17 files changed, 227 insertions, 139 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index ad325a8c7e1e..52f437997cc6 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -87,6 +87,11 @@ head-y			:= head$(MMUEXT).o
 obj-$(CONFIG_DEBUG_LL)	+= debug.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
+# This is executed very early using a temporary stack when no memory allocator
+# nor global data is available. Everything has to be allocated on the stack.
+CFLAGS_head-inflate-data.o := $(call cc-option,-Wframe-larger-than=10240)
+obj-$(CONFIG_XIP_DEFLATED_DATA) += head-inflate-data.o
+
 obj-$(CONFIG_ARM_VIRT_EXT)	+= hyp-stub.o
 AFLAGS_hyp-stub.o		:=-Wa,-march=armv7-a
 ifeq ($(CONFIG_ARM_PSCI),y)
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 8e8d20cdbce7..5266fd9ad6b4 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -87,6 +87,8 @@ EXPORT_SYMBOL(__raw_writesl);
 EXPORT_SYMBOL(strchr);
 EXPORT_SYMBOL(strrchr);
 EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(__memset32);
+EXPORT_SYMBOL(__memset64);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memchr);
diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c
index a3308ad1a024..fda5579123a8 100644
--- a/arch/arm/kernel/cpuidle.c
+++ b/arch/arm/kernel/cpuidle.c
@@ -101,8 +101,8 @@ static int __init arm_cpuidle_read_ops(struct device_node *dn, int cpu)
 
 	ops = arm_cpuidle_get_ops(enable_method);
 	if (!ops) {
-		pr_warn("%s: unsupported enable-method property: %s\n",
-			dn->full_name, enable_method);
+		pr_warn("%pOF: unsupported enable-method property: %s\n",
+			dn, enable_method);
 		return -EOPNOTSUPP;
 	}
 
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index f676febbb270..ecaa68dd1af5 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -95,7 +95,7 @@ void __init arm_dt_init_cpu_maps(void)
 		if (of_node_cmp(cpu->type, "cpu"))
 			continue;
 
-		pr_debug(" * %s...\n", cpu->full_name);
+		pr_debug(" * %pOF...\n", cpu);
 		/*
 		 * A device tree containing CPU nodes with missing "reg"
 		 * properties is considered invalid to build the
@@ -103,8 +103,7 @@ void __init arm_dt_init_cpu_maps(void)
 		 */
 		cell = of_get_property(cpu, "reg", &prop_bytes);
 		if (!cell || prop_bytes < sizeof(*cell)) {
-			pr_debug(" * %s missing reg property\n",
-				     cpu->full_name);
+			pr_debug(" * %pOF missing reg property\n", cpu);
 			of_node_put(cpu);
 			return;
 		}
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index c731f0d2b2af..fbc707626b3e 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -721,6 +721,7 @@ do_fpe:
  */
 
 	.pushsection .data
+	.align	2
 ENTRY(fp_enter)
 	.word	no_fp
 	.popsection
@@ -1224,6 +1225,7 @@ vector_addrexcptn:
 	W(b)	vector_fiq
 
 	.data
+	.align	2
 
 	.globl	cr_alignment
 cr_alignment:
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index eb5cd77bf1d8..ca3614dc6938 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -27,6 +27,14 @@
 
 #include "entry-header.S"
 
+saved_psr	.req	r8
+#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
+saved_pc	.req	r9
+#define TRACE(x...) x
+#else
+saved_pc	.req	lr
+#define TRACE(x...)
+#endif
 
 	.align	5
 #if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING))
@@ -41,7 +49,9 @@ ret_fast_syscall:
  UNWIND(.cantunwind	)
 	disable_irq_notrace			@ disable interrupts
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	tst	r1, #_TIF_SYSCALL_WORK
+	bne	fast_work_pending
+	tst	r1, #_TIF_WORK_MASK
 	bne	fast_work_pending
 
 	/* perform architecture specific actions before user return */
@@ -67,12 +77,15 @@ ret_fast_syscall:
 	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
 	disable_irq_notrace			@ disable interrupts
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	tst	r1, #_TIF_SYSCALL_WORK
+	bne	fast_work_pending
+	tst	r1, #_TIF_WORK_MASK
 	beq	no_work_pending
  UNWIND(.fnend		)
 ENDPROC(ret_fast_syscall)
 
