Merge branches 'devel-stable', 'fixes' and 'mmci' into for-linus

Documentation/kernel-parameters.txt

@@ -2438,7 +2438,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			real-time workloads.  It can also improve energy
 			efficiency for asymmetric multiprocessors.
 
-	rcu_nocbs_poll	[KNL,BOOT]
+	rcu_nocb_poll	[KNL,BOOT]
 			Rather than requiring that offloaded CPUs
 			(specified by rcu_nocbs= above) explicitly
 			awaken the corresponding "rcuoN" kthreads,

Documentation/x86/boot.txt

@@ -57,7 +57,7 @@ Protocol 2.10:	(Kernel 2.6.31) Added a protocol for relaxed alignment
 Protocol 2.11:	(Kernel 3.6) Added a field for offset of EFI handover
 		protocol entry point.
 
-Protocol 2.12:	(Kernel 3.9) Added the xloadflags field and extension fields
+Protocol 2.12:	(Kernel 3.8) Added the xloadflags field and extension fields
 	 	to struct boot_params for for loading bzImage and ramdisk
 		above 4G in 64bit.
 

MAINTAINERS

@@ -1489,7 +1489,7 @@ AVR32 ARCHITECTURE
 M:	Haavard Skinnemoen <hskinnemoen@gmail.com>
 M:	Hans-Christian Egtvedt <egtvedt@samfundet.no>
 W:	http://www.atmel.com/products/AVR32/
-W:	http://avr32linux.org/
+W:	http://mirror.egtvedt.no/avr32linux.org/
 W:	http://avrfreaks.net/
 S:	Maintained
 F:	arch/avr32/

Makefile

 VERSION = 3
 PATCHLEVEL = 8
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
-NAME = Terrified Chipmunk
+EXTRAVERSION = -rc7
+NAME = Unicycling Gorilla
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"

arch/arm/boot/Makefile

@@ -68,8 +68,8 @@ else
 endif
 
 check_for_multiple_loadaddr = \
-if [ $(words $(UIMAGE_LOADADDR)) -gt 1 ]; then \
-	echo 'multiple load addresses: $(UIMAGE_LOADADDR)'; \
+if [ $(words $(UIMAGE_LOADADDR)) -ne 1 ]; then \
+	echo 'multiple (or no) load addresses: $(UIMAGE_LOADADDR)'; \
 	echo 'This is incompatible with uImages'; \
 	echo 'Specify LOADADDR on the commandline to build an uImage'; \
 	false; \

arch/arm/common/gic.c

@@ -351,6 +351,25 @@ void __init gic_cascade_irq(unsigned int gic_nr, unsigned int irq)
 	irq_set_chained_handler(irq, gic_handle_cascade_irq);
 }
 
+static u8 gic_get_cpumask(struct gic_chip_data *gic)
+{
+	void __iomem *base = gic_data_dist_base(gic);
+	u32 mask, i;
+
+	for (i = mask = 0; i < 32; i += 4) {
+		mask = readl_relaxed(base + GIC_DIST_TARGET + i);
+		mask |= mask >> 16;
+		mask |= mask >> 8;
+		if (mask)
+			break;
+	}
+
+	if (!mask)
+		pr_crit("GIC CPU mask not found - kernel will fail to boot.\n");
+
+	return mask;
+}
+
 static void __init gic_dist_init(struct gic_chip_data *gic)
 {
 	unsigned int i;
@@ -369,7 +388,9 @@ static void __init gic_dist_init(struct gic_chip_data *gic)
 	/*
 	 * Set all global interrupts to this CPU only.
 	 */
-	cpumask = readl_relaxed(base + GIC_DIST_TARGET + 0);
+	cpumask = gic_get_cpumask(gic);
+	cpumask |= cpumask << 8;
+	cpumask |= cpumask << 16;
 	for (i = 32; i < gic_irqs; i += 4)
 		writel_relaxed(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
 
@@ -400,7 +421,7 @@ static void __cpuinit gic_cpu_init(struct gic_chip_data *gic)
 	 * Get what the GIC says our CPU mask is.
 	 */
 	BUG_ON(cpu >= NR_GIC_CPU_IF);
-	cpu_mask = readl_relaxed(dist_base + GIC_DIST_TARGET + 0);
+	cpu_mask = gic_get_cpumask(gic);
 	gic_cpu_map[cpu] = cpu_mask;
 
