diff mbox series

[RFCv2,bpf-next,06/18] xdp: controlling XDP-hints from BPF-prog via helper

Message ID 166256553093.1434226.11320655607309623999.stgit@firesoul (mailing list archive)
State RFC
Delegated to: BPF
Headers show
Series XDP-hints: XDP gaining access to HW offload hints via BTF | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR fail PR summary
bpf/vmtest-bpf-next-VM_Test-1 pending Logs for ${{ matrix.test }} on ${{ matrix.arch }} with ${{ matrix.toolchain }}
bpf/vmtest-bpf-next-VM_Test-2 fail Logs for build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-3 fail Logs for build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-4 fail Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-5 success Logs for llvm-toolchain
bpf/vmtest-bpf-next-VM_Test-6 success Logs for set-matrix
netdev/tree_selection success Clearly marked for bpf-next, async
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count fail Series longer than 15 patches (and no cover letter)
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 4448 this patch: 4448
netdev/cc_maintainers warning 15 maintainers not CCed: edumazet@google.com andrii@kernel.org john.fastabend@gmail.com jolsa@kernel.org pabeni@redhat.com song@kernel.org yhs@fb.com daniel@iogearbox.net kuba@kernel.org martin.lau@linux.dev haoluo@google.com kpsingh@kernel.org hawk@kernel.org davem@davemloft.net sdf@google.com
netdev/build_clang success Errors and warnings before: 1077 this patch: 1077
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 4619 this patch: 4619
netdev/checkpatch warning WARNING: line length of 92 exceeds 80 columns WARNING: please, no space before tabs
netdev/kdoc success Errors and warnings before: 23 this patch: 23
netdev/source_inline success Was 0 now: 0

Commit Message

Jesper Dangaard Brouer Sept. 7, 2022, 3:45 p.m. UTC
XDP BPF-prog's need a way to interact with the XDP-hints. This patch
introduces a BPF-helper function, that allow XDP BPF-prog's to interact
with the XDP-hints.  Choosing BPF-helper to avoid directly exposing
xdp_buff_flags as UAPI.

BPF-prog can query if any XDP-hints have been setup and if this is
compatible with the xdp_hints_common struct.

Notice that XDP-hints are setup by the driver prior to calling the XDP
BPF-prog, which is useful as a BPF software layer for adjusting the HW
provided XDP-hints in-case of HW issues or missing HW features, for
use-case like xdp2skb or AF_XDP.

The BPF-prog might also prefer to use metadata area for other things,
either disabling XDP-hints or updating with another XDP-hints layout
that might still be compatible with common struct. Thus, helper have
"update" and "delete" mode flags.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
 include/net/xdp.h              |   41 ++++++++++++++++++++++++++++----
 include/uapi/linux/bpf.h       |   41 ++++++++++++++++++++++++++++++++
 net/core/filter.c              |   52 ++++++++++++++++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |   43 ++++++++++++++++++++++++++++++++-
 4 files changed, 172 insertions(+), 5 deletions(-)
diff mbox series

Patch

diff --git a/include/net/xdp.h b/include/net/xdp.h
index ea5836ccee82..c7cdcef83fa5 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -213,14 +213,19 @@  struct xdp_txq_info {
 };
 
 enum xdp_buff_flags {
-	XDP_FLAGS_HAS_FRAGS		= BIT(0), /* non-linear xdp buff */
-	XDP_FLAGS_FRAGS_PF_MEMALLOC	= BIT(1), /* xdp paged memory is under
+	XDP_FLAGS_HINTS_ENABLED 	= BIT(0),/* enum xdp_hint */
+#define	XDP_FLAGS_HINTS_COMPAT_COMMON_	  BIT(1) /* HINTS_BTF_COMPAT_COMMON */
+	XDP_FLAGS_HINTS_COMPAT_COMMON	= XDP_FLAGS_HINTS_COMPAT_COMMON_,
+
+	XDP_FLAGS_HAS_FRAGS		= BIT(2), /* non-linear xdp buff */
+	XDP_FLAGS_FRAGS_PF_MEMALLOC	= BIT(3), /* xdp paged memory is under
 						   * pressure
 						   */
-	XDP_FLAGS_HAS_HINTS		= BIT(2),
-	XDP_FLAGS_HINTS_COMPAT_COMMON	= BIT(3),
 };
 
+#define XDP_FLAGS_HINTS_MASK	(XDP_FLAGS_HINTS_ENABLED |	\
+				 XDP_FLAGS_HINTS_COMPAT_COMMON)
+
 struct xdp_buff {
 	void *data;
 	void *data_end;
@@ -257,6 +262,34 @@  static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp)
 	xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC;
 }
 
