Merge branch 'for-next/read-barrier-depends' into for-next/core

* for-next/read-barrier-depends:
  : Allow architectures to override __READ_ONCE()
  arm64: Reduce the number of header files pulled into vmlinux.lds.S
  compiler.h: Move compiletime_assert() macros into compiler_types.h
  checkpatch: Remove checks relating to [smp_]read_barrier_depends()
  include/linux: Remove smp_read_barrier_depends() from comments
  tools/memory-model: Remove smp_read_barrier_depends() from informal doc
  Documentation/barriers/kokr: Remove references to [smp_]read_barrier_depends()
  Documentation/barriers: Remove references to [smp_]read_barrier_depends()
  locking/barriers: Remove definitions for [smp_]read_barrier_depends()
  alpha: Replace smp_read_barrier_depends() usage with smp_[r]mb()
  vhost: Remove redundant use of read_barrier_depends() barrier
  asm/rwonce: Don't pull <asm/barrier.h> into 'asm-generic/rwonce.h'
  asm/rwonce: Remove smp_read_barrier_depends() invocation
  alpha: Override READ_ONCE() with barriered implementation
  asm/rwonce: Allow __READ_ONCE to be overridden by the architecture
  compiler.h: Split {READ,WRITE}_ONCE definitions out into rwonce.h
  tools: bpf: Use local copy of headers including uapi/linux/filter.h

14 files changed, 67 insertions, 74 deletions

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 2144530d1428..2f8f7e54792f 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -16,10 +16,10 @@
 
 /*
  * To ensure dependency ordering is preserved for the _relaxed and
- * _release atomics, an smp_read_barrier_depends() is unconditionally
- * inserted into the _relaxed variants, which are used to build the
- * barriered versions. Avoid redundant back-to-back fences in the
- * _acquire and _fence versions.
+ * _release atomics, an smp_mb() is unconditionally inserted into the
+ * _relaxed variants, which are used to build the barriered versions.
+ * Avoid redundant back-to-back fences in the _acquire and _fence
+ * versions.
  */
 #define __atomic_acquire_fence()
 #define __atomic_post_full_fence()
@@ -70,7 +70,7 @@ static inline int atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
@@ -88,7 +88,7 @@ static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
@@ -123,7 +123,7 @@ static __inline__ s64 atomic64_##op##_return_relaxed(s64 i, atomic64_t * v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
@@ -141,7 +141,7 @@ static __inline__ s64 atomic64_fetch_##op##_relaxed(s64 i, atomic64_t * v)	\
 	".previous"							\
 	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
 	:"Ir" (i), "m" (v->counter) : "memory");			\
-	smp_read_barrier_depends();					\
+	smp_mb();							\
 	return result;							\
 }
 
diff --git a/arch/alpha/include/asm/barrier.h b/arch/alpha/include/asm/barrier.h
index 92ec486a4f9e..c56bfffc9918 100644
--- a/arch/alpha/include/asm/barrier.h
+++ b/arch/alpha/include/asm/barrier.h
@@ -2,64 +2,15 @@
 #ifndef __BARRIER_H
 #define __BARRIER_H
 
-#include <asm/compiler.h>
-
 #define mb()	__asm__ __volatile__("mb": : :"memory")
 #define rmb()	__asm__ __volatile__("mb": : :"memory")
 #define wmb()	__asm__ __volatile__("wmb": : :"memory")
 
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- */
-#define read_barrier_depends() __asm__ __volatile__("mb": : :"memory")
+#define __smp_load_acquire(p)						\
+({									\
+	compiletime_assert_atomic_type(*p);				\
+	__READ_ONCE(*p);						\
+})
 
 #ifdef CONFIG_SMP
 #define __ASM_SMP_MB	"\tmb\n"
diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h
index 162c17b2631f..660b14ce1317 100644
--- a/arch/alpha/include/asm/pgtable.h
+++ b/arch/alpha/include/asm/pgtable.h
@@ -277,9 +277,9 @@ extern inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= __DIRTY_BITS; retur
 extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; return pte; }
 
