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

Pull ARM updates from Russell King:
 "The major items included in here are:

   - MCPM, multi-cluster power management, part of the infrastructure
     required for ARMs big.LITTLE support.

   - A rework of the ARM KVM code to allow re-use by ARM64.

   - Error handling cleanups of the IS_ERR_OR_NULL() madness and fixes
     of that stuff for arch/arm

   - Preparatory patches for Cortex-M3 support from Uwe Kleine-König.

  There is also a set of three patches in here from Hugh/Catalin to
  address freeing of inappropriate page tables on LPAE.  You already
  have these from akpm, but they were already part of my tree at the
  time he sent them, so unfortunately they'll end up with duplicate
  commits"

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (77 commits)
  ARM: EXYNOS: remove unnecessary use of IS_ERR_VALUE()
  ARM: IMX: remove unnecessary use of IS_ERR_VALUE()
  ARM: OMAP: use consistent error checking
  ARM: cleanup: OMAP hwmod error checking
  ARM: 7709/1: mcpm: Add explicit AFLAGS to support v6/v7 multiplatform kernels
  ARM: 7700/2: Make cpu_init() notrace
  ARM: 7702/1: Set the page table freeing ceiling to TASK_SIZE
  ARM: 7701/1: mm: Allow arch code to control the user page table ceiling
  ARM: 7703/1: Disable preemption in broadcast_tlb*_a15_erratum()
  ARM: mcpm: provide an interface to set the SMP ops at run time
  ARM: mcpm: generic SMP secondary bringup and hotplug support
  ARM: mcpm_head.S: vlock-based first man election
  ARM: mcpm: Add baremetal voting mutexes
  ARM: mcpm: introduce helpers for platform coherency exit/setup
  ARM: mcpm: introduce the CPU/cluster power API
  ARM: multi-cluster PM: secondary kernel entry code
  ARM: cacheflush: add synchronization helpers for mixed cache state accesses
  ARM: cpu hotplug: remove majority of cache flushing from platforms
  ARM: smp: flush L1 cache in cpu_die()
  ARM: tegra: remove tegra specific cpu_disable()
  ...

