Merge branch 'rwonce/rework' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux

Pull READ/WRITE_ONCE rework from Will Deacon:
 "This the READ_ONCE rework I've been working on for a while, which
  bumps the minimum GCC version and improves code-gen on arm64 when
  stack protector is enabled"

[ Side note: I'm _really_ tempted to raise the minimum gcc version to
  4.9, so that we can just say that we require _Generic() support.

  That would allow us to more cleanly handle a lot of the cases where we
  depend on very complex macros with 'sizeof' or __builtin_choose_expr()
  with __builtin_types_compatible_p() etc.

  This branch has a workaround for sparse not handling _Generic(),
  either, but that was already fixed in the sparse development branch,
  so it's really just gcc-4.9 that we'd require.   - Linus ]

* 'rwonce/rework' of git://git.kernel.org/pub/scm/linux/kernel/git/will/linux:
  compiler_types.h: Use unoptimized __unqual_scalar_typeof for sparse
  compiler_types.h: Optimize __unqual_scalar_typeof compilation time
  compiler.h: Enforce that READ_ONCE_NOCHECK() access size is sizeof(long)
  compiler-types.h: Include naked type in __pick_integer_type() match
  READ_ONCE: Fix comment describing 2x32-bit atomicity
  gcov: Remove old GCC 3.4 support
  arm64: barrier: Use '__unqual_scalar_typeof' for acquire/release macros
  locking/barriers: Use '__unqual_scalar_typeof' for load-acquire macros
  READ_ONCE: Drop pointer qualifiers when reading from scalar types
  READ_ONCE: Enforce atomicity for {READ,WRITE}_ONCE() memory accesses
  READ_ONCE: Simplify implementations of {READ,WRITE}_ONCE()
  arm64: csum: Disable KASAN for do_csum()
  fault_inject: Don't rely on "return value" from WRITE_ONCE()
  net: tls: Avoid assigning 'const' pointer to non-const pointer
  netfilter: Avoid assigning 'const' pointer to non-const pointer
  compiler/gcc: Raise minimum GCC version for kernel builds to 4.8

Author: torvalds

Documentation/process/changes.rst

@@ -29,7 +29,7 @@ you probably needn't concern yourself with pcmciautils.
 ====================== ===============  ========================================
         Program        Minimal version       Command to check the version
 ====================== ===============  ========================================
-GNU C                  4.6              gcc --version
+GNU C                  4.8              gcc --version
 GNU make               3.81             make --version
 binutils               2.23             ld -v
 flex                   2.5.35           flex --version

arch/arm/crypto/Kconfig

@@ -30,7 +30,7 @@ config CRYPTO_SHA1_ARM_NEON
 
 config CRYPTO_SHA1_ARM_CE
 	tristate "SHA1 digest algorithm (ARM v8 Crypto Extensions)"
-	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
+	depends on KERNEL_MODE_NEON
 	select CRYPTO_SHA1_ARM
 	select CRYPTO_HASH
 	help
@@ -39,7 +39,7 @@ config CRYPTO_SHA1_ARM_CE
 
 config CRYPTO_SHA2_ARM_CE
 	tristate "SHA-224/256 digest algorithm (ARM v8 Crypto Extensions)"
-	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
+	depends on KERNEL_MODE_NEON
 	select CRYPTO_SHA256_ARM
 	select CRYPTO_HASH
 	help
@@ -96,7 +96,7 @@ config CRYPTO_AES_ARM_BS
 
 config CRYPTO_AES_ARM_CE
 	tristate "Accelerated AES using ARMv8 Crypto Extensions"
-	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
+	depends on KERNEL_MODE_NEON
 	select CRYPTO_SKCIPHER
 	select CRYPTO_LIB_AES
 	select CRYPTO_SIMD
@@ -106,7 +106,7 @@ config CRYPTO_AES_ARM_CE
 
 config CRYPTO_GHASH_ARM_CE
 	tristate "PMULL-accelerated GHASH using NEON/ARMv8 Crypto Extensions"
-	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
+	depends on KERNEL_MODE_NEON
 	select CRYPTO_HASH
 	select CRYPTO_CRYPTD
 	select CRYPTO_GF128MUL
@@ -118,13 +118,13 @@ config CRYPTO_GHASH_ARM_CE
 
 config CRYPTO_CRCT10DIF_ARM_CE
 	tristate "CRCT10DIF digest algorithm using PMULL instructions"
-	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
+	depends on KERNEL_MODE_NEON
 	depends on CRC_T10DIF
 	select CRYPTO_HASH
 