 	/* Slower path - fall through to work_pending */
+fast_work_pending:
 #endif
 
 	tst	r1, #_TIF_SYSCALL_WORK
@@ -141,16 +154,17 @@ ENTRY(vector_swi)
  ARM(	stmdb	r8, {sp, lr}^		)	@ Calling sp, lr
  THUMB(	mov	r8, sp			)
  THUMB(	store_user_sp_lr r8, r10, S_SP	)	@ calling sp, lr
-	mrs	r8, spsr			@ called from non-FIQ mode, so ok.
-	str	lr, [sp, #S_PC]			@ Save calling PC
-	str	r8, [sp, #S_PSR]		@ Save CPSR
+	mrs	saved_psr, spsr			@ called from non-FIQ mode, so ok.
+ TRACE(	mov	saved_pc, lr		)
+	str	saved_pc, [sp, #S_PC]		@ Save calling PC
+	str	saved_psr, [sp, #S_PSR]		@ Save CPSR
 	str	r0, [sp, #S_OLD_R0]		@ Save OLD_R0
 #endif
 	zero_fp
 	alignment_trap r10, ip, __cr_alignment
-	enable_irq
-	ct_user_exit
-	get_thread_info tsk
+	asm_trace_hardirqs_on save=0
+	enable_irq_notrace
+	ct_user_exit save=0
 
 	/*
 	 * Get the system call number.
@@ -163,11 +177,11 @@ ENTRY(vector_swi)
 	 * value to determine if it is an EABI or an old ABI call.
 	 */
 #ifdef CONFIG_ARM_THUMB
-	tst	r8, #PSR_T_BIT
+	tst	saved_psr, #PSR_T_BIT
 	movne	r10, #0				@ no thumb OABI emulation
- USER(	ldreq	r10, [lr, #-4]		)	@ get SWI instruction
+ USER(	ldreq	r10, [saved_pc, #-4]	)	@ get SWI instruction
 #else
- USER(	ldr	r10, [lr, #-4]		)	@ get SWI instruction
+ USER(	ldr	r10, [saved_pc, #-4]	)	@ get SWI instruction
 #endif
  ARM_BE8(rev	r10, r10)			@ little endian instruction
 
@@ -178,15 +192,17 @@ ENTRY(vector_swi)
 	 */
 #elif defined(CONFIG_ARM_THUMB)
 	/* Legacy ABI only, possibly thumb mode. */
-	tst	r8, #PSR_T_BIT			@ this is SPSR from save_user_regs
+	tst	saved_psr, #PSR_T_BIT		@ this is SPSR from save_user_regs
 	addne	scno, r7, #__NR_SYSCALL_BASE	@ put OS number in
- USER(	ldreq	scno, [lr, #-4]		)
+ USER(	ldreq	scno, [saved_pc, #-4]	)
 
 #else
 	/* Legacy ABI only. */
- USER(	ldr	scno, [lr, #-4]		)	@ get SWI instruction
+ USER(	ldr	scno, [saved_pc, #-4]	)	@ get SWI instruction
 #endif
 
+	/* saved_psr and saved_pc are now dead */
+
 	uaccess_disable tbl
 
 	adr	tbl, sys_call_table		@ load syscall table pointer
@@ -205,6 +221,12 @@ ENTRY(vector_swi)
 	bic	scno, scno, #0xff000000		@ mask off SWI op-code
 	eor	scno, scno, #__NR_SYSCALL_BASE	@ check OS number
 #endif
+	get_thread_info tsk
+	/*
+	 * Reload the registers that may have been corrupted on entry to
+	 * the syscall assembly (by tracing or context tracking.)
+	 */
+ TRACE(	ldmia	sp, {r0 - r3}		)
 
