Merge branch 'linux-linaro-lsk' into linux-linaro-lsk-android

18 files changed, 113 insertions, 40 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index a4429bcd609..00e3702ec79 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -404,6 +404,12 @@ config CLONE_BACKWARDS2
 	help
 	  Architecture has the first two arguments of clone(2) swapped.
 
+config CLONE_BACKWARDS3
+	bool
+	help
+	  Architecture has tls passed as the 3rd argument of clone(2),
+	  not the 5th one.
+
 config ODD_RT_SIGACTION
 	bool
 	help
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 18d50322a9e..4bb08e3e52b 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -37,16 +37,18 @@
 #define c5_AIFSR	15	/* Auxilary Instrunction Fault Status R */
 #define c6_DFAR		16	/* Data Fault Address Register */
 #define c6_IFAR		17	/* Instruction Fault Address Register */
-#define c9_L2CTLR	18	/* Cortex A15 L2 Control Register */
-#define c10_PRRR	19	/* Primary Region Remap Register */
-#define c10_NMRR	20	/* Normal Memory Remap Register */
-#define c12_VBAR	21	/* Vector Base Address Register */
-#define c13_CID		22	/* Context ID Register */
-#define c13_TID_URW	23	/* Thread ID, User R/W */
-#define c13_TID_URO	24	/* Thread ID, User R/O */
-#define c13_TID_PRIV	25	/* Thread ID, Privileged */
-#define c14_CNTKCTL	26	/* Timer Control Register (PL1) */
-#define NR_CP15_REGS	27	/* Number of regs (incl. invalid) */
+#define c7_PAR		18	/* Physical Address Register */
+#define c7_PAR_high	19	/* PAR top 32 bits */
+#define c9_L2CTLR	20	/* Cortex A15 L2 Control Register */
+#define c10_PRRR	21	/* Primary Region Remap Register */
+#define c10_NMRR	22	/* Normal Memory Remap Register */
+#define c12_VBAR	23	/* Vector Base Address Register */
+#define c13_CID		24	/* Context ID Register */
+#define c13_TID_URW	25	/* Thread ID, User R/W */
+#define c13_TID_URO	26	/* Thread ID, User R/O */
+#define c13_TID_PRIV	27	/* Thread ID, Privileged */
+#define c14_CNTKCTL	28	/* Timer Control Register (PL1) */
+#define NR_CP15_REGS	29	/* Number of regs (incl. invalid) */
 
 #define ARM_EXCEPTION_RESET	  0
 #define ARM_EXCEPTION_UNDEFINED   1
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index bdf2b8458ec..aa9b4ac3fdf 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -43,6 +43,7 @@ struct mmu_gather {
 	struct mm_struct	*mm;
 	unsigned int		fullmm;
 	struct vm_area_struct	*vma;
+	unsigned long		start, end;
 	unsigned long		range_start;
 	unsigned long		range_end;
 	unsigned int		nr;
@@ -107,10 +108,12 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
-	tlb->fullmm = fullmm;
+	tlb->fullmm = !(start | (end+1));
+	tlb->start = start;
+	tlb->end = end;
 	tlb->vma = NULL;
 	tlb->max = ARRAY_SIZE(tlb->local);
 	tlb->pages = tlb->local;
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 9e7076df89e..3a9d627cab6 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -54,7 +54,12 @@ armpmu_map_cache_event(const unsigned (*cache_map)
 static int
 armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
 {
-	int mapping = (*event_map)[config];
+	int mapping;
+
+	if (config >= PERF_COUNT_HW_MAX)
+		return -ENOENT;
+
+	mapping = (*event_map)[config];
 	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
 }
 
@@ -268,6 +273,9 @@ validate_event(struct pmu_hw_events *hw_events,
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct pmu *leader_pmu = event->group_leader->pmu;
 
+	if (is_software_event(event))
+		return 1;
+
 	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
 		return 1;
 
