[v9,3/3] eal/stack: enable lock-free stack for aarch64
Checks
Commit Message
Enable both c11 atomic and non c11 atomic lock-free stack for aarch64.
Introduced a new header to reduce the ifdef clutter across generic and c11
files. The rte_stack_lf_stubs.h contains stub implementations of
__rte_stack_lf_count, __rte_stack_lf_push_elems and
__rte_stack_lf_pop_elems.
Suggested-by: Gage Eads <gage.eads@intel.com>
Suggested-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: Phil Yang <phil.yang@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Tested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
---
doc/guides/prog_guide/env_abstraction_layer.rst | 4 +--
doc/guides/rel_notes/release_19_11.rst | 3 ++
lib/librte_stack/Makefile | 3 +-
lib/librte_stack/rte_stack_lf.h | 4 +++
lib/librte_stack/rte_stack_lf_c11.h | 16 ---------
lib/librte_stack/rte_stack_lf_generic.h | 16 ---------
lib/librte_stack/rte_stack_lf_stubs.h | 44 +++++++++++++++++++++++++
7 files changed, 55 insertions(+), 35 deletions(-)
create mode 100644 lib/librte_stack/rte_stack_lf_stubs.h
Comments
On Wed, Aug 14, 2019 at 10:30 AM Phil Yang <phil.yang@arm.com> wrote:
>
> Enable both c11 atomic and non c11 atomic lock-free stack for aarch64.
>
> Introduced a new header to reduce the ifdef clutter across generic and c11
> files. The rte_stack_lf_stubs.h contains stub implementations of
> __rte_stack_lf_count, __rte_stack_lf_push_elems and
> __rte_stack_lf_pop_elems.
>
> Suggested-by: Gage Eads <gage.eads@intel.com>
> Suggested-by: Jerin Jacob <jerinj@marvell.com>
> Signed-off-by: Phil Yang <phil.yang@arm.com>
> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
> Tested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
> Acked-by: Jerin Jacob <jerinj@marvell.com>
> ---
> doc/guides/prog_guide/env_abstraction_layer.rst | 4 +--
> doc/guides/rel_notes/release_19_11.rst | 3 ++
> lib/librte_stack/Makefile | 3 +-
> lib/librte_stack/rte_stack_lf.h | 4 +++
> lib/librte_stack/rte_stack_lf_c11.h | 16 ---------
> lib/librte_stack/rte_stack_lf_generic.h | 16 ---------
> lib/librte_stack/rte_stack_lf_stubs.h | 44 +++++++++++++++++++++++++
> 7 files changed, 55 insertions(+), 35 deletions(-)
> create mode 100644 lib/librte_stack/rte_stack_lf_stubs.h
>
> diff --git a/doc/guides/prog_guide/env_abstraction_layer.rst b/doc/guides/prog_guide/env_abstraction_layer.rst
> index 94f30fd..6e59fae 100644
> --- a/doc/guides/prog_guide/env_abstraction_layer.rst
> +++ b/doc/guides/prog_guide/env_abstraction_layer.rst
> @@ -648,8 +648,8 @@ Known Issues
> Alternatively, applications can use the lock-free stack mempool handler. When
> considering this handler, note that:
>
> - - It is currently limited to the x86_64 platform, because it uses an
> - instruction (16-byte compare-and-swap) that is not yet available on other
> + - It is currently limited to the aarch64 and x86_64 platforms, because it uses
> + an instruction (16-byte compare-and-swap) that is not yet available on other
> platforms.
> - It has worse average-case performance than the non-preemptive rte_ring, but
> software caching (e.g. the mempool cache) can mitigate this by reducing the
> diff --git a/doc/guides/rel_notes/release_19_11.rst b/doc/guides/rel_notes/release_19_11.rst
> index 8490d89..60ffd70 100644
> --- a/doc/guides/rel_notes/release_19_11.rst
> +++ b/doc/guides/rel_notes/release_19_11.rst
> @@ -56,6 +56,9 @@ New Features
> Also, make sure to start the actual text at the margin.
