All of lore.kernel.org
 help / color / mirror / Atom feed
From: Stafford Horne <shorne@gmail.com>
To: LKML <linux-kernel@vger.kernel.org>
Cc: Openrisc <openrisc@lists.librecores.org>,
	Stafford Horne <shorne@gmail.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Jonas Bonn <jonas@southpole.se>,
	Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Subject: [PATCH v3 02/13] openrisc: add 1 and 2 byte cmpxchg support
Date: Sun, 22 Oct 2017 12:15:49 +0900	[thread overview]
Message-ID: <20171022031600.29612-3-shorne@gmail.com> (raw)
In-Reply-To: <20171022031600.29612-1-shorne@gmail.com>

OpenRISC only supports hardware instructions that perform 4 byte atomic
operations.  For enabling qrwlocks for upcoming SMP support 1 and 2 byte
implementations are needed.  To do this we leverage the 4 byte atomic
operations and shift/mask the 1 and 2 byte areas as needed.

This heavily borrows ideas and routines from sh and mips, which do
something similar.

Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Stafford Horne <shorne@gmail.com>
---
 arch/openrisc/include/asm/cmpxchg.h | 147 ++++++++++++++++++++++++++++--------
 1 file changed, 115 insertions(+), 32 deletions(-)

diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h
index f0a5d8b844d6..d29f7db53906 100644
--- a/arch/openrisc/include/asm/cmpxchg.h
+++ b/arch/openrisc/include/asm/cmpxchg.h
@@ -1,32 +1,29 @@
 /*
+ * 1,2 and 4 byte cmpxchg and xchg implementations for OpenRISC.
+ *
  * Copyright (C) 2014 Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
+ * Copyright (C) 2017 Stafford Horne <shorne@gmail.com>
  *
  * This file is licensed under the terms of the GNU General Public License
  * version 2.  This program is licensed "as is" without any warranty of any
  * kind, whether express or implied.
+ *
+ * Note:
+ * The portable implementations of 1 and 2 byte xchg and cmpxchg using a 4
+ * byte cmpxchg is sourced heavily from the sh and mips implementations.
  */
 
 #ifndef __ASM_OPENRISC_CMPXCHG_H
 #define __ASM_OPENRISC_CMPXCHG_H
 
 #include  <linux/types.h>
-
-/*
- * This function doesn't exist, so you'll get a linker error
- * if something tries to do an invalid cmpxchg().
- */
-extern void __cmpxchg_called_with_bad_pointer(void);
+#include  <linux/bitops.h>
 
 #define __HAVE_ARCH_CMPXCHG 1
 
-static inline unsigned long
-__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
+static inline unsigned long cmpxchg_u32(volatile void *ptr,
+		unsigned long old, unsigned long new)
 {
-	if (size != 4) {
-		__cmpxchg_called_with_bad_pointer();
-		return old;
-	}
-
 	__asm__ __volatile__(
 		"1:	l.lwa %0, 0(%1)		\n"
 		"	l.sfeq %0, %2		\n"
@@ -43,6 +40,97 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
 	return old;
 }
 
+static inline unsigned long xchg_u32(volatile void *ptr,
+		unsigned long val)
+{
+	__asm__ __volatile__(
+		"1:	l.lwa %0, 0(%1)		\n"
+		"	l.swa 0(%1), %2		\n"
+		"	l.bnf 1b		\n"
+		"	 l.nop			\n"
+		: "=&r"(val)
+		: "r"(ptr), "r"(val)
+		: "cc", "memory");
+
+	return val;
+}
+
+static inline u32 cmpxchg_small(volatile void *ptr, u32 old, u32 new,
+				int size)
+{
+	int off = (unsigned long)ptr % sizeof(u32);
+	volatile u32 *p = ptr - off;
+#ifdef __BIG_ENDIAN
+	int bitoff = (sizeof(u32) - size - off) * BITS_PER_BYTE;
+#else
+	int bitoff = off * BITS_PER_BYTE;
+#endif
+	u32 bitmask = ((0x1 << size * BITS_PER_BYTE) - 1) << bitoff;
+	u32 load32, old32, new32;
+	u32 ret;
+
+	load32 = READ_ONCE(*p);
+
+	while (true) {
+		ret = (load32 & bitmask) >> bitoff;
+		if (old != ret)
+			return ret;
+
+		old32 = (load32 & ~bitmask) | (old << bitoff);
+		new32 = (load32 & ~bitmask) | (new << bitoff);
+
+		/* Do 32 bit cmpxchg */
+		load32 = cmpxchg_u32(p, old32, new32);
+		if (load32 == old32)
+			return old;
+	}
+}
+
+/* xchg */
+
+static inline u32 xchg_small(volatile void *ptr, u32 x, int size)
+{
+	int off = (unsigned long)ptr % sizeof(u32);
+	volatile u32 *p = ptr - off;
+#ifdef __BIG_ENDIAN
+	int bitoff = (sizeof(u32) - size - off) * BITS_PER_BYTE;
+#else
+	int bitoff = off * BITS_PER_BYTE;
+#endif
+	u32 bitmask = ((0x1 << size * BITS_PER_BYTE) - 1) << bitoff;
+	u32 oldv, newv;
+	u32 ret;
+
+	do {
+		oldv = READ_ONCE(*p);
+		ret = (oldv & bitmask) >> bitoff;
+		newv = (oldv & ~bitmask) | (x << bitoff);
+	} while (cmpxchg_u32(p, oldv, newv) != oldv);
+
+	return ret;
+}
+
+/*
+ * This function doesn't exist, so you'll get a linker error
+ * if something tries to do an invalid cmpxchg().
+ */
+extern unsigned long __cmpxchg_called_with_bad_pointer(void)
+	__compiletime_error("Bad argument size for cmpxchg");
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+		unsigned long new, int size)
+{
+	switch (size) {
+	case 1:
+	case 2:
+		return cmpxchg_small(ptr, old, new, size);
+	case 4:
+		return cmpxchg_u32(ptr, old, new);
+	default:
+		return __cmpxchg_called_with_bad_pointer();
+	}
+}
+
 #define cmpxchg(ptr, o, n)						\
 	({								\
 		(__typeof__(*(ptr))) __cmpxchg((ptr),			\
@@ -55,32 +143,27 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
  * This function doesn't exist, so you'll get a linker error if
  * something tries to do an invalidly-sized xchg().
  */
-extern void __xchg_called_with_bad_pointer(void);
+extern unsigned long __xchg_called_with_bad_pointer(void)
+	__compiletime_error("Bad argument size for xchg");
 
-static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
-				   int size)
+static inline unsigned long __xchg(volatile void *ptr, unsigned long with,
+		int size)
 {
-	if (size != 4) {
-		__xchg_called_with_bad_pointer();
-		return val;
+	switch (size) {
+	case 1:
+	case 2:
+		return xchg_small(ptr, with, size);
+	case 4:
+		return xchg_u32(ptr, with);
+	default:
+		return __xchg_called_with_bad_pointer();
 	}
-
-	__asm__ __volatile__(
-		"1:	l.lwa %0, 0(%1)		\n"
-		"	l.swa 0(%1), %2		\n"
-		"	l.bnf 1b		\n"
-		"	 l.nop			\n"
-		: "=&r"(val)
-		: "r"(ptr), "r"(val)
-		: "cc", "memory");
-
-	return val;
 }
 
 #define xchg(ptr, with) 						\
 	({								\
-		(__typeof__(*(ptr))) __xchg((unsigned long)(with),	\
-					    (ptr),			\
+		(__typeof__(*(ptr))) __xchg((ptr),			\
+					    (unsigned long)(with),	\
 					    sizeof(*(ptr)));		\
 	})
 
-- 
2.13.6

WARNING: multiple messages have this Message-ID (diff)
From: Stafford Horne <shorne@gmail.com>
To: openrisc@lists.librecores.org
Subject: [OpenRISC] [PATCH v3 02/13] openrisc: add 1 and 2 byte cmpxchg support
Date: Sun, 22 Oct 2017 12:15:49 +0900	[thread overview]
Message-ID: <20171022031600.29612-3-shorne@gmail.com> (raw)
In-Reply-To: <20171022031600.29612-1-shorne@gmail.com>

OpenRISC only supports hardware instructions that perform 4 byte atomic
operations.  For enabling qrwlocks for upcoming SMP support 1 and 2 byte
implementations are needed.  To do this we leverage the 4 byte atomic
operations and shift/mask the 1 and 2 byte areas as needed.

This heavily borrows ideas and routines from sh and mips, which do
something similar.

Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Stafford Horne <shorne@gmail.com>
---
 arch/openrisc/include/asm/cmpxchg.h | 147 ++++++++++++++++++++++++++++--------
 1 file changed, 115 insertions(+), 32 deletions(-)

diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h
index f0a5d8b844d6..d29f7db53906 100644
--- a/arch/openrisc/include/asm/cmpxchg.h
+++ b/arch/openrisc/include/asm/cmpxchg.h
@@ -1,32 +1,29 @@
 /*
+ * 1,2 and 4 byte cmpxchg and xchg implementations for OpenRISC.
+ *
  * Copyright (C) 2014 Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
+ * Copyright (C) 2017 Stafford Horne <shorne@gmail.com>
  *
  * This file is licensed under the terms of the GNU General Public License
  * version 2.  This program is licensed "as is" without any warranty of any
  * kind, whether express or implied.
+ *
+ * Note:
+ * The portable implementations of 1 and 2 byte xchg and cmpxchg using a 4
+ * byte cmpxchg is sourced heavily from the sh and mips implementations.
  */
 
