY(compare_and_swap_2)		/* 2 - ELF32 Atomic 64bit CAS */
 END(lws_table)
 	/* End of lws table */
 
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 279b80f3bb29..c0c61fa9cd9e 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -47,6 +47,12 @@
 				 STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE)
 #define STACK_FRAME_MARKER	12
 
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define STACK_FRAME_MIN_SIZE	32
+#else
+#define STACK_FRAME_MIN_SIZE	STACK_FRAME_OVERHEAD
+#endif
+
 /* Size of dummy stack frame allocated when calling signal handler. */
 #define __SIGNAL_FRAMESIZE	128
 #define __SIGNAL_FRAMESIZE32	64
@@ -60,6 +66,7 @@
 #define STACK_FRAME_REGS_MARKER	ASM_CONST(0x72656773)
 #define STACK_INT_FRAME_SIZE	(sizeof(struct pt_regs) + STACK_FRAME_OVERHEAD)
 #define STACK_FRAME_MARKER	2
+#define STACK_FRAME_MIN_SIZE	STACK_FRAME_OVERHEAD
 
 /* Size of stack frame allocated when calling signal handler. */
 #define __SIGNAL_FRAMESIZE	64
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 35aa339410bd..4dbe072eecbe 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -61,6 +61,7 @@ static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
+	smp_mb();
 	return !arch_spin_value_unlocked(*lock);
 }
 
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
index 0c9c8d7d0734..170a0346f756 100644
--- a/arch/powerpc/lib/locks.c
+++ b/arch/powerpc/lib/locks.c
@@ -70,12 +70,16 @@ void __rw_yield(arch_rwlock_t *rw)
 
 void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
+	smp_mb();
+
 	while (lock->slock) {
 		HMT_low();
 		if (SHARED_PROCESSOR)
 			__spin_yield(lock);
 	}
 	HMT_medium();
+
+	smp_mb();
 }
 
 EXPORT_SYMBOL(arch_spin_unlock_wait);
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 74d1e780748b..2396dda282cd 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -35,7 +35,7 @@ static int valid_next_sp(unsigned long sp, unsigned long prev_sp)
 		return 0;		/* must be 16-byte aligned */
 	if (!validate_sp(sp, current, STACK_FRAME_OVERHEAD))
 		return 0;
-	if (sp >= prev_sp + STACK_FRAME_OVERHEAD)
+	if (sp >= prev_sp + STACK_FRAME_MIN_SIZE)
 		return 1;
 	/*
 	 * sp could decrease when we jump off an interrupt stack
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 3584ed9b20a1..e309c5c41158 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -810,11 +810,21 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	pte_t *ptep;
 
 	down_read(&mm->mmap_sem);
+retry:
 	ptep = get_locked_pte(current->mm, addr, &ptl);
 	if (unlikely(!ptep)) {
 		up_read(&mm->mmap_sem);
 		return -EFAULT;
 	}
+	if (!(pte_val(*ptep) & _PAGE_INVALID) &&
+	     (pte_val(*ptep) & _PAGE_PROTECT)) {
+			pte_unmap_unlock(*ptep, ptl);
+			if (fixup_user_fault(current, mm, addr, FAULT_FLAG_WRITE)) {
+				up_read(&mm->mmap_sem);
+				return -EFAULT;
+			}
+			goto retry;
+		}
 
 	new = old = pgste_get_lock(ptep);
 	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 4dbf967da50d..6cfcf2a2eb93 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -183,12 +183,27 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 static bool mem_avoid_overlap(struct mem_vector *img)
 {
 	int i;
+	struct setup_data *ptr;
 
 	for (i = 0; i < MEM_AVOID_MAX; i++) {
 		if (mem_overlaps(img, &mem_avoid[i]))
 			return true;
 	}
 
+	/* Avoid all entries in the setup_data linked list. */
+	ptr = (struct setup_data *)(unsigned long)real_mode->hdr.setup_data;
+	while (ptr) {
+		struct mem_vector avoid;
+
+		avoid.start = (u64)ptr;
+		avoid.size = sizeof(*ptr) + ptr->len;
+
+		if (mem_overlaps(img, &avoid))
+			return true;
+
+		ptr = (struct setup_data *)(unsigned long)ptr->next;
+	}
+
 	return false;
 }
 