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 8eea97be1ed..4a519907043 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -180,6 +180,10 @@ static const struct coproc_reg cp15_regs[] = {
 			NULL, reset_unknown, c6_DFAR },
 	{ CRn( 6), CRm( 0), Op1( 0), Op2( 2), is32,
 			NULL, reset_unknown, c6_IFAR },
+
+	/* PAR swapped by interrupt.S */
+	{ CRn( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR },
+
 	/*
 	 * DC{C,I,CI}SW operations:
 	 */
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index f7793df62f5..16cd4ba5d7f 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -49,6 +49,7 @@ __kvm_hyp_code_start:
 ENTRY(__kvm_tlb_flush_vmid_ipa)
 	push	{r2, r3}
 
+	dsb	ishst
 	add	r0, r0, #KVM_VTTBR
 	ldrd	r2, r3, [r0]
 	mcrr	p15, 6, r2, r3, c2	@ Write VTTBR
@@ -291,6 +292,7 @@ THUMB(	orr	r2, r2, #PSR_T_BIT	)
 	ldr	r2, =BSYM(panic)
 	msr	ELR_hyp, r2
 	ldr	r0, =\panic_str
+	clrex				@ Clear exclusive monitor
 	eret
 .endm
 
@@ -414,6 +416,10 @@ guest_trap:
 	mrcne	p15, 4, r2, c6, c0, 4	@ HPFAR
 	bne	3f
 
+	/* Preserve PAR */
+	mrrc	p15, 0, r0, r1, c7	@ PAR
+	push	{r0, r1}
+
 	/* Resolve IPA using the xFAR */
 	mcr	p15, 0, r2, c7, c8, 0	@ ATS1CPR
 	isb
@@ -424,13 +430,20 @@ guest_trap:
 	lsl	r2, r2, #4
 	orr	r2, r2, r1, lsl #24
 
+	/* Restore PAR */
+	pop	{r0, r1}
+	mcrr	p15, 0, r0, r1, c7	@ PAR
+
 3:	load_vcpu			@ Load VCPU pointer to r0
 	str	r2, [r0, #VCPU_HPFAR]
 
 1:	mov	r1, #ARM_EXCEPTION_HVC
 	b	__kvm_vcpu_return
 
-4:	pop	{r0, r1, r2}		@ Failed translation, return to guest
+4:	pop	{r0, r1}		@ Failed translation, return to guest
+	mcrr	p15, 0, r0, r1, c7	@ PAR
+	clrex
+	pop	{r0, r1, r2}
 	eret
 
 /*
@@ -456,6 +469,7 @@ switch_to_guest_vfp:
 
 	pop	{r3-r7}
 	pop	{r0-r2}
+	clrex
 	eret
 #endif
 
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 3c8f2f0b4c5..2b44b95a86d 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -302,11 +302,14 @@ vcpu	.req	r0		@ vcpu pointer always in r0
 	.endif
 
 	mrc	p15, 0, r2, c14, c1, 0	@ CNTKCTL
+	mrrc	p15, 0, r4, r5, c7	@ PAR
 
 	.if \store_to_vcpu == 0
-	push	{r2}
+	push	{r2,r4-r5}
 	.else
 	str	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
+	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
+	strd	r4, r5, [r12]
 	.endif
 .endm
 
@@ -319,12 +322,15 @@ vcpu	.req	r0		@ vcpu pointer always in r0
  */
 .macro write_cp15_state read_from_vcpu
 	.if \read_from_vcpu == 0
-	pop	{r2}
+	pop	{r2,r4-r5}
 	.else
 	ldr	r2, [vcpu, #CP15_OFFSET(c14_CNTKCTL)]
+	add	r12, vcpu, #CP15_OFFSET(c7_PAR)
+	ldrd	r4, r5, [r12]
 	.endif
 
