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

Pull ARM updates from Russell King:
 "Included in this update:

   - perf updates from Will Deacon:

     The main changes are callchain stability fixes from Jean Pihet and
     event mapping and PMU name rework from Mark Rutland

     The latter is preparatory work for enabling some code re-use with
     arm64 in the future.

   - updates for nommu from Uwe Kleine-König:

     Two different fixes for the same problem making some ARM nommu
     configurations not boot since 3.6-rc1.  The problem is that
     user_addr_max returned the biggest available RAM address which
     makes some copy_from_user variants fail to read from XIP memory.

   - deprecate legacy OMAP DMA API, in preparation for it's removal.

     The popular drivers have been converted over, leaving a very small
     number of rarely used drivers, which hopefully can be converted
     during the next cycle with a bit more visibility (and hopefully
     people popping out of the woodwork to help test)

   - more tweaks for BE systems, particularly with the kernel image
     format.  In connection with this, I've cleaned up the way we
     generate the linker script for the decompressor.

   - removal of hard-coded assumptions of the kernel stack size, making
     everywhere depend on the value of THREAD_SIZE_ORDER.

   - MCPM updates from Nicolas Pitre.

   - Make it easier for proper CPU part number checks (which should
     always include the vendor field).

   - Assembly code optimisation - use the "bx" instruction when
     returning from a function on ARMv6+ rather than "mov pc, reg".

   - Save the last kernel misaligned fault location and report it via
     the procfs alignment file.

   - Clean up the way we create the initial stack frame, which is a
     repeated pattern in several different locations.

   - Support for 8-byte get_user(), needed for some DRM implementations.

   - mcs locking from Will Deacon.

   - Save and restore a few more Cortex-A9 registers (for errata
     workarounds)

   - Fix various aspects of the SWP emulation, and the ELF hwcap for the
     SWP instruction.

   - Update LPAE logic for pte_write and pmd_write to make it more
     correct.

   - Support for Broadcom Brahma15 CPU cores.

   - ARM assembly crypto updates from Ard Biesheuvel"

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (53 commits)
  ARM: add comments to the early page table remap code
  ARM: 8122/1: smp_scu: enable SCU standby support
  ARM: 8121/1: smp_scu: use macro for SCU enable bit
  ARM: 8120/1: crypto: sha512: add ARM NEON implementation
  ARM: 8119/1: crypto: sha1: add ARM NEON implementation
  ARM: 8118/1: crypto: sha1/make use of common SHA-1 structures
  ARM: 8113/1: remove remaining definitions of PLAT_PHYS_OFFSET from <mach/memory.h>
  ARM: 8111/1: Enable erratum 798181 for Broadcom Brahma-B15
  ARM: 8110/1: do CPU-specific init for Broadcom Brahma15 cores
  ARM: 8109/1: mm: Modify pte_write and pmd_write logic for LPAE
  ARM: 8108/1: mm: Introduce {pte,pmd}_isset and {pte,pmd}_isclear
  ARM: hwcap: disable HWCAP_SWP if the CPU advertises it has exclusives
  ARM: SWP emulation: only initialise on ARMv7 CPUs
  ARM: SWP emulation: always enable when SMP is enabled
  ARM: 8103/1: save/restore Cortex-A9 CP15 registers on suspend/resume
  ARM: 8098/1: mcs lock: implement wfe-based polling for MCS locking
  ARM: 8091/2: add get_user() support for 8 byte types
  ARM: 8097/1: unistd.h: relocate comments back to place
  ARM: 8096/1: Describe required sort order for textofs-y (TEXT_OFFSET)
  ARM: 8090/1: add revision info for PL310 errata 588369 and 727915
  ...

