x86, asm: use bool for bitops and other assembly outputs

The gcc people have confirmed that using "bool" when combined with
inline assembly always is treated as a byte-sized operand that can be
assumed to be 0 or 1, which is exactly what the SET instruction
emits.  Change the output types and intermediate variables of as many
operations as practical to "bool".

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1465414726-197858-3-git-send-email-hpa@linux.intel.com


Reviewed-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>

arch/x86/boot/bitops.h

@@ -16,14 +16,16 @@
 #define BOOT_BITOPS_H
 #define _LINUX_BITOPS_H		/* Inhibit inclusion of <linux/bitops.h> */
 
-static inline int constant_test_bit(int nr, const void *addr)
+#include <linux/types.h>
+
+static inline bool constant_test_bit(int nr, const void *addr)
 {
 	const u32 *p = (const u32 *)addr;
 	return ((1UL << (nr & 31)) & (p[nr >> 5])) != 0;
 }
-static inline int variable_test_bit(int nr, const void *addr)
+static inline bool variable_test_bit(int nr, const void *addr)
 {
-	u8 v;
+	bool v;
 	const u32 *p = (const u32 *)addr;
 
 	asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr));

arch/x86/boot/boot.h

@@ -176,16 +176,16 @@ static inline void wrgs32(u32 v, addr_t addr)
 }
 
 /* Note: these only return true/false, not a signed return value! */
-static inline int memcmp_fs(const void *s1, addr_t s2, size_t len)
+static inline bool memcmp_fs(const void *s1, addr_t s2, size_t len)
 {
-	u8 diff;
+	bool diff;
 	asm volatile("fs; repe; cmpsb; setnz %0"
 		     : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
-static inline int memcmp_gs(const void *s1, addr_t s2, size_t len)
+static inline bool memcmp_gs(const void *s1, addr_t s2, size_t len)
 {
-	u8 diff;
+	bool diff;
 	asm volatile("gs; repe; cmpsb; setnz %0"
 		     : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;

arch/x86/boot/string.c

@@ -17,7 +17,7 @@
 
 int memcmp(const void *s1, const void *s2, size_t len)
 {
-	u8 diff;
+	bool diff;
 	asm("repe; cmpsb; setnz %0"
 	    : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;

arch/x86/include/asm/apm.h

@@ -45,11 +45,11 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 		: "memory", "cc");
 }
 
-static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
-						u32 ecx_in, u32 *eax)
+static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
+					    u32 ecx_in, u32 *eax)
 {
 	int	cx, dx, si;
-	u8	error;
+	bool	error;
 
 	/*
 	 * N.B. We do NOT need a cld after the BIOS call

arch/x86/include/asm/archrandom.h

@@ -43,7 +43,7 @@
 #ifdef CONFIG_ARCH_RANDOM
 
 /* Instead of arch_get_random_long() when alternatives haven't run. */
-static inline int rdrand_long(unsigned long *v)
+static inline bool rdrand_long(unsigned long *v)
 {
 	int ok;
 	asm volatile("1: " RDRAND_LONG "\n\t"
@@ -53,13 +53,13 @@ static inline int rdrand_long(unsigned long *v)
 		     "2:"
 		     : "=r" (ok), "=a" (*v)
 		     : "0" (RDRAND_RETRY_LOOPS));
-	return ok;
+	return !!ok;
 }
 
 /* A single attempt at RDSEED */
 static inline bool rdseed_long(unsigned long *v)
 {
-	unsigned char ok;
+	bool ok;
 	asm volatile(RDSEED_LONG "\n\t"
 		     "setc %0"
 		     : "=qm" (ok), "=a" (*v));
@@ -67,7 +67,7 @@ static inline bool rdseed_long(unsigned long *v)
 }
 
 #define GET_RANDOM(name, type, rdrand, nop)			\
-static inline int name(type *v)					\
+static inline bool name(type *v)				\
 {								\
 	int ok;							\
 	alternative_io("movl $0, %0\n\t"			\
@@ -80,13 +80,13 @@ static inline int name(type *v)					\
 		       X86_FEATURE_RDRAND,                      \
 		       ASM_OUTPUT2("=r" (ok), "=a" (*v)),       \
 		       "0" (RDRAND_RETRY_LOOPS));		\
-	return ok;						\
+	return !!ok;						\
 }
 
 #define GET_SEED(name, type, rdseed, nop)			\
-static inline int name(type *v)					\
+static inline bool name(type *v)				\
 {								\
-	unsigned char ok;					\
+	bool ok;						\
 	alternative_io("movb $0, %0\n\t"			\
 		       nop,					\
 		       rdseed "\n\t"				\
@@ -119,7 +119,7 @@ GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
 
 #else
 
-static inline int rdrand_long(unsigned long *v)
+static inline bool rdrand_long(unsigned long *v)
 {
 	return 0;
 }

arch/x86/include/asm/atomic.h

@@ -75,7 +75,7 @@ static __always_inline void atomic_sub(int i, atomic_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static __always_inline int atomic_sub_and_test(int i, atomic_t *v)
+static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e");
 }
@@ -112,7 +112,7 @@ static __always_inline void atomic_dec(atomic_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static __always_inline int atomic_dec_and_test(atomic_t *v)
+static __always_inline bool atomic_dec_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
 }
@@ -125,7 +125,7 @@ static __always_inline int atomic_dec_and_test(atomic_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static __always_inline int atomic_inc_and_test(atomic_t *v)
+static __always_inline bool atomic_inc_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
 }
@@ -139,7 +139,7 @@ static __always_inline int atomic_inc_and_test(atomic_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static __always_inline int atomic_add_negative(int i, atomic_t *v)
+static __always_inline bool atomic_add_negative(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s");
 }

arch/x86/include/asm/atomic64_64.h

@@ -70,7 +70,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic64_sub_and_test(long i, atomic64_t *v)
+static inline bool atomic64_sub_and_test(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", "e");
 }
@@ -109,7 +109,7 @@ static __always_inline void atomic64_dec(atomic64_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline int atomic64_dec_and_test(atomic64_t *v)
+static inline bool atomic64_dec_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e");
 }
@@ -122,7 +122,7 @@ static inline int atomic64_dec_and_test(atomic64_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic64_inc_and_test(atomic64_t *v)
+static inline bool atomic64_inc_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", "e");
 }
@@ -136,7 +136,7 @@ static inline int atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline int atomic64_add_negative(long i, atomic64_t *v)
+static inline bool atomic64_add_negative(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", "s");
 }
@@ -180,7 +180,7 @@ static inline long atomic64_xchg(atomic64_t *v, long new)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
+static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
 {
 	long c, old;
 	c = atomic64_read(v);

arch/x86/include/asm/bitops.h

@@ -201,7 +201,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static __always_inline int test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", "c");
 }
@@ -213,7 +213,7 @@ static __always_inline int test_and_set_bit(long nr, volatile unsigned long *add
  *
  * This is the same as test_and_set_bit on x86.
  */
-static __always_inline int
+static __always_inline bool
 test_and_set_bit_lock(long nr, volatile unsigned long *addr)
 {
 	return test_and_set_bit(nr, addr);
@@ -228,9 +228,9 @@ test_and_set_bit_lock(long nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	unsigned char oldbit;
+	bool oldbit;
 
 	asm("bts %2,%1\n\t"
 	    "setc %0"
@@ -247,7 +247,7 @@ static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *a
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", "c");
 }
@@ -268,9 +268,9 @@ static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *a
  * accessed from a hypervisor on the same CPU if running in a VM: don't change
  * this without also updating arch/x86/kernel/kvm.c
  */
-static __always_inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	unsigned char oldbit;
+	bool oldbit;
 
 	asm volatile("btr %2,%1\n\t"
 		     "setc %0"
@@ -280,9 +280,9 @@ static __always_inline int __test_and_clear_bit(long nr, volatile unsigned long
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static __always_inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	unsigned char oldbit;
+	bool oldbit;
 
 	asm volatile("btc %2,%1\n\t"
 		     "setc %0"
@@ -300,20 +300,20 @@ static __always_inline int __test_and_change_bit(long nr, volatile unsigned long
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static __always_inline int test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", "c");
 }
 
-static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr)
+static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
 {
 	return ((1UL << (nr & (BITS_PER_LONG-1))) &
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
-static __always_inline int variable_test_bit(long nr, volatile const unsigned long *addr)
+static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
-	unsigned char oldbit;
+	bool oldbit;
 
 	asm volatile("bt %2,%1\n\t"
 		     "setc %0"
@@ -329,7 +329,7 @@ static __always_inline int variable_test_bit(long nr, volatile const unsigned lo
  * @nr: bit number to test
  * @addr: Address to start counting from
  */
-static int test_bit(int nr, const volatile unsigned long *addr);
+static bool test_bit(int nr, const volatile unsigned long *addr);
 #endif
 
 #define test_bit(nr, addr)			\

arch/x86/include/asm/local.h

@@ -50,7 +50,7 @@ static inline void local_sub(long i, local_t *l)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline int local_sub_and_test(long i, local_t *l)
+static inline bool local_sub_and_test(long i, local_t *l)
 {
 	GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, "er", i, "%0", "e");
 }
@@ -63,7 +63,7 @@ static inline int local_sub_and_test(long i, local_t *l)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline int local_dec_and_test(local_t *l)
+static inline bool local_dec_and_test(local_t *l)
 {
 	GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e");
 }
@@ -76,7 +76,7 @@ static inline int local_dec_and_test(local_t *l)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline int local_inc_and_test(local_t *l)
+static inline bool local_inc_and_test(local_t *l)
 {
 	GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", "e");
 }
@@ -90,7 +90,7 @@ static inline int local_inc_and_test(local_t *l)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline int local_add_negative(long i, local_t *l)
+static inline bool local_add_negative(long i, local_t *l)
 {
 	GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, "er", i, "%0", "s");
 }

arch/x86/include/asm/percpu.h

@@ -510,14 +510,14 @@ do {									\
 /* This is not atomic against other CPUs -- CPU preemption needs to be off */
 #define x86_test_and_clear_bit_percpu(bit, var)				\
 ({									\
-	unsigned char old__;						\
+	bool old__;							\
 	asm volatile("btr %2,"__percpu_arg(1)"\n\tsetc %0"		\
 		     : "=qm" (old__), "+m" (var)			\
 		     : "dIr" (bit));					\
 	old__;								\
 })
 
