Merge branch 'fixes' of master.kernel.org:/home/rmk/linux-2.6-arm

* 'fixes' of master.kernel.org:/home/rmk/linux-2.6-arm:
  ARM: 6745/1: kprobes insn decoding fix
  ARM: tlb: move noMMU tlb_flush() to asm/tlb.h
  ARM: tlb: delay page freeing for SMP and ARMv7 CPUs
  ARM: Keep exit text/data around for SMP_ON_UP
  ARM: Ensure predictable endian state on signal handler entry
  ARM: 6740/1: Place correctly notes section in the linker script
  ARM: 6700/1: SPEAr: Correct SOC config base address for spear320
  ARM: 6722/1: SPEAr: sp810: switch to slow mode before reset
  ARM: 6712/1: SPEAr: replace readl(), writel() with relaxed versions in uncompress.h
  ARM: 6720/1: SPEAr: Append UL to VMALLOC_END
  ARM: 6676/1: Correct the cpu_architecture() function for ARMv7
  ARM: 6739/1: update .gitignore for boot/compressed
  ARM: 6743/1: errata: interrupted ICALLUIS may prevent completion of broadcasted operation
  ARM: 6742/1: pmu: avoid setting IRQ affinity on UP systems
  ARM: 6741/1: errata: pl310 cache sync operation may be faulty

arch/arm/Kconfig

@@ -1177,6 +1177,31 @@ config ARM_ERRATA_743622
 	  visible impact on the overall performance or power consumption of the
 	  processor.
 
+config ARM_ERRATA_751472
+	bool "ARM errata: Interrupted ICIALLUIS may prevent completion of broadcasted operation"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for the 751472 Cortex-A9 (prior
+	  to r3p0) erratum. An interrupted ICIALLUIS operation may prevent the
+	  completion of a following broadcasted operation if the second
+	  operation is received by a CPU before the ICIALLUIS has completed,
+	  potentially leading to corrupted entries in the cache or TLB.
+
+config ARM_ERRATA_753970
+	bool "ARM errata: cache sync operation may be faulty"
+	depends on CACHE_PL310
+	help
+	  This option enables the workaround for the 753970 PL310 (r3p0) erratum.
+
+	  Under some condition the effect of cache sync operation on
+	  the store buffer still remains when the operation completes.
+	  This means that the store buffer is always asked to drain and
+	  this prevents it from merging any further writes. The workaround
+	  is to replace the normal offset of cache sync operation (0x730)
+	  by another offset targeting an unmapped PL310 register 0x740.
+	  This has the same effect as the cache sync operation: store buffer
+	  drain and waiting for all buffers empty.
+
 endmenu
 
 source "arch/arm/common/Kconfig"

arch/arm/Makefile

@@ -15,7 +15,7 @@ ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux	+= --be8
 endif
 
-OBJCOPYFLAGS	:=-O binary -R .note -R .note.gnu.build-id -R .comment -S
+OBJCOPYFLAGS	:=-O binary -R .comment -S
 GZFLAGS		:=-9
 #KBUILD_CFLAGS	+=-pipe
 # Explicitly specifiy 32-bit ARM ISA since toolchain default can be -mthumb:

arch/arm/boot/compressed/.gitignore

 font.c
-piggy.gz
+lib1funcs.S
+piggy.gzip
+piggy.lzo
+piggy.lzma
+vmlinux
 vmlinux.lds

arch/arm/include/asm/hardware/cache-l2x0.h

@@ -36,6 +36,7 @@
 #define L2X0_RAW_INTR_STAT		0x21C
 #define L2X0_INTR_CLEAR			0x220
 #define L2X0_CACHE_SYNC			0x730
+#define L2X0_DUMMY_REG			0x740
 #define L2X0_INV_LINE_PA		0x770
 #define L2X0_INV_WAY			0x77C
 #define L2X0_CLEAN_LINE_PA		0x7B0

arch/arm/include/asm/hardware/sp810.h

@@ -58,6 +58,9 @@
 
 static inline void sysctl_soft_reset(void __iomem *base)
 {
+	/* switch to slow mode */
+	writel(0x2, base + SCCTRL);
+
 	/* writing any value to SCSYSSTAT reg will reset system */
 	writel(0, base + SCSYSSTAT);
 }

arch/arm/include/asm/tlb.h

@@ -18,16 +18,34 @@
 #define __ASMARM_TLB_H
 
 #include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
 
 #ifndef CONFIG_MMU
 
 #include <linux/pagemap.h>
+
+#define tlb_flush(tlb)	((void) tlb)
+
 #include <asm-generic/tlb.h>
 
