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

Pull MIPS updates from Ralf Baechle:
 "Boston platform support:
   - Document DT bindings
   - Add CLK driver for board clocks

  CM:
   - Avoid per-core locking with CM3 & higher
   - WARN on attempt to lock invalid VP, not BUG

  CPS:
   - Select CONFIG_SYS_SUPPORTS_SCHED_SMT for MIPSr6
   - Prevent multi-core with dcache aliasing
   - Handle cores not powering down more gracefully
   - Handle spurious VP starts more gracefully

  DSP:
   - Add lwx & lhx missaligned access support

  eBPF:
   - Add MIPS support along with many supporting change to add the
     required infrastructure

  Generic arch code:
   - Misc sysmips MIPS_ATOMIC_SET fixes
   - Drop duplicate HAVE_SYSCALL_TRACEPOINTS
   - Negate error syscall return in trace
   - Correct forced syscall errors
   - Traced negative syscalls should return -ENOSYS
   - Allow samples/bpf/tracex5 to access syscall arguments for sane
     traces
   - Cleanup from old Kconfig options in defconfigs
   - Fix PREF instruction usage by memcpy for MIPS R6
   - Fix various special cases in the FPU eulation
   - Fix some special cases in MIPS16e2 support
   - Fix MIPS I ISA /proc/cpuinfo reporting
   - Sort MIPS Kconfig alphabetically
   - Fix minimum alignment requirement of IRQ stack as required by
     ABI / GCC
   - Fix special cases in the module loader
   - Perform post-DMA cache flushes on systems with MAARs
   - Probe the I6500 CPU
   - Cleanup cmpxchg and add support for 1 and 2 byte operations
   - Use queued read/write locks (qrwlock)
   - Use queued spinlocks (qspinlock)
   - Add CPU shared FTLB feature detection
   - Handle tlbex-tlbp race condition
   - Allow storing pgd in C0_CONTEXT for MIPSr6
   - Use current_cpu_type() in m4kc_tlbp_war()
   - Support Boston in the generic kernel

  Generic platform:
   - yamon-dt: Pull YAMON DT shim code out of SEAD-3 board
   - yamon-dt: Support > 256MB of RAM
   - yamon-dt: Use serial* rather than uart* aliases
   - Abstract FDT fixup application
   - Set RTC_ALWAYS_BCD to 0
   - Add a MAINTAINERS entry

  core kernel:
   - qspinlock.c: include linux/prefetch.h

  Loongson 3:
   - Add support

  Perf:
   - Add I6500 support

  SEAD-3:
   - Remove GIC timer from DT
   - Set interrupt-parent per-device, not at root node
   - Fix GIC interrupt specifiers

  SMP:
   - Skip IPI setup if we only have a single CPU

  VDSO:
   - Make comment match reality
   - Improvements to time code in VDSO"

* 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (86 commits)
  locking/qspinlock: Include linux/prefetch.h
  MIPS: Fix MIPS I ISA /proc/cpuinfo reporting
  MIPS: Fix minimum alignment requirement of IRQ stack
  MIPS: generic: Support MIPS Boston development boards
  MIPS: DTS: img: Don't attempt to build-in all .dtb files
  clk: boston: Add a driver for MIPS Boston board clocks
  dt-bindings: Document img,boston-clock binding
  MIPS: Traced negative syscalls should return -ENOSYS
  MIPS: Correct forced syscall errors
  MIPS: Negate error syscall return in trace
  MIPS: Drop duplicate HAVE_SYSCALL_TRACEPOINTS select
  MIPS16e2: Provide feature overrides for non-MIPS16 systems
  MIPS: MIPS16e2: Report ASE presence in /proc/cpuinfo
  MIPS: MIPS16e2: Subdecode extended LWSP/SWSP instructions
  MIPS: MIPS16e2: Identify ASE presence
  MIPS: VDSO: Fix a mismatch between comment and preprocessor constant
  MIPS: VDSO: Add implementation of gettimeofday() fallback
  MIPS: VDSO: Add implementation of clock_gettime() fallback
  MIPS: VDSO: Fix conversions in do_monotonic()/do_monotonic_coarse()
  MIPS: Use current_cpu_type() in m4kc_tlbp_war()
  ...