arch/arm/Kconfig

@@ -263,8 +263,22 @@ config NEED_MACH_MEMORY_H
 
 config PHYS_OFFSET
 	hex "Physical address of main memory" if MMU
-	depends on !ARM_PATCH_PHYS_VIRT && !NEED_MACH_MEMORY_H
+	depends on !ARM_PATCH_PHYS_VIRT
 	default DRAM_BASE if !MMU
+	default 0x00000000 if ARCH_EBSA110 || \
+			EP93XX_SDCE3_SYNC_PHYS_OFFSET || \
+			ARCH_FOOTBRIDGE || \
+			ARCH_INTEGRATOR || \
+			ARCH_IOP13XX || \
+			ARCH_KS8695 || \
+			(ARCH_REALVIEW && !REALVIEW_HIGH_PHYS_OFFSET)
+	default 0x10000000 if ARCH_OMAP1 || ARCH_RPC
+	default 0x20000000 if ARCH_S5PV210
+	default 0x70000000 if REALVIEW_HIGH_PHYS_OFFSET
+	default 0xc0000000 if EP93XX_SDCE0_PHYS_OFFSET || ARCH_SA1100
+	default 0xd0000000 if EP93XX_SDCE1_PHYS_OFFSET
+	default 0xe0000000 if EP93XX_SDCE2_PHYS_OFFSET
+	default 0xf0000000 if EP93XX_SDCE3_ASYNC_PHYS_OFFSET
 	help
 	  Please provide the physical address corresponding to the
 	  location of main memory in your system.
@@ -436,7 +450,6 @@ config ARCH_EP93XX
 	select ARM_VIC
 	select CLKDEV_LOOKUP
 	select CPU_ARM920T
-	select NEED_MACH_MEMORY_H
 	help
 	  This enables support for the Cirrus EP93xx series of CPUs.
 

arch/arm/Makefile

@@ -127,6 +127,9 @@ CHECKFLAGS	+= -D__arm__
 
 #Default value
 head-y		:= arch/arm/kernel/head$(MMUEXT).o
+
+# Text offset. This list is sorted numerically by address in order to
+# provide a means to avoid/resolve conflicts in multi-arch kernels.
 textofs-y	:= 0x00008000
 textofs-$(CONFIG_ARCH_CLPS711X) := 0x00028000
 # We don't want the htc bootloader to corrupt kernel during resume

arch/arm/boot/compressed/Makefile

@@ -81,7 +81,7 @@ ZTEXTADDR	:= 0
 ZBSSADDR	:= ALIGN(8)
 endif
 
-SEDFLAGS	= s/TEXT_START/$(ZTEXTADDR)/;s/BSS_START/$(ZBSSADDR)/
+CPPFLAGS_vmlinux.lds := -DTEXT_START="$(ZTEXTADDR)" -DBSS_START="$(ZBSSADDR)"
 
 suffix_$(CONFIG_KERNEL_GZIP) = gzip
 suffix_$(CONFIG_KERNEL_LZO)  = lzo
@@ -199,8 +199,5 @@ CFLAGS_font.o := -Dstatic=
 $(obj)/font.c: $(FONTC)
 	$(call cmd,shipped)
 
-$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile $(KCONFIG_CONFIG)
-	@sed "$(SEDFLAGS)" < $< > $@
-
 $(obj)/hyp-stub.S: $(srctree)/arch/$(SRCARCH)/kernel/hyp-stub.S
 	$(call cmd,shipped)

arch/arm/boot/compressed/head.S

@@ -125,9 +125,11 @@ start:
  THUMB(		adr	r12, BSYM(1f)	)
  THUMB(		bx	r12		)
 
-		.word	0x016f2818		@ Magic numbers to help the loader
-		.word	start			@ absolute load/run zImage address
-		.word	_edata			@ zImage end address
+		.word	_magic_sig	@ Magic numbers to help the loader
+		.word	_magic_start	@ absolute load/run zImage address
+		.word	_magic_end	@ zImage end address
+		.word	0x04030201	@ endianness flag
+
  THUMB(		.thumb			)
 1:
  ARM_BE8(	setend	be )			@ go BE8 if compiled for BE8

arch/arm/boot/compressed/vmlinux.lds.in → arch/arm/boot/compressed/vmlinux.lds.S

@@ -1,12 +1,20 @@
 /*
- *  linux/arch/arm/boot/compressed/vmlinux.lds.in
- *
  *  Copyright (C) 2000 Russell King
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define ZIMAGE_MAGIC(x) ( (((x) >> 24) & 0x000000ff) | \
+			  (((x) >>  8) & 0x0000ff00) | \
+			  (((x) <<  8) & 0x00ff0000) | \
+			  (((x) << 24) & 0xff000000) )
+#else
+#define ZIMAGE_MAGIC(x) (x)
+#endif
+
 OUTPUT_ARCH(arm)
 ENTRY(_start)
 SECTIONS
@@ -57,6 +65,10 @@ SECTIONS
   .pad			: { BYTE(0); . = ALIGN(8); }
   _edata = .;
 
