Merge branch 'fixes' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM fixes from Russell King:
 "A set of fixes from various people - Will Deacon gets a prize for
  removing code this time around.  The biggest fix in this lot is
  sorting out the ARM740T mess.  The rest are relatively small fixes."

* 'fixes' of git://git.linaro.org/people/rmk/linux-arm:
  ARM: 7699/1: sched_clock: Add more notrace to prevent recursion
  ARM: 7698/1: perf: fix group validation when using enable_on_exec
  ARM: 7697/1: hw_breakpoint: do not use __cpuinitdata for dbg_cpu_pm_nb
  ARM: 7696/1: Fix kexec by setting outer_cache.inv_all for Feroceon
  ARM: 7694/1: ARM, TCM: initialize TCM in paging_init(), instead of setup_arch()
  ARM: 7692/1: iop3xx: move IOP3XX_PERIPHERAL_VIRT_BASE
  ARM: modules: don't export cpu_set_pte_ext when !MMU
  ARM: mm: remove broken condition check for v4 flushing
  ARM: mm: fix numerous hideous errors in proc-arm740.S
  ARM: cache: remove ARMv3 support code
  ARM: tlbflush: remove ARMv3 support

17 files changed, 34 insertions, 182 deletions

diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h
index cca9f15704ed..ea289e1435e7 100644
--- a/arch/arm/include/asm/glue-cache.h
+++ b/arch/arm/include/asm/glue-cache.h
@@ -19,14 +19,6 @@
 #undef _CACHE
 #undef MULTI_CACHE
 
-#if defined(CONFIG_CPU_CACHE_V3)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE v3
-# endif
-#endif
-
 #if defined(CONFIG_CPU_CACHE_V4)
 # ifdef _CACHE
 #  define MULTI_CACHE 1
diff --git a/arch/arm/include/asm/hardware/iop3xx.h b/arch/arm/include/asm/hardware/iop3xx.h
index 02fe2fbe2477..ed94b1a366ae 100644
--- a/arch/arm/include/asm/hardware/iop3xx.h
+++ b/arch/arm/include/asm/hardware/iop3xx.h
@@ -37,7 +37,7 @@ extern int iop3xx_get_init_atu(void);
  * IOP3XX processor registers
  */
 #define IOP3XX_PERIPHERAL_PHYS_BASE	0xffffe000
-#define IOP3XX_PERIPHERAL_VIRT_BASE	0xfeffe000
+#define IOP3XX_PERIPHERAL_VIRT_BASE	0xfedfe000
 #define IOP3XX_PERIPHERAL_SIZE		0x00002000
 #define IOP3XX_PERIPHERAL_UPPER_PA (IOP3XX_PERIPHERAL_PHYS_BASE +\
 					IOP3XX_PERIPHERAL_SIZE - 1)
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index 9e9c041358ca..ab865e65a84c 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -14,7 +14,6 @@
 
 #include <asm/glue.h>
 
-#define TLB_V3_PAGE	(1 << 0)
 #define TLB_V4_U_PAGE	(1 << 1)
 #define TLB_V4_D_PAGE	(1 << 2)
 #define TLB_V4_I_PAGE	(1 << 3)
@@ -22,7 +21,6 @@
 #define TLB_V6_D_PAGE	(1 << 5)
 #define TLB_V6_I_PAGE	(1 << 6)
 
-#define TLB_V3_FULL	(1 << 8)
 #define TLB_V4_U_FULL	(1 << 9)
 #define TLB_V4_D_FULL	(1 << 10)
 #define TLB_V4_I_FULL	(1 << 11)
@@ -52,7 +50,6 @@
  *	=============
  *
  *	We have the following to choose from:
- *	  v3    - ARMv3
  *	  v4    - ARMv4 without write buffer
  *	  v4wb  - ARMv4 with write buffer without I TLB flush entry instruction
  *	  v4wbi - ARMv4 with write buffer with I TLB flush entry instruction
@@ -330,7 +327,6 @@ static inline void local_flush_tlb_all(void)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
 	tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
 	tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
 	tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
@@ -351,9 +347,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (possible_tlb_flags & (TLB_V3_FULL|TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
+	if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
 		if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
-			tlb_op(TLB_V3_FULL, "c6, c0, 0", zero);
 			tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero);
 			tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero);
 			tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero);
@@ -385,9 +380,8 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	if (possible_tlb_flags & (TLB_V3_PAGE|TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
+	if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
 	    cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
-		tlb_op(TLB_V3_PAGE, "c6, c0, 0", uaddr);
 		tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr);
 		tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", uaddr);
 		tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", uaddr);
@@ -418,7 +412,6 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
 	if (tlb_flag(TLB_WB))
 		dsb();
 