 #else /* !CONFIG_MMU */
 
+#include <linux/swap.h>
 #include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+
+/*
+ * We need to delay page freeing for SMP as other CPUs can access pages
+ * which have been removed but not yet had their TLB entries invalidated.
+ * Also, as ARMv7 speculative prefetch can drag new entries into the TLB,
+ * we need to apply this same delaying tactic to ensure correct operation.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_CPU_32v7)
+#define tlb_fast_mode(tlb)	0
+#define FREE_PTE_NR		500
+#else
+#define tlb_fast_mode(tlb)	1
+#define FREE_PTE_NR		0
+#endif
 
 /*
  * TLB handling.  This allows us to remove pages from the page
@@ -36,12 +54,58 @@
 struct mmu_gather {
 	struct mm_struct	*mm;
 	unsigned int		fullmm;
+	struct vm_area_struct	*vma;
 	unsigned long		range_start;
 	unsigned long		range_end;
+	unsigned int		nr;
+	struct page		*pages[FREE_PTE_NR];
 };
 
 DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
 
+/*
+ * This is unnecessarily complex.  There's three ways the TLB shootdown
+ * code is used:
+ *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
+ *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
+ *     tlb->vma will be non-NULL.
+ *  2. Unmapping all vmas.  See exit_mmap().
+ *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
+ *     tlb->vma will be non-NULL.  Additionally, page tables will be freed.
+ *  3. Unmapping argument pages.  See shift_arg_pages().
+ *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
+ *     tlb->vma will be NULL.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	if (tlb->fullmm || !tlb->vma)
+		flush_tlb_mm(tlb->mm);
+	else if (tlb->range_end > 0) {
+		flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end);
+		tlb->range_start = TASK_SIZE;
+		tlb->range_end = 0;
+	}
+}
+
+static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
+{
+	if (!tlb->fullmm) {
+		if (addr < tlb->range_start)
+			tlb->range_start = addr;
+		if (addr + PAGE_SIZE > tlb->range_end)
+			tlb->range_end = addr + PAGE_SIZE;
+	}
+}
+
+static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+	tlb_flush(tlb);
+	if (!tlb_fast_mode(tlb)) {
+		free_pages_and_swap_cache(tlb->pages, tlb->nr);
+		tlb->nr = 0;
+	}
+}
+
 static inline struct mmu_gather *
 tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
 {
@@ -49,6 +113,8 @@ tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
 
 	tlb->mm = mm;
 	tlb->fullmm = full_mm_flush;
+	tlb->vma = NULL;
+	tlb->nr = 0;
 
 	return tlb;
 }
@@ -56,8 +122,7 @@ tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
 static inline void
 tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
 {
-	if (tlb->fullmm)
-		flush_tlb_mm(tlb->mm);
+	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */
 	check_pgt_cache();
@@ -71,12 +136,7 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
 static inline void
 tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
 {
-	if (!tlb->fullmm) {
-		if (addr < tlb->range_start)
-			tlb->range_start = addr;
-		if (addr + PAGE_SIZE > tlb->range_end)
-			tlb->range_end = addr + PAGE_SIZE;
-	}
+	tlb_add_flush(tlb, addr);
 }
 
 /*
@@ -89,6 +149,7 @@ tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 {
 	if (!tlb->fullmm) {
 		flush_cache_range(vma, vma->vm_start, vma->vm_end);
+		tlb->vma = vma;
 		tlb->range_start = TASK_SIZE;
 		tlb->range_end = 0;
 	}
@@ -97,12 +158,30 @@ tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 static inline void
 tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 {
-	if (!tlb->fullmm && tlb->range_end > 0)
-		flush_tlb_range(vma, tlb->range_start, tlb->range_end);
+	if (!tlb->fullmm)
+		tlb_flush(tlb);
+}
+
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	if (tlb_fast_mode(tlb)) {
+		free_page_and_swap_cache(page);
+	} else {
+		tlb->pages[tlb->nr++] = page;
+		if (tlb->nr >= FREE_PTE_NR)
+			tlb_flush_mmu(tlb);
+	}
+}
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
+	unsigned long addr)
+{
+	pgtable_page_dtor(pte);
+	tlb_add_flush(tlb, addr);
+	tlb_remove_page(tlb, pte);
 }
 
