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

Pull ARM updates from Russell King:
 "This contains the usual updates from other people (listed below) and
  the usual random muddle of miscellaneous ARM updates which cover some
  low priority bug fixes and performance improvements.

  I've started to put the pull request wording into the merge commits,
  which are:

   - NoMMU stuff:

     This includes the following series sent earlier to the list:
      - nommu-fixes
      - R7 Support
      - MPU support

     I've left out the ARCH_MULTIPLATFORM/!MMU stuff that Arnd and I
     were discussing today until we've reached a conclusion/that's had
     some more review.

     This is rebased (and re-tested) on your devel-stable branch because
     otherwise there were going to be conflicts with Uwe's V7M work now
     that you've merged that.  I've included the fix for limiting MPU to
     CPU_V7.

   - Huge page support

     These changes bring both HugeTLB support and Transparent HugePage
     (THP) support to ARM.  Only long descriptors (LPAE) are supported
     in this series.

     The code has been tested on an Arndale board (Exynos 5250).

   - LPAE updates

     Please pull these miscellaneous LPAE fixes I've been collecting for
     a while now for 3.11.  They've been tested and reviewed by quite a
     few people, and most of the patches are pretty trivial.  -- Will Deacon.

   - arch_timer cleanups

     Please pull these arch_timer cleanups I've been holding onto for a
     while.  They're the same as my last posting, but have been rebased
     to v3.10-rc3.

   - mpidr linearisation (multiprocessor id register - identifies which
     CPU number we are in the system)

     This patch series that implements MPIDR linearization through a
     simple hashing algorithm and updates current cpu_{suspend}/{resume}
     code to use the newly created hash structures to retrieve context
     pointers.  It represents a stepping stone for the implementation of
     power management code on forthcoming multi-cluster ARM systems.

     It has been tested on TC2 (dual cluster A15xA7 system), iMX6q,
     OMAP4 and Tegra, with processors hitting low-power states requiring
     warm-boot resume through the cpu_resume code path"

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (77 commits)
  ARM: 7775/1: mm: Remove do_sect_fault from LPAE code
  ARM: 7777/1: Avoid extra calls to the C compiler
  ARM: 7774/1: Fix dtb dependency to use order-only prerequisites
  ARM: 7770/1: remove residual ARMv2 support from decompressor
  ARM: 7769/1: Cortex-A15: fix erratum 798181 implementation
  ARM: 7768/1: prevent risks of out-of-bound access in ASID allocator
  ARM: 7767/1: let the ASID allocator handle suspended animation
  ARM: 7766/1: versatile: don't mark pen as __INIT
  ARM: 7765/1: perf: Record the user-mode PC in the call chain.
  ARM: 7735/2: Preserve the user r/w register TPIDRURW on context switch and fork
  ARM: kernel: implement stack pointer save array through MPIDR hashing
  ARM: kernel: build MPIDR hash function data structure
  ARM: mpu: Ensure that MPU depends on CPU_V7
  ARM: mpu: protect the vectors page with an MPU region
  ARM: mpu: Allow enabling of the MPU via kconfig
  ARM: 7758/1: introduce config HAS_BANDGAP
  ARM: 7757/1: mm: don't flush icache in switch_mm with hardware broadcasting
  ARM: 7751/1: zImage: don't overwrite ourself with a page table
  ARM: 7749/1: spinlock: retry trylock operation if strex fails on free lock
  ARM: 7748/1: oabi: handle faults when loading swi instruction from userspace
  ...

1 files changed, 259 insertions, 4 deletions

diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 5a3aba614a40..1fa50100ab6a 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -8,6 +8,7 @@
 #include <linux/pagemap.h>
 #include <linux/io.h>
 #include <linux/memblock.h>
+#include <linux/kernel.h>
 
 #include <asm/cacheflush.h>
 #include <asm/sections.h>
@@ -15,9 +16,260 @@
 #include <asm/setup.h>
 #include <asm/traps.h>
 #include <asm/mach/arch.h>
+#include <asm/cputype.h>
+#include <asm/mpu.h>
 
 #include "mm.h"
 
