From 24e82b7c045ba5afde5bd81f691b7a72283de35e Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 20 Feb 2025 15:29:29 +0800 Subject: bpf: Add networking timestamping support to bpf_get/setsockopt() The new SK_BPF_CB_FLAGS and new SK_BPF_CB_TX_TIMESTAMPING are added to bpf_get/setsockopt. The later patches will implement the BPF networking timestamping. The BPF program will use bpf_setsockopt(SK_BPF_CB_FLAGS, SK_BPF_CB_TX_TIMESTAMPING) to enable the BPF networking timestamping on a socket. Signed-off-by: Jason Xing Signed-off-by: Martin KaFai Lau Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20250220072940.99994-2-kerneljasonxing@gmail.com --- tools/include/uapi/linux/bpf.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 2acf9b336371..4e0632848440 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6913,6 +6913,12 @@ enum { BPF_SOCK_OPS_ALL_CB_FLAGS = 0x7F, }; +enum { + SK_BPF_CB_TX_TIMESTAMPING = 1<<0, + SK_BPF_CB_MASK = (SK_BPF_CB_TX_TIMESTAMPING - 1) | + SK_BPF_CB_TX_TIMESTAMPING +}; + /* List of known BPF sock_ops operators. * New entries can only be added at the end */ @@ -7091,6 +7097,7 @@ enum { TCP_BPF_SYN_IP = 1006, /* Copy the IP[46] and TCP header */ TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */ + SK_BPF_CB_FLAGS = 1009, /* Get or set sock ops flags in socket */ }; enum { -- cgit v1.2.3 From 6b98ec7e882af1c3088a88757e2226d06c8514f9 Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 20 Feb 2025 15:29:34 +0800 Subject: bpf: Add BPF_SOCK_OPS_TSTAMP_SCHED_CB callback Support SCM_TSTAMP_SCHED case for bpf timestamping. Add a new sock_ops callback, BPF_SOCK_OPS_TSTAMP_SCHED_CB. This callback will occur at the same timestamping point as the user space's SCM_TSTAMP_SCHED. The BPF program can use it to get the same SCM_TSTAMP_SCHED timestamp without modifying the user-space application. A new SKBTX_BPF flag is added to mark skb_shinfo(skb)->tx_flags, ensuring that the new BPF timestamping and the current user space's SO_TIMESTAMPING do not interfere with each other. Signed-off-by: Jason Xing Signed-off-by: Martin KaFai Lau Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20250220072940.99994-7-kerneljasonxing@gmail.com --- tools/include/uapi/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 4e0632848440..bb62fe25b2d0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -7031,6 +7031,11 @@ enum { * by the kernel or the * earlier bpf-progs. */ + BPF_SOCK_OPS_TSTAMP_SCHED_CB, /* Called when skb is passing + * through dev layer when + * SK_BPF_CB_TX_TIMESTAMPING + * feature is on. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect -- cgit v1.2.3 From ecebb17ad818bc043e558c278a6c56d5bbaebacc Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 20 Feb 2025 15:29:35 +0800 Subject: bpf: Add BPF_SOCK_OPS_TSTAMP_SND_SW_CB callback Support sw SCM_TSTAMP_SND case for bpf timestamping. Add a new sock_ops callback, BPF_SOCK_OPS_TSTAMP_SND_SW_CB. This callback will occur at the same timestamping point as the user space's software SCM_TSTAMP_SND. The BPF program can use it to get the same SCM_TSTAMP_SND timestamp without modifying the user-space application. Based on this patch, BPF program will get the software timestamp when the driver is ready to send the skb. In the sebsequent patch, the hardware timestamp will be supported. Signed-off-by: Jason Xing Signed-off-by: Martin KaFai Lau Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20250220072940.99994-8-kerneljasonxing@gmail.com --- tools/include/uapi/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bb62fe25b2d0..abe8d6c30dae 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -7036,6 +7036,10 @@ enum { * SK_BPF_CB_TX_TIMESTAMPING * feature is on. */ + BPF_SOCK_OPS_TSTAMP_SND_SW_CB, /* Called when skb is about to send + * to the nic when SK_BPF_CB_TX_TIMESTAMPING + * feature is on. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect -- cgit v1.2.3 From 2deaf7f42b8c551e84da20483ca2d4a65c3623b3 Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 20 Feb 2025 15:29:36 +0800 Subject: bpf: Add BPF_SOCK_OPS_TSTAMP_SND_HW_CB callback Support hw SCM_TSTAMP_SND case for bpf timestamping. Add a new sock_ops callback, BPF_SOCK_OPS_TSTAMP_SND_HW_CB. This callback will occur at the same timestamping point as the user space's hardware SCM_TSTAMP_SND. The BPF program can use it to get the same SCM_TSTAMP_SND timestamp without modifying the user-space application. To avoid increasing the code complexity, replace SKBTX_HW_TSTAMP with SKBTX_HW_TSTAMP_NOBPF instead of changing numerous callers from driver side using SKBTX_HW_TSTAMP. The new definition of SKBTX_HW_TSTAMP means the combination tests of socket timestamping and bpf timestamping. After this patch, drivers can work under the bpf timestamping. Considering some drivers don't assign the skb with hardware timestamp, this patch does the assignment and then BPF program can acquire the hwstamp from skb directly. Signed-off-by: Jason Xing Signed-off-by: Martin KaFai Lau Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20250220072940.99994-9-kerneljasonxing@gmail.com --- tools/include/uapi/linux/bpf.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index abe8d6c30dae..72045c242396 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -7040,6 +7040,10 @@ enum { * to the nic when SK_BPF_CB_TX_TIMESTAMPING * feature is on. */ + BPF_SOCK_OPS_TSTAMP_SND_HW_CB, /* Called in hardware phase when + * SK_BPF_CB_TX_TIMESTAMPING feature + * is on. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect -- cgit v1.2.3 From b3b81e6b009dd8f85cd3b9c65eb492249c2649a8 Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 20 Feb 2025 15:29:37 +0800 Subject: bpf: Add BPF_SOCK_OPS_TSTAMP_ACK_CB callback Support the ACK case for bpf timestamping. Add a new sock_ops callback, BPF_SOCK_OPS_TSTAMP_ACK_CB. This callback will occur at the same timestamping point as the user space's SCM_TSTAMP_ACK. The BPF program can use it to get the same SCM_TSTAMP_ACK timestamp without modifying the user-space application. This patch extends txstamp_ack to two bits: 1 stands for SO_TIMESTAMPING mode, 2 bpf extension. Signed-off-by: Jason Xing Signed-off-by: Martin KaFai Lau Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20250220072940.99994-10-kerneljasonxing@gmail.com --- tools/include/uapi/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 72045c242396..cc10104f34a0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -7044,6 +7044,11 @@ enum { * SK_BPF_CB_TX_TIMESTAMPING feature * is on. */ + BPF_SOCK_OPS_TSTAMP_ACK_CB, /* Called when all the skbs in the + * same sendmsg call are acked + * when SK_BPF_CB_TX_TIMESTAMPING + * feature is on. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect -- cgit v1.2.3 From c9525d240c8117de35171ae705058ddf9667be27 Mon Sep 17 00:00:00 2001 From: Jason Xing Date: Thu, 20 Feb 2025 15:29:38 +0800 Subject: bpf: Add BPF_SOCK_OPS_TSTAMP_SENDMSG_CB callback This patch introduces a new callback in tcp_tx_timestamp() to correlate tcp_sendmsg timestamp with timestamps from other tx timestamping callbacks (e.g., SND/SW/ACK). Without this patch, BPF program wouldn't know which timestamps belong to which flow because of no socket lock protection. This new callback is inserted in tcp_tx_timestamp() to address this issue because tcp_tx_timestamp() still owns the same socket lock with tcp_sendmsg_locked() in the meanwhile tcp_tx_timestamp() initializes the timestamping related fields for the skb, especially tskey. The tskey is the bridge to do the correlation. For TCP, BPF program hooks the beginning of tcp_sendmsg_locked() and then stores the sendmsg timestamp at the bpf_sk_storage, correlating this timestamp with its tskey that are later used in other sending timestamping callbacks. Signed-off-by: Jason Xing Signed-off-by: Martin KaFai Lau Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20250220072940.99994-11-kerneljasonxing@gmail.com --- tools/include/uapi/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index cc10104f34a0..defa5bb881f4 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -7049,6 +7049,11 @@ enum { * when SK_BPF_CB_TX_TIMESTAMPING * feature is on. */ + BPF_SOCK_OPS_TSTAMP_SENDMSG_CB, /* Called when every sendmsg syscall + * is triggered. It's used to correlate + * sendmsg timestamp with corresponding + * tskey. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect -- cgit v1.2.3 From ca4419f15abd19ba8be1e109661b60f9f5b6c9f0 Mon Sep 17 00:00:00 2001 From: Song Yoong Siang Date: Sun, 16 Feb 2025 17:34:26 +0800 Subject: xsk: Add launch time hardware offload support to XDP Tx metadata Extend the XDP Tx metadata framework so that user can requests launch time hardware offload, where the Ethernet device will schedule the packet for transmission at a pre-determined time called launch time. The value of launch time is communicated from user space to Ethernet driver via launch_time field of struct xsk_tx_metadata. Suggested-by: Stanislav Fomichev Signed-off-by: Song Yoong Siang Signed-off-by: Martin KaFai Lau Acked-by: Stanislav Fomichev Acked-by: Jakub Kicinski Link: https://patch.msgid.link/20250216093430.957880-2-yoong.siang.song@intel.com --- tools/include/uapi/linux/if_xdp.h | 10 ++++++++++ tools/include/uapi/linux/netdev.h | 3 +++ 2 files changed, 13 insertions(+) (limited to 'tools/include/uapi/linux') diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index 42ec5ddaab8d..42869770776e 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -127,6 +127,12 @@ struct xdp_options { */ #define XDP_TXMD_FLAGS_CHECKSUM (1 << 1) +/* Request launch time hardware offload. The device will schedule the packet for + * transmission at a pre-determined time called launch time. The value of + * launch time is communicated via launch_time field of struct xsk_tx_metadata. + */ +#define XDP_TXMD_FLAGS_LAUNCH_TIME (1 << 2) + /* AF_XDP offloads request. 'request' union member is consumed by the driver * when the packet is being transmitted. 'completion' union member is * filled by the driver when the transmit completion arrives. @@ -142,6 +148,10 @@ struct xsk_tx_metadata { __u16 csum_start; /* Offset from csum_start where checksum should be stored. */ __u16 csum_offset; + + /* XDP_TXMD_FLAGS_LAUNCH_TIME */ + /* Launch time in nanosecond against the PTP HW Clock */ + __u64 launch_time; } request; struct { diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 6c6ee183802d..b97ff8bbb0c6 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -59,10 +59,13 @@ enum netdev_xdp_rx_metadata { * by the driver. * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the * driver. + * @NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO: Launch time HW offload is supported + * by the driver. */ enum netdev_xsk_flags { NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1, NETDEV_XSK_FLAGS_TX_CHECKSUM = 2, + NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO = 4, }; enum netdev_queue_type { -- cgit v1.2.3