Merge "Merge android-4.4@610af85 (v4.4.85) into msm-4.4"

11 files changed, 74 insertions, 44 deletions

diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index 210ef3e72332..0ddd7144c492 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -88,7 +88,9 @@ extern int ioc_exists;
 #define ARC_REG_SLC_FLUSH	0x904
 #define ARC_REG_SLC_INVALIDATE	0x905
 #define ARC_REG_SLC_RGN_START	0x914
+#define ARC_REG_SLC_RGN_START1	0x915
 #define ARC_REG_SLC_RGN_END	0x916
+#define ARC_REG_SLC_RGN_END1	0x917
 
 /* Bit val in SLC_CONTROL */
 #define SLC_CTRL_IM		0x040
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index d81b6d7e11e7..9a84cbdd44b0 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -543,6 +543,7 @@ noinline void slc_op(phys_addr_t paddr, unsigned long sz, const int op)
 	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
 	unsigned int ctrl;
+	phys_addr_t end;
 
 	spin_lock_irqsave(&lock, flags);
 
@@ -572,8 +573,16 @@ noinline void slc_op(phys_addr_t paddr, unsigned long sz, const int op)
 	 * END needs to be setup before START (latter triggers the operation)
 	 * END can't be same as START, so add (l2_line_sz - 1) to sz
 	 */
-	write_aux_reg(ARC_REG_SLC_RGN_END, (paddr + sz + l2_line_sz - 1));
-	write_aux_reg(ARC_REG_SLC_RGN_START, paddr);
+	end = paddr + sz + l2_line_sz - 1;
+	if (is_pae40_enabled())
+		write_aux_reg(ARC_REG_SLC_RGN_END1, upper_32_bits(end));
+
+	write_aux_reg(ARC_REG_SLC_RGN_END, lower_32_bits(end));
+
+	if (is_pae40_enabled())
+		write_aux_reg(ARC_REG_SLC_RGN_START1, upper_32_bits(paddr));
+
+	write_aux_reg(ARC_REG_SLC_RGN_START, lower_32_bits(paddr));
 
 	while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
 
diff --git a/arch/arm64/include/asm/current.h b/arch/arm64/include/asm/current.h
index 2e61d21294ba..483a6c9d3e10 100644
--- a/arch/arm64/include/asm/current.h
+++ b/arch/arm64/include/asm/current.h
@@ -10,9 +10,17 @@
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 struct task_struct;
 
+/*
+ * We don't use read_sysreg() as we want the compiler to cache the value where
+ * possible.
+ */
 static __always_inline struct task_struct *get_current(void)
 {
-	return (struct task_struct *)read_sysreg(sp_el0);
+	unsigned long sp_el0;
+
+	asm ("mrs %0, sp_el0" : "=r" (sp_el0));
+
+	return (struct task_struct *)sp_el0;
 }
 #define current get_current()
 #else
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index b98332269462..9d9287277201 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -115,10 +115,10 @@
 
 /*
  * This is the base location for PIE (ET_DYN with INTERP) loads. On
- * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * 64-bit, this is above 4GB to leave the entire 32-bit address
  * space open for things that want to use the area for 32-bit pointers.
  */
-#define ELF_ET_DYN_BASE		0x100000000UL
+#define ELF_ET_DYN_BASE		(2 * TASK_SIZE_64 / 3)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index a05033beb2a2..4325b3622a92 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -28,8 +28,10 @@ DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
  * We don't use this_cpu_read(cpu_number) as that has implicit writes to
  * preempt_count, and associated (compiler) barriers, that we'd like to avoid
  * the expense of. If we're preemptible, the value can be stale at use anyway.
+ * And we can't use this_cpu_ptr() either, as that winds up recursing back
+ * here under CONFIG_DEBUG_PREEMPT=y.
  */
-#define raw_smp_processor_id() (*this_cpu_ptr(&cpu_number))
+#define raw_smp_processor_id() (*raw_cpu_ptr(&cpu_number))
 
