Merge tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:

 - An improvement from Ard Biesheuvel, who noted that the identity map
   setup was taking a long time due to flush_cache_louis().

 - Update a comment about dma_ops from Wolfram Sang.

 - Remove use of "-p" with ld, where this flag has been a no-op since
   2004.

 - Remove the printing of the virtual memory layout, which is no longer
   useful since we hide pointers.

 - Correct SCU help text.

 - Remove legacy TWD registration method.

 - Add pgprot_device() implementation for mapping PCI sysfs resource
   files.

 - Initialise PFN limits earlier for kmemleak.

 - Fix argument count to match macro definition (affects clang builds)

 - Use unified assembler language almost everywhere for clang, and other
   clang improvements (from Stefan Agner, Nathan Chancellor).

 - Support security extension for noMMU and other noMMU cleanups (from
   Vladimir Murzin).

 - Remove unnecessary SMP bringup code (which was incorrectly copy'n'
   pasted from the ARM platform implementations) and remove it from the
   arch code to discourge further copys of it appearing.

 - Add Cortex A9 erratum preventing kexec working on some SoCs.

 - AMBA bus identification updates from Mike Leach.

 - More use of raw spinlocks to avoid -RT kernel issues (from Yang Shi
   and Sebastian Andrzej Siewior).

 - MCPM hyp/svc mode mismatch fixes from Marek Szyprowski.

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (32 commits)
  ARM: 8849/1: NOMMU: Fix encodings for PMSAv8's PRBAR4/PRLAR4
  ARM: 8848/1: virt: Align GIC version check with arm64 counterpart
  ARM: 8847/1: pm: fix HYP/SVC mode mismatch when MCPM is used
  ARM: 8845/1: use unified assembler in c files
  ARM: 8844/1: use unified assembler in assembly files
  ARM: 8843/1: use unified assembler in headers
  ARM: 8841/1: use unified assembler in macros
  ARM: 8840/1: use a raw_spinlock_t in unwind
  ARM: 8839/1: kprobe: make patch_lock a raw_spinlock_t
  ARM: 8837/1: coresight: etmv4: Update ID register table to add UCI support
  ARM: 8836/1: drivers: amba: Update component matching to use the CoreSight UCI values.
  ARM: 8838/1: drivers: amba: Updates to component identification for driver matching.
  ARM: 8833/1: Ensure that NEON code always compiles with Clang
  ARM: avoid Cortex-A9 livelock on tight dmb loops
  ARM: smp: remove arch-provided "pen_release"
  ARM: actions: remove boot_lock and pen_release
  ARM: oxnas: remove CPU hotplug implementation
  ARM: qcom: remove unnecessary boot_lock
  ARM: 8832/1: NOMMU: Limit visibility for CONFIG_FLASH_{MEM_BASE,SIZE}
  ARM: 8831/1: NOMMU: pmsa-v8: remove unneeded semicolon
  ...

13 files changed, 32 insertions, 37 deletions

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 28a48e0d4cca..b59921a560da 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -376,9 +376,9 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort, t=TUSER()
 9999:
 	.if	\inc == 1
-	\instr\cond\()b\()\t\().w \reg, [\ptr, #\off]
+	\instr\()b\t\cond\().w \reg, [\ptr, #\off]
 	.elseif	\inc == 4
-	\instr\cond\()\t\().w \reg, [\ptr, #\off]
+	\instr\t\cond\().w \reg, [\ptr, #\off]
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -417,9 +417,9 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.rept	\rept
 9999:
 	.if	\inc == 1
-	\instr\cond\()b\()\t \reg, [\ptr], #\inc
+	\instr\()b\t\cond \reg, [\ptr], #\inc
 	.elseif	\inc == 4
-	\instr\cond\()\t \reg, [\ptr], #\inc
+	\instr\t\cond \reg, [\ptr], #\inc
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -460,7 +460,7 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.macro check_uaccess, addr:req, size:req, limit:req, tmp:req, bad:req
 #ifndef CONFIG_CPU_USE_DOMAINS
 	adds	\tmp, \addr, #\size - 1
-	sbcccs	\tmp, \tmp, \limit
+	sbcscc	\tmp, \tmp, \limit
 	bcs	\bad
 #ifdef CONFIG_CPU_SPECTRE
 	movcs	\addr, #0
@@ -474,7 +474,7 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	sub	\tmp, \limit, #1
 	subs	\tmp, \tmp, \addr	@ tmp = limit - 1 - addr
 	addhs	\tmp, \tmp, #1		@ if (tmp >= 0) {
-	subhss	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
+	subshs	\tmp, \tmp, \size	@ tmp = limit - (addr + size) }
 	movlo	\addr, #0		@ if (tmp < 0) addr = NULL
 	csdb
 #endif
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 69772e742a0a..83ae97c049d9 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -11,6 +11,8 @@
 #define sev()	__asm__ __volatile__ ("sev" : : : "memory")
 #define wfe()	__asm__ __volatile__ ("wfe" : : : "memory")
 #define wfi()	__asm__ __volatile__ ("wfi" : : : "memory")
+#else
+#define wfe()	do { } while (0)
 #endif
 
