Merge remote-tracking branch 'lts/linux-4.4.y' into linux-linaro-lsk-v4.4

Conflicts:
	set ARM64_WORKAROUND_CAVIUM_27456 to 12 in
	arch/arm64/include/asm/cpufeature.h
	and add asm/memory.h in arch/arm64/kernel/entry.S

diff --cc arch/arm64/Kconfig
Simple merge

diff --cc arch/arm64/include/asm/cpufeature.h
index 37a53fc6b384eadb7d5b755066ec9fe67717167c,8136afc9df0d7c3ce4db25fe814c8ebd270fc30d..876fe06222047b7d177c2b30150a6fa6b6119877
--- 1/arch/arm64/include/asm/cpufeature.h
--- 2/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@@ -30,11 -30,9 +30,13 @@@
  #define ARM64_HAS_LSE_ATOMICS                 5
  #define ARM64_WORKAROUND_CAVIUM_23154         6
  #define ARM64_WORKAROUND_834220                       7
 -#define ARM64_WORKAROUND_CAVIUM_27456         8
 +#define ARM64_HAS_NO_HW_PREFETCH              8
 +#define ARM64_HAS_UAO                         9
 +#define ARM64_ALT_PAN_NOT_UAO                 10
 +
 +#define ARM64_NCAPS                           11
++#define ARM64_WORKAROUND_CAVIUM_27456         12      
+ 
 -#define ARM64_NCAPS                           9
  
  #ifndef __ASSEMBLY__
  

diff --cc arch/arm64/include/asm/elf.h
Simple merge

diff --cc arch/arm64/kernel/cpu_errata.c
Simple merge

diff --cc arch/arm64/kernel/entry.S
index 1f7f5a2b61bf0de999d80e6ced16bec120f716b6,5a3753d09e20d607ab9419cec2d27e3aef50b8b0..588c8e1778d44a6cde02ef8ebb4b6db33652b809
--- 1/arch/arm64/kernel/entry.S
--- 2/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@@ -27,7 -27,7 +27,8 @@@
  #include <asm/cpufeature.h>
  #include <asm/errno.h>
  #include <asm/esr.h>
 +#include <asm/irq.h>
+ #include <asm/memory.h>
  #include <asm/thread_info.h>
  #include <asm/unistd.h>
  
@@@ -89,15 -89,18 +90,21 @@@
  
        .if     \el == 0
        mrs     x21, sp_el0
 -      get_thread_info tsk                     // Ensure MDSCR_EL1.SS is clear,
 +      mov     tsk, sp
 +      and     tsk, tsk, #~(THREAD_SIZE - 1)   // Ensure MDSCR_EL1.SS is clear,
        ldr     x19, [tsk, #TI_FLAGS]           // since we can unmask debug
        disable_step_tsk x19, x20               // exceptions when scheduling.
 +
 +      mov     x29, xzr                        // fp pointed to user-space
        .else
        add     x21, sp, #S_FRAME_SIZE
-       .endif
+       get_thread_info tsk
+       /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+       ldr     x20, [tsk, #TI_ADDR_LIMIT]
+       str     x20, [sp, #S_ORIG_ADDR_LIMIT]
+       mov     x20, #TASK_SIZE_64
+       str     x20, [tsk, #TI_ADDR_LIMIT]
+       .endif /* \el == 0 */
        mrs     x22, elr_el1
        mrs     x23, spsr_el1
        stp     lr, x21, [sp, #S_LR]

diff --cc arch/arm64/kernel/smp.c
Simple merge

diff --cc arch/arm64/mm/mmu.c
index cd4177a1781d8e86c99269091995a7f3090f37bc,653735a8c58a86248e37593648de4a62f301893c..8fc302d84e1f524aa0496fd213524a9d30602ebc
--- 1/arch/arm64/mm/mmu.c
--- 2/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@@ -775,73 -679,21 +775,73 @@@ void *__init __fixmap_remap_fdt(phys_ad
        dt_virt = (void *)dt_virt_base + offset;
  
        /* map the first chunk so we can read the size from the header */
 -      create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base,
 -                     SWAPPER_BLOCK_SIZE, prot);
 +      create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE),
 +                      dt_virt_base, SWAPPER_BLOCK_SIZE, prot);
  