 	/*

arch/arm/include/asm/delay.h

@@ -24,6 +24,7 @@ extern struct arm_delay_ops {
 	void (*delay)(unsigned long);
 	void (*const_udelay)(unsigned long);
 	void (*udelay)(unsigned long);
+	bool const_clock;
 } arm_delay_ops;
 
 #define __delay(n)		arm_delay_ops.delay(n)

arch/arm/include/asm/memory.h

@@ -37,7 +37,7 @@
  */
 #define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
 #define TASK_SIZE		(UL(CONFIG_PAGE_OFFSET) - UL(0x01000000))
-#define TASK_UNMAPPED_BASE	(UL(CONFIG_PAGE_OFFSET) / 3)
+#define TASK_UNMAPPED_BASE	ALIGN(TASK_SIZE / 3, SZ_16M)
 
 /*
  * The maximum size of a 26-bit user space task.

arch/arm/include/asm/pgtable.h

@@ -247,7 +247,8 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER | L_PTE_NONE;
+	const pteval_t mask = L_PTE_XN | L_PTE_RDONLY | L_PTE_USER |
+		L_PTE_NONE | L_PTE_VALID;
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }

arch/arm/kernel/sched_clock.c

@@ -93,11 +93,11 @@ static void notrace update_sched_clock(void)
 	 * detectable in cyc_to_fixed_sched_clock().
 	 */
 	raw_local_irq_save(flags);
-	cd.epoch_cyc = cyc;
+	cd.epoch_cyc_copy = cyc;
 	smp_wmb();
 	cd.epoch_ns = ns;
 	smp_wmb();
-	cd.epoch_cyc_copy = cyc;
+	cd.epoch_cyc = cyc;
 	raw_local_irq_restore(flags);
 }
 

arch/arm/kernel/smp.c

@@ -686,6 +686,9 @@ static int cpufreq_callback(struct notifier_block *nb,
 	if (freq->flags & CPUFREQ_CONST_LOOPS)
 		return NOTIFY_OK;
 
+	if (arm_delay_ops.const_clock)
+		return NOTIFY_OK;
+
 	if (!per_cpu(l_p_j_ref, cpu)) {
 		per_cpu(l_p_j_ref, cpu) =
 			per_cpu(cpu_data, cpu).loops_per_jiffy;

arch/arm/lib/delay.c

@@ -77,6 +77,7 @@ void __init register_current_timer_delay(const struct delay_timer *timer)
 		arm_delay_ops.delay		= __timer_delay;
 		arm_delay_ops.const_udelay	= __timer_const_udelay;
 		arm_delay_ops.udelay		= __timer_udelay;
+		arm_delay_ops.const_clock	= true;
 		delay_calibrated		= true;
 	} else {
 		pr_info("Ignoring duplicate/late registration of read_current_timer delay\n");

arch/arm/mach-exynos/Kconfig

@@ -414,7 +414,7 @@ config MACH_EXYNOS4_DT
 	select CPU_EXYNOS4210
 	select HAVE_SAMSUNG_KEYPAD if INPUT_KEYBOARD
 	select PINCTRL
-	select PINCTRL_EXYNOS4
+	select PINCTRL_EXYNOS
 	select USE_OF
 	help
 	  Machine support for Samsung Exynos4 machine with device tree enabled.

arch/arm/mach-realview/include/mach/irqs-eb.h

@@ -115,7 +115,7 @@
 /*
  * Only define NR_IRQS if less than NR_IRQS_EB
  */
-#define NR_IRQS_EB		(IRQ_EB_GIC_START + 96)
+#define NR_IRQS_EB		(IRQ_EB_GIC_START + 128)
 
 #if defined(CONFIG_MACH_REALVIEW_EB) \
 	&& (!defined(NR_IRQS) || (NR_IRQS < NR_IRQS_EB))

arch/arm/mm/alignment.c

@@ -749,7 +749,6 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	unsigned long instr = 0, instrptr;
 	int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs);
 	unsigned int type;
-	mm_segment_t fs;
 	unsigned int fault;
 	u16 tinstr = 0;
 	int isize = 4;
@@ -760,16 +759,15 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	instrptr = instruction_pointer(regs);
 