+#ifdef CONFIG_ARM_MPU
+struct mpu_rgn_info mpu_rgn_info;
+
+/* Region number */
+static void rgnr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c2, 0" : : "r" (v));
+}
+
+/* Data-side / unified region attributes */
+
+/* Region access control register */
+static void dracr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 4" : : "r" (v));
+}
+
+/* Region size register */
+static void drsr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 2" : : "r" (v));
+}
+
+/* Region base address register */
+static void drbar_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 0" : : "r" (v));
+}
+
+static u32 drbar_read(void)
+{
+	u32 v;
+	asm("mrc        p15, 0, %0, c6, c1, 0" : "=r" (v));
+	return v;
+}
+/* Optional instruction-side region attributes */
+
+/* I-side Region access control register */
+static void iracr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 5" : : "r" (v));
+}
+
+/* I-side Region size register */
+static void irsr_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 3" : : "r" (v));
+}
+
+/* I-side Region base address register */
+static void irbar_write(u32 v)
+{
+	asm("mcr        p15, 0, %0, c6, c1, 1" : : "r" (v));
+}
+
+static unsigned long irbar_read(void)
+{
+	unsigned long v;
+	asm("mrc        p15, 0, %0, c6, c1, 1" : "=r" (v));
+	return v;
+}
+
+/* MPU initialisation functions */
+void __init sanity_check_meminfo_mpu(void)
+{
+	int i;
+	struct membank *bank = meminfo.bank;
+	phys_addr_t phys_offset = PHYS_OFFSET;
+	phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size;
+
+	/* Initially only use memory continuous from PHYS_OFFSET */
+	if (bank_phys_start(&bank[0]) != phys_offset)
+		panic("First memory bank must be contiguous from PHYS_OFFSET");
+
+	/* Banks have already been sorted by start address */
+	for (i = 1; i < meminfo.nr_banks; i++) {
+		if (bank[i].start <= bank_phys_end(&bank[0]) &&
+		    bank_phys_end(&bank[i]) > bank_phys_end(&bank[0])) {
+			bank[0].size = bank_phys_end(&bank[i]) - bank[0].start;
+		} else {
+			pr_notice("Ignoring RAM after 0x%.8lx. "
+			"First non-contiguous (ignored) bank start: 0x%.8lx\n",
+				(unsigned long)bank_phys_end(&bank[0]),
+				(unsigned long)bank_phys_start(&bank[i]));
+			break;
+		}
+	}
+	/* All contiguous banks are now merged in to the first bank */
+	meminfo.nr_banks = 1;
+	specified_mem_size = bank[0].size;
+
+	/*
+	 * MPU has curious alignment requirements: Size must be power of 2, and
+	 * region start must be aligned to the region size
+	 */
+	if (phys_offset != 0)
+		pr_info("PHYS_OFFSET != 0 => MPU Region size constrained by alignment requirements\n");
+
+	/*
+	 * Maximum aligned region might overflow phys_addr_t if phys_offset is
+	 * 0. Hence we keep everything below 4G until we take the smaller of
+	 * the aligned_region_size and rounded_mem_size, one of which is
+	 * guaranteed to be smaller than the maximum physical address.
+	 */
+	aligned_region_size = (phys_offset - 1) ^ (phys_offset);
+	/* Find the max power-of-two sized region that fits inside our bank */
+	rounded_mem_size = (1 <<  __fls(bank[0].size)) - 1;
+
+	/* The actual region size is the smaller of the two */
+	aligned_region_size = aligned_region_size < rounded_mem_size
+				? aligned_region_size + 1
+				: rounded_mem_size + 1;
+
+	if (aligned_region_size != specified_mem_size)
+		pr_warn("Truncating memory from 0x%.8lx to 0x%.8lx (MPU region constraints)",
+				(unsigned long)specified_mem_size,
+				(unsigned long)aligned_region_size);
+
+	meminfo.bank[0].size = aligned_region_size;
+	pr_debug("MPU Region from 0x%.8lx size 0x%.8lx (end 0x%.8lx))\n",
+		(unsigned long)phys_offset,
+		(unsigned long)aligned_region_size,
+		(unsigned long)bank_phys_end(&bank[0]));
+
+}
+
+static int mpu_present(void)
+{
+	return ((read_cpuid_ext(CPUID_EXT_MMFR0) & MMFR0_PMSA) == MMFR0_PMSAv7);
+}
+
+static int mpu_max_regions(void)
+{
+	/*
+	 * We don't support a different number of I/D side regions so if we
+	 * have separate instruction and data memory maps then return
+	 * whichever side has a smaller number of supported regions.
+	 */
+	u32 dregions, iregions, mpuir;
+	mpuir = read_cpuid(CPUID_MPUIR);
+
+	dregions = iregions = (mpuir & MPUIR_DREGION_SZMASK) >> MPUIR_DREGION;
+