-	tlb_op(TLB_V3_PAGE, "c6, c0, 0", kaddr);
 	tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr);
 	tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr);
 	tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr);
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 5dc1aa6f0f7d..1fd749ee4a1b 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -1043,7 +1043,7 @@ static int dbg_cpu_pm_notify(struct notifier_block *self, unsigned long action,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata dbg_cpu_pm_nb = {
+static struct notifier_block dbg_cpu_pm_nb = {
 	.notifier_call = dbg_cpu_pm_notify,
 };
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 146157dfe27c..8c3094d0f7b7 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -253,7 +253,10 @@ validate_event(struct pmu_hw_events *hw_events,
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct pmu *leader_pmu = event->group_leader->pmu;
 
-	if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF)
+	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
+		return 1;
+
+	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
 		return 1;
 
 	return armpmu->get_event_idx(hw_events, event) >= 0;
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index bd6f56b9ec21..59d2adb764a9 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -45,12 +45,12 @@ static u32 notrace jiffy_sched_clock_read(void)
 
 static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
 
-static inline u64 cyc_to_ns(u64 cyc, u32 mult, u32 shift)
+static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 {
 	return (cyc * mult) >> shift;
 }
 
-static unsigned long long cyc_to_sched_clock(u32 cyc, u32 mask)
+static unsigned long long notrace cyc_to_sched_clock(u32 cyc, u32 mask)
 {
 	u64 epoch_ns;
 	u32 epoch_cyc;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index d343a6c3a6d1..234e339196c0 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -56,7 +56,6 @@
 #include <asm/virt.h>
 
 #include "atags.h"
-#include "tcm.h"
 
 
 #if defined(CONFIG_FPE_NWFPE) || defined(CONFIG_FPE_FASTFPE)
@@ -798,8 +797,6 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_crashkernel();
 
-	tcm_init();
-
 #ifdef CONFIG_MULTI_IRQ_HANDLER
 	handle_arch_irq = mdesc->handle_irq;
 #endif
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
index 30ae6bb4a310..f50f19e5c138 100644
--- a/arch/arm/kernel/tcm.c
+++ b/arch/arm/kernel/tcm.c
@@ -17,7 +17,6 @@
 #include <asm/mach/map.h>
 #include <asm/memory.h>
 #include <asm/system_info.h>
-#include "tcm.h"
 
 static struct gen_pool *tcm_pool;
 static bool dtcm_present;
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 025d17328730..4045c4931a30 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -43,7 +43,7 @@ config CPU_ARM740T
 	depends on !MMU
 	select CPU_32v4T
 	select CPU_ABRT_LV4T
-	select CPU_CACHE_V3	# although the core is v4t
+	select CPU_CACHE_V4
 	select CPU_CP15_MPU
 	select CPU_PABRT_LEGACY
 	help
@@ -469,9 +469,6 @@ config CPU_PABRT_V7
 	bool
 
 # The cache model
-config CPU_CACHE_V3
-	bool
-
 config CPU_CACHE_V4
 	bool
 
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 4e333fa2756f..9e51be96f635 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -33,7 +33,6 @@ obj-$(CONFIG_CPU_PABRT_LEGACY)	+= pabort-legacy.o
 obj-$(CONFIG_CPU_PABRT_V6)	+= pabort-v6.o
 obj-$(CONFIG_CPU_PABRT_V7)	+= pabort-v7.o
 
-obj-$(CONFIG_CPU_CACHE_V3)	+= cache-v3.o
 obj-$(CONFIG_CPU_CACHE_V4)	+= cache-v4.o
 obj-$(CONFIG_CPU_CACHE_V4WT)	+= cache-v4wt.o
 obj-$(CONFIG_CPU_CACHE_V4WB)	+= cache-v4wb.o
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index dd3d59122cc3..48bc3c0a87ce 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -343,6 +343,7 @@ void __init feroceon_l2_init(int __l2_wt_override)
 	outer_cache.inv_range = feroceon_l2_inv_range;
 	outer_cache.clean_range = feroceon_l2_clean_range;
 	outer_cache.flush_range = feroceon_l2_flush_range;
+	outer_cache.inv_all = l2_inv_all;
 
