[patch V4 09/31] bitops: Add x86-specific parity functions

From: zengzhaoxiu@163.com
To: linux-kernel@vger.kernel.org, bp@suse.de,
	gnomes@lxorguk.ukuu.org.uk, andi@firstfloor.org,
	dvyukov@google.com
Cc: Zhaoxiu Zeng <zhaoxiu.zeng@gmail.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
	x86@kernel.org, Denys Vlasenko <dvlasenk@redhat.com>
Subject: [patch V4 09/31] bitops: Add x86-specific parity functions
Date: Wed, 11 May 2016 17:16:38 +0800	[thread overview]
Message-ID: <1462958205-24890-1-git-send-email-zengzhaoxiu@163.com> (raw)
In-Reply-To: <1462955158-28394-1-git-send-email-zengzhaoxiu@163.com>

From: Zhaoxiu Zeng <zhaoxiu.zeng@gmail.com>

Use alternatives, lifted from arch_hweight

Signed-off-by: Zhaoxiu Zeng <zhaoxiu.zeng@gmail.com>
---
 arch/x86/include/asm/arch_hweight.h |   5 ++
 arch/x86/include/asm/arch_parity.h  | 117 ++++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/bitops.h       |   4 +-
 3 files changed, 125 insertions(+), 1 deletion(-)
 create mode 100644 arch/x86/include/asm/arch_parity.h

diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index 02e799f..c79d50d 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -63,4 +63,9 @@ static __always_inline unsigned long __arch_hweight64(__u64 w)
 }
 #endif /* CONFIG_X86_32 */
 
+#undef POPCNT32
+#undef POPCNT64
+#undef REG_IN
+#undef REG_OUT
+
 #endif
diff --git a/arch/x86/include/asm/arch_parity.h b/arch/x86/include/asm/arch_parity.h
new file mode 100644
index 0000000..38fde0f
--- /dev/null
+++ b/arch/x86/include/asm/arch_parity.h
@@ -0,0 +1,117 @@
+#ifndef _ASM_X86_PARITY_H
+#define _ASM_X86_PARITY_H
+
+#include <asm/cpufeatures.h>
+
+/*
+ * the generic version use the Parity Flag directly
+ *
+ * Parity flag - Set if the least-significant byte of the
+ *               result contains an even number of 1 bits;
+ *               cleared otherwise.
+ */
+
+static inline unsigned int __arch_parity4(unsigned int w)
+{
+	unsigned int res = 0;
+
+	asm("test $0xf, %1; setpo %b0"
+		: "+q" (res)
+		: "r" (w)
+		: "cc");
+
+	return res;
+}
+
+static inline unsigned int __arch_parity8(unsigned int w)
+{
+	unsigned int res = 0;
+
+	asm("test %1, %1; setpo %b0"
+		: "+q" (res)
+		: "r" (w)
+		: "cc");
+
+	return res;
+}
+
+static inline unsigned int __arch_parity16(unsigned int w)
+{
+	unsigned int res = 0;
+
+	asm("xor %h1, %b1; setpo %b0"
+		: "+q" (res), "+q" (w)
+		: : "cc");
+
+	return res;
+}
+
+#ifdef CONFIG_64BIT
+/* popcnt %eax, %eax -- redundant REX prefix for alignment */
+#define POPCNT32 ".byte 0xf3,0x40,0x0f,0xb8,0xc0"
+/* popcnt %rax, %rax */
+#define POPCNT64 ".byte 0xf3,0x48,0x0f,0xb8,0xc0"
+#else
+/* popcnt %eax, %eax */
+#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc0"
+#endif
+
+static __always_inline unsigned int __arch_parity32(unsigned int w)
+{
+	unsigned int res;
+	unsigned int tmp;
+
+	asm(ALTERNATIVE(
+		"	mov	%%eax, %1	\n"
+		"	shr	$16, %%eax	\n"
+		"	xor	%1, %%eax	\n"
+		"	xor	%%ah, %%al	\n"
+		"	mov	$0, %%eax	\n"
+		"	setpo	%%al	\n",
+		POPCNT32 "			\n"
+		"	and	$1, %%eax	\n",
+		X86_FEATURE_POPCNT)
+		: "=a" (res), "=&r" (tmp)
+		: "a" (w)
+		: "cc");
+
+	return res;
+}
+
+#ifdef CONFIG_X86_32
+static inline unsigned int __arch_parity64(__u64 w)
+{
+	return __arch_parity32((unsigned int)(w >> 32) ^ (unsigned int)w);
+}
+#else
+static __always_inline unsigned int __arch_parity64(__u64 w)
+{
+	unsigned int res;
+	__u64 tmp;
+
+	asm(ALTERNATIVE(
+		"	mov	%%rax, %1	\n"
+		"	shr	$32, %%rax	\n"
+		"	xor	%k1, %%eax	\n"
+		"	mov	%%eax, %k1	\n"
+		"	shr	$16, %%eax	\n"
+		"	xor	%k1, %%eax 	\n"
+		"	xor	%%ah, %%al	\n"
+		"	mov	$0, %%eax	\n"
+		"	setpo	%%al	\n",
+		POPCNT64 "			\n"
+		"	and	$1, %%eax	\n",
+		X86_FEATURE_POPCNT)
+		: "=a" (res), "=&r" (tmp)
+		: "a" (w)
+		: "cc");
+
+	return res;
+}
+#endif /* CONFIG_X86_32 */
+
+#undef POPCNT32
+#undef POPCNT64
+
+#endif
+
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 7766d1c..f5b0122 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -498,9 +498,11 @@ static __always_inline int fls64(__u64 x)
 #include <asm-generic/bitops/sched.h>
 
 #include <asm/arch_hweight.h>
-
 #include <asm-generic/bitops/const_hweight.h>
 
+#include <asm/arch_parity.h>
+#include <asm-generic/bitops/const_parity.h>
+
 #include <asm-generic/bitops/le.h>
 
 #include <asm-generic/bitops/ext2-atomic-setbit.h>
-- 
2.7.4