+	/* Check for separate d-side and i-side memory maps */
+	if (mpuir & MPUIR_nU)
+		iregions = (mpuir & MPUIR_IREGION_SZMASK) >> MPUIR_IREGION;
+
+	/* Use the smallest of the two maxima */
+	return min(dregions, iregions);
+}
+
+static int mpu_iside_independent(void)
+{
+	/* MPUIR.nU specifies whether there is *not* a unified memory map */
+	return read_cpuid(CPUID_MPUIR) & MPUIR_nU;
+}
+
+static int mpu_min_region_order(void)
+{
+	u32 drbar_result, irbar_result;
+	/* We've kept a region free for this probing */
+	rgnr_write(MPU_PROBE_REGION);
+	isb();
+	/*
+	 * As per ARM ARM, write 0xFFFFFFFC to DRBAR to find the minimum
+	 * region order
+	*/
+	drbar_write(0xFFFFFFFC);
+	drbar_result = irbar_result = drbar_read();
+	drbar_write(0x0);
+	/* If the MPU is non-unified, we use the larger of the two minima*/
+	if (mpu_iside_independent()) {
+		irbar_write(0xFFFFFFFC);
+		irbar_result = irbar_read();
+		irbar_write(0x0);
+	}
+	isb(); /* Ensure that MPU region operations have completed */
+	/* Return whichever result is larger */
+	return __ffs(max(drbar_result, irbar_result));
+}
+
+static int mpu_setup_region(unsigned int number, phys_addr_t start,
+			unsigned int size_order, unsigned int properties)
+{
+	u32 size_data;
+
+	/* We kept a region free for probing resolution of MPU regions*/
+	if (number > mpu_max_regions() || number == MPU_PROBE_REGION)
+		return -ENOENT;
+
+	if (size_order > 32)
+		return -ENOMEM;
+
+	if (size_order < mpu_min_region_order())
+		return -ENOMEM;
+
+	/* Writing N to bits 5:1 (RSR_SZ)  specifies region size 2^N+1 */
+	size_data = ((size_order - 1) << MPU_RSR_SZ) | 1 << MPU_RSR_EN;
+
+	dsb(); /* Ensure all previous data accesses occur with old mappings */
+	rgnr_write(number);
+	isb();
+	drbar_write(start);
+	dracr_write(properties);
+	isb(); /* Propagate properties before enabling region */
+	drsr_write(size_data);
+
+	/* Check for independent I-side registers */
+	if (mpu_iside_independent()) {
+		irbar_write(start);
+		iracr_write(properties);
+		isb();
+		irsr_write(size_data);
+	}
+	isb();
+
+	/* Store region info (we treat i/d side the same, so only store d) */
+	mpu_rgn_info.rgns[number].dracr = properties;
+	mpu_rgn_info.rgns[number].drbar = start;
+	mpu_rgn_info.rgns[number].drsr = size_data;
+	return 0;
+}
+
+/*
+* Set up default MPU regions, doing nothing if there is no MPU
+*/
+void __init mpu_setup(void)
+{
+	int region_err;
+	if (!mpu_present())
+		return;
+
+	region_err = mpu_setup_region(MPU_RAM_REGION, PHYS_OFFSET,
+					ilog2(meminfo.bank[0].size),
+					MPU_AP_PL1RW_PL0RW | MPU_RGN_NORMAL);
+	if (region_err) {
+		panic("MPU region initialization failure! %d", region_err);
+	} else {
+		pr_info("Using ARMv7 PMSA Compliant MPU. "
+			 "Region independence: %s, Max regions: %d\n",
+			mpu_iside_independent() ? "Yes" : "No",
+			mpu_max_regions());
+	}
+}
+#else
+static void sanity_check_meminfo_mpu(void) {}
+static void __init mpu_setup(void) {}
+#endif /* CONFIG_ARM_MPU */
+
 void __init arm_mm_memblock_reserve(void)
 {
 #ifndef CONFIG_CPU_V7M
@@ -37,7 +289,9 @@ void __init arm_mm_memblock_reserve(void)
 
 void __init sanity_check_meminfo(void)
 {
-	phys_addr_t end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]);
+	phys_addr_t end;
+	sanity_check_meminfo_mpu();
+	end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]);
 	high_memory = __va(end - 1) + 1;
 }
 
@@ -48,6 +302,7 @@ void __init sanity_check_meminfo(void)
 void __init paging_init(struct machine_desc *mdesc)
 {
 	early_trap_init((void *)CONFIG_VECTORS_BASE);
+	mpu_setup();
 	bootmem_init();
 }
 
@@ -94,16 +349,16 @@ void __iomem *__arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset,
 	return __arm_ioremap_pfn(pfn, offset, size, mtype);
 }
 
-void __iomem *__arm_ioremap(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size,
 			    unsigned int mtype)
 {
 	return (void __iomem *)phys_addr;
 }
 EXPORT_SYMBOL(__arm_ioremap);
 
-void __iomem * (*arch_ioremap_caller)(unsigned long, size_t, unsigned int, void *);
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
 
-void __iomem *__arm_ioremap_caller(unsigned long phys_addr, size_t size,
+void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
 	return __arm_ioremap(phys_addr, size, mtype);