 	mcr	p15, 0, r2, c14, c1, 0	@ CNTKCTL
+	mcrr	p15, 0, r4, r5, c7	@ PAR
 
 	.if \read_from_vcpu == 0
 	pop	{r2-r12}
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 654f0968030..5546653e5cc 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -35,6 +35,7 @@ struct mmu_gather {
 	struct mm_struct	*mm;
 	unsigned int		fullmm;
 	struct vm_area_struct	*vma;
+	unsigned long		start, end;
 	unsigned long		range_start;
 	unsigned long		range_end;
 	unsigned int		nr;
@@ -97,10 +98,12 @@ static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int fullmm)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
-	tlb->fullmm = fullmm;
+	tlb->fullmm = !(start | (end+1));
+	tlb->start = start;
+	tlb->end = end;
 	tlb->vma = NULL;
 	tlb->max = ARRAY_SIZE(tlb->local);
 	tlb->pages = tlb->local;
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index ef3a9de0195..bc5efc7c3f3 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -22,7 +22,7 @@
  * unmapping a portion of the virtual address space, these hooks are called according to
  * the following template:
  *
- *	tlb <- tlb_gather_mmu(mm, full_mm_flush);	// start unmap for address space MM
+ *	tlb <- tlb_gather_mmu(mm, start, end);		// start unmap for address space MM
  *	{
  *	  for each vma that needs a shootdown do {
  *	    tlb_start_vma(tlb, vma);
@@ -58,6 +58,7 @@ struct mmu_gather {
 	unsigned int		max;
 	unsigned char		fullmm;		/* non-zero means full mm flush */
 	unsigned char		need_flush;	/* really unmapped some PTEs? */
+	unsigned long		start, end;
 	unsigned long		start_addr;
 	unsigned long		end_addr;
 	struct page		**pages;
@@ -155,13 +156,15 @@ static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
 	tlb->max = ARRAY_SIZE(tlb->local);
 	tlb->pages = tlb->local;
 	tlb->nr = 0;
-	tlb->fullmm = full_mm_flush;
+	tlb->fullmm = !(start | (end+1));
+	tlb->start = start;
+	tlb->end = end;
 	tlb->start_addr = ~0UL;
 }
 
diff --git a/arch/m68k/emu/natfeat.c b/arch/m68k/emu/natfeat.c
index 2291a7d69d4..fa277aecfb7 100644
--- a/arch/m68k/emu/natfeat.c
+++ b/arch/m68k/emu/natfeat.c
@@ -18,9 +18,11 @@
 #include <asm/machdep.h>
 #include <asm/natfeat.h>
 
+extern long nf_get_id2(const char *feature_name);
+
 asm("\n"
-"	.global nf_get_id,nf_call\n"
-"nf_get_id:\n"
+"	.global nf_get_id2,nf_call\n"
+"nf_get_id2:\n"
 "	.short	0x7300\n"
 "	rts\n"
 "nf_call:\n"
@@ -29,12 +31,25 @@ asm("\n"
 "1:	moveq.l	#0,%d0\n"
 "	rts\n"
 "	.section __ex_table,\"a\"\n"
-"	.long	nf_get_id,1b\n"
+"	.long	nf_get_id2,1b\n"
 "	.long	nf_call,1b\n"
 "	.previous");
-EXPORT_SYMBOL_GPL(nf_get_id);
 EXPORT_SYMBOL_GPL(nf_call);
 
