Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM updates from Russell King:
 "This set includes adding support for Neon acceleration of RAID6 XOR
  code from Ard Biesheuvel, cache flushing and barrier updates from Will
  Deacon, and a cleanup to the ARM debug code which reduces the amount
  of code by about 500 lines.

  A few other cleanups, such as constifying the machine descriptors
  which already shouldn't be written to, cleaning up the printing of the
  L2 cache size"

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (55 commits)
  ARM: 7826/1: debug: support debug ll on hisilicon soc
  ARM: 7830/1: delay: don't bother reporting bogomips in /proc/cpuinfo
  ARM: 7829/1: Add ".text.unlikely" and ".text.hot" to arm unwind tables
  ARM: 7828/1: ARMv7-M: implement restart routine common to all v7-M machines
  ARM: 7827/1: highbank: fix debug uart virtual address for LPAE
  ARM: 7823/1: errata: workaround Cortex-A15 erratum 773022
  ARM: 7806/1: allow DEBUG_UNCOMPRESS for Tegra
  ARM: 7793/1: debug: use generic option for ep93xx PL10x debug port
  ARM: debug: move SPEAr debug to generic PL01x code
  ARM: debug: move davinci debug to generic 8250 code
  ARM: debug: move keystone debug to generic 8250 code
  ARM: debug: remove DEBUG_ROCKCHIP_UART
  ARM: debug: provide generic option choices for 8250 and PL01x ports
  ARM: debug: move PL01X debug include into arch/arm/include/debug/
  ARM: debug: provide PL01x debug uart phys/virt address configuration options
  ARM: debug: add support for word accesses to debug/8250.S
  ARM: debug: move 8250 debug include into arch/arm/include/debug/
  ARM: debug: provide 8250 debug uart phys/virt address configuration options
  ARM: debug: provide 8250 debug uart register shift configuration option
  ARM: debug: provide 8250 debug uart flow control configuration option
  ...

1 files changed, 149 insertions, 32 deletions

diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index f467e9b3f8d5..38960264040c 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -319,67 +319,110 @@ extern struct cpu_tlb_fns cpu_tlb;
 #define tlb_op(f, regs, arg)	__tlb_op(f, "p15, 0, %0, " regs, arg)
 #define tlb_l2_op(f, regs, arg)	__tlb_op(f, "p15, 1, %0, " regs, arg)
 
-static inline void local_flush_tlb_all(void)
+static inline void __local_flush_tlb_all(void)
 {
 	const int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
-	if (tlb_flag(TLB_WB))
-		dsb();
-
 	tlb_op(TLB_V4_U_FULL | TLB_V6_U_FULL, "c8, c7, 0", zero);
 	tlb_op(TLB_V4_D_FULL | TLB_V6_D_FULL, "c8, c6, 0", zero);
 	tlb_op(TLB_V4_I_FULL | TLB_V6_I_FULL, "c8, c5, 0", zero);
-	tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero);
+}
+
+static inline void local_flush_tlb_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_all();
+	tlb_op(TLB_V7_UIS_FULL, "c8, c7, 0", zero);
 
 	if (tlb_flag(TLB_BARRIER)) {
-		dsb();
+		dsb(nsh);
 		isb();
 	}
 }
 
-static inline void local_flush_tlb_mm(struct mm_struct *mm)
+static inline void __flush_tlb_all(void)
 {
 	const int zero = 0;
-	const int asid = ASID(mm);
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
 	if (tlb_flag(TLB_WB))
-		dsb();
+		dsb(ishst);
+
+	__local_flush_tlb_all();
+	tlb_op(TLB_V7_UIS_FULL, "c8, c3, 0", zero);
+
+	if (tlb_flag(TLB_BARRIER)) {
+		dsb(ish);
+		isb();
+	}
+}
+
+static inline void __local_flush_tlb_mm(struct mm_struct *mm)
+{
+	const int zero = 0;
+	const int asid = ASID(mm);
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
 	if (possible_tlb_flags & (TLB_V4_U_FULL|TLB_V4_D_FULL|TLB_V4_I_FULL)) {
-		if (cpumask_test_cpu(get_cpu(), mm_cpumask(mm))) {
+		if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
 			tlb_op(TLB_V4_U_FULL, "c8, c7, 0", zero);
 			tlb_op(TLB_V4_D_FULL, "c8, c6, 0", zero);
 			tlb_op(TLB_V4_I_FULL, "c8, c5, 0", zero);
 		}
-		put_cpu();
 	}
 
 	tlb_op(TLB_V6_U_ASID, "c8, c7, 2", asid);
 	tlb_op(TLB_V6_D_ASID, "c8, c6, 2", asid);
 	tlb_op(TLB_V6_I_ASID, "c8, c5, 2", asid);
+}
+
+static inline void local_flush_tlb_mm(struct mm_struct *mm)
+{
+	const int asid = ASID(mm);
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_mm(mm);
+	tlb_op(TLB_V7_UIS_ASID, "c8, c7, 2", asid);
+
+	if (tlb_flag(TLB_BARRIER))
+		dsb(nsh);
+}
+
+static inline void __flush_tlb_mm(struct mm_struct *mm)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_mm(mm);
 #ifdef CONFIG_ARM_ERRATA_720789
-	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", zero);
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 0", 0);
 #else
-	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", asid);
+	tlb_op(TLB_V7_UIS_ASID, "c8, c3, 2", ASID(mm));
 #endif
 
 	if (tlb_flag(TLB_BARRIER))
-		dsb();
+		dsb(ish);
 }
 
 static inline void
-local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 {
 	const int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
 	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
 
