1. Patchew
  2. linux
  3. [PATCH RFC cmpxchg 0/8] Provide emulation for one- and two-byte cmpxchg()
  4. View patch

[PATCH RFC cmpxchg 1/8] lib: Add one-byte and two-byte cmpxchg() emulation functions

Paul E. McKenney posted 8 patches 1 year, 10 months ago
[PATCH RFC cmpxchg 1/8] lib: Add one-byte and two-byte cmpxchg() emulation functions
Posted by Paul E. McKenney 1 year, 10 months ago 
Architectures are required to provide four-byte cmpxchg() and 64-bit
architectures are additionally required to provide eight-byte cmpxchg().
However, there are cases where one-byte and two-byte cmpxchg()
would be extremely useful.  Therefore, provide cmpxchg_emu_u8() and
cmpxchg_emu_u16() that emulate one-byte and two-byte cmpxchg() in terms
of four-byte cmpxchg().

Note that these emulations are fully ordered, and can (for example)
cause one-byte cmpxchg_relaxed() to incur the overhead of full ordering.
If this causes problems for a given architecture, that architecture is
free to provide its own lighter-weight primitives.

[ paulmck: Apply Marco Elver feedback. ]
[ paulmck: Apply kernel test robot feedback. ]

Link: https://lore.kernel.org/all/0733eb10-5e7a-4450-9b8a-527b97c842ff@paulmck-laptop/

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Marco Elver <elver@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc: Douglas Anderson <dianders@chromium.org>
Cc: Petr Mladek <pmladek@suse.com>
Cc: <linux-arch@vger.kernel.org>
---
 arch/Kconfig                |  3 ++
 include/linux/cmpxchg-emu.h | 16 ++++++++
 lib/Makefile                |  1 +
 lib/cmpxchg-emu.c           | 74 +++++++++++++++++++++++++++++++++++++
 4 files changed, 94 insertions(+)
 create mode 100644 include/linux/cmpxchg-emu.h
 create mode 100644 lib/cmpxchg-emu.c

diff --git a/arch/Kconfig b/arch/Kconfig
index ae4a4f37bbf08..01093c60952a5 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1609,4 +1609,7 @@ config CC_HAS_SANE_FUNCTION_ALIGNMENT
 	# strict alignment always, even with -falign-functions.
 	def_bool CC_HAS_MIN_FUNCTION_ALIGNMENT || CC_IS_CLANG
 
+config ARCH_NEED_CMPXCHG_1_2_EMU
+	bool
+
 endmenu
diff --git a/include/linux/cmpxchg-emu.h b/include/linux/cmpxchg-emu.h
new file mode 100644
index 0000000000000..fee8171fa05eb
--- /dev/null
+++ b/include/linux/cmpxchg-emu.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Emulated 1-byte and 2-byte cmpxchg operations for architectures
+ * lacking direct support for these sizes.  These are implemented in terms
+ * of 4-byte cmpxchg operations.
+ *
+ * Copyright (C) 2024 Paul E. McKenney.
+ */
+
+#ifndef __LINUX_CMPXCHG_EMU_H
+#define __LINUX_CMPXCHG_EMU_H
+
+uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new);
+uintptr_t cmpxchg_emu_u16(volatile u16 *p, uintptr_t old, uintptr_t new);
+
+#endif /* __LINUX_CMPXCHG_EMU_H */
diff --git a/lib/Makefile b/lib/Makefile
index ffc6b2341b45a..1d93b61a7ecbe 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -236,6 +236,7 @@ obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
 lib-$(CONFIG_GENERIC_BUG) += bug.o
 
 obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
+obj-$(CONFIG_ARCH_NEED_CMPXCHG_1_2_EMU) += cmpxchg-emu.o
 
