From 3efd7ab46d0aebc3e567a9846e79a98dbad3291c Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Tue, 10 Sep 2024 17:14:46 +0000 Subject: net: netdev netlink api to bind dma-buf to a net device API takes the dma-buf fd as input, and binds it to the netdevice. The user can specify the rx queues to bind the dma-buf to. Suggested-by: Stanislav Fomichev Signed-off-by: Mina Almasry Reviewed-by: Donald Hunter Reviewed-by: Jakub Kicinski Link: https://patch.msgid.link/20240910171458.219195-3-almasrymina@google.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/netdev.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/uapi/linux/netdev.h') diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 43742ac5b00d..91bf3ecc5f1d 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -173,6 +173,16 @@ enum { NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) }; +enum { + NETDEV_A_DMABUF_IFINDEX = 1, + NETDEV_A_DMABUF_QUEUES, + NETDEV_A_DMABUF_FD, + NETDEV_A_DMABUF_ID, + + __NETDEV_A_DMABUF_MAX, + NETDEV_A_DMABUF_MAX = (__NETDEV_A_DMABUF_MAX - 1) +}; + enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, @@ -186,6 +196,7 @@ enum { NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, NETDEV_CMD_QSTATS_GET, + NETDEV_CMD_BIND_RX, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) -- cgit v1.2.3 From d0caf9876a1c9f844307effb598ad1312d9e0025 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Tue, 10 Sep 2024 17:14:57 +0000 Subject: netdev: add dmabuf introspection Add dmabuf information to page_pool stats: $ ./cli.py --spec ../netlink/specs/netdev.yaml --dump page-pool-get ... {'dmabuf': 10, 'id': 456, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 455, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 454, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 453, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 452, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 451, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 450, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, {'dmabuf': 10, 'id': 449, 'ifindex': 3, 'inflight': 1023, 'inflight-mem': 4190208}, And queue stats: $ ./cli.py --spec ../netlink/specs/netdev.yaml --dump queue-get ... {'dmabuf': 10, 'id': 8, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 9, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 10, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 11, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 12, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 13, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 14, 'ifindex': 3, 'type': 'rx'}, {'dmabuf': 10, 'id': 15, 'ifindex': 3, 'type': 'rx'}, Suggested-by: Jakub Kicinski Signed-off-by: Mina Almasry Reviewed-by: Jakub Kicinski Link: https://patch.msgid.link/20240910171458.219195-14-almasrymina@google.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 10 ++++++++++ include/uapi/linux/netdev.h | 2 ++ net/core/netdev-genl.c | 7 +++++++ net/core/page_pool_user.c | 5 +++++ tools/include/uapi/linux/netdev.h | 2 ++ 5 files changed, 26 insertions(+) (limited to 'include/uapi/linux/netdev.h') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 0c747530c275..08412c279297 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -167,6 +167,10 @@ attribute-sets: "re-attached", they are just waiting to disappear. Attribute is absent if Page Pool has not been detached, and can still be used to allocate new memory. + - + name: dmabuf + doc: ID of the dmabuf this page-pool is attached to. + type: u32 - name: page-pool-info subset-of: page-pool @@ -268,6 +272,10 @@ attribute-sets: name: napi-id doc: ID of the NAPI instance which services this queue. type: u32 + - + name: dmabuf + doc: ID of the dmabuf attached to this queue, if any. + type: u32 - name: qstats @@ -543,6 +551,7 @@ operations: - inflight - inflight-mem - detach-time + - dmabuf dump: reply: *pp-reply config-cond: page-pool @@ -607,6 +616,7 @@ operations: - type - napi-id - ifindex + - dmabuf dump: request: attributes: diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 91bf3ecc5f1d..7c308f04e7a0 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -93,6 +93,7 @@ enum { NETDEV_A_PAGE_POOL_INFLIGHT, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, NETDEV_A_PAGE_POOL_DETACH_TIME, + NETDEV_A_PAGE_POOL_DMABUF, __NETDEV_A_PAGE_POOL_MAX, NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) @@ -131,6 +132,7 @@ enum { NETDEV_A_QUEUE_IFINDEX, NETDEV_A_QUEUE_TYPE, NETDEV_A_QUEUE_NAPI_ID, + NETDEV_A_QUEUE_DMABUF, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 9153a8ab0cf8..1cb954f2d39e 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -295,6 +295,7 @@ static int netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) { + struct net_devmem_dmabuf_binding *binding; struct netdev_rx_queue *rxq; struct netdev_queue *txq; void *hdr; @@ -314,6 +315,12 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID, rxq->napi->napi_id)) goto nla_put_failure; + + binding = rxq->mp_params.mp_priv; + if (binding && + nla_put_u32(rsp, NETDEV_A_QUEUE_DMABUF, binding->id)) + goto nla_put_failure; + break; case NETDEV_QUEUE_TYPE_TX: txq = netdev_get_tx_queue(netdev, q_idx); diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index cd6267ba6fa3..48335766c1bf 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -9,6 +9,7 @@ #include #include +#include "devmem.h" #include "page_pool_priv.h" #include "netdev-genl-gen.h" @@ -213,6 +214,7 @@ static int page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, const struct genl_info *info) { + struct net_devmem_dmabuf_binding *binding = pool->mp_priv; size_t inflight, refsz; void *hdr; @@ -242,6 +244,9 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, pool->user.detach_time)) goto err_cancel; + if (binding && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_DMABUF, binding->id)) + goto err_cancel; + genlmsg_end(rsp, hdr); return 0; diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 91bf3ecc5f1d..7c308f04e7a0 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -93,6 +93,7 @@ enum { NETDEV_A_PAGE_POOL_INFLIGHT, NETDEV_A_PAGE_POOL_INFLIGHT_MEM, NETDEV_A_PAGE_POOL_DETACH_TIME, + NETDEV_A_PAGE_POOL_DMABUF, __NETDEV_A_PAGE_POOL_MAX, NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1) @@ -131,6 +132,7 @@ enum { NETDEV_A_QUEUE_IFINDEX, NETDEV_A_QUEUE_TYPE, NETDEV_A_QUEUE_NAPI_ID, + NETDEV_A_QUEUE_DMABUF, __NETDEV_A_QUEUE_MAX, NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1) -- cgit v1.2.3 From 516010460011ae74ac3b7383cf90ed27e2711cd6 Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Fri, 11 Oct 2024 18:44:57 +0000 Subject: netdev-genl: Dump napi_defer_hard_irqs Support dumping defer_hard_irqs for a NAPI ID. Signed-off-by: Joe Damato Reviewed-by: Eric Dumazet Reviewed-by: Jakub Kicinski Link: https://patch.msgid.link/20241011184527.16393-3-jdamato@fastly.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 8 ++++++++ include/uapi/linux/netdev.h | 1 + net/core/netdev-genl.c | 6 ++++++ tools/include/uapi/linux/netdev.h | 1 + 4 files changed, 16 insertions(+) (limited to 'include/uapi/linux/netdev.h') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 08412c279297..585e87ec3c16 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -248,6 +248,13 @@ attribute-sets: threaded mode. If NAPI is not in threaded mode (i.e. uses normal softirq context), the attribute will be absent. type: u32 + - + name: defer-hard-irqs + doc: The number of consecutive empty polls before IRQ deferral ends + and hardware IRQs are re-enabled. + type: u32 + checks: + max: s32-max - name: queue attributes: @@ -636,6 +643,7 @@ operations: - ifindex - irq - pid + - defer-hard-irqs dump: request: attributes: diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 7c308f04e7a0..13dc0b027e86 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -122,6 +122,7 @@ enum { NETDEV_A_NAPI_ID, NETDEV_A_NAPI_IRQ, NETDEV_A_NAPI_PID, + NETDEV_A_NAPI_DEFER_HARD_IRQS, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 358cba248796..f98e5d1d0d21 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -161,6 +161,7 @@ static int netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, const struct genl_info *info) { + u32 napi_defer_hard_irqs; void *hdr; pid_t pid; @@ -189,6 +190,11 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, goto nla_put_failure; } + napi_defer_hard_irqs = napi_get_defer_hard_irqs(napi); + if (nla_put_s32(rsp, NETDEV_A_NAPI_DEFER_HARD_IRQS, + napi_defer_hard_irqs)) + goto nla_put_failure; + genlmsg_end(rsp, hdr); return 0; diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 7c308f04e7a0..13dc0b027e86 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -122,6 +122,7 @@ enum { NETDEV_A_NAPI_ID, NETDEV_A_NAPI_IRQ, NETDEV_A_NAPI_PID, + NETDEV_A_NAPI_DEFER_HARD_IRQS, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) -- cgit v1.2.3 From 0137891e74576f77a7901718dc0ce08ca074ae74 Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Fri, 11 Oct 2024 18:44:59 +0000 Subject: netdev-genl: Dump gro_flush_timeout Support dumping gro_flush_timeout for a NAPI ID. Signed-off-by: Joe Damato Reviewed-by: Jakub Kicinski Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20241011184527.16393-5-jdamato@fastly.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 9 +++++++++ include/uapi/linux/netdev.h | 1 + net/core/netdev-genl.c | 6 ++++++ tools/include/uapi/linux/netdev.h | 1 + 4 files changed, 17 insertions(+) (limited to 'include/uapi/linux/netdev.h') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 585e87ec3c16..7b47454c51dd 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -255,6 +255,14 @@ attribute-sets: type: u32 checks: max: s32-max + - + name: gro-flush-timeout + doc: The timeout, in nanoseconds, of when to trigger the NAPI watchdog + timer which schedules NAPI processing. Additionally, a non-zero + value will also prevent GRO from flushing recent super-frames at + the end of a NAPI cycle. This may add receive latency in exchange + for reducing the number of frames processed by the network stack. + type: uint - name: queue attributes: @@ -644,6 +652,7 @@ operations: - irq - pid - defer-hard-irqs + - gro-flush-timeout dump: request: attributes: diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 13dc0b027e86..cacd33359c76 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -123,6 +123,7 @@ enum { NETDEV_A_NAPI_IRQ, NETDEV_A_NAPI_PID, NETDEV_A_NAPI_DEFER_HARD_IRQS, + NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index f98e5d1d0d21..ac19f2e6cfbe 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -161,6 +161,7 @@ static int netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, const struct genl_info *info) { + unsigned long gro_flush_timeout; u32 napi_defer_hard_irqs; void *hdr; pid_t pid; @@ -195,6 +196,11 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, napi_defer_hard_irqs)) goto nla_put_failure; + gro_flush_timeout = napi_get_gro_flush_timeout(napi); + if (nla_put_uint(rsp, NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, + gro_flush_timeout)) + goto nla_put_failure; + genlmsg_end(rsp, hdr); return 0; diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 13dc0b027e86..