> =========================================================
>
> +* **Added Lock-free Stack for aarch64.**
> +
> + The lock-free stack implementation is enabled for aarch64 platforms.
>
> Removed Items
> -------------
> diff --git a/lib/librte_stack/Makefile b/lib/librte_stack/Makefile
> index 8d18ce5..c337ab7 100644
> --- a/lib/librte_stack/Makefile
> +++ b/lib/librte_stack/Makefile
> @@ -24,6 +24,7 @@ SYMLINK-$(CONFIG_RTE_LIBRTE_STACK)-include := rte_stack.h \
> rte_stack_std.h \
> rte_stack_lf.h \
> rte_stack_lf_generic.h \
> - rte_stack_lf_c11.h
> + rte_stack_lf_c11.h \
> + rte_stack_lf_stubs.h
Please, use the same indentation type than the other lines.
>
> include $(RTE_SDK)/mk/rte.lib.mk
> diff --git a/lib/librte_stack/rte_stack_lf.h b/lib/librte_stack/rte_stack_lf.h
> index f5581f0..e67630c 100644
> --- a/lib/librte_stack/rte_stack_lf.h
> +++ b/lib/librte_stack/rte_stack_lf.h
> @@ -5,11 +5,15 @@
> #ifndef _RTE_STACK_LF_H_
> #define _RTE_STACK_LF_H_
>
> +#if !(defined(RTE_ARCH_X86_64) || defined(RTE_ARCH_ARM64))
> +#include "rte_stack_lf_stubs.h"
> +#else
> #ifdef RTE_USE_C11_MEM_MODEL
> #include "rte_stack_lf_c11.h"
> #else
> #include "rte_stack_lf_generic.h"
> #endif
> +#endif
>
> /**
> * @internal Push several objects on the lock-free stack (MT-safe).
> diff --git a/lib/librte_stack/rte_stack_lf_c11.h b/lib/librte_stack/rte_stack_lf_c11.h
> index 3d677ae..999359f 100644
> --- a/lib/librte_stack/rte_stack_lf_c11.h
> +++ b/lib/librte_stack/rte_stack_lf_c11.h
> @@ -36,12 +36,6 @@ __rte_stack_lf_push_elems(struct rte_stack_lf_list *list,
> struct rte_stack_lf_elem *last,
> unsigned int num)
> {
> -#ifndef RTE_ARCH_X86_64
> - RTE_SET_USED(first);
> - RTE_SET_USED(last);
> - RTE_SET_USED(list);
> - RTE_SET_USED(num);
> -#else
> struct rte_stack_lf_head old_head;
> int success;
>
> @@ -79,7 +73,6 @@ __rte_stack_lf_push_elems(struct rte_stack_lf_list *list,
> * to the LIFO len update.
> */
> __atomic_add_fetch(&list->len, num, __ATOMIC_RELEASE);
> -#endif
> }
>
> static __rte_always_inline struct rte_stack_lf_elem *
> @@ -88,14 +81,6 @@ __rte_stack_lf_pop_elems(struct rte_stack_lf_list *list,
> void **obj_table,
> struct rte_stack_lf_elem **last)
> {
> -#ifndef RTE_ARCH_X86_64
> - RTE_SET_USED(obj_table);
> - RTE_SET_USED(last);
> - RTE_SET_USED(list);
> - RTE_SET_USED(num);
> -
> - return NULL;
> -#else
> struct rte_stack_lf_head old_head;
> uint64_t len;
> int success;
> @@ -169,7 +154,6 @@ __rte_stack_lf_pop_elems(struct rte_stack_lf_list *list,
> } while (success == 0);
>
> return old_head.top;
> -#endif
> }
>
> #endif /* _RTE_STACK_LF_C11_H_ */
> diff --git a/lib/librte_stack/rte_stack_lf_generic.h b/lib/librte_stack/rte_stack_lf_generic.h
> index 3182151..3abbb53 100644
> --- a/lib/librte_stack/rte_stack_lf_generic.h
> +++ b/lib/librte_stack/rte_stack_lf_generic.h
> @@ -36,12 +36,6 @@ __rte_stack_lf_push_elems(struct rte_stack_lf_list *list,
> struct rte_stack_lf_elem *last,
> unsigned int num)
> {
> -#ifndef RTE_ARCH_X86_64
> - RTE_SET_USED(first);
> - RTE_SET_USED(last);
> - RTE_SET_USED(list);
> - RTE_SET_USED(num);
> -#else
> struct rte_stack_lf_head old_head;
> int success;
>
> @@ -75,7 +69,6 @@ __rte_stack_lf_push_elems(struct rte_stack_lf_list *list,
> } while (success == 0);
>
> rte_atomic64_add((rte_atomic64_t *)&list->len, num);
> -#endif
> }
>
> static __rte_always_inline struct rte_stack_lf_elem *
> @@ -84,14 +77,6 @@ __rte_stack_lf_pop_elems(struct rte_stack_lf_list *list,
> void **obj_table,
> struct rte_stack_lf_elem **last)
> {
> -#ifndef RTE_ARCH_X86_64
> - RTE_SET_USED(obj_table);
> - RTE_SET_USED(last);
> - RTE_SET_USED(list);
> - RTE_SET_USED(num);
> -
> - return NULL;
> -#else
> struct rte_stack_lf_head old_head;
> int success;
>
> @@ -159,7 +144,6 @@ __rte_stack_lf_pop_elems(struct rte_stack_lf_list *list,
> } while (success == 0);
>
> return old_head.top;
> -#endif
> }
>
> #endif /* _RTE_STACK_LF_GENERIC_H_ */
> diff --git a/lib/librte_stack/rte_stack_lf_stubs.h b/lib/librte_stack/rte_stack_lf_stubs.h
> new file mode 100644
> index 0000000..a05abf1
> --- /dev/null
> +++ b/lib/librte_stack/rte_stack_lf_stubs.h
> @@ -0,0 +1,44 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2019 Arm Limited
> + */
> +
> +#ifndef _RTE_STACK_LF_STUBS_H_
> +#define _RTE_STACK_LF_STUBS_H_
> +
> +#include <rte_common.h>
> +
> +static __rte_always_inline unsigned int
> +__rte_stack_lf_count(struct rte_stack *s)
> +{
> + RTE_SET_USED(s);
> +
> + return 0;
> +}
> +
> +static __rte_always_inline void
> +__rte_stack_lf_push_elems(struct rte_stack_lf_list *list,
> + struct rte_stack_lf_elem *first,
> + struct rte_stack_lf_elem *last,
> + unsigned int num)
> +{
> + RTE_SET_USED(first);
> + RTE_SET_USED(last);
> + RTE_SET_USED(list);
> + RTE_SET_USED(num);
> +}
> +
> +static __rte_always_inline struct rte_stack_lf_elem *
> +__rte_stack_lf_pop_elems(struct rte_stack_lf_list *list,
> + unsigned int num,
> + void **obj_table,
> + struct rte_stack_lf_elem **last)
> +{
> + RTE_SET_USED(obj_table);
> + RTE_SET_USED(last);
> + RTE_SET_USED(list);
> + RTE_SET_USED(num);
> +
> + return NULL;
> +}
> +
> +#endif /* _RTE_STACK_LF_STUBS_H_ */
> --
> 2.7.4
>
> -----Original Message-----
> From: David Marchand <david.marchand@redhat.com>
> Sent: Monday, October 14, 2019 11:45 PM
> To: Phil Yang (Arm Technology China) <Phil.Yang@arm.com>
> Cc: thomas@monjalon.net; jerinj@marvell.com; Gage Eads
> <gage.eads@intel.com>; dev <dev@dpdk.org>; hemant.agrawal@nxp.com;
> Honnappa Nagarahalli <Honnappa.Nagarahalli@arm.com>; Gavin Hu (Arm
> Technology China) <Gavin.Hu@arm.com>; nd <nd@arm.com>
> Subject: Re: [dpdk-dev] [PATCH v9 3/3] eal/stack: enable lock-free stack for
> aarch64
>
> On Wed, Aug 14, 2019 at 10:30 AM Phil Yang <phil.yang@arm.com> wrote:
> >
> > Enable both c11 atomic and non c11 atomic lock-free stack for aarch64.
