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

Pull ARM updates from Russell King:
 "Included in this update are both some long term fixes and some new
  features.

  Fixes:

   - An integer overflow in the calculation of ELF_ET_DYN_BASE.

   - Avoiding OOMs for high-order IOMMU allocations

   - SMP requires the data cache to be enabled for synchronisation
     primitives to work, so prevent the CPU_DCACHE_DISABLE option being
     visible on SMP builds.

   - A bug going back 10+ years in the noMMU ARM94* CPU support code,
     where it corrupts registers.  Found by folk getting Linux running
     on their cameras.

   - Versatile Express needs an errata workaround enabled for CPU
     hot-unplug to work.

  Features:

   - Clean up module linker by handling out of range relocations
     separately from relocation cases we don't handle.

   - Fix a long term bug in the pci_mmap_page_range() code, which we
     hope won't impact userspace (we hope there's no users of the
     existing broken interface.)

   - Don't map DMA coherent allocations when we don't have a MMU.

   - Drop experimental status for SMP_ON_UP.

   - Warn when DT doesn't specify ePAPR mandatory cache properties.

   - Add documentation concerning how we find the start of physical
     memory for AUTO_ZRELADDR kernels, detailing why we have chosen the
     mask and the implications of changing it.

   - Updates from Ard Biesheuvel to address some issues with large
     kernels (such as allyesconfig) failing to link.

   - Allow hibernation to work on modern (ARMv7) CPUs - this appears to
     have never worked in the past on these CPUs.

   - Enable IRQ_SHOW_LEVEL, which changes the /proc/interrupts output
     format (hopefully without userspace breaking...  let's hope that if
     it causes someone a problem, they tell us.)

   - Fix tegra-ahb DT offsets.

   - Rework ARM errata 643719 code (and ARMv7 flush_cache_louis()/
     flush_dcache_all()) code to be more efficient, and enable this
     errata workaround by default for ARMv7+SMP CPUs.  This complements
     the Versatile Express fix above.

   - Rework ARMv7 context code for errata 430973, so that only Cortex A8
     CPUs are impacted by the branch target buffer flush when this
     errata is enabled.  Also update the help text to indicate that all
     r1p* A8 CPUs are impacted.

   - Switch ARM to the generic show_mem() implementation, it conveys all
     the information which we were already reporting.

   - Prevent slow timer sources being used for udelay() - timers running
     at less than 1MHz are not useful for this, and can cause udelay()
     to return immediately, without any wait.  Using such a slow timer
     is silly.

   - VDSO support for 32-bit ARM, mainly for gettimeofday() using the
     ARM architected timer.

   - Perf support for Scorpion performance monitoring units"

vdso semantic conflict fixed up as per linux-next.

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (52 commits)
  ARM: update errata 430973 documentation to cover Cortex A8 r1p*
  ARM: ensure delay timer has sufficient accuracy for delays
  ARM: switch to use the generic show_mem() implementation
  ARM: proc-v7: avoid errata 430973 workaround for non-Cortex A8 CPUs
  ARM: enable ARM errata 643719 workaround by default
  ARM: cache-v7: optimise test for Cortex A9 r0pX devices
  ARM: cache-v7: optimise branches in v7_flush_cache_louis
  ARM: cache-v7: consolidate initialisation of cache level index
  ARM: cache-v7: shift CLIDR to extract appropriate field before masking
  ARM: cache-v7: use movw/movt instructions
  ARM: allow 16-bit instructions in ALT_UP()
  ARM: proc-arm94*.S: fix setup function
  ARM: vexpress: fix CPU hotplug with CT9x4 tile.
  ARM: 8276/1: Make CPU_DCACHE_DISABLE depend on !SMP
  ARM: 8335/1: Documentation: DT bindings: Tegra AHB: document the legacy base address
  ARM: 8334/1: amba: tegra-ahb: detect and correct bogus base address
  ARM: 8333/1: amba: tegra-ahb: fix register offsets in the macros
  ARM: 8339/1: Enable CONFIG_GENERIC_IRQ_SHOW_LEVEL
  ARM: 8338/1: kexec: Relax SMP validation to improve DT compatibility
  ARM: 8337/1: mm: Do not invoke OOM for higher order IOMMU DMA allocations
  ...

Author: torvalds

Documentation/devicetree/bindings/arm/pmu.txt

@@ -18,6 +18,8 @@ Required properties:
 	"arm,arm11mpcore-pmu"
 	"arm,arm1176-pmu"
 	"arm,arm1136-pmu"
+	"qcom,scorpion-pmu"
+	"qcom,scorpion-mp-pmu"
 	"qcom,krait-pmu"
 - interrupts : 1 combined interrupt or 1 per core. If the interrupt is a per-cpu
                interrupt (PPI) then 1 interrupt should be specified.

Documentation/devicetree/bindings/arm/tegra/nvidia,tegra20-ahb.txt

@@ -5,9 +5,12 @@ Required properties:
   Tegra30, must contain "nvidia,tegra30-ahb".  Otherwise, must contain
   '"nvidia,<chip>-ahb", "nvidia,tegra30-ahb"' where <chip> is tegra124,
   tegra132, or tegra210.
-- reg : Should contain 1 register ranges(address and length)
+- reg : Should contain 1 register ranges(address and length).  For
+  Tegra20, Tegra30, and Tegra114 chips, the value must be <0x6000c004
+  0x10c>.  For Tegra124, Tegra132 and Tegra210 chips, the value should
+  be be <0x6000c000 0x150>.
 
-Example:
+Example (for a Tegra20 chip):
 	ahb: ahb@6000c004 {
 		compatible = "nvidia,tegra20-ahb";
 		reg = <0x6000c004 0x10c>; /* AHB Arbitration + Gizmo Controller */

arch/arm/Kconfig

@@ -21,6 +21,7 @@ config ARM
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
+	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
@@ -1063,7 +1064,7 @@ config ARM_ERRATA_430973
 	depends on CPU_V7
 	help
 	  This option enables the workaround for the 430973 Cortex-A8
-	  (r1p0..r1p2) erratum. If a code sequence containing an ARM/Thumb
+	  r1p* erratum. If a code sequence containing an ARM/Thumb
 	  interworking branch is replaced with another code sequence at the
 	  same virtual address, whether due to self-modifying code or virtual
 	  to physical address re-mapping, Cortex-A8 does not recover from the
@@ -1132,6 +1133,7 @@ config ARM_ERRATA_742231
 config ARM_ERRATA_643719
 	bool "ARM errata: LoUIS bit field in CLIDR register is incorrect"
 	depends on CPU_V7 && SMP
+	default y
 	help
 	  This option enables the workaround for the 643719 Cortex-A9 (prior to
 	  r1p0) erratum. On affected cores the LoUIS bit field of the CLIDR
@@ -1349,7 +1351,7 @@ config SMP
 	  If you don't know what to do here, say N.
 
 config SMP_ON_UP
-	bool "Allow booting SMP kernel on uniprocessor systems (EXPERIMENTAL)"
+	bool "Allow booting SMP kernel on uniprocessor systems"
 	depends on SMP && !XIP_KERNEL && MMU
 	default y
 	help

arch/arm/Makefile

@@ -13,7 +13,7 @@
 # Ensure linker flags are correct
 LDFLAGS		:=
 
-LDFLAGS_vmlinux	:=-p --no-undefined -X
+LDFLAGS_vmlinux	:=-p --no-undefined -X --pic-veneer
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux	+= --be8
 LDFLAGS_MODULE	+= --be8
@@ -264,6 +264,7 @@ core-$(CONFIG_FPE_FASTFPE)	+= $(FASTFPE_OBJ)
 core-$(CONFIG_VFP)		+= arch/arm/vfp/
 core-$(CONFIG_XEN)		+= arch/arm/xen/
 core-$(CONFIG_KVM_ARM_HOST) 	+= arch/arm/kvm/
+core-$(CONFIG_VDSO)		+= arch/arm/vdso/
 
 # If we have a machine-specific directory, then include it in the build.
 core-y				+= arch/arm/kernel/ arch/arm/mm/ arch/arm/common/
@@ -321,6 +322,12 @@ dtbs: prepare scripts
 dtbs_install:
 	$(Q)$(MAKE) $(dtbinst)=$(boot)/dts
 
+PHONY += vdso_install
+vdso_install:
+ifeq ($(CONFIG_VDSO),y)
+	$(Q)$(MAKE) $(build)=arch/arm/vdso $@
+endif
+
 # We use MRPROPER_FILES and CLEAN_FILES now
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
@@ -345,4 +352,5 @@ define archhelp
   echo  '                  Install using (your) ~/bin/$(INSTALLKERNEL) or'
   echo  '                  (distribution) /sbin/$(INSTALLKERNEL) or'
   echo  '                  install to $$(INSTALL_PATH) and run lilo'
+  echo  '  vdso_install  - Install unstripped vdso.so to $$(INSTALL_MOD_PATH)/vdso'
 endef

arch/arm/boot/compressed/head.S

@@ -10,8 +10,11 @@
  */
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/v7m.h>
+
+ AR_CLASS(	.arch	armv7-a	)
+ M_CLASS(	.arch	armv7-m	)
 
-	.arch	armv7-a
 /*
  * Debugging stuff
  *
@@ -114,7 +117,12 @@
  * sort out different calling conventions
  */
 		.align
-		.arm				@ Always enter in ARM state
+		/*
+		 * Always enter in ARM state for CPUs that support the ARM ISA.
+		 * As of today (2014) that's exactly the members of the A and R
+		 * classes.
+		 */
+ AR_CLASS(	.arm	)
 start:
 		.type	start,#function
 		.rept	7
@@ -132,14 +140,15 @@ start:
 
  THUMB(		.thumb			)
 1:
- ARM_BE8(	setend	be )			@ go BE8 if compiled for BE8
-		mrs	r9, cpsr
+ ARM_BE8(	setend	be		)	@ go BE8 if compiled for BE8
+ AR_CLASS(	mrs	r9, cpsr	)
 #ifdef CONFIG_ARM_VIRT_EXT
 		bl	__hyp_stub_install	@ get into SVC mode, reversibly
 #endif
 		mov	r7, r1			@ save architecture ID
 		mov	r8, r2			@ save atags pointer
 
+#ifndef CONFIG_CPU_V7M
 		/*
 		 * Booting from Angel - need to enter SVC mode and disable
 		 * FIQs/IRQs (numeric definitions from angel arm.h source).
@@ -155,6 +164,7 @@ not_angel:
 		safe_svcmode_maskall r0
 		msr	spsr_cxsf, r9		@ Save the CPU boot mode in
 						@ SPSR
+#endif
 		/*
 		 * Note that some cache flushing and other stuff may
 		 * be needed here - is there an Angel SWI call for this?
@@ -168,9 +178,26 @@ not_angel:
 		.text
 
 #ifdef CONFIG_AUTO_ZRELADDR
-		@ determine final kernel image address
+		/*
+		 * Find the start of physical memory.  As we are executing
+		 * without the MMU on, we are in the physical address space.
+		 * We just need to get rid of any offset by aligning the
+		 * address.
+		 *
+		 * This alignment is a balance between the requirements of
+		 * different platforms - we have chosen 128MB to allow
+		 * platforms which align the start of their physical memory
+		 * to 128MB to use this feature, while allowing the zImage
+		 * to be placed within the first 128MB of memory on other
+		 * platforms.  Increasing the alignment means we place
+		 * stricter alignment requirements on the start of physical
+		 * memory, but relaxing it means that we break people who
+		 * are already placing their zImage in (eg) the top 64MB
+		 * of this range.
+		 */
 		mov	r4, pc
 		and	r4, r4, #0xf8000000
+		/* Determine final kernel image address. */
 		add	r4, r4, #TEXT_OFFSET
 #else
 		ldr	r4, =zreladdr
@@ -810,6 +837,16 @@ __common_mmu_cache_on:
 call_cache_fn:	adr	r12, proc_types
 #ifdef CONFIG_CPU_CP15
 		mrc	p15, 0, r9, c0, c0	@ get processor ID
+#elif defined(CONFIG_CPU_V7M)
+		/*
+		 * On v7-M the processor id is located in the V7M_SCB_CPUID
+		 * register, but as cache handling is IMPLEMENTATION DEFINED on
+		 * v7-M (if existant at all) we just return early here.
+		 * If V7M_SCB_CPUID were used the cpu ID functions (i.e.
+		 * __armv7_mmu_cache_{on,off,flush}) would be selected which
+		 * use cp15 registers that are not implemented on v7-M.
+		 */
+		bx	lr
 #else
 		ldr	r9, =CONFIG_PROCESSOR_ID
 #endif
@@ -1310,8 +1347,9 @@ __hyp_reentry_vectors:
 
 __enter_kernel:
 		mov	r0, #0			@ must be 0
- ARM(		mov	pc, r4	)		@ call kernel
- THUMB(		bx	r4	)		@ entry point is always ARM
+ ARM(		mov	pc, r4		)	@ call kernel
+ M_CLASS(	add	r4, r4, #1	)	@ enter in Thumb mode for M class
+ THUMB(		bx	r4		)	@ entry point is always ARM for A/R classes
 
 reloc_code_end:
 

arch/arm/include/asm/Kbuild

@@ -1,6 +1,5 @@
 
 
-generic-y += auxvec.h
 generic-y += bitsperlong.h
 generic-y += cputime.h
 generic-y += current.h

arch/arm/include/asm/assembler.h

@@ -237,6 +237,9 @@
 	.pushsection ".alt.smp.init", "a"			;\
 	.long	9998b						;\
 9997:	instr							;\
+	.if . - 9997b == 2					;\
+		nop						;\
+	.endif							;\
 	.if . - 9997b != 4					;\
 		.error "ALT_UP() content must assemble to exactly 4 bytes";\
 	.endif							;\

arch/arm/include/asm/auxvec.h

@@ -0,0 +1 @@
+#include <uapi/asm/auxvec.h>

arch/arm/include/asm/cputype.h

@@ -253,4 +253,20 @@ static inline int cpu_is_pj4(void)
 #else
 #define cpu_is_pj4()	0
 #endif
+
+static inline int __attribute_const__ cpuid_feature_extract_field(u32 features,
+								  int field)
+{
+	int feature = (features >> field) & 15;
+
+	/* feature registers are signed values */
+	if (feature > 8)
+		feature -= 16;
+
+	return feature;
+}
+
+#define cpuid_feature_extract(reg, field) \
+	cpuid_feature_extract_field(read_cpuid_ext(reg), field)
+
 #endif

arch/arm/include/asm/elf.h

@@ -1,7 +1,9 @@
 #ifndef __ASMARM_ELF_H
 #define __ASMARM_ELF_H
 
+#include <asm/auxvec.h>
 #include <asm/hwcap.h>
+#include <asm/vdso_datapage.h>
 
 /*
  * ELF register definitions..
@@ -115,7 +117,7 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
    the loader.  We need to make sure that it is out of the way of the program
    that it will "exec", and that there is sufficient room for the brk.  */
 
-#define ELF_ET_DYN_BASE	(2 * TASK_SIZE / 3)
+#define ELF_ET_DYN_BASE	(TASK_SIZE / 3 * 2)
 
 /* When the program starts, a1 contains a pointer to a function to be 
    registered with atexit, as per the SVR4 ABI.  A value of 0 means we 
@@ -126,6 +128,13 @@ extern void elf_set_personality(const struct elf32_hdr *);
 #define SET_PERSONALITY(ex)	elf_set_personality(&(ex))
 
 #ifdef CONFIG_MMU
+#ifdef CONFIG_VDSO
+#define ARCH_DLINFO						\
+do {								\
+	NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
+		    (elf_addr_t)current->mm->context.vdso);	\
+} while (0)
+#endif
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 struct linux_binprm;
 int arch_setup_additional_pages(struct linux_binprm *, int);

arch/arm/include/asm/futex.h

@@ -13,7 +13,7 @@
 	"	.align	3\n"					\
 	"	.long	1b, 4f, 2b, 4f\n"			\
 	"	.popsection\n"					\
-	"	.pushsection .fixup,\"ax\"\n"			\
+	"	.pushsection .text.fixup,\"ax\"\n"		\
 	"	.align	2\n"					\
 	"4:	mov	%0, " err_reg "\n"			\
 	"	b	3b\n"					\

arch/arm/include/asm/mmu.h

@@ -11,6 +11,9 @@ typedef struct {
 #endif
 	unsigned int	vmalloc_seq;
 	unsigned long	sigpage;
+#ifdef CONFIG_VDSO
+	unsigned long	vdso;
+#endif
 } mm_context_t;
 
 #ifdef CONFIG_CPU_HAS_ASID

arch/arm/include/asm/pmu.h

@@ -92,6 +92,7 @@ struct pmu_hw_events {
 struct arm_pmu {
 	struct pmu	pmu;
 	cpumask_t	active_irqs;
+	int		*irq_affinity;
 	char		*name;
 	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
 	void		(*enable)(struct perf_event *event);

arch/arm/include/asm/smp_plat.h

@@ -104,6 +104,7 @@ static inline u32 mpidr_hash_size(void)
 	return 1 << mpidr_hash.bits;
 }
 
+extern int platform_can_secondary_boot(void);
 extern int platform_can_cpu_hotplug(void);
 
 #endif

arch/arm/include/asm/uaccess.h

@@ -315,7 +315,7 @@ do {									\
 	__asm__ __volatile__(					\
 	"1:	" TUSER(ldrb) "	%1,[%2],#0\n"			\
 	"2:\n"							\
-	"	.pushsection .fixup,\"ax\"\n"			\
+	"	.pushsection .text.fixup,\"ax\"\n"		\
 	"	.align	2\n"					\
 	"3:	mov	%0, %3\n"				\
 	"	mov	%1, #0\n"				\
@@ -351,7 +351,7 @@ do {									\
 	__asm__ __volatile__(					\
 	"1:	" TUSER(ldr) "	%1,[%2],#0\n"			\
 	"2:\n"							\
-	"	.pushsection .fixup,\"ax\"\n"			\
+	"	.pushsection .text.fixup,\"ax\"\n"		\
 	"	.align	2\n"					\
 	"3:	mov	%0, %3\n"				\
 	"	mov	%1, #0\n"				\
@@ -397,7 +397,7 @@ do {									\
 	__asm__ __volatile__(					\
 	"1:	" TUSER(strb) "	%1,[%2],#0\n"			\
 	"2:\n"							\
-	"	.pushsection .fixup,\"ax\"\n"			\
+	"	.pushsection .text.fixup,\"ax\"\n"		\
 	"	.align	2\n"					\
 	"3:	mov	%0, %3\n"				\
 	"	b	2b\n"					\
@@ -430,7 +430,7 @@ do {									\
 	__asm__ __volatile__(					\
 	"1:	" TUSER(str) "	%1,[%2],#0\n"			\
 	"2:\n"							\
-	"	.pushsection .fixup,\"ax\"\n"			\
+	"	.pushsection .text.fixup,\"ax\"\n"		\
 	"	.align	2\n"					\
 	"3:	mov	%0, %3\n"				\
 	"	b	2b\n"					\
@@ -458,7 +458,7 @@ do {									\
  THUMB(	"1:	" TUSER(str) "	" __reg_oper1 ", [%1]\n"	) \
  THUMB(	"2:	" TUSER(str) "	" __reg_oper0 ", [%1, #4]\n"	) \
 	"3:\n"							\
-	"	.pushsection .fixup,\"ax\"\n"			\
+	"	.pushsection .text.fixup,\"ax\"\n"		\
 	"	.align	2\n"					\
 	"4:	mov	%0, %3\n"				\
 	"	b	3b\n"					\

arch/arm/include/asm/unified.h

@@ -24,6 +24,14 @@
 	.syntax unified
 #endif
 
+#ifdef CONFIG_CPU_V7M
+#define AR_CLASS(x...)
+#define M_CLASS(x...)	x
+#else
+#define AR_CLASS(x...)	x
+#define M_CLASS(x...)
+#endif
+
 #ifdef CONFIG_THUMB2_KERNEL
 
 #if __GNUC__ < 4