From: "Bryan O'Sullivan" <bos@pathscale.com>
To: linux-kernel@vger.kernel.org, openib-general@openib.org
Subject: [PATCH 2 of 20] memcpy32 for x86_64
Date: Wed, 28 Dec 2005 16:31:21 -0800 [thread overview]
Message-ID: <801287704e408ed65660.1135816281@eng-12.pathscale.com> (raw)
In-Reply-To: <patchbomb.1135816279@eng-12.pathscale.com>
Introduce an x86_64-specific memcpy32 routine. The routine is similar
to memcpy, but is guaranteed to work in units of 32 bits at a time.
Signed-off-by: Bryan O'Sullivan <bos@pathscale.com>
diff -r ef833f6712e7 -r 801287704e40 arch/x86_64/kernel/x8664_ksyms.c
--- a/arch/x86_64/kernel/x8664_ksyms.c Wed Dec 28 14:19:42 2005 -0800
+++ b/arch/x86_64/kernel/x8664_ksyms.c Wed Dec 28 14:19:42 2005 -0800
@@ -164,6 +164,8 @@
EXPORT_SYMBOL(memcpy);
EXPORT_SYMBOL(__memcpy);
+EXPORT_SYMBOL_GPL(memcpy32);
+
#ifdef CONFIG_RWSEM_XCHGADD_ALGORITHM
/* prototypes are wrong, these are assembly with custom calling functions */
extern void rwsem_down_read_failed_thunk(void);
diff -r ef833f6712e7 -r 801287704e40 arch/x86_64/lib/Makefile
--- a/arch/x86_64/lib/Makefile Wed Dec 28 14:19:42 2005 -0800
+++ b/arch/x86_64/lib/Makefile Wed Dec 28 14:19:42 2005 -0800
@@ -9,4 +9,4 @@
lib-y := csum-partial.o csum-copy.o csum-wrappers.o delay.o \
usercopy.o getuser.o putuser.o \
thunk.o clear_page.o copy_page.o bitstr.o bitops.o
-lib-y += memcpy.o memmove.o memset.o copy_user.o
+lib-y += memcpy.o memcpy32.o memmove.o memset.o copy_user.o
diff -r ef833f6712e7 -r 801287704e40 include/asm-x86_64/string.h
--- a/include/asm-x86_64/string.h Wed Dec 28 14:19:42 2005 -0800
+++ b/include/asm-x86_64/string.h Wed Dec 28 14:19:42 2005 -0800
@@ -45,6 +45,15 @@
#define __HAVE_ARCH_MEMMOVE
void * memmove(void * dest,const void *src,size_t count);
+/*
+ * memcpy32 - copy data, 32 bits at a time
+ *
+ * @dst: destination (must be 32-bit aligned)
+ * @src: source (must be 32-bit aligned)
+ * @count: number of 32-bit quantities to copy
+ */
+void memcpy32(void *dst, const void *src, size_t count);
+
/* Use C out of line version for memcmp */
#define memcmp __builtin_memcmp
int memcmp(const void * cs,const void * ct,size_t count);
diff -r ef833f6712e7 -r 801287704e40 arch/x86_64/lib/memcpy32.S
--- /dev/null Thu Jan 1 00:00:00 1970 +0000
+++ b/arch/x86_64/lib/memcpy32.S Wed Dec 28 14:19:42 2005 -0800
@@ -0,0 +1,23 @@
+/*
+ * Copyright (c) 2003, 2004, 2005 PathScale, Inc.
+ */
+
+/*
+ * memcpy32 - Copy a memory block, 32 bits at a time.
+ *
+ * Count is number of dwords; it need not be a qword multiple.