 local_restart:
 	ldr	r10, [tsk, #TI_FLAGS]		@ check for syscall tracing
@@ -234,8 +256,9 @@ local_restart:
 	 * current task.
 	 */
 9001:
-	sub	lr, lr, #4
+	sub	lr, saved_pc, #4
 	str	lr, [sp, #S_PC]
+	get_thread_info tsk
 	b	ret_fast_syscall
 #endif
 ENDPROC(vector_swi)
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 8733012d231f..a25027b87a60 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -79,47 +79,68 @@ ENDPROC(__vet_atags)
  */
 	__INIT
 __mmap_switched:
-	adr	r3, __mmap_switched_data
-
-	ldmia	r3!, {r4, r5, r6, r7}
-	cmp	r4, r5				@ Copy data segment if needed
-1:	cmpne	r5, r6
-	ldrne	fp, [r4], #4
-	strne	fp, [r5], #4
-	bne	1b
-
-	mov	fp, #0				@ Clear BSS (and zero fp)
-1:	cmp	r6, r7
-	strcc	fp, [r6],#4
-	bcc	1b
-
- ARM(	ldmia	r3, {r4, r5, r6, r7, sp})
- THUMB(	ldmia	r3, {r4, r5, r6, r7}	)
- THUMB(	ldr	sp, [r3, #16]		)
-	str	r9, [r4]			@ Save processor ID
-	str	r1, [r5]			@ Save machine type
-	str	r2, [r6]			@ Save atags pointer
-	cmp	r7, #0
-	strne	r0, [r7]			@ Save control register values
+
+	mov	r7, r1
+	mov	r8, r2
+	mov	r10, r0
+
+	adr	r4, __mmap_switched_data
+	mov	fp, #0
+
+#if defined(CONFIG_XIP_DEFLATED_DATA)
+   ARM(	ldr	sp, [r4], #4 )
+ THUMB(	ldr	sp, [r4] )
+ THUMB(	add	r4, #4 )
+	bl	__inflate_kernel_data		@ decompress .data to RAM
+	teq	r0, #0
+	bne	__error
+#elif defined(CONFIG_XIP_KERNEL)
+   ARM(	ldmia	r4!, {r0, r1, r2, sp} )
+ THUMB(	ldmia	r4!, {r0, r1, r2, r3} )
+ THUMB(	mov	sp, r3 )
+	sub	r2, r2, r1
+	bl	memcpy				@ copy .data to RAM
+#endif
+
+   ARM(	ldmia	r4!, {r0, r1, sp} )
+ THUMB(	ldmia	r4!, {r0, r1, r3} )
+ THUMB(	mov	sp, r3 )
+	sub	r1, r1, r0
+	bl	__memzero			@ clear .bss
+
+	ldmia	r4, {r0, r1, r2, r3}
+	str	r9, [r0]			@ Save processor ID
+	str	r7, [r1]			@ Save machine type
+	str	r8, [r2]			@ Save atags pointer
+	cmp	r3, #0
+	strne	r10, [r3]			@ Save control register values
 	b	start_kernel
 ENDPROC(__mmap_switched)
 
 	.align	2
 	.type	__mmap_switched_data, %object
 __mmap_switched_data:
-	.long	__data_loc			@ r4
-	.long	_sdata				@ r5
-	.long	__bss_start			@ r6
-	.long	_end				@ r7
-	.long	processor_id			@ r4
-	.long	__machine_arch_type		@ r5
-	.long	__atags_pointer			@ r6
+#ifdef CONFIG_XIP_KERNEL
+#ifndef CONFIG_XIP_DEFLATED_DATA
+	.long	_sdata				@ r0
+	.long	__data_loc			@ r1
+	.long	_edata_loc			@ r2
+#endif
+	.long	__bss_stop			@ sp (temporary stack in .bss)
+#endif
+
+	.long	__bss_start			@ r0
+	.long	__bss_stop			@ r1
+	.long	init_thread_union + THREAD_START_SP @ sp
+
+	.long	processor_id			@ r0
+	.long	__machine_arch_type		@ r1
+	.long	__atags_pointer			@ r2
 #ifdef CONFIG_CPU_CP15
-	.long	cr_alignment			@ r7
+	.long	cr_alignment			@ r3
 #else
-	.long	0				@ r7
+	.long	0				@ r3
 #endif
-	.long	init_thread_union + THREAD_START_SP @ sp
 	.size	__mmap_switched_data, . - __mmap_switched_data
 
