[PATCH v2 00/10] x86: use gcc 6+ asm flag output feature

[PATCH v2 00/10] x86: use gcc 6+ asm flag output feature

[H. Peter Anvin]

From: "H. Peter Anvin" <hpa@zytor.com>

gcc 6+ has the ability to let flags (actually, conditions, which are
specific combinations of flags) to be used directly as asm() outputs.
The syntax for that is "=@cc<cc>" where <cc> is the same set of
letters that would be used in a j<cc> or set<cc> instruction
(e.g. "=@ccz" to test the ZF flag.)

This patchset by itself reduces the size of the x86-64 kernel by
0.12%, from a baseline of 4.7-rc2 built with gcc 6.1 (first line is
with the patchset, the second one is without):

     text       data       bss        dec       hex filename

 68245656   41004339  20533248  129783243   7bc55cb o.i386-allconfig/vmlinux
 68355716   41008499  20533248  129897463   7be13f7 o.i386-allconfig/vmlinux

127384005  129742359  38150144  295276508  11998fdc o.x86_64-allconfig/vmlinux
127538765  129742295  38150144  295431204  119bec24 o.x86_64-allconfig/vmlinux

v2: fix a conflict between <linux/random.h> and <asm/archrandom.h>
    discovered by Ingo Molnar.  There are a few places in x86-specific
    code where we need all of <arch/archrandom.h> even when
    xCONFIG_ARCH_RANDOM is disabled, so <linux/random.h> does not
    suffice.  Only the <asm/archrandom.h> patch has been changed;
    since it is a little bit different from the others I have moved it
    to the end.

[PATCH v2 01/10] x86, bitops: remove use of "sbb" to return CF

[H. Peter Anvin]

From: "H. Peter Anvin" <hpa@zytor.com>

Use SETC instead of SBB to return the value of CF from assembly. Using
SETcc enables uniformity with other flags-returning pieces of assembly
code.

Signed-off-by: H. Peter Anvin <hpa@zytor.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/include/asm/bitops.h      | 24 ++++++++++++------------
 arch/x86/include/asm/percpu.h      | 12 ++++++------
 arch/x86/include/asm/signal.h      |  6 +++---
 arch/x86/include/asm/sync_bitops.h | 18 +++++++++---------
 arch/x86/kernel/vm86_32.c          |  5 +----
 5 files changed, 31 insertions(+), 34 deletions(-)

diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 7766d1c..b2b797d 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -230,11 +230,11 @@ test_and_set_bit_lock(long nr, volatile unsigned long *addr)
  */
 static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
 	asm("bts %2,%1\n\t"
-	    "sbb %0,%0"
-	    : "=r" (oldbit), ADDR
+	    "setc %0"
+	    : "=qm" (oldbit), ADDR
 	    : "Ir" (nr));
 	return oldbit;
 }
@@ -270,11 +270,11 @@ static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *a
  */
 static __always_inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
 	asm volatile("btr %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR
+		     "setc %0"
+		     : "=qm" (oldbit), ADDR
 		     : "Ir" (nr));
 	return oldbit;
 }
@@ -282,11 +282,11 @@ 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)
 {
-	int oldbit;
+	unsigned char oldbit;
 
 	asm volatile("btc %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR
+		     "setc %0"
+		     : "=qm" (oldbit), ADDR
 		     : "Ir" (nr) : "memory");
 
 	return oldbit;
@@ -313,11 +313,11 @@ static __always_inline int constant_test_bit(long nr, const volatile unsigned lo
 
 static __always_inline int variable_test_bit(long nr, volatile const unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
 	asm volatile("bt %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit)
+		     "setc %0"
+		     : "=qm" (oldbit)
 		     : "m" (*(unsigned long *)addr), "Ir" (nr));
 
 	return oldbit;
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e0ba66c..65039e9 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -510,9 +510,9 @@ do {									\
 /* This is not atomic against other CPUs -- CPU preemption needs to be off */
 #define x86_test_and_clear_bit_percpu(bit, var)				\
 ({									\
-	int old__;							\
-	asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0"		\
-		     : "=r" (old__), "+m" (var)				\
+	unsigned char old__;						\
+	asm volatile("btr %2,"__percpu_arg(1)"\n\tsetc %0"		\
+		     : "=qm" (old__), "+m" (var)			\
 		     : "dIr" (bit));					\
 	old__;								\
 })
@@ -532,11 +532,11 @@ static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
 static inline int x86_this_cpu_variable_test_bit(int nr,
                         const unsigned long __percpu *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
 	asm volatile("bt "__percpu_arg(2)",%1\n\t"
-			"sbb %0,%0"
-			: "=r" (oldbit)
+			"setc %0"
+			: "=qm" (oldbit)
 			: "m" (*(unsigned long *)addr), "Ir" (nr));
 
 	return oldbit;
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 2138c9a..dd1e7d6 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -81,9 +81,9 @@ static inline int __const_sigismember(sigset_t *set, int _sig)
 
 static inline int __gen_sigismember(sigset_t *set, int _sig)
 {
-	int ret;
-	asm("btl %2,%1\n\tsbbl %0,%0"
-	    : "=r"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
+	unsigned char ret;
+	asm("btl %2,%1\n\tsetc %0"
+	    : "=qm"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
 	return ret;
 }
 
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index f28a24b..cbf8847 100644
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -79,10 +79,10 @@ static inline void sync_change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
-	asm volatile("lock; bts %2,%1\n\tsbbl %0,%0"
-		     : "=r" (oldbit), "+m" (ADDR)
+	asm volatile("lock; bts %2,%1\n\tsetc %0"
+		     : "=qm" (oldbit), "+m" (ADDR)
 		     : "Ir" (nr) : "memory");
 	return oldbit;
 }
@@ -97,10 +97,10 @@ static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
-	asm volatile("lock; btr %2,%1\n\tsbbl %0,%0"
-		     : "=r" (oldbit), "+m" (ADDR)
+	asm volatile("lock; btr %2,%1\n\tsetc %0"
+		     : "=qm" (oldbit), "+m" (ADDR)
 		     : "Ir" (nr) : "memory");
 	return oldbit;
 }
@@ -115,10 +115,10 @@ static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
-	asm volatile("lock; btc %2,%1\n\tsbbl %0,%0"
-		     : "=r" (oldbit), "+m" (ADDR)
+	asm volatile("lock; btc %2,%1\n\tsetc %0"
+		     : "=qm" (oldbit), "+m" (ADDR)
 		     : "Ir" (nr) : "memory");
 	return oldbit;
 }
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 3dce1ca..01f30e5 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -440,10 +440,7 @@ static inline unsigned long get_vflags(struct kernel_vm86_regs *regs)
 
 static inline int is_revectored(int nr, struct revectored_struct *bitmap)
 {
-	__asm__ __volatile__("btl %2,%1\n\tsbbl %0,%0"
-		:"=r" (nr)
-		:"m" (*bitmap), "r" (nr));
-	return nr;
+	return test_bit(nr, bitmap->__map);
 }
 
 #define val_byte(val, n) (((__u8 *)&val)[n])
-- 
2.7.3.0.11.gd79db92

[PATCH v2 02/10] x86, asm: use bool for bitops and other assembly outputs

[H. Peter Anvin]