-static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
+static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,
                         const unsigned long __percpu *addr)
 {
 	unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG;
@@ -529,10 +529,10 @@ static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
 #endif
 }
 
-static inline int x86_this_cpu_variable_test_bit(int nr,
+static inline bool x86_this_cpu_variable_test_bit(int nr,
                         const unsigned long __percpu *addr)
 {
-	unsigned char oldbit;
+	bool oldbit;
 
 	asm volatile("bt "__percpu_arg(2)",%1\n\t"
 			"setc %0"

arch/x86/include/asm/rmwcc.h

@@ -23,11 +23,11 @@ cc_label:								\
 
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
-	char c;								\
+	bool c;								\
 	asm volatile (fullop "; set" cc " %1"				\
 			: "+m" (var), "=qm" (c)				\
 			: __VA_ARGS__ : "memory");			\
-	return c != 0;							\
+	return c;							\
 } while (0)
 
 #define GEN_UNARY_RMWcc(op, var, arg0, cc)				\

arch/x86/include/asm/rwsem.h

@@ -77,7 +77,7 @@ static inline void __down_read(struct rw_semaphore *sem)
 /*
  * trylock for reading -- returns 1 if successful, 0 if contention
  */
-static inline int __down_read_trylock(struct rw_semaphore *sem)
+static inline bool __down_read_trylock(struct rw_semaphore *sem)
 {
 	long result, tmp;
 	asm volatile("# beginning __down_read_trylock\n\t"
@@ -93,7 +93,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 		     : "+m" (sem->count), "=&a" (result), "=&r" (tmp)
 		     : "i" (RWSEM_ACTIVE_READ_BIAS)
 		     : "memory", "cc");
-	return result >= 0 ? 1 : 0;
+	return result >= 0;
 }
 
 /*
@@ -134,9 +134,10 @@ static inline int __down_write_killable(struct rw_semaphore *sem)
 /*
  * trylock for writing -- returns 1 if successful, 0 if contention
  */
-static inline int __down_write_trylock(struct rw_semaphore *sem)
+static inline bool __down_write_trylock(struct rw_semaphore *sem)
 {
-	long result, tmp;
+	bool result;
+	long tmp0, tmp1;
 	asm volatile("# beginning __down_write_trylock\n\t"
 		     "  mov          %0,%1\n\t"
 		     "1:\n\t"
@@ -144,14 +145,14 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
 		     /* was the active mask 0 before? */
 		     "  jnz          2f\n\t"
 		     "  mov          %1,%2\n\t"
-		     "  add          %3,%2\n\t"
+		     "  add          %4,%2\n\t"
 		     LOCK_PREFIX "  cmpxchg  %2,%0\n\t"
 		     "  jnz	     1b\n\t"
 		     "2:\n\t"
-		     "  sete         %b1\n\t"
-		     "  movzbl       %b1, %k1\n\t"
+		     "  sete         %3\n\t"
 		     "# ending __down_write_trylock\n\t"
-		     : "+m" (sem->count), "=&a" (result), "=&r" (tmp)
+		     : "+m" (sem->count), "=&a" (tmp0), "=&r" (tmp1),
+		       "=qm" (result)
 		     : "er" (RWSEM_ACTIVE_WRITE_BIAS)
 		     : "memory", "cc");
 	return result;

include/linux/random.h

@@ -95,27 +95,27 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed)
 #ifdef CONFIG_ARCH_RANDOM
 # include <asm/archrandom.h>
 #else
-static inline int arch_get_random_long(unsigned long *v)
+static inline bool arch_get_random_long(unsigned long *v)
 {
 	return 0;
 }
-static inline int arch_get_random_int(unsigned int *v)
+static inline bool arch_get_random_int(unsigned int *v)
 {
 	return 0;
 }
-static inline int arch_has_random(void)
+static inline bool arch_has_random(void)
 {
 	return 0;
 }
-static inline int arch_get_random_seed_long(unsigned long *v)
+static inline bool arch_get_random_seed_long(unsigned long *v)
 {
 	return 0;
 }
-static inline int arch_get_random_seed_int(unsigned int *v)
+static inline bool arch_get_random_seed_int(unsigned int *v)
 {
 	return 0;
 }
-static inline int arch_has_random_seed(void)
+static inline bool arch_has_random_seed(void)
 {
 	return 0;
 }