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

Pull ARM updates from Russell King:
 "In this set, we have:
   - Refactoring of some of the old StrongARM-1100 GPIO code to make
     things simpler by Dmitry Eremin-Solenikov
   - Read-only and non-executable support for modules on ARM from Laura
     Abbot
   - Removal of unnecessary set_drvdata() calls in AMBA code
   - Some non-executable support for kernel lowmem mappings at the 1MB
     section granularity, and dumping of kernel page tables via debugfs
   - Some improvements for the timer/clock code on Footbridge platforms,
     and cleanup some of the LED code there
   - Fix fls/ffs() signatures to match x86 to prevent build warnings,
     particularly where these are used with min/max() macros
   - Avoid using the bootmem allocator on ARM (patches from Santosh
     Shilimkar)
   - Various asid/unaligned access updates from Will Deacon"

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (51 commits)
  ARM: SMP implementations are not supposed to return from smp_ops.cpu_die()
  ARM: ignore memory below PHYS_OFFSET
  Fix select-induced Kconfig warning for ZBOOT_ROM
  ARM: fix ffs/fls implementations to match x86
  ARM: 7935/1: sa1100: collie: add gpio-keys configuration
  ARM: 7932/1: bcm: Add DEBUG_LL console support
  ARM: 7929/1: Remove duplicate SCHED_HRTICK config option
  ARM: 7928/1: kconfig: select HAVE_EFFICIENT_UNALIGNED_ACCESS for CPUv6+ && MMU
  ARM: 7927/1: dcache: select DCACHE_WORD_ACCESS for big-endian CPUs
  ARM: 7926/1: mm: flesh out and fix the comments in the ASID allocator
  ARM: 7925/1: mm: keep track of last ASID allocation to improve bitmap searching
  ARM: 7924/1: mm: don't bother with reserved ttbr0 when running with LPAE
  ARM: PCI: add legacy IDE IRQ implementation
  ARM: footbridge: cleanup LEDs code
  ARM: pgd allocation: retry on failure
  ARM: footbridge: add one-shot mode for DC21285 timer
  ARM: footbridge: add sched_clock implementation
  ARM: 7922/1: l2x0: add Marvell Tauros3 support
  ARM: 7877/1: use built-in byte swap function
  ARM: 7921/1: mcpm: remove redundant dsb instructions prior to sev
  ...

Documentation/devicetree/bindings/arm/l2cc.txt

@@ -7,20 +7,21 @@ The ARM L2 cache representation in the device tree should be done as follows:
 Required properties:
 
 - compatible : should be one of:
-	"arm,pl310-cache"
-	"arm,l220-cache"
-	"arm,l210-cache"
-	"marvell,aurora-system-cache": Marvell Controller designed to be
+  "arm,pl310-cache"
+  "arm,l220-cache"
+  "arm,l210-cache"
+  "bcm,bcm11351-a2-pl310-cache": DEPRECATED by "brcm,bcm11351-a2-pl310-cache"
+  "brcm,bcm11351-a2-pl310-cache": For Broadcom bcm11351 chipset where an
+     offset needs to be added to the address before passing down to the L2
+     cache controller
+  "marvell,aurora-system-cache": Marvell Controller designed to be
      compatible with the ARM one, with system cache mode (meaning
      maintenance operations on L1 are broadcasted to the L2 and L2
      performs the same operation).
-	"marvell,"aurora-outer-cache: Marvell Controller designed to be
-	 compatible with the ARM one with outer cache mode.
-	"brcm,bcm11351-a2-pl310-cache": For Broadcom bcm11351 chipset where an
-	offset needs to be added to the address before passing down to the L2
-	cache controller
-	"bcm,bcm11351-a2-pl310-cache": DEPRECATED by
-	                               "brcm,bcm11351-a2-pl310-cache"
+  "marvell,aurora-outer-cache": Marvell Controller designed to be
+     compatible with the ARM one with outer cache mode.
+  "marvell,tauros3-cache": Marvell Tauros3 cache controller, compatible
+     with arm,pl310-cache controller.
 - cache-unified : Specifies the cache is a unified cache.
 - cache-level : Should be set to 2 for a level 2 cache.
 - reg : Physical base address and size of cache controller's memory mapped