-	fs = get_fs();
-	set_fs(KERNEL_DS);
 	if (thumb_mode(regs)) {
-		fault = __get_user(tinstr, (u16 *)(instrptr & ~1));
+		u16 *ptr = (u16 *)(instrptr & ~1);
+		fault = probe_kernel_address(ptr, tinstr);
 		if (!fault) {
 			if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
 			    IS_T32(tinstr)) {
 				/* Thumb-2 32-bit */
 				u16 tinst2 = 0;
-				fault = __get_user(tinst2, (u16 *)(instrptr+2));
+				fault = probe_kernel_address(ptr + 1, tinst2);
 				instr = (tinstr << 16) | tinst2;
 				thumb2_32b = 1;
 			} else {
@@ -778,8 +776,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 			}
 		}
 	} else
-		fault = __get_user(instr, (u32 *)instrptr);
-	set_fs(fs);
+		fault = probe_kernel_address(instrptr, instr);
 
 	if (fault) {
 		type = TYPE_FAULT;

arch/arm/mm/dma-mapping.c

@@ -640,7 +640,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 
 	if (is_coherent || nommu())
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
-	else if (gfp & GFP_ATOMIC)
+	else if (!(gfp & __GFP_WAIT))
 		addr = __alloc_from_pool(size, &page);
 	else if (!IS_ENABLED(CONFIG_CMA))
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);

arch/arm/vfp/vfphw.S

@@ -22,12 +22,14 @@
 	.macro	DBGSTR, str
 #ifdef DEBUG
 	stmfd	sp!, {r0-r3, ip, lr}
-	add	r0, pc, #4
+	ldr	r0, =1f
 	bl	printk
-	b	1f
-	.asciz  KERN_DEBUG "VFP: \str\n"
-	.balign 4
-1:	ldmfd	sp!, {r0-r3, ip, lr}
+	ldmfd	sp!, {r0-r3, ip, lr}
+
+	.pushsection .rodata, "a"
+1:	.ascii	KERN_DEBUG "VFP: \str\n"
+	.byte	0
+	.previous
 #endif
 	.endm
 
@@ -35,12 +37,14 @@
 #ifdef DEBUG
 	stmfd	sp!, {r0-r3, ip, lr}
 	mov	r1, \arg
-	add	r0, pc, #4
+	ldr	r0, =1f
 	bl	printk
-	b	1f
-	.asciz  KERN_DEBUG "VFP: \str\n"
-	.balign 4
-1:	ldmfd	sp!, {r0-r3, ip, lr}
+	ldmfd	sp!, {r0-r3, ip, lr}
+
+	.pushsection .rodata, "a"
+1:	.ascii	KERN_DEBUG "VFP: \str\n"
+	.byte	0
+	.previous
 #endif
 	.endm
 
@@ -50,12 +54,14 @@
 	mov	r3, \arg3
 	mov	r2, \arg2
 	mov	r1, \arg1
-	add	r0, pc, #4
+	ldr	r0, =1f
 	bl	printk
-	b	1f
-	.asciz  KERN_DEBUG "VFP: \str\n"
-	.balign 4
-1:	ldmfd	sp!, {r0-r3, ip, lr}
+	ldmfd	sp!, {r0-r3, ip, lr}
+
+	.pushsection .rodata, "a"
+1:	.ascii	KERN_DEBUG "VFP: \str\n"
+	.byte	0
+	.previous
 #endif
 	.endm
 

arch/arm/vfp/vfpmodule.c

@@ -413,7 +413,7 @@ void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs)
 	 * If there isn't a second FP instruction, exit now. Note that
 	 * the FPEXC.FP2V bit is valid only if FPEXC.EX is 1.
 	 */
-	if (fpexc ^ (FPEXC_EX | FPEXC_FP2V))
+	if ((fpexc & (FPEXC_EX | FPEXC_FP2V)) != (FPEXC_EX | FPEXC_FP2V))
 		goto exit;
 
 	/*

arch/avr32/include/asm/dma-mapping.h

@@ -336,4 +336,14 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 
+/* drivers/base/dma-mapping.c */
+extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
+extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+				  void *cpu_addr, dma_addr_t dma_addr,
+				  size_t size);
+
+#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
+#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
+
 #endif /* __ASM_AVR32_DMA_MAPPING_H */