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

Pull ARM updates from Russell King:
"These are late by a week; they should have been merged during the
merge window, but unfortunately, the ARM kernel build/boot farms were
indicating random failures, and it wasn't clear whether the cause was
something in these changes or something during the merge window.

This is a set of merge window fixes with some documentation additions"

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm:
ARM: avoid unwanted GCC memset()/memcpy() optimisations for IO variants
ARM: pgtable: document mapping types
ARM: io: convert ioremap*() to functions
ARM: io: fix ioremap_wt() implementation
ARM: io: document ARM specific behaviour of ioremap*() implementations
ARM: fix lockdep unannotated irqs-off warning
ARM: 8397/1: fix vdsomunge not to depend on glibc specific error.h
ARM: add helpful message when truncating physical memory
ARM: add help text for HIGHPTE configuration entry
ARM: fix DEBUG_SET_MODULE_RONX build dependencies
ARM: 8396/1: use phys_addr_t in pfn_to_kaddr()
ARM: 8394/1: update memblock limit after mapping lowmem
ARM: 8393/1: smp: Fix suspicious RCU usage with ipi tracepoints

arch/arm/Kconfig

···
 config HIGHPTE
 	bool "Allocate 2nd-level pagetables from highmem"
 	depends on HIGHMEM
+	help
+	  The VM uses one page of physical memory for each page table.
+	  For systems with a lot of processes, this can use a lot of
+	  precious low memory, eventually leading to low memory being
+	  consumed by page tables.  Setting this option will allow
+	  user-space 2nd level page tables to reside in high memory.
 
 config HW_PERF_EVENTS
 	bool "Enable hardware performance counter support for perf events"

arch/arm/Kconfig.debug

···
 
 config DEBUG_SET_MODULE_RONX
 	bool "Set loadable kernel module data as NX and text as RO"
-	depends on MODULES
+	depends on MODULES && MMU
 	---help---
 	  This option helps catch unintended modifications to loadable
 	  kernel module's text and read-only data. It also prevents execution

arch/arm/include/asm/io.h

···
  * The _caller variety takes a __builtin_return_address(0) value for
  * /proc/vmalloc to use - and should only be used in non-inline functions.
  */
-extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
-	size_t, unsigned int, void *);
 extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int,
 	void *);
-
 extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int);
 extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached);
 extern void __iounmap(volatile void __iomem *addr);
-extern void __arm_iounmap(volatile void __iomem *addr);
 
 extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 	unsigned int, void *);
···
 static inline void memset_io(volatile void __iomem *dst, unsigned c,
 	size_t count)
 {
-	memset((void __force *)dst, c, count);
+	extern void mmioset(void *, unsigned int, size_t);
+	mmioset((void __force *)dst, c, count);
 }
 #define memset_io(dst,c,count) memset_io(dst,c,count)
 
 static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
 	size_t count)
 {
-	memcpy(to, (const void __force *)from, count);
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy(to, (const void __force *)from, count);
 }
 #define memcpy_fromio(to,from,count) memcpy_fromio(to,from,count)
 
 static inline void memcpy_toio(volatile void __iomem *to, const void *from,
 	size_t count)
 {
-	memcpy((void __force *)to, from, count);
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy((void __force *)to, from, count);
 }
 #define memcpy_toio(to,from,count) memcpy_toio(to,from,count)
 
···
 #endif	/* readl */
 
 /*
- * ioremap and friends.
+ * ioremap() and friends.
  *
- * ioremap takes a PCI memory address, as specified in
- * Documentation/io-mapping.txt.
+ * ioremap() takes a resource address, and size.  Due to the ARM memory
+ * types, it is important to use the correct ioremap() function as each
+ * mapping has specific properties.
  *
+ * Function		Memory type	Cacheability	Cache hint
+ * ioremap()		Device		n/a		n/a
+ * ioremap_nocache()	Device		n/a		n/a
+ * ioremap_cache()	Normal		Writeback	Read allocate
+ * ioremap_wc()		Normal		Non-cacheable	n/a
+ * ioremap_wt()		Normal		Non-cacheable	n/a
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
+ * - writes may be delayed before they hit the endpoint device
+ *
+ * ioremap_nocache() is the same as ioremap() as there are too many device
+ * drivers using this for device registers, and documentation which tells
+ * people to use it for such for this to be any different.  This is not a
+ * safe fallback for memory-like mappings, or memory regions where the
+ * compiler may generate unaligned accesses - eg, via inlining its own
+ * memcpy.
+ *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ * - ordering is not guaranteed without explicit dependencies or barrier
+ *   instructions
+ * - writes may be delayed before they hit the endpoint memory
+ *
+ * The cache hint is only a performance hint: CPUs may alias these hints.
+ * Eg, a CPU not implementing read allocate but implementing write allocate
+ * will provide a write allocate mapping instead.
  */
-#define ioremap(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_nocache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_cache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
-#define ioremap_wc(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE_WC)
-#define ioremap_wt(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
-#define iounmap				__arm_iounmap
+void __iomem *ioremap(resource_size_t res_cookie, size_t size);
+#define ioremap ioremap
+#define ioremap_nocache ioremap
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size);
+#define ioremap_cache ioremap_cache
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
+#define ioremap_wc ioremap_wc
+#define ioremap_wt ioremap_wc
+
+void iounmap(volatile void __iomem *iomem_cookie);
+#define iounmap iounmap
 
