Merge tag 'locking-urgent-2020-06-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull atomics rework from Thomas Gleixner:
 "Peter Zijlstras rework of atomics and fallbacks. This solves two
  problems:

   1) Compilers uninline small atomic_* static inline functions which
      can expose them to instrumentation.

   2) The instrumentation of atomic primitives was done at the
      architecture level while composites or fallbacks were provided at
      the generic level. As a result there are no uninstrumented
      variants of the fallbacks.

  Both issues were in the way of fully isolating fragile entry code
  pathes and especially the text poke int3 handler which is prone to an
  endless recursion problem when anything in that code path is about to
  be instrumented. This was always a problem, but got elevated due to
  the new batch mode updates of tracing.

  The solution is to mark the functions __always_inline and to flip the
  fallback and instrumentation so the non-instrumented variants are at
  the architecture level and the instrumentation is done in generic
  code.

  The latter introduces another fallback variant which will go away once
  all architectures have been moved over to arch_atomic_*"

* tag 'locking-urgent-2020-06-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking/atomics: Flip fallbacks and instrumentation
  asm-generic/atomic: Use __always_inline for fallback wrappers

arch/arm64/include/asm/atomic.h

@@ -101,8 +101,8 @@ static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define arch_atomic_read(v)			READ_ONCE((v)->counter)
-#define arch_atomic_set(v, i)			WRITE_ONCE(((v)->counter), (i))
+#define arch_atomic_read(v)			__READ_ONCE((v)->counter)
+#define arch_atomic_set(v, i)			__WRITE_ONCE(((v)->counter), (i))
 
 #define arch_atomic_add_return_relaxed		arch_atomic_add_return_relaxed
 #define arch_atomic_add_return_acquire		arch_atomic_add_return_acquire
@@ -225,6 +225,6 @@ static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 
 #define arch_atomic64_dec_if_positive		arch_atomic64_dec_if_positive
 
-#include <asm-generic/atomic-instrumented.h>
+#define ARCH_ATOMIC
 
 #endif /* __ASM_ATOMIC_H */

arch/x86/include/asm/atomic.h

@@ -28,7 +28,7 @@ static __always_inline int arch_atomic_read(const atomic_t *v)
 	 * Note for KASAN: we deliberately don't use READ_ONCE_NOCHECK() here,
 	 * it's non-inlined function that increases binary size and stack usage.
 	 */
-	return READ_ONCE((v)->counter);
+	return __READ_ONCE((v)->counter);
 }
 
 /**
@@ -40,7 +40,7 @@ static __always_inline int arch_atomic_read(const atomic_t *v)
  */
 static __always_inline void arch_atomic_set(atomic_t *v, int i)
 {
-	WRITE_ONCE(v->counter, i);
+	__WRITE_ONCE(v->counter, i);
 }
 
 /**
@@ -166,6 +166,7 @@ static __always_inline int arch_atomic_add_return(int i, atomic_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
+#define arch_atomic_add_return arch_atomic_add_return
 
 /**
  * arch_atomic_sub_return - subtract integer and return
@@ -178,32 +179,37 @@ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v)
 {
 	return arch_atomic_add_return(-i, v);
 }
+#define arch_atomic_sub_return arch_atomic_sub_return
 
 static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
 {
 	return xadd(&v->counter, i);
 }
+#define arch_atomic_fetch_add arch_atomic_fetch_add
 
 static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v)
 {
 	return xadd(&v->counter, -i);
 }
+#define arch_atomic_fetch_sub arch_atomic_fetch_sub
 
 static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	return arch_cmpxchg(&v->counter, old, new);
 }
+#define arch_atomic_cmpxchg arch_atomic_cmpxchg
 