-       if (fdt_check_header(dt_virt) != 0)
+       if (fdt_magic(dt_virt) != FDT_MAGIC)
                return NULL;
  
 -      size = fdt_totalsize(dt_virt);
 -      if (size > MAX_FDT_SIZE)
 +      *size = fdt_totalsize(dt_virt);
 +      if (*size > MAX_FDT_SIZE)
                return NULL;
  
 -      if (offset + size > SWAPPER_BLOCK_SIZE)
 -              create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base,
 -                             round_up(offset + size, SWAPPER_BLOCK_SIZE), prot);
 +      if (offset + *size > SWAPPER_BLOCK_SIZE)
 +              create_mapping_noalloc(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base,
 +                             round_up(offset + *size, SWAPPER_BLOCK_SIZE), prot);
  
 -      memblock_reserve(dt_phys, size);
 +      return dt_virt;
 +}
 +
 +void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
 +{
 +      void *dt_virt;
 +      int size;
 +
 +      dt_virt = __fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL_RO);
 +      if (!dt_virt)
 +              return NULL;
  
 +      memblock_reserve(dt_phys, size);
        return dt_virt;
  }
 +
 +int __init arch_ioremap_pud_supported(void)
 +{
 +      /* only 4k granule supports level 1 block mappings */
 +      return IS_ENABLED(CONFIG_ARM64_4K_PAGES);
 +}
 +
 +int __init arch_ioremap_pmd_supported(void)
 +{
 +      return 1;
 +}
 +
 +int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot)
 +{
 +      BUG_ON(phys & ~PUD_MASK);
 +      set_pud(pud, __pud(phys | PUD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))));
 +      return 1;
 +}
 +
 +int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot)
 +{
 +      BUG_ON(phys & ~PMD_MASK);
 +      set_pmd(pmd, __pmd(phys | PMD_TYPE_SECT | pgprot_val(mk_sect_prot(prot))));
 +      return 1;
 +}
 +
 +int pud_clear_huge(pud_t *pud)
 +{
 +      if (!pud_sect(*pud))
 +              return 0;
 +      pud_clear(pud);
 +      return 1;
 +}
 +
 +int pmd_clear_huge(pmd_t *pmd)
 +{
 +      if (!pmd_sect(*pmd))
 +              return 0;
 +      pmd_clear(pmd);
 +      return 1;
 +}

diff --cc arch/arm64/mm/proc.S
index 0c19534a901e616ecc5fe508ce205dc0de8fe0f4,18201e9e8cc71c22d017a9573cf722bdab63de74..a92738e8b1eb670772e9314643eadc29d7f954ba
--- 1/arch/arm64/mm/proc.S
--- 2/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@@ -137,36 -139,20 +139,46 @@@ ENTRY(cpu_do_switch_mm
        bfi     x0, x1, #48, #16                // set the ASID
        msr     ttbr0_el1, x0                   // set TTBR0
        isb
+ alternative_if_not ARM64_WORKAROUND_CAVIUM_27456
        ret
+       nop
+       nop
+       nop
+ alternative_else
+       ic      iallu
+       dsb     nsh
+       isb
+       ret
+ alternative_endif
  ENDPROC(cpu_do_switch_mm)
  
 -      .section ".text.init", #alloc, #execinstr
 +      .pushsection ".idmap.text", "ax"
 +/*
 + * void idmap_cpu_replace_ttbr1(phys_addr_t new_pgd)
 + *
 + * This is the low-level counterpart to cpu_replace_ttbr1, and should not be
 + * called by anything else. It can only be executed from a TTBR0 mapping.
 + */
 +ENTRY(idmap_cpu_replace_ttbr1)
 +      mrs     x2, daif
 +      msr     daifset, #0xf
 +
 +      adrp    x1, empty_zero_page
 +      msr     ttbr1_el1, x1
 +      isb
 +
 +      tlbi    vmalle1
 +      dsb     nsh
 +      isb
 +
 +      msr     ttbr1_el1, x0
 +      isb
 +
 +      msr     daif, x2
 +
 +      ret
 +ENDPROC(idmap_cpu_replace_ttbr1)
 +      .popsection
  
  /*
   *    __cpu_setup

diff --cc include/linux/perf_event.h
Simple merge

diff --cc kernel/events/uprobes.c
Simple merge

diff --cc tools/perf/arch/x86/util/intel-pt.c
Simple merge