 /*
- * The smp_read_barrier_depends() in the following functions are required to
- * order the load of *dir (the pointer in the top level page table) with any
- * subsequent load of the returned pmd_t *ret (ret is data dependent on *dir).
+ * The smp_rmb() in the following functions are required to order the load of
+ * *dir (the pointer in the top level page table) with any subsequent load of
+ * the returned pmd_t *ret (ret is data dependent on *dir).
  *
  * If this ordering is not enforced, the CPU might load an older value of
  * *ret, which may be uninitialized data. See mm/memory.c:__pte_alloc for
@@ -293,7 +293,7 @@ extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; retu
 extern inline pmd_t * pmd_offset(pud_t * dir, unsigned long address)
 {
 	pmd_t *ret = (pmd_t *) pud_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1));
-	smp_read_barrier_depends(); /* see above */
+	smp_rmb(); /* see above */
 	return ret;
 }
 #define pmd_offset pmd_offset
@@ -303,7 +303,7 @@ extern inline pte_t * pte_offset_kernel(pmd_t * dir, unsigned long address)
 {
 	pte_t *ret = (pte_t *) pmd_page_vaddr(*dir)
 		+ ((address >> PAGE_SHIFT) & (PTRS_PER_PAGE - 1));
-	smp_read_barrier_depends(); /* see above */
+	smp_rmb(); /* see above */
 	return ret;
 }
 #define pte_offset_kernel pte_offset_kernel
diff --git a/arch/alpha/include/asm/rwonce.h b/arch/alpha/include/asm/rwonce.h
new file mode 100644
index 000000000000..35542bcf92b3
--- /dev/null
+++ b/arch/alpha/include/asm/rwonce.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Google LLC.
+ */
+#ifndef __ASM_RWONCE_H
+#define __ASM_RWONCE_H
+
+#ifdef CONFIG_SMP
+
+#include <asm/barrier.h>
+
+/*
+ * Alpha is apparently daft enough to reorder address-dependent loads
+ * on some CPU implementations. Knock some common sense into it with
+ * a memory barrier in READ_ONCE().
+ *
+ * For the curious, more information about this unusual reordering is
+ * available in chapter 15 of the "perfbook":
+ *
+ *  https://kernel.org/pub/linux/kernel/people/paulmck/perfbook/perfbook.html
+ *
+ */
+#define __READ_ONCE(x)							\
+({									\
+	__unqual_scalar_typeof(x) __x =					\
+		(*(volatile typeof(__x) *)(&(x)));			\
+	mb();								\
+	(typeof(x))__x;							\
+})
+
+#endif /* CONFIG_SMP */
+
+#include <asm-generic/rwonce.h>
+
+#endif /* __ASM_RWONCE_H */
diff --git a/arch/arm/include/asm/vdso/gettimeofday.h b/arch/arm/include/asm/vdso/gettimeofday.h
index 36dc18553ed8..1b207cf07697 100644
--- a/arch/arm/include/asm/vdso/gettimeofday.h
+++ b/arch/arm/include/asm/vdso/gettimeofday.h
@@ -7,6 +7,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/errno.h>
 #include <asm/unistd.h>
 #include <asm/vdso/cp15.h>
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index 3bf626f6fe0c..329fb15f6bac 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -8,7 +8,7 @@
 #ifndef __ASM_KERNEL_PGTABLE_H
 #define __ASM_KERNEL_PGTABLE_H
 
-#include <linux/pgtable.h>
+#include <asm/pgtable-hwdef.h>
 #include <asm/sparsemem.h>
 
 /*
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 2a88cb734d06..afa722504bfd 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -10,11 +10,8 @@
 #ifndef __ASM_MEMORY_H
 #define __ASM_MEMORY_H
 
-#include <linux/compiler.h>
 #include <linux/const.h>
 #include <linux/sizes.h>
-#include <linux/types.h>
-#include <asm/bug.h>
 #include <asm/page-def.h>
 
 /*
@@ -157,11 +154,15 @@
 #endif
 
 #ifndef __ASSEMBLY__
-extern u64			vabits_actual;
-#define PAGE_END		(_PAGE_END(vabits_actual))
 
 #include <linux/bitops.h>
+#include <linux/compiler.h>
 #include <linux/mmdebug.h>
+#include <linux/types.h>
+#include <asm/bug.h>
+
+extern u64			vabits_actual;
+#define PAGE_END		(_PAGE_END(vabits_actual))
 
 extern s64			physvirt_offset;
 extern s64			memstart_addr;
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index bc5c7b091152..8d7c466f809b 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -19,6 +19,7 @@
 #include <linux/string.h>
 
 #include <asm/cpufeature.h>
+#include <asm/mmu.h>
 #include <asm/ptrace.h>
 #include <asm/memory.h>
 #include <asm/extable.h>
diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
index b7c549d46d18..d0cbb04bfc10 100644
--- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -7,6 +7,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/unistd.h>
 #include <asm/errno.h>
 
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
index cf39eae5eaaf..9c29ad3049f8 100644
--- a/arch/arm64/include/asm/vdso/gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -7,6 +7,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/unistd.h>
 
 #define VDSO_HAS_CLOCK_GETRES		1
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 7b9a7c45ef85..945b46a1990d 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -15,6 +15,7 @@
 #include <asm/assembler.h>
 #include <asm/asm-offsets.h>
 #include <asm/asm_pointer_auth.h>
+#include <asm/bug.h>
 #include <asm/cpufeature.h>
 #include <asm/errno.h>
 #include <asm/esr.h>
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 6827da7f3aa5..e1e7c0431b4d 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -10,7 +10,6 @@
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/cache.h>
 #include <asm/kernel-pgtable.h>
-#include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/page.h>
 
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 6e6ed5581eed..076544393c3c 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -6,6 +6,7 @@
 
 #include <linux/linkage.h>
 
+#include <asm/alternative.h>
 #include <asm/assembler.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_mmu.h>
diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h
index c8e818688ec1..3099362d9f26 100644
--- a/arch/riscv/include/asm/vdso/gettimeofday.h
+++ b/arch/riscv/include/asm/vdso/gettimeofday.h
@@ -4,6 +4,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/barrier.h>
 #include <asm/unistd.h>
 #include <asm/csr.h>
 #include <uapi/linux/time.h>