 #ifndef __ASM_OPENRISC_CMPXCHG_H
 #define __ASM_OPENRISC_CMPXCHG_H
 
 #include  <linux/types.h>
-
-/*
- * This function doesn't exist, so you'll get a linker error
- * if something tries to do an invalid cmpxchg().
- */
-extern void __cmpxchg_called_with_bad_pointer(void);
+#include  <linux/bitops.h>
 
 #define __HAVE_ARCH_CMPXCHG 1
 
-static inline unsigned long
-__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
+static inline unsigned long cmpxchg_u32(volatile void *ptr,
+		unsigned long old, unsigned long new)
 {
-	if (size != 4) {
-		__cmpxchg_called_with_bad_pointer();
-		return old;
-	}
-
 	__asm__ __volatile__(
 		"1:	l.lwa %0, 0(%1)		\n"
 		"	l.sfeq %0, %2		\n"
@@ -43,6 +40,97 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
 	return old;
 }
 
+static inline unsigned long xchg_u32(volatile void *ptr,
+		unsigned long val)
+{
+	__asm__ __volatile__(
+		"1:	l.lwa %0, 0(%1)		\n"
+		"	l.swa 0(%1), %2		\n"
+		"	l.bnf 1b		\n"
+		"	 l.nop			\n"
+		: "=&r"(val)
+		: "r"(ptr), "r"(val)
+		: "cc", "memory");
+
+	return val;
+}
+
+static inline u32 cmpxchg_small(volatile void *ptr, u32 old, u32 new,
+				int size)
+{
+	int off = (unsigned long)ptr % sizeof(u32);
+	volatile u32 *p = ptr - off;
+#ifdef __BIG_ENDIAN
+	int bitoff = (sizeof(u32) - size - off) * BITS_PER_BYTE;
+#else
+	int bitoff = off * BITS_PER_BYTE;
+#endif
+	u32 bitmask = ((0x1 << size * BITS_PER_BYTE) - 1) << bitoff;
+	u32 load32, old32, new32;
+	u32 ret;
+
+	load32 = READ_ONCE(*p);
+
+	while (true) {
+		ret = (load32 & bitmask) >> bitoff;
+		if (old != ret)
+			return ret;
+
+		old32 = (load32 & ~bitmask) | (old << bitoff);
+		new32 = (load32 & ~bitmask) | (new << bitoff);
+
+		/* Do 32 bit cmpxchg */
+		load32 = cmpxchg_u32(p, old32, new32);
+		if (load32 == old32)
+			return old;
+	}
+}
+
+/* xchg */
+
+static inline u32 xchg_small(volatile void *ptr, u32 x, int size)
+{
+	int off = (unsigned long)ptr % sizeof(u32);
+	volatile u32 *p = ptr - off;
+#ifdef __BIG_ENDIAN
+	int bitoff = (sizeof(u32) - size - off) * BITS_PER_BYTE;
+#else
+	int bitoff = off * BITS_PER_BYTE;
+#endif
+	u32 bitmask = ((0x1 << size * BITS_PER_BYTE) - 1) << bitoff;
+	u32 oldv, newv;
+	u32 ret;
+
+	do {
+		oldv = READ_ONCE(*p);
+		ret = (oldv & bitmask) >> bitoff;
+		newv = (oldv & ~bitmask) | (x << bitoff);
+	} while (cmpxchg_u32(p, oldv, newv) != oldv);
+
+	return ret;
+}
+
+/*
+ * This function doesn't exist, so you'll get a linker error
+ * if something tries to do an invalid cmpxchg().
+ */
+extern unsigned long __cmpxchg_called_with_bad_pointer(void)
+	__compiletime_error("Bad argument size for cmpxchg");
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+		unsigned long new, int size)
+{
+	switch (size) {
+	case 1:
+	case 2:
+		return cmpxchg_small(ptr, old, new, size);
+	case 4:
+		return cmpxchg_u32(ptr, old, new);
+	default:
+		return __cmpxchg_called_with_bad_pointer();
+	}
+}
+
 #define cmpxchg(ptr, o, n)						\
 	({								\
 		(__typeof__(*(ptr))) __cmpxchg((ptr),			\
@@ -55,32 +143,27 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
  * This function doesn't exist, so you'll get a linker error if
  * something tries to do an invalidly-sized xchg().
  */
-extern void __xchg_called_with_bad_pointer(void);
+extern unsigned long __xchg_called_with_bad_pointer(void)
+	__compiletime_error("Bad argument size for xchg");
 