> >
> > Introduced a new header to reduce the ifdef clutter across generic and c11
> > files. The rte_stack_lf_stubs.h contains stub implementations of
> > __rte_stack_lf_count, __rte_stack_lf_push_elems and
> > __rte_stack_lf_pop_elems.
> >
> > Suggested-by: Gage Eads <gage.eads@intel.com>
> > Suggested-by: Jerin Jacob <jerinj@marvell.com>
> > Signed-off-by: Phil Yang <phil.yang@arm.com>
> > Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
> > Tested-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
> > Acked-by: Jerin Jacob <jerinj@marvell.com>
> > ---
<snip>
> > -------------
> > diff --git a/lib/librte_stack/Makefile b/lib/librte_stack/Makefile
> > index 8d18ce5..c337ab7 100644
> > --- a/lib/librte_stack/Makefile
> > +++ b/lib/librte_stack/Makefile
> > @@ -24,6 +24,7 @@ SYMLINK-$(CONFIG_RTE_LIBRTE_STACK)-include :=
> rte_stack.h \
> > rte_stack_std.h \
> > rte_stack_lf.h \
> > rte_stack_lf_generic.h \
> > - rte_stack_lf_c11.h
> > + rte_stack_lf_c11.h \
> > + rte_stack_lf_stubs.h
>
> Please, use the same indentation type than the other lines.
Updated in v10.
Thanks,
Phil
@@ -648,8 +648,8 @@ Known Issues
Alternatively, applications can use the lock-free stack mempool handler. When
considering this handler, note that:
- - It is currently limited to the x86_64 platform, because it uses an
- instruction (16-byte compare-and-swap) that is not yet available on other
+ - It is currently limited to the aarch64 and x86_64 platforms, because it uses
+ an instruction (16-byte compare-and-swap) that is not yet available on other
platforms.
- It has worse average-case performance than the non-preemptive rte_ring, but
software caching (e.g. the mempool cache) can mitigate this by reducing the
@@ -56,6 +56,9 @@ New Features
Also, make sure to start the actual text at the margin.
=========================================================
+* **Added Lock-free Stack for aarch64.**
+
+ The lock-free stack implementation is enabled for aarch64 platforms.
Removed Items
-------------
@@ -24,6 +24,7 @@ SYMLINK-$(CONFIG_RTE_LIBRTE_STACK)-include := rte_stack.h \
rte_stack_std.h \
rte_stack_lf.h \
rte_stack_lf_generic.h \
- rte_stack_lf_c11.h
+ rte_stack_lf_c11.h \
+ rte_stack_lf_stubs.h
include $(RTE_SDK)/mk/rte.lib.mk
@@ -5,11 +5,15 @@
#ifndef _RTE_STACK_LF_H_
#define _RTE_STACK_LF_H_
+#if !(defined(RTE_ARCH_X86_64) || defined(RTE_ARCH_ARM64))
+#include "rte_stack_lf_stubs.h"
+#else
#ifdef RTE_USE_C11_MEM_MODEL
#include "rte_stack_lf_c11.h"
#else
#include "rte_stack_lf_generic.h"
#endif
+#endif
/**
* @internal Push several objects on the lock-free stack (MT-safe).
@@ -36,12 +36,6 @@ __rte_stack_lf_push_elems(struct rte_stack_lf_list *list,
struct rte_stack_lf_elem *last,
unsigned int num)
{
-#ifndef RTE_ARCH_X86_64
- RTE_SET_USED(first);
- RTE_SET_USED(last);
- RTE_SET_USED(list);
- RTE_SET_USED(num);
-#else
struct rte_stack_lf_head old_head;
int success;
@@ -79,7 +73,6 @@ __rte_stack_lf_push_elems(struct rte_stack_lf_list *list,
* to the LIFO len update.
