From: Stanislav Fomichev <sdf@google.com>
To: bpf@vger.kernel.org
Cc: ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
martin.lau@linux.dev, song@kernel.org, yhs@fb.com,
john.fastabend@gmail.com, kpsingh@kernel.org, sdf@google.com,
haoluo@google.com, jolsa@kernel.org, kuba@kernel.org,
toke@kernel.org, willemb@google.com, dsahern@kernel.org,
magnus.karlsson@intel.com, bjorn@kernel.org,
maciej.fijalkowski@intel.com, hawk@kernel.org,
yoong.siang.song@intel.com, netdev@vger.kernel.org,
xdp-hints@xdp-project.net
Subject: [xdp-hints] [PATCH bpf-next v2 1/9] xsk: Support tx_metadata_len
Date: Thu, 14 Sep 2023 14:04:44 -0700 [thread overview]
Message-ID: <20230914210452.2588884-2-sdf@google.com> (raw)
In-Reply-To: <20230914210452.2588884-1-sdf@google.com>
For zerocopy mode, tx_desc->addr can point to the arbitrary offset
and carry some TX metadata in the headroom. For copy mode, there
is no way currently to populate skb metadata.
Introduce new tx_metadata_len umem config option that indicates how many
bytes to treat as metadata. Metadata bytes come prior to tx_desc address
(same as in RX case).
The size of the metadata has the same constraints as XDP:
- less than 256 bytes
- 4-byte aligned
- non-zero
This data is not interpreted in any way right now.
Signed-off-by: Stanislav Fomichev <sdf@google.com>
---
include/net/xdp_sock.h | 1 +
include/net/xsk_buff_pool.h | 1 +
include/uapi/linux/if_xdp.h | 1 +
net/xdp/xdp_umem.c | 4 ++++
net/xdp/xsk.c | 12 +++++++++++-
net/xdp/xsk_buff_pool.c | 1 +
net/xdp/xsk_queue.h | 17 ++++++++++-------
tools/include/uapi/linux/if_xdp.h | 1 +
8 files changed, 30 insertions(+), 8 deletions(-)
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 1617af380162..10993a05d220 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -28,6 +28,7 @@ struct xdp_umem {
struct user_struct *user;
refcount_t users;
u8 flags;
+ u8 tx_metadata_len;
bool zc;
struct page **pgs;
int id;
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index b0bdff26fc88..1985ffaf9b0c 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -77,6 +77,7 @@ struct xsk_buff_pool {
u32 chunk_size;
u32 chunk_shift;
u32 frame_len;
+ u8 tx_metadata_len; /* inherited from umem */
u8 cached_need_wakeup;
bool uses_need_wakeup;
bool dma_need_sync;
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index 8d48863472b9..2ecf79282c26 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -76,6 +76,7 @@ struct xdp_umem_reg {
__u32 chunk_size;
__u32 headroom;
__u32 flags;
+ __u32 tx_metadata_len;
};
struct xdp_statistics {
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 06cead2b8e34..333f3d53aad4 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -199,6 +199,9 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
return -EINVAL;
+ if (mr->tx_metadata_len > 256 || mr->tx_metadata_len % 4)
+ return -EINVAL;
+
umem->size = size;
umem->headroom = headroom;
umem->chunk_size = chunk_size;
@@ -207,6 +210,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
umem->pgs = NULL;
umem->user = NULL;
umem->flags = mr->flags;
+ umem->tx_metadata_len = mr->tx_metadata_len;
INIT_LIST_HEAD(&umem->xsk_dma_list);
refcount_set(&umem->users, 1);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 55f8b9b0e06d..5e479869ede1 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -1255,6 +1255,14 @@ struct xdp_umem_reg_v1 {
__u32 headroom;
};
+struct xdp_umem_reg_v2 {
+ __u64 addr; /* Start of packet data area */
+ __u64 len; /* Length of packet data area */
+ __u32 chunk_size;
+ __u32 headroom;
+ __u32 flags;
+};
+
static int xsk_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
@@ -1298,8 +1306,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
if (optlen < sizeof(struct xdp_umem_reg_v1))
return -EINVAL;
- else if (optlen < sizeof(mr))
+ else if (optlen < sizeof(struct xdp_umem_reg_v2))
mr_size = sizeof(struct xdp_umem_reg_v1);
+ else if (optlen < sizeof(mr))
+ mr_size = sizeof(struct xdp_umem_reg_v2);
if (copy_from_sockptr(&mr, optval, mr_size))
return -EFAULT;
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index b3f7b310811e..57c8d7100de8 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -85,6 +85,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
XDP_PACKET_HEADROOM;
