Merge tag 'v4.6-rc3' into perf/core, to refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

14 files changed, 410 insertions, 94 deletions

diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 871b8267d211..27d05813ff09 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -170,41 +170,11 @@ int main(void)
   DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE);
   BLANK();
 #ifdef CONFIG_KVM_ARM_HOST
-  DEFINE(VCPU_KVM,		offsetof(struct kvm_vcpu, kvm));
-  DEFINE(VCPU_MIDR,		offsetof(struct kvm_vcpu, arch.midr));
-  DEFINE(VCPU_CP15,		offsetof(struct kvm_vcpu, arch.cp15));
-  DEFINE(VCPU_VFP_GUEST,	offsetof(struct kvm_vcpu, arch.vfp_guest));
-  DEFINE(VCPU_VFP_HOST,		offsetof(struct kvm_vcpu, arch.host_cpu_context));
-  DEFINE(VCPU_REGS,		offsetof(struct kvm_vcpu, arch.regs));
-  DEFINE(VCPU_USR_REGS,		offsetof(struct kvm_vcpu, arch.regs.usr_regs));
-  DEFINE(VCPU_SVC_REGS,		offsetof(struct kvm_vcpu, arch.regs.svc_regs));
-  DEFINE(VCPU_ABT_REGS,		offsetof(struct kvm_vcpu, arch.regs.abt_regs));
-  DEFINE(VCPU_UND_REGS,		offsetof(struct kvm_vcpu, arch.regs.und_regs));
-  DEFINE(VCPU_IRQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.irq_regs));
-  DEFINE(VCPU_FIQ_REGS,		offsetof(struct kvm_vcpu, arch.regs.fiq_regs));
-  DEFINE(VCPU_PC,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_pc));
-  DEFINE(VCPU_CPSR,		offsetof(struct kvm_vcpu, arch.regs.usr_regs.ARM_cpsr));
-  DEFINE(VCPU_HCR,		offsetof(struct kvm_vcpu, arch.hcr));
-  DEFINE(VCPU_IRQ_LINES,	offsetof(struct kvm_vcpu, arch.irq_lines));
-  DEFINE(VCPU_HSR,		offsetof(struct kvm_vcpu, arch.fault.hsr));
-  DEFINE(VCPU_HxFAR,		offsetof(struct kvm_vcpu, arch.fault.hxfar));
-  DEFINE(VCPU_HPFAR,		offsetof(struct kvm_vcpu, arch.fault.hpfar));
-  DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.fault.hyp_pc));
-  DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
-  DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
-  DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
-  DEFINE(VGIC_V2_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
-  DEFINE(VGIC_V2_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_eisr));
-  DEFINE(VGIC_V2_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
-  DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
-  DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
-  DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
-  DEFINE(VCPU_TIMER_CNTV_CTL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));
-  DEFINE(VCPU_TIMER_CNTV_CVAL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval));
-  DEFINE(KVM_TIMER_CNTVOFF,	offsetof(struct kvm, arch.timer.cntvoff));
-  DEFINE(KVM_TIMER_ENABLED,	offsetof(struct kvm, arch.timer.enabled));
-  DEFINE(KVM_VGIC_VCTRL,	offsetof(struct kvm, arch.vgic.vctrl_base));
-  DEFINE(KVM_VTTBR,		offsetof(struct kvm, arch.vttbr));
+  DEFINE(VCPU_GUEST_CTXT,	offsetof(struct kvm_vcpu, arch.ctxt));
+  DEFINE(VCPU_HOST_CTXT,	offsetof(struct kvm_vcpu, arch.host_cpu_context));
+  DEFINE(CPU_CTXT_VFP,		offsetof(struct kvm_cpu_context, vfp));
+  DEFINE(CPU_CTXT_GP_REGS,	offsetof(struct kvm_cpu_context, gp_regs));
+  DEFINE(GP_REGS_USR,		offsetof(struct kvm_regs, usr_regs));
 #endif
   BLANK();
 #ifdef CONFIG_VDSO
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index dfc7cd6851ad..703fa0f3cd8f 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -399,8 +399,10 @@
 		CALL(sys_execveat)
 		CALL(sys_userfaultfd)
 		CALL(sys_membarrier)
-		CALL(sys_mlock2)
+/* 390 */	CALL(sys_mlock2)
 		CALL(sys_copy_file_range)
+		CALL(sys_preadv2)
+		CALL(sys_pwritev2)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 3ce377f7251f..e2550500486d 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -1064,7 +1064,6 @@ ENDPROC(vector_\name)
 	.endm
 