 /*
  * io{read,write}{16,32}be() macros

arch/arm/include/asm/memory.h

···
  */
 #define __pa(x)			__virt_to_phys((unsigned long)(x))
 #define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
-#define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+#define pfn_to_kaddr(pfn)	__va((phys_addr_t)(pfn) << PAGE_SHIFT)
 
 extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x);
 

arch/arm/include/asm/pgtable-2level.h

···
 
 /*
  * These are the memory types, defined to be compatible with
- * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
+ * pre-ARMv6 CPUs cacheable and bufferable bits: n/a,n/a,C,B
+ * ARMv6+ without TEX remapping, they are a table index.
+ * ARMv6+ with TEX remapping, they correspond to n/a,TEX(0),C,B
+ *
+ * MT type		Pre-ARMv6	ARMv6+ type / cacheable status
+ * UNCACHED		Uncached	Strongly ordered
+ * BUFFERABLE		Bufferable	Normal memory / non-cacheable
+ * WRITETHROUGH		Writethrough	Normal memory / write through
+ * WRITEBACK		Writeback	Normal memory / write back, read alloc
+ * MINICACHE		Minicache	N/A
+ * WRITEALLOC		Writeback	Normal memory / write back, write alloc
+ * DEV_SHARED		Uncached	Device memory (shared)
+ * DEV_NONSHARED	Uncached	Device memory (non-shared)
+ * DEV_WC		Bufferable	Normal memory / non-cacheable
+ * DEV_CACHED		Writeback	Normal memory / write back, read alloc
+ * VECTORS		Variable	Normal memory / variable
+ *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
  */
 #define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
 #define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */

arch/arm/kernel/armksyms.c

···
 
 extern void fpundefinstr(void);
 
+void mmioset(void *, unsigned int, size_t);
+void mmiocpy(void *, const void *, size_t);
+
 	/* platform dependent support */
 EXPORT_SYMBOL(arm_delay_ops);
 
···
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memchr);
 EXPORT_SYMBOL(__memzero);
+
+EXPORT_SYMBOL(mmioset);
+EXPORT_SYMBOL(mmiocpy);
 
 #ifdef CONFIG_MMU
 EXPORT_SYMBOL(copy_page);

arch/arm/kernel/entry-armv.S

···
 	zero_fp
 
 	.if	\trace
-#ifdef CONFIG_IRQSOFF_TRACER
+#ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
 	ct_user_exit save = 0

arch/arm/kernel/smp.c

···
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	if ((unsigned)ipinr < NR_IPI) {
-		trace_ipi_entry(ipi_types[ipinr]);
+		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
 		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
 	}
 
···
 	}
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_exit(ipi_types[ipinr]);
+		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
 	set_irq_regs(old_regs);
 }
 

arch/arm/lib/memcpy.S

···
 
 /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
 
+ENTRY(mmiocpy)
 ENTRY(memcpy)
 
 #include "copy_template.S"
 
 ENDPROC(memcpy)
+ENDPROC(mmiocpy)

arch/arm/lib/memset.S

···
 	.text
 	.align	5
 
+ENTRY(mmioset)
 ENTRY(memset)
 UNWIND( .fnstart         )
 	ands	r3, r0, #3		@ 1 unaligned?
···
 	b	1b
 UNWIND( .fnend   )
 ENDPROC(memset)
+ENDPROC(mmioset)

arch/arm/mm/ioremap.c

···
 }
 #endif
 
-void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
+static void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	unsigned long offset, size_t size, unsigned int mtype, void *caller)
 {
 	const struct mem_type *type;
···
 		  unsigned int mtype)
 {
 	return __arm_ioremap_pfn_caller(pfn, offset, size, mtype,
-			__builtin_return_address(0));
+					__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
···
 				      unsigned int, void *) =
 	__arm_ioremap_caller;
 
