Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus

Pull MIPS updates from Ralf Baechle:
 "This is the main pull request for MIPS for 4.8.  Also includes is a
  minor SSB cleanup as SSB code traditionally is merged through the MIPS
  tree:

  ATH25:
    - MIPS: Add default configuration for ath25

  Boot:
    - For zboot, copy appended dtb to the end of the kernel
    - store the appended dtb address in a variable

  BPF:
    - Fix off by one error in offset allocation

  Cobalt code:
    - Fix typos

  Core code:
    - debugfs_create_file returns NULL on error, so don't use IS_ERR for
      testing for errors.
    - Fix double locking issue in RM7000 S-cache code.  This would only
      affect RM7000 ARC systems on reboot.
    - Fix page table corruption on THP permission changes.
    - Use compat_sys_keyctl for 32 bit userspace on 64 bit kernels.
      David says, there are no compatibility issues raised by this fix.
    - Move some signal code around.
    - Rewrite r4k count/compare clockevent device registration such that
      min_delta_ticks/max_delta_ticks files are guaranteed to be
      initialized.
    - Only register r4k count/compare as clockevent device if we can
      assume the clock to be constant.
    - Fix MSA asm warnings in control reg accessors
    - uasm and tlbex fixes and tweaking.
    - Print segment physical address when EU=1.
    - Define AT_VECTOR_SIZE_ARCH for ARCH_DLINFO.
    - CP: Allow booting by VP other than VP 0
    - Cache handling fixes and optimizations for r4k class caches
    - Add hotplug support for R6 processors
    - Cleanup hotplug bits in kconfig
    - traps: return correct si code for accessing nonmapped addresses
    - Remove cpu_has_safe_index_cacheops

  Lantiq:
    - Register IRQ handler for virtual IRQ number
    - Fix EIU interrupt loading code
    - Use the real EXIN count
    - Fix build error.

  Loongson 3:
    - Increase HPET_MIN_PROG_DELTA and decrease HPET_MIN_CYCLES

  Octeon:
    - Delete built-in DTB pruning code for D-Link DSR-1000N.
    - Clean up GPIO definitions in dlink_dsr-1000n.dts.
    - Add more LEDs to the DSR-100n DTS
    - Fix off by one in octeon_irq_gpio_map()
    - Typo fixes
    - Enable SATA by default in cavium_octeon_defconfig
    - Support readq/writeq()
    - Remove forced mappings of USB interrupts.
    - Ensure DMA descriptors are always in the low 4GB
    - Improve USB reset code for OCTEON II.

  Pistachio:
    - Add maintainers entry for pistachio SoC Support
    - Remove plat_setup_iocoherency

  Ralink:
    - Fix pwm UART in spis group pinmux.

  SSB:
    - Change bare unsigned to unsigned int to suit coding style

  Tools:
    - Fix reloc tool compiler warnings.

  Other:
    - Delete use of ARCH_WANT_OPTIONAL_GPIOLIB"

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (61 commits)
  MIPS: mm: Fix definition of R6 cache instruction
  MIPS: tools: Fix relocs tool compiler warnings
  MIPS: Cobalt: Fix typo
  MIPS: Octeon: Fix typo
  MIPS: Lantiq: Fix build failure
  MIPS: Use CPHYSADDR to implement mips32 __pa
  MIPS: Octeon: Dlink_dsr-1000n.dts: add more leds.
  MIPS: Octeon: Clean up GPIO definitions in dlink_dsr-1000n.dts.
  MIPS: Octeon: Delete built-in DTB pruning code for D-Link DSR-1000N.
  MIPS: store the appended dtb address in a variable
  MIPS: ZBOOT: copy appended dtb to the end of the kernel
  MIPS: ralink: fix spis group pinmux
  MIPS: Factor o32 specific code into signal_o32.c
  MIPS: non-exec stack & heap when non-exec PT_GNU_STACK is present
  MIPS: Use per-mm page to execute branch delay slot instructions
  MIPS: Modify error handling
  MIPS: c-r4k: Use SMP calls for CM indexed cache ops
  MIPS: c-r4k: Avoid small flush_icache_range SMP calls
  MIPS: c-r4k: Local flush_icache_range cache op override
  MIPS: c-r4k: Split r4k_flush_kernel_vmap_range()
  ...

1 files changed, 21 insertions, 13 deletions

diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index f9d01e953acb..f95f094f36e4 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -72,7 +72,7 @@ EXPORT_SYMBOL(cpu_core_map);
  * A logcal cpu mask containing only one VPE per core to
  * reduce the number of IPIs on large MT systems.
  */
-cpumask_t cpu_foreign_map __read_mostly;
+cpumask_t cpu_foreign_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_foreign_map);
 
 /* representing cpus for which sibling maps can be computed */
@@ -124,7 +124,7 @@ static inline void set_cpu_core_map(int cpu)
  * Calculate a new cpu_foreign_map mask whenever a
  * new cpu appears or disappears.
  */
-static inline void calculate_cpu_foreign_map(void)
+void calculate_cpu_foreign_map(void)
 {
 	int i, k, core_present;
 	cpumask_t temp_foreign_map;
@@ -141,7 +141,9 @@ static inline void calculate_cpu_foreign_map(void)
 			cpumask_set_cpu(i, &temp_foreign_map);
 	}
 
-	cpumask_copy(&cpu_foreign_map, &temp_foreign_map);
+	for_each_online_cpu(i)
+		cpumask_andnot(&cpu_foreign_map[i],
+			       &temp_foreign_map, &cpu_sibling_map[i]);
 }
 
 struct plat_smp_ops *mp_ops;
@@ -344,16 +346,9 @@ asmlinkage void start_secondary(void)
 static void stop_this_cpu(void *dummy)
 {
 	/*
-	 * Remove this CPU. Be a bit slow here and
-	 * set the bits for every online CPU so we don't miss
-	 * any IPI whilst taking this VPE down.
+	 * Remove this CPU:
 	 */
 
-	cpumask_copy(&cpu_foreign_map, cpu_online_mask);
-
-	/* Make it visible to every other CPU */
-	smp_mb();
-
 	set_cpu_online(smp_processor_id(), false);
 	calculate_cpu_foreign_map();
 	local_irq_disable();
@@ -512,10 +507,17 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned l
 		smp_on_other_tlbs(flush_tlb_range_ipi, &fd);
 	} else {
 		unsigned int cpu;
+		int exec = vma->vm_flags & VM_EXEC;
 
 		for_each_online_cpu(cpu) {
+			/*
+			 * flush_cache_range() will only fully flush icache if
+			 * the VMA is executable, otherwise we must invalidate
+			 * ASID without it appearing to has_valid_asid() as if
+			 * mm has been completely unused by that CPU.
+			 */
 			if (cpu != smp_processor_id() && cpu_context(cpu, mm))
-				cpu_context(cpu, mm) = 0;
+				cpu_context(cpu, mm) = !exec;
 		}
 	}
 	local_flush_tlb_range(vma, start, end);
@@ -560,8 +562,14 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
 		unsigned int cpu;
 
 		for_each_online_cpu(cpu) {
+			/*
+			 * flush_cache_page() only does partial flushes, so
+			 * invalidate ASID without it appearing to
+			 * has_valid_asid() as if mm has been completely unused
+			 * by that CPU.
+			 */
 			if (cpu != smp_processor_id() && cpu_context(cpu, vma->vm_mm))
-				cpu_context(cpu, vma->vm_mm) = 0;
+				cpu_context(cpu, vma->vm_mm) = 1;
 		}
 	}
 	local_flush_tlb_page(vma, page);