arch/arm/Kconfig

@@ -6,12 +6,13 @@ config ARM
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT if MMU
 	select CLONE_BACKWARDS
 	select CPU_PM if (SUSPEND || CPU_IDLE)
-	select DCACHE_WORD_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && !CPU_BIG_ENDIAN && MMU
+	select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI)
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
 	select GENERIC_IDLE_POLL_SETUP
@@ -36,6 +37,7 @@ config ARM
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL)
+	select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
 	select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL)
 	select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL)
 	select HAVE_FUNCTION_TRACER if (!XIP_KERNEL)
@@ -63,6 +65,7 @@ config ARM
 	select IRQ_FORCED_THREADING
 	select KTIME_SCALAR
 	select MODULES_USE_ELF_REL
+	select NO_BOOTMEM
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3
 	select PERF_USE_VMALLOC
@@ -1651,9 +1654,6 @@ config HZ
 config SCHED_HRTICK
 	def_bool HIGH_RES_TIMERS
 
-config SCHED_HRTICK
-	def_bool HIGH_RES_TIMERS
-
 config THUMB2_KERNEL
 	bool "Compile the kernel in Thumb-2 mode" if !CPU_THUMBONLY
 	depends on (CPU_V7 || CPU_V7M) && !CPU_V6 && !CPU_V6K
@@ -1934,6 +1934,7 @@ config ZBOOT_ROM_BSS
 config ZBOOT_ROM
 	bool "Compressed boot loader in ROM/flash"
 	depends on ZBOOT_ROM_TEXT != ZBOOT_ROM_BSS
+	depends on !ARM_APPENDED_DTB && !XIP_KERNEL && !AUTO_ZRELADDR
 	help
 	  Say Y here if you intend to execute your compressed kernel image
 	  (zImage) directly from ROM or flash.  If unsure, say N.
@@ -1969,7 +1970,7 @@ endchoice
 
 config ARM_APPENDED_DTB
 	bool "Use appended device tree blob to zImage (EXPERIMENTAL)"
-	depends on OF && !ZBOOT_ROM
+	depends on OF
 	help
 	  With this option, the boot code will look for a device tree binary
 	  (DTB) appended to zImage
@@ -2057,7 +2058,7 @@ endchoice
 
 config XIP_KERNEL
 	bool "Kernel Execute-In-Place from ROM"
-	depends on !ZBOOT_ROM && !ARM_LPAE && !ARCH_MULTIPLATFORM
+	depends on !ARM_LPAE && !ARCH_MULTIPLATFORM
 	help
 	  Execute-In-Place allows the kernel to run from non-volatile storage
 	  directly addressable by the CPU, such as NOR flash. This saves RAM
@@ -2120,7 +2121,6 @@ config CRASH_DUMP
 
 config AUTO_ZRELADDR
 	bool "Auto calculation of the decompressed kernel image address"
-	depends on !ZBOOT_ROM
 	help
 	  ZRELADDR is the physical address where the decompressed kernel
 	  image will be placed. If AUTO_ZRELADDR is selected, the address

arch/arm/Kconfig.debug

@@ -2,6 +2,18 @@ menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
 
+config ARM_PTDUMP
+	bool "Export kernel pagetable layout to userspace via debugfs"
+	depends on DEBUG_KERNEL
+	select DEBUG_FS
+	---help---
+	  Say Y here if you want to show the kernel pagetable layout in a
+	  debugfs file. This information is only useful for kernel developers
+	  who are working in architecture specific areas of the kernel.
+	  It is probably not a good idea to enable this feature in a production
+	  kernel.
+	  If in doubt, say "N"
+
 config STRICT_DEVMEM
 	bool "Filter access to /dev/mem"
 	depends on MMU
@@ -94,6 +106,17 @@ choice
 		depends on ARCH_BCM2835
 		select DEBUG_UART_PL01X
 
