Re: [PATCH v10 bpf-next 05/18] net: xdp: add xdp_update_skb_shared_info utility routine

Re: [PATCH v10 bpf-next 05/18] net: xdp: add xdp_update_skb_shared_info utility routine

[kernel test robot]

[-- Attachment #1: Type: text/plain, Size: 6400 bytes --]

CC: kbuild-all(a)lists.01.org
In-Reply-To: <1c65090b9b379528b18994c9ee5658c75ff1c71b.1627463617.git.lorenzo@kernel.org>
References: <1c65090b9b379528b18994c9ee5658c75ff1c71b.1627463617.git.lorenzo@kernel.org>
TO: Lorenzo Bianconi <lorenzo@kernel.org>
TO: bpf(a)vger.kernel.org
TO: netdev(a)vger.kernel.org
CC: lorenzo.bianconi(a)redhat.com
CC: davem(a)davemloft.net
CC: kuba(a)kernel.org
CC: ast(a)kernel.org
CC: daniel(a)iogearbox.net
CC: shayagr(a)amazon.com
CC: john.fastabend(a)gmail.com
CC: dsahern(a)kernel.org

Hi Lorenzo,

I love your patch! Perhaps something to improve:

[auto build test WARNING on bpf-next/master]

url:    https://github.com/0day-ci/linux/commits/Lorenzo-Bianconi/net-skbuff-add-size-metadata-to-skb_shared_info-for-xdp/20210728-183811
base:   https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git master
:::::: branch date: 7 days ago
:::::: commit date: 7 days ago
config: x86_64-randconfig-m001-20210804 (attached as .config)
compiler: gcc-9 (Debian 9.3.0-22) 9.3.0

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>

smatch warnings:
net/core/xdp.c:568 __xdp_build_skb_from_frame() error: uninitialized symbol 'nr_frags'.
net/core/xdp.c:569 __xdp_build_skb_from_frame() error: uninitialized symbol 'frag_size'.
net/core/xdp.c:569 __xdp_build_skb_from_frame() error: uninitialized symbol 'frag_tsize'.