 #if __LINUX_ARM_ARCH__ >= 7
diff --git a/arch/arm/include/asm/hardware/entry-macro-iomd.S b/arch/arm/include/asm/hardware/entry-macro-iomd.S
index 8c215acd9b57..f7692731e514 100644
--- a/arch/arm/include/asm/hardware/entry-macro-iomd.S
+++ b/arch/arm/include/asm/hardware/entry-macro-iomd.S
@@ -16,25 +16,25 @@
 		ldr	\tmp, =irq_prio_h
 		teq	\irqstat, #0
 #ifdef IOMD_BASE
-		ldreqb	\irqstat, [\base, #IOMD_DMAREQ]	@ get dma
+		ldrbeq	\irqstat, [\base, #IOMD_DMAREQ]	@ get dma
 		addeq	\tmp, \tmp, #256		@ irq_prio_h table size
 		teqeq	\irqstat, #0
 		bne	2406f
 #endif
-		ldreqb	\irqstat, [\base, #IOMD_IRQREQA]	@ get low priority
+		ldrbeq	\irqstat, [\base, #IOMD_IRQREQA]	@ get low priority
 		addeq	\tmp, \tmp, #256		@ irq_prio_d table size
 		teqeq	\irqstat, #0
 #ifdef IOMD_IRQREQC
-		ldreqb	\irqstat, [\base, #IOMD_IRQREQC]
+		ldrbeq	\irqstat, [\base, #IOMD_IRQREQC]
 		addeq	\tmp, \tmp, #256		@ irq_prio_l table size
 		teqeq	\irqstat, #0
 #endif
 #ifdef IOMD_IRQREQD
-		ldreqb	\irqstat, [\base, #IOMD_IRQREQD]
+		ldrbeq	\irqstat, [\base, #IOMD_IRQREQD]
 		addeq	\tmp, \tmp, #256		@ irq_prio_lc table size
 		teqeq	\irqstat, #0
 #endif
-2406:		ldrneb	\irqnr, [\tmp, \irqstat]	@ get IRQ number
+2406:		ldrbne	\irqnr, [\tmp, \irqstat]	@ get IRQ number
 		.endm
 
 /*
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index a757401129f9..48ce1b19069b 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -125,6 +125,9 @@ extern pgprot_t		pgprot_s2_device;
 #define pgprot_stronglyordered(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_UNCACHED)
 
+#define pgprot_device(prot) \
+	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_DEV_SHARED | L_PTE_SHARED | L_PTE_DIRTY | L_PTE_XN)
+
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK, L_PTE_MT_BUFFERABLE | L_PTE_XN)
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 120f4c9bbfde..57fe73ea0f72 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -89,7 +89,11 @@ extern void release_thread(struct task_struct *);
 unsigned long get_wchan(struct task_struct *p);
 
 #if __LINUX_ARM_ARCH__ == 6 || defined(CONFIG_ARM_ERRATA_754327)
-#define cpu_relax()			smp_mb()
+#define cpu_relax()						\
+	do {							\
+		smp_mb();					\
+		__asm__ __volatile__("nop; nop; nop; nop; nop; nop; nop; nop; nop; nop;");	\
+	} while (0)
 #else
 #define cpu_relax()			barrier()
 #endif
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 709a55989cb0..451ae684aaf4 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -67,7 +67,6 @@ struct secondary_data {
 	void *stack;
 };
 extern struct secondary_data secondary_data;
-extern volatile int pen_release;
 extern void secondary_startup(void);
 extern void secondary_startup_arm(void);
 
diff --git a/arch/arm/include/asm/smp_twd.h b/arch/arm/include/asm/smp_twd.h
index 312784ee9936..c729d2113a24 100644
--- a/arch/arm/include/asm/smp_twd.h
+++ b/arch/arm/include/asm/smp_twd.h
@@ -19,20 +19,4 @@
 #define TWD_TIMER_CONTROL_PERIODIC	(1 << 1)
 #define TWD_TIMER_CONTROL_IT_ENABLE	(1 << 2)
 