+	config DEBUG_BCM_KONA_UART
+		bool "Kernel low-level debugging messages via BCM KONA UART"
+		depends on ARCH_BCM
+		select DEBUG_UART_8250
+		help
+		  Say Y here if you want kernel low-level debugging support
+		  on Broadcom SoC platforms.
+		  This low level debug works for Broadcom
+		  mobile SoCs in the Kona family of chips (e.g. bcm28155,
+		  bcm11351, etc...)
+
 	config DEBUG_CLPS711X_UART1
 		bool "Kernel low-level debugging messages via UART1"
 		depends on ARCH_CLPS711X
@@ -988,6 +1011,7 @@ config DEBUG_UART_PHYS
 	default 0x20064000 if DEBUG_RK29_UART1 || DEBUG_RK3X_UART2
 	default 0x20068000 if DEBUG_RK29_UART2 || DEBUG_RK3X_UART3
 	default 0x20201000 if DEBUG_BCM2835
+	default 0x3e000000 if DEBUG_BCM_KONA_UART
 	default 0x4000e400 if DEBUG_LL_UART_EFM32
 	default 0x40090000 if ARCH_LPC32XX
 	default 0x40100000 if DEBUG_PXA_UART1
@@ -1049,6 +1073,7 @@ config DEBUG_UART_VIRT
 	default 0xfe018000 if DEBUG_MMP_UART3
 	default 0xfe100000 if DEBUG_IMX23_UART || DEBUG_IMX28_UART
 	default 0xfe230000 if DEBUG_PICOXCELL_UART
+	default 0xfe300000 if DEBUG_BCM_KONA_UART
 	default 0xfe800000 if ARCH_IOP32X
 	default 0xfeb00000 if DEBUG_HI3620_UART || DEBUG_HI3716_UART
 	default 0xfeb24000 if DEBUG_RK3X_UART0
@@ -1091,7 +1116,8 @@ config DEBUG_UART_8250_WORD
 	default y if DEBUG_PICOXCELL_UART || DEBUG_SOCFPGA_UART || \
 		ARCH_KEYSTONE || \
 		DEBUG_DAVINCI_DMx_UART0 || DEBUG_DAVINCI_DA8XX_UART1 || \
-		DEBUG_DAVINCI_DA8XX_UART2 || DEBUG_DAVINCI_TNETV107X_UART1
+		DEBUG_DAVINCI_DA8XX_UART2 || DEBUG_DAVINCI_TNETV107X_UART1 || \
+		DEBUG_BCM_KONA_UART
 
 config DEBUG_UART_8250_FLOW_CONTROL
 	bool "Enable flow control for 8250 UART"
@@ -1150,4 +1176,15 @@ config PID_IN_CONTEXTIDR
 	  additional instructions during context switch. Say Y here only if you
 	  are planning to use hardware trace tools with this kernel.
 
+config DEBUG_SET_MODULE_RONX
+	bool "Set loadable kernel module data as NX and text as RO"
+	depends on MODULES
+	---help---
+	  This option helps catch unintended modifications to loadable
+	  kernel module's text and read-only data. It also prevents execution
+	  of module data. Such protection may interfere with run-time code
+	  patching and dynamic kernel tracing - and they might also protect
+	  against certain classes of kernel exploits.
+	  If in doubt, say "N".
+
 endmenu

arch/arm/boot/compressed/Makefile

@@ -108,12 +108,12 @@ endif
 
 targets       := vmlinux vmlinux.lds \
 		 piggy.$(suffix_y) piggy.$(suffix_y).o \
-		 lib1funcs.o lib1funcs.S ashldi3.o ashldi3.S \
-		 font.o font.c head.o misc.o $(OBJS)
+		 lib1funcs.o lib1funcs.S ashldi3.o ashldi3.S bswapsdi2.o \
+		 bswapsdi2.S font.o font.c head.o misc.o $(OBJS)
 