-static inline unsigned long __xchg(unsigned long val, volatile void *ptr,
-				   int size)
+static inline unsigned long __xchg(volatile void *ptr, unsigned long with,
+		int size)
 {
-	if (size != 4) {
-		__xchg_called_with_bad_pointer();
-		return val;
+	switch (size) {
+	case 1:
+	case 2:
+		return xchg_small(ptr, with, size);
+	case 4:
+		return xchg_u32(ptr, with);
+	default:
+		return __xchg_called_with_bad_pointer();
 	}
-
-	__asm__ __volatile__(
-		"1:	l.lwa %0, 0(%1)		\n"
-		"	l.swa 0(%1), %2		\n"
-		"	l.bnf 1b		\n"
-		"	 l.nop			\n"
-		: "=&r"(val)
-		: "r"(ptr), "r"(val)
-		: "cc", "memory");
-
-	return val;
 }
 
 #define xchg(ptr, with) 						\
 	({								\
-		(__typeof__(*(ptr))) __xchg((unsigned long)(with),	\
-					    (ptr),			\
+		(__typeof__(*(ptr))) __xchg((ptr),			\
+					    (unsigned long)(with),	\
 					    sizeof(*(ptr)));		\
 	})
 
-- 
2.13.6


  parent reply	other threads:[~2017-10-22  3:16 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-10-22  3:15 [PATCH v3 00/13] OpenRISC SMP Support Stafford Horne
2017-10-22  3:15 ` [OpenRISC] " Stafford Horne
2017-10-22  3:15 ` [PATCH v3 01/13] openrisc: use shadow registers to save regs on exception Stafford Horne
2017-10-22  3:15   ` [OpenRISC] " Stafford Horne
2017-10-22  3:15 ` Stafford Horne [this message]
2017-10-22  3:15   ` [OpenRISC] [PATCH v3 02/13] openrisc: add 1 and 2 byte cmpxchg support Stafford Horne
2017-10-22  3:15 ` [PATCH v3 03/13] openrisc: use qspinlocks and qrwlocks Stafford Horne
2017-10-22  3:15   ` [OpenRISC] " Stafford Horne
2017-10-22  3:15 ` [PATCH v3 04/13] dt-bindings: add openrisc to vendor prefixes list Stafford Horne
2017-10-22  3:15   ` [OpenRISC] " Stafford Horne
2017-10-22  3:15 ` [PATCH v3 05/13] irqchip: add initial support for ompic Stafford Horne
2017-10-22  3:15   ` [OpenRISC] " Stafford Horne
2017-10-23  8:00   ` Marc Zyngier
2017-10-23  8:00     ` [OpenRISC] " Marc Zyngier
2017-10-23  8:00     ` Marc Zyngier
2017-10-23 12:57     ` Stafford Horne
2017-10-23 12:57       ` [OpenRISC] " Stafford Horne
2017-10-27  3:19   ` Rob Herring
2017-10-27  3:19     ` [OpenRISC] " Rob Herring
2017-10-27  3:19     ` Rob Herring
2017-10-22  3:15 ` [PATCH v3 06/13] openrisc: initial SMP support Stafford Horne
2017-10-22  3:15   ` [OpenRISC] " Stafford Horne
2017-10-22  3:15 ` [PATCH v3 07/13] openrisc: fix initial preempt state for secondary cpu tasks Stafford Horne
2017-10-22  3:15   ` [OpenRISC] " Stafford Horne
2017-10-22  3:15 ` [PATCH v3 08/13] openrisc: sleep instead of spin on secondary wait Stafford Horne
2017-10-22  3:15   ` [OpenRISC] " Stafford Horne
2017-10-22  3:15 ` [PATCH v3 09/13] openrisc: add cacheflush support to fix icache aliasing Stafford Horne
2017-10-22  3:15   ` [OpenRISC] " Stafford Horne
2017-10-22  3:15 ` [PATCH v3 10/13] openrisc: add simple_smp dts and defconfig for simulators Stafford Horne
2017-10-22  3:15   ` [OpenRISC] " Stafford Horne
2017-10-22  3:15 ` [PATCH v3 11/13] openrisc: support framepointers and STACKTRACE_SUPPORT Stafford Horne
2017-10-22  3:15   ` [OpenRISC] " Stafford Horne
2017-10-22  3:15 ` [PATCH v3 12/13] openrisc: enable LOCKDEP_SUPPORT and irqflags tracing Stafford Horne
2017-10-22  3:15   ` [OpenRISC] " Stafford Horne
2017-10-22  3:16 ` [PATCH v3 13/13] openrisc: add tick timer multi-core sync logic Stafford Horne
2017-10-22  3:16   ` [OpenRISC] " Stafford Horne

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=20171022031600.29612-3-shorne@gmail.com \
    --to=shorne@gmail.com \
    --cc=jonas@southpole.se \
    --cc=linux-kernel@vger.kernel.org \
    --cc=openrisc@lists.librecores.org \
    --cc=peterz@infradead.org \
    --cc=stefan.kristiansson@saunalahti.fi \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.