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 7252cd339175..6762a55b798a 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -123,14 +123,14 @@ enum fixed_addresses {
 	__end_of_permanent_fixed_addresses,
 
 	/*
-	 * 256 temporary boot-time mappings, used by early_ioremap(),
+	 * 512 temporary boot-time mappings, used by early_ioremap(),
 	 * before ioremap() is functional.
 	 *
-	 * If necessary we round it up to the next 256 pages boundary so
+	 * If necessary we round it up to the next 512 pages boundary so
 	 * that we can have a single pgd entry and a single pte table:
 	 */
 #define NR_FIX_BTMAPS		64
-#define FIX_BTMAPS_SLOTS	4
+#define FIX_BTMAPS_SLOTS	8
 #define TOTAL_FIX_BTMAPS	(NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS)
 	FIX_BTMAP_END =
 	 (__end_of_permanent_fixed_addresses ^
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index e22c1dbf7feb..d869931bde62 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -19,6 +19,7 @@ extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
 extern pmd_t level2_fixmap_pgt[512];
 extern pmd_t level2_ident_pgt[512];
+extern pte_t level1_fixmap_pgt[512];
 extern pgd_t init_level4_pgt[];
 
 #define swapper_pg_dir init_level4_pgt
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 5ad35ad94d0f..95700e52061d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -511,6 +511,7 @@ static int rapl_cpu_prepare(int cpu)
 	struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
 	int phys_id = topology_physical_package_id(cpu);
 	u64 ms;
+	u64 msr_rapl_power_unit_bits;
 
 	if (pmu)
 		return 0;
@@ -518,6 +519,9 @@ static int rapl_cpu_prepare(int cpu)
 	if (phys_id < 0)
 		return -1;
 
+	if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
+		return -1;
+
 	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
 	if (!pmu)
 		return -1;
@@ -531,8 +535,7 @@ static int rapl_cpu_prepare(int cpu)
 	 *
 	 * we cache in local PMU instance
 	 */
-	rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit);
-	pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL;
+	pmu->hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
 	pmu->pmu = &rapl_pmu_class;
 
 	/*
@@ -649,7 +652,9 @@ static int __init rapl_pmu_init(void)
 	get_online_cpus();
 
 	for_each_online_cpu(cpu) {
-		rapl_cpu_prepare(cpu);
+		ret = rapl_cpu_prepare(cpu);
+		if (ret)
+			goto out;
 		rapl_cpu_init(cpu);
 	}
 
@@ -672,6 +677,7 @@ static int __init rapl_pmu_init(void)
 		hweight32(rapl_cntr_mask),
 		ktime_to_ms(pmu->timer_interval));
 
+out:
 	put_online_cpus();
 
 	return 0;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 395be6d8bbde..682876533ed9 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1287,6 +1287,9 @@ static void remove_siblinginfo(int cpu)
 
 	for_each_cpu(sibling, cpu_sibling_mask(cpu))
 		cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
+	for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
+		cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
+	cpumask_clear(cpu_llc_shared_mask(cpu));
 	cpumask_clear(cpu_sibling_mask(cpu));
 	cpumask_clear(cpu_core_mask(cpu));
 	c->phys_proc_id = 0;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 2423ef04ffea..c83da6fb2dee 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1866,12 +1866,11 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
  *
  * We can construct this by grafting the Xen provided pagetable into
  * head_64.S's preconstructed pagetables.  We copy the Xen L2's into
- * level2_ident_pgt, level2_kernel_pgt and level2_fixmap_pgt.  This
- * means that only the kernel has a physical mapping to start with -
- * but that's enough to get __va working.  We need to fill in the rest
- * of the physical mapping once some sort of allocator has been set
- * up.
- * NOTE: for PVH, the page tables are native.
+ * level2_ident_pgt, and level2_kernel_pgt.  This means that only the
+ * kernel has a physical mapping to start with - but that's enough to
+ * get __va working.  We need to fill in the rest of the physical
+ * mapping once some sort of allocator has been set up.  NOTE: for
+ * PVH, the page tables are native.
  */
 void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 {
@@ -1902,8 +1901,11 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 		/* L3_i[0] -> level2_ident_pgt */
 		convert_pfn_mfn(level3_ident_pgt);
 		/* L3_k[510] -> level2_kernel_pgt
-		 * L3_i[511] -> level2_fixmap_pgt */
+		 * L3_k[511] -> level2_fixmap_pgt */
 		convert_pfn_mfn(level3_kernel_pgt);
+
+		/* L3_k[511][506] -> level1_fixmap_pgt */
+		convert_pfn_mfn(level2_fixmap_pgt);
 	}
 	/* We get [511][511] and have Xen's version of level2_kernel_pgt */
 	l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
@@ -1913,21 +1915,15 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	addr[1] = (unsigned long)l3;
 	addr[2] = (unsigned long)l2;
 	/* Graft it onto L4[272][0]. Note that we creating an aliasing problem:
-	 * Both L4[272][0] and L4[511][511] have entries that point to the same
+	 * Both L4[272][0] and L4[511][510] have entries that point to the same
 	 * L2 (PMD) tables. Meaning that if you modify it in __va space
 	 * it will be also modified in the __ka space! (But if you just
 	 * modify the PMD table to point to other PTE's or none, then you
 	 * are OK - which is what cleanup_highmap does) */
 	copy_page(level2_ident_pgt, l2);
-	/* Graft it onto L4[511][511] */
+	/* Graft it onto L4[511][510] */
 	copy_page(level2_kernel_pgt, l2);
 