From: "H. Peter Anvin" <hpa@zytor.com>

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>
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             |  8 +++++---
 arch/x86/boot/boot.h               |  8 ++++----
 arch/x86/boot/string.c             |  2 +-
 arch/x86/include/asm/apm.h         |  6 +++---
 arch/x86/include/asm/archrandom.h  | 16 ++++++++--------
 arch/x86/include/asm/atomic.h      |  8 ++++----
 arch/x86/include/asm/atomic64_64.h | 10 +++++-----
 arch/x86/include/asm/bitops.h      | 28 ++++++++++++++--------------
 arch/x86/include/asm/local.h       |  8 ++++----
 arch/x86/include/asm/percpu.h      |  8 ++++----
 arch/x86/include/asm/rmwcc.h       |  4 ++--
 arch/x86/include/asm/rwsem.h       | 17 +++++++++--------
 include/linux/random.h             | 12 ++++++------
 13 files changed, 69 insertions(+), 66 deletions(-)

diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h
index 878e4b9..0d41d68 100644
--- a/arch/x86/boot/bitops.h
+++ b/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));
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 9011a88..2edb2d5 100644
--- a/arch/x86/boot/boot.h
+++ b/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;
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 318b846..cc3bd58 100644
--- a/arch/x86/boot/string.c
+++ b/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;
diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h
index 20370c6..93eebc63 100644
--- a/arch/x86/include/asm/apm.h
+++ b/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
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index 69f1366..ab6f599 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/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;
 }
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 3e86742..17d8812 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/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");
 }
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 0373510..4f881d7 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/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);
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index b2b797d..8cbb7f4 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/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)			\
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 4ad6560..0cdc65b 100644
--- a/arch/x86/include/asm/local.h
+++ b/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");
 }
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 65039e9..184d7f3 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/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"
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 8f7866a..a15b73d 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/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)				\
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index 453744c..c508770 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/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;
diff --git a/include/linux/random.h b/include/linux/random.h
index e47e533..3d6e981 100644
--- a/include/linux/random.h
+++ b/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;
 }
-- 
2.7.3.0.11.gd79db92

[PATCH v2 03/10] x86, asm: change the GEN_*_RMWcc() macros to not quote the condition

[H. Peter Anvin]

From: "H. Peter Anvin" <hpa@zytor.com>

Change the lexical defintion of the GEN_*_RMWcc() macros to not take
the condition code as a quoted string.  This will help support
changing them to use the new __GCC_ASM_FLAG_OUTPUTS__ feature in a
subsequent patch.

Signed-off-by: H. Peter Anvin <hpa@zytor.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/include/asm/atomic.h      | 8 ++++----
 arch/x86/include/asm/atomic64_64.h | 8 ++++----
 arch/x86/include/asm/bitops.h      | 6 +++---
 arch/x86/include/asm/local.h       | 8 ++++----
 arch/x86/include/asm/preempt.h     | 2 +-
 arch/x86/include/asm/rmwcc.h       | 4 ++--
 6 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 17d8812..7322c15 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -77,7 +77,7 @@ static __always_inline void atomic_sub(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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
 }
 
 /**
@@ -114,7 +114,7 @@ static __always_inline void atomic_dec(atomic_t *v)
  */
 static __always_inline bool atomic_dec_and_test(atomic_t *v)
 {
-	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
 }
 
 /**
@@ -127,7 +127,7 @@ static __always_inline bool atomic_dec_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");
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
 }
 
 /**
@@ -141,7 +141,7 @@ static __always_inline bool atomic_inc_and_test(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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
 }
 
 /**
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 4f881d7..57bf925 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -72,7 +72,7 @@ static inline void atomic64_sub(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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
 }
 
 /**
@@ -111,7 +111,7 @@ static __always_inline void atomic64_dec(atomic64_t *v)
  */
 static inline bool atomic64_dec_and_test(atomic64_t *v)
 {
-	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e");
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
 }
 
 /**
@@ -124,7 +124,7 @@ static inline bool atomic64_dec_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");
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
 }
 
 /**
@@ -138,7 +138,7 @@ static inline bool atomic64_inc_and_test(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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
 }
 
 /**
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 8cbb7f4..ed8f485 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -203,7 +203,7 @@ static __always_inline void change_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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", c);
 }
 
 /**
@@ -249,7 +249,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
  */
 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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", c);
 }
 
 /**
@@ -302,7 +302,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
  */
 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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", c);
 }
 
 static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 0cdc65b..7511978 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -52,7 +52,7 @@ static inline void local_sub(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");
+	GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, "er", i, "%0", e);
 }
 
 /**
@@ -65,7 +65,7 @@ static inline bool local_sub_and_test(long i, local_t *l)
  */
 static inline bool local_dec_and_test(local_t *l)
 {
-	GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e");
+	GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", e);
 }
 
 /**
@@ -78,7 +78,7 @@ static inline bool local_dec_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");
+	GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", e);
 }
 
 /**
@@ -92,7 +92,7 @@ static inline bool local_inc_and_test(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");
+	GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, "er", i, "%0", s);
 }
 
 /**
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index d397deb..17f2186 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -81,7 +81,7 @@ static __always_inline void __preempt_count_sub(int val)
  */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
+	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e);
 }
 
 /*
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index a15b73d..e3264c4 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -5,7 +5,7 @@
 
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
-	asm_volatile_goto (fullop "; j" cc " %l[cc_label]"		\
+	asm_volatile_goto (fullop "; j" #cc " %l[cc_label]"		\
 			: : "m" (var), ## __VA_ARGS__ 			\
 			: "memory" : cc_label);				\
 	return 0;							\
@@ -24,7 +24,7 @@ cc_label:								\
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
 	bool c;								\
-	asm volatile (fullop "; set" cc " %1"				\
+	asm volatile (fullop "; set" #cc " %1"				\
 			: "+m" (var), "=qm" (c)				\
 			: __VA_ARGS__ : "memory");			\
 	return c;							\
-- 
2.7.3.0.11.gd79db92

[PATCH v2 04/10] x86, asm: define CC_SET() and CC_OUT() macros

[H. Peter Anvin]

From: "H. Peter Anvin" <hpa@zytor.com>

The CC_SET() and CC_OUT() macros can be used together to take
advantage of the new __GCC_ASM_FLAG_OUTPUTS__ feature in gcc 6+ while
remaining backwards compatible.  CC_SET() generates a SET instruction
on older compilers; CC_OUT() makes sure the output is received in the
correct variable.

Signed-off-by: H. Peter Anvin <hpa@zytor.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/include/asm/asm.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index f5063b6..7acb51c 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -42,6 +42,18 @@
 #define _ASM_SI		__ASM_REG(si)
 #define _ASM_DI		__ASM_REG(di)
 
+/*
+ * Macros to generate condition code outputs from inline assembly,
+ * The output operand must be type "bool".
+ */
+#ifdef __GCC_ASM_FLAG_OUTPUTS__
+# define CC_SET(c) "\n\t/* output condition code " #c "*/\n"
+# define CC_OUT(c) "=@cc" #c
+#else
+# define CC_SET(c) "\n\tset" #c " %[_cc_" #c "]\n"
+# define CC_OUT(c) [_cc_ ## c] "=qm"
+#endif
+
 /* Exception table entry */
 #ifdef __ASSEMBLY__
 # define _ASM_EXTABLE_HANDLE(from, to, handler)			\
-- 
2.7.3.0.11.gd79db92

[PATCH v2 05/10] x86, asm: change GEN_*_RMWcc() to use CC_SET()/CC_OUT()

[H. Peter Anvin]

From: "H. Peter Anvin" <hpa@zytor.com>

Change the GEN_*_RMWcc() macros to use the CC_SET()/CC_OUT() macros
defined in <asm/asm.h>, and disable the use of asm goto if
__GCC_ASM_FLAG_OUTPUTS__ is enabled.  This allows gcc to receive the
flags output directly in gcc 6+.

Signed-off-by: H. Peter Anvin <hpa@zytor.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/include/asm/rmwcc.h | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index e3264c4..661dd30 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -1,7 +1,9 @@
 #ifndef _ASM_X86_RMWcc
 #define _ASM_X86_RMWcc
 
-#ifdef CC_HAVE_ASM_GOTO
+#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO)
+
+/* Use asm goto */
 
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
@@ -19,13 +21,15 @@ cc_label:								\
 #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
 	__GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val))
 
-#else /* !CC_HAVE_ASM_GOTO */
+#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
+
+/* Use flags output or a set instruction */
 
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
 	bool c;								\
-	asm volatile (fullop "; set" #cc " %1"				\
-			: "+m" (var), "=qm" (c)				\
+	asm volatile (fullop ";" CC_SET(cc)				\
+			: "+m" (var), CC_OUT(cc) (c)			\
 			: __VA_ARGS__ : "memory");			\
 	return c;							\
 } while (0)
@@ -36,6 +40,6 @@ do {									\
 #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
 	__GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val))
 
-#endif /* CC_HAVE_ASM_GOTO */
+#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
 
 #endif /* _ASM_X86_RMWcc */
-- 
2.7.3.0.11.gd79db92

[PATCH v2 06/10] x86, asm: Use CC_SET()/CC_OUT() in <asm/bitops.h>

[H. Peter Anvin]

From: "H. Peter Anvin" <hpa@zytor.com>

Remove open-coded uses of set instructions to use CC_SET()/CC_OUT() in
<asm/bitops.h>.