 	.section .stubs, "ax", %progbits
-__stubs_start:
 	@ This must be the first word
 	.word	vector_swi
 
@@ -1202,14 +1201,13 @@ vector_addrexcptn:
 	.long	__fiq_svc			@  e
 	.long	__fiq_svc			@  f
 
-	.globl	vector_fiq_offset
-	.equ	vector_fiq_offset, vector_fiq
+	.globl	vector_fiq
 
 	.section .vectors, "ax", %progbits
-__vectors_start:
+.L__vectors_start:
 	W(b)	vector_rst
 	W(b)	vector_und
-	W(ldr)	pc, __vectors_start + 0x1000
+	W(ldr)	pc, .L__vectors_start + 0x1000
 	W(b)	vector_pabt
 	W(b)	vector_dabt
 	W(b)	vector_addrexcptn
diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c
index a71501ff6f18..b09561a6d06a 100644
--- a/arch/arm/kernel/hibernate.c
+++ b/arch/arm/kernel/hibernate.c
@@ -62,7 +62,7 @@ static int notrace arch_save_image(unsigned long unused)
 
 	ret = swsusp_save();
 	if (ret == 0)
-		_soft_restart(virt_to_phys(cpu_resume), false);
+		_soft_restart(virt_to_idmap(cpu_resume), false);
 	return ret;
 }
 
@@ -87,7 +87,7 @@ static void notrace arch_restore_image(void *unused)
 	for (pbe = restore_pblist; pbe; pbe = pbe->next)
 		copy_page(pbe->orig_address, pbe->address);
 
-	_soft_restart(virt_to_phys(cpu_resume), false);
+	_soft_restart(virt_to_idmap(cpu_resume), false);
 }
 
 static u64 resume_stack[PAGE_SIZE/2/sizeof(u64)] __nosavedata;
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index 2a55373f49bf..0b1e4a93d67e 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -17,6 +17,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/irqchip/arm-gic-v3.h>
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 #include <asm/virt.h>
@@ -161,6 +162,29 @@ ARM_BE8(orr	r7, r7, #(1 << 25))     @ HSCTLR.EE
 1:
 #endif
 
+#ifdef CONFIG_ARM_GIC_V3
+	@ Check whether GICv3 system registers are available
+	mrc	p15, 0, r7, c0, c1, 1	@ ID_PFR1
+	ubfx	r7, r7, #28, #4
+	cmp	r7, #1
+	bne	2f
+
+	@ Enable system register accesses
+	mrc	p15, 4, r7, c12, c9, 5	@ ICC_HSRE
+	orr	r7, r7, #(ICC_SRE_EL2_ENABLE | ICC_SRE_EL2_SRE)
+	mcr	p15, 4, r7, c12, c9, 5	@ ICC_HSRE
+	isb
+
+	@ SRE bit could be forced to 0 by firmware.
+	@ Check whether it sticks before accessing any other sysreg
+	mrc	p15, 4, r7, c12, c9, 5	@ ICC_HSRE
+	tst	r7, #ICC_SRE_EL2_SRE
+	beq	2f
+	mov	r7, #0
+	mcr	p15, 4, r7, c12, c11, 0	@ ICH_HCR
+2:
+#endif
+
 	bx	lr			@ The boot CPU mode is left in r4.
 ENDPROC(__hyp_stub_install_secondary)
 
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 1d45320ee125..ece04a457486 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -95,7 +95,7 @@ void __init init_IRQ(void)
 			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)
+		if (ret && ret != -ENODEV)
 			pr_err("L2C: failed to init: %d\n", ret);
 	}
 
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 8bf3b7c09888..59fd0e24c56b 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -143,10 +143,8 @@ void (*kexec_reinit)(void);
 
 void machine_kexec(struct kimage *image)
 {
-	unsigned long page_list;
-	unsigned long reboot_code_buffer_phys;
-	unsigned long reboot_entry = (unsigned long)relocate_new_kernel;
-	unsigned long reboot_entry_phys;
+	unsigned long page_list, reboot_entry_phys;
+	void (*reboot_entry)(void);
 	void *reboot_code_buffer;
 