-#define tlb_remove_page(tlb,page)	free_page_and_swap_cache(page)
-#define pte_free_tlb(tlb, ptep, addr)	pte_free((tlb)->mm, ptep)
+#define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
 #define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
 
 #define tlb_migrate_finish(mm)		do { } while (0)

arch/arm/include/asm/tlbflush.h

@@ -10,12 +10,7 @@
 #ifndef _ASMARM_TLBFLUSH_H
 #define _ASMARM_TLBFLUSH_H
 
-
-#ifndef CONFIG_MMU
-
-#define tlb_flush(tlb)	((void) tlb)
-
-#else /* CONFIG_MMU */
+#ifdef CONFIG_MMU
 
 #include <asm/glue.h>
 

arch/arm/kernel/kprobes-decode.c

@@ -1437,7 +1437,7 @@ arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 
 		return space_cccc_1100_010x(insn, asi);
 
-	} else if ((insn & 0x0e000000) == 0x0c400000) {
+	} else if ((insn & 0x0e000000) == 0x0c000000) {
 
 		return space_cccc_110x(insn, asi);
 

arch/arm/kernel/pmu.c

@@ -97,28 +97,34 @@ set_irq_affinity(int irq,
 			   irq, cpu);
 	return err;
 #else
-	return 0;
+	return -EINVAL;
 #endif
 }
 
 static int
 init_cpu_pmu(void)
 {
-	int i, err = 0;
+	int i, irqs, err = 0;
 	struct platform_device *pdev = pmu_devices[ARM_PMU_DEVICE_CPU];
 
-	if (!pdev) {
-		err = -ENODEV;
-		goto out;
-	}
+	if (!pdev)
+		return -ENODEV;
+
+	irqs = pdev->num_resources;
+
+	/*
+	 * If we have a single PMU interrupt that we can't shift, assume that
+	 * we're running on a uniprocessor machine and continue.
+	 */
+	if (irqs == 1 && !irq_can_set_affinity(platform_get_irq(pdev, 0)))
+		return 0;
 
-	for (i = 0; i < pdev->num_resources; ++i) {
+	for (i = 0; i < irqs; ++i) {
 		err = set_irq_affinity(platform_get_irq(pdev, i), i);
 		if (err)
 			break;
 	}
 
-out:
 	return err;
 }
 

arch/arm/kernel/setup.c

@@ -226,8 +226,8 @@ int cpu_architecture(void)
 		 * Register 0 and check for VMSAv7 or PMSAv7 */
 		asm("mrc	p15, 0, %0, c0, c1, 4"
 		    : "=r" (mmfr0));
-		if ((mmfr0 & 0x0000000f) == 0x00000003 ||
-		    (mmfr0 & 0x000000f0) == 0x00000030)
+		if ((mmfr0 & 0x0000000f) >= 0x00000003 ||
+		    (mmfr0 & 0x000000f0) >= 0x00000030)
 			cpu_arch = CPU_ARCH_ARMv7;
 		else if ((mmfr0 & 0x0000000f) == 0x00000002 ||
 			 (mmfr0 & 0x000000f0) == 0x00000020)

arch/arm/kernel/signal.c

@@ -474,7 +474,9 @@ setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 	unsigned long handler = (unsigned long)ka->sa.sa_handler;
 	unsigned long retcode;
 	int thumb = 0;
-	unsigned long cpsr = regs->ARM_cpsr & ~PSR_f;
+	unsigned long cpsr = regs->ARM_cpsr & ~(PSR_f | PSR_E_BIT);
+
+	cpsr |= PSR_ENDSTATE;
 
 	/*
 	 * Maybe we need to deliver a 32-bit signal to a 26-bit task.