-	/* Get [511][510] and graft that in level2_fixmap_pgt */
-	l3 = m2v(pgd[pgd_index(__START_KERNEL_map + PMD_SIZE)].pgd);
-	l2 = m2v(l3[pud_index(__START_KERNEL_map + PMD_SIZE)].pud);
-	copy_page(level2_fixmap_pgt, l2);
-	/* Note that we don't do anything with level1_fixmap_pgt which
-	 * we don't need. */
 	if (!xen_feature(XENFEAT_auto_translated_physmap)) {
 		/* Make pagetable pieces RO */
 		set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
@@ -1937,6 +1933,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 		set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
 		set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
 		set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
+		set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
 
 		/* Pin down new L4 */
 		pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index 216446295ada..51230ba97bef 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -67,7 +67,12 @@
 #define VMALLOC_START		0xC0000000
 #define VMALLOC_END		0xC7FEFFFF
 #define TLBTEMP_BASE_1		0xC7FF0000
-#define TLBTEMP_BASE_2		0xC7FF8000
+#define TLBTEMP_BASE_2		(TLBTEMP_BASE_1 + DCACHE_WAY_SIZE)
+#if 2 * DCACHE_WAY_SIZE > ICACHE_WAY_SIZE
+#define TLBTEMP_SIZE		(2 * DCACHE_WAY_SIZE)
+#else
+#define TLBTEMP_SIZE		ICACHE_WAY_SIZE
+#endif
 
 /*
  * For the Xtensa architecture, the PTE layout is as follows:
diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index fd686dc45d1a..c7211e7e182d 100644
--- a/arch/xtensa/include/asm/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
@@ -52,7 +52,12 @@
  */
 	.macro	get_fs	ad, sp
 	GET_CURRENT(\ad,\sp)
+#if THREAD_CURRENT_DS > 1020
+	addi	\ad, \ad, TASK_THREAD
+	l32i	\ad, \ad, THREAD_CURRENT_DS - TASK_THREAD
+#else
 	l32i	\ad, \ad, THREAD_CURRENT_DS
+#endif
 	.endm
 
 /*
diff --git a/arch/xtensa/include/uapi/asm/ioctls.h b/arch/xtensa/include/uapi/asm/ioctls.h
index b4cb1100c0fb..a47909f0c34b 100644
--- a/arch/xtensa/include/uapi/asm/ioctls.h
+++ b/arch/xtensa/include/uapi/asm/ioctls.h
@@ -28,17 +28,17 @@
 #define TCSETSW		0x5403
 #define TCSETSF		0x5404
 
-#define TCGETA		_IOR('t', 23, struct termio)
-#define TCSETA		_IOW('t', 24, struct termio)
-#define TCSETAW		_IOW('t', 25, struct termio)
-#define TCSETAF		_IOW('t', 28, struct termio)
+#define TCGETA		0x80127417	/* _IOR('t', 23, struct termio) */
+#define TCSETA		0x40127418	/* _IOW('t', 24, struct termio) */
+#define TCSETAW		0x40127419	/* _IOW('t', 25, struct termio) */
+#define TCSETAF		0x4012741C	/* _IOW('t', 28, struct termio) */
 