vim +/nr_frags +568 net/core/xdp.c

65e6dcf73398dd Lorenzo Bianconi 2021-01-29  529  
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  530  struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  531  					   struct sk_buff *skb,
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  532  					   struct net_device *dev)
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  533  {
78139a2230d403 Lorenzo Bianconi 2021-07-28  534  	unsigned int frag_size, frag_tsize;
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  535  	unsigned int headroom, frame_size;
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  536  	void *hard_start;
78139a2230d403 Lorenzo Bianconi 2021-07-28  537  	u8 nr_frags;
78139a2230d403 Lorenzo Bianconi 2021-07-28  538  
78139a2230d403 Lorenzo Bianconi 2021-07-28  539  	/* xdp multi-buff frame */
78139a2230d403 Lorenzo Bianconi 2021-07-28  540  	if (unlikely(xdp_frame_is_mb(xdpf))) {
78139a2230d403 Lorenzo Bianconi 2021-07-28  541  		struct skb_shared_info *sinfo;
78139a2230d403 Lorenzo Bianconi 2021-07-28  542  
78139a2230d403 Lorenzo Bianconi 2021-07-28  543  		sinfo = xdp_get_shared_info_from_frame(xdpf);
78139a2230d403 Lorenzo Bianconi 2021-07-28  544  		frag_tsize = sinfo->xdp_frags_tsize;
78139a2230d403 Lorenzo Bianconi 2021-07-28  545  		frag_size = sinfo->xdp_frags_size;
78139a2230d403 Lorenzo Bianconi 2021-07-28  546  		nr_frags = sinfo->nr_frags;
78139a2230d403 Lorenzo Bianconi 2021-07-28  547  	}
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  548  
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  549  	/* Part of headroom was reserved to xdpf */
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  550  	headroom = sizeof(*xdpf) + xdpf->headroom;
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  551  
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  552  	/* Memory size backing xdp_frame data already have reserved
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  553  	 * room for build_skb to place skb_shared_info in tailroom.
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  554  	 */
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  555  	frame_size = xdpf->frame_sz;
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  556  
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  557  	hard_start = xdpf->data - headroom;
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  558  	skb = build_skb_around(skb, hard_start, frame_size);
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  559  	if (unlikely(!skb))
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  560  		return NULL;
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  561  
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  562  	skb_reserve(skb, headroom);
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  563  	__skb_put(skb, xdpf->len);
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  564  	if (xdpf->metasize)
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  565  		skb_metadata_set(skb, xdpf->metasize);
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  566  
78139a2230d403 Lorenzo Bianconi 2021-07-28  567  	if (unlikely(xdp_frame_is_mb(xdpf)))
78139a2230d403 Lorenzo Bianconi 2021-07-28 @568  		xdp_update_skb_shared_info(skb, nr_frags,
78139a2230d403 Lorenzo Bianconi 2021-07-28 @569  					   frag_size, frag_tsize,
78139a2230d403 Lorenzo Bianconi 2021-07-28  570  					   xdp_frame_is_frag_pfmemalloc(xdpf));
78139a2230d403 Lorenzo Bianconi 2021-07-28  571  
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  572  	/* Essential SKB info: protocol and skb->dev */
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  573  	skb->protocol = eth_type_trans(skb, dev);
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  574  
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  575  	/* Optional SKB info, currently missing:
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  576  	 * - HW checksum info		(skb->ip_summed)
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  577  	 * - HW RX hash			(skb_set_hash)
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  578  	 * - RX ring dev queue index	(skb_record_rx_queue)
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  579  	 */
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  580  
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  581  	/* Until page_pool get SKB return path, release DMA here */
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  582  	xdp_release_frame(xdpf);
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  583  
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  584  	/* Allow SKB to reuse area used by xdp_frame */
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  585  	xdp_scrub_frame(xdpf);
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  586  
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  587  	return skb;
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  588  }
97a0e1ea7b41c2 Lorenzo Bianconi 2021-01-12  589  EXPORT_SYMBOL_GPL(__xdp_build_skb_from_frame);
89f479f0eccfc8 Lorenzo Bianconi 2021-01-12  590  

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org

[-- Attachment #2: config.gz --]
[-- Type: application/gzip, Size: 32290 bytes --]

[PATCH v10 bpf-next 00/18] mvneta: introduce XDP multi-buffer support

[Lorenzo Bianconi]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=y, Size: 7405 bytes --]

From: Lorenzo Bianconi <lorenzo@kernel.org>

This series introduce XDP multi-buffer support. The mvneta driver is
the first to support these new "non-linear" xdp_{buff,frame}. Reviewers
please focus on how these new types of xdp_{buff,frame} packets
traverse the different layers and the layout design. It is on purpose
that BPF-helpers are kept simple, as we don't want to expose the
internal layout to allow later changes.

The main idea for the new multi-buffer layout is to reuse the same
layout used for non-linear SKB. This rely on the "skb_shared_info"
struct at the end of the first buffer to link together subsequent
buffers. Keeping the layout compatible with SKBs is also done to ease
and speedup creating a SKB from an xdp_{buff,frame}.
Converting xdp_frame to SKB and deliver it to the network stack is shown
in patch 05/18 (e.g. cpumaps).

A multi-buffer bit (mb) has been introduced in the flags field of xdp_{buff,frame}
structure to notify the bpf/network layer if this is a xdp multi-buffer frame
(mb = 1) or not (mb = 0).
The mb bit will be set by a xdp multi-buffer capable driver only for
non-linear frames maintaining the capability to receive linear frames
without any extra cost since the skb_shared_info structure at the end
of the first buffer will be initialized only if mb is set.
Moreover the flags field in xdp_{buff,frame} will be reused even for
xdp rx csum offloading in future series.