Signed-off-by: H. Peter Anvin <hpa@zytor.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/include/asm/bitops.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index ed8f485..68557f52 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -233,8 +233,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
 	bool oldbit;
 
 	asm("bts %2,%1\n\t"
-	    "setc %0"
-	    : "=qm" (oldbit), ADDR
+	    CC_SET(c)
+	    : CC_OUT(c) (oldbit), ADDR
 	    : "Ir" (nr));
 	return oldbit;
 }
@@ -273,8 +273,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long
 	bool oldbit;
 
 	asm volatile("btr %2,%1\n\t"
-		     "setc %0"
-		     : "=qm" (oldbit), ADDR
+		     CC_SET(c)
+		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr));
 	return oldbit;
 }
@@ -285,8 +285,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
 	bool oldbit;
 
 	asm volatile("btc %2,%1\n\t"
-		     "setc %0"
-		     : "=qm" (oldbit), ADDR
+		     CC_SET(c)
+		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr) : "memory");
 
 	return oldbit;
@@ -316,8 +316,8 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
 	bool oldbit;
 
 	asm volatile("bt %2,%1\n\t"
-		     "setc %0"
-		     : "=qm" (oldbit)
+		     CC_SET(c)
+		     : CC_OUT(c) (oldbit)
 		     : "m" (*(unsigned long *)addr), "Ir" (nr));
 
 	return oldbit;
-- 
2.7.3.0.11.gd79db92

[PATCH v2 07/10] x86, asm: Use CC_SET()/CC_OUT() in <asm/percpu.h>

[H. Peter Anvin]

From: "H. Peter Anvin" <hpa@zytor.com>

Remove open-coded uses of set instructions to use CC_SET()/CC_OUT() in
<asm/percpu.h>.

Signed-off-by: H. Peter Anvin <hpa@zytor.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/include/asm/percpu.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 184d7f3..e02e3f8 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -511,8 +511,9 @@ do {									\
 #define x86_test_and_clear_bit_percpu(bit, var)				\
 ({									\
 	bool old__;							\
-	asm volatile("btr %2,"__percpu_arg(1)"\n\tsetc %0"		\
-		     : "=qm" (old__), "+m" (var)			\
+	asm volatile("btr %2,"__percpu_arg(1)"\n\t"			\
+		     CC_SET(c)						\
+		     : CC_OUT(c) (old__), "+m" (var)			\
 		     : "dIr" (bit));					\
 	old__;								\
 })
@@ -535,8 +536,8 @@ static inline bool x86_this_cpu_variable_test_bit(int nr,
 	bool oldbit;
 
 	asm volatile("bt "__percpu_arg(2)",%1\n\t"
-			"setc %0"
-			: "=qm" (oldbit)
+			CC_SET(c)
+			: CC_OUT(c) (oldbit)
 			: "m" (*(unsigned long *)addr), "Ir" (nr));
 
 	return oldbit;
-- 
2.7.3.0.11.gd79db92

[PATCH v2 08/10] x86, asm: Use CC_SET()/CC_OUT() in <asm/rwsem.h>

[H. Peter Anvin]

From: "H. Peter Anvin" <hpa@zytor.com>

Remove open-coded uses of set instructions to use CC_SET()/CC_OUT() in
<asm/rwsem.h>.

Signed-off-by: H. Peter Anvin <hpa@zytor.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/include/asm/rwsem.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index c508770..1e8be26 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -149,10 +149,10 @@ static inline bool __down_write_trylock(struct rw_semaphore *sem)
 		     LOCK_PREFIX "  cmpxchg  %2,%0\n\t"
 		     "  jnz	     1b\n\t"
 		     "2:\n\t"
-		     "  sete         %3\n\t"
+		     CC_SET(e)
 		     "# ending __down_write_trylock\n\t"
 		     : "+m" (sem->count), "=&a" (tmp0), "=&r" (tmp1),
-		       "=qm" (result)
+		       CC_OUT(e) (result)
 		     : "er" (RWSEM_ACTIVE_WRITE_BIAS)
 		     : "memory", "cc");
 	return result;
-- 
2.7.3.0.11.gd79db92

[PATCH v2 09/10] x86, asm, boot: Use CC_SET()/CC_OUT() in arch/x86/boot/boot.h

[H. Peter Anvin]

Remove open-coded uses of set instructions to use CC_SET()/CC_OUT() in
arch/x86/boot/boot.h.

Signed-off-by: H. Peter Anvin <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/boot.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 2edb2d5..7c1495f 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -24,6 +24,7 @@
 #include <linux/types.h>
 #include <linux/edd.h>
 #include <asm/setup.h>
+#include <asm/asm.h>
 #include "bitops.h"
 #include "ctype.h"
 #include "cpuflags.h"
@@ -179,15 +180,15 @@ static inline void wrgs32(u32 v, addr_t addr)
 static inline bool memcmp_fs(const void *s1, addr_t s2, size_t len)
 {
 	bool diff;
-	asm volatile("fs; repe; cmpsb; setnz %0"
-		     : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	asm volatile("fs; repe; cmpsb" CC_SET(nz)
+		     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 static inline bool memcmp_gs(const void *s1, addr_t s2, size_t len)
 {
 	bool diff;
-	asm volatile("gs; repe; cmpsb; setnz %0"
-		     : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	asm volatile("gs; repe; cmpsb" CC_SET(nz)
+		     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 
-- 
2.7.3.0.11.gd79db92

[PATCH v2 10/10] x86, asm: Use CC_SET()/CC_OUT() and static_cpu_has() in archrandom.h

[H. Peter Anvin]

Use CC_SET()/CC_OUT() and static_cpu_has().  This produces code good
enough to eliminate ad hoc use of alternatives in <asm/archrandom.h>,
greatly simplifying the code.

While we are at it, make x86_init_rdrand() compile out completely if
we don't need it.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

v2: fix a conflict between <linux/random.h> and <asm/archrandom.h>
    discovered by Ingo Molnar.  There are a few places in x86-specific
    code where we need all of <arch/archrandom.h> even when
    CONFIG_ARCH_RANDOM is disabled, so <linux/random.h> does not
    suffice.
---
 arch/x86/include/asm/archrandom.h | 128 ++++++++++++++++++--------------------
 arch/x86/kernel/cpu/rdrand.c      |   4 +-
 2 files changed, 62 insertions(+), 70 deletions(-)

diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index ab6f599..5b0579a 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -25,8 +25,6 @@
 
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
-#include <asm/alternative.h>
-#include <asm/nops.h>
 
 #define RDRAND_RETRY_LOOPS	10
 
@@ -40,97 +38,91 @@
 # define RDSEED_LONG	RDSEED_INT
 #endif
 
-#ifdef CONFIG_ARCH_RANDOM
+/* Unconditional execution of RDRAND and RDSEED */
 
-/* Instead of arch_get_random_long() when alternatives haven't run. */
 static inline bool rdrand_long(unsigned long *v)
 {
-	int ok;
-	asm volatile("1: " RDRAND_LONG "\n\t"
-		     "jc 2f\n\t"
-		     "decl %0\n\t"
-		     "jnz 1b\n\t"
-		     "2:"
-		     : "=r" (ok), "=a" (*v)
-		     : "0" (RDRAND_RETRY_LOOPS));
-	return !!ok;
+	bool ok;
+	unsigned int retry = RDRAND_RETRY_LOOPS;
+	do {
+		asm volatile(RDRAND_LONG "\n\t"
+			     CC_SET(c)
+			     : CC_OUT(c) (ok), "=a" (*v));
+		if (ok)
+			return true;
+	} while (--retry);
+	return false;
+}
+
+static inline bool rdrand_int(unsigned int *v)
+{
+	bool ok;
+	unsigned int retry = RDRAND_RETRY_LOOPS;
+	do {
+		asm volatile(RDRAND_INT "\n\t"
+			     CC_SET(c)
+			     : CC_OUT(c) (ok), "=a" (*v));
+		if (ok)
+			return true;
+	} while (--retry);
+	return false;
 }
 