Documentation/arm/vlocks.txt

@@ -0,0 +1,211 @@
+vlocks for Bare-Metal Mutual Exclusion
+======================================
+
+Voting Locks, or "vlocks" provide a simple low-level mutual exclusion
+mechanism, with reasonable but minimal requirements on the memory
+system.
+
+These are intended to be used to coordinate critical activity among CPUs
+which are otherwise non-coherent, in situations where the hardware
+provides no other mechanism to support this and ordinary spinlocks
+cannot be used.
+
+
+vlocks make use of the atomicity provided by the memory system for
+writes to a single memory location.  To arbitrate, every CPU "votes for
+itself", by storing a unique number to a common memory location.  The
+final value seen in that memory location when all the votes have been
+cast identifies the winner.
+
+In order to make sure that the election produces an unambiguous result
+in finite time, a CPU will only enter the election in the first place if
+no winner has been chosen and the election does not appear to have
+started yet.
+
+
+Algorithm
+---------
+
+The easiest way to explain the vlocks algorithm is with some pseudo-code:
+
+
+	int currently_voting[NR_CPUS] = { 0, };
+	int last_vote = -1; /* no votes yet */
+
+	bool vlock_trylock(int this_cpu)
+	{
+		/* signal our desire to vote */
+		currently_voting[this_cpu] = 1;
+		if (last_vote != -1) {
+			/* someone already volunteered himself */
+			currently_voting[this_cpu] = 0;
+			return false; /* not ourself */
+		}
+
+		/* let's suggest ourself */
+		last_vote = this_cpu;
+		currently_voting[this_cpu] = 0;
+
+		/* then wait until everyone else is done voting */
+		for_each_cpu(i) {
+			while (currently_voting[i] != 0)
+				/* wait */;
+		}
+
+		/* result */
+		if (last_vote == this_cpu)
+			return true; /* we won */
+		return false;
+	}
+
+	bool vlock_unlock(void)
+	{
+		last_vote = -1;
+	}
+
+
+The currently_voting[] array provides a way for the CPUs to determine
+whether an election is in progress, and plays a role analogous to the
+"entering" array in Lamport's bakery algorithm [1].
+
+However, once the election has started, the underlying memory system
+atomicity is used to pick the winner.  This avoids the need for a static
+priority rule to act as a tie-breaker, or any counters which could
+overflow.
+
+As long as the last_vote variable is globally visible to all CPUs, it
+will contain only one value that won't change once every CPU has cleared
+its currently_voting flag.
+
+
+Features and limitations
+------------------------
+
+ * vlocks are not intended to be fair.  In the contended case, it is the
+   _last_ CPU which attempts to get the lock which will be most likely
+   to win.
+
+   vlocks are therefore best suited to situations where it is necessary
+   to pick a unique winner, but it does not matter which CPU actually
+   wins.
+
+ * Like other similar mechanisms, vlocks will not scale well to a large
+   number of CPUs.
+
+   vlocks can be cascaded in a voting hierarchy to permit better scaling
+   if necessary, as in the following hypothetical example for 4096 CPUs:
+
+	/* first level: local election */
+	my_town = towns[(this_cpu >> 4) & 0xf];
+	I_won = vlock_trylock(my_town, this_cpu & 0xf);
+	if (I_won) {
+		/* we won the town election, let's go for the state */
+		my_state = states[(this_cpu >> 8) & 0xf];
+		I_won = vlock_lock(my_state, this_cpu & 0xf));
+		if (I_won) {
+			/* and so on */
+			I_won = vlock_lock(the_whole_country, this_cpu & 0xf];
+			if (I_won) {
+				/* ... */
+			}
+			vlock_unlock(the_whole_country);
+		}
+		vlock_unlock(my_state);
+	}
+	vlock_unlock(my_town);
+
+
+ARM implementation
+------------------
+
+The current ARM implementation [2] contains some optimisations beyond
+the basic algorithm:
+
+ * By packing the members of the currently_voting array close together,
+   we can read the whole array in one transaction (providing the number
+   of CPUs potentially contending the lock is small enough).  This
+   reduces the number of round-trips required to external memory.
+
+   In the ARM implementation, this means that we can use a single load
+   and comparison:
+
+	LDR	Rt, [Rn]
+	CMP	Rt, #0
+
+   ...in place of code equivalent to:
+
+	LDRB	Rt, [Rn]
+	CMP	Rt, #0
+	LDRBEQ	Rt, [Rn, #1]
+	CMPEQ	Rt, #0
+	LDRBEQ	Rt, [Rn, #2]
+	CMPEQ	Rt, #0
+	LDRBEQ	Rt, [Rn, #3]
+	CMPEQ	Rt, #0
+
+   This cuts down on the fast-path latency, as well as potentially
+   reducing bus contention in contended cases.
+
+   The optimisation relies on the fact that the ARM memory system
+   guarantees coherency between overlapping memory accesses of
+   different sizes, similarly to many other architectures.  Note that
+   we do not care which element of currently_voting appears in which
+   bits of Rt, so there is no need to worry about endianness in this
+   optimisation.
+
+   If there are too many CPUs to read the currently_voting array in
+   one transaction then multiple transations are still required.  The
+   implementation uses a simple loop of word-sized loads for this
+   case.  The number of transactions is still fewer than would be
+   required if bytes were loaded individually.
+
+
+   In principle, we could aggregate further by using LDRD or LDM, but
+   to keep the code simple this was not attempted in the initial
+   implementation.
+
+
+ * vlocks are currently only used to coordinate between CPUs which are
+   unable to enable their caches yet.  This means that the
+   implementation removes many of the barriers which would be required
+   when executing the algorithm in cached memory.
+
+   packing of the currently_voting array does not work with cached
+   memory unless all CPUs contending the lock are cache-coherent, due
+   to cache writebacks from one CPU clobbering values written by other
+   CPUs.  (Though if all the CPUs are cache-coherent, you should be
+   probably be using proper spinlocks instead anyway).
+
+
+ * The "no votes yet" value used for the last_vote variable is 0 (not
+   -1 as in the pseudocode).  This allows statically-allocated vlocks
+   to be implicitly initialised to an unlocked state simply by putting
+   them in .bss.
+
+   An offset is added to each CPU's ID for the purpose of setting this
+   variable, so that no CPU uses the value 0 for its ID.
+
+
+Colophon
+--------
+
+Originally created and documented by Dave Martin for Linaro Limited, for
+use in ARM-based big.LITTLE platforms, with review and input gratefully
+received from Nicolas Pitre and Achin Gupta.  Thanks to Nicolas for
+grabbing most of this text out of the relevant mail thread and writing
+up the pseudocode.
+
+Copyright (C) 2012-2013  Linaro Limited
+Distributed under the terms of Version 2 of the GNU General Public
+License, as defined in linux/COPYING.
+
+
+References
+----------
+
+[1] Lamport, L. "A New Solution of Dijkstra's Concurrent Programming
+    Problem", Communications of the ACM 17, 8 (August 1974), 453-455.
+
+    http://en.wikipedia.org/wiki/Lamport%27s_bakery_algorithm
+
+[2] linux/arch/arm/common/vlock.S, www.kernel.org.