Typical use cases for this series are:
- Jumbo-frames
- Packet header split (please see Google’s use-case @ NetDevConf 0x14, [0])
- TSO

The two following ebpf helpers (and related selftests) has been introduced:
- bpf_xdp_adjust_data:
  Move xdp_md->data and xdp_md->data_end pointers in subsequent fragments
  according to the offset provided by the ebpf program. This helper can be
  used to read/write values in frame payload.
- bpf_xdp_get_buff_len:
  Return the total frame size (linear + paged parts)

bpf_xdp_adjust_tail and bpf_xdp_copy helpers have been modified to take into
account xdp multi-buff frames.

More info about the main idea behind this approach can be found here [1][2].

Changes since v9:
- introduce bpf_xdp_adjust_data helper and related selftest
- add xdp_frags_size and xdp_frags_tsize fields in skb_shared_info
- introduce xdp_update_skb_shared_info utility routine in ordere to not reset
  frags array in skb_shared_info converting from a xdp_buff/xdp_frame to a skb 
- simplify bpf_xdp_copy routine

Changes since v8:
- add proper dma unmapping if XDP_TX fails on mvneta for a xdp multi-buff
- switch back to skb_shared_info implementation from previous xdp_shared_info
  one
- avoid using a bietfield in xdp_buff/xdp_frame since it introduces performance
  regressions. Tested now on 10G NIC (ixgbe) to verify there are no performance
  penalties for regular codebase
- add bpf_xdp_get_buff_len helper and remove frame_length field in xdp ctx
- add data_len field in skb_shared_info struct
- introduce XDP_FLAGS_FRAGS_PF_MEMALLOC flag

Changes since v7:
- rebase on top of bpf-next
- fix sparse warnings
- improve comments for frame_length in include/net/xdp.h

Changes since v6:
- the main difference respect to previous versions is the new approach proposed
  by Eelco to pass full length of the packet to eBPF layer in XDP context
- reintroduce multi-buff support to eBPF kself-tests
- reintroduce multi-buff support to bpf_xdp_adjust_tail helper
- introduce multi-buffer support to bpf_xdp_copy helper
- rebase on top of bpf-next

Changes since v5:
- rebase on top of bpf-next
- initialize mb bit in xdp_init_buff() and drop per-driver initialization
- drop xdp->mb initialization in xdp_convert_zc_to_xdp_frame()
- postpone introduction of frame_length field in XDP ctx to another series
- minor changes

Changes since v4:
- rebase ontop of bpf-next
- introduce xdp_shared_info to build xdp multi-buff instead of using the
  skb_shared_info struct
- introduce frame_length in xdp ctx
- drop previous bpf helpers
- fix bpf_xdp_adjust_tail for xdp multi-buff
- introduce xdp multi-buff self-tests for bpf_xdp_adjust_tail
- fix xdp_return_frame_bulk for xdp multi-buff

Changes since v3:
- rebase ontop of bpf-next
- add patch 10/13 to copy back paged data from a xdp multi-buff frame to
  userspace buffer for xdp multi-buff selftests

Changes since v2:
- add throughput measurements
- drop bpf_xdp_adjust_mb_header bpf helper
- introduce selftest for xdp multibuffer
- addressed comments on bpf_xdp_get_frags_count
- introduce xdp multi-buff support to cpumaps

Changes since v1:
- Fix use-after-free in xdp_return_{buff/frame}
- Introduce bpf helpers
- Introduce xdp_mb sample program
- access skb_shared_info->nr_frags only on the last fragment

Changes since RFC:
- squash multi-buffer bit initialization in a single patch
- add mvneta non-linear XDP buff support for tx side

[0] https://netdevconf.info/0x14/session.html?talk-the-path-to-tcp-4k-mtu-and-rx-zerocopy
[1] https://github.com/xdp-project/xdp-project/blob/master/areas/core/xdp-multi-buffer01-design.org
[2] https://netdevconf.info/0x14/session.html?tutorial-add-XDP-support-to-a-NIC-driver (XDPmulti-buffers section)

Eelco Chaudron (3):
  bpf: add multi-buff support to the bpf_xdp_adjust_tail() API
  bpf: add multi-buffer support to xdp copy helpers
  bpf: update xdp_adjust_tail selftest to include multi-buffer