 # Make sure files are removed during clean
 extra-y       += piggy.gzip piggy.lzo piggy.lzma piggy.xzkern piggy.lz4 \
-		 lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs) \
+		 lib1funcs.S ashldi3.S bswapsdi2.S $(libfdt) $(libfdt_hdrs) \
 		 hyp-stub.S
 
 ifeq ($(CONFIG_FUNCTION_TRACER),y)
@@ -156,6 +156,12 @@ ashldi3 = $(obj)/ashldi3.o
 $(obj)/ashldi3.S: $(srctree)/arch/$(SRCARCH)/lib/ashldi3.S
 	$(call cmd,shipped)
 
+# For __bswapsi2, __bswapdi2
+bswapsdi2 = $(obj)/bswapsdi2.o
+
+$(obj)/bswapsdi2.S: $(srctree)/arch/$(SRCARCH)/lib/bswapsdi2.S
+	$(call cmd,shipped)
+
 # We need to prevent any GOTOFF relocs being used with references
 # to symbols in the .bss section since we cannot relocate them
 # independently from the rest at run time.  This can be achieved by
@@ -177,7 +183,8 @@ if [ $(words $(ZRELADDR)) -gt 1 -a "$(CONFIG_AUTO_ZRELADDR)" = "" ]; then \
 fi
 
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \
-		$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) $(ashldi3) FORCE
+		$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) $(ashldi3) \
+		$(bswapsdi2) FORCE
 	@$(check_for_multiple_zreladdr)
 	$(call if_changed,ld)
 	@$(check_for_bad_syms)

arch/arm/common/mcpm_entry.c

@@ -35,8 +35,7 @@ void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
 	unsigned long *poke = &mcpm_entry_early_pokes[cluster][cpu][0];
 	poke[0] = poke_phys_addr;
 	poke[1] = poke_val;
-	__cpuc_flush_dcache_area((void *)poke, 8);
-	outer_clean_range(__pa(poke), __pa(poke + 2));
+	__sync_cache_range_w(poke, 2 * sizeof(*poke));
 }
 
 static const struct mcpm_platform_ops *platform_ops;
@@ -167,7 +166,7 @@ void __mcpm_cpu_down(unsigned int cpu, unsigned int cluster)
 	dmb();
 	mcpm_sync.clusters[cluster].cpus[cpu].cpu = CPU_DOWN;
 	sync_cache_w(&mcpm_sync.clusters[cluster].cpus[cpu].cpu);
-	dsb_sev();
+	sev();
 }
 
 /*
@@ -183,7 +182,7 @@ void __mcpm_outbound_leave_critical(unsigned int cluster, int state)
 	dmb();
 	mcpm_sync.clusters[cluster].cluster = state;
 	sync_cache_w(&mcpm_sync.clusters[cluster].cluster);
-	dsb_sev();
+	sev();
 }
 
 /*

arch/arm/include/asm/bitops.h

@@ -254,25 +254,59 @@ static inline int constant_fls(int x)
 }
 
 /*
- * On ARMv5 and above those functions can be implemented around
- * the clz instruction for much better code efficiency.
+ * On ARMv5 and above those functions can be implemented around the
+ * clz instruction for much better code efficiency.  __clz returns
+ * the number of leading zeros, zero input will return 32, and
+ * 0x80000000 will return 0.
  */
+static inline unsigned int __clz(unsigned int x)
+{
+	unsigned int ret;
+
+	asm("clz\t%0, %1" : "=r" (ret) : "r" (x));
 
+	return ret;
+}
+
+/*
+ * fls() returns zero if the input is zero, otherwise returns the bit
+ * position of the last set bit, where the LSB is 1 and MSB is 32.
+ */
 static inline int fls(int x)
 {
-	int ret;
-
 	if (__builtin_constant_p(x))
 	       return constant_fls(x);
 