-#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg
 static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 {
 	return try_cmpxchg(&v->counter, old, new);
 }
+#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg
 
 static inline int arch_atomic_xchg(atomic_t *v, int new)
 {
 	return arch_xchg(&v->counter, new);
 }
+#define arch_atomic_xchg arch_atomic_xchg
 
 static inline void arch_atomic_and(int i, atomic_t *v)
 {
@@ -221,6 +227,7 @@ static inline int arch_atomic_fetch_and(int i, atomic_t *v)
 
 	return val;
 }
+#define arch_atomic_fetch_and arch_atomic_fetch_and
 
 static inline void arch_atomic_or(int i, atomic_t *v)
 {
@@ -238,6 +245,7 @@ static inline int arch_atomic_fetch_or(int i, atomic_t *v)
 
 	return val;
 }
+#define arch_atomic_fetch_or arch_atomic_fetch_or
 
 static inline void arch_atomic_xor(int i, atomic_t *v)
 {
@@ -255,6 +263,7 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
 
 	return val;
 }
+#define arch_atomic_fetch_xor arch_atomic_fetch_xor
 
 #ifdef CONFIG_X86_32
 # include <asm/atomic64_32.h>
@@ -262,6 +271,6 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
 # include <asm/atomic64_64.h>
 #endif
 
-#include <asm-generic/atomic-instrumented.h>
+#define ARCH_ATOMIC
 
 #endif /* _ASM_X86_ATOMIC_H */

arch/x86/include/asm/atomic64_32.h

@@ -75,6 +75,7 @@ static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
 {
 	return arch_cmpxchg64(&v->counter, o, n);
 }
+#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
 
 /**
  * arch_atomic64_xchg - xchg atomic64 variable
@@ -94,6 +95,7 @@ static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
 			     : "memory");
 	return o;
 }
+#define arch_atomic64_xchg arch_atomic64_xchg
 
 /**
  * arch_atomic64_set - set atomic64 variable
@@ -138,6 +140,7 @@ static inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 			     ASM_NO_INPUT_CLOBBER("memory"));
 	return i;
 }
+#define arch_atomic64_add_return arch_atomic64_add_return
 
 /*
  * Other variants with different arithmetic operators:
@@ -149,6 +152,7 @@ static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 			     ASM_NO_INPUT_CLOBBER("memory"));
 	return i;
 }
+#define arch_atomic64_sub_return arch_atomic64_sub_return
 
 static inline s64 arch_atomic64_inc_return(atomic64_t *v)
 {
@@ -242,6 +246,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 			     "S" (v) : "memory");
 	return (int)a;
 }
+#define arch_atomic64_add_unless arch_atomic64_add_unless
 
 static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
@@ -281,6 +286,7 @@ static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
 
 	return old;
 }
+#define arch_atomic64_fetch_and arch_atomic64_fetch_and
 
 static inline void arch_atomic64_or(s64 i, atomic64_t *v)
 {
@@ -299,6 +305,7 @@ static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
 
 	return old;
 }
+#define arch_atomic64_fetch_or arch_atomic64_fetch_or
 
 static inline void arch_atomic64_xor(s64 i, atomic64_t *v)
 {
@@ -317,6 +324,7 @@ static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
 
 	return old;
 }
+#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor
 
 static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
 {
@@ -327,6 +335,7 @@ static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
 
 	return old;
 }
+#define arch_atomic64_fetch_add arch_atomic64_fetch_add
 
 #define arch_atomic64_fetch_sub(i, v)	arch_atomic64_fetch_add(-(i), (v))
 

arch/x86/include/asm/atomic64_64.h

@@ -19,7 +19,7 @@
  */
 static inline s64 arch_atomic64_read(const atomic64_t *v)
 {
-	return READ_ONCE((v)->counter);
+	return __READ_ONCE((v)->counter);
 }
 
 /**
@@ -31,7 +31,7 @@ static inline s64 arch_atomic64_read(const atomic64_t *v)
  */
 static inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
-	WRITE_ONCE(v->counter, i);
+	__WRITE_ONCE(v->counter, i);
 }
 