Lorenzo Bianconi (15):
  net: skbuff: add size metadata to skb_shared_info for xdp
  xdp: introduce flags field in xdp_buff/xdp_frame
  net: mvneta: update mb bit before passing the xdp buffer to eBPF layer
  net: mvneta: simplify mvneta_swbm_add_rx_fragment management
  net: xdp: add xdp_update_skb_shared_info utility routine
  net: marvell: rely on xdp_update_skb_shared_info utility routine
  xdp: add multi-buff support to xdp_return_{buff/frame}
  net: mvneta: add multi buffer support to XDP_TX
  net: mvneta: enable jumbo frames for XDP
  bpf: introduce bpf_xdp_get_buff_len helper
  bpf: move user_size out of bpf_test_init
  bpf: introduce multibuff support to bpf_prog_test_run_xdp()
  bpf: test_run: add xdp_shared_info pointer in bpf_test_finish
    signature
  net: xdp: introduce bpf_xdp_adjust_data helper
  bpf: add bpf_xdp_adjust_data selftest

 drivers/net/ethernet/marvell/mvneta.c         | 213 ++++++++++--------
 include/linux/skbuff.h                        |   6 +-
 include/net/xdp.h                             |  95 +++++++-
 include/uapi/linux/bpf.h                      |  38 ++++
 kernel/trace/bpf_trace.c                      |   3 +
 net/bpf/test_run.c                            | 117 ++++++++--
 net/core/filter.c                             | 210 ++++++++++++++++-
 net/core/xdp.c                                |  76 ++++++-
 tools/include/uapi/linux/bpf.h                |  38 ++++
 .../bpf/prog_tests/xdp_adjust_data.c          |  55 +++++
 .../bpf/prog_tests/xdp_adjust_tail.c          | 118 ++++++++++
 .../selftests/bpf/prog_tests/xdp_bpf2bpf.c    | 151 +++++++++----
 .../bpf/progs/test_xdp_adjust_tail_grow.c     |  10 +-
 .../bpf/progs/test_xdp_adjust_tail_shrink.c   |  32 ++-
 .../selftests/bpf/progs/test_xdp_bpf2bpf.c    |   2 +-
 .../bpf/progs/test_xdp_update_frags.c         |  49 ++++
 16 files changed, 1044 insertions(+), 169 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/xdp_adjust_data.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_xdp_update_frags.c

-- 
2.31.1

[PATCH v10 bpf-next 05/18] net: xdp: add xdp_update_skb_shared_info utility routine

[Lorenzo Bianconi]

Introduce xdp_update_skb_shared_info routine to update frags array
metadata in skb_shared_info data structure converting to a skb from
a xdp_buff or xdp_frame.
According to the current skb_shared_info architecture in
xdp_frame/xdp_buff and to the xdp multi-buff support, there is
no need to run skb_add_rx_frag() and reset frags array converting the buffer
to a skb since the frag array will be in the same position for xdp_buff/xdp_frame
and for the skb, we just need to update memory metadata.
Introduce XDP_FLAGS_PF_MEMALLOC flag in xdp_buff_flags in order to mark
the xdp_buff or xdp_frame as under memory-pressure if pages of the frags array
are under memory pressure. Doing so we can avoid looping over all fragments in
xdp_update_skb_shared_info routine. The driver is expected to set the
flag constructing the xdp_buffer using xdp_buff_set_frag_pfmemalloc
utility routine.
Rely on xdp_update_skb_shared_info in __xdp_build_skb_from_frame routine
converting the multi-buff xdp_frame to a skb after performing a XDP_REDIRECT.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 include/net/xdp.h | 33 ++++++++++++++++++++++++++++++++-
 net/core/xdp.c    | 17 +++++++++++++++++
 2 files changed, 49 insertions(+), 1 deletion(-)

diff --git a/include/net/xdp.h b/include/net/xdp.h
index ed5ea784fd45..53cccdc9528c 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -67,7 +67,10 @@ struct xdp_txq_info {
 };
 
 enum xdp_buff_flags {
-	XDP_FLAGS_MULTI_BUFF	= BIT(0), /* non-linear xdp buff */
+	XDP_FLAGS_MULTI_BUFF		= BIT(0), /* non-linear xdp buff */
+	XDP_FLAGS_FRAGS_PF_MEMALLOC	= BIT(1), /* xdp multi-buff paged memory
+						   * is under pressure
+						   */
 };
 
 struct xdp_buff {
@@ -96,6 +99,16 @@ static __always_inline void xdp_buff_clear_mb(struct xdp_buff *xdp)
 	xdp->flags &= ~XDP_FLAGS_MULTI_BUFF;
 }
 
+static __always_inline bool xdp_buff_is_frag_pfmemalloc(struct xdp_buff *xdp)
+{
+	return !!(xdp->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC);
+}
+
+static __always_inline void xdp_buff_set_frag_pfmemalloc(struct xdp_buff *xdp)
+{
+	xdp->flags |= XDP_FLAGS_FRAGS_PF_MEMALLOC;
+}
+
 static __always_inline void
 xdp_init_buff(struct xdp_buff *xdp, u32 frame_sz, struct xdp_rxq_info *rxq)
 {
@@ -151,6 +164,11 @@ static __always_inline bool xdp_frame_is_mb(struct xdp_frame *frame)
 	return !!(frame->flags & XDP_FLAGS_MULTI_BUFF);
 }
 
+static __always_inline bool xdp_frame_is_frag_pfmemalloc(struct xdp_frame *frame)
+{
+	return !!(frame->flags & XDP_FLAGS_FRAGS_PF_MEMALLOC);
+}
+
 #define XDP_BULK_QUEUE_SIZE	16
 struct xdp_frame_bulk {
 	int count;
@@ -186,6 +204,19 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame)
 	frame->dev_rx = NULL;
 }
 
+static inline void
+xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags,
+			   unsigned int size, unsigned int truesize,
+			   bool pfmemalloc)
+{
+	skb_shinfo(skb)->nr_frags = nr_frags;
+
+	skb->len += size;
+	skb->data_len += size;
+	skb->truesize += truesize;
+	skb->pfmemalloc |= pfmemalloc;
+}
+
 /* Avoids inlining WARN macro in fast-path */
 void xdp_warn(const char *msg, const char *func, const int line);
 #define XDP_WARN(msg) xdp_warn(msg, __func__, __LINE__)
diff --git a/net/core/xdp.c b/net/core/xdp.c
index cc92ccb38432..504be3ce3ca9 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -531,8 +531,20 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					   struct sk_buff *skb,
 					   struct net_device *dev)
 {
+	unsigned int frag_size, frag_tsize;
 	unsigned int headroom, frame_size;
 	void *hard_start;
+	u8 nr_frags;
+
+	/* xdp multi-buff frame */
+	if (unlikely(xdp_frame_is_mb(xdpf))) {
+		struct skb_shared_info *sinfo;
+
+		sinfo = xdp_get_shared_info_from_frame(xdpf);
+		frag_tsize = sinfo->xdp_frags_tsize;
+		frag_size = sinfo->xdp_frags_size;
+		nr_frags = sinfo->nr_frags;
+	}
 
 	/* Part of headroom was reserved to xdpf */
 	headroom = sizeof(*xdpf) + xdpf->headroom;
@@ -552,6 +564,11 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 	if (xdpf->metasize)
 		skb_metadata_set(skb, xdpf->metasize);
 
+	if (unlikely(xdp_frame_is_mb(xdpf)))
+		xdp_update_skb_shared_info(skb, nr_frags,
+					   frag_size, frag_tsize,
+					   xdp_frame_is_frag_pfmemalloc(xdpf));
+
 	/* Essential SKB info: protocol and skb->dev */
 	skb->protocol = eth_type_trans(skb, dev);
 
-- 
2.31.1