-/* A single attempt at RDSEED */
 static inline bool rdseed_long(unsigned long *v)
 {
 	bool ok;
 	asm volatile(RDSEED_LONG "\n\t"
-		     "setc %0"
-		     : "=qm" (ok), "=a" (*v));
+		     CC_SET(c)
+		     : CC_OUT(c) (ok), "=a" (*v));
 	return ok;
 }
 
-#define GET_RANDOM(name, type, rdrand, nop)			\
-static inline bool name(type *v)				\
-{								\
-	int ok;							\
-	alternative_io("movl $0, %0\n\t"			\
-		       nop,					\
-		       "\n1: " rdrand "\n\t"			\
-		       "jc 2f\n\t"				\
-		       "decl %0\n\t"                            \
-		       "jnz 1b\n\t"                             \
-		       "2:",                                    \
-		       X86_FEATURE_RDRAND,                      \
-		       ASM_OUTPUT2("=r" (ok), "=a" (*v)),       \
-		       "0" (RDRAND_RETRY_LOOPS));		\
-	return !!ok;						\
-}
-
-#define GET_SEED(name, type, rdseed, nop)			\
-static inline bool name(type *v)				\
-{								\
-	bool ok;						\
-	alternative_io("movb $0, %0\n\t"			\
-		       nop,					\
-		       rdseed "\n\t"				\
-		       "setc %0",				\
-		       X86_FEATURE_RDSEED,                      \
-		       ASM_OUTPUT2("=q" (ok), "=a" (*v)));	\
-	return ok;						\
+static inline bool rdseed_int(unsigned int *v)
+{
+	bool ok;
+	asm volatile(RDSEED_INT "\n\t"
+		     CC_SET(c)
+		     : CC_OUT(c) (ok), "=a" (*v));
+	return ok;
 }
 
-#ifdef CONFIG_X86_64
-
-GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP5);
-GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP4);
-
-GET_SEED(arch_get_random_seed_long, unsigned long, RDSEED_LONG, ASM_NOP5);
-GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
-
-#else
-
-GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP3);
-GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP3);
-
-GET_SEED(arch_get_random_seed_long, unsigned long, RDSEED_LONG, ASM_NOP4);
-GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
-
-#endif /* CONFIG_X86_64 */
-
+/* Conditional execution based on CPU type */
 #define arch_has_random()	static_cpu_has(X86_FEATURE_RDRAND)
 #define arch_has_random_seed()	static_cpu_has(X86_FEATURE_RDSEED)
 
-#else
+/*
+ * These are the generic interfaces; they must not be declared if the
+ * stubs in <linux/random.h> are to be invoked,
+ * i.e. CONFIG_ARCH_RANDOM is not defined.
+ */
+#ifdef CONFIG_ARCH_RANDOM
 
-static inline bool rdrand_long(unsigned long *v)
+static inline bool arch_get_random_long(unsigned long *v)
 {
-	return 0;
+	return arch_has_random() ? rdrand_long(v) : false;
 }
 
-static inline bool rdseed_long(unsigned long *v)
+static inline bool arch_get_random_int(unsigned int *v)
 {
-	return 0;
+	return arch_has_random() ? rdrand_int(v) : false;
 }
 
-#endif  /* CONFIG_ARCH_RANDOM */
+static inline bool arch_get_random_seed_long(unsigned long *v)
+{
+	return arch_has_random_seed() ? rdseed_long(v) : false;
+}
+
+static inline bool arch_get_random_seed_int(unsigned int *v)
+{
+	return arch_has_random_seed() ? rdseed_int(v) : false;
+}
 
 extern void x86_init_rdrand(struct cpuinfo_x86 *c);
 
+#else  /* !CONFIG_ARCH_RANDOM */
+
+static inline void x86_init_rdrand(struct cpuinfo_x86 *c) { }
+
+#endif  /* !CONFIG_ARCH_RANDOM */
+
 #endif /* ASM_X86_ARCHRANDOM_H */
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index f6f50c4..cfa97ff 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -39,9 +39,9 @@ __setup("nordrand", x86_rdrand_setup);
  */
 #define SANITY_CHECK_LOOPS 8
 
+#ifdef CONFIG_ARCH_RANDOM
 void x86_init_rdrand(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_ARCH_RANDOM
 	unsigned long tmp;
 	int i;
 
@@ -55,5 +55,5 @@ void x86_init_rdrand(struct cpuinfo_x86 *c)
 			return;
 		}
 	}
-#endif
 }
+#endif
-- 
2.7.3.0.11.gd79db92

[tip:x86/asm] x86, bitops: remove use of "sbb" to return CF

[tip-bot for H. Peter Anvin]

Commit-ID:  2823d4da5d8a0c222747b24eceb65f5b30717d02
Gitweb:     http://git.kernel.org/tip/2823d4da5d8a0c222747b24eceb65f5b30717d02
Author:     H. Peter Anvin <hpa@zytor.com>
AuthorDate: Wed, 8 Jun 2016 12:38:37 -0700
Committer:  H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Wed, 8 Jun 2016 12:41:20 -0700

x86, bitops: remove use of "sbb" to return CF

Use SETC instead of SBB to return the value of CF from assembly. Using
SETcc enables uniformity with other flags-returning pieces of assembly
code.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1465414726-197858-2-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/include/asm/bitops.h      | 24 ++++++++++++------------
 arch/x86/include/asm/percpu.h      | 12 ++++++------
 arch/x86/include/asm/signal.h      |  6 +++---
 arch/x86/include/asm/sync_bitops.h | 18 +++++++++---------
 arch/x86/kernel/vm86_32.c          |  5 +----
 5 files changed, 31 insertions(+), 34 deletions(-)

diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 7766d1c..b2b797d 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -230,11 +230,11 @@ test_and_set_bit_lock(long nr, volatile unsigned long *addr)
  */
 static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
 	asm("bts %2,%1\n\t"
-	    "sbb %0,%0"
-	    : "=r" (oldbit), ADDR
+	    "setc %0"
+	    : "=qm" (oldbit), ADDR
 	    : "Ir" (nr));
 	return oldbit;
 }
@@ -270,11 +270,11 @@ static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *a
  */
 static __always_inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
 	asm volatile("btr %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR
+		     "setc %0"
+		     : "=qm" (oldbit), ADDR
 		     : "Ir" (nr));
 	return oldbit;
 }
@@ -282,11 +282,11 @@ 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)
 {
-	int oldbit;
+	unsigned char oldbit;
 
 	asm volatile("btc %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR
+		     "setc %0"
+		     : "=qm" (oldbit), ADDR
 		     : "Ir" (nr) : "memory");
 
 	return oldbit;
@@ -313,11 +313,11 @@ static __always_inline int constant_test_bit(long nr, const volatile unsigned lo
 
 static __always_inline int variable_test_bit(long nr, volatile const unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
 	asm volatile("bt %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit)
+		     "setc %0"
+		     : "=qm" (oldbit)
 		     : "m" (*(unsigned long *)addr), "Ir" (nr));
 