 obj-$(CONFIG_DYNAMIC_DEBUG_CORE) += dynamic_debug.o
 #ensure exported functions have prototypes
diff --git a/lib/cmpxchg-emu.c b/lib/cmpxchg-emu.c
new file mode 100644
index 0000000000000..a88c4f3c88430
--- /dev/null
+++ b/lib/cmpxchg-emu.c
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Emulated 1-byte and 2-byte cmpxchg operations for architectures
+ * lacking direct support for these sizes.  These are implemented in terms
+ * of 4-byte cmpxchg operations.
+ *
+ * Copyright (C) 2024 Paul E. McKenney.
+ */
+
+#include <linux/types.h>
+#include <linux/export.h>
+#include <linux/instrumented.h>
+#include <linux/atomic.h>
+#include <linux/panic.h>
+#include <linux/bug.h>
+#include <asm-generic/rwonce.h>
+#include <linux/cmpxchg-emu.h>
+
+union u8_32 {
+	u8 b[4];
+	u32 w;
+};
+
+/* Emulate one-byte cmpxchg() in terms of 4-byte cmpxchg. */
+uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new)
+{
+	u32 *p32 = (u32 *)(((uintptr_t)p) & ~0x3);
+	int i = ((uintptr_t)p) & 0x3;
+	union u8_32 old32;
+	union u8_32 new32;
+	u32 ret;
+
+	ret = READ_ONCE(*p32);
+	do {
+		old32.w = ret;
+		if (old32.b[i] != old)
+			return old32.b[i];
+		new32.w = old32.w;
+		new32.b[i] = new;
+		instrument_atomic_read_write(p, 1);
+		ret = data_race(cmpxchg(p32, old32.w, new32.w));
+	} while (ret != old32.w);
+	return old;
+}
+EXPORT_SYMBOL_GPL(cmpxchg_emu_u8);
+
+union u16_32 {
+	u16 h[2];
+	u32 w;
+};
+
+/* Emulate two-byte cmpxchg() in terms of 4-byte cmpxchg. */
+uintptr_t cmpxchg_emu_u16(volatile u16 *p, uintptr_t old, uintptr_t new)
+{
+	u32 *p32 = (u32 *)(((uintptr_t)p) & ~0x3);
+	int i = (((uintptr_t)p) & 0x2) / 2;
+	union u16_32 old32;
+	union u16_32 new32;
+	u32 ret;
+
+	WARN_ON_ONCE(((uintptr_t)p) & 0x1);
+	ret = READ_ONCE(*p32);
+	do {
+		old32.w = ret;
+		if (old32.h[i] != old)
+			return old32.h[i];
+		new32.w = old32.w;
+		new32.h[i] = new;
+		instrument_atomic_read_write(p, 2);
+		ret = data_race(cmpxchg(p32, old32.w, new32.w));
+	} while (ret != old32.w);
+	return old;
+}
+EXPORT_SYMBOL_GPL(cmpxchg_emu_u16);
-- 
2.40.1
Re: [PATCH RFC cmpxchg 1/8] lib: Add one-byte and two-byte cmpxchg() emulation functions
Posted by Marco Elver 1 year, 10 months ago 
On Mon, 1 Apr 2024 at 23:39, Paul E. McKenney <paulmck@kernel.org> wrote:
>
> Architectures are required to provide four-byte cmpxchg() and 64-bit
> architectures are additionally required to provide eight-byte cmpxchg().
> However, there are cases where one-byte and two-byte cmpxchg()
> would be extremely useful.  Therefore, provide cmpxchg_emu_u8() and
> cmpxchg_emu_u16() that emulate one-byte and two-byte cmpxchg() in terms
> of four-byte cmpxchg().
>
> Note that these emulations are fully ordered, and can (for example)
> cause one-byte cmpxchg_relaxed() to incur the overhead of full ordering.
> If this causes problems for a given architecture, that architecture is
> free to provide its own lighter-weight primitives.
>
> [ paulmck: Apply Marco Elver feedback. ]
> [ paulmck: Apply kernel test robot feedback. ]
>
> Link: https://lore.kernel.org/all/0733eb10-5e7a-4450-9b8a-527b97c842ff@paulmck-laptop/
>
> Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
> Cc: Marco Elver <elver@google.com>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
> Cc: Douglas Anderson <dianders@chromium.org>
> Cc: Petr Mladek <pmladek@suse.com>
> Cc: <linux-arch@vger.kernel.org>