 	/*
@@ -159,9 +157,6 @@ void machine_kexec(struct kimage *image)
 
 	page_list = image->head & PAGE_MASK;
 
-	/* we need both effective and real address here */
-	reboot_code_buffer_phys =
-	    page_to_pfn(image->control_code_page) << PAGE_SHIFT;
 	reboot_code_buffer = page_address(image->control_code_page);
 
 	/* Prepare parameters for reboot_code_buffer*/
@@ -174,10 +169,11 @@ void machine_kexec(struct kimage *image)
 
 	/* copy our kernel relocation code to the control code page */
 	reboot_entry = fncpy(reboot_code_buffer,
-			     reboot_entry,
+			     &relocate_new_kernel,
 			     relocate_new_kernel_size);
-	reboot_entry_phys = (unsigned long)reboot_entry +
-		(reboot_code_buffer_phys - (unsigned long)reboot_code_buffer);
+
+	/* get the identity mapping physical address for the reboot code */
+	reboot_entry_phys = virt_to_idmap(reboot_entry);
 
 	pr_info("Bye!\n");
 
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index efdddcb97dd1..4f14b5ce6535 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -34,7 +34,7 @@
  * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off.
  */
 #undef MODULES_VADDR
-#define MODULES_VADDR	(((unsigned long)_etext + ~PMD_MASK) & PMD_MASK)
+#define MODULES_VADDR	(((unsigned long)_exiprom + ~PMD_MASK) & PMD_MASK)
 #endif
 
 #ifdef CONFIG_MMU
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 4152158f6e6a..15063851cd10 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -712,6 +712,11 @@ static const struct attribute_group *armv7_pmuv2_attr_groups[] = {
 #define	ARMV7_EXCLUDE_USER	(1 << 30)
 #define	ARMV7_INCLUDE_HYP	(1 << 27)
 
+/*
+ * Secure debug enable reg
+ */
+#define ARMV7_SDER_SUNIDEN	BIT(1) /* Permit non-invasive debug */
+
 static inline u32 armv7_pmnc_read(void)
 {
 	u32 val;
@@ -1094,7 +1099,13 @@ static int armv7pmu_set_event_filter(struct hw_perf_event *event,
 static void armv7pmu_reset(void *info)
 {
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
-	u32 idx, nb_cnt = cpu_pmu->num_events;
+	u32 idx, nb_cnt = cpu_pmu->num_events, val;
+
+	if (cpu_pmu->secure_access) {
+		asm volatile("mrc p15, 0, %0, c1, c1, 1" : "=r" (val));
+		val |= ARMV7_SDER_SUNIDEN;
+		asm volatile("mcr p15, 0, %0, c1, c1, 1" : : "r" (val));
+	}
 
 	/* The counter and interrupt enable registers are unknown at reset. */
 	for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) {
diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c
index 38269358fd25..71a2ff9ec490 100644
--- a/arch/arm/kernel/reboot.c
+++ b/arch/arm/kernel/reboot.c
@@ -50,7 +50,7 @@ static void __soft_restart(void *addr)
 	flush_cache_all();
 
 	/* Switch to the identity mapping. */
-	phys_reset = (phys_reset_t)(unsigned long)virt_to_idmap(cpu_reset);
+	phys_reset = (phys_reset_t)virt_to_idmap(cpu_reset);
 	phys_reset((unsigned long)addr);
 
 	/* Should never get here. */
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 139791ed473d..a28fce0bdbbe 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -430,11 +430,13 @@ static void __init patch_aeabi_idiv(void)
 	pr_info("CPU: div instructions available: patching division code\n");
 
 	fn_addr = ((uintptr_t)&__aeabi_uidiv) & ~1;
+	asm ("" : "+g" (fn_addr));
 	((u32 *)fn_addr)[0] = udiv_instruction();
 	((u32 *)fn_addr)[1] = bx_lr_instruction();
 	flush_icache_range(fn_addr, fn_addr + 8);
 
 	fn_addr = ((uintptr_t)&__aeabi_idiv) & ~1;
+	asm ("" : "+g" (fn_addr));
 	((u32 *)fn_addr)[0] = sdiv_instruction();
 	((u32 *)fn_addr)[1] = bx_lr_instruction();
 	flush_icache_range(fn_addr, fn_addr + 8);
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 08b7847bf912..ec279d161b32 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -40,7 +40,7 @@
  * to run the rebalance_domains for all idle cores and the cpu_capacity can be
  * updated during this sequence.
  */
-static DEFINE_PER_CPU(unsigned long, cpu_scale);
+static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
 
 unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
 {
@@ -306,8 +306,6 @@ void __init init_cpu_topology(void)
 		cpu_topo->socket_id = -1;
 		cpumask_clear(&cpu_topo->core_sibling);
 		cpumask_clear(&cpu_topo->thread_sibling);
-
-		set_capacity_scale(cpu, SCHED_CAPACITY_SCALE);
 	}
 	smp_wmb();
 