 	return oldbit;
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e0ba66c..65039e9 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -510,9 +510,9 @@ do {									\
 /* This is not atomic against other CPUs -- CPU preemption needs to be off */
 #define x86_test_and_clear_bit_percpu(bit, var)				\
 ({									\
-	int old__;							\
-	asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0"		\
-		     : "=r" (old__), "+m" (var)				\
+	unsigned char old__;						\
+	asm volatile("btr %2,"__percpu_arg(1)"\n\tsetc %0"		\
+		     : "=qm" (old__), "+m" (var)			\
 		     : "dIr" (bit));					\
 	old__;								\
 })
@@ -532,11 +532,11 @@ static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
 static inline int x86_this_cpu_variable_test_bit(int nr,
                         const unsigned long __percpu *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
 	asm volatile("bt "__percpu_arg(2)",%1\n\t"
-			"sbb %0,%0"
-			: "=r" (oldbit)
+			"setc %0"
+			: "=qm" (oldbit)
 			: "m" (*(unsigned long *)addr), "Ir" (nr));
 
 	return oldbit;
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 2138c9a..dd1e7d6 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -81,9 +81,9 @@ static inline int __const_sigismember(sigset_t *set, int _sig)
 
 static inline int __gen_sigismember(sigset_t *set, int _sig)
 {
-	int ret;
-	asm("btl %2,%1\n\tsbbl %0,%0"
-	    : "=r"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
+	unsigned char ret;
+	asm("btl %2,%1\n\tsetc %0"
+	    : "=qm"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
 	return ret;
 }
 
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index f28a24b..cbf8847 100644
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -79,10 +79,10 @@ static inline void sync_change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
-	asm volatile("lock; bts %2,%1\n\tsbbl %0,%0"
-		     : "=r" (oldbit), "+m" (ADDR)
+	asm volatile("lock; bts %2,%1\n\tsetc %0"
+		     : "=qm" (oldbit), "+m" (ADDR)
 		     : "Ir" (nr) : "memory");
 	return oldbit;
 }
@@ -97,10 +97,10 @@ static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
-	asm volatile("lock; btr %2,%1\n\tsbbl %0,%0"
-		     : "=r" (oldbit), "+m" (ADDR)
+	asm volatile("lock; btr %2,%1\n\tsetc %0"
+		     : "=qm" (oldbit), "+m" (ADDR)
 		     : "Ir" (nr) : "memory");
 	return oldbit;
 }
@@ -115,10 +115,10 @@ static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
-	asm volatile("lock; btc %2,%1\n\tsbbl %0,%0"
-		     : "=r" (oldbit), "+m" (ADDR)
+	asm volatile("lock; btc %2,%1\n\tsetc %0"
+		     : "=qm" (oldbit), "+m" (ADDR)
 		     : "Ir" (nr) : "memory");
 	return oldbit;
 }
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 3dce1ca..01f30e5 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -440,10 +440,7 @@ static inline unsigned long get_vflags(struct kernel_vm86_regs *regs)
 
 static inline int is_revectored(int nr, struct revectored_struct *bitmap)
 {
-	__asm__ __volatile__("btl %2,%1\n\tsbbl %0,%0"
-		:"=r" (nr)
-		:"m" (*bitmap), "r" (nr));
-	return nr;
+	return test_bit(nr, bitmap->__map);
 }
 
 #define val_byte(val, n) (((__u8 *)&val)[n])

[tip:x86/asm] x86, asm: use bool for bitops and other assembly outputs

[tip-bot for H. Peter Anvin]

Commit-ID:  117780eef7740729e803bdcc0d5f2f48137ea8e3
Gitweb:     http://git.kernel.org/tip/117780eef7740729e803bdcc0d5f2f48137ea8e3
Author:     H. Peter Anvin <hpa@zytor.com>
AuthorDate: Wed, 8 Jun 2016 12:38:38 -0700
Committer:  H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Wed, 8 Jun 2016 12:41:20 -0700

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             |  8 +++++---
 arch/x86/boot/boot.h               |  8 ++++----
 arch/x86/boot/string.c             |  2 +-
 arch/x86/include/asm/apm.h         |  6 +++---
 arch/x86/include/asm/archrandom.h  | 16 ++++++++--------
 arch/x86/include/asm/atomic.h      |  8 ++++----
 arch/x86/include/asm/atomic64_64.h | 10 +++++-----
 arch/x86/include/asm/bitops.h      | 28 ++++++++++++++--------------
 arch/x86/include/asm/local.h       |  8 ++++----
 arch/x86/include/asm/percpu.h      |  8 ++++----
 arch/x86/include/asm/rmwcc.h       |  4 ++--
 arch/x86/include/asm/rwsem.h       | 17 +++++++++--------
 include/linux/random.h             | 12 ++++++------
 13 files changed, 69 insertions(+), 66 deletions(-)

diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h
index 878e4b9..0d41d68 100644
--- a/arch/x86/boot/bitops.h
+++ b/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));
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 9011a88..2edb2d5 100644
--- a/arch/x86/boot/boot.h
+++ b/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;
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 318b846..cc3bd58 100644
--- a/arch/x86/boot/string.c
+++ b/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;
diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h
index 20370c6..93eebc63 100644
--- a/arch/x86/include/asm/apm.h
+++ b/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
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index 69f1366..ab6f599 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/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;
 }
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 3e86742..17d8812 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/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");
 }
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 0373510..4f881d7 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/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);
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index b2b797d..8cbb7f4 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/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)			\
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 4ad6560..0cdc65b 100644
--- a/arch/x86/include/asm/local.h
+++ b/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");
 }
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 65039e9..184d7f3 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/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"
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 8f7866a..a15b73d 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/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)				\
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index 453744c..c508770 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/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;
diff --git a/include/linux/random.h b/include/linux/random.h
index e47e533..3d6e981 100644
--- a/include/linux/random.h
+++ b/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;
 }

[tip:x86/asm] x86, asm: change the GEN_*_RMWcc() macros to not quote the condition

[tip-bot for H. Peter Anvin]

Commit-ID:  18fe58229d80c7f4f138a07e84ba608e1ebd232b
Gitweb:     http://git.kernel.org/tip/18fe58229d80c7f4f138a07e84ba608e1ebd232b
Author:     H. Peter Anvin <hpa@zytor.com>
AuthorDate: Wed, 8 Jun 2016 12:38:39 -0700
Committer:  H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Wed, 8 Jun 2016 12:41:20 -0700

x86, asm: change the GEN_*_RMWcc() macros to not quote the condition

Change the lexical defintion of the GEN_*_RMWcc() macros to not take
the condition code as a quoted string.  This will help support
changing them to use the new __GCC_ASM_FLAG_OUTPUTS__ feature in a
subsequent patch.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1465414726-197858-4-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/include/asm/atomic.h      | 8 ++++----
 arch/x86/include/asm/atomic64_64.h | 8 ++++----
 arch/x86/include/asm/bitops.h      | 6 +++---
 arch/x86/include/asm/local.h       | 8 ++++----
 arch/x86/include/asm/preempt.h     | 2 +-
 arch/x86/include/asm/rmwcc.h       | 4 ++--
 6 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 17d8812..7322c15 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -77,7 +77,7 @@ static __always_inline void atomic_sub(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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
 }
 
 /**
@@ -114,7 +114,7 @@ static __always_inline void atomic_dec(atomic_t *v)
  */
 static __always_inline bool atomic_dec_and_test(atomic_t *v)
 {
-	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
 }
 
 /**
@@ -127,7 +127,7 @@ static __always_inline bool atomic_dec_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");
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
 }
 
 /**
@@ -141,7 +141,7 @@ static __always_inline bool atomic_inc_and_test(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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
 }
 
 /**
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 4f881d7..57bf925 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -72,7 +72,7 @@ static inline void atomic64_sub(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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
 }
 
 /**
@@ -111,7 +111,7 @@ static __always_inline void atomic64_dec(atomic64_t *v)
  */
 static inline bool atomic64_dec_and_test(atomic64_t *v)
 {
-	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e");
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
 }
 
 /**
@@ -124,7 +124,7 @@ static inline bool atomic64_dec_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");
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
 }
 
 /**
@@ -138,7 +138,7 @@ static inline bool atomic64_inc_and_test(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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
 }
 