 /**
@@ -159,37 +159,43 @@ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
+#define arch_atomic64_add_return arch_atomic64_add_return
 
 static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 {
 	return arch_atomic64_add_return(-i, v);
 }
+#define arch_atomic64_sub_return arch_atomic64_sub_return
 
 static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
 {
 	return xadd(&v->counter, i);
 }
+#define arch_atomic64_fetch_add arch_atomic64_fetch_add
 
 static inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v)
 {
 	return xadd(&v->counter, -i);
 }
+#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub
 
 static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 {
 	return arch_cmpxchg(&v->counter, old, new);
 }
+#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
 
-#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
 static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
 {
 	return try_cmpxchg(&v->counter, old, new);
 }
+#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
 
 static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new)
 {
 	return arch_xchg(&v->counter, new);
 }
+#define arch_atomic64_xchg arch_atomic64_xchg
 
 static inline void arch_atomic64_and(s64 i, atomic64_t *v)
 {
@@ -207,6 +213,7 @@ static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
 	} while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
 	return val;
 }
+#define arch_atomic64_fetch_and arch_atomic64_fetch_and
 
 static inline void arch_atomic64_or(s64 i, atomic64_t *v)
 {
@@ -224,6 +231,7 @@ static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
 	} while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
 	return val;
 }
+#define arch_atomic64_fetch_or arch_atomic64_fetch_or
 
 static inline void arch_atomic64_xor(s64 i, atomic64_t *v)
 {
@@ -241,5 +249,6 @@ static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
 	} while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
 	return val;
 }
+#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor
 
 #endif /* _ASM_X86_ATOMIC64_64_H */

include/linux/atomic.h

@@ -25,6 +25,12 @@
  * See Documentation/memory-barriers.txt for ACQUIRE/RELEASE definitions.
  */
 
+#define atomic_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c))
+#define atomic_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c))
+
+#define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c))
+#define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c))
+
 /*
  * The idea here is to build acquire/release variants by adding explicit
  * barriers on top of the relaxed variant. In the case where the relaxed
@@ -71,7 +77,12 @@
 	__ret;								\
 })
 
+#ifdef ARCH_ATOMIC
+#include <linux/atomic-arch-fallback.h>
+#include <asm-generic/atomic-instrumented.h>
+#else
 #include <linux/atomic-fallback.h>
+#endif
 
 #include <asm-generic/atomic-long.h>
 

scripts/atomic/fallbacks/acquire

 cat <<EOF
-static inline ${ret}
-${atomic}_${pfx}${name}${sfx}_acquire(${params})
+static __always_inline ${ret}
+${arch}${atomic}_${pfx}${name}${sfx}_acquire(${params})
 {
-	${ret} ret = ${atomic}_${pfx}${name}${sfx}_relaxed(${args});
+	${ret} ret = ${arch}${atomic}_${pfx}${name}${sfx}_relaxed(${args});
 	__atomic_acquire_fence();
 	return ret;
 }

scripts/atomic/fallbacks/add_negative

 cat <<EOF
 /**
- * ${atomic}_add_negative - add and test if negative
+ * ${arch}${atomic}_add_negative - add and test if negative
  * @i: integer value to add
  * @v: pointer of type ${atomic}_t
  *
@@ -8,9 +8,9 @@ cat <<EOF
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline bool
-${atomic}_add_negative(${int} i, ${atomic}_t *v)
+static __always_inline bool
+${arch}${atomic}_add_negative(${int} i, ${atomic}_t *v)
 {
-	return ${atomic}_add_return(i, v) < 0;
+	return ${arch}${atomic}_add_return(i, v) < 0;
 }
 EOF

scripts/atomic/fallbacks/add_unless

 cat << EOF
 /**
- * ${atomic}_add_unless - add unless the number is already a given value
+ * ${arch}${atomic}_add_unless - add unless the number is already a given value
  * @v: pointer of type ${atomic}_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -8,9 +8,9 @@ cat << EOF
  * Atomically adds @a to @v, if @v was not already @u.
  * Returns true if the addition was done.
  */
-static inline bool
-${atomic}_add_unless(${atomic}_t *v, ${int} a, ${int} u)
+static __always_inline bool
+${arch}${atomic}_add_unless(${atomic}_t *v, ${int} a, ${int} u)
 {
-	return ${atomic}_fetch_add_unless(v, a, u) != u;
+	return ${arch}${atomic}_fetch_add_unless(v, a, u) != u;
 }
 EOF