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
new file mode 100644
index 000000000000..cba1ec899a69
--- /dev/null
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -0,0 +1,316 @@
+/* ld script to make ARM Linux kernel
+ * taken from the i386 version by Russell King
+ * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ */
+
+#include <asm-generic/vmlinux.lds.h>
+#include <asm/cache.h>
+#include <asm/thread_info.h>
+#include <asm/memory.h>
+#include <asm/page.h>
+
+#define PROC_INFO							\
+	. = ALIGN(4);							\
+	VMLINUX_SYMBOL(__proc_info_begin) = .;				\
+	*(.proc.info.init)						\
+	VMLINUX_SYMBOL(__proc_info_end) = .;
+
+#define IDMAP_TEXT							\
+	ALIGN_FUNCTION();						\
+	VMLINUX_SYMBOL(__idmap_text_start) = .;				\
+	*(.idmap.text)							\
+	VMLINUX_SYMBOL(__idmap_text_end) = .;				\
+	. = ALIGN(PAGE_SIZE);						\
+	VMLINUX_SYMBOL(__hyp_idmap_text_start) = .;			\
+	*(.hyp.idmap.text)						\
+	VMLINUX_SYMBOL(__hyp_idmap_text_end) = .;
+
+#ifdef CONFIG_HOTPLUG_CPU
+#define ARM_CPU_DISCARD(x)
+#define ARM_CPU_KEEP(x)		x
+#else
+#define ARM_CPU_DISCARD(x)	x
+#define ARM_CPU_KEEP(x)
+#endif
+
+#if (defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)) || \
+	defined(CONFIG_GENERIC_BUG)
+#define ARM_EXIT_KEEP(x)	x
+#define ARM_EXIT_DISCARD(x)
+#else
+#define ARM_EXIT_KEEP(x)
+#define ARM_EXIT_DISCARD(x)	x
+#endif
+
+OUTPUT_ARCH(arm)
+ENTRY(stext)
+
+#ifndef __ARMEB__
+jiffies = jiffies_64;
+#else
+jiffies = jiffies_64 + 4;
+#endif
+
+SECTIONS
+{
+	/*
+	 * XXX: The linker does not define how output sections are
+	 * assigned to input sections when there are multiple statements
+	 * matching the same input section name.  There is no documented
+	 * order of matching.
+	 *
+	 * unwind exit sections must be discarded before the rest of the
+	 * unwind sections get included.
+	 */
+	/DISCARD/ : {
+		*(.ARM.exidx.exit.text)
+		*(.ARM.extab.exit.text)
+		ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text))
+		ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text))
+		ARM_EXIT_DISCARD(EXIT_TEXT)
+		ARM_EXIT_DISCARD(EXIT_DATA)
+		EXIT_CALL
+#ifndef CONFIG_MMU
+		*(.text.fixup)
+		*(__ex_table)
+#endif
+#ifndef CONFIG_SMP_ON_UP
+		*(.alt.smp.init)
+#endif
+		*(.discard)
+		*(.discard.*)
+	}
+
+	. = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR);
+	_xiprom = .;			/* XIP ROM area to be mapped */
+
+	.head.text : {
+		_text = .;
+		HEAD_TEXT
+	}
+
+	.text : {			/* Real text segment		*/
+		_stext = .;		/* Text and read-only data	*/
+			IDMAP_TEXT
+			__exception_text_start = .;
+			*(.exception.text)
+			__exception_text_end = .;
+			IRQENTRY_TEXT
+			TEXT_TEXT
+			SCHED_TEXT
+			LOCK_TEXT
+			KPROBES_TEXT
+			*(.gnu.warning)
+			*(.glue_7)
+			*(.glue_7t)
+		. = ALIGN(4);
+		*(.got)			/* Global offset table		*/
+			ARM_CPU_KEEP(PROC_INFO)
+	}
+
+	RO_DATA(PAGE_SIZE)
+
+	. = ALIGN(4);
+	__ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) {
+		__start___ex_table = .;
+#ifdef CONFIG_MMU
+		*(__ex_table)
+#endif
+		__stop___ex_table = .;
+	}
+
+#ifdef CONFIG_ARM_UNWIND
+	/*
+	 * Stack unwinding tables
+	 */
+	. = ALIGN(8);
+	.ARM.unwind_idx : {
+		__start_unwind_idx = .;
+		*(.ARM.exidx*)
+		__stop_unwind_idx = .;
+	}
+	.ARM.unwind_tab : {
+		__start_unwind_tab = .;
+		*(.ARM.extab*)
+		__stop_unwind_tab = .;
+	}
+#endif
+
+	NOTES
+
+	_etext = .;			/* End of text and rodata section */
+
+	/*
+	 * The vectors and stubs are relocatable code, and the
+	 * only thing that matters is their relative offsets
+	 */
+	__vectors_start = .;
+	.vectors 0xffff0000 : AT(__vectors_start) {
+		*(.vectors)
+	}
+	. = __vectors_start + SIZEOF(.vectors);
+	__vectors_end = .;
+
+	__stubs_start = .;
+	.stubs ADDR(.vectors) + 0x1000 : AT(__stubs_start) {