*/
__atomic_add_fetch(&list->len, num, __ATOMIC_RELEASE);
-#endif
}
static __rte_always_inline struct rte_stack_lf_elem *
@@ -88,14 +81,6 @@ __rte_stack_lf_pop_elems(struct rte_stack_lf_list *list,
void **obj_table,
struct rte_stack_lf_elem **last)
{
-#ifndef RTE_ARCH_X86_64
- RTE_SET_USED(obj_table);
- RTE_SET_USED(last);
- RTE_SET_USED(list);
- RTE_SET_USED(num);
-
- return NULL;
-#else
struct rte_stack_lf_head old_head;
uint64_t len;
int success;
@@ -169,7 +154,6 @@ __rte_stack_lf_pop_elems(struct rte_stack_lf_list *list,
} while (success == 0);
return old_head.top;
-#endif
}
#endif /* _RTE_STACK_LF_C11_H_ */
@@ -36,12 +36,6 @@ __rte_stack_lf_push_elems(struct rte_stack_lf_list *list,
struct rte_stack_lf_elem *last,
unsigned int num)
{
-#ifndef RTE_ARCH_X86_64
- RTE_SET_USED(first);
- RTE_SET_USED(last);
- RTE_SET_USED(list);
- RTE_SET_USED(num);
-#else
struct rte_stack_lf_head old_head;
int success;
@@ -75,7 +69,6 @@ __rte_stack_lf_push_elems(struct rte_stack_lf_list *list,
} while (success == 0);
rte_atomic64_add((rte_atomic64_t *)&list->len, num);
-#endif
}
static __rte_always_inline struct rte_stack_lf_elem *
@@ -84,14 +77,6 @@ __rte_stack_lf_pop_elems(struct rte_stack_lf_list *list,
void **obj_table,
struct rte_stack_lf_elem **last)
{
-#ifndef RTE_ARCH_X86_64
- RTE_SET_USED(obj_table);
- RTE_SET_USED(last);
- RTE_SET_USED(list);
- RTE_SET_USED(num);
-
- return NULL;
-#else
struct rte_stack_lf_head old_head;
int success;
@@ -159,7 +144,6 @@ __rte_stack_lf_pop_elems(struct rte_stack_lf_list *list,
} while (success == 0);
return old_head.top;
-#endif
}
#endif /* _RTE_STACK_LF_GENERIC_H_ */
new file mode 100644
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 Arm Limited
+ */
+
+#ifndef _RTE_STACK_LF_STUBS_H_
+#define _RTE_STACK_LF_STUBS_H_
+
+#include <rte_common.h>
+
+static __rte_always_inline unsigned int
+__rte_stack_lf_count(struct rte_stack *s)
+{
+ RTE_SET_USED(s);
+
+ return 0;
+}
+
+static __rte_always_inline void
+__rte_stack_lf_push_elems(struct rte_stack_lf_list *list,
+ struct rte_stack_lf_elem *first,
+ struct rte_stack_lf_elem *last,
+ unsigned int num)
+{
+ RTE_SET_USED(first);
+ RTE_SET_USED(last);
+ RTE_SET_USED(list);
+ RTE_SET_USED(num);
+}
+
+static __rte_always_inline struct rte_stack_lf_elem *
+__rte_stack_lf_pop_elems(struct rte_stack_lf_list *list,
+ unsigned int num,
+ void **obj_table,
+ struct rte_stack_lf_elem **last)
+{
+ RTE_SET_USED(obj_table);
+ RTE_SET_USED(last);
+ RTE_SET_USED(list);
+ RTE_SET_USED(num);
+
+ return NULL;
+}
+
+#endif /* _RTE_STACK_LF_STUBS_H_ */