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, 47 insertions, 17 deletions

diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 2ac37372ef52..b55b1015724b 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -20,6 +20,7 @@
 #include <asm/smp_plat.h>
 #include <asm/thread_notify.h>
 #include <asm/tlbflush.h>
+#include <asm/proc-fns.h>
 
 /*
  * On ARMv6, we have the following structure in the Context ID:
@@ -39,33 +40,51 @@
  * non 64-bit operations.
  */
 #define ASID_FIRST_VERSION	(1ULL << ASID_BITS)
-#define NUM_USER_ASIDS		(ASID_FIRST_VERSION - 1)
-
-#define ASID_TO_IDX(asid)	((asid & ~ASID_MASK) - 1)
-#define IDX_TO_ASID(idx)	((idx + 1) & ~ASID_MASK)
+#define NUM_USER_ASIDS		ASID_FIRST_VERSION
 
 static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
 static atomic64_t asid_generation = ATOMIC64_INIT(ASID_FIRST_VERSION);
 static DECLARE_BITMAP(asid_map, NUM_USER_ASIDS);
 
-DEFINE_PER_CPU(atomic64_t, active_asids);
+static DEFINE_PER_CPU(atomic64_t, active_asids);
 static DEFINE_PER_CPU(u64, reserved_asids);
 static cpumask_t tlb_flush_pending;
 
+#ifdef CONFIG_ARM_ERRATA_798181
+void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
+			     cpumask_t *mask)
+{
+	int cpu;
+	unsigned long flags;
+	u64 context_id, asid;
+
+	raw_spin_lock_irqsave(&cpu_asid_lock, flags);
+	context_id = mm->context.id.counter;
+	for_each_online_cpu(cpu) {
+		if (cpu == this_cpu)
+			continue;
+		/*
+		 * We only need to send an IPI if the other CPUs are
+		 * running the same ASID as the one being invalidated.
+		 */
+		asid = per_cpu(active_asids, cpu).counter;
+		if (asid == 0)
+			asid = per_cpu(reserved_asids, cpu);
+		if (context_id == asid)
+			cpumask_set_cpu(cpu, mask);
+	}
+	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
+}
+#endif
+
 #ifdef CONFIG_ARM_LPAE
 static void cpu_set_reserved_ttbr0(void)
 {
-	unsigned long ttbl = __pa(swapper_pg_dir);
-	unsigned long ttbh = 0;
-
 	/*
 	 * Set TTBR0 to swapper_pg_dir which contains only global entries. The
 	 * ASID is set to 0.
 	 */
-	asm volatile(
-	"	mcrr	p15, 0, %0, %1, c2		@ set TTBR0\n"
-	:
-	: "r" (ttbl), "r" (ttbh));
+	cpu_set_ttbr(0, __pa(swapper_pg_dir));
 	isb();
 }
 #else
@@ -128,7 +147,16 @@ static void flush_context(unsigned int cpu)
 			asid = 0;
 		} else {
 			asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
-			__set_bit(ASID_TO_IDX(asid), asid_map);
+			/*
+			 * If this CPU has already been through a
+			 * rollover, but hasn't run another task in
+			 * the meantime, we must preserve its reserved
+			 * ASID, as this is the only trace we have of
+			 * the process it is still running.
+			 */
+			if (asid == 0)
+				asid = per_cpu(reserved_asids, i);
+			__set_bit(asid & ~ASID_MASK, asid_map);
 		}
 		per_cpu(reserved_asids, i) = asid;
 	}
@@ -167,17 +195,19 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 		/*
 		 * Allocate a free ASID. If we can't find one, take a
 		 * note of the currently active ASIDs and mark the TLBs
-		 * as requiring flushes.
+		 * as requiring flushes. We always count from ASID #1,
+		 * as we reserve ASID #0 to switch via TTBR0 and indicate
+		 * rollover events.
 		 */
-		asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS);
+		asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
 		if (asid == NUM_USER_ASIDS) {
 			generation = atomic64_add_return(ASID_FIRST_VERSION,
 							 &asid_generation);
 			flush_context(cpu);
-			asid = find_first_zero_bit(asid_map, NUM_USER_ASIDS);
+			asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
 		}
 		__set_bit(asid, asid_map);
-		asid = generation | IDX_TO_ASID(asid);
+		asid |= generation;
 		cpumask_clear(mm_cpumask(mm));
 	}