Merge branches 'debug', 'fixes', 'l2c' (early part), 'misc' and 'sa1100' into for-next

Author: Russell King

Documentation/ABI/testing/sysfs-bus-amba

@@ -0,0 +1,20 @@
+What:		/sys/bus/amba/devices/.../driver_override
+Date:		September 2014
+Contact:	Antonios Motakis <[email protected]>
+Description:
+		This file allows the driver for a device to be specified which
+		will override standard OF, ACPI, ID table, and name matching.
+		When specified, only a driver with a name matching the value
+		written to driver_override will have an opportunity to bind to
+		the device. The override is specified by writing a string to the
+		driver_override file (echo vfio-amba > driver_override)	and may
+		be cleared with an empty string (echo > driver_override).
+		This returns the device to standard matching rules binding.
+		Writing to driver_override does not automatically unbind the
+		device from its current driver or make any attempt to
+		automatically load the specified driver. If no driver with a
+		matching name is currently loaded in the kernel, the device will
+		not bind to any driver. This also allows devices to opt-out of
+		driver binding using a driver_override name such as "none".
+		Only a single driver may be specified in the override, there is
+		no support for parsing delimiters.

Documentation/devicetree/bindings/arm/l2cc.txt

@@ -57,6 +57,16 @@ Optional properties:
 - cache-id-part: cache id part number to be used if it is not present
   on hardware
 - wt-override: If present then L2 is forced to Write through mode
+- arm,double-linefill : Override double linefill enable setting. Enable if
+  non-zero, disable if zero.
+- arm,double-linefill-incr : Override double linefill on INCR read. Enable
+  if non-zero, disable if zero.
+- arm,double-linefill-wrap : Override double linefill on WRAP read. Enable
+  if non-zero, disable if zero.
+- arm,prefetch-drop : Override prefetch drop enable setting. Enable if non-zero,
+  disable if zero.
+- arm,prefetch-offset : Override prefetch offset value. Valid values are
+  0-7, 15, 23, and 31.
 
 Example:
 

arch/arm/Kconfig

@@ -29,6 +29,7 @@ config ARM
 	select HANDLE_DOMAIN_IRQ
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
+	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)

arch/arm/boot/compressed/head.S

@@ -178,7 +178,7 @@ not_angel:
 
 		/*
 		 * Set up a page table only if it won't overwrite ourself.
-		 * That means r4 < pc && r4 - 16k page directory > &_end.
+		 * 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.
 		 */
@@ -263,16 +263,37 @@ restart:	adr	r0, LC0
 		 * OK... Let's do some funky business here.
 		 * If we do have a DTB appended to zImage, and we do have
 		 * an ATAG list around, we want the later to be translated
-		 * and folded into the former here.  To be on the safe side,
-		 * let's temporarily move  the stack away into the malloc
-		 * area.  No GOT fixup has occurred yet, but none of the
-		 * code we're about to call uses any global variable.
+		 * and folded into the former here. No GOT fixup has occurred
+		 * yet, but none of the code we're about to call uses any
+		 * global variable.
 		*/
-		add	sp, sp, #0x10000
+
+		/* Get the initial DTB size */
+		ldr	r5, [r6, #4]
+#ifndef __ARMEB__
+		/* convert to little endian */
+		eor	r1, r5, r5, ror #16
+		bic	r1, r1, #0x00ff0000
+		mov	r5, r5, ror #8
+		eor	r5, r5, r1, lsr #8
+#endif
+		/* 50% DTB growth should be good enough */
+		add	r5, r5, r5, lsr #1
+		/* preserve 64-bit alignment */
+		add	r5, r5, #7
+		bic	r5, r5, #7
+		/* clamp to 32KB min and 1MB max */
+		cmp	r5, #(1 << 15)
+		movlo	r5, #(1 << 15)
+		cmp	r5, #(1 << 20)
+		movhi	r5, #(1 << 20)
+		/* temporarily relocate the stack past the DTB work space */
+		add	sp, sp, r5
+
 		stmfd	sp!, {r0-r3, ip, lr}
 		mov	r0, r8
 		mov	r1, r6
-		sub	r2, sp, r6
+		mov	r2, r5
 		bl	atags_to_fdt
 