+static __always_inline bool xdp_buff_has_hints(struct xdp_buff *xdp)
+{
+	return !!(xdp->flags & XDP_FLAGS_HINTS_MASK);
+}
+
+static __always_inline bool xdp_buff_has_hints_compat(struct xdp_buff *xdp)
+{
+	u32 flags = xdp->flags;
+
+	if (!(flags & XDP_FLAGS_HINTS_COMPAT_COMMON))
+		return false;
+
+	return !!(flags & XDP_FLAGS_HINTS_MASK);
+}
+
+static __always_inline void xdp_buff_set_hints_flags(struct xdp_buff *xdp,
+						     bool is_compat_common)
+{
+	u32 common = is_compat_common ? XDP_FLAGS_HINTS_COMPAT_COMMON : 0;
+
+	xdp->flags |= XDP_FLAGS_HINTS_ENABLED | common;
+}
+
+static __always_inline void xdp_buff_clear_hints_flags(struct xdp_buff *xdp)
+{
+	xdp->flags &= ~XDP_FLAGS_HINTS_MASK;
+}
+
 static __always_inline void
 xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq)
 {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 934a2a8beb87..36ba104e612e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5355,6 +5355,37 @@  union bpf_attr {
  *	Return
  *		Current *ktime*.
  *
+ * long xdp_hints_btf(struct xdp_buff *xdp_md, u64 flags)
+ *	Description
+ *		Update and get info on XDP hints ctx state.
+ *
+ *		Drivers can provide XDP-hints information via the metadata area,
+ *		which defines the layout of this area via BTF. The *full* BTF ID
+ *		is available as the last member.
+ *
+ *		This **full** BTF ID is a 64-bit value, encoding the BTF
+ *		**object** ID as the high 32-bit and BTF *type* ID as lower
+ *		32-bit.  This is needed as the BTF **type** ID (32-bit) can
+ *		originate from different BTF **object** sources, e.g.  vmlinux,
+ *		module or local BTF-object.
+ *
+ *		In-case a BPF-prog want to redefine the layout of this area it
+ *		should update the full BTF ID (last-member) and call this helper
+ *		to specify if the layout is compatible with kernel struct
+ *		xdp_hints_common.
+ *
+ *		The **flags** are used to control the mode of the helper.
+ *		See enum xdp_hints_btf_mode_flags.
+ *
+ *     Return
+ * 		0 if driver didn't populate XDP-hints.
+ *
+ *		Flag **HINTS_BTF_ENABLED** (1) if driver populated hints.
+ *
+ *		Flag **HINTS_BTF_COMPAT_COMMON** (2) if layout is compatible
+ *		with kernel struct xdp_hints_common. Thus, return value 3 as
+ *		both flags will be set.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5566,6 +5597,7 @@  union bpf_attr {
 	FN(tcp_raw_check_syncookie_ipv4),	\
 	FN(tcp_raw_check_syncookie_ipv6),	\
 	FN(ktime_get_tai_ns),		\
+	FN(xdp_hints_btf),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5977,6 +6009,15 @@  struct xdp_md {
 	__u32 egress_ifindex;  /* txq->dev->ifindex */
 };
 
+/* Mode flags for BPF_FUNC_xdp_hints_btf helper. */
+enum xdp_hints_btf_mode_flags {
+	HINTS_BTF_QUERY_ONLY    = (1U << 0),
+	HINTS_BTF_ENABLED       = (1U << 0), /* Return value */
+	HINTS_BTF_COMPAT_COMMON = (1U << 1), /* Return and query value */
+	HINTS_BTF_UPDATE        = (1U << 2),
+	HINTS_BTF_DISABLE       = (1U << 3),
+};
+
 /* DEVMAP map-value layout
  *
  * The struct data-layout of map-value is a configuration interface.
diff --git a/net/core/filter.c b/net/core/filter.c
index 1acfaffeaf32..35f29990a67e 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6094,6 +6094,56 @@  static const struct bpf_func_proto bpf_xdp_check_mtu_proto = {
 	.arg5_type      = ARG_ANYTHING,
 };
 