 #define TCSBRK		_IO('t', 29)
 #define TCXONC		_IO('t', 30)
 #define TCFLSH		_IO('t', 31)
 
-#define TIOCSWINSZ	_IOW('t', 103, struct winsize)
-#define TIOCGWINSZ	_IOR('t', 104, struct winsize)
+#define TIOCSWINSZ	0x40087467	/* _IOW('t', 103, struct winsize) */
+#define TIOCGWINSZ	0x80087468	/* _IOR('t', 104, struct winsize) */
 #define	TIOCSTART	_IO('t', 110)		/* start output, like ^Q */
 #define	TIOCSTOP	_IO('t', 111)		/* stop output, like ^S */
 #define TIOCOUTQ        _IOR('t', 115, int)     /* output queue size */
@@ -88,7 +88,6 @@
 #define TIOCSETD	_IOW('T', 35, int)
 #define TIOCGETD	_IOR('T', 36, int)
 #define TCSBRKP		_IOW('T', 37, int)   /* Needed for POSIX tcsendbreak()*/
-#define TIOCTTYGSTRUCT	_IOR('T', 38, struct tty_struct) /* For debugging only*/
 #define TIOCSBRK	_IO('T', 39) 	     /* BSD compatibility */
 #define TIOCCBRK	_IO('T', 40)	     /* BSD compatibility */
 #define TIOCGSID	_IOR('T', 41, pid_t) /* Return the session ID of FD*/
@@ -114,8 +113,10 @@
 #define TIOCSERGETLSR   _IOR('T', 89, unsigned int) /* Get line status reg. */
   /* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
 # define TIOCSER_TEMT    0x01		     /* Transmitter physically empty */
-#define TIOCSERGETMULTI _IOR('T', 90, struct serial_multiport_struct) /* Get multiport config  */
-#define TIOCSERSETMULTI _IOW('T', 91, struct serial_multiport_struct) /* Set multiport config */
+#define TIOCSERGETMULTI 0x80a8545a /* Get multiport config  */
+			/* _IOR('T', 90, struct serial_multiport_struct) */
+#define TIOCSERSETMULTI 0x40a8545b /* Set multiport config */
+			/* _IOW('T', 91, struct serial_multiport_struct) */
 
 #define TIOCMIWAIT	_IO('T', 92) /* wait for a change on serial input line(s) */
 #define TIOCGICOUNT	0x545D	/* read serial port inline interrupt counts */
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index ef7f4990722b..a06b7efaae82 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1001,9 +1001,8 @@ ENTRY(fast_syscall_xtensa)
 	movi	a7, 4			# sizeof(unsigned int)
 	access_ok a3, a7, a0, a2, .Leac	# a0: scratch reg, a2: sp
 
-	addi	a6, a6, -1		# assuming SYS_XTENSA_ATOMIC_SET = 1
-	_bgeui	a6, SYS_XTENSA_COUNT - 1, .Lill
-	_bnei	a6, SYS_XTENSA_ATOMIC_CMP_SWP - 1, .Lnswp
+	_bgeui	a6, SYS_XTENSA_COUNT, .Lill
+	_bnei	a6, SYS_XTENSA_ATOMIC_CMP_SWP, .Lnswp
 
 	/* Fall through for ATOMIC_CMP_SWP. */
 
@@ -1015,27 +1014,26 @@ TRY	s32i	a5, a3, 0		# different, modify value
 	l32i	a7, a2, PT_AREG7	# restore a7
 	l32i	a0, a2, PT_AREG0	# restore a0
 	movi	a2, 1			# and return 1
-	addi	a6, a6, 1		# restore a6 (really necessary?)
 	rfe
 
 1:	l32i	a7, a2, PT_AREG7	# restore a7
 	l32i	a0, a2, PT_AREG0	# restore a0
 	movi	a2, 0			# return 0 (note that we cannot set
-	addi	a6, a6, 1		# restore a6 (really necessary?)
 	rfe
 
