Merge tag 'riscv-for-linus-4.15-rc2_cleanups' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/linux

Pull RISC-V cleanups and ABI fixes from Palmer Dabbelt:
 "This contains a handful of small cleanups that are a result of
  feedback that didn't make it into our original patch set, either
  because the feedback hadn't been given yet, I missed the original
  emails, or we weren't ready to submit the changes yet.

  I've been maintaining the various cleanup patch sets I have as their
  own branches, which I then merged together and signed. Each merge
  commit has a short summary of the changes, and each branch is based on
  your latest tag (4.15-rc1, in this case). If this isn't the right way
  to do this then feel free to suggest something else, but it seems sane
  to me.

  Here's a short summary of the changes, roughly in order of how
  interesting they are.

   - libgcc.h has been moved from include/lib, where it's the only
     member, to include/linux. This is meant to avoid tab completion
     conflicts.

   - VDSO entries for clock_get/gettimeofday/getcpu have been added.
     These are simple syscalls now, but we want to let glibc use them
     from the start so we can make them faster later.

   - A VDSO entry for instruction cache flushing has been added so
     userspace can flush the instruction cache.

   - The VDSO symbol versions for __vdso_cmpxchg{32,64} have been
     removed, as those VDSO entries don't actually exist.

   - __io_writes has been corrected to respect the given type.

   - A new READ_ONCE in arch_spin_is_locked().

   - __test_and_op_bit_ord() is now actually ordered.

   - Various small fixes throughout the tree to enable allmodconfig to
     build cleanly.

   - Removal of some dead code in our atomic support headers.

   - Improvements to various comments in our atomic support headers"

* tag 'riscv-for-linus-4.15-rc2_cleanups' of git://git.kernel.org/pub/scm/linux/kernel/git/palmer/linux: (23 commits)
  RISC-V: __io_writes should respect the length argument
  move libgcc.h to include/linux
  RISC-V: Clean up an unused include
  RISC-V: Allow userspace to flush the instruction cache
  RISC-V: Flush I$ when making a dirty page executable
  RISC-V: Add missing include
  RISC-V: Use define for get_cycles like other architectures
  RISC-V: Provide stub of setup_profiling_timer()
  RISC-V: Export some expected symbols for modules
  RISC-V: move empty_zero_page definition to C and export it
  RISC-V: io.h: type fixes for warnings
  RISC-V: use RISCV_{INT,SHORT} instead of {INT,SHORT} for asm macros
  RISC-V: use generic serial.h
  RISC-V: remove spin_unlock_wait()
  RISC-V: `sfence.vma` orderes the instruction cache
  RISC-V: Add READ_ONCE in arch_spin_is_locked()
  RISC-V: __test_and_op_bit_ord should be strongly ordered
  RISC-V: Remove smb_mb__{before,after}_spinlock()
  RISC-V: Remove __smp_bp__{before,after}_atomic
  RISC-V: Comment on why {,cmp}xchg is ordered how it is
  ...

1 files changed, 54 insertions, 49 deletions

diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index e2e37c57cbeb..e65d1cd89e28 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -50,30 +50,30 @@ static __always_inline void atomic64_set(atomic64_t *v, long i)
  * have the AQ or RL bits set.  These don't return anything, so there's only
  * one version to worry about.
  */
-#define ATOMIC_OP(op, asm_op, c_op, I, asm_type, c_type, prefix)				\
-static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)		\
-{												\
-	__asm__ __volatile__ (									\
-		"amo" #asm_op "." #asm_type " zero, %1, %0"					\
-		: "+A" (v->counter)								\
-		: "r" (I)									\
-		: "memory");									\
+#define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix)				\
+static __always_inline void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)	\
+{											\
+	__asm__ __volatile__ (								\
+		"amo" #asm_op "." #asm_type " zero, %1, %0"				\
+		: "+A" (v->counter)							\
+		: "r" (I)								\
+		: "memory");								\
 }
 