+long nf_get_id(const char *feature_name)
+{
+	/* feature_name may be in vmalloc()ed memory, so make a copy */
+	char name_copy[32];
+	size_t n;
+
+	n = strlcpy(name_copy, feature_name, sizeof(name_copy));
+	if (n >= sizeof(name_copy))
+		return 0;
+
+	return nf_get_id2(name_copy);
+}
+EXPORT_SYMBOL_GPL(nf_get_id);
+
 void nfprint(const char *fmt, ...)
 {
 	static char buf[256];
diff --git a/arch/m68k/include/asm/div64.h b/arch/m68k/include/asm/div64.h
index 444ea8a09e9..ef881cfbbca 100644
--- a/arch/m68k/include/asm/div64.h
+++ b/arch/m68k/include/asm/div64.h
@@ -15,16 +15,17 @@
 		unsigned long long n64;				\
 	} __n;							\
 	unsigned long __rem, __upper;				\
+	unsigned long __base = (base);				\
 								\
 	__n.n64 = (n);						\
 	if ((__upper = __n.n32[0])) {				\
 		asm ("divul.l %2,%1:%0"				\
-			: "=d" (__n.n32[0]), "=d" (__upper)	\
-			: "d" (base), "0" (__n.n32[0]));	\
+		     : "=d" (__n.n32[0]), "=d" (__upper)	\
+		     : "d" (__base), "0" (__n.n32[0]));		\
 	}							\
 	asm ("divu.l %2,%1:%0"					\
-		: "=d" (__n.n32[1]), "=d" (__rem)		\
-		: "d" (base), "1" (__upper), "0" (__n.n32[1]));	\
+	     : "=d" (__n.n32[1]), "=d" (__rem)			\
+	     : "d" (__base), "1" (__upper), "0" (__n.n32[1]));	\
 	(n) = __n.n64;						\
 	__rem;							\
 })
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index d22a4ecffff..4fab52294d9 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -28,7 +28,7 @@ config MICROBLAZE
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IDLE_POLL_SETUP
 	select MODULES_USE_ELF_RELA
-	select CLONE_BACKWARDS
+	select CLONE_BACKWARDS3
 
 config SWAP
 	def_bool n
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index b75d7d68668..6d6d92b4ea1 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -32,6 +32,7 @@ struct mmu_gather {
 	struct mm_struct *mm;
 	struct mmu_table_batch *batch;
 	unsigned int fullmm;
+	unsigned long start, end;
 };
 
 struct mmu_table_batch {
@@ -48,10 +49,13 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
 static inline void tlb_gather_mmu(struct mmu_gather *tlb,
 				  struct mm_struct *mm,
-				  unsigned int full_mm_flush)
+				  unsigned long start,
+				  unsigned long end)
 {
 	tlb->mm = mm;
-	tlb->fullmm = full_mm_flush;
+	tlb->start = start;
+	tlb->end = end;
+	tlb->fullmm = !(start | (end+1));
 	tlb->batch = NULL;
 	if (tlb->fullmm)
 		__tlb_flush_mm(mm);
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index e61d43d9f68..362192ed12f 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -36,10 +36,12 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
-	tlb->fullmm = full_mm_flush;
+	tlb->start = start;
+	tlb->end = end;
+	tlb->fullmm = !(start | (end+1));
 
 	init_tlb_gather(tlb);
 }
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 4febacd1a8a..29b0301c18a 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -45,10 +45,12 @@ static inline void init_tlb_gather(struct mmu_gather *tlb)
 }
 
 static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned int full_mm_flush)
+tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
 	tlb->mm = mm;
-	tlb->fullmm = full_mm_flush;
+	tlb->start = start;
+	tlb->end = end;
+	tlb->fullmm = !(start | (end+1));
 
 	init_tlb_gather(tlb);
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 52441a2af53..8aac56bda7d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -314,8 +314,8 @@ static struct uncore_event_desc snbep_uncore_imc_events[] = {
 static struct uncore_event_desc snbep_uncore_qpi_events[] = {
 	INTEL_UNCORE_EVENT_DESC(clockticks,       "event=0x14"),
 	INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
-	INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x02,umask=0x08"),
-	INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x03,umask=0x04"),
+	INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x102,umask=0x08"),
+	INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x103,umask=0x04"),
 	{ /* end: all zeroes */ },
 };
 
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index dbded5aedb8..48f8375e4c6 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin,
 				*begin = new_begin;
 		}
 	} else {
-		*begin = TASK_UNMAPPED_BASE;
+		*begin = mmap_legacy_base();
 		*end = TASK_SIZE;
 	}
 }
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 845df6835f9..c1af32385ab 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -98,7 +98,7 @@ static unsigned long mmap_base(void)
  * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64
  * does, but not when emulating X86_32
  */
-static unsigned long mmap_legacy_base(void)
+unsigned long mmap_legacy_base(void)
 {
 	if (mmap_is_ia32())
 		return TASK_UNMAPPED_BASE;