scripts/atomic/fallbacks/andnot

 cat <<EOF
-static inline ${ret}
-${atomic}_${pfx}andnot${sfx}${order}(${int} i, ${atomic}_t *v)
+static __always_inline ${ret}
+${arch}${atomic}_${pfx}andnot${sfx}${order}(${int} i, ${atomic}_t *v)
 {
-	${retstmt}${atomic}_${pfx}and${sfx}${order}(~i, v);
+	${retstmt}${arch}${atomic}_${pfx}and${sfx}${order}(~i, v);
 }
 EOF

scripts/atomic/fallbacks/dec

 cat <<EOF
-static inline ${ret}
-${atomic}_${pfx}dec${sfx}${order}(${atomic}_t *v)
+static __always_inline ${ret}
+${arch}${atomic}_${pfx}dec${sfx}${order}(${atomic}_t *v)
 {
-	${retstmt}${atomic}_${pfx}sub${sfx}${order}(1, v);
+	${retstmt}${arch}${atomic}_${pfx}sub${sfx}${order}(1, v);
 }
 EOF

scripts/atomic/fallbacks/dec_and_test

 cat <<EOF
 /**
- * ${atomic}_dec_and_test - decrement and test
+ * ${arch}${atomic}_dec_and_test - decrement and test
  * @v: pointer of type ${atomic}_t
  *
  * Atomically decrements @v by 1 and
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline bool
-${atomic}_dec_and_test(${atomic}_t *v)
+static __always_inline bool
+${arch}${atomic}_dec_and_test(${atomic}_t *v)
 {
-	return ${atomic}_dec_return(v) == 0;
+	return ${arch}${atomic}_dec_return(v) == 0;
 }
 EOF

scripts/atomic/fallbacks/dec_if_positive

 cat <<EOF
-static inline ${ret}
-${atomic}_dec_if_positive(${atomic}_t *v)
+static __always_inline ${ret}
+${arch}${atomic}_dec_if_positive(${atomic}_t *v)
 {
-	${int} dec, c = ${atomic}_read(v);
+	${int} dec, c = ${arch}${atomic}_read(v);
 
 	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))
 			break;
-	} while (!${atomic}_try_cmpxchg(v, &c, dec));
+	} while (!${arch}${atomic}_try_cmpxchg(v, &c, dec));
 
 	return dec;
 }

scripts/atomic/fallbacks/dec_unless_positive

 cat <<EOF
-static inline bool
-${atomic}_dec_unless_positive(${atomic}_t *v)
+static __always_inline bool
+${arch}${atomic}_dec_unless_positive(${atomic}_t *v)
 {
-	${int} c = ${atomic}_read(v);
+	${int} c = ${arch}${atomic}_read(v);
 
 	do {
 		if (unlikely(c > 0))
 			return false;
-	} while (!${atomic}_try_cmpxchg(v, &c, c - 1));
+	} while (!${arch}${atomic}_try_cmpxchg(v, &c, c - 1));
 
 	return true;
 }

scripts/atomic/fallbacks/fence

 cat <<EOF
-static inline ${ret}
-${atomic}_${pfx}${name}${sfx}(${params})
+static __always_inline ${ret}
+${arch}${atomic}_${pfx}${name}${sfx}(${params})
 {
 	${ret} ret;
 	__atomic_pre_full_fence();
-	ret = ${atomic}_${pfx}${name}${sfx}_relaxed(${args});
+	ret = ${arch}${atomic}_${pfx}${name}${sfx}_relaxed(${args});
 	__atomic_post_full_fence();
 	return ret;
 }