+		*(.stubs)
+	}
+	. = __stubs_start + SIZEOF(.stubs);
+	__stubs_end = .;
+
+	PROVIDE(vector_fiq_offset = vector_fiq - ADDR(.vectors));
+
+	INIT_TEXT_SECTION(8)
+	.exit.text : {
+		ARM_EXIT_KEEP(EXIT_TEXT)
+	}
+	.init.proc.info : {
+		ARM_CPU_DISCARD(PROC_INFO)
+	}
+	.init.arch.info : {
+		__arch_info_begin = .;
+		*(.arch.info.init)
+		__arch_info_end = .;
+	}
+	.init.tagtable : {
+		__tagtable_begin = .;
+		*(.taglist.init)
+		__tagtable_end = .;
+	}
+#ifdef CONFIG_SMP_ON_UP
+	.init.smpalt : {
+		__smpalt_begin = .;
+		*(.alt.smp.init)
+		__smpalt_end = .;
+	}
+#endif
+	.init.pv_table : {
+		__pv_table_begin = .;
+		*(.pv_table)
+		__pv_table_end = .;
+	}
+	.init.data : {
+		INIT_SETUP(16)
+		INIT_CALLS
+		CON_INITCALL
+		SECURITY_INITCALL
+		INIT_RAM_FS
+	}
+
+#ifdef CONFIG_SMP
+	PERCPU_SECTION(L1_CACHE_BYTES)
+#endif
+
+	_exiprom = .;			/* End of XIP ROM area */
+	__data_loc = ALIGN(4);		/* location in binary */
+	. = PAGE_OFFSET + TEXT_OFFSET;
+
+	.data : AT(__data_loc) {
+		_data = .;		/* address in memory */
+		_sdata = .;
+
+		/*
+		 * first, the init task union, aligned
+		 * to an 8192 byte boundary.
+		 */
+		INIT_TASK_DATA(THREAD_SIZE)
+
+		. = ALIGN(PAGE_SIZE);
+		__init_begin = .;
+		INIT_DATA
+		ARM_EXIT_KEEP(EXIT_DATA)
+		. = ALIGN(PAGE_SIZE);
+		__init_end = .;
+
+		NOSAVE_DATA
+		CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
+		READ_MOSTLY_DATA(L1_CACHE_BYTES)
+
+		/*
+		 * and the usual data section
+		 */
+		DATA_DATA
+		CONSTRUCTORS
+
+		_edata = .;
+	}
+	_edata_loc = __data_loc + SIZEOF(.data);
+
+#ifdef CONFIG_HAVE_TCM
+        /*
+	 * We align everything to a page boundary so we can
+	 * free it after init has commenced and TCM contents have
+	 * been copied to its destination.
+	 */
+	.tcm_start : {
+		. = ALIGN(PAGE_SIZE);
+		__tcm_start = .;
+		__itcm_start = .;
+	}
+
+	/*
+	 * Link these to the ITCM RAM
+	 * Put VMA to the TCM address and LMA to the common RAM
+	 * and we'll upload the contents from RAM to TCM and free
+	 * the used RAM after that.
+	 */
+	.text_itcm ITCM_OFFSET : AT(__itcm_start)
+	{
+		__sitcm_text = .;
+		*(.tcm.text)
+		*(.tcm.rodata)
+		. = ALIGN(4);
+		__eitcm_text = .;
+	}
+
+	/*
+	 * Reset the dot pointer, this is needed to create the
+	 * relative __dtcm_start below (to be used as extern in code).
+	 */
+	. = ADDR(.tcm_start) + SIZEOF(.tcm_start) + SIZEOF(.text_itcm);
+
+	.dtcm_start : {
+		__dtcm_start = .;
+	}
+
+	/* TODO: add remainder of ITCM as well, that can be used for data! */
+	.data_dtcm DTCM_OFFSET : AT(__dtcm_start)
+	{
+		. = ALIGN(4);
+		__sdtcm_data = .;
+		*(.tcm.data)
+		. = ALIGN(4);
+		__edtcm_data = .;
+	}
+
+	/* Reset the dot pointer or the linker gets confused */
+	. = ADDR(.dtcm_start) + SIZEOF(.data_dtcm);
+
+	/* End marker for freeing TCM copy in linked object */
+	.tcm_end : AT(ADDR(.dtcm_start) + SIZEOF(.data_dtcm)){
+		. = ALIGN(PAGE_SIZE);
+		__tcm_end = .;
+	}
+#endif
+
+	BSS_SECTION(0, 0, 0)
+	_end = .;
+
+	STABS_DEBUG
+}
+
+/*
+ * These must never be empty
+ * If you have to comment these two assert statements out, your
+ * binutils is too old (for other reasons as well)
+ */
+ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support")
+ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
+
+/*
+ * The HYP init code can't be more than a page long,
+ * and should not cross a page boundary.
+ * The above comment applies as well.
+ */
+ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & PAGE_MASK) <= PAGE_SIZE,
+	"HYP init code too big or misaligned")
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 8b60fde5ce48..e2c6da096cef 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -3,14 +3,16 @@
  * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz>
  */
 
