Merge branch 'misc' into devel

Conflicts:
	arch/arm/Kconfig
	arch/arm/common/Makefile
	arch/arm/kernel/Makefile
	arch/arm/kernel/smp.c

6 files changed, 77 insertions, 16 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 4414a01e1e8..8493ed04797 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -599,6 +599,14 @@ config CPU_CP15_MPU
 	help
 	  Processor has the CP15 register, which has MPU related registers.
 
+config CPU_USE_DOMAINS
+	bool
+	depends on MMU
+	default y if !CPU_32v6K
+	help
+	  This option enables or disables the use of domain switching
+	  via the set_fs() function.
+
 #
 # CPU supports 36-bit I/O
 #
@@ -628,6 +636,33 @@ config ARM_THUMBEE
 	  Say Y here if you have a CPU with the ThumbEE extension and code to
 	  make use of it. Say N for code that can run on CPUs without ThumbEE.
 
+config SWP_EMULATE
+	bool "Emulate SWP/SWPB instructions"
+	depends on CPU_V7
+	select HAVE_PROC_CPU if PROC_FS
+	default y if SMP
+	help
+	  ARMv6 architecture deprecates use of the SWP/SWPB instructions.
+	  ARMv7 multiprocessing extensions introduce the ability to disable
+	  these instructions, triggering an undefined instruction exception
+	  when executed. Say Y here to enable software emulation of these
+	  instructions for userspace (not kernel) using LDREX/STREX.
+	  Also creates /proc/cpu/swp_emulation for statistics.
+
+	  In some older versions of glibc [<=2.8] SWP is used during futex
+	  trylock() operations with the assumption that the code will not
+	  be preempted. This invalid assumption may be more likely to fail
+	  with SWP emulation enabled, leading to deadlock of the user
+	  application.
+
+	  NOTE: when accessing uncached shared regions, LDREX/STREX rely
+	  on an external transaction monitoring block called a global
+	  monitor to maintain update atomicity. If your system does not
+	  implement a global monitor, this option can cause programs that
+	  perform SWP operations to uncached memory to deadlock.
+
+	  If unsure, say Y.
+
 config CPU_BIG_ENDIAN
 	bool "Build big-endian kernel"
 	depends on ARCH_SUPPORTS_BIG_ENDIAN
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 809f1bf9fa2..6b48e0a3d7a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -312,7 +312,7 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 		addr = page_address(page);
 
 	if (addr)
-		*handle = page_to_dma(dev, page);
+		*handle = pfn_to_dma(dev, page_to_pfn(page));
 
 	return addr;
 }
@@ -407,7 +407,7 @@ void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr
 	if (!arch_is_coherent())
 		__dma_free_remap(cpu_addr, size);
 
-	__dma_free_buffer(dma_to_page(dev, handle), size);
+	__dma_free_buffer(pfn_to_page(dma_to_pfn(dev, handle)), size);
 }
 EXPORT_SYMBOL(dma_free_coherent);
 
@@ -555,17 +555,20 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	struct scatterlist *s;
 	int i, j;
 
+	BUG_ON(!valid_dma_direction(dir));
+
 	for_each_sg(sg, s, nents, i) {
-		s->dma_address = dma_map_page(dev, sg_page(s), s->offset,
+		s->dma_address = __dma_map_page(dev, sg_page(s), s->offset,
 						s->length, dir);
 		if (dma_mapping_error(dev, s->dma_address))
 			goto bad_mapping;
 	}
+	debug_dma_map_sg(dev, sg, nents, nents, dir);
 	return nents;
 
  bad_mapping:
 	for_each_sg(sg, s, i, j)
-		dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+		__dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
 	return 0;
 }
 EXPORT_SYMBOL(dma_map_sg);
@@ -586,8 +589,10 @@ void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
 	struct scatterlist *s;
 	int i;
 
+	debug_dma_unmap_sg(dev, sg, nents, dir);
+
 	for_each_sg(sg, s, nents, i)
-		dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
+		__dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
 }
 EXPORT_SYMBOL(dma_unmap_sg);
 
@@ -612,6 +617,8 @@ void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 		__dma_page_dev_to_cpu(sg_page(s), s->offset,
 				      s->length, dir);
 	}
+
+	debug_dma_sync_sg_for_cpu(dev, sg, nents, dir);
 }
 EXPORT_SYMBOL(dma_sync_sg_for_cpu);
 