Acked-by: Marco Elver <elver@google.com>

> ---
>  arch/Kconfig                |  3 ++
>  include/linux/cmpxchg-emu.h | 16 ++++++++
>  lib/Makefile                |  1 +
>  lib/cmpxchg-emu.c           | 74 +++++++++++++++++++++++++++++++++++++
>  4 files changed, 94 insertions(+)
>  create mode 100644 include/linux/cmpxchg-emu.h
>  create mode 100644 lib/cmpxchg-emu.c
>
> diff --git a/arch/Kconfig b/arch/Kconfig
> index ae4a4f37bbf08..01093c60952a5 100644
> --- a/arch/Kconfig
> +++ b/arch/Kconfig
> @@ -1609,4 +1609,7 @@ config CC_HAS_SANE_FUNCTION_ALIGNMENT
>         # strict alignment always, even with -falign-functions.
>         def_bool CC_HAS_MIN_FUNCTION_ALIGNMENT || CC_IS_CLANG
>
> +config ARCH_NEED_CMPXCHG_1_2_EMU
> +       bool
> +
>  endmenu
> diff --git a/include/linux/cmpxchg-emu.h b/include/linux/cmpxchg-emu.h
> new file mode 100644
> index 0000000000000..fee8171fa05eb
> --- /dev/null
> +++ b/include/linux/cmpxchg-emu.h
> @@ -0,0 +1,16 @@
> +/* SPDX-License-Identifier: GPL-2.0+ */
> +/*
> + * Emulated 1-byte and 2-byte cmpxchg operations for architectures
> + * lacking direct support for these sizes.  These are implemented in terms
> + * of 4-byte cmpxchg operations.
> + *
> + * Copyright (C) 2024 Paul E. McKenney.
> + */
> +
> +#ifndef __LINUX_CMPXCHG_EMU_H
> +#define __LINUX_CMPXCHG_EMU_H
> +
> +uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new);
> +uintptr_t cmpxchg_emu_u16(volatile u16 *p, uintptr_t old, uintptr_t new);
> +
> +#endif /* __LINUX_CMPXCHG_EMU_H */
> diff --git a/lib/Makefile b/lib/Makefile
> index ffc6b2341b45a..1d93b61a7ecbe 100644
> --- a/lib/Makefile
> +++ b/lib/Makefile
> @@ -236,6 +236,7 @@ obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
>  lib-$(CONFIG_GENERIC_BUG) += bug.o
>
>  obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
> +obj-$(CONFIG_ARCH_NEED_CMPXCHG_1_2_EMU) += cmpxchg-emu.o
>
>  obj-$(CONFIG_DYNAMIC_DEBUG_CORE) += dynamic_debug.o
>  #ensure exported functions have prototypes
> diff --git a/lib/cmpxchg-emu.c b/lib/cmpxchg-emu.c
> new file mode 100644
> index 0000000000000..a88c4f3c88430
> --- /dev/null
> +++ b/lib/cmpxchg-emu.c
> @@ -0,0 +1,74 @@
> +/* SPDX-License-Identifier: GPL-2.0+ */
> +/*
> + * Emulated 1-byte and 2-byte cmpxchg operations for architectures
> + * lacking direct support for these sizes.  These are implemented in terms
> + * of 4-byte cmpxchg operations.
> + *
> + * Copyright (C) 2024 Paul E. McKenney.
> + */
> +
> +#include <linux/types.h>
> +#include <linux/export.h>
> +#include <linux/instrumented.h>
> +#include <linux/atomic.h>
> +#include <linux/panic.h>
> +#include <linux/bug.h>
> +#include <asm-generic/rwonce.h>
> +#include <linux/cmpxchg-emu.h>
> +
> +union u8_32 {
> +       u8 b[4];
> +       u32 w;
> +};
> +
> +/* Emulate one-byte cmpxchg() in terms of 4-byte cmpxchg. */
> +uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new)
> +{
> +       u32 *p32 = (u32 *)(((uintptr_t)p) & ~0x3);
> +       int i = ((uintptr_t)p) & 0x3;
> +       union u8_32 old32;