+#ifdef CONFIG_XIP_KERNEL
+#include "vmlinux-xip.lds.S"
+#else
+
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/cache.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/page.h>
-#ifdef CONFIG_ARM_KERNMEM_PERMS
 #include <asm/pgtable.h>
-#endif
 
 #define PROC_INFO							\
 	. = ALIGN(4);							\
@@ -18,6 +20,11 @@
 	*(.proc.info.init)						\
 	VMLINUX_SYMBOL(__proc_info_end) = .;
 
+#define HYPERVISOR_TEXT							\
+	VMLINUX_SYMBOL(__hyp_text_start) = .;				\
+	*(.hyp.text)							\
+	VMLINUX_SYMBOL(__hyp_text_end) = .;
+
 #define IDMAP_TEXT							\
 	ALIGN_FUNCTION();						\
 	VMLINUX_SYMBOL(__idmap_text_start) = .;				\
@@ -84,17 +91,13 @@ SECTIONS
 		*(.discard.*)
 	}
 
-#ifdef CONFIG_XIP_KERNEL
-	. = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR);
-#else
 	. = PAGE_OFFSET + TEXT_OFFSET;
-#endif
 	.head.text : {
 		_text = .;
 		HEAD_TEXT
 	}
 
-#ifdef CONFIG_ARM_KERNMEM_PERMS
+#ifdef CONFIG_DEBUG_RODATA
 	. = ALIGN(1<<SECTION_SHIFT);
 #endif
 
@@ -105,9 +108,11 @@ SECTIONS
 			*(.exception.text)
 			__exception_text_end = .;
 			IRQENTRY_TEXT
+			SOFTIRQENTRY_TEXT
 			TEXT_TEXT
 			SCHED_TEXT
 			LOCK_TEXT
+			HYPERVISOR_TEXT
 			KPROBES_TEXT
 			*(.gnu.warning)
 			*(.glue_7)
@@ -117,7 +122,7 @@ SECTIONS
 			ARM_CPU_KEEP(PROC_INFO)
 	}
 