pool->umem = umem;
pool->addrs = umem->addrs;
+ pool->tx_metadata_len = umem->tx_metadata_len;
INIT_LIST_HEAD(&pool->free_list);
INIT_LIST_HEAD(&pool->xskb_list);
INIT_LIST_HEAD(&pool->xsk_tx_list);
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 13354a1e4280..c74a1372bcb9 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -143,15 +143,17 @@ static inline bool xp_unused_options_set(u32 options)
static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
struct xdp_desc *desc)
{
- u64 offset = desc->addr & (pool->chunk_size - 1);
+ u64 addr = desc->addr - pool->tx_metadata_len;
+ u64 len = desc->len + pool->tx_metadata_len;
+ u64 offset = addr & (pool->chunk_size - 1);
if (!desc->len)
return false;
- if (offset + desc->len > pool->chunk_size)
+ if (offset + len > pool->chunk_size)
return false;
- if (desc->addr >= pool->addrs_cnt)
+ if (addr >= pool->addrs_cnt)
return false;
if (xp_unused_options_set(desc->options))
@@ -162,16 +164,17 @@ static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
struct xdp_desc *desc)
{
- u64 addr = xp_unaligned_add_offset_to_addr(desc->addr);
+ u64 addr = xp_unaligned_add_offset_to_addr(desc->addr) - pool->tx_metadata_len;
+ u64 len = desc->len + pool->tx_metadata_len;
if (!desc->len)
return false;
- if (desc->len > pool->chunk_size)
+ if (len > pool->chunk_size)
return false;
- if (addr >= pool->addrs_cnt || addr + desc->len > pool->addrs_cnt ||
- xp_desc_crosses_non_contig_pg(pool, addr, desc->len))
+ if (addr >= pool->addrs_cnt || addr + len > pool->addrs_cnt ||
+ xp_desc_crosses_non_contig_pg(pool, addr, len))
return false;
if (xp_unused_options_set(desc->options))
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index 73a47da885dc..34411a2e5b6c 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -76,6 +76,7 @@ struct xdp_umem_reg {
__u32 chunk_size;
__u32 headroom;
__u32 flags;
+ __u32 tx_metadata_len;
};
struct xdp_statistics {
--
2.42.0.459.ge4e396fd5e-goog
next prev parent reply other threads:[~2023-09-14 21:04 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-09-14 21:04 [xdp-hints] [PATCH bpf-next v2 0/9] xsk: TX metadata Stanislav Fomichev
2023-09-14 21:04 ` Stanislav Fomichev [this message]
2023-09-14 21:04 ` [xdp-hints] [PATCH bpf-next v2 2/9] xsk: add TX timestamp and TX checksum offload support Stanislav Fomichev
2023-09-15 1:29 ` [xdp-hints] " kernel test robot
2023-09-15 1:30 ` Vinicius Costa Gomes
2023-09-15 16:25 ` Stanislav Fomichev
2023-09-15 9:44 ` kernel test robot
2023-09-14 21:04 ` [xdp-hints] [PATCH bpf-next v2 3/9] tools: ynl: print xsk-features from the sample Stanislav Fomichev
2023-09-14 21:04 ` [xdp-hints] [PATCH bpf-next v2 4/9] net/mlx5e: Implement AF_XDP TX timestamp and checksum offload Stanislav Fomichev
2023-09-15 2:44 ` [xdp-hints] " kernel test robot
2023-09-14 21:04 ` [xdp-hints] [PATCH bpf-next v2 5/9] selftests/xsk: Support tx_metadata_len Stanislav Fomichev
2023-09-14 21:04 ` [xdp-hints] [PATCH bpf-next v2 6/9] selftests/bpf: Add csum helpers Stanislav Fomichev
2023-09-14 21:04 ` [xdp-hints] [PATCH bpf-next v2 7/9] selftests/bpf: Add TX side to xdp_metadata Stanislav Fomichev
2023-09-14 21:04 ` [xdp-hints] [PATCH bpf-next v2 8/9] selftests/bpf: Add TX side to xdp_hw_metadata Stanislav Fomichev
2023-09-14 21:04 ` [xdp-hints] [PATCH bpf-next v2 9/9] xsk: document tx_metadata_len layout Stanislav Fomichev
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
List information: https://lists.xdp-project.net/postorius/lists/xdp-hints.xdp-project.net/
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230914210452.2588884-2-sdf@google.com \
--to=sdf@google.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bjorn@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=dsahern@kernel.org \
--cc=haoluo@google.com \
--cc=hawk@kernel.org \
--cc=john.fastabend@gmail.com \
--cc=jolsa@kernel.org \
--cc=kpsingh@kernel.org \
--cc=kuba@kernel.org \
--cc=maciej.fijalkowski@intel.com \
--cc=magnus.karlsson@intel.com \
--cc=martin.lau@linux.dev \
--cc=netdev@vger.kernel.org \
--cc=song@kernel.org \
--cc=toke@kernel.org \
--cc=willemb@google.com \
--cc=xdp-hints@xdp-project.net \
--cc=yhs@fb.com \
--cc=yoong.siang.song@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox