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

Pull ARM updates from Russell King:

 - amba bus updates

 - simplify ldr_this_cpu assembler macro for uniprocessor builds

 - avoid explicit assembler literal loads

 - more spectre-bhb improvements

 - add Cortex-A9 Errata 764319 workaround

 - add all unwind tables for modules

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm:
  ARM: 9204/2: module: Add all unwind tables when load module
  ARM: 9206/1: A9: Add ARM ERRATA 764319 workaround (Updated)
  ARM: 9201/1: spectre-bhb: rely on linker to emit cross-section literal loads
  ARM: 9200/1: spectre-bhb: avoid cross-subsection jump using a numbered label
  ARM: 9199/1: spectre-bhb: use local DSB and elide ISB in loop8 sequence
  ARM: 9198/1: spectre-bhb: simplify BPIALL vector macro
  ARM: 9195/1: entry: avoid explicit literal loads
  ARM: 9194/1: assembler: simplify ldr_this_cpu for !SMP builds
  ARM: 9192/1: amba: fix memory leak in amba_device_try_add()
  ARM: 9193/1: amba: Add amba_read_periphid() helper

arch/arm/Kconfig

@@ -972,6 +972,17 @@ config ARM_ERRATA_764369
 	  relevant cache maintenance functions and sets a specific bit
 	  in the diagnostic control register of the SCU.
 
+config ARM_ERRATA_764319
+	bool "ARM errata: Read to DBGPRSR and DBGOSLSR may generate Undefined instruction"
+	depends on CPU_V7
+	help
+	  This option enables the workaround for the 764319 Cortex A-9 erratum.
+	  CP14 read accesses to the DBGPRSR and DBGOSLSR registers generate an
+	  unexpected Undefined Instruction exception when the DBGSWENABLE
+	  external pin is set to 0, even when the CP14 accesses are performed
+	  from a privileged mode. This work around catches the exception in a
+	  way the kernel does not stop execution.
+
 config ARM_ERRATA_775420
        bool "ARM errata: A data cache maintenance operation which aborts, might lead to deadlock"
        depends on CPU_V7

arch/arm/include/asm/assembler.h

@@ -666,12 +666,11 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	__adldst_l	str, \src, \sym, \tmp, \cond
 	.endm
 
-	.macro		__ldst_va, op, reg, tmp, sym, cond
+	.macro		__ldst_va, op, reg, tmp, sym, cond, offset
 #if __LINUX_ARM_ARCH__ >= 7 || \
     !defined(CONFIG_ARM_HAS_GROUP_RELOCS) || \
     (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
 	mov_l		\tmp, \sym, \cond
-	\op\cond	\reg, [\tmp]
 #else
 	/*
 	 * Avoid a literal load, by emitting a sequence of ADD/LDR instructions
@@ -683,24 +682,29 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.reloc		.L0_\@, R_ARM_ALU_PC_G0_NC, \sym
 	.reloc		.L1_\@, R_ARM_ALU_PC_G1_NC, \sym
 	.reloc		.L2_\@, R_ARM_LDR_PC_G2, \sym
-.L0_\@: sub\cond	\tmp, pc, #8
-.L1_\@: sub\cond	\tmp, \tmp, #4
-.L2_\@: \op\cond	\reg, [\tmp, #0]
+.L0_\@: sub\cond	\tmp, pc, #8 - \offset
+.L1_\@: sub\cond	\tmp, \tmp, #4 - \offset
+.L2_\@:
 #endif
+	\op\cond	\reg, [\tmp, #\offset]
 	.endm
 
 	/*
 	 * ldr_va - load a 32-bit word from the virtual address of \sym
 	 */
-	.macro		ldr_va, rd:req, sym:req, cond
-	__ldst_va	ldr, \rd, \rd, \sym, \cond
+	.macro		ldr_va, rd:req, sym:req, cond, tmp, offset=0
+	.ifnb		\tmp
+	__ldst_va	ldr, \rd, \tmp, \sym, \cond, \offset
+	.else
+	__ldst_va	ldr, \rd, \rd, \sym, \cond, \offset
+	.endif
 	.endm
 
 	/*
 	 * str_va - store a 32-bit word to the virtual address of \sym
 	 */
 	.macro		str_va, rn:req, sym:req, tmp:req, cond
-	__ldst_va	str, \rn, \tmp, \sym, \cond
+	__ldst_va	str, \rn, \tmp, \sym, \cond, 0
 	.endm
 
 	/*
@@ -727,9 +731,11 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	 *		  are permitted to overlap with 'rd' if != sp
 	 */
 	.macro		ldr_this_cpu, rd:req, sym:req, t1:req, t2:req
-#if __LINUX_ARM_ARCH__ >= 7 || \
-    !defined(CONFIG_ARM_HAS_GROUP_RELOCS) || \
-    (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
+#ifndef CONFIG_SMP
+	ldr_va		\rd, \sym, tmp=\t1
+#elif __LINUX_ARM_ARCH__ >= 7 || \
+      !defined(CONFIG_ARM_HAS_GROUP_RELOCS) || \
+      (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
 	this_cpu_offset	\t1
 	mov_l		\t2, \sym
 	ldr		\rd, [\t1, \t2]

arch/arm/include/asm/module.h

@@ -3,20 +3,10 @@
 #define _ASM_ARM_MODULE_H
 
 #include <asm-generic/module.h>
-
-struct unwind_table;
+#include <asm/unwind.h>
 
 #ifdef CONFIG_ARM_UNWIND
-enum {
-	ARM_SEC_INIT,
-	ARM_SEC_DEVINIT,
-	ARM_SEC_CORE,
-	ARM_SEC_EXIT,
-	ARM_SEC_DEVEXIT,
-	ARM_SEC_HOT,
-	ARM_SEC_UNLIKELY,
-	ARM_SEC_MAX,
-};
+#define ELF_SECTION_UNWIND 0x70000001
 #endif
 
 #define PLT_ENT_STRIDE		L1_CACHE_BYTES
@@ -36,7 +26,8 @@ struct mod_plt_sec {
 
 struct mod_arch_specific {
 #ifdef CONFIG_ARM_UNWIND
-	struct unwind_table *unwind[ARM_SEC_MAX];
+	struct list_head unwind_list;
+	struct unwind_table *init_table;
 #endif
 #ifdef CONFIG_ARM_MODULE_PLTS
 	struct mod_plt_sec	core;

arch/arm/include/asm/unwind.h

@@ -24,6 +24,7 @@ struct unwind_idx {
 
 struct unwind_table {
 	struct list_head list;
+	struct list_head mod_list;
 	const struct unwind_idx *start;
 	const struct unwind_idx *origin;
 	const struct unwind_idx *stop;

arch/arm/kernel/entry-armv.S

@@ -61,9 +61,8 @@
 	.macro	pabt_helper
 	@ PABORT handler takes pt_regs in r2, fault address in r4 and psr in r5
 #ifdef MULTI_PABORT
-	ldr	ip, .LCprocfns
-	mov	lr, pc
-	ldr	pc, [ip, #PROCESSOR_PABT_FUNC]
+	ldr_va	ip, processor, offset=PROCESSOR_PABT_FUNC
+	bl_r	ip
 #else
 	bl	CPU_PABORT_HANDLER
 #endif
@@ -82,9 +81,8 @@
 	@ the fault status register in r1.  r9 must be preserved.
 	@
 #ifdef MULTI_DABORT
-	ldr	ip, .LCprocfns
-	mov	lr, pc
-	ldr	pc, [ip, #PROCESSOR_DABT_FUNC]
+	ldr_va	ip, processor, offset=PROCESSOR_DABT_FUNC
+	bl_r	ip
 #else
 	bl	CPU_DABORT_HANDLER
 #endif
@@ -302,16 +300,6 @@ __fiq_svc:
  UNWIND(.fnend		)
 ENDPROC(__fiq_svc)
 
-	.align	5
-.LCcralign:
-	.word	cr_alignment
-#ifdef MULTI_DABORT
-.LCprocfns:
-	.word	processor
-#endif
-.LCfp:
-	.word	fp_enter
-
 /*
  * Abort mode handlers
  */
@@ -370,7 +358,7 @@ ENDPROC(__fiq_abt)
  THUMB(	stmia	sp, {r0 - r12}	)
 