 /**
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 8cbb7f4..ed8f485 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -203,7 +203,7 @@ static __always_inline void change_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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", c);
 }
 
 /**
@@ -249,7 +249,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
  */
 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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", c);
 }
 
 /**
@@ -302,7 +302,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
  */
 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");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", c);
 }
 
 static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 0cdc65b..7511978 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -52,7 +52,7 @@ static inline void local_sub(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");
+	GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, "er", i, "%0", e);
 }
 
 /**
@@ -65,7 +65,7 @@ static inline bool local_sub_and_test(long i, local_t *l)
  */
 static inline bool local_dec_and_test(local_t *l)
 {
-	GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e");
+	GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", e);
 }
 
 /**
@@ -78,7 +78,7 @@ static inline bool local_dec_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");
+	GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", e);
 }
 
 /**
@@ -92,7 +92,7 @@ static inline bool local_inc_and_test(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");
+	GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, "er", i, "%0", s);
 }
 
 /**
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index d397deb..17f2186 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -81,7 +81,7 @@ static __always_inline void __preempt_count_sub(int val)
  */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
+	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e);
 }
 
 /*
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index a15b73d..e3264c4 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -5,7 +5,7 @@
 
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
-	asm_volatile_goto (fullop "; j" cc " %l[cc_label]"		\
+	asm_volatile_goto (fullop "; j" #cc " %l[cc_label]"		\
 			: : "m" (var), ## __VA_ARGS__ 			\
 			: "memory" : cc_label);				\
 	return 0;							\
@@ -24,7 +24,7 @@ cc_label:								\
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
 	bool c;								\
-	asm volatile (fullop "; set" cc " %1"				\
+	asm volatile (fullop "; set" #cc " %1"				\
 			: "+m" (var), "=qm" (c)				\
 			: __VA_ARGS__ : "memory");			\
 	return c;							\

[tip:x86/asm] x86, asm: define CC_SET() and CC_OUT() macros

[tip-bot for H. Peter Anvin]

Commit-ID:  ff3554b409b82d349f71e9d7082648b7b0a1a5bb
Gitweb:     http://git.kernel.org/tip/ff3554b409b82d349f71e9d7082648b7b0a1a5bb
Author:     H. Peter Anvin <hpa@zytor.com>
AuthorDate: Wed, 8 Jun 2016 12:38:40 -0700
Committer:  H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Wed, 8 Jun 2016 12:41:20 -0700

x86, asm: define CC_SET() and CC_OUT() macros

The CC_SET() and CC_OUT() macros can be used together to take
advantage of the new __GCC_ASM_FLAG_OUTPUTS__ feature in gcc 6+ while
remaining backwards compatible.  CC_SET() generates a SET instruction
on older compilers; CC_OUT() makes sure the output is received in the
correct variable.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1465414726-197858-5-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/include/asm/asm.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index f5063b6..7acb51c 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -42,6 +42,18 @@
 #define _ASM_SI		__ASM_REG(si)
 #define _ASM_DI		__ASM_REG(di)
 
+/*
+ * Macros to generate condition code outputs from inline assembly,
+ * The output operand must be type "bool".
+ */
+#ifdef __GCC_ASM_FLAG_OUTPUTS__
+# define CC_SET(c) "\n\t/* output condition code " #c "*/\n"
+# define CC_OUT(c) "=@cc" #c
+#else
+# define CC_SET(c) "\n\tset" #c " %[_cc_" #c "]\n"
+# define CC_OUT(c) [_cc_ ## c] "=qm"
+#endif
+
 /* Exception table entry */
 #ifdef __ASSEMBLY__
 # define _ASM_EXTABLE_HANDLE(from, to, handler)			\

[tip:x86/asm] x86, asm: change GEN_*_RMWcc() to use CC_SET()/CC_OUT()

[tip-bot for H. Peter Anvin]

Commit-ID:  ba741e356c49bfce0adcfa851080666870867f6b
Gitweb:     http://git.kernel.org/tip/ba741e356c49bfce0adcfa851080666870867f6b
Author:     H. Peter Anvin <hpa@zytor.com>
AuthorDate: Wed, 8 Jun 2016 12:38:41 -0700
Committer:  H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Wed, 8 Jun 2016 12:41:20 -0700

x86, asm: change GEN_*_RMWcc() to use CC_SET()/CC_OUT()

Change the GEN_*_RMWcc() macros to use the CC_SET()/CC_OUT() macros
defined in <asm/asm.h>, and disable the use of asm goto if
__GCC_ASM_FLAG_OUTPUTS__ is enabled.  This allows gcc to receive the
flags output directly in gcc 6+.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1465414726-197858-6-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/include/asm/rmwcc.h | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index e3264c4..661dd30 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -1,7 +1,9 @@
 #ifndef _ASM_X86_RMWcc
 #define _ASM_X86_RMWcc
 
-#ifdef CC_HAVE_ASM_GOTO
+#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO)
+
+/* Use asm goto */
 
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
@@ -19,13 +21,15 @@ cc_label:								\
 #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
 	__GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val))
 
-#else /* !CC_HAVE_ASM_GOTO */
+#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
+
+/* Use flags output or a set instruction */
 
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
 	bool c;								\
-	asm volatile (fullop "; set" #cc " %1"				\
-			: "+m" (var), "=qm" (c)				\
+	asm volatile (fullop ";" CC_SET(cc)				\
+			: "+m" (var), CC_OUT(cc) (c)			\
 			: __VA_ARGS__ : "memory");			\
 	return c;							\
 } while (0)
@@ -36,6 +40,6 @@ do {									\
 #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
 	__GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val))
 
-#endif /* CC_HAVE_ASM_GOTO */
+#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
 
 #endif /* _ASM_X86_RMWcc */

[tip:x86/asm] x86, asm: Use CC_SET()/CC_OUT() in <asm/bitops.h>

[tip-bot for H. Peter Anvin]

Commit-ID:  86b61240d4c233b440cd29daf0baa440daf4a148
Gitweb:     http://git.kernel.org/tip/86b61240d4c233b440cd29daf0baa440daf4a148
Author:     H. Peter Anvin <hpa@zytor.com>
AuthorDate: Wed, 8 Jun 2016 12:38:42 -0700
Committer:  H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Wed, 8 Jun 2016 12:41:20 -0700

x86, asm: Use CC_SET()/CC_OUT() in <asm/bitops.h>

Remove open-coded uses of set instructions to use CC_SET()/CC_OUT() in
<asm/bitops.h>.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1465414726-197858-7-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/include/asm/bitops.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index ed8f485..68557f52 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -233,8 +233,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
 	bool oldbit;
 
 	asm("bts %2,%1\n\t"
-	    "setc %0"
-	    : "=qm" (oldbit), ADDR
+	    CC_SET(c)
+	    : CC_OUT(c) (oldbit), ADDR
 	    : "Ir" (nr));
 	return oldbit;
 }
@@ -273,8 +273,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long
 	bool oldbit;
 
 	asm volatile("btr %2,%1\n\t"
-		     "setc %0"
-		     : "=qm" (oldbit), ADDR
+		     CC_SET(c)
+		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr));
 	return oldbit;
 }
@@ -285,8 +285,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
 	bool oldbit;
 
 	asm volatile("btc %2,%1\n\t"
-		     "setc %0"
-		     : "=qm" (oldbit), ADDR
+		     CC_SET(c)
+		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr) : "memory");
 
 	return oldbit;
@@ -316,8 +316,8 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
 	bool oldbit;
 
 	asm volatile("bt %2,%1\n\t"
-		     "setc %0"
-		     : "=qm" (oldbit)
+		     CC_SET(c)
+		     : CC_OUT(c) (oldbit)
 		     : "m" (*(unsigned long *)addr), "Ir" (nr));
 
 	return oldbit;

[tip:x86/asm] x86, asm: Use CC_SET()/CC_OUT() in <asm/percpu.h>

[tip-bot for H. Peter Anvin]