+  _magic_sig = ZIMAGE_MAGIC(0x016f2818);
+  _magic_start = ZIMAGE_MAGIC(_start);
+  _magic_end = ZIMAGE_MAGIC(_edata);
+
   . = BSS_START;
   __bss_start = .;
   .bss			: { *(.bss) }
@@ -73,4 +85,3 @@ SECTIONS
   .stab.indexstr 0	: { *(.stab.indexstr) }
   .comment 0		: { *(.comment) }
 }
-

arch/arm/common/mcpm_entry.c

@@ -12,11 +12,13 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/irqflags.h>
+#include <linux/cpu_pm.h>
 
 #include <asm/mcpm.h>
 #include <asm/cacheflush.h>
 #include <asm/idmap.h>
 #include <asm/cputype.h>
+#include <asm/suspend.h>
 
 extern unsigned long mcpm_entry_vectors[MAX_NR_CLUSTERS][MAX_CPUS_PER_CLUSTER];
 
@@ -146,6 +148,56 @@ int mcpm_cpu_powered_up(void)
 	return 0;
 }
 
+#ifdef CONFIG_ARM_CPU_SUSPEND
+
+static int __init nocache_trampoline(unsigned long _arg)
+{
+	void (*cache_disable)(void) = (void *)_arg;
+	unsigned int mpidr = read_cpuid_mpidr();
+	unsigned int cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	unsigned int cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	phys_reset_t phys_reset;
+
+	mcpm_set_entry_vector(cpu, cluster, cpu_resume);
+	setup_mm_for_reboot();
+
+	__mcpm_cpu_going_down(cpu, cluster);
+	BUG_ON(!__mcpm_outbound_enter_critical(cpu, cluster));
+	cache_disable();
+	__mcpm_outbound_leave_critical(cluster, CLUSTER_DOWN);
+	__mcpm_cpu_down(cpu, cluster);
+
+	phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
+	phys_reset(virt_to_phys(mcpm_entry_point));
+	BUG();
+}
+
+int __init mcpm_loopback(void (*cache_disable)(void))
+{
+	int ret;
+
+	/*
+	 * We're going to soft-restart the current CPU through the
+	 * low-level MCPM code by leveraging the suspend/resume
+	 * infrastructure. Let's play it safe by using cpu_pm_enter()
+	 * in case the CPU init code path resets the VFP or similar.
+	 */
+	local_irq_disable();
+	local_fiq_disable();
+	ret = cpu_pm_enter();
+	if (!ret) {
+		ret = cpu_suspend((unsigned long)cache_disable, nocache_trampoline);
+		cpu_pm_exit();
+	}
+	local_fiq_enable();
+	local_irq_enable();
+	if (ret)
+		pr_err("%s returned %d\n", __func__, ret);
+	return ret;
+}
+
+#endif
+
 struct sync_struct mcpm_sync;
 
 /*

arch/arm/crypto/Makefile

@@ -5,10 +5,14 @@
 obj-$(CONFIG_CRYPTO_AES_ARM) += aes-arm.o
 obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
+obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
+obj-$(CONFIG_CRYPTO_SHA512_ARM_NEON) += sha512-arm-neon.o
 
 aes-arm-y	:= aes-armv4.o aes_glue.o
 aes-arm-bs-y	:= aesbs-core.o aesbs-glue.o
 sha1-arm-y	:= sha1-armv4-large.o sha1_glue.o
+sha1-arm-neon-y	:= sha1-armv7-neon.o sha1_neon_glue.o
+sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o
 
 quiet_cmd_perl = PERL    $@
       cmd_perl = $(PERL) $(<) > $(@)

arch/arm/crypto/aes-armv4.S

@@ -35,6 +35,7 @@
 @ that is being targetted.
 
 #include <linux/linkage.h>
+#include <asm/assembler.h>
 
 .text
 
@@ -648,7 +649,7 @@ _armv4_AES_set_encrypt_key:
 
 .Ldone:	mov	r0,#0
 	ldmia   sp!,{r4-r12,lr}
-.Labrt:	mov	pc,lr
+.Labrt:	ret	lr
 ENDPROC(private_AES_set_encrypt_key)
 
 .align	5