@@ -636,5 +643,16 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 		__dma_page_cpu_to_dev(sg_page(s), s->offset,
 				      s->length, dir);
 	}
+
+	debug_dma_sync_sg_for_device(dev, sg, nents, dir);
 }
 EXPORT_SYMBOL(dma_sync_sg_for_device);
+
+#define PREALLOC_DMA_DEBUG_ENTRIES	4096
+
+static int __init dma_debug_do_init(void)
+{
+	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+	return 0;
+}
+fs_initcall(dma_debug_do_init);
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 55c17a6fb22..ab506272b2d 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -204,12 +204,8 @@ void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	/*
 	 * Don't allow RAM to be mapped - this causes problems with ARMv6+
 	 */
-	if (pfn_valid(pfn)) {
-		printk(KERN_WARNING "BUG: Your driver calls ioremap() on system memory.  This leads\n"
-		       "to architecturally unpredictable behaviour on ARMv6+, and ioremap()\n"
-		       "will fail in the next kernel release.  Please fix your driver.\n");
-		WARN_ON(1);
-	}
+	if (WARN_ON(pfn_valid(pfn)))
+		return NULL;
 
 	type = get_mem_type(mtype);
 	if (!type)
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 72ad3e1f56c..79c01f540cb 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -24,6 +24,7 @@
 #include <asm/smp_plat.h>
 #include <asm/tlb.h>
 #include <asm/highmem.h>
+#include <asm/traps.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -914,12 +915,11 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 {
 	struct map_desc map;
 	unsigned long addr;
-	void *vectors;
 
 	/*
 	 * Allocate the vector page early.
 	 */
-	vectors = early_alloc(PAGE_SIZE);
+	vectors_page = early_alloc(PAGE_SIZE);
 
 	for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
 		pmd_clear(pmd_off_k(addr));
@@ -959,7 +959,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 * location (0xffff0000).  If we aren't using high-vectors, also
 	 * create a mapping at the low-vectors virtual address.
 	 */
-	map.pfn = __phys_to_pfn(virt_to_phys(vectors));
+	map.pfn = __phys_to_pfn(virt_to_phys(vectors_page));
 	map.virtual = 0xffff0000;
 	map.length = PAGE_SIZE;
 	map.type = MT_HIGH_VECTORS;
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index b795afd0a2c..f8f777df8d7 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -109,6 +109,10 @@
  *  110x   0   1   0	r/w	r/o
  *  11x0   0   1   0	r/w	r/o
  *  1111   0   1   1	r/w	r/w
+ *
+ * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed:
+ *  110x   1   1   1	r/o	r/o
+ *  11x0   1   1   1	r/o	r/o
  */
 	.macro	armv6_mt_table pfx
 \pfx\()_mt_table:
@@ -148,8 +152,11 @@
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
+#ifdef CONFIG_CPU_USE_DOMAINS
+	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
 	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
 
 	tst	r1, #L_PTE_EXEC
 	orreq	r3, r3, #PTE_EXT_XN
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 9b9ff5d949f..7401f4d7e67 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -148,8 +148,11 @@ ENTRY(cpu_v7_set_pte_ext)
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
+#ifdef CONFIG_CPU_USE_DOMAINS
+	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
 	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
 
 	tst	r1, #L_PTE_EXEC
 	orreq	r3, r3, #PTE_EXT_XN
@@ -273,8 +276,6 @@ __v7_setup:
 	ALT_SMP(orr	r4, r4, #TTB_FLAGS_SMP)
 	ALT_UP(orr	r4, r4, #TTB_FLAGS_UP)
 	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
-	mov	r10, #0x1f			@ domains 0, 1 = manager
-	mcr	p15, 0, r10, c3, c0, 0		@ load domain access register
 	/*
 	 * Memory region attributes with SCTLR.TRE=1
 	 *
@@ -313,6 +314,10 @@ __v7_setup:
 #ifdef CONFIG_CPU_ENDIAN_BE8
 	orr	r6, r6, #1 << 25		@ big-endian page tables
 #endif
+#ifdef CONFIG_SWP_EMULATE
+	orr     r5, r5, #(1 << 10)              @ set SW bit in "clear"
+	bic     r6, r6, #(1 << 10)              @ clear it in "mmuset"
+#endif
    	mrc	p15, 0, r0, c1, c0, 0		@ read control register
 	bic	r0, r0, r5			@ clear bits them
 	orr	r0, r0, r6			@ set them