+/* flags type &enum xdp_hints_btf_mode_flags */
+BPF_CALL_2(bpf_xdp_hints_btf, struct xdp_buff *, xdp, u64, flags)
+{
+	bool is_compat_common;
+	s64 ret = 0;
+
+	/* UAPI value HINTS_BTF_COMPAT_COMMON happens to match xdp_buff->flags
+	 * XDP_FLAGS_HINTS_COMPAT_COMMON which makes below code easier
+	 */
+	BUILD_BUG_ON(HINTS_BTF_COMPAT_COMMON != XDP_FLAGS_HINTS_COMPAT_COMMON_);
+
+	if (flags & HINTS_BTF_QUERY_ONLY) {
+		ret = xdp->flags & XDP_FLAGS_HINTS_MASK;
+		goto out;
+	}
+	if (flags & HINTS_BTF_DISABLE) {
+		xdp_buff_clear_hints_flags(xdp);
+		goto out;
+	}
+	if (flags & HINTS_BTF_UPDATE) {
+		is_compat_common = !!(flags & HINTS_BTF_COMPAT_COMMON);
+
+		if (is_compat_common) {
+			unsigned long metalen = xdp_get_metalen(xdp);
+
+			if (sizeof(struct xdp_hints_common) < metalen)
+				is_compat_common = false;
+			/* TODO: Can kernel validate if hints are BTF compat
+			 * with common?
+			 */
+		}
+	/* TODO: Could BPF prog provide BTF as ARG_PTR_TO_BTF_ID to prove compat_common ? */
+		xdp_buff_set_hints_flags(xdp, is_compat_common);
+
+		ret = xdp->flags & XDP_FLAGS_HINTS_MASK;
+		goto out;
+	}
+
+ out:
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_xdp_hints_btf_proto = {
+	.func		= bpf_xdp_hints_btf,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 #if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len)
 {
@@ -7944,6 +7994,8 @@  xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_fib_lookup_proto;
 	case BPF_FUNC_check_mtu:
 		return &bpf_xdp_check_mtu_proto;
+	case BPF_FUNC_xdp_hints_btf:
+		return &bpf_xdp_hints_btf_proto;
 #ifdef CONFIG_INET
 	case BPF_FUNC_sk_lookup_udp:
 		return &bpf_xdp_sk_lookup_udp_proto;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1d6085e15fc8..36ba104e612e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -79,7 +79,7 @@  struct bpf_insn {
 /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */
 struct bpf_lpm_trie_key {
 	__u32	prefixlen;	/* up to 32 for AF_INET, 128 for AF_INET6 */
-	__u8	data[0];	/* Arbitrary size */
+	__u8	data[];	/* Arbitrary size */
 };
 
 struct bpf_cgroup_storage_key {
@@ -5355,6 +5355,37 @@  union bpf_attr {
  *	Return
  *		Current *ktime*.
  *
+ * long xdp_hints_btf(struct xdp_buff *xdp_md, u64 flags)
+ *	Description
+ *		Update and get info on XDP hints ctx state.
+ *
+ *		Drivers can provide XDP-hints information via the metadata area,
+ *		which defines the layout of this area via BTF. The *full* BTF ID
+ *		is available as the last member.
+ *
+ *		This **full** BTF ID is a 64-bit value, encoding the BTF
+ *		**object** ID as the high 32-bit and BTF *type* ID as lower
+ *		32-bit.  This is needed as the BTF **type** ID (32-bit) can
+ *		originate from different BTF **object** sources, e.g.  vmlinux,
+ *		module or local BTF-object.
+ *
+ *		In-case a BPF-prog want to redefine the layout of this area it
+ *		should update the full BTF ID (last-member) and call this helper
+ *		to specify if the layout is compatible with kernel struct
+ *		xdp_hints_common.
+ *
+ *		The **flags** are used to control the mode of the helper.
+ *		See enum xdp_hints_btf_mode_flags.
+ *
+ *     Return
+ * 		0 if driver didn't populate XDP-hints.
+ *
+ *		Flag **HINTS_BTF_ENABLED** (1) if driver populated hints.
+ *
+ *		Flag **HINTS_BTF_COMPAT_COMMON** (2) if layout is compatible
+ *		with kernel struct xdp_hints_common. Thus, return value 3 as
+ *		both flags will be set.
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5566,6 +5597,7 @@  union bpf_attr {
 	FN(tcp_raw_check_syncookie_ipv4),	\
 	FN(tcp_raw_check_syncookie_ipv6),	\
 	FN(ktime_get_tai_ns),		\
+	FN(xdp_hints_btf),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5977,6 +6009,15 @@  struct xdp_md {
 	__u32 egress_ifindex;  /* txq->dev->ifindex */
 };
 
+/* Mode flags for BPF_FUNC_xdp_hints_btf helper. */
+enum xdp_hints_btf_mode_flags {
+	HINTS_BTF_QUERY_ONLY    = (1U << 0),
+	HINTS_BTF_ENABLED       = (1U << 0), /* Return value */
+	HINTS_BTF_COMPAT_COMMON = (1U << 1), /* Return and query value */
+	HINTS_BTF_UPDATE        = (1U << 2),
+	HINTS_BTF_DISABLE       = (1U << 3),
+};
+
 /* DEVMAP map-value layout
  *
  * The struct data-layout of map-value is a configuration interface.