 .Lnswp:	/* Atomic set, add, and exg_add. */
 
 TRY	l32i	a7, a3, 0		# orig
+	addi	a6, a6, -SYS_XTENSA_ATOMIC_SET
 	add	a0, a4, a7		# + arg
 	moveqz	a0, a4, a6		# set
+	addi	a6, a6, SYS_XTENSA_ATOMIC_SET
 TRY	s32i	a0, a3, 0		# write new value
 
 	mov	a0, a2
 	mov	a2, a7
 	l32i	a7, a0, PT_AREG7	# restore a7
 	l32i	a0, a0, PT_AREG0	# restore a0
-	addi	a6, a6, 1		# restore a6 (really necessary?)
 	rfe
 
 CATCH
@@ -1044,7 +1042,7 @@ CATCH
 	movi	a2, -EFAULT
 	rfe
 
-.Lill:	l32i	a7, a2, PT_AREG0	# restore a7
+.Lill:	l32i	a7, a2, PT_AREG7	# restore a7
 	l32i	a0, a2, PT_AREG0	# restore a0
 	movi	a2, -EINVAL
 	rfe
@@ -1565,7 +1563,7 @@ ENTRY(fast_second_level_miss)
 	rsr	a0, excvaddr
 	bltu	a0, a3, 2f
 
-	addi	a1, a0, -(2 << (DCACHE_ALIAS_ORDER + PAGE_SHIFT))
+	addi	a1, a0, -TLBTEMP_SIZE
 	bgeu	a1, a3, 2f
 
 	/* Check if we have to restore an ITLB mapping. */
@@ -1820,7 +1818,6 @@ ENTRY(_switch_to)
 
 	entry	a1, 16
 
-	mov	a10, a2			# preserve 'prev' (a2)
 	mov	a11, a3			# and 'next' (a3)
 
 	l32i	a4, a2, TASK_THREAD_INFO
@@ -1828,8 +1825,14 @@ ENTRY(_switch_to)
 
 	save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
-	s32i	a0, a10, THREAD_RA	# save return address
-	s32i	a1, a10, THREAD_SP	# save stack pointer
+#if THREAD_RA > 1020 || THREAD_SP > 1020
+	addi	a10, a2, TASK_THREAD
+	s32i	a0, a10, THREAD_RA - TASK_THREAD	# save return address
+	s32i	a1, a10, THREAD_SP - TASK_THREAD	# save stack pointer
+#else
+	s32i	a0, a2, THREAD_RA	# save return address
+	s32i	a1, a2, THREAD_SP	# save stack pointer
+#endif
 
 	/* Disable ints while we manipulate the stack pointer. */
 
@@ -1870,7 +1873,6 @@ ENTRY(_switch_to)
 	load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
 	wsr	a14, ps
-	mov	a2, a10			# return 'prev'
 	rsync
 
 	retw
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 2d9cc6dbfd78..e8b76b8e4b29 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -49,9 +49,8 @@ dma_alloc_coherent(struct device *dev,size_t size,dma_addr_t *handle,gfp_t flag)
 
 	/* We currently don't support coherent memory outside KSEG */
 
-	if (ret < XCHAL_KSEG_CACHED_VADDR
-	    || ret >= XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE)
-		BUG();
+	BUG_ON(ret < XCHAL_KSEG_CACHED_VADDR ||
+	       ret > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
 
 
 	if (ret != 0) {
@@ -68,10 +67,11 @@ EXPORT_SYMBOL(dma_alloc_coherent);
 void dma_free_coherent(struct device *hwdev, size_t size,
 			 void *vaddr, dma_addr_t dma_handle)
 {
-	long addr=(long)vaddr+XCHAL_KSEG_CACHED_VADDR-XCHAL_KSEG_BYPASS_VADDR;
+	unsigned long addr = (unsigned long)vaddr +
+		XCHAL_KSEG_CACHED_VADDR - XCHAL_KSEG_BYPASS_VADDR;
 
-	if (addr < 0 || addr >= XCHAL_KSEG_SIZE)
-		BUG();
+	BUG_ON(addr < XCHAL_KSEG_CACHED_VADDR ||
+	       addr > XCHAL_KSEG_CACHED_VADDR + XCHAL_KSEG_SIZE - 1);
 
 	free_pages(addr, get_order(size));
 }