 /*
diff --git a/arch/arm/kernel/head-inflate-data.c b/arch/arm/kernel/head-inflate-data.c
new file mode 100644
index 000000000000..6dd0ce5e6058
--- /dev/null
+++ b/arch/arm/kernel/head-inflate-data.c
@@ -0,0 +1,62 @@
+/*
+ * XIP kernel .data segment decompressor
+ *
+ * Created by:	Nicolas Pitre, August 2017
+ * Copyright:	(C) 2017  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/zutil.h>
+
+/* for struct inflate_state */
+#include "../../../lib/zlib_inflate/inftrees.h"
+#include "../../../lib/zlib_inflate/inflate.h"
+#include "../../../lib/zlib_inflate/infutil.h"
+
+extern char __data_loc[];
+extern char _edata_loc[];
+extern char _sdata[];
+
+/*
+ * This code is called very early during the boot process to decompress
+ * the .data segment stored compressed in ROM. Therefore none of the global
+ * variables are valid yet, hence no kernel services such as memory
+ * allocation is available. Everything must be allocated on the stack and
+ * we must avoid any global data access. We use a temporary stack located
+ * in the .bss area. The linker script makes sure the .bss is big enough
+ * to hold our stack frame plus some room for called functions.
+ *
+ * We mimic the code in lib/decompress_inflate.c to use the smallest work
+ * area possible. And because everything is statically allocated on the
+ * stack then there is no need to clean up before returning.
+ */
+
+int __init __inflate_kernel_data(void)
+{
+	struct z_stream_s stream, *strm = &stream;
+	struct inflate_state state;
+	char *in = __data_loc;
+	int rc;
+
+	/* Check and skip gzip header (assume no filename) */
+	if (in[0] != 0x1f || in[1] != 0x8b || in[2] != 0x08 || in[3] & ~3)
+		return -1;
+	in += 10;
+
+	strm->workspace = &state;
+	strm->next_in = in;
+	strm->avail_in = _edata_loc - __data_loc;  /* upper bound */
+	strm->next_out = _sdata;
+	strm->avail_out = _edata_loc - __data_loc;
+	zlib_inflateInit2(strm, -MAX_WBITS);
+	WS(strm)->inflate_state.wsize = 0;
+	WS(strm)->inflate_state.window = NULL;
+	rc = zlib_inflate(strm, Z_FINISH);
+	if (rc == Z_OK || rc == Z_STREAM_END)
+		rc = strm->avail_out;  /* should be 0 */
+	return rc;
+}
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 04286fd9e09c..6b1148cafffd 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -556,6 +556,7 @@ ENDPROC(__fixup_smp)
 	.word	__smpalt_end
 
 	.pushsection .data
+	.align	2
 	.globl	smp_on_up
 smp_on_up:
 	ALT_SMP(.long	1)
@@ -716,6 +717,7 @@ ENTRY(fixup_pv_table)
 ENDPROC(fixup_pv_table)
 
 	.data
+	.align	2
 	.globl	__pv_phys_pfn_offset
 	.type	__pv_phys_pfn_offset, %object
 __pv_phys_pfn_offset:
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index ec7e7377d423..60146e32619a 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -31,6 +31,7 @@
  * zeroing of .bss would clobber it.
  */
 .data
+	.align	2
 ENTRY(__boot_cpu_mode)
 	.long	0
 .text
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index 49fadbda8c63..81cd4d43b3ec 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -367,6 +367,7 @@ ENTRY(iwmmxt_task_release)
 ENDPROC(iwmmxt_task_release)
 
 	.data
+	.align	2
 concan_owner:
 	.word	0
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 1f3574ec4fad..237973492479 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -14,6 +14,7 @@
 #include <linux/uaccess.h>
 #include <linux/tracehook.h>
 #include <linux/uprobes.h>
+#include <linux/syscalls.h>
 
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
@@ -636,6 +637,10 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 	 * Update the trace code with the current status.
 	 */
 	trace_hardirqs_off();
+
+	/* Check valid user FS if needed */
+	addr_limit_user_check();
+
 	do {
 		if (likely(thread_flags & _TIF_NEED_RESCHED)) {
 			schedule();
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index 0f6c1000582c..9f08d214d05a 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -171,6 +171,7 @@ mpidr_hash_ptr:
 	.long	mpidr_hash - .			@ mpidr_hash struct offset
 
 	.data
+	.align	2
 	.type	sleep_save_sp, #object
 ENTRY(sleep_save_sp)
 	.space	SLEEP_SAVE_SP_SZ		@ struct sleep_save_sp
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 3a2fa203637a..65228bf4c6df 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -171,6 +171,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
 	__save_stack_trace(tsk, trace, 1);
 }
+EXPORT_SYMBOL(save_stack_trace_tsk);
 
 void save_stack_trace(struct stack_trace *trace)
 {
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index bf949a763dbe..24ac3cab411d 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -127,8 +127,7 @@ static void __init parse_dt_topology(void)
 
 		rate = of_get_property(cn, "clock-frequency", &len);
 		if (!rate || len != 4) {
-			pr_err("%s missing clock-frequency property\n",
-				cn->full_name);
+			pr_err("%pOF missing clock-frequency property\n", cn);
 			continue;
 		}
 