  ATRAP(	mrc	p15, 0, r7, c1, c0, 0)
- ATRAP(	ldr	r8, .LCcralign)
+ ATRAP(	ldr_va	r8, cr_alignment)
 
 	ldmia	r0, {r3 - r5}
 	add	r0, sp, #S_PC		@ here for interlock avoidance
@@ -379,8 +367,6 @@ ENDPROC(__fiq_abt)
 	str	r3, [sp]		@ save the "real" r0 copied
 					@ from the exception stack
 
- ATRAP(	ldr	r8, [r8, #0])
-
 	@
 	@ We are now ready to fill in the remaining blanks on the stack:
 	@
@@ -505,9 +491,7 @@ __und_usr_thumb:
  */
 #if __LINUX_ARM_ARCH__ < 7
 /* If the target CPU may not be Thumb-2-capable, a run-time check is needed: */
-#define NEED_CPU_ARCHITECTURE
-	ldr	r5, .LCcpu_architecture
-	ldr	r5, [r5]
+	ldr_va	r5, cpu_architecture
 	cmp	r5, #CPU_ARCH_ARMv7
 	blo	__und_usr_fault_16		@ 16bit undefined instruction
 /*
@@ -654,12 +638,6 @@ call_fpe:
 	ret.w	lr				@ CP#14 (Debug)
 	ret.w	lr				@ CP#15 (Control)
 
-#ifdef NEED_CPU_ARCHITECTURE
-	.align	2
-.LCcpu_architecture:
-	.word	__cpu_architecture
-#endif
-
 #ifdef CONFIG_NEON
 	.align	6
 
@@ -685,9 +663,8 @@ call_fpe:
 #endif
 
 do_fpe:
-	ldr	r4, .LCfp
 	add	r10, r10, #TI_FPSTATE		@ r10 = workspace
-	ldr	pc, [r4]			@ Call FP module USR entry point
+	ldr_va	pc, fp_enter, tmp=r4		@ Call FP module USR entry point
 
 /*
  * The FP module is called with these registers set:
@@ -1101,6 +1078,12 @@ __kuser_helper_end:
  */
 	.macro	vector_stub, name, mode, correction=0
 	.align	5
+#ifdef CONFIG_HARDEN_BRANCH_HISTORY
+vector_bhb_bpiall_\name:
+	mcr	p15, 0, r0, c7, c5, 6	@ BPIALL
+	@ isb not needed due to "movs pc, lr" in the vector stub
+	@ which gives a "context synchronisation".
+#endif
 
 vector_\name:
 	.if \correction
@@ -1111,7 +1094,8 @@ vector_\name:
 	stmia	sp, {r0, lr}		@ save r0, lr
 
 	@ Save spsr_<exception> (parent CPSR)
-2:	mrs	lr, spsr
+.Lvec_\name:
+	mrs	lr, spsr
 	str	lr, [sp, #8]		@ save spsr
 
 	@
@@ -1148,25 +1132,11 @@ vector_bhb_loop8_\name:
 3:	W(b)	. + 4
 	subs	r0, r0, #1
 	bne	3b
-	dsb
-	isb
-	b	2b
-ENDPROC(vector_bhb_loop8_\name)
-
-vector_bhb_bpiall_\name:
-	.if \correction
-	sub	lr, lr, #\correction
-	.endif
-
-	@ Save r0, lr_<exception> (parent PC)
-	stmia	sp, {r0, lr}
-
-	@ bhb workaround
-	mcr	p15, 0, r0, c7, c5, 6	@ BPIALL
+	dsb	nsh
 	@ isb not needed due to "movs pc, lr" in the vector stub
 	@ which gives a "context synchronisation".
-	b	2b
-ENDPROC(vector_bhb_bpiall_\name)
+	b	.Lvec_\name
+ENDPROC(vector_bhb_loop8_\name)
 	.previous
 #endif
 
@@ -1176,10 +1146,15 @@ ENDPROC(vector_bhb_bpiall_\name)
 	.endm
 
 	.section .stubs, "ax", %progbits
-	@ This must be the first word
+	@ These need to remain at the start of the section so that
+	@ they are in range of the 'SWI' entries in the vector tables
+	@ located 4k down.
+.L__vector_swi:
 	.word	vector_swi
 #ifdef CONFIG_HARDEN_BRANCH_HISTORY
+.L__vector_bhb_loop8_swi:
 	.word	vector_bhb_loop8_swi
+.L__vector_bhb_bpiall_swi:
 	.word	vector_bhb_bpiall_swi
 #endif
 