-	asm("clz\t%0, %1" : "=r" (ret) : "r" (x));
-       	ret = 32 - ret;
-	return ret;
+	return 32 - __clz(x);
+}
+
+/*
+ * __fls() returns the bit position of the last bit set, where the
+ * LSB is 0 and MSB is 31.  Zero input is undefined.
+ */
+static inline unsigned long __fls(unsigned long x)
+{
+	return fls(x) - 1;
+}
+
+/*
+ * ffs() returns zero if the input was zero, otherwise returns the bit
+ * position of the first set bit, where the LSB is 1 and MSB is 32.
+ */
+static inline int ffs(int x)
+{
+	return fls(x & -x);
+}
+
+/*
+ * __ffs() returns the bit position of the first bit set, where the
+ * LSB is 0 and MSB is 31.  Zero input is undefined.
+ */
+static inline unsigned long __ffs(unsigned long x)
+{
+	return ffs(x) - 1;
 }
 
-#define __fls(x) (fls(x) - 1)
-#define ffs(x) ({ unsigned long __t = (x); fls(__t & -__t); })
-#define __ffs(x) (ffs(x) - 1)
 #define ffz(x) __ffs( ~(x) )
 
 #endif

arch/arm/include/asm/cacheflush.h

@@ -481,4 +481,9 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size)
 	: : : "r0","r1","r2","r3","r4","r5","r6","r7", \
 	      "r9","r10","lr","memory" )
 
+int set_memory_ro(unsigned long addr, int numpages);
+int set_memory_rw(unsigned long addr, int numpages);
+int set_memory_x(unsigned long addr, int numpages);
+int set_memory_nx(unsigned long addr, int numpages);
+
 #endif

arch/arm/include/asm/checksum.h

@@ -87,19 +87,33 @@ static inline __wsum
 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
 		   unsigned short proto, __wsum sum)
 {
-	__asm__(
-	"adds	%0, %1, %2		@ csum_tcpudp_nofold	\n\
-	adcs	%0, %0, %3					\n"
+	u32 lenprot = len | proto << 16;
+	if (__builtin_constant_p(sum) && sum == 0) {
+		__asm__(
+		"adds	%0, %1, %2	@ csum_tcpudp_nofold0	\n\t"
 #ifdef __ARMEB__
-	"adcs	%0, %0, %4					\n"
+		"adcs	%0, %0, %3				\n\t"
 #else
-	"adcs	%0, %0, %4, lsl #8				\n"
+		"adcs	%0, %0, %3, ror #8			\n\t"
 #endif
-	"adcs	%0, %0, %5					\n\
-	adc	%0, %0, #0"
-	: "=&r"(sum)
-	: "r" (sum), "r" (daddr), "r" (saddr), "r" (len), "Ir" (htons(proto))
-	: "cc");
+		"adc	%0, %0, #0"
+		: "=&r" (sum)
+		: "r" (daddr), "r" (saddr), "r" (lenprot)
+		: "cc");
+	} else {
+		__asm__(
+		"adds	%0, %1, %2	@ csum_tcpudp_nofold	\n\t"
+		"adcs	%0, %0, %3				\n\t"
+#ifdef __ARMEB__
+		"adcs	%0, %0, %4				\n\t"
+#else
+		"adcs	%0, %0, %4, ror #8			\n\t"
+#endif
+		"adc	%0, %0, #0"
+		: "=&r"(sum)
+		: "r" (sum), "r" (daddr), "r" (saddr), "r" (lenprot)
+		: "cc");
+	}
 	return sum;
 }	
 /*

arch/arm/include/asm/hardware/cache-l2x0.h

@@ -131,6 +131,7 @@ struct l2x0_regs {
 	unsigned long prefetch_ctrl;
 	unsigned long pwr_ctrl;
 	unsigned long ctrl;
+	unsigned long aux2_ctrl;
 };
 
 extern struct l2x0_regs l2x0_saved_regs;