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index 8265b116218d..7a844310085e 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -77,9 +77,7 @@ SECTIONS
 		*(.text.fixup)
 		*(__ex_table)
 #endif
-#ifndef CONFIG_SMP_ON_UP
 		*(.alt.smp.init)
-#endif
 		*(.discard)
 		*(.discard.*)
 	}
@@ -181,19 +179,7 @@ SECTIONS
 		*(.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.rodata : {
 		INIT_SETUP(16)
 		INIT_CALLS
 		CON_INITCALL
@@ -201,48 +187,46 @@ SECTIONS
 		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)
+/*
+ * From this point, stuff is considered writable and will be copied to RAM
+ */
+	__data_loc = ALIGN(4);		/* location in file */
+	. = PAGE_OFFSET + TEXT_OFFSET;	/* location in memory */
+#undef LOAD_OFFSET
+#define LOAD_OFFSET (PAGE_OFFSET + TEXT_OFFSET - __data_loc)
+
+	. = ALIGN(THREAD_SIZE);
+	_sdata = .;
+	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	.data.ro_after_init : AT(ADDR(.data.ro_after_init) - LOAD_OFFSET) {
+		*(.data..ro_after_init)
+	}
+	_edata = .;
 
-		. = ALIGN(PAGE_SIZE);
-		__init_begin = .;
+	. = ALIGN(PAGE_SIZE);
+	__init_begin = .;
+	.init.data : AT(ADDR(.init.data) - LOAD_OFFSET) {
 		INIT_DATA
+	}
+	.exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) {
 		ARM_EXIT_KEEP(EXIT_DATA)
-		. = ALIGN(PAGE_SIZE);
-		__init_end = .;
-
-		*(.data..ro_after_init)
-
-		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_SMP
+	PERCPU_SECTION(L1_CACHE_BYTES)
+#endif
+
+	/*
+	 * End of copied data. We need a dummy section to get its LMA.
+	 * Also located before final ALIGN() as trailing padding is not stored
+	 * in the resulting binary file and useless to copy.
+	 */
+	.data.endmark : AT(ADDR(.data.endmark) - LOAD_OFFSET) { }
+	_edata_loc = LOADADDR(.data.endmark);
 
-	BUG_TABLE
+	. = ALIGN(PAGE_SIZE);
+	__init_end = .;
 
 #ifdef CONFIG_HAVE_TCM
         /*
@@ -301,7 +285,7 @@ SECTIONS
 	}
 #endif
 
-	BSS_SECTION(0, 0, 0)
+	BSS_SECTION(0, 0, 8)
 	_end = .;
 
 	STABS_DEBUG
@@ -322,3 +306,11 @@ 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")
+
+#ifdef CONFIG_XIP_DEFLATED_DATA
+/*
+ * The .bss is used as a stack area for __inflate_kernel_data() whose stack
+ * frame is 9568 bytes. Make sure it has extra room left.
+ */
+ASSERT((_end - __bss_start) >= 12288, ".bss too small for CONFIG_XIP_DEFLATED_DATA")
+#endif
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index c83a7ba737d6..f73ba564b5e5 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -214,14 +214,9 @@ SECTIONS
 		*(.pv_table)
 		__pv_table_end = .;
 	}
-	.init.data : {
-		INIT_DATA
-		INIT_SETUP(16)
-		INIT_CALLS
-		CON_INITCALL
-		SECURITY_INITCALL
-		INIT_RAM_FS
-	}
+
+	INIT_DATA_SECTION(16)
+
 	.exit.data : {
 		ARM_EXIT_KEEP(EXIT_DATA)
 	}
@@ -236,33 +231,10 @@ SECTIONS
 	. = ALIGN(THREAD_SIZE);
 #endif
 	__init_end = .;
-	__data_loc = .;
-
-	.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)
-
-		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);
 
-	BUG_TABLE
+	_sdata = .;
+	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	_edata = .;
 
 #ifdef CONFIG_HAVE_TCM
         /*