 #ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I)			\
-        ATOMIC_OP (op, asm_op, c_op, I, w,  int,   )
+#define ATOMIC_OPS(op, asm_op, I)			\
+        ATOMIC_OP (op, asm_op, I, w,  int,   )
 #else
-#define ATOMIC_OPS(op, asm_op, c_op, I)			\
-        ATOMIC_OP (op, asm_op, c_op, I, w,  int,   )	\
-        ATOMIC_OP (op, asm_op, c_op, I, d, long, 64)
+#define ATOMIC_OPS(op, asm_op, I)			\
+        ATOMIC_OP (op, asm_op, I, w,  int,   )	\
+        ATOMIC_OP (op, asm_op, I, d, long, 64)
 #endif
 
-ATOMIC_OPS(add, add, +,  i)
-ATOMIC_OPS(sub, add, +, -i)
-ATOMIC_OPS(and, and, &,  i)
-ATOMIC_OPS( or,  or, |,  i)
-ATOMIC_OPS(xor, xor, ^,  i)
+ATOMIC_OPS(add, add,  i)
+ATOMIC_OPS(sub, add, -i)
+ATOMIC_OPS(and, and,  i)
+ATOMIC_OPS( or,  or,  i)
+ATOMIC_OPS(xor, xor,  i)
 
 #undef ATOMIC_OP
 #undef ATOMIC_OPS
@@ -83,7 +83,7 @@ ATOMIC_OPS(xor, xor, ^,  i)
  * There's two flavors of these: the arithmatic ops have both fetch and return
  * versions, while the logical ops only have fetch versions.
  */
-#define ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, asm_type, c_type, prefix)			\
+#define ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, asm_type, c_type, prefix)				\
 static __always_inline c_type atomic##prefix##_fetch_##op##c_or(c_type i, atomic##prefix##_t *v)	\
 {													\
 	register c_type ret;										\
@@ -103,13 +103,13 @@ static __always_inline c_type atomic##prefix##_##op##_return##c_or(c_type i, ato
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
+        ATOMIC_FETCH_OP (op, asm_op,       I, asm_or, c_or, w,  int,   )	\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )
 #else
 #define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
+        ATOMIC_FETCH_OP (op, asm_op,       I, asm_or, c_or, w,  int,   )	\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )	\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I, asm_or, c_or, d, long, 64)	\
+        ATOMIC_FETCH_OP (op, asm_op,       I, asm_or, c_or, d, long, 64)	\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
 #endif
 
@@ -126,28 +126,28 @@ ATOMIC_OPS(sub, add, +, -i, .aqrl,         )
 #undef ATOMIC_OPS
 
 #ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )
+#define ATOMIC_OPS(op, asm_op, I, asm_or, c_or)				\
+        ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, w,  int,   )
 #else
-#define ATOMIC_OPS(op, asm_op, c_op, I, asm_or, c_or)				\
-        ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, w,  int,   )		\
-        ATOMIC_FETCH_OP(op, asm_op, c_op, I, asm_or, c_or, d, long, 64)
+#define ATOMIC_OPS(op, asm_op, I, asm_or, c_or)				\
+        ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, w,  int,   )	\
+        ATOMIC_FETCH_OP(op, asm_op, I, asm_or, c_or, d, long, 64)
 #endif
 
-ATOMIC_OPS(and, and, &,  i,      , _relaxed)
-ATOMIC_OPS(and, and, &,  i, .aq  , _acquire)
-ATOMIC_OPS(and, and, &,  i, .rl  , _release)
-ATOMIC_OPS(and, and, &,  i, .aqrl,         )
+ATOMIC_OPS(and, and, i,      , _relaxed)
+ATOMIC_OPS(and, and, i, .aq  , _acquire)
+ATOMIC_OPS(and, and, i, .rl  , _release)
+ATOMIC_OPS(and, and, i, .aqrl,         )
 