-void __iomem *
-__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype)
+void __iomem *ioremap(resource_size_t res_cookie, size_t size)
 {
-	return arch_ioremap_caller(phys_addr, size, mtype,
-		__builtin_return_address(0));
+	return arch_ioremap_caller(res_cookie, size, MT_DEVICE,
+				   __builtin_return_address(0));
 }
-EXPORT_SYMBOL(__arm_ioremap);
+EXPORT_SYMBOL(ioremap);
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size)
+{
+	return arch_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED,
+				   __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
+{
+	return arch_ioremap_caller(res_cookie, size, MT_DEVICE_WC,
+				   __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wc);
 
 /*
  * Remap an arbitrary physical address space into the kernel virtual
···
 
 void (*arch_iounmap)(volatile void __iomem *) = __iounmap;
 
-void __arm_iounmap(volatile void __iomem *io_addr)
+void iounmap(volatile void __iomem *cookie)
 {
-	arch_iounmap(io_addr);
+	arch_iounmap(cookie);
 }
-EXPORT_SYMBOL(__arm_iounmap);
+EXPORT_SYMBOL(iounmap);
 
 #ifdef CONFIG_PCI
 static int pci_ioremap_mem_type = MT_DEVICE;

arch/arm/mm/mmu.c

···
 	int highmem = 0;
 	phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
 	struct memblock_region *reg;
+	bool should_use_highmem = false;
 
 	for_each_memblock(memory, reg) {
 		phys_addr_t block_start = reg->base;
···
 				pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n",
 					  &block_start, &block_end);
 				memblock_remove(reg->base, reg->size);
+				should_use_highmem = true;
 				continue;
 			}
 
···
 					  &block_start, &block_end, &vmalloc_limit);
 				memblock_remove(vmalloc_limit, overlap_size);
 				block_end = vmalloc_limit;
+				should_use_highmem = true;
 			}
 		}
 
···
 
 		}
 	}
+
+	if (should_use_highmem)
+		pr_notice("Consider using a HIGHMEM enabled kernel.\n");
 
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
···
 	build_mem_type_table();
 	prepare_page_table();
 	map_lowmem();
+	memblock_set_current_limit(arm_lowmem_limit);
 	dma_contiguous_remap();
 	devicemaps_init(mdesc);
 	kmap_init();

arch/arm/mm/nommu.c

···
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
-void __iomem *__arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset,
-			   size_t size, unsigned int mtype, void *caller)
-{
-	return __arm_ioremap_pfn(pfn, offset, size, mtype);
-}
-
-void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size,
-			    unsigned int mtype)
-{
-	return (void __iomem *)phys_addr;
-}
-EXPORT_SYMBOL(__arm_ioremap);
-
-void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
-
 void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
-	return __arm_ioremap(phys_addr, size, mtype);
+	return (void __iomem *)phys_addr;
 }
+
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
+
+void __iomem *ioremap(resource_size_t res_cookie, size_t size)
+{
+	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE,
+				    __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap);
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size)
+{
+	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED,
+				    __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
+{
+	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_WC,
+				    __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wc);
+
+void __iounmap(volatile void __iomem *addr)
+{
+}
+EXPORT_SYMBOL(__iounmap);
 
 void (*arch_iounmap)(volatile void __iomem *);
 
-void __arm_iounmap(volatile void __iomem *addr)
+void iounmap(volatile void __iomem *addr)
 {
 }
-EXPORT_SYMBOL(__arm_iounmap);
+EXPORT_SYMBOL(iounmap);

arch/arm/vdso/vdsomunge.c

···
  * it does.
  */
 
-#define _GNU_SOURCE
-
 #include <byteswap.h>
 #include <elf.h>
 #include <errno.h>
-#include <error.h>
 #include <fcntl.h>
+#include <stdarg.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
···
 #define EF_ARM_ABI_FLOAT_HARD 0x400
 #endif
 
+static int failed;
+static const char *argv0;
 static const char *outfile;
+
+static void fail(const char *fmt, ...)
+{
+	va_list ap;
+
+	failed = 1;
+	fprintf(stderr, "%s: ", argv0);
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	exit(EXIT_FAILURE);
+}
 
 static void cleanup(void)
 {
-	if (error_message_count > 0 && outfile != NULL)
+	if (failed && outfile != NULL)
 		unlink(outfile);
 }
 