arch/arm/kernel/vmlinux.lds.S

@@ -21,6 +21,12 @@
 #define ARM_CPU_KEEP(x)
 #endif
 
+#if defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)
+#define ARM_EXIT_KEEP(x)	x
+#else
+#define ARM_EXIT_KEEP(x)
+#endif
+
 OUTPUT_ARCH(arm)
 ENTRY(stext)
 
@@ -43,6 +49,7 @@ SECTIONS
 		_sinittext = .;
 			HEAD_TEXT
 			INIT_TEXT
+			ARM_EXIT_KEEP(EXIT_TEXT)
 		_einittext = .;
 		ARM_CPU_DISCARD(PROC_INFO)
 		__arch_info_begin = .;
@@ -67,6 +74,7 @@ SECTIONS
 #ifndef CONFIG_XIP_KERNEL
 		__init_begin = _stext;
 		INIT_DATA
+		ARM_EXIT_KEEP(EXIT_DATA)
 #endif
 	}
 
@@ -162,6 +170,7 @@ SECTIONS
 		. = ALIGN(PAGE_SIZE);
 		__init_begin = .;
 		INIT_DATA
+		ARM_EXIT_KEEP(EXIT_DATA)
 		. = ALIGN(PAGE_SIZE);
 		__init_end = .;
 #endif
@@ -247,6 +256,8 @@ SECTIONS
 	}
 #endif
 
+	NOTES
+
 	BSS_SECTION(0, 0, 0)
 	_end = .;
 

arch/arm/mach-spear3xx/include/mach/spear320.h

@@ -62,7 +62,7 @@
 #define SPEAR320_SMII1_BASE		0xAB000000
 #define SPEAR320_SMII1_SIZE		0x01000000
 
-#define SPEAR320_SOC_CONFIG_BASE	0xB4000000
+#define SPEAR320_SOC_CONFIG_BASE	0xB3000000
 #define SPEAR320_SOC_CONFIG_SIZE	0x00000070
 /* Interrupt registers offsets and masks */
 #define INT_STS_MASK_REG		0x04

arch/arm/mm/cache-l2x0.c

@@ -49,7 +49,13 @@ static inline void cache_wait(void __iomem *reg, unsigned long mask)
 static inline void cache_sync(void)
 {
 	void __iomem *base = l2x0_base;
+
+#ifdef CONFIG_ARM_ERRATA_753970
+	/* write to an unmmapped register */
+	writel_relaxed(0, base + L2X0_DUMMY_REG);
+#else
 	writel_relaxed(0, base + L2X0_CACHE_SYNC);
+#endif
 	cache_wait(base + L2X0_CACHE_SYNC, 1);
 }
 

arch/arm/mm/proc-v7.S

@@ -264,6 +264,12 @@ __v7_setup:
 	orreq	r10, r10, #1 << 6		@ set bit #6
 	mcreq	p15, 0, r10, c15, c0, 1		@ write diagnostic register
 #endif
+#ifdef CONFIG_ARM_ERRATA_751472
+	cmp	r6, #0x30			@ present prior to r3p0
+	mrclt	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orrlt	r10, r10, #1 << 11		@ set bit #11
+	mcrlt	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
 
 3:	mov	r10, #0
 #ifdef HARVARD_CACHE

arch/arm/plat-spear/include/plat/uncompress.h

@@ -24,10 +24,10 @@ static inline void putc(int c)
 {
 	void __iomem *base = (void __iomem *)SPEAR_DBG_UART_BASE;
 
-	while (readl(base + UART01x_FR) & UART01x_FR_TXFF)
+	while (readl_relaxed(base + UART01x_FR) & UART01x_FR_TXFF)
 		barrier();
 
-	writel(c, base + UART01x_DR);
+	writel_relaxed(c, base + UART01x_DR);
 }
 
 static inline void flush(void)

arch/arm/plat-spear/include/plat/vmalloc.h

@@ -14,6 +14,6 @@
 #ifndef __PLAT_VMALLOC_H
 #define __PLAT_VMALLOC_H
 
-#define VMALLOC_END		0xF0000000
+#define VMALLOC_END		0xF0000000UL
 
 #endif /* __PLAT_VMALLOC_H */