> +       union u8_32 new32;
> +       u32 ret;
> +
> +       ret = READ_ONCE(*p32);
> +       do {
> +               old32.w = ret;
> +               if (old32.b[i] != old)
> +                       return old32.b[i];
> +               new32.w = old32.w;
> +               new32.b[i] = new;
> +               instrument_atomic_read_write(p, 1);
> +               ret = data_race(cmpxchg(p32, old32.w, new32.w));
> +       } while (ret != old32.w);
> +       return old;
> +}
> +EXPORT_SYMBOL_GPL(cmpxchg_emu_u8);
> +
> +union u16_32 {
> +       u16 h[2];
> +       u32 w;
> +};
> +
> +/* Emulate two-byte cmpxchg() in terms of 4-byte cmpxchg. */
> +uintptr_t cmpxchg_emu_u16(volatile u16 *p, uintptr_t old, uintptr_t new)
> +{
> +       u32 *p32 = (u32 *)(((uintptr_t)p) & ~0x3);
> +       int i = (((uintptr_t)p) & 0x2) / 2;
> +       union u16_32 old32;
> +       union u16_32 new32;
> +       u32 ret;
> +
> +       WARN_ON_ONCE(((uintptr_t)p) & 0x1);
> +       ret = READ_ONCE(*p32);
> +       do {
> +               old32.w = ret;
> +               if (old32.h[i] != old)
> +                       return old32.h[i];
> +               new32.w = old32.w;
> +               new32.h[i] = new;
> +               instrument_atomic_read_write(p, 2);
> +               ret = data_race(cmpxchg(p32, old32.w, new32.w));
> +       } while (ret != old32.w);
> +       return old;
> +}
> +EXPORT_SYMBOL_GPL(cmpxchg_emu_u16);
> --
> 2.40.1
>
Re: [PATCH RFC cmpxchg 1/8] lib: Add one-byte and two-byte cmpxchg() emulation functions
Posted by Paul E. McKenney 1 year, 10 months ago 
On Tue, Apr 02, 2024 at 03:07:22PM +0200, Marco Elver wrote:
> On Mon, 1 Apr 2024 at 23:39, Paul E. McKenney <paulmck@kernel.org> wrote:
> >
> > Architectures are required to provide four-byte cmpxchg() and 64-bit
> > architectures are additionally required to provide eight-byte cmpxchg().
> > However, there are cases where one-byte and two-byte cmpxchg()
> > would be extremely useful.  Therefore, provide cmpxchg_emu_u8() and
> > cmpxchg_emu_u16() that emulate one-byte and two-byte cmpxchg() in terms
> > of four-byte cmpxchg().
> >
> > Note that these emulations are fully ordered, and can (for example)
> > cause one-byte cmpxchg_relaxed() to incur the overhead of full ordering.
> > If this causes problems for a given architecture, that architecture is
> > free to provide its own lighter-weight primitives.
> >
> > [ paulmck: Apply Marco Elver feedback. ]
> > [ paulmck: Apply kernel test robot feedback. ]
> >
> > Link: https://lore.kernel.org/all/0733eb10-5e7a-4450-9b8a-527b97c842ff@paulmck-laptop/
> >
> > Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
> > Cc: Marco Elver <elver@google.com>
> > Cc: Andrew Morton <akpm@linux-foundation.org>
> > Cc: Thomas Gleixner <tglx@linutronix.de>
> > Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
> > Cc: Douglas Anderson <dianders@chromium.org>
> > Cc: Petr Mladek <pmladek@suse.com>
> > Cc: <linux-arch@vger.kernel.org>
> 
> Acked-by: Marco Elver <elver@google.com>