 struct seq_file;
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index f592e7406fc5..b8b40d95ebef 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -369,7 +369,7 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_THREAD_INFO_IN_TASK
 	init_task.thread_info.ttbr0 = virt_to_phys(empty_zero_page);
 #else
-	init_thread_info.ttbr0 = (init_thread_union.thread_info);
+	init_thread_info.ttbr0 = virt_to_phys(empty_zero_page);
 #endif
 #endif
 
diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
index 1cd792db15ef..1eab79c9ac48 100644
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
@@ -117,11 +117,10 @@
 	.set T1, REG_T1
 .endm
 
-#define K_BASE		%r8
 #define HASH_PTR	%r9
+#define BLOCKS_CTR	%r8
 #define BUFFER_PTR	%r10
 #define BUFFER_PTR2	%r13
-#define BUFFER_END	%r11
 
 #define PRECALC_BUF	%r14
 #define WK_BUF		%r15
@@ -205,14 +204,14 @@
 		 * blended AVX2 and ALU instruction scheduling
 		 * 1 vector iteration per 8 rounds
 		 */
-		vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP
+		vmovdqu (i * 2)(BUFFER_PTR), W_TMP
 	.elseif ((i & 7) == 1)
-		vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\
+		vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\
 			 WY_TMP, WY_TMP
 	.elseif ((i & 7) == 2)
 		vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY
 	.elseif ((i & 7) == 4)
-		vpaddd  K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 	.elseif ((i & 7) == 7)
 		vmovdqu  WY_TMP, PRECALC_WK(i&~7)
 
@@ -255,7 +254,7 @@
 		vpxor	WY, WY_TMP, WY_TMP
 	.elseif ((i & 7) == 7)
 		vpxor	WY_TMP2, WY_TMP, WY
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -291,7 +290,7 @@
 		vpsrld	$30, WY, WY
 		vpor	WY, WY_TMP, WY
 	.elseif ((i & 7) == 7)
-		vpaddd	K_XMM(K_BASE), WY, WY_TMP
+		vpaddd  K_XMM + K_XMM_AR(%rip), WY, WY_TMP
 		vmovdqu	WY_TMP, PRECALC_WK(i&~7)
 
 		PRECALC_ROTATE_WY
@@ -446,6 +445,16 @@
 
 .endm
 
+/* Add constant only if (%2 > %3) condition met (uses RTA as temp)
+ * %1 + %2 >= %3 ? %4 : 0
+ */
+.macro ADD_IF_GE a, b, c, d
+	mov     \a, RTA
+	add     $\d, RTA
+	cmp     $\c, \b
+	cmovge  RTA, \a
+.endm
+
 /*
  * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining
  */
@@ -463,13 +472,16 @@
 	lea	(2*4*80+32)(%rsp), WK_BUF
 
 	# Precalc WK for first 2 blocks
-	PRECALC_OFFSET = 0
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64
 	.set i, 0
 	.rept    160
 		PRECALC i
 		.set i, i + 1
 	.endr
-	PRECALC_OFFSET = 128
+
+	/* Go to next block if needed */
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 	xchg	WK_BUF, PRECALC_BUF
 
 	.align 32
@@ -479,8 +491,8 @@ _loop:
 	 * we use K_BASE value as a signal of a last block,
 	 * it is set below by: cmovae BUFFER_PTR, K_BASE
 	 */
-	cmp	K_BASE, BUFFER_PTR
-	jne	_begin
+	test BLOCKS_CTR, BLOCKS_CTR
+	jnz _begin
 	.align 32
 	jmp	_end
 	.align 32
@@ -512,10 +524,10 @@ _loop0:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR       /* move to next odd-64-byte block */
-	cmp	BUFFER_END, BUFFER_PTR    /* is current block the last one? */
-	cmovae	K_BASE, BUFFER_PTR	/* signal the last iteration smartly */
-
+	/* Update Counter */
+	sub $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128
 	/*
 	 * rounds
 	 * 60,62,64,66,68
@@ -532,8 +544,8 @@ _loop0:
 	UPDATE_HASH	12(HASH_PTR), D
 	UPDATE_HASH	16(HASH_PTR), E
 