 		/*
@@ -285,11 +306,11 @@ restart:	adr	r0, LC0
 		bic	r0, r0, #1
 		add	r0, r0, #0x100
 		mov	r1, r6
-		sub	r2, sp, r6
+		mov	r2, r5
 		bleq	atags_to_fdt
 
 		ldmfd	sp!, {r0-r3, ip, lr}
-		sub	sp, sp, #0x10000
+		sub	sp, sp, r5
 #endif
 
 		mov	r8, r6			@ use the appended device tree
@@ -306,7 +327,7 @@ restart:	adr	r0, LC0
 		subs	r1, r5, r1
 		addhi	r9, r9, r1
 
-		/* Get the dtb's size */
+		/* Get the current DTB size */
 		ldr	r5, [r6, #4]
 #ifndef __ARMEB__
 		/* convert r5 (dtb size) to little endian */

arch/arm/boot/dts/exynos4210.dtsi

@@ -81,6 +81,15 @@
 		reg = <0x10023CA0 0x20>;
 	};
 
+	l2c: l2-cache-controller@10502000 {
+		compatible = "arm,pl310-cache";
+		reg = <0x10502000 0x1000>;
+		cache-unified;
+		cache-level = <2>;
+		arm,tag-latency = <2 2 1>;
+		arm,data-latency = <2 2 1>;
+	};
+
 	gic: interrupt-controller@10490000 {
 		cpu-offset = <0x8000>;
 	};

arch/arm/boot/dts/exynos4x12.dtsi

@@ -54,6 +54,20 @@
 		reg = <0x10023CA0 0x20>;
 	};
 
+	l2c: l2-cache-controller@10502000 {
+		compatible = "arm,pl310-cache";
+		reg = <0x10502000 0x1000>;
+		cache-unified;
+		cache-level = <2>;
+		arm,tag-latency = <2 2 1>;
+		arm,data-latency = <3 2 1>;
+		arm,double-linefill = <1>;
+		arm,double-linefill-incr = <0>;
+		arm,double-linefill-wrap = <1>;
+		arm,prefetch-drop = <1>;
+		arm,prefetch-offset = <7>;
+	};
+
 	clock: clock-controller@10030000 {
 		compatible = "samsung,exynos4412-clock";
 		reg = <0x10030000 0x20000>;

arch/arm/include/asm/bitrev.h

@@ -0,0 +1,20 @@
+#ifndef __ASM_BITREV_H
+#define __ASM_BITREV_H
+
+static __always_inline __attribute_const__ u32 __arch_bitrev32(u32 x)
+{
+	__asm__ ("rbit %0, %1" : "=r" (x) : "r" (x));
+	return x;
+}
+
+static __always_inline __attribute_const__ u16 __arch_bitrev16(u16 x)
+{
+	return __arch_bitrev32((u32)x) >> 16;
+}
+
+static __always_inline __attribute_const__ u8 __arch_bitrev8(u8 x)
+{
+	return __arch_bitrev32((u32)x) >> 24;
+}
+
+#endif

arch/arm/include/asm/compiler.h

@@ -8,8 +8,21 @@
  * This string is meant to be concatenated with the inline asm string and
  * will cause compilation to stop on mismatch.
  * (for details, see gcc PR 15089)
+ * For compatibility with clang, we have to specifically take the equivalence
+ * of 'r11' <-> 'fp' and 'r12' <-> 'ip' into account as well.
  */
-#define __asmeq(x, y)  ".ifnc " x "," y " ; .err ; .endif\n\t"
+#define __asmeq(x, y)				\
+	".ifnc " x "," y "; "			\
+	  ".ifnc " x y ",fpr11; " 		\
+	    ".ifnc " x y ",r11fp; "		\
+	      ".ifnc " x y ",ipr12; " 		\
+	        ".ifnc " x y ",r12ip; "		\
+	          ".err; "			\
+	        ".endif; "			\
+	      ".endif; "			\
+	    ".endif; "				\
+	  ".endif; "				\
+	".endif\n\t"
 