Thank you!  I will apply on my next rebase.

							Thanx, Paul

> > ---
> >  arch/Kconfig                |  3 ++
> >  include/linux/cmpxchg-emu.h | 16 ++++++++
> >  lib/Makefile                |  1 +
> >  lib/cmpxchg-emu.c           | 74 +++++++++++++++++++++++++++++++++++++
> >  4 files changed, 94 insertions(+)
> >  create mode 100644 include/linux/cmpxchg-emu.h
> >  create mode 100644 lib/cmpxchg-emu.c
> >
> > diff --git a/arch/Kconfig b/arch/Kconfig
> > index ae4a4f37bbf08..01093c60952a5 100644
> > --- a/arch/Kconfig
> > +++ b/arch/Kconfig
> > @@ -1609,4 +1609,7 @@ config CC_HAS_SANE_FUNCTION_ALIGNMENT
> >         # strict alignment always, even with -falign-functions.
> >         def_bool CC_HAS_MIN_FUNCTION_ALIGNMENT || CC_IS_CLANG
> >
> > +config ARCH_NEED_CMPXCHG_1_2_EMU
> > +       bool
> > +
> >  endmenu
> > diff --git a/include/linux/cmpxchg-emu.h b/include/linux/cmpxchg-emu.h
> > new file mode 100644
> > index 0000000000000..fee8171fa05eb
> > --- /dev/null
> > +++ b/include/linux/cmpxchg-emu.h
> > @@ -0,0 +1,16 @@
> > +/* SPDX-License-Identifier: GPL-2.0+ */
> > +/*
> > + * Emulated 1-byte and 2-byte cmpxchg operations for architectures
> > + * lacking direct support for these sizes.  These are implemented in terms
> > + * of 4-byte cmpxchg operations.
> > + *
> > + * Copyright (C) 2024 Paul E. McKenney.
> > + */
> > +
> > +#ifndef __LINUX_CMPXCHG_EMU_H
> > +#define __LINUX_CMPXCHG_EMU_H
> > +
> > +uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new);
> > +uintptr_t cmpxchg_emu_u16(volatile u16 *p, uintptr_t old, uintptr_t new);
> > +
> > +#endif /* __LINUX_CMPXCHG_EMU_H */
> > diff --git a/lib/Makefile b/lib/Makefile
> > index ffc6b2341b45a..1d93b61a7ecbe 100644
> > --- a/lib/Makefile
> > +++ b/lib/Makefile
> > @@ -236,6 +236,7 @@ obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
> >  lib-$(CONFIG_GENERIC_BUG) += bug.o
> >
> >  obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
> > +obj-$(CONFIG_ARCH_NEED_CMPXCHG_1_2_EMU) += cmpxchg-emu.o
> >
> >  obj-$(CONFIG_DYNAMIC_DEBUG_CORE) += dynamic_debug.o
> >  #ensure exported functions have prototypes
> > diff --git a/lib/cmpxchg-emu.c b/lib/cmpxchg-emu.c
> > new file mode 100644
> > index 0000000000000..a88c4f3c88430
> > --- /dev/null
> > +++ b/lib/cmpxchg-emu.c
> > @@ -0,0 +1,74 @@
> > +/* SPDX-License-Identifier: GPL-2.0+ */
> > +/*
> > + * Emulated 1-byte and 2-byte cmpxchg operations for architectures
> > + * lacking direct support for these sizes.  These are implemented in terms
> > + * of 4-byte cmpxchg operations.
> > + *
> > + * Copyright (C) 2024 Paul E. McKenney.
> > + */
> > +
> > +#include <linux/types.h>
> > +#include <linux/export.h>
> > +#include <linux/instrumented.h>
> > +#include <linux/atomic.h>
> > +#include <linux/panic.h>
> > +#include <linux/bug.h>
> > +#include <asm-generic/rwonce.h>
> > +#include <linux/cmpxchg-emu.h>
> > +
> > +union u8_32 {
> > +       u8 b[4];
> > +       u32 w;
> > +};
> > +
> > +/* Emulate one-byte cmpxchg() in terms of 4-byte cmpxchg. */
> > +uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new)
> > +{
> > +       u32 *p32 = (u32 *)(((uintptr_t)p) & ~0x3);
> > +       int i = ((uintptr_t)p) & 0x3;
> > +       union u8_32 old32;
> > +       union u8_32 new32;
> > +       u32 ret;
> > +
> > +       ret = READ_ONCE(*p32);
> > +       do {
> > +               old32.w = ret;
> > +               if (old32.b[i] != old)
> > +                       return old32.b[i];
> > +               new32.w = old32.w;
> > +               new32.b[i] = new;
> > +               instrument_atomic_read_write(p, 1);
> > +               ret = data_race(cmpxchg(p32, old32.w, new32.w));
> > +       } while (ret != old32.w);
> > +       return old;
> > +}
> > +EXPORT_SYMBOL_GPL(cmpxchg_emu_u8);
> > +
> > +union u16_32 {
> > +       u16 h[2];
> > +       u32 w;
> > +};
> > +
> > +/* Emulate two-byte cmpxchg() in terms of 4-byte cmpxchg. */
> > +uintptr_t cmpxchg_emu_u16(volatile u16 *p, uintptr_t old, uintptr_t new)
> > +{
> > +       u32 *p32 = (u32 *)(((uintptr_t)p) & ~0x3);
> > +       int i = (((uintptr_t)p) & 0x2) / 2;
> > +       union u16_32 old32;
> > +       union u16_32 new32;
> > +       u32 ret;
> > +
> > +       WARN_ON_ONCE(((uintptr_t)p) & 0x1);
> > +       ret = READ_ONCE(*p32);
> > +       do {
> > +               old32.w = ret;
> > +               if (old32.h[i] != old)
> > +                       return old32.h[i];
> > +               new32.w = old32.w;
> > +               new32.h[i] = new;
> > +               instrument_atomic_read_write(p, 2);
> > +               ret = data_race(cmpxchg(p32, old32.w, new32.w));
> > +       } while (ret != old32.w);
> > +       return old;
> > +}
> > +EXPORT_SYMBOL_GPL(cmpxchg_emu_u16);
> > --
> > 2.40.1
> >

Patchew 2.1-devel-b67e4c2

© 2016 - 2026 Red Hat, Inc.