 config CRYPTO_CRC32_ARM_CE
 	tristate "CRC32(C) digest algorithm using CRC and/or PMULL instructions"
-	depends on KERNEL_MODE_NEON && (CC_IS_CLANG || GCC_VERSION >= 40800)
+	depends on KERNEL_MODE_NEON
 	depends on CRC32
 	select CRYPTO_HASH
 

arch/arm64/include/asm/barrier.h

@@ -76,8 +76,8 @@ static inline unsigned long array_index_mask_nospec(unsigned long idx,
 #define __smp_store_release(p, v)					\
 do {									\
 	typeof(p) __p = (p);						\
-	union { typeof(*p) __val; char __c[1]; } __u =			\
-		{ .__val = (__force typeof(*p)) (v) };			\
+	union { __unqual_scalar_typeof(*p) __val; char __c[1]; } __u =	\
+		{ .__val = (__force __unqual_scalar_typeof(*p)) (v) };	\
 	compiletime_assert_atomic_type(*p);				\
 	kasan_check_write(__p, sizeof(*p));				\
 	switch (sizeof(*p)) {						\
@@ -110,7 +110,7 @@ do {									\
 
 #define __smp_load_acquire(p)						\
 ({									\
-	union { typeof(*p) __val; char __c[1]; } __u;			\
+	union { __unqual_scalar_typeof(*p) __val; char __c[1]; } __u;	\
 	typeof(p) __p = (p);						\
 	compiletime_assert_atomic_type(*p);				\
 	kasan_check_read(__p, sizeof(*p));				\
@@ -136,33 +136,33 @@ do {									\
 			: "Q" (*__p) : "memory");			\
 		break;							\
 	}								\
-	__u.__val;							\
+	(typeof(*p))__u.__val;						\
 })
 
 #define smp_cond_load_relaxed(ptr, cond_expr)				\
 ({									\
 	typeof(ptr) __PTR = (ptr);					\
-	typeof(*ptr) VAL;						\
+	__unqual_scalar_typeof(*ptr) VAL;				\
 	for (;;) {							\
 		VAL = READ_ONCE(*__PTR);				\
 		if (cond_expr)						\
 			break;						\
 		__cmpwait_relaxed(__PTR, VAL);				\
 	}								\
-	VAL;								\
+	(typeof(*ptr))VAL;						\
 })
 
 #define smp_cond_load_acquire(ptr, cond_expr)				\
 ({									\
 	typeof(ptr) __PTR = (ptr);					\
-	typeof(*ptr) VAL;						\
+	__unqual_scalar_typeof(*ptr) VAL;				\
 	for (;;) {							\
 		VAL = smp_load_acquire(__PTR);				\
 		if (cond_expr)						\
 			break;						\
 		__cmpwait_relaxed(__PTR, VAL);				\
 	}								\
-	VAL;								\
+	(typeof(*ptr))VAL;						\
 })
 
 #include <asm-generic/barrier.h>

arch/arm64/lib/csum.c

@@ -14,7 +14,11 @@ static u64 accumulate(u64 sum, u64 data)
 	return tmp + (tmp >> 64);
 }
 
-unsigned int do_csum(const unsigned char *buff, int len)
+/*
+ * We over-read the buffer and this makes KASAN unhappy. Instead, disable
+ * instrumentation and call kasan explicitly.
+ */
+unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len)
 {
 	unsigned int offset, shift, sum;
 	const u64 *ptr;
@@ -42,7 +46,7 @@ unsigned int do_csum(const unsigned char *buff, int len)
 	 * odd/even alignment, and means we can ignore it until the very end.
 	 */
 	shift = offset * 8;
-	data = READ_ONCE_NOCHECK(*ptr++);
+	data = *ptr++;
 #ifdef __LITTLE_ENDIAN
 	data = (data >> shift) << shift;
 #else
@@ -58,10 +62,10 @@ unsigned int do_csum(const unsigned char *buff, int len)
 	while (unlikely(len > 64)) {
 		__uint128_t tmp1, tmp2, tmp3, tmp4;
 
-		tmp1 = READ_ONCE_NOCHECK(*(__uint128_t *)ptr);
-		tmp2 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 2));
-		tmp3 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 4));
-		tmp4 = READ_ONCE_NOCHECK(*(__uint128_t *)(ptr + 6));
+		tmp1 = *(__uint128_t *)ptr;
+		tmp2 = *(__uint128_t *)(ptr + 2);
+		tmp3 = *(__uint128_t *)(ptr + 4);
+		tmp4 = *(__uint128_t *)(ptr + 6);
 
 		len -= 64;
 		ptr += 8;
@@ -85,7 +89,7 @@ unsigned int do_csum(const unsigned char *buff, int len)
 		__uint128_t tmp;
 
 		sum64 = accumulate(sum64, data);
-		tmp = READ_ONCE_NOCHECK(*(__uint128_t *)ptr);
+		tmp = *(__uint128_t *)ptr;
 
 		len -= 16;
 		ptr += 2;
@@ -100,7 +104,7 @@ unsigned int do_csum(const unsigned char *buff, int len)
 	}
 	if (len > 0) {
 		sum64 = accumulate(sum64, data);
-		data = READ_ONCE_NOCHECK(*ptr);
+		data = *ptr;
 		len -= 8;
 	}
 	/*

crypto/Kconfig

@@ -316,7 +316,6 @@ config CRYPTO_AEGIS128
 config CRYPTO_AEGIS128_SIMD
 	bool "Support SIMD acceleration for AEGIS-128"
 	depends on CRYPTO_AEGIS128 && ((ARM || ARM64) && KERNEL_MODE_NEON)
-	depends on !ARM || CC_IS_CLANG || GCC_VERSION >= 40800
 	default y
 
 config CRYPTO_AEGIS128_AESNI_SSE2

drivers/xen/time.c

@@ -64,7 +64,7 @@ static void xen_get_runstate_snapshot_cpu_delta(
 	do {
 		state_time = get64(&state->state_entry_time);
 		rmb();	/* Hypervisor might update data. */
-		*res = READ_ONCE(*state);
+		*res = __READ_ONCE(*state);
 		rmb();	/* Hypervisor might update data. */
 	} while (get64(&state->state_entry_time) != state_time ||
 		 (state_time & XEN_RUNSTATE_UPDATE));

include/asm-generic/barrier.h

@@ -128,10 +128,10 @@ do {									\
 #ifndef __smp_load_acquire
 #define __smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = READ_ONCE(*p);				\
+	__unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p);		\
 	compiletime_assert_atomic_type(*p);				\
 	__smp_mb();							\
-	___p1;								\
+	(typeof(*p))___p1;						\
 })
 #endif
 
@@ -183,10 +183,10 @@ do {									\
 #ifndef smp_load_acquire
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = READ_ONCE(*p);				\
+	__unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p);		\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
-	___p1;								\
+	(typeof(*p))___p1;						\
 })
 #endif
 
@@ -229,14 +229,14 @@ do {									\
 #ifndef smp_cond_load_relaxed
 #define smp_cond_load_relaxed(ptr, cond_expr) ({		\
 	typeof(ptr) __PTR = (ptr);				\
-	typeof(*ptr) VAL;					\
+	__unqual_scalar_typeof(*ptr) VAL;			\
 	for (;;) {						\
 		VAL = READ_ONCE(*__PTR);			\
 		if (cond_expr)					\
 			break;					\
 		cpu_relax();					\
 	}							\
-	VAL;							\
+	(typeof(*ptr))VAL;					\
 })
 #endif
 
@@ -250,10 +250,10 @@ do {									\
  */
 #ifndef smp_cond_load_acquire
 #define smp_cond_load_acquire(ptr, cond_expr) ({		\
-	typeof(*ptr) _val;					\
+	__unqual_scalar_typeof(*ptr) _val;			\
 	_val = smp_cond_load_relaxed(ptr, cond_expr);		\
 	smp_acquire__after_ctrl_dep();				\
-	_val;							\
+	(typeof(*ptr))_val;					\
 })
 #endif
 

include/linux/compiler-gcc.h

@@ -10,7 +10,8 @@
 		     + __GNUC_MINOR__ * 100	\
 		     + __GNUC_PATCHLEVEL__)
 
-#if GCC_VERSION < 40600
+/* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */
+#if GCC_VERSION < 40800
 # error Sorry, your compiler is too old - please upgrade it.
 #endif
 
@@ -126,9 +127,7 @@
 #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__)
 #define __HAVE_BUILTIN_BSWAP32__
 #define __HAVE_BUILTIN_BSWAP64__
-#if GCC_VERSION >= 40800
 #define __HAVE_BUILTIN_BSWAP16__
-#endif
 #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */
 
 #if GCC_VERSION >= 70000