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, 81 insertions, 1 deletions

diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 1c8278de6c46..9b653278c9e8 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -367,7 +367,7 @@ void __init early_print(const char *str, ...)
 
 static void __init cpuid_init_hwcaps(void)
 {
-	unsigned int divide_instrs;
+	unsigned int divide_instrs, vmsa;
 
 	if (cpu_architecture() < CPU_ARCH_ARMv7)
 		return;
@@ -380,6 +380,11 @@ static void __init cpuid_init_hwcaps(void)
 	case 1:
 		elf_hwcap |= HWCAP_IDIVT;
 	}
+
+	/* LPAE implies atomic ldrd/strd instructions */
+	vmsa = (read_cpuid_ext(CPUID_EXT_MMFR0) & 0xf) >> 0;
+	if (vmsa >= 5)
+		elf_hwcap |= HWCAP_LPAE;
 }
 
 static void __init feat_v6_fixup(void)
@@ -470,9 +475,82 @@ void __init smp_setup_processor_id(void)
 	for (i = 1; i < nr_cpu_ids; ++i)
 		cpu_logical_map(i) = i == cpu ? 0 : i;
 
+	/*
+	 * clear __my_cpu_offset on boot CPU to avoid hang caused by
+	 * using percpu variable early, for example, lockdep will
+	 * access percpu variable inside lock_release
+	 */
+	set_my_cpu_offset(0);
+
 	printk(KERN_INFO "Booting Linux on physical CPU 0x%x\n", mpidr);
 }
 
+struct mpidr_hash mpidr_hash;
+#ifdef CONFIG_SMP
+/**
+ * smp_build_mpidr_hash - Pre-compute shifts required at each affinity
+ *			  level in order to build a linear index from an
+ *			  MPIDR value. Resulting algorithm is a collision
+ *			  free hash carried out through shifting and ORing
+ */
+static void __init smp_build_mpidr_hash(void)
+{
+	u32 i, affinity;
+	u32 fs[3], bits[3], ls, mask = 0;
+	/*
+	 * Pre-scan the list of MPIDRS and filter out bits that do
+	 * not contribute to affinity levels, ie they never toggle.
+	 */
+	for_each_possible_cpu(i)
+		mask |= (cpu_logical_map(i) ^ cpu_logical_map(0));
+	pr_debug("mask of set bits 0x%x\n", mask);
+	/*
+	 * Find and stash the last and first bit set at all affinity levels to
+	 * check how many bits are required to represent them.
+	 */
+	for (i = 0; i < 3; i++) {
+		affinity = MPIDR_AFFINITY_LEVEL(mask, i);
+		/*
+		 * Find the MSB bit and LSB bits position
+		 * to determine how many bits are required
+		 * to express the affinity level.
+		 */
+		ls = fls(affinity);
+		fs[i] = affinity ? ffs(affinity) - 1 : 0;
+		bits[i] = ls - fs[i];
+	}
+	/*
+	 * An index can be created from the MPIDR by isolating the
+	 * significant bits at each affinity level and by shifting
+	 * them in order to compress the 24 bits values space to a
+	 * compressed set of values. This is equivalent to hashing
+	 * the MPIDR through shifting and ORing. It is a collision free
+	 * hash though not minimal since some levels might contain a number
+	 * of CPUs that is not an exact power of 2 and their bit
+	 * representation might contain holes, eg MPIDR[7:0] = {0x2, 0x80}.
+	 */
+	mpidr_hash.shift_aff[0] = fs[0];
+	mpidr_hash.shift_aff[1] = MPIDR_LEVEL_BITS + fs[1] - bits[0];
+	mpidr_hash.shift_aff[2] = 2*MPIDR_LEVEL_BITS + fs[2] -
+						(bits[1] + bits[0]);
+	mpidr_hash.mask = mask;
+	mpidr_hash.bits = bits[2] + bits[1] + bits[0];
+	pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] mask[0x%x] bits[%u]\n",
+				mpidr_hash.shift_aff[0],
+				mpidr_hash.shift_aff[1],
+				mpidr_hash.shift_aff[2],
+				mpidr_hash.mask,
+				mpidr_hash.bits);
+	/*
+	 * 4x is an arbitrary value used to warn on a hash table much bigger
+	 * than expected on most systems.
+	 */
+	if (mpidr_hash_size() > 4 * num_possible_cpus())
+		pr_warn("Large number of MPIDR hash buckets detected\n");
+	sync_cache_w(&mpidr_hash);
+}
+#endif
+
 static void __init setup_processor(void)
 {
 	struct proc_info_list *list;
@@ -820,6 +898,7 @@ void __init setup_arch(char **cmdline_p)
 				smp_set_ops(mdesc->smp);
 		}
 		smp_init_cpus();
+		smp_build_mpidr_hash();
 	}
 #endif
 
@@ -892,6 +971,7 @@ static const char *hwcap_str[] = {
 	"vfpv4",
 	"idiva",
 	"idivt",
+	"lpae",
 	NULL
 };