Merge branch 'linux-linaro-lsk' into linux-linaro-lsk-rt

25 files changed, 171 insertions, 73 deletions

diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 9ce8ba1a1433..adb9aa5c88c7 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -48,6 +48,8 @@ CONFIG_SERIAL_SIRFSOC=y
 CONFIG_SERIAL_SIRFSOC_CONSOLE=y
 CONFIG_SERIAL_VT8500=y
 CONFIG_SERIAL_VT8500_CONSOLE=y
+CONFIG_SERIAL_XILINX_PS_UART=y
+CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y
 CONFIG_IPMI_HANDLER=y
 CONFIG_IPMI_SI=y
 CONFIG_I2C=y
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 8c79344552d5..11d68917d3b1 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -362,6 +362,16 @@ ENTRY(vector_swi)
 	str	r0, [sp, #S_OLD_R0]		@ Save OLD_R0
 	zero_fp
 
+#ifdef CONFIG_ALIGNMENT_TRAP
+	ldr	ip, __cr_alignment
+	ldr	ip, [ip]
+	mcr	p15, 0, ip, c1, c0		@ update control register
+#endif
+
+	enable_irq
+	ct_user_exit
+	get_thread_info tsk
+
 	/*
 	 * Get the system call number.
 	 */
@@ -375,9 +385,9 @@ ENTRY(vector_swi)
 #ifdef CONFIG_ARM_THUMB
 	tst	r8, #PSR_T_BIT
 	movne	r10, #0				@ no thumb OABI emulation
-	ldreq	r10, [lr, #-4]			@ get SWI instruction
+ USER(	ldreq	r10, [lr, #-4]		)	@ get SWI instruction
 #else
-	ldr	r10, [lr, #-4]			@ get SWI instruction
+ USER(	ldr	r10, [lr, #-4]		)	@ get SWI instruction
 #endif
  ARM_BE8(rev	r10, r10)			@ little endian instruction
 
@@ -390,22 +400,13 @@ ENTRY(vector_swi)
 	/* Legacy ABI only, possibly thumb mode. */
 	tst	r8, #PSR_T_BIT			@ this is SPSR from save_user_regs
 	addne	scno, r7, #__NR_SYSCALL_BASE	@ put OS number in
-	ldreq	scno, [lr, #-4]
+ USER(	ldreq	scno, [lr, #-4]		)
 
 #else
 	/* Legacy ABI only. */
-	ldr	scno, [lr, #-4]			@ get SWI instruction
+ USER(	ldr	scno, [lr, #-4]		)	@ get SWI instruction
 #endif
 
-#ifdef CONFIG_ALIGNMENT_TRAP
-	ldr	ip, __cr_alignment
-	ldr	ip, [ip]
-	mcr	p15, 0, ip, c1, c0		@ update control register
-#endif
-	enable_irq
-	ct_user_exit
-
-	get_thread_info tsk
 	adr	tbl, sys_call_table		@ load syscall table pointer
 
 #if defined(CONFIG_OABI_COMPAT)
@@ -440,6 +441,21 @@ local_restart:
 	eor	r0, scno, #__NR_SYSCALL_BASE	@ put OS number back
 	bcs	arm_syscall	
 	b	sys_ni_syscall			@ not private func
+
+#if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI)
+	/*
+	 * We failed to handle a fault trying to access the page
+	 * containing the swi instruction, but we're not really in a
+	 * position to return -EFAULT. Instead, return back to the
+	 * instruction and re-enter the user fault handling path trying
+	 * to page it in. This will likely result in sending SEGV to the
+	 * current task.
+	 */
+9001:
+	sub	lr, lr, #4
+	str	lr, [sp, #S_PC]
+	b	ret_fast_syscall
+#endif
 ENDPROC(vector_swi)
 
 	/*
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/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index c3ef920823b6..70ae735dec53 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -14,10 +14,11 @@
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
+#include <asm/fncpy.h>
 #include <asm/mach-types.h>
 #include <asm/system_misc.h>
 
-extern const unsigned char relocate_new_kernel[];
+extern void relocate_new_kernel(void);
 extern const unsigned int relocate_new_kernel_size;
 
 extern unsigned long kexec_start_address;
@@ -133,6 +134,8 @@ void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list;
 	unsigned long reboot_code_buffer_phys;
+	unsigned long reboot_entry = (unsigned long)relocate_new_kernel;
+	unsigned long reboot_entry_phys;
 	void *reboot_code_buffer;
 
 	if (num_online_cpus() > 1) {
@@ -156,18 +159,18 @@ void machine_kexec(struct kimage *image)
 
 
 	/* copy our kernel relocation code to the control code page */
-	memcpy(reboot_code_buffer,
-	       relocate_new_kernel, relocate_new_kernel_size);
+	reboot_entry = fncpy(reboot_code_buffer,
+			     reboot_entry,
+			     relocate_new_kernel_size);
+	reboot_entry_phys = (unsigned long)reboot_entry +
+		(reboot_code_buffer_phys - (unsigned long)reboot_code_buffer);
 