 	enable_l2();
 
diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S
deleted file mode 100644
index 8a3fadece8d3..000000000000
--- a/arch/arm/mm/cache-v3.S
+++ /dev/null
@@ -1,137 +0,0 @@
-/*
- *  linux/arch/arm/mm/cache-v3.S
- *
- *  Copyright (C) 1997-2002 Russell king
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/page.h>
-#include "proc-macros.S"
-
-/*
- *	flush_icache_all()
- *
- *	Unconditionally clean and invalidate the entire icache.
- */
-ENTRY(v3_flush_icache_all)
-	mov	pc, lr
-ENDPROC(v3_flush_icache_all)
-
-/*
- *	flush_user_cache_all()
- *
- *	Invalidate all cache entries in a particular address
- *	space.
- *
- *	- mm	- mm_struct describing address space
- */
-ENTRY(v3_flush_user_cache_all)
-	/* FALLTHROUGH */
-/*
- *	flush_kern_cache_all()
- *
- *	Clean and invalidate the entire cache.
- */
-ENTRY(v3_flush_kern_cache_all)
-	/* FALLTHROUGH */
-
-/*
- *	flush_user_cache_range(start, end, flags)
- *
- *	Invalidate a range of cache entries in the specified
- *	address space.
- *
- *	- start - start address (may not be aligned)
- *	- end	- end address (exclusive, may not be aligned)
- *	- flags	- vma_area_struct flags describing address space
- */
-ENTRY(v3_flush_user_cache_range)
-	mov	ip, #0
-	mcreq	p15, 0, ip, c7, c0, 0		@ flush ID cache
-	mov	pc, lr
-
-/*
- *	coherent_kern_range(start, end)
- *
- *	Ensure coherency between the Icache and the Dcache in the
- *	region described by start.  If you have non-snooping
- *	Harvard caches, you need to implement this function.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_coherent_kern_range)
-	/* FALLTHROUGH */
-
-/*
- *	coherent_user_range(start, end)
- *
- *	Ensure coherency between the Icache and the Dcache in the
- *	region described by start.  If you have non-snooping
- *	Harvard caches, you need to implement this function.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_coherent_user_range)
-	mov	r0, #0
-	mov	pc, lr
-
-/*
- *	flush_kern_dcache_area(void *page, size_t size)
- *
- *	Ensure no D cache aliasing occurs, either with itself or
- *	the I cache
- *
- *	- addr	- kernel address
- *	- size	- region size
- */
-ENTRY(v3_flush_kern_dcache_area)
-	/* FALLTHROUGH */
-
-/*
- *	dma_flush_range(start, end)
- *
- *	Clean and invalidate the specified virtual address range.
- *
- *	- start  - virtual start address
- *	- end	 - virtual end address
- */
-ENTRY(v3_dma_flush_range)
-	mov	r0, #0
-	mcr	p15, 0, r0, c7, c0, 0		@ flush ID cache
-	mov	pc, lr
-
-/*
- *	dma_unmap_area(start, size, dir)
- *	- start	- kernel virtual start address
- *	- size	- size of region
- *	- dir	- DMA direction
- */
-ENTRY(v3_dma_unmap_area)
-	teq	r2, #DMA_TO_DEVICE
-	bne	v3_dma_flush_range
-	/* FALLTHROUGH */
-
-/*
- *	dma_map_area(start, size, dir)
- *	- start	- kernel virtual start address
- *	- size	- size of region
- *	- dir	- DMA direction
- */
-ENTRY(v3_dma_map_area)
-	mov	pc, lr
-ENDPROC(v3_dma_unmap_area)
-ENDPROC(v3_dma_map_area)
-
-	.globl	v3_flush_kern_cache_louis
-	.equ	v3_flush_kern_cache_louis, v3_flush_kern_cache_all
-
-	__INITDATA
-
-	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
-	define_cache_functions v3
diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S
index 43e5d77be677..a7ba68f59f0c 100644
--- a/arch/arm/mm/cache-v4.S
+++ b/arch/arm/mm/cache-v4.S
@@ -58,7 +58,7 @@ ENTRY(v4_flush_kern_cache_all)
 ENTRY(v4_flush_user_cache_range)
 #ifdef CONFIG_CPU_CP15
 	mov	ip, #0
-	mcreq	p15, 0, ip, c7, c7, 0		@ flush ID cache
+	mcr	p15, 0, ip, c7, c7, 0		@ flush ID cache
 	mov	pc, lr
 #else
 	/* FALLTHROUGH */
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 78978945492a..a84ff763ac39 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -34,6 +34,7 @@
 #include <asm/mach/pci.h>
 