-	cmp	K_BASE, BUFFER_PTR	/* is current block the last one? */
-	je	_loop
+	test	BLOCKS_CTR, BLOCKS_CTR
+	jz	_loop
 
 	mov	TB, B
 
@@ -575,10 +587,10 @@ _loop2:
 		.set j, j+2
 	.endr
 
-	add	$(2*64), BUFFER_PTR2      /* move to next even-64-byte block */
-
-	cmp	BUFFER_END, BUFFER_PTR2   /* is current block the last one */
-	cmovae	K_BASE, BUFFER_PTR       /* signal the last iteration smartly */
+	/* update counter */
+	sub     $1, BLOCKS_CTR
+	/* Move to the next block only if needed*/
+	ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
 
 	jmp	_loop3
 _loop3:
@@ -641,19 +653,12 @@ _loop3:
 
 	avx2_zeroupper
 
-	lea	K_XMM_AR(%rip), K_BASE
-
+	/* Setup initial values */
 	mov	CTX, HASH_PTR
 	mov	BUF, BUFFER_PTR
-	lea	64(BUF), BUFFER_PTR2
-
-	shl	$6, CNT			/* mul by 64 */
-	add	BUF, CNT
-	add	$64, CNT
-	mov	CNT, BUFFER_END
 
-	cmp	BUFFER_END, BUFFER_PTR2
-	cmovae	K_BASE, BUFFER_PTR2
+	mov	BUF, BUFFER_PTR2
+	mov	CNT, BLOCKS_CTR
 
 	xmm_mov	BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP
 
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 7de207a11014..dd14616b7739 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data,
 
 static bool avx2_usable(void)
 {
-	if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
+	if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
 		&& boot_cpu_has(X86_FEATURE_BMI1)
 		&& boot_cpu_has(X86_FEATURE_BMI2))
 		return true;
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a55697d19824..cc0f2f5da19b 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1190,6 +1190,8 @@ ENTRY(nmi)
 	 * other IST entries.
 	 */
 
+	ASM_CLAC
+
 	/* Use %rdx as our temp variable throughout */
 	pushq	%rdx
 
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 07cf288b692e..bcd3d6199464 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -247,11 +247,11 @@ extern int force_personality32;
 
 /*
  * This is the base location for PIE (ET_DYN with INTERP) loads. On
- * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * 64-bit, this is above 4GB to leave the entire 32-bit address
  * space open for things that want to use the area for 32-bit pointers.
  */
 #define ELF_ET_DYN_BASE		(mmap_is_ia32() ? 0x000400000UL : \
-						  0x100000000UL)
+						  (TASK_SIZE / 3 * 2))
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports.  This could be done in user space,
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 8900400230c6..2cdae69d7e0b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -153,7 +153,7 @@ static void __intel_pmu_lbr_enable(bool pmi)
 	 */
 	if (cpuc->lbr_sel)
 		lbr_select = cpuc->lbr_sel->config;
-	if (!pmi)
+	if (!pmi && cpuc->lbr_sel)
 		wrmsrl(MSR_LBR_SELECT, lbr_select);
 
 	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
@@ -432,8 +432,10 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 	int out = 0;
 	int num = x86_pmu.lbr_nr;
 
-	if (cpuc->lbr_sel->config & LBR_CALL_STACK)
-		num = tos;
+	if (cpuc->lbr_sel) {
+		if (cpuc->lbr_sel->config & LBR_CALL_STACK)
+			num = tos;
+	}
 
 	for (i = 0; i < num; i++) {
 		unsigned long lbr_idx = (tos - i) & mask;