-#include <linux/ioport.h>
-
-struct twd_local_timer {
-	struct resource	res[2];
-};
-
-#define DEFINE_TWD_LOCAL_TIMER(name,base,irq)	\
-struct twd_local_timer name __initdata = {	\
-	.res	= {				\
-		DEFINE_RES_MEM(base, 0x10),	\
-		DEFINE_RES_IRQ(irq),		\
-	},					\
-};
-
-int twd_local_timer_register(struct twd_local_timer *);
-
 #endif
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 099c78fcf62d..8f009e788ad4 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -210,11 +210,12 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 
 	prefetchw(&rw->lock);
 	__asm__ __volatile__(
+"	.syntax unified\n"
 "1:	ldrex	%0, [%2]\n"
 "	adds	%0, %0, #1\n"
 "	strexpl	%1, %0, [%2]\n"
 	WFE("mi")
-"	rsbpls	%0, %1, #0\n"
+"	rsbspl	%0, %1, #0\n"
 "	bmi	1b"
 	: "=&r" (tmp), "=&r" (tmp2)
 	: "r" (&rw->lock)
diff --git a/arch/arm/include/asm/suspend.h b/arch/arm/include/asm/suspend.h
index 452bbdcbcc83..506314265c6f 100644
--- a/arch/arm/include/asm/suspend.h
+++ b/arch/arm/include/asm/suspend.h
@@ -10,6 +10,7 @@ struct sleep_save_sp {
 };
 
 extern void cpu_resume(void);
+extern void cpu_resume_no_hyp(void);
 extern void cpu_resume_arm(void);
 extern int cpu_suspend(unsigned long, int (*)(unsigned long));
 
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index ae5a0df5316e..dff49845eb87 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -85,7 +85,8 @@ static inline void set_fs(mm_segment_t fs)
 #define __range_ok(addr, size) ({ \
 	unsigned long flag, roksum; \
 	__chk_user_ptr(addr);	\
-	__asm__("adds %1, %2, %3; sbcccs %1, %1, %0; movcc %0, #0" \
+	__asm__(".syntax unified\n" \
+		"adds %1, %2, %3; sbcscc %1, %1, %0; movcc %0, #0" \
 		: "=&r" (flag), "=&r" (roksum) \
 		: "r" (addr), "Ir" (size), "0" (current_thread_info()->addr_limit) \
 		: "cc"); \
diff --git a/arch/arm/include/asm/v7m.h b/arch/arm/include/asm/v7m.h
index 187ccf6496ad..2cb00d15831b 100644
--- a/arch/arm/include/asm/v7m.h
+++ b/arch/arm/include/asm/v7m.h
@@ -49,7 +49,7 @@
  * (0 -> msp; 1 -> psp). Bits [1:0] are fixed to 0b01.
  */
 #define EXC_RET_STACK_MASK			0x00000004
-#define EXC_RET_THREADMODE_PROCESSSTACK		0xfffffffd
+#define EXC_RET_THREADMODE_PROCESSSTACK		(3 << 2)
 
 /* Cache related definitions */
 
diff --git a/arch/arm/include/asm/vfpmacros.h b/arch/arm/include/asm/vfpmacros.h
index ef5dfedacd8d..628c336e8e3b 100644
--- a/arch/arm/include/asm/vfpmacros.h
+++ b/arch/arm/include/asm/vfpmacros.h
@@ -29,13 +29,13 @@
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
 	tst	\tmp, #HWCAP_VFPD32
-	ldcnel	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	ldclne	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
 	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
 	cmp	\tmp, #2			    @ 32 x 64bit registers?
-	ldceql	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
+	ldcleq	p11, cr0, [\base],#32*4		    @ FLDMIAD \base!, {d16-d31}
 	addne	\base, \base, #32*4		    @ step over unused register space
 #endif
 #endif
@@ -53,13 +53,13 @@
 	ldr	\tmp, =elf_hwcap		    @ may not have MVFR regs
 	ldr	\tmp, [\tmp, #0]
 	tst	\tmp, #HWCAP_VFPD32
-	stcnel	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	stclne	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
 	addeq	\base, \base, #32*4		    @ step over unused register space
 #else
 	VFPFMRX	\tmp, MVFR0			    @ Media and VFP Feature Register 0
 	and	\tmp, \tmp, #MVFR0_A_SIMD_MASK	    @ A_SIMD field
 	cmp	\tmp, #2			    @ 32 x 64bit registers?
-	stceql	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
+	stcleq	p11, cr0, [\base],#32*4		    @ FSTMIAD \base!, {d16-d31}
 	addne	\base, \base, #32*4		    @ step over unused register space
 #endif
 #endif
diff --git a/arch/arm/include/debug/tegra.S b/arch/arm/include/debug/tegra.S
index 3bc80599c022..4a5a645c76e2 100644
--- a/arch/arm/include/debug/tegra.S
+++ b/arch/arm/include/debug/tegra.S
@@ -173,7 +173,7 @@
 
 		.macro	senduart, rd, rx
 		cmp	\rx, #0
-		strneb	\rd, [\rx, #UART_TX << UART_SHIFT]
+		strbne	\rd, [\rx, #UART_TX << UART_SHIFT]
 1001:
 		.endm