···
 	int infd;
 
 	atexit(cleanup);
+	argv0 = argv[0];
 
 	if (argc != 3)
-		error(EXIT_FAILURE, 0, "Usage: %s [infile] [outfile]", argv[0]);
+		fail("Usage: %s [infile] [outfile]\n", argv[0]);
 
 	infile = argv[1];
 	outfile = argv[2];
 
 	infd = open(infile, O_RDONLY);
 	if (infd < 0)
-		error(EXIT_FAILURE, errno, "Cannot open %s", infile);
+		fail("Cannot open %s: %s\n", infile, strerror(errno));
 
 	if (fstat(infd, &stat) != 0)
-		error(EXIT_FAILURE, errno, "Failed stat for %s", infile);
+		fail("Failed stat for %s: %s\n", infile, strerror(errno));
 
 	inbuf = mmap(NULL, stat.st_size, PROT_READ, MAP_PRIVATE, infd, 0);
 	if (inbuf == MAP_FAILED)
-		error(EXIT_FAILURE, errno, "Failed to map %s", infile);
+		fail("Failed to map %s: %s\n", infile, strerror(errno));
 
 	close(infd);
 
 	inhdr = inbuf;
 
 	if (memcmp(&inhdr->e_ident, ELFMAG, SELFMAG) != 0)
-		error(EXIT_FAILURE, 0, "Not an ELF file");
+		fail("Not an ELF file\n");
 
 	if (inhdr->e_ident[EI_CLASS] != ELFCLASS32)
-		error(EXIT_FAILURE, 0, "Unsupported ELF class");
+		fail("Unsupported ELF class\n");
 
 	swap = inhdr->e_ident[EI_DATA] != HOST_ORDER;
 
 	if (read_elf_half(inhdr->e_type, swap) != ET_DYN)
-		error(EXIT_FAILURE, 0, "Not a shared object");
+		fail("Not a shared object\n");
 
-	if (read_elf_half(inhdr->e_machine, swap) != EM_ARM) {
-		error(EXIT_FAILURE, 0, "Unsupported architecture %#x",
-		      inhdr->e_machine);
-	}
+	if (read_elf_half(inhdr->e_machine, swap) != EM_ARM)
+		fail("Unsupported architecture %#x\n", inhdr->e_machine);
 
 	e_flags = read_elf_word(inhdr->e_flags, swap);
 
 	if (EF_ARM_EABI_VERSION(e_flags) != EF_ARM_EABI_VER5) {
-		error(EXIT_FAILURE, 0, "Unsupported EABI version %#x",
-		      EF_ARM_EABI_VERSION(e_flags));
+		fail("Unsupported EABI version %#x\n",
+		     EF_ARM_EABI_VERSION(e_flags));
 	}
 
 	if (e_flags & EF_ARM_ABI_FLOAT_HARD)
-		error(EXIT_FAILURE, 0,
-		      "Unexpected hard-float flag set in e_flags");
+		fail("Unexpected hard-float flag set in e_flags\n");
 
 	clear_soft_float = !!(e_flags & EF_ARM_ABI_FLOAT_SOFT);
 
 	outfd = open(outfile, O_RDWR | O_CREAT | O_TRUNC, S_IRUSR | S_IWUSR);
 	if (outfd < 0)
-		error(EXIT_FAILURE, errno, "Cannot open %s", outfile);
+		fail("Cannot open %s: %s\n", outfile, strerror(errno));
 
 	if (ftruncate(outfd, stat.st_size) != 0)
-		error(EXIT_FAILURE, errno, "Cannot truncate %s", outfile);
+		fail("Cannot truncate %s: %s\n", outfile, strerror(errno));
 
 	outbuf = mmap(NULL, stat.st_size, PROT_READ | PROT_WRITE, MAP_SHARED,
 		      outfd, 0);
 	if (outbuf == MAP_FAILED)
-		error(EXIT_FAILURE, errno, "Failed to map %s", outfile);
+		fail("Failed to map %s: %s\n", outfile, strerror(errno));
 
 	close(outfd);
 
···
 	}
 
 	if (msync(outbuf, stat.st_size, MS_SYNC) != 0)
-		error(EXIT_FAILURE, errno, "Failed to sync %s", outfile);
+		fail("Failed to sync %s: %s\n", outfile, strerror(errno));
 
 	return EXIT_SUCCESS;
 }