scripts/atomic/fallbacks/fetch_add_unless

 cat << EOF
 /**
- * ${atomic}_fetch_add_unless - add unless the number is already a given value
+ * ${arch}${atomic}_fetch_add_unless - add unless the number is already a given value
  * @v: pointer of type ${atomic}_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -8,15 +8,15 @@ cat << EOF
  * Atomically adds @a to @v, so long as @v was not already @u.
  * Returns original value of @v
  */
-static inline ${int}
-${atomic}_fetch_add_unless(${atomic}_t *v, ${int} a, ${int} u)
+static __always_inline ${int}
+${arch}${atomic}_fetch_add_unless(${atomic}_t *v, ${int} a, ${int} u)
 {
-	${int} c = ${atomic}_read(v);
+	${int} c = ${arch}${atomic}_read(v);
 
 	do {
 		if (unlikely(c == u))
 			break;
-	} while (!${atomic}_try_cmpxchg(v, &c, c + a));
+	} while (!${arch}${atomic}_try_cmpxchg(v, &c, c + a));
 
 	return c;
 }

scripts/atomic/fallbacks/inc

 cat <<EOF
-static inline ${ret}
-${atomic}_${pfx}inc${sfx}${order}(${atomic}_t *v)
+static __always_inline ${ret}
+${arch}${atomic}_${pfx}inc${sfx}${order}(${atomic}_t *v)
 {
-	${retstmt}${atomic}_${pfx}add${sfx}${order}(1, v);
+	${retstmt}${arch}${atomic}_${pfx}add${sfx}${order}(1, v);
 }
 EOF

scripts/atomic/fallbacks/inc_and_test

 cat <<EOF
 /**
- * ${atomic}_inc_and_test - increment and test
+ * ${arch}${atomic}_inc_and_test - increment and test
  * @v: pointer of type ${atomic}_t
  *
  * Atomically increments @v by 1
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline bool
-${atomic}_inc_and_test(${atomic}_t *v)
+static __always_inline bool
+${arch}${atomic}_inc_and_test(${atomic}_t *v)
 {
-	return ${atomic}_inc_return(v) == 0;
+	return ${arch}${atomic}_inc_return(v) == 0;
 }
 EOF

scripts/atomic/fallbacks/inc_not_zero

 cat <<EOF
 /**
- * ${atomic}_inc_not_zero - increment unless the number is zero
+ * ${arch}${atomic}_inc_not_zero - increment unless the number is zero
  * @v: pointer of type ${atomic}_t
  *
  * Atomically increments @v by 1, if @v is non-zero.
  * Returns true if the increment was done.
  */
-static inline bool
-${atomic}_inc_not_zero(${atomic}_t *v)
+static __always_inline bool
+${arch}${atomic}_inc_not_zero(${atomic}_t *v)
 {
-	return ${atomic}_add_unless(v, 1, 0);
+	return ${arch}${atomic}_add_unless(v, 1, 0);
 }
 EOF

scripts/atomic/fallbacks/inc_unless_negative

 cat <<EOF
-static inline bool
-${atomic}_inc_unless_negative(${atomic}_t *v)
+static __always_inline bool
+${arch}${atomic}_inc_unless_negative(${atomic}_t *v)
 {
-	${int} c = ${atomic}_read(v);
+	${int} c = ${arch}${atomic}_read(v);
 
 	do {
 		if (unlikely(c < 0))
 			return false;
-	} while (!${atomic}_try_cmpxchg(v, &c, c + 1));
+	} while (!${arch}${atomic}_try_cmpxchg(v, &c, c + 1));
 
 	return true;
 }

scripts/atomic/fallbacks/read_acquire

 cat <<EOF
-static inline ${ret}
-${atomic}_read_acquire(const ${atomic}_t *v)
+static __always_inline ${ret}
+${arch}${atomic}_read_acquire(const ${atomic}_t *v)
 {
 	return smp_load_acquire(&(v)->counter);
 }

scripts/atomic/fallbacks/release

 cat <<EOF
-static inline ${ret}
-${atomic}_${pfx}${name}${sfx}_release(${params})
+static __always_inline ${ret}
+${arch}${atomic}_${pfx}${name}${sfx}_release(${params})
 {
 	__atomic_release_fence();
-	${retstmt}${atomic}_${pfx}${name}${sfx}_relaxed(${args});
+	${retstmt}${arch}${atomic}_${pfx}${name}${sfx}_relaxed(${args});
 }
 EOF

scripts/atomic/fallbacks/set_release

 cat <<EOF
-static inline void
-${atomic}_set_release(${atomic}_t *v, ${int} i)
+static __always_inline void
+${arch}${atomic}_set_release(${atomic}_t *v, ${int} i)
 {
 	smp_store_release(&(v)->counter, i);
 }

scripts/atomic/fallbacks/sub_and_test

 cat <<EOF
 /**
- * ${atomic}_sub_and_test - subtract value from variable and test result
+ * ${arch}${atomic}_sub_and_test - subtract value from variable and test result
  * @i: integer value to subtract
  * @v: pointer of type ${atomic}_t
  *
@@ -8,9 +8,9 @@ cat <<EOF
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline bool
-${atomic}_sub_and_test(${int} i, ${atomic}_t *v)
+static __always_inline bool
+${arch}${atomic}_sub_and_test(${int} i, ${atomic}_t *v)
 {
-	return ${atomic}_sub_return(i, v) == 0;
+	return ${arch}${atomic}_sub_return(i, v) == 0;
 }
 EOF

scripts/atomic/fallbacks/try_cmpxchg

 cat <<EOF
-static inline bool
-${atomic}_try_cmpxchg${order}(${atomic}_t *v, ${int} *old, ${int} new)
+static __always_inline bool
+${arch}${atomic}_try_cmpxchg${order}(${atomic}_t *v, ${int} *old, ${int} new)
 {
 	${int} r, o = *old;
-	r = ${atomic}_cmpxchg${order}(v, o, new);
+	r = ${arch}${atomic}_cmpxchg${order}(v, o, new);
 	if (unlikely(r != o))
 		*old = r;
 	return likely(r == o);

scripts/atomic/gen-atomic-fallback.sh

@@ -2,10 +2,11 @@
 # SPDX-License-Identifier: GPL-2.0
 
 ATOMICDIR=$(dirname $0)
+ARCH=$2
 
 . ${ATOMICDIR}/atomic-tbl.sh
 
-#gen_template_fallback(template, meta, pfx, name, sfx, order, atomic, int, args...)
+#gen_template_fallback(template, meta, pfx, name, sfx, order, arch, atomic, int, args...)
 gen_template_fallback()
 {
 	local template="$1"; shift
@@ -14,10 +15,11 @@ gen_template_fallback()
 	local name="$1"; shift
 	local sfx="$1"; shift
 	local order="$1"; shift
+	local arch="$1"; shift
 	local atomic="$1"; shift
 	local int="$1"; shift
 
-	local atomicname="${atomic}_${pfx}${name}${sfx}${order}"
+	local atomicname="${arch}${atomic}_${pfx}${name}${sfx}${order}"
 
 	local ret="$(gen_ret_type "${meta}" "${int}")"
 	local retstmt="$(gen_ret_stmt "${meta}")"
@@ -32,7 +34,7 @@ gen_template_fallback()
 	fi
 }
 
-#gen_proto_fallback(meta, pfx, name, sfx, order, atomic, int, args...)
+#gen_proto_fallback(meta, pfx, name, sfx, order, arch, atomic, int, args...)
 gen_proto_fallback()
 {
 	local meta="$1"; shift
@@ -56,16 +58,17 @@ cat << EOF
 EOF
 }
 
