[RFC PATCH 10/11] bpf: add bpf_buffer_reserve and bpf_buffer_commit

[Kris Van Hees <kris.van.hees@oracle.com>]

Add two helpers that are primarily used in combination with the
writable-buffer support.  The bpf_buffer_reserve() helper sets aside
a chunk of buffer space that can be written to, and once all data
has been written, the bpf_buffer_commit() helper is used to make the
data in the ring buffer visible to userspace.

Signed-off-by: Kris Van Hees <kris.van.hees@oracle.com>
Reviewed-by: Nick Alcock <nick.alcock@oracle.com>
---
 include/uapi/linux/bpf.h                  | 39 ++++++++++++++++++++++-
 kernel/bpf/verifier.c                     |  6 +++-
 tools/include/uapi/linux/bpf.h            | 39 ++++++++++++++++++++++-
 tools/testing/selftests/bpf/bpf_helpers.h |  4 +++
 4 files changed, 85 insertions(+), 3 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 7bcb707539d1..2b7772aa00b6 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2681,6 +2681,41 @@ union bpf_attr {
  *		the implementing program type.
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_buffer_reserve(void *ctx, int id, struct bpf_map *map, int size)
+ *	Description
+ *		Reserve *size* bytes in the output buffer for the special BPF
+ *		BPF perf event referenced by *map*, a BPF map of type
+ *		**BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The perf event must have
+ *		the attributes: **PERF_SAMPLE_RAW** as **sample_type**,
+ *		**PERF_TYPE_SOFTWARE** as **type**, and
+ *		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.  The reserved space
+ *		will be available as the writable buffer identified with
+ *		numeric ID **id** in the context.
+ *
+ *		The amount of reserved bytes cannot exceed the page size.
+ *		The chunk of buffer space will be reserved within a single
+ *		page, and if this results in unused space at the end of the
+ *		previous page in the ring-buffer, that unsused space will be
+ *		filled with zeros.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_buffer_commit(void *ctx, int id, struct bpf_map *map)
+ *	Description
+ *		FInalize the previously reserved space in the output buffer
+ *		for the special BPF perf event referenced by *map*, a BPF map
+ *		of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The perf event must
+ *		have the attributes: **PERF_SAMPLE_RAW** as **sample_type**,
+ *		**PERF_TYPE_SOFTWARE** as **type**, and
+ *		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ *		The writable buffer identified with numeric ID **id** in the
+ *		context will be invalidated, and can no longer be used to
+ *		write data to until a new **bpf_buffer_reserve**\ () has been
+ *		invoked.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2792,7 +2827,9 @@ union bpf_attr {
 	FN(strtoul),			\
 	FN(sk_storage_get),		\
 	FN(sk_storage_delete),		\
-	FN(finalize_context),
+	FN(finalize_context),		\
+	FN(buffer_reserve),		\
+	FN(buffer_commit),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 90ae04b4d5c7..ff73ed743a58 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2763,7 +2763,9 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
 		if (func_id != BPF_FUNC_perf_event_read &&
 		    func_id != BPF_FUNC_perf_event_output &&
-		    func_id != BPF_FUNC_perf_event_read_value)
+		    func_id != BPF_FUNC_perf_event_read_value &&
+		    func_id != BPF_FUNC_buffer_reserve &&
+		    func_id != BPF_FUNC_buffer_commit)
 			goto error;
 		break;
 	case BPF_MAP_TYPE_STACK_TRACE:
@@ -2848,6 +2850,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_FUNC_perf_event_read:
 	case BPF_FUNC_perf_event_output:
 	case BPF_FUNC_perf_event_read_value:
+	case BPF_FUNC_buffer_reserve:
+	case BPF_FUNC_buffer_commit:
 		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
 			goto error;
 		break;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 7bcb707539d1..2b7772aa00b6 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2681,6 +2681,41 @@ union bpf_attr {
  *		the implementing program type.
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_buffer_reserve(void *ctx, int id, struct bpf_map *map, int size)
+ *	Description
+ *		Reserve *size* bytes in the output buffer for the special BPF
+ *		BPF perf event referenced by *map*, a BPF map of type
+ *		**BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The perf event must have
+ *		the attributes: **PERF_SAMPLE_RAW** as **sample_type**,
+ *		**PERF_TYPE_SOFTWARE** as **type**, and
+ *		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.  The reserved space
+ *		will be available as the writable buffer identified with
+ *		numeric ID **id** in the context.
+ *
+ *		The amount of reserved bytes cannot exceed the page size.
+ *		The chunk of buffer space will be reserved within a single
+ *		page, and if this results in unused space at the end of the
+ *		previous page in the ring-buffer, that unsused space will be
+ *		filled with zeros.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_buffer_commit(void *ctx, int id, struct bpf_map *map)
+ *	Description
+ *		FInalize the previously reserved space in the output buffer
+ *		for the special BPF perf event referenced by *map*, a BPF map
+ *		of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The perf event must
+ *		have the attributes: **PERF_SAMPLE_RAW** as **sample_type**,
+ *		**PERF_TYPE_SOFTWARE** as **type**, and
+ *		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ *		The writable buffer identified with numeric ID **id** in the
+ *		context will be invalidated, and can no longer be used to
+ *		write data to until a new **bpf_buffer_reserve**\ () has been
+ *		invoked.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2792,7 +2827,9 @@ union bpf_attr {
 	FN(strtoul),			\
 	FN(sk_storage_get),		\
 	FN(sk_storage_delete),		\
-	FN(finalize_context),
+	FN(finalize_context),		\
+	FN(buffer_reserve),		\
+	FN(buffer_commit),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index d98a62b3b56c..72af8157d4db 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -218,6 +218,10 @@ static int (*bpf_sk_storage_delete)(void *map, struct bpf_sock *sk) =
 	(void *)BPF_FUNC_sk_storage_delete;
 static int (*bpf_finalize_context)(void *ctx, void *map) =
 	(void *) BPF_FUNC_finalize_context;
+static int (*bpf_buffer_reserve)(void *ctx, int id, void *map, int size) =
+	(void *) BPF_FUNC_buffer_reserve;
+static int (*bpf_buffer_commit)(void *ctx, int id, void *map) =
+	(void *) BPF_FUNC_buffer_commit;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
-- 
2.20.1