-ATOMIC_OPS( or,  or, |,  i,      , _relaxed)
-ATOMIC_OPS( or,  or, |,  i, .aq  , _acquire)
-ATOMIC_OPS( or,  or, |,  i, .rl  , _release)
-ATOMIC_OPS( or,  or, |,  i, .aqrl,         )
+ATOMIC_OPS( or,  or, i,      , _relaxed)
+ATOMIC_OPS( or,  or, i, .aq  , _acquire)
+ATOMIC_OPS( or,  or, i, .rl  , _release)
+ATOMIC_OPS( or,  or, i, .aqrl,         )
 
-ATOMIC_OPS(xor, xor, ^,  i,      , _relaxed)
-ATOMIC_OPS(xor, xor, ^,  i, .aq  , _acquire)
-ATOMIC_OPS(xor, xor, ^,  i, .rl  , _release)
-ATOMIC_OPS(xor, xor, ^,  i, .aqrl,         )
+ATOMIC_OPS(xor, xor, i,      , _relaxed)
+ATOMIC_OPS(xor, xor, i, .aq  , _acquire)
+ATOMIC_OPS(xor, xor, i, .rl  , _release)
+ATOMIC_OPS(xor, xor, i, .aqrl,         )
 
 #undef ATOMIC_OPS
 
@@ -182,13 +182,13 @@ ATOMIC_OPS(add_negative, add,  <, 0)
 #undef ATOMIC_OP
 #undef ATOMIC_OPS
 
-#define ATOMIC_OP(op, func_op, c_op, I, c_type, prefix)				\
+#define ATOMIC_OP(op, func_op, I, c_type, prefix)				\
 static __always_inline void atomic##prefix##_##op(atomic##prefix##_t *v)	\
 {										\
 	atomic##prefix##_##func_op(I, v);					\
 }
 
-#define ATOMIC_FETCH_OP(op, func_op, c_op, I, c_type, prefix)				\
+#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix)					\
 static __always_inline c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v)	\
 {											\
 	return atomic##prefix##_fetch_##func_op(I, v);					\
@@ -202,16 +202,16 @@ static __always_inline c_type atomic##prefix##_##op##_return(atomic##prefix##_t
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS(op, asm_op, c_op, I)						\
-        ATOMIC_OP       (op, asm_op, c_op, I,  int,   )				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I,  int,   )				\
+        ATOMIC_OP       (op, asm_op,       I,  int,   )				\
+        ATOMIC_FETCH_OP (op, asm_op,       I,  int,   )				\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )
 #else
 #define ATOMIC_OPS(op, asm_op, c_op, I)						\
-        ATOMIC_OP       (op, asm_op, c_op, I,  int,   )				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I,  int,   )				\
+        ATOMIC_OP       (op, asm_op,       I,  int,   )				\
+        ATOMIC_FETCH_OP (op, asm_op,       I,  int,   )				\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )				\
-        ATOMIC_OP       (op, asm_op, c_op, I, long, 64)				\
-        ATOMIC_FETCH_OP (op, asm_op, c_op, I, long, 64)				\
+        ATOMIC_OP       (op, asm_op,       I, long, 64)				\
+        ATOMIC_FETCH_OP (op, asm_op,       I, long, 64)				\
         ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
 #endif
 
@@ -300,8 +300,13 @@ static __always_inline long atomic64_inc_not_zero(atomic64_t *v)
 
 /*
  * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
- * {cmp,}xchg and the operations that return, so they need a barrier.  We just
- * use the other implementations directly.
+ * {cmp,}xchg and the operations that return, so they need a barrier.
+ */
+/*
+ * FIXME: atomic_cmpxchg_{acquire,release,relaxed} are all implemented by
+ * assigning the same barrier to both the LR and SC operations, but that might
+ * not make any sense.  We're waiting on a memory model specification to
+ * determine exactly what the right thing to do is here.
  */
 #define ATOMIC_OP(c_t, prefix, c_or, size, asm_or)						\
 static __always_inline c_t atomic##prefix##_cmpxchg##c_or(atomic##prefix##_t *v, c_t o, c_t n) 	\