arch/arm/Kconfig

@@ -59,6 +59,7 @@ config ARM
 	select CLONE_BACKWARDS
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
+	select HAVE_CONTEXT_TRACKING
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
@@ -1479,6 +1480,14 @@ config HAVE_ARM_TWD
 	help
 	  This options enables support for the ARM timer and watchdog unit
 
+config MCPM
+	bool "Multi-Cluster Power Management"
+	depends on CPU_V7 && SMP
+	help
+	  This option provides the common power management infrastructure
+	  for (multi-)cluster based systems, such as big.LITTLE based
+	  systems.
+
 choice
 	prompt "Memory split"
 	default VMSPLIT_3G
@@ -1565,8 +1574,9 @@ config SCHED_HRTICK
 	def_bool HIGH_RES_TIMERS
 
 config THUMB2_KERNEL
-	bool "Compile the kernel in Thumb-2 mode"
+	bool "Compile the kernel in Thumb-2 mode" if !CPU_THUMBONLY
 	depends on CPU_V7 && !CPU_V6 && !CPU_V6K
+	default y if CPU_THUMBONLY
 	select AEABI
 	select ARM_ASM_UNIFIED
 	select ARM_UNWIND

arch/arm/Kconfig.debug

@@ -641,6 +641,17 @@ config DEBUG_LL_INCLUDE
 	default "debug/zynq.S" if DEBUG_ZYNQ_UART0 || DEBUG_ZYNQ_UART1
 	default "mach/debug-macro.S"
 
+config DEBUG_UNCOMPRESS
+	bool
+	default y if ARCH_MULTIPLATFORM && DEBUG_LL && \
+		     !DEBUG_OMAP2PLUS_UART && \
+		     !DEBUG_TEGRA_UART
+
+config UNCOMPRESS_INCLUDE
+	string
+	default "debug/uncompress.h" if ARCH_MULTIPLATFORM
+	default "mach/uncompress.h"
+
 config EARLY_PRINTK
 	bool "Early printk"
 	depends on DEBUG_LL

arch/arm/boot/compressed/Makefile

@@ -24,6 +24,9 @@ endif
 AFLAGS_head.o += -DTEXT_OFFSET=$(TEXT_OFFSET)
 HEAD	= head.o
 OBJS	+= misc.o decompress.o
+ifeq ($(CONFIG_DEBUG_UNCOMPRESS),y)
+OBJS	+= debug.o
+endif
 FONTC	= $(srctree)/drivers/video/console/font_acorn_8x8.c
 
 # string library code (-Os is enforced to keep it much smaller)

arch/arm/boot/compressed/debug.S

@@ -0,0 +1,12 @@
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+#include CONFIG_DEBUG_LL_INCLUDE
+
+ENTRY(putc)
+	addruart r1, r2, r3
+	waituart r3, r1
+	senduart r0, r1
+	busyuart r3, r1
+	mov	 pc, lr
+ENDPROC(putc)

arch/arm/boot/compressed/misc.c

@@ -25,13 +25,7 @@ unsigned int __machine_arch_type;
 static void putstr(const char *ptr);
 extern void error(char *x);
 
-#ifdef CONFIG_ARCH_MULTIPLATFORM
-static inline void putc(int c) {}
-static inline void flush(void) {}
-static inline void arch_decomp_setup(void) {}
-#else
-#include <mach/uncompress.h>
-#endif
+#include CONFIG_UNCOMPRESS_INCLUDE
 
 #ifdef CONFIG_DEBUG_ICEDCC
 

arch/arm/common/Makefile

@@ -11,3 +11,6 @@ obj-$(CONFIG_SHARP_PARAM)	+= sharpsl_param.o
 obj-$(CONFIG_SHARP_SCOOP)	+= scoop.o
 obj-$(CONFIG_PCI_HOST_ITE8152)  += it8152.o
 obj-$(CONFIG_ARM_TIMER_SP804)	+= timer-sp.o
+obj-$(CONFIG_MCPM)		+= mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
+AFLAGS_mcpm_head.o		:= -march=armv7-a
+AFLAGS_vlock.o			:= -march=armv7-a