@@ -1322,10 +1297,11 @@ vector_addrexcptn:
 	.globl	vector_fiq
 
 	.section .vectors, "ax", %progbits
-.L__vectors_start:
 	W(b)	vector_rst
 	W(b)	vector_und
-	W(ldr)	pc, .L__vectors_start + 0x1000
+ARM(	.reloc	., R_ARM_LDR_PC_G0, .L__vector_swi		)
+THUMB(	.reloc	., R_ARM_THM_PC12, .L__vector_swi		)
+	W(ldr)	pc, .
 	W(b)	vector_pabt
 	W(b)	vector_dabt
 	W(b)	vector_addrexcptn
@@ -1334,21 +1310,23 @@ vector_addrexcptn:
 
 #ifdef CONFIG_HARDEN_BRANCH_HISTORY
 	.section .vectors.bhb.loop8, "ax", %progbits
-.L__vectors_bhb_loop8_start:
 	W(b)	vector_rst
 	W(b)	vector_bhb_loop8_und
-	W(ldr)	pc, .L__vectors_bhb_loop8_start + 0x1004
+ARM(	.reloc	., R_ARM_LDR_PC_G0, .L__vector_bhb_loop8_swi	)
+THUMB(	.reloc	., R_ARM_THM_PC12, .L__vector_bhb_loop8_swi	)
+	W(ldr)	pc, .
 	W(b)	vector_bhb_loop8_pabt
 	W(b)	vector_bhb_loop8_dabt
 	W(b)	vector_addrexcptn
 	W(b)	vector_bhb_loop8_irq
 	W(b)	vector_bhb_loop8_fiq
 
 	.section .vectors.bhb.bpiall, "ax", %progbits
-.L__vectors_bhb_bpiall_start:
 	W(b)	vector_rst
 	W(b)	vector_bhb_bpiall_und
-	W(ldr)	pc, .L__vectors_bhb_bpiall_start + 0x1008
+ARM(	.reloc	., R_ARM_LDR_PC_G0, .L__vector_bhb_bpiall_swi	)
+THUMB(	.reloc	., R_ARM_THM_PC12, .L__vector_bhb_bpiall_swi	)
+	W(ldr)	pc, .
 	W(b)	vector_bhb_bpiall_pabt
 	W(b)	vector_bhb_bpiall_dabt
 	W(b)	vector_addrexcptn

arch/arm/kernel/entry-common.S

@@ -164,7 +164,7 @@ ENTRY(vector_bhb_loop8_swi)
 1:	b	2f
 2:	subs	r8, r8, #1
 	bne	1b
-	dsb
+	dsb	nsh
 	isb
 	b	3f
 ENDPROC(vector_bhb_loop8_swi)
@@ -198,7 +198,7 @@ ENTRY(vector_swi)
 #endif
 	reload_current r10, ip
 	zero_fp
-	alignment_trap r10, ip, __cr_alignment
+	alignment_trap r10, ip, cr_alignment
 	asm_trace_hardirqs_on save=0
 	enable_irq_notrace
 	ct_user_exit save=0
@@ -328,14 +328,6 @@ __sys_trace_return:
 	bl	syscall_trace_exit
 	b	ret_slow_syscall
 
-	.align	5
-#ifdef CONFIG_ALIGNMENT_TRAP
-	.type	__cr_alignment, #object
-__cr_alignment:
-	.word	cr_alignment
-#endif
-	.ltorg
-
 	.macro	syscall_table_start, sym
 	.equ	__sys_nr, 0
 	.type	\sym, #object

arch/arm/kernel/entry-header.S

@@ -48,8 +48,7 @@
 	.macro	alignment_trap, rtmp1, rtmp2, label
 #ifdef CONFIG_ALIGNMENT_TRAP
 	mrc	p15, 0, \rtmp2, c1, c0, 0
-	ldr	\rtmp1, \label
-	ldr	\rtmp1, [\rtmp1]
+	ldr_va	\rtmp1, \label
 	teq	\rtmp1, \rtmp2
 	mcrne	p15, 0, \rtmp1, c1, c0, 0
 #endif