1 files changed, 109 insertions, 0 deletions

diff --git a/arch/mips/kernel/cmpxchg.c b/arch/mips/kernel/cmpxchg.c
new file mode 100644
index 000000000000..7730f1d3434f
--- /dev/null
+++ b/arch/mips/kernel/cmpxchg.c
@@ -0,0 +1,109 @@
+/*
+ * Copyright (C) 2017 Imagination Technologies
+ * Author: Paul Burton <paul.burton@imgtec.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/bitops.h>
+#include <asm/cmpxchg.h>
+
+unsigned long __xchg_small(volatile void *ptr, unsigned long val, unsigned int size)
+{
+	u32 old32, new32, load32, mask;
+	volatile u32 *ptr32;
+	unsigned int shift;
+
+	/* Check that ptr is naturally aligned */
+	WARN_ON((unsigned long)ptr & (size - 1));
+
+	/* Mask value to the correct size. */
+	mask = GENMASK((size * BITS_PER_BYTE) - 1, 0);
+	val &= mask;
+
+	/*
+	 * Calculate a shift & mask that correspond to the value we wish to
+	 * exchange within the naturally aligned 4 byte integerthat includes
+	 * it.
+	 */
+	shift = (unsigned long)ptr & 0x3;
+	if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+		shift ^= sizeof(u32) - size;
+	shift *= BITS_PER_BYTE;
+	mask <<= shift;
+
+	/*
+	 * Calculate a pointer to the naturally aligned 4 byte integer that
+	 * includes our byte of interest, and load its value.
+	 */
+	ptr32 = (volatile u32 *)((unsigned long)ptr & ~0x3);
+	load32 = *ptr32;
+
+	do {
+		old32 = load32;
+		new32 = (load32 & ~mask) | (val << shift);
+		load32 = cmpxchg(ptr32, old32, new32);
+	} while (load32 != old32);
+
+	return (load32 & mask) >> shift;
+}
+
+unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old,
+			      unsigned long new, unsigned int size)
+{
+	u32 mask, old32, new32, load32;
+	volatile u32 *ptr32;
+	unsigned int shift;
+	u8 load;
+
+	/* Check that ptr is naturally aligned */
+	WARN_ON((unsigned long)ptr & (size - 1));
+
+	/* Mask inputs to the correct size. */
+	mask = GENMASK((size * BITS_PER_BYTE) - 1, 0);
+	old &= mask;
+	new &= mask;
+
+	/*
+	 * Calculate a shift & mask that correspond to the value we wish to
+	 * compare & exchange within the naturally aligned 4 byte integer
+	 * that includes it.
+	 */
+	shift = (unsigned long)ptr & 0x3;
+	if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+		shift ^= sizeof(u32) - size;
+	shift *= BITS_PER_BYTE;
+	mask <<= shift;
+
+	/*
+	 * Calculate a pointer to the naturally aligned 4 byte integer that
+	 * includes our byte of interest, and load its value.
+	 */
+	ptr32 = (volatile u32 *)((unsigned long)ptr & ~0x3);
+	load32 = *ptr32;
+
+	while (true) {
+		/*
+		 * Ensure the byte we want to exchange matches the expected
+		 * old value, and if not then bail.
+		 */
+		load = (load32 & mask) >> shift;
+		if (load != old)
+			return load;
+
+		/*
+		 * Calculate the old & new values of the naturally aligned
+		 * 4 byte integer that include the byte we want to exchange.
+		 * Attempt to exchange the old value for the new value, and
+		 * return if we succeed.
+		 */
+		old32 = (load32 & ~mask) | (old << shift);
+		new32 = (load32 & ~mask) | (new << shift);
+		load32 = cmpxchg(ptr32, old32, new32);
+		if (load32 == old32)
+			return old;
+	}
+}