+ * Input:
+ * rdi destination
+ * rsi source
+ * rdx count
+ */
+
+ .globl memcpy32
+memcpy32:
+ movl %edx,%ecx
+ shrl $1,%ecx
+ andl $1,%edx
+ rep movsq
+ movl %edx,%ecx
+ rep movsd
+ ret
next prev parent reply other threads:[~2005-12-29 0:44 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-12-29 0:31 [PATCH 0 of 20] [RFC] ipath - PathScale InfiniPath driver Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 1 of 20] Introduce __memcpy_toio32 Bryan O'Sullivan
2005-12-29 0:31 ` Bryan O'Sullivan [this message]
2005-12-29 0:31 ` [PATCH 3 of 20] Add memcpy_toio32 to each arch Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 4 of 20] Define BITS_PER_BYTE Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 5 of 20] ipath - driver core header files Bryan O'Sullivan
2005-12-29 8:18 ` Pekka Enberg
2005-12-29 14:15 ` Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 6 of 20] ipath - driver debugging headers Bryan O'Sullivan
2005-12-29 8:22 ` Pekka Enberg
2005-12-29 0:31 ` [PATCH 7 of 20] ipath - MMIO copy routines Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 8 of 20] ipath - core driver, part 1 of 4 Bryan O'Sullivan
2005-12-30 8:39 ` Greg KH
2005-12-30 23:47 ` Bryan O'Sullivan
2005-12-31 0:12 ` Greg KH
2005-12-29 0:31 ` [PATCH 9 of 20] ipath - core driver, part 2 " Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 10 of 20] ipath - core driver, part 3 " Bryan O'Sullivan
2005-12-30 18:46 ` Linus Torvalds
2005-12-30 23:50 ` Bryan O'Sullivan
2005-12-31 8:36 ` Arjan van de Ven
2005-12-29 0:31 ` [PATCH 11 of 20] ipath - core driver, part 4 " Bryan O'Sullivan
2005-12-29 2:19 ` [openib-general] " Roland Dreier
2005-12-29 14:21 ` Bryan O'Sullivan
2005-12-30 8:12 ` Greg KH
2005-12-30 23:17 ` Bryan O'Sullivan
2005-12-31 0:08 ` Greg KH
2005-12-29 0:31 ` [PATCH 12 of 20] ipath - misc driver support code Bryan O'Sullivan
2005-12-30 8:25 ` Greg KH
2005-12-30 23:10 ` Bryan O'Sullivan
2005-12-31 0:13 ` Greg KH
2005-12-30 18:15 ` Arjan van de Ven
2005-12-29 0:31 ` [PATCH 13 of 20] ipath - routines used by upper layer driver code Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 14 of 20] ipath - infiniband verbs header Bryan O'Sullivan
2005-12-29 8:21 ` Pekka Enberg
2005-12-29 14:22 ` Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 15 of 20] ipath - infiniband verbs support, part 1 of 3 Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 16 of 20] path - infiniband verbs support, part 2 " Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 17 of 20] ipath - infiniband verbs support, part 3 " Bryan O'Sullivan
2005-12-29 19:24 ` Pekka Enberg
2005-12-30 3:19 ` Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 18 of 20] ipath - infiniband management datagram support Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 19 of 20] ipath - kbuild infrastructure Bryan O'Sullivan
2005-12-29 0:31 ` [PATCH 20 of 20] ipath - integrate driver into infiniband " Bryan O'Sullivan
2005-12-29 19:01 ` [PATCH 0 of 20] [RFC] ipath - PathScale InfiniPath driver Horst von Brand
2005-12-29 19:26 ` Lee Revell
2005-12-31 5:36 ` Jan Engelhardt
2006-01-02 16:05 ` Horst von Brand
2006-01-02 16:22 ` Christoph Hellwig
2005-12-30 3:17 ` Bryan O'Sullivan
2005-12-30 8:00 ` Greg KH
2005-12-30 23:11 ` Bryan O'Sullivan
2005-12-31 0:10 ` Greg KH
2005-12-31 1:40 ` Bryan O'Sullivan
2006-01-02 20:35 ` Eric W. Biederman
2006-01-02 22:22 ` Bryan O'Sullivan
2006-01-04 21:26 ` Roland Dreier
2006-01-05 15:28 ` Bryan O'Sullivan
2006-01-03 17:27 ` Greg KH
2006-01-03 20:54 ` Bryan O'Sullivan
2006-01-03 20:57 ` Arjan van de Ven
2006-01-03 21:24 ` Bryan O'Sullivan
2006-01-03 21:26 ` Arjan van de Ven
2006-01-04 3:33 ` Bryan O'Sullivan
2006-01-04 21:28 ` [openib-general] " Roland Dreier
2006-01-05 15:31 ` Bryan O'Sullivan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=801287704e408ed65660.1135816281@eng-12.pathscale.com \
--to=bos@pathscale.com \
--cc=linux-kernel@vger.kernel.org \
--cc=openib-general@openib.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Powered by JetHome