Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Alexander Shishkin <alexander.shishkin@linux.intel.com>
To:     linux-kernel@vger.kernel.org, x86@kernel.org,
        Andy Lutomirski <luto@kernel.org>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Ravi Shankar <ravi.v.shankar@intel.com>,
        Tony Luck <tony.luck@intel.com>,
        Sohil Mehta <sohil.mehta@intel.com>
Cc:     Peter Zijlstra <peterz@infradead.org>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>
Subject: [PATCH v3 02/12] x86/asm: Introduce inline memcpy and memset
Date:   Fri,  9 Jun 2023 21:36:22 +0300
Message-Id: <20230609183632.48706-3-alexander.shishkin@linux.intel.com>
In-Reply-To: <20230609183632.48706-1-alexander.shishkin@linux.intel.com>
References: <20230609183632.48706-1-alexander.shishkin@linux.intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Peter Zijlstra <peterz@infradead.org>

Provide inline memcpy and memset functions that can be used instead of
the GCC builtins whenever necessary.

Code posted by Peter Zijlstra <peterz@infradead.org>.
Link: https://lore.kernel.org/lkml/Y759AJ%2F0N9fqwDED@hirez.programming.kicks-ass.net/
[Missing Signed-off-by from PeterZ]
Signed-off-by: Sohil Mehta <sohil.mehta@intel.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
---
 arch/x86/include/asm/string_32.h | 21 +++++++++++++++++++++
 arch/x86/include/asm/string_64.h | 21 +++++++++++++++++++++
 2 files changed, 42 insertions(+)

diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index 32c0d981a82a..8896270e5eda 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -151,6 +151,16 @@ extern void *memcpy(void *, const void *, size_t);
 
 #endif /* !CONFIG_FORTIFY_SOURCE */
 
+static __always_inline void *__inline_memcpy(void *to, const void *from, size_t len)
+{
+	void *ret = to;
+
+	asm volatile("rep movsb"
+		     : "+D" (to), "+S" (from), "+c" (len)
+		     : : "memory");
+	return ret;
+}
+
 #define __HAVE_ARCH_MEMMOVE
 void *memmove(void *dest, const void *src, size_t n);
 
@@ -195,6 +205,17 @@ extern void *memset(void *, int, size_t);
 #define memset(s, c, count) __builtin_memset(s, c, count)
 #endif /* !CONFIG_FORTIFY_SOURCE */
 
+static __always_inline void *__inline_memset(void *s, int v, size_t n)
+{
+	void *ret = s;
+
+	asm volatile("rep stosb"
+		     : "+D" (s), "+c" (n)
+		     : "a" ((uint8_t)v)
+		     : "memory");
+	return ret;
+}
+
 #define __HAVE_ARCH_MEMSET16
 static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
 {
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 857d364b9888..ea51e2d73265 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -18,10 +18,31 @@
 extern void *memcpy(void *to, const void *from, size_t len);
 extern void *__memcpy(void *to, const void *from, size_t len);
 
+static __always_inline void *__inline_memcpy(void *to, const void *from, size_t len)
+{
+	void *ret = to;
+
+	asm volatile("rep movsb"
+		     : "+D" (to), "+S" (from), "+c" (len)
+		     : : "memory");
+	return ret;
+}
+
 #define __HAVE_ARCH_MEMSET
 void *memset(void *s, int c, size_t n);
 void *__memset(void *s, int c, size_t n);
 
+static __always_inline void *__inline_memset(void *s, int v, size_t n)
+{
+	void *ret = s;
+
+	asm volatile("rep stosb"
+		     : "+D" (s), "+c" (n)
+		     : "a" ((uint8_t)v)
+		     : "memory");
+	return ret;
+}
+
 /*
  * KMSAN needs to instrument as much code as possible. Use C versions of
  * memsetXX() from lib/string.c under KMSAN.
-- 
2.39.2