Commit-ID:  64be6d36f5674f3424d1901772f76e21874f4954
Gitweb:     http://git.kernel.org/tip/64be6d36f5674f3424d1901772f76e21874f4954
Author:     H. Peter Anvin <hpa@zytor.com>
AuthorDate: Wed, 8 Jun 2016 12:38:43 -0700
Committer:  H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Wed, 8 Jun 2016 12:41:20 -0700

x86, asm: Use CC_SET()/CC_OUT() in <asm/percpu.h>

Remove open-coded uses of set instructions to use CC_SET()/CC_OUT() in
<asm/percpu.h>.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1465414726-197858-8-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/include/asm/percpu.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 184d7f3..e02e3f8 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -511,8 +511,9 @@ do {									\
 #define x86_test_and_clear_bit_percpu(bit, var)				\
 ({									\
 	bool old__;							\
-	asm volatile("btr %2,"__percpu_arg(1)"\n\tsetc %0"		\
-		     : "=qm" (old__), "+m" (var)			\
+	asm volatile("btr %2,"__percpu_arg(1)"\n\t"			\
+		     CC_SET(c)						\
+		     : CC_OUT(c) (old__), "+m" (var)			\
 		     : "dIr" (bit));					\
 	old__;								\
 })
@@ -535,8 +536,8 @@ static inline bool x86_this_cpu_variable_test_bit(int nr,
 	bool oldbit;
 
 	asm volatile("bt "__percpu_arg(2)",%1\n\t"
-			"setc %0"
-			: "=qm" (oldbit)
+			CC_SET(c)
+			: CC_OUT(c) (oldbit)
 			: "m" (*(unsigned long *)addr), "Ir" (nr));
 
 	return oldbit;

[tip:x86/asm] x86, asm: Use CC_SET()/CC_OUT() in <asm/rwsem.h>

[tip-bot for H. Peter Anvin]

Commit-ID:  35ccfb7114e2f0f454f264c049b03c31f4c6bbc0
Gitweb:     http://git.kernel.org/tip/35ccfb7114e2f0f454f264c049b03c31f4c6bbc0
Author:     H. Peter Anvin <hpa@zytor.com>
AuthorDate: Wed, 8 Jun 2016 12:38:44 -0700
Committer:  H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Wed, 8 Jun 2016 12:41:20 -0700

x86, asm: Use CC_SET()/CC_OUT() in <asm/rwsem.h>

Remove open-coded uses of set instructions to use CC_SET()/CC_OUT() in
<asm/rwsem.h>.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1465414726-197858-9-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/include/asm/rwsem.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index c508770..1e8be26 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -149,10 +149,10 @@ static inline bool __down_write_trylock(struct rw_semaphore *sem)
 		     LOCK_PREFIX "  cmpxchg  %2,%0\n\t"
 		     "  jnz	     1b\n\t"
 		     "2:\n\t"
-		     "  sete         %3\n\t"
+		     CC_SET(e)
 		     "# ending __down_write_trylock\n\t"
 		     : "+m" (sem->count), "=&a" (tmp0), "=&r" (tmp1),
-		       "=qm" (result)
+		       CC_OUT(e) (result)
 		     : "er" (RWSEM_ACTIVE_WRITE_BIAS)
 		     : "memory", "cc");
 	return result;

[tip:x86/asm] x86, asm, boot: Use CC_SET()/CC_OUT() in arch/x86/boot/boot.h

[tip-bot for H. Peter Anvin]

Commit-ID:  66928b4eb92dfb6d87c204238057b9278b36452b
Gitweb:     http://git.kernel.org/tip/66928b4eb92dfb6d87c204238057b9278b36452b
Author:     H. Peter Anvin <hpa@linux.intel.com>
AuthorDate: Wed, 8 Jun 2016 12:38:45 -0700
Committer:  H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Wed, 8 Jun 2016 12:41:20 -0700

x86, asm, boot: Use CC_SET()/CC_OUT() in arch/x86/boot/boot.h

Remove open-coded uses of set instructions to use CC_SET()/CC_OUT() in
arch/x86/boot/boot.h.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/1465414726-197858-10-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/boot.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 2edb2d5..7c1495f 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -24,6 +24,7 @@
 #include <linux/types.h>
 #include <linux/edd.h>
 #include <asm/setup.h>
+#include <asm/asm.h>
 #include "bitops.h"
 #include "ctype.h"
 #include "cpuflags.h"
@@ -179,15 +180,15 @@ static inline void wrgs32(u32 v, addr_t addr)
 static inline bool memcmp_fs(const void *s1, addr_t s2, size_t len)
 {
 	bool diff;
-	asm volatile("fs; repe; cmpsb; setnz %0"
-		     : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	asm volatile("fs; repe; cmpsb" CC_SET(nz)
+		     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 static inline bool memcmp_gs(const void *s1, addr_t s2, size_t len)
 {
 	bool diff;
-	asm volatile("gs; repe; cmpsb; setnz %0"
-		     : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	asm volatile("gs; repe; cmpsb" CC_SET(nz)
+		     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 

[tip:x86/asm] x86, asm: Use CC_SET()/CC_OUT() and static_cpu_has() in archrandom.h

[tip-bot for H. Peter Anvin]

Commit-ID:  3b290398638ee4e57f1fb2e35c02005cba9a737f
Gitweb:     http://git.kernel.org/tip/3b290398638ee4e57f1fb2e35c02005cba9a737f
Author:     H. Peter Anvin <hpa@linux.intel.com>
AuthorDate: Wed, 8 Jun 2016 12:38:46 -0700
Committer:  H. Peter Anvin <hpa@linux.intel.com>
CommitDate: Wed, 8 Jun 2016 12:41:20 -0700

x86, asm: Use CC_SET()/CC_OUT() and static_cpu_has() in archrandom.h

Use CC_SET()/CC_OUT() and static_cpu_has().  This produces code good
enough to eliminate ad hoc use of alternatives in <asm/archrandom.h>,
greatly simplifying the code.

While we are at it, make x86_init_rdrand() compile out completely if
we don't need it.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/1465414726-197858-11-git-send-email-hpa@linux.intel.com

v2: fix a conflict between <linux/random.h> and <asm/archrandom.h>
    discovered by Ingo Molnar.  There are a few places in x86-specific
    code where we need all of <arch/archrandom.h> even when
    CONFIG_ARCH_RANDOM is disabled, so <linux/random.h> does not
    suffice.
---
 arch/x86/include/asm/archrandom.h | 128 ++++++++++++++++++--------------------
 arch/x86/kernel/cpu/rdrand.c      |   4 +-
 2 files changed, 62 insertions(+), 70 deletions(-)

diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index ab6f599..5b0579a 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -25,8 +25,6 @@
 
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
-#include <asm/alternative.h>
-#include <asm/nops.h>
 
 #define RDRAND_RETRY_LOOPS	10
 
@@ -40,97 +38,91 @@
 # define RDSEED_LONG	RDSEED_INT
 #endif
 
-#ifdef CONFIG_ARCH_RANDOM
+/* Unconditional execution of RDRAND and RDSEED */
 
-/* Instead of arch_get_random_long() when alternatives haven't run. */
 static inline bool rdrand_long(unsigned long *v)
 {
-	int ok;
-	asm volatile("1: " RDRAND_LONG "\n\t"
-		     "jc 2f\n\t"
-		     "decl %0\n\t"
-		     "jnz 1b\n\t"
-		     "2:"
-		     : "=r" (ok), "=a" (*v)
-		     : "0" (RDRAND_RETRY_LOOPS));
-	return !!ok;
+	bool ok;
+	unsigned int retry = RDRAND_RETRY_LOOPS;
+	do {
+		asm volatile(RDRAND_LONG "\n\t"
+			     CC_SET(c)
+			     : CC_OUT(c) (ok), "=a" (*v));
+		if (ok)
+			return true;
+	} while (--retry);
+	return false;
+}
+
+static inline bool rdrand_int(unsigned int *v)
+{
+	bool ok;
+	unsigned int retry = RDRAND_RETRY_LOOPS;
+	do {
+		asm volatile(RDRAND_INT "\n\t"
+			     CC_SET(c)
+			     : CC_OUT(c) (ok), "=a" (*v));
+		if (ok)
+			return true;
+	} while (--retry);
+	return false;
 }
 