-	if (tlb_flag(TLB_WB))
-		dsb();
-
 	if (possible_tlb_flags & (TLB_V4_U_PAGE|TLB_V4_D_PAGE|TLB_V4_I_PAGE|TLB_V4_I_FULL) &&
 	    cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
 		tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", uaddr);
@@ -392,6 +435,36 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", uaddr);
 	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", uaddr);
 	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", uaddr);
+}
+
+static inline void
+local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_page(vma, uaddr);
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", uaddr);
+
+	if (tlb_flag(TLB_BARRIER))
+		dsb(nsh);
+}
+
+static inline void
+__flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_page(vma, uaddr);
 #ifdef CONFIG_ARM_ERRATA_720789
 	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 3", uaddr & PAGE_MASK);
 #else
@@ -399,19 +472,14 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 #endif
 
 	if (tlb_flag(TLB_BARRIER))
-		dsb();
+		dsb(ish);
 }
 
-static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
+static inline void __local_flush_tlb_kernel_page(unsigned long kaddr)
 {
 	const int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
-	kaddr &= PAGE_MASK;
-
-	if (tlb_flag(TLB_WB))
-		dsb();
-
 	tlb_op(TLB_V4_U_PAGE, "c8, c7, 1", kaddr);
 	tlb_op(TLB_V4_D_PAGE, "c8, c6, 1", kaddr);
 	tlb_op(TLB_V4_I_PAGE, "c8, c5, 1", kaddr);
@@ -421,26 +489,75 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
 	tlb_op(TLB_V6_U_PAGE, "c8, c7, 1", kaddr);
 	tlb_op(TLB_V6_D_PAGE, "c8, c6, 1", kaddr);
 	tlb_op(TLB_V6_I_PAGE, "c8, c5, 1", kaddr);
+}
+
+static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	kaddr &= PAGE_MASK;
+
+	if (tlb_flag(TLB_WB))
+		dsb(nshst);
+
+	__local_flush_tlb_kernel_page(kaddr);
+	tlb_op(TLB_V7_UIS_PAGE, "c8, c7, 1", kaddr);
+
+	if (tlb_flag(TLB_BARRIER)) {
+		dsb(nsh);
+		isb();
+	}
+}
+
+static inline void __flush_tlb_kernel_page(unsigned long kaddr)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	kaddr &= PAGE_MASK;
+
+	if (tlb_flag(TLB_WB))
+		dsb(ishst);
+
+	__local_flush_tlb_kernel_page(kaddr);
 	tlb_op(TLB_V7_UIS_PAGE, "c8, c3, 1", kaddr);
 
 	if (tlb_flag(TLB_BARRIER)) {
-		dsb();
+		dsb(ish);
 		isb();
 	}
 }
 
+/*
+ * Branch predictor maintenance is paired with full TLB invalidation, so
+ * there is no need for any barriers here.
+ */
+static inline void __local_flush_bp_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_V6_BP))
+		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero));
+}
+
 static inline void local_flush_bp_all(void)
 {
 	const int zero = 0;
 	const unsigned int __tlb_flag = __cpu_tlb_flags;
 
+	__local_flush_bp_all();
 	if (tlb_flag(TLB_V7_UIS_BP))
-		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero));
-	else if (tlb_flag(TLB_V6_BP))
 		asm("mcr p15, 0, %0, c7, c5, 6" : : "r" (zero));
+}
 
-	if (tlb_flag(TLB_BARRIER))
-		isb();
+static inline void __flush_bp_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	__local_flush_bp_all();
+	if (tlb_flag(TLB_V7_UIS_BP))
+		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero));
 }
 
 #include <asm/cputype.h>
@@ -461,7 +578,7 @@ static inline void dummy_flush_tlb_a15_erratum(void)
 	 * Dummy TLBIMVAIS. Using the unmapped address 0 and ASID 0.
 	 */
 	asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
-	dsb();
+	dsb(ish);
 }
 #else
 static inline int erratum_a15_798181(void)
@@ -495,7 +612,7 @@ static inline void flush_pmd_entry(void *pmd)
 	tlb_l2_op(TLB_L2CLEAN_FR, "c15, c9, 1  @ L2 flush_pmd", pmd);
 
 	if (tlb_flag(TLB_WB))
-		dsb();
+		dsb(ishst);
 }
 
 static inline void clean_pmd_entry(void *pmd)