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
  ...

2 files changed, 68 insertions, 16 deletions

diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c
index aabc02a..d1153c8 100644
--- a/arch/arm/boot/compressed/atags_to_fdt.c
+++ b/arch/arm/boot/compressed/atags_to_fdt.c
@@ -53,6 +53,17 @@ static const void *getprop(const void *fdt, const char *node_path,
 	return fdt_getprop(fdt, offset, property, len);
 }
 
+static uint32_t get_cell_size(const void *fdt)
+{
+	int len;
+	uint32_t cell_size = 1;
+	const uint32_t *size_len =  getprop(fdt, "/", "#size-cells", &len);
+
+	if (size_len)
+		cell_size = fdt32_to_cpu(*size_len);
+	return cell_size;
+}
+
 static void merge_fdt_bootargs(void *fdt, const char *fdt_cmdline)
 {
 	char cmdline[COMMAND_LINE_SIZE];
@@ -95,9 +106,11 @@ static void merge_fdt_bootargs(void *fdt, const char *fdt_cmdline)
 int atags_to_fdt(void *atag_list, void *fdt, int total_space)
 {
 	struct tag *atag = atag_list;
-	uint32_t mem_reg_property[2 * NR_BANKS];
+	/* In the case of 64 bits memory size, need to reserve 2 cells for
+	 * address and size for each bank */
+	uint32_t mem_reg_property[2 * 2 * NR_BANKS];
 	int memcount = 0;
-	int ret;
+	int ret, memsize;
 
 	/* make sure we've got an aligned pointer */
 	if ((u32)atag_list & 0x3)
@@ -137,8 +150,25 @@ int atags_to_fdt(void *atag_list, void *fdt, int total_space)
 				continue;
 			if (!atag->u.mem.size)
 				continue;
-			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.start);
-			mem_reg_property[memcount++] = cpu_to_fdt32(atag->u.mem.size);
+			memsize = get_cell_size(fdt);
+
+			if (memsize == 2) {
+				/* if memsize is 2, that means that
+				 * each data needs 2 cells of 32 bits,
+				 * so the data are 64 bits */
+				uint64_t *mem_reg_prop64 =
+					(uint64_t *)mem_reg_property;
+				mem_reg_prop64[memcount++] =
+					cpu_to_fdt64(atag->u.mem.start);
+				mem_reg_prop64[memcount++] =
+					cpu_to_fdt64(atag->u.mem.size);
+			} else {
+				mem_reg_property[memcount++] =
+					cpu_to_fdt32(atag->u.mem.start);
+				mem_reg_property[memcount++] =
+					cpu_to_fdt32(atag->u.mem.size);
+			}
+
 		} else if (atag->hdr.tag == ATAG_INITRD2) {
 			uint32_t initrd_start, initrd_size;
 			initrd_start = atag->u.initrd.start;
@@ -150,8 +180,10 @@ int atags_to_fdt(void *atag_list, void *fdt, int total_space)
 		}
 	}
 
-	if (memcount)
-		setprop(fdt, "/memory", "reg", mem_reg_property, 4*memcount);
+	if (memcount) {
+		setprop(fdt, "/memory", "reg", mem_reg_property,
+			4 * memcount * memsize);
+	}
 
 	return fdt_pack(fdt);
 }
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 032a8d9..75189f1 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -142,7 +142,6 @@ start:
 		mov	r7, r1			@ save architecture ID
 		mov	r8, r2			@ save atags pointer
 
-#ifndef __ARM_ARCH_2__
 		/*
 		 * Booting from Angel - need to enter SVC mode and disable
 		 * FIQs/IRQs (numeric definitions from angel arm.h source).
@@ -158,10 +157,6 @@ not_angel:
 		safe_svcmode_maskall r0
 		msr	spsr_cxsf, r9		@ Save the CPU boot mode in
 						@ SPSR
-#else
-		teqp	pc, #0x0c000003		@ turn off interrupts
-#endif
-
 		/*
 		 * Note that some cache flushing and other stuff may
 		 * be needed here - is there an Angel SWI call for this?
@@ -183,7 +178,19 @@ not_angel:
 		ldr	r4, =zreladdr
 #endif
 
-		bl	cache_on
+		/*
+		 * Set up a page table only if it won't overwrite ourself.
+		 * That means r4 < pc && r4 - 16k page directory > &_end.
+		 * Given that r4 > &_end is most unfrequent, we add a rough
+		 * additional 1MB of room for a possible appended DTB.
+		 */
+		mov	r0, pc
+		cmp	r0, r4
+		ldrcc	r0, LC0+32
+		addcc	r0, r0, pc
+		cmpcc	r4, r0
+		orrcc	r4, r4, #1		@ remember we skipped cache_on
+		blcs	cache_on
 
 restart:	adr	r0, LC0
 		ldmia	r0, {r1, r2, r3, r6, r10, r11, r12}
@@ -229,7 +236,7 @@ restart:	adr	r0, LC0
  *   r0  = delta
  *   r2  = BSS start
  *   r3  = BSS end
- *   r4  = final kernel address
+ *   r4  = final kernel address (possibly with LSB set)
  *   r5  = appended dtb size (still unknown)
  *   r6  = _edata
  *   r7  = architecture ID
@@ -277,6 +284,7 @@ restart:	adr	r0, LC0
 		 */
 		cmp	r0, #1
 		sub	r0, r4, #TEXT_OFFSET
+		bic	r0, r0, #1
 		add	r0, r0, #0x100
 		mov	r1, r6
 		sub	r2, sp, r6
@@ -323,12 +331,13 @@ dtb_check_done:
 
 /*
  * Check to see if we will overwrite ourselves.
- *   r4  = final kernel address
+ *   r4  = final kernel address (possibly with LSB set)
  *   r9  = size of decompressed image
  *   r10 = end of this image, including  bss/stack/malloc space if non XIP
  * We basically want:
  *   r4 - 16k page directory >= r10 -> OK
  *   r4 + image length <= address of wont_overwrite -> OK
+ * Note: the possible LSB in r4 is harmless here.
  */
 		add	r10, r10, #16384
 		cmp	r4, r10
@@ -390,7 +399,8 @@ dtb_check_done:
 		add	sp, sp, r6
 #endif
 
-		bl	cache_clean_flush
+		tst	r4, #1
+		bleq	cache_clean_flush
 
 		adr	r0, BSYM(restart)
 		add	r0, r0, r6
@@ -402,7 +412,7 @@ wont_overwrite:
  *   r0  = delta
  *   r2  = BSS start
  *   r3  = BSS end
- *   r4  = kernel execution address
+ *   r4  = kernel execution address (possibly with LSB set)
  *   r5  = appended dtb size (0 if not present)
  *   r7  = architecture ID
  *   r8  = atags pointer
@@ -465,6 +475,15 @@ not_relocated:	mov	r0, #0
 		cmp	r2, r3
 		blo	1b
 
+		/*
+		 * Did we skip the cache setup earlier?
+		 * That is indicated by the LSB in r4.
+		 * Do it now if so.
+		 */
+		tst	r4, #1
+		bic	r4, r4, #1
+		blne	cache_on
+
 /*
  * The C runtime environment should now be setup sufficiently.
  * Set up some pointers, and start decompressing.
@@ -513,6 +532,7 @@ LC0:		.word	LC0			@ r1
 		.word	_got_start		@ r11
 		.word	_got_end		@ ip
 		.word	.L_user_stack_end	@ sp
+		.word	_end - restart + 16384 + 1024*1024
 		.size	LC0, . - LC0
 
 #ifdef CONFIG_ARCH_RPC