-#ifdef CONFIG_DEBUG_RODATA
+#ifdef CONFIG_DEBUG_ALIGN_RODATA
 	. = ALIGN(1<<SECTION_SHIFT);
 #endif
 	RO_DATA(PAGE_SIZE)
@@ -152,32 +157,33 @@ SECTIONS
 
 	_etext = .;			/* End of text and rodata section */
 
-#ifndef CONFIG_XIP_KERNEL
-# ifdef CONFIG_ARM_KERNMEM_PERMS
+#ifdef CONFIG_DEBUG_RODATA
 	. = ALIGN(1<<SECTION_SHIFT);
-# else
+#else
 	. = ALIGN(PAGE_SIZE);
-# endif
-	__init_begin = .;
 #endif
+	__init_begin = .;
+
 	/*
 	 * The vectors and stubs are relocatable code, and the
 	 * only thing that matters is their relative offsets
 	 */
 	__vectors_start = .;
-	.vectors 0 : AT(__vectors_start) {
+	.vectors 0xffff0000 : AT(__vectors_start) {
 		*(.vectors)
 	}
 	. = __vectors_start + SIZEOF(.vectors);
 	__vectors_end = .;
 
 	__stubs_start = .;
-	.stubs 0x1000 : AT(__stubs_start) {
+	.stubs ADDR(.vectors) + 0x1000 : AT(__stubs_start) {
 		*(.stubs)
 	}
 	. = __stubs_start + SIZEOF(.stubs);
 	__stubs_end = .;
 
+	PROVIDE(vector_fiq_offset = vector_fiq - ADDR(.vectors));
+
 	INIT_TEXT_SECTION(8)
 	.exit.text : {
 		ARM_EXIT_KEEP(EXIT_TEXT)
@@ -208,37 +214,28 @@ SECTIONS
 		__pv_table_end = .;
 	}
 	.init.data : {
-#ifndef CONFIG_XIP_KERNEL
 		INIT_DATA
-#endif
 		INIT_SETUP(16)
 		INIT_CALLS
 		CON_INITCALL
 		SECURITY_INITCALL
 		INIT_RAM_FS
 	}
-#ifndef CONFIG_XIP_KERNEL
 	.exit.data : {
 		ARM_EXIT_KEEP(EXIT_DATA)
 	}
-#endif
 
 #ifdef CONFIG_SMP
 	PERCPU_SECTION(L1_CACHE_BYTES)
 #endif
 
-#ifdef CONFIG_XIP_KERNEL
-	__data_loc = ALIGN(4);		/* location in binary */
-	. = PAGE_OFFSET + TEXT_OFFSET;
-#else
-#ifdef CONFIG_ARM_KERNMEM_PERMS
+#ifdef CONFIG_DEBUG_RODATA
 	. = ALIGN(1<<SECTION_SHIFT);
 #else
 	. = ALIGN(THREAD_SIZE);
 #endif
 	__init_end = .;
 	__data_loc = .;
-#endif
 
 	.data : AT(__data_loc) {
 		_data = .;		/* address in memory */
@@ -250,15 +247,6 @@ SECTIONS
 		 */
 		INIT_TASK_DATA(THREAD_SIZE)
 
-#ifdef CONFIG_XIP_KERNEL
-		. = ALIGN(PAGE_SIZE);
-		__init_begin = .;
-		INIT_DATA
-		ARM_EXIT_KEEP(EXIT_DATA)
-		. = ALIGN(PAGE_SIZE);
-		__init_end = .;
-#endif
-
 		NOSAVE_DATA
 		CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES)
 		READ_MOSTLY_DATA(L1_CACHE_BYTES)
@@ -336,6 +324,15 @@ SECTIONS
 	STABS_DEBUG
 }
 
+#ifdef CONFIG_DEBUG_RODATA
+/*
+ * Without CONFIG_DEBUG_ALIGN_RODATA, __start_rodata_section_aligned will
+ * be the first section-aligned location after __start_rodata. Otherwise,
+ * it will be equal to __start_rodata.
+ */
+__start_rodata_section_aligned = ALIGN(__start_rodata, 1 << SECTION_SHIFT);
+#endif
+
 /*
  * These must never be empty
  * If you have to comment these two assert statements out, your
@@ -351,3 +348,5 @@ ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
  */
 ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & PAGE_MASK) <= PAGE_SIZE,
 	"HYP init code too big or misaligned")
+
+#endif /* CONFIG_XIP_KERNEL */