-#gen_proto_order_variants(meta, pfx, name, sfx, atomic, int, args...)
+#gen_proto_order_variants(meta, pfx, name, sfx, arch, atomic, int, args...)
 gen_proto_order_variants()
 {
 	local meta="$1"; shift
 	local pfx="$1"; shift
 	local name="$1"; shift
 	local sfx="$1"; shift
-	local atomic="$1"
+	local arch="$1"
+	local atomic="$2"
 
-	local basename="${atomic}_${pfx}${name}${sfx}"
+	local basename="${arch}${atomic}_${pfx}${name}${sfx}"
 
 	local template="$(find_fallback_template "${pfx}" "${name}" "${sfx}" "${order}")"
 
@@ -94,7 +97,7 @@ gen_proto_order_variants()
 	gen_basic_fallbacks "${basename}"
 
 	if [ ! -z "${template}" ]; then
-		printf "#endif /* ${atomic}_${pfx}${name}${sfx} */\n\n"
+		printf "#endif /* ${arch}${atomic}_${pfx}${name}${sfx} */\n\n"
 		gen_proto_fallback "${meta}" "${pfx}" "${name}" "${sfx}" "" "$@"
 		gen_proto_fallback "${meta}" "${pfx}" "${name}" "${sfx}" "_acquire" "$@"
 		gen_proto_fallback "${meta}" "${pfx}" "${name}" "${sfx}" "_release" "$@"
@@ -149,20 +152,19 @@ cat << EOF
 #ifndef _LINUX_ATOMIC_FALLBACK_H
 #define _LINUX_ATOMIC_FALLBACK_H
 
+#include <linux/compiler.h>
+
 EOF
 
-for xchg in "xchg" "cmpxchg" "cmpxchg64"; do
+for xchg in "${ARCH}xchg" "${ARCH}cmpxchg" "${ARCH}cmpxchg64"; do
 	gen_xchg_fallbacks "${xchg}"
 done
 
 grep '^[a-z]' "$1" | while read name meta args; do
-	gen_proto "${meta}" "${name}" "atomic" "int" ${args}
+	gen_proto "${meta}" "${name}" "${ARCH}" "atomic" "int" ${args}
 done
 
 cat <<EOF
-#define atomic_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c))
-#define atomic_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c))
-
 #ifdef CONFIG_GENERIC_ATOMIC64
 #include <asm-generic/atomic64.h>
 #endif
@@ -170,12 +172,9 @@ cat <<EOF
 EOF
 
 grep '^[a-z]' "$1" | while read name meta args; do
-	gen_proto "${meta}" "${name}" "atomic64" "s64" ${args}
+	gen_proto "${meta}" "${name}" "${ARCH}" "atomic64" "s64" ${args}
 done
 
 cat <<EOF
-#define atomic64_cond_read_acquire(v, c) smp_cond_load_acquire(&(v)->counter, (c))
-#define atomic64_cond_read_relaxed(v, c) smp_cond_load_relaxed(&(v)->counter, (c))
-
 #endif /* _LINUX_ATOMIC_FALLBACK_H */
 EOF

scripts/atomic/gen-atomics.sh

@@ -10,10 +10,11 @@ LINUXDIR=${ATOMICDIR}/../..
 cat <<EOF |
 gen-atomic-instrumented.sh      asm-generic/atomic-instrumented.h
 gen-atomic-long.sh              asm-generic/atomic-long.h
+gen-atomic-fallback.sh          linux/atomic-arch-fallback.h		arch_
 gen-atomic-fallback.sh          linux/atomic-fallback.h
 EOF
-while read script header; do
-	/bin/sh ${ATOMICDIR}/${script} ${ATOMICTBL} > ${LINUXDIR}/include/${header}
+while read script header args; do
+	/bin/sh ${ATOMICDIR}/${script} ${ATOMICTBL} ${args} > ${LINUXDIR}/include/${header}
 	HASH="$(sha1sum ${LINUXDIR}/include/${header})"
 	HASH="${HASH%% *}"
 	printf "// %s\n" "${HASH}" >> ${LINUXDIR}/include/${header}