-/* A single attempt at RDSEED */
 static inline bool rdseed_long(unsigned long *v)
 {
 	bool ok;
 	asm volatile(RDSEED_LONG "\n\t"
-		     "setc %0"
-		     : "=qm" (ok), "=a" (*v));
+		     CC_SET(c)
+		     : CC_OUT(c) (ok), "=a" (*v));
 	return ok;
 }
 
-#define GET_RANDOM(name, type, rdrand, nop)			\
-static inline bool name(type *v)				\
-{								\
-	int ok;							\
-	alternative_io("movl $0, %0\n\t"			\
-		       nop,					\
-		       "\n1: " rdrand "\n\t"			\
-		       "jc 2f\n\t"				\
-		       "decl %0\n\t"                            \
-		       "jnz 1b\n\t"                             \
-		       "2:",                                    \
-		       X86_FEATURE_RDRAND,                      \
-		       ASM_OUTPUT2("=r" (ok), "=a" (*v)),       \
-		       "0" (RDRAND_RETRY_LOOPS));		\
-	return !!ok;						\
-}
-
-#define GET_SEED(name, type, rdseed, nop)			\
-static inline bool name(type *v)				\
-{								\
-	bool ok;						\
-	alternative_io("movb $0, %0\n\t"			\
-		       nop,					\
-		       rdseed "\n\t"				\
-		       "setc %0",				\
-		       X86_FEATURE_RDSEED,                      \
-		       ASM_OUTPUT2("=q" (ok), "=a" (*v)));	\
-	return ok;						\
+static inline bool rdseed_int(unsigned int *v)
+{
+	bool ok;
+	asm volatile(RDSEED_INT "\n\t"
+		     CC_SET(c)
+		     : CC_OUT(c) (ok), "=a" (*v));
+	return ok;
 }
 
-#ifdef CONFIG_X86_64
-
-GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP5);
-GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP4);
-
-GET_SEED(arch_get_random_seed_long, unsigned long, RDSEED_LONG, ASM_NOP5);
-GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
-
-#else
-
-GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP3);
-GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP3);
-
-GET_SEED(arch_get_random_seed_long, unsigned long, RDSEED_LONG, ASM_NOP4);
-GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
-
-#endif /* CONFIG_X86_64 */
-
+/* Conditional execution based on CPU type */
 #define arch_has_random()	static_cpu_has(X86_FEATURE_RDRAND)
 #define arch_has_random_seed()	static_cpu_has(X86_FEATURE_RDSEED)
 
-#else
+/*
+ * These are the generic interfaces; they must not be declared if the
+ * stubs in <linux/random.h> are to be invoked,
+ * i.e. CONFIG_ARCH_RANDOM is not defined.
+ */
+#ifdef CONFIG_ARCH_RANDOM
 
-static inline bool rdrand_long(unsigned long *v)
+static inline bool arch_get_random_long(unsigned long *v)
 {
-	return 0;
+	return arch_has_random() ? rdrand_long(v) : false;
 }
 
-static inline bool rdseed_long(unsigned long *v)
+static inline bool arch_get_random_int(unsigned int *v)
 {
-	return 0;
+	return arch_has_random() ? rdrand_int(v) : false;
 }
 
-#endif  /* CONFIG_ARCH_RANDOM */
+static inline bool arch_get_random_seed_long(unsigned long *v)
+{
+	return arch_has_random_seed() ? rdseed_long(v) : false;
+}
+
+static inline bool arch_get_random_seed_int(unsigned int *v)
+{
+	return arch_has_random_seed() ? rdseed_int(v) : false;
+}
 
 extern void x86_init_rdrand(struct cpuinfo_x86 *c);
 
+#else  /* !CONFIG_ARCH_RANDOM */
+
+static inline void x86_init_rdrand(struct cpuinfo_x86 *c) { }
+
+#endif  /* !CONFIG_ARCH_RANDOM */
+
 #endif /* ASM_X86_ARCHRANDOM_H */
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index f6f50c4..cfa97ff 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -39,9 +39,9 @@ __setup("nordrand", x86_rdrand_setup);
  */
 #define SANITY_CHECK_LOOPS 8
 
+#ifdef CONFIG_ARCH_RANDOM
 void x86_init_rdrand(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_ARCH_RANDOM
 	unsigned long tmp;
 	int i;
 
@@ -55,5 +55,5 @@ void x86_init_rdrand(struct cpuinfo_x86 *c)
 			return;
 		}
 	}
-#endif
 }
+#endif

Re: [PATCH v2 00/10] x86: use gcc 6+ asm flag output feature

[H. Peter Anvin]

On June 8, 2016 12:38:36 PM PDT, "H. Peter Anvin" <hpa@linux.intel.com> wrote:
>From: "H. Peter Anvin" <hpa@zytor.com>
>
>gcc 6+ has the ability to let flags (actually, conditions, which are
>specific combinations of flags) to be used directly as asm() outputs.
>The syntax for that is "=@cc<cc>" where <cc> is the same set of
>letters that would be used in a j<cc> or set<cc> instruction
>(e.g. "=@ccz" to test the ZF flag.)
>
>This patchset by itself reduces the size of the x86-64 kernel by
>0.12%, from a baseline of 4.7-rc2 built with gcc 6.1 (first line is
>with the patchset, the second one is without):
>
>     text       data       bss        dec       hex filename
>
>68245656   41004339  20533248  129783243   7bc55cb
>o.i386-allconfig/vmlinux
>68355716   41008499  20533248  129897463   7be13f7
>o.i386-allconfig/vmlinux
>
>127384005  129742359  38150144  295276508  11998fdc
>o.x86_64-allconfig/vmlinux
>127538765  129742295  38150144  295431204  119bec24
>o.x86_64-allconfig/vmlinux
>
>v2: fix a conflict between <linux/random.h> and <asm/archrandom.h>
>    discovered by Ingo Molnar.  There are a few places in x86-specific
>    code where we need all of <arch/archrandom.h> even when
>    xCONFIG_ARCH_RANDOM is disabled, so <linux/random.h> does not
>    suffice.  Only the <asm/archrandom.h> patch has been changed;
>    since it is a little bit different from the others I have moved it
>    to the end.

I should probably clarify one thing: the output type *must* be bool for the flags output.  Fortunately, not only does it also work for the older compilers, but it sometimes allows GCC to generate better code, which is why I have made the change unconditionally.
-- 
Sent from my Android device with K-9 Mail. Please excuse brevity and formatting.

Re: [PATCH v2 10/10] x86, asm: Use CC_SET()/CC_OUT() and static_cpu_has() in archrandom.h

[Borislav Petkov]

On Wed, Jun 08, 2016 at 12:38:46PM -0700, H. Peter Anvin wrote:
> Use CC_SET()/CC_OUT() and static_cpu_has().  This produces code good
> enough to eliminate ad hoc use of alternatives in <asm/archrandom.h>,
> greatly simplifying the code.
> 
> While we are at it, make x86_init_rdrand() compile out completely if
> we don't need it.
> 
> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
> 
> v2: fix a conflict between <linux/random.h> and <asm/archrandom.h>
>     discovered by Ingo Molnar.  There are a few places in x86-specific
>     code where we need all of <arch/archrandom.h> even when
>     CONFIG_ARCH_RANDOM is disabled, so <linux/random.h> does not
>     suffice.
> ---
>  arch/x86/include/asm/archrandom.h | 128 ++++++++++++++++++--------------------
>  arch/x86/kernel/cpu/rdrand.c      |   4 +-
>  2 files changed, 62 insertions(+), 70 deletions(-)

Reviewed-by: Borislav Petkov <bp@suse.de>

-- 
Regards/Gruss,
    Boris.

ECO tip #101: Trim your mails when you reply.