-
-	flush_icache_range((unsigned long) reboot_code_buffer,
-			   (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
 	printk(KERN_INFO "Bye!\n");
 
 	if (kexec_reinit)
 		kexec_reinit();
 
-	soft_restart(reboot_code_buffer_phys);
+	soft_restart(reboot_entry_phys);
 }
 
 void arch_crash_save_vmcoreinfo(void)
diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S
index d0cdedf4864d..95858966d84e 100644
--- a/arch/arm/kernel/relocate_kernel.S
+++ b/arch/arm/kernel/relocate_kernel.S
@@ -2,10 +2,12 @@
  * relocate_kernel.S - put the kernel image in place to boot
  */
 
+#include <linux/linkage.h>
 #include <asm/kexec.h>
 
-	.globl relocate_new_kernel
-relocate_new_kernel:
+	.align	3	/* not needed for this code, but keeps fncpy() happy */
+
+ENTRY(relocate_new_kernel)
 
 	ldr	r0,kexec_indirection_page
 	ldr	r1,kexec_start_address
@@ -79,6 +81,8 @@ kexec_mach_type:
 kexec_boot_atags:
 	.long	0x0
 
+ENDPROC(relocate_new_kernel)
+
 relocate_new_kernel_end:
 
 	.globl relocate_new_kernel_size
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/process.c b/arch/arm64/kernel/process.c
index 3193bf35dbc8..75c6b1e0d606 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -203,9 +203,27 @@ 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 096a7ad5f004..bc09a147454f 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/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c
index 2c9573098c0d..d498a1f9bccf 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 33d067148e61..3efbf0b29c1b 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
@@ -181,6 +188,11 @@ 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 96ec3982be8d..94607bfa273d 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -46,7 +46,12 @@ 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/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index becc08e6a65c..637c97fcbeb5 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -35,6 +35,12 @@
 					STACK_FRAME_OVERHEAD + 288)
 #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
@@ -46,6 +52,7 @@
 #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/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/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 0dc7d9e21c34..9d7d36c82fc2 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/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fe862750583b..87084ab90d19 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1284,6 +1284,9 @@ 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/kvm/x86.c b/arch/x86/kvm/x86.c
index 98b2fa39e295..cc4b5b257cc6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1196,20 +1196,37 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	elapsed = ns - kvm->arch.last_tsc_nsec;
 
 	if (vcpu->arch.virtual_tsc_khz) {
+		int faulted = 0;
+
 		/* n.b - signed multiplication and division required */
 		usdiff = data - kvm->arch.last_tsc_write;
 #ifdef CONFIG_X86_64
 		usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz;
 #else
 		/* do_div() only does unsigned */
-		asm("idivl %2; xor %%edx, %%edx"
-		: "=A"(usdiff)
-		: "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz));
+		asm("1: idivl %[divisor]\n"
+		    "2: xor %%edx, %%edx\n"
+		    "   movl $0, %[faulted]\n"
+		    "3:\n"
+		    ".section .fixup,\"ax\"\n"
+		    "4: movl $1, %[faulted]\n"
+		    "   jmp  3b\n"
+		    ".previous\n"
+
+		_ASM_EXTABLE(1b, 4b)
+
+		: "=A"(usdiff), [faulted] "=r" (faulted)
+		: "A"(usdiff * 1000), [divisor] "rm"(vcpu->arch.virtual_tsc_khz));
+
 #endif
 		do_div(elapsed, 1000);
 		usdiff -= elapsed;
 		if (usdiff < 0)
 			usdiff = -usdiff;
+
+		/* idivl overflow => difference is larger than USEC_PER_SEC */
+		if (faulted)
+			usdiff = USEC_PER_SEC;
 	} else
 		usdiff = USEC_PER_SEC; /* disable TSC match window below */
 
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index d7546c94da52..385efb23ddce 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -68,7 +68,12 @@
 #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
 
 /*
  * Xtensa Linux config PTE layout (when present):
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 aa7f9add7d77..6e53174f8556 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1121,9 +1121,8 @@ 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. */
 
@@ -1135,27 +1134,26 @@ 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
@@ -1164,7 +1162,7 @@ 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
@@ -1703,7 +1701,7 @@ 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. */
@@ -1961,7 +1959,6 @@ ENTRY(_switch_to)
 
 	entry	a1, 16
 
-	mov	a10, a2			# preserve 'prev' (a2)
 	mov	a11, a3			# and 'next' (a3)
 
 	l32i	a4, a2, TASK_THREAD_INFO
@@ -1969,8 +1966,14 @@ 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. */
 
@@ -2011,7 +2014,6 @@ 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));
 }