 #include "mm.h"
+#include "tcm.h"
 
 /*
  * empty_zero_page is a special page that is used for
@@ -1277,6 +1278,7 @@ void __init paging_init(struct machine_desc *mdesc)
 	dma_contiguous_remap();
 	devicemaps_init(mdesc);
 	kmap_init();
+	tcm_init();
 
 	top_pmd = pmd_off_k(0xffff0000);
 
diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S
index dc5de5d53f20..fde2d2a794cf 100644
--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -77,24 +77,27 @@ __arm740_setup:
 	mcr	p15, 0, r0, c6,	c0		@ set area 0, default
 
 	ldr	r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM
-	ldr	r1, =(CONFIG_DRAM_SIZE >> 12)	@ size of RAM (must be >= 4KB)
-	mov	r2, #10				@ 11 is the minimum (4KB)
-1:	add	r2, r2, #1			@ area size *= 2
-	mov	r1, r1, lsr #1
+	ldr	r3, =(CONFIG_DRAM_SIZE >> 12)	@ size of RAM (must be >= 4KB)
+	mov	r4, #10				@ 11 is the minimum (4KB)
+1:	add	r4, r4, #1			@ area size *= 2
+	movs	r3, r3, lsr #1
 	bne	1b				@ count not zero r-shift
-	orr	r0, r0, r2, lsl #1		@ the area register value
+	orr	r0, r0, r4, lsl #1		@ the area register value
 	orr	r0, r0, #1			@ set enable bit
 	mcr	p15, 0, r0, c6,	c1		@ set area 1, RAM
 
 	ldr	r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH
-	ldr	r1, =(CONFIG_FLASH_SIZE >> 12)	@ size of FLASH (must be >= 4KB)
-	mov	r2, #10				@ 11 is the minimum (4KB)
-1:	add	r2, r2, #1			@ area size *= 2
-	mov	r1, r1, lsr #1
+	ldr	r3, =(CONFIG_FLASH_SIZE >> 12)	@ size of FLASH (must be >= 4KB)
+	cmp	r3, #0
+	moveq	r0, #0
+	beq	2f
+	mov	r4, #10				@ 11 is the minimum (4KB)
+1:	add	r4, r4, #1			@ area size *= 2
+	movs	r3, r3, lsr #1
 	bne	1b				@ count not zero r-shift
-	orr	r0, r0, r2, lsl #1		@ the area register value
+	orr	r0, r0, r4, lsl #1		@ the area register value
 	orr	r0, r0, #1			@ set enable bit
-	mcr	p15, 0, r0, c6,	c2		@ set area 2, ROM/FLASH
+2:	mcr	p15, 0, r0, c6,	c2		@ set area 2, ROM/FLASH
 
 	mov	r0, #0x06
 	mcr	p15, 0, r0, c2, c0		@ Region 1&2 cacheable
@@ -137,13 +140,14 @@ __arm740_proc_info:
 	.long	0x41807400
 	.long	0xfffffff0
 	.long	0
+	.long	0
 	b	__arm740_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
-	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT
+	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT
 	.long	cpu_arm740_name
 	.long	arm740_processor_functions
 	.long	0
 	.long	0
-	.long	v3_cache_fns			@ cache model
+	.long	v4_cache_fns			@ cache model
 	.size	__arm740_proc_info, . - __arm740_proc_info
diff --git a/arch/arm/mm/proc-syms.c b/arch/arm/mm/proc-syms.c
index 3e6210b4d6d4..054b491ff764 100644
--- a/arch/arm/mm/proc-syms.c
+++ b/arch/arm/mm/proc-syms.c
@@ -17,7 +17,9 @@
 
 #ifndef MULTI_CPU
 EXPORT_SYMBOL(cpu_dcache_clean_area);
+#ifdef CONFIG_MMU
 EXPORT_SYMBOL(cpu_set_pte_ext);
+#endif
 #else
 EXPORT_SYMBOL(processor);
 #endif
diff --git a/arch/arm/kernel/tcm.h b/arch/arm/mm/tcm.h
index 8015ad434a40..8015ad434a40 100644
--- a/arch/arm/kernel/tcm.h
+++ b/arch/arm/mm/tcm.h