 
 #endif /* __ASM_ARM_COMPILER_H */

arch/arm/include/asm/outercache.h

@@ -23,6 +23,8 @@
 
 #include <linux/types.h>
 
+struct l2x0_regs;
+
 struct outer_cache_fns {
 	void (*inv_range)(unsigned long, unsigned long);
 	void (*clean_range)(unsigned long, unsigned long);
@@ -36,6 +38,7 @@ struct outer_cache_fns {
 
 	/* This is an ARM L2C thing */
 	void (*write_sec)(unsigned long, unsigned);
+	void (*configure)(const struct l2x0_regs *);
 };
 
 extern struct outer_cache_fns outer_cache;

arch/arm/include/uapi/asm/unistd.h

@@ -413,6 +413,7 @@
 #define __NR_getrandom			(__NR_SYSCALL_BASE+384)
 #define __NR_memfd_create		(__NR_SYSCALL_BASE+385)
 #define __NR_bpf			(__NR_SYSCALL_BASE+386)
+#define __NR_execveat			(__NR_SYSCALL_BASE+387)
 
 /*
  * The following SWIs are ARM private.

arch/arm/kernel/calls.S

@@ -396,6 +396,7 @@
 		CALL(sys_getrandom)
 /* 385 */	CALL(sys_memfd_create)
 		CALL(sys_bpf)
+		CALL(sys_execveat)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted

arch/arm/kernel/entry-header.S

@@ -253,21 +253,22 @@
 	.endm
 
 	.macro	restore_user_regs, fast = 0, offset = 0
-	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
-	ldr	lr, [sp, #\offset + S_PC]!	@ get pc
+	mov	r2, sp
+	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
+	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
 	msr	spsr_cxsf, r1			@ save in spsr_svc
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
 	@ We must avoid clrex due to Cortex-A15 erratum #830321
-	strex	r1, r2, [sp]			@ clear the exclusive monitor
+	strex	r1, r2, [r2]			@ clear the exclusive monitor
 #endif
 	.if	\fast
-	ldmdb	sp, {r1 - lr}^			@ get calling r1 - lr
+	ldmdb	r2, {r1 - lr}^			@ get calling r1 - lr
 	.else
-	ldmdb	sp, {r0 - lr}^			@ get calling r0 - lr
+	ldmdb	r2, {r0 - lr}^			@ get calling r0 - lr
 	.endif
 	mov	r0, r0				@ ARMv5T and earlier require a nop
 						@ after ldm {}^
-	add	sp, sp, #S_FRAME_SIZE - S_PC
+	add	sp, sp, #\offset + S_FRAME_SIZE
 	movs	pc, lr				@ return & move spsr_svc into cpsr
 	.endm
 

arch/arm/kernel/entry-v7m.S

@@ -22,10 +22,12 @@
 
 __invalid_entry:
 	v7m_exception_entry
+#ifdef CONFIG_PRINTK
 	adr	r0, strerr
 	mrs	r1, ipsr
 	mov	r2, lr
 	bl	printk
+#endif
 	mov	r0, sp
 	bl	show_regs
 1:	b	1b

arch/arm/kernel/head.S

@@ -346,6 +346,12 @@ __turn_mmu_on_loc:
 
 #if defined(CONFIG_SMP)
 	.text
+ENTRY(secondary_startup_arm)
+	.arm
+ THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is entered in ARM.
+ THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
+ THUMB(	.thumb			)	@ switch to Thumb now.
+ THUMB(1:			)
 ENTRY(secondary_startup)
 	/*
 	 * Common entry point for secondary CPUs.
@@ -385,6 +391,7 @@ ENTRY(secondary_startup)
  THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
  THUMB(	ret	r12				)
 ENDPROC(secondary_startup)
+ENDPROC(secondary_startup_arm)
 
 	/*
 	 * r6  = &secondary_data
@@ -586,7 +593,7 @@ __fixup_pv_table:
 	add	r5, r5, r3	@ adjust table end address
 	add	r6, r6, r3	@ adjust __pv_phys_pfn_offset address
 	add	r7, r7, r3	@ adjust __pv_offset address
-	mov	r0, r8, lsr #12	@ convert to PFN
+	mov	r0, r8, lsr #PAGE_SHIFT	@ convert to PFN
 	str	r0, [r6]	@ save computed PHYS_OFFSET to __pv_phys_pfn_offset
 	strcc	ip, [r7, #HIGH_OFFSET]	@ save to __pv_offset high bits
 	mov	r6, r3, lsr #24	@ constant for add/sub instructions

arch/arm/kernel/irq.c

@@ -109,7 +109,8 @@ void __init init_IRQ(void)
 
 	if (IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_CACHE_L2X0) &&
 	    (machine_desc->l2c_aux_mask || machine_desc->l2c_aux_val)) {
-		outer_cache.write_sec = machine_desc->l2c_write_sec;
+		if (!outer_cache.write_sec)
+			outer_cache.write_sec = machine_desc->l2c_write_sec;
 		ret = l2x0_of_init(machine_desc->l2c_aux_val,
 				   machine_desc->l2c_aux_mask);
 		if (ret)

arch/arm/kernel/perf_event.c

@@ -116,8 +116,14 @@ int armpmu_event_set_period(struct perf_event *event)
 		ret = 1;
 	}
 
-	if (left > (s64)armpmu->max_period)
-		left = armpmu->max_period;
+	/*
+	 * Limit the maximum period to prevent the counter value
+	 * from overtaking the one we are about to program. In
+	 * effect we are reducing max_period to account for
+	 * interrupt latency (and we are being very conservative).
+	 */
+	if (left > (armpmu->max_period >> 1))
+		left = armpmu->max_period >> 1;
 
 	local64_set(&hwc->prev_count, (u64)-left);
 

arch/arm/kernel/setup.c

@@ -657,10 +657,13 @@ int __init arm_add_memory(u64 start, u64 size)
 
 	/*
 	 * Ensure that start/size are aligned to a page boundary.
-	 * Size is appropriately rounded down, start is rounded up.
+	 * Size is rounded down, start is rounded up.
 	 */
-	size -= start & ~PAGE_MASK;
 	aligned_start = PAGE_ALIGN(start);
+	if (aligned_start > start + size)
+		size = 0;
+	else
+		size -= aligned_start - start;
 
 #ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT
 	if (aligned_start > ULONG_MAX) {

arch/arm/kernel/suspend.c

@@ -14,10 +14,6 @@ extern int __cpu_suspend(unsigned long, int (*)(unsigned long), u32 cpuid);
 extern void cpu_resume_mmu(void);
 
 #ifdef CONFIG_MMU
-/*
- * Hide the first two arguments to __cpu_suspend - these are an implementation
- * detail which platform code shouldn't have to know about.
- */
 int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 {
 	struct mm_struct *mm = current->active_mm;

arch/arm/lib/Makefile

@@ -15,19 +15,8 @@ lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
 		   io-readsb.o io-writesb.o io-readsl.o io-writesl.o  \
 		   call_with_stack.o bswapsdi2.o
 
-mmu-y	:= clear_user.o copy_page.o getuser.o putuser.o
-
-# the code in uaccess.S is not preemption safe and
-# probably faster on ARMv3 only
-ifeq ($(CONFIG_PREEMPT),y)
-  mmu-y	+= copy_from_user.o copy_to_user.o
-else
-ifneq ($(CONFIG_CPU_32v3),y)
-  mmu-y	+= copy_from_user.o copy_to_user.o
-else
-  mmu-y	+= uaccess.o
-endif
-endif
+mmu-y		:= clear_user.o copy_page.o getuser.o putuser.o       \
+		   copy_from_user.o copy_to_user.o
 
 # using lib_ here won't override already available weak symbols
 obj-$(CONFIG_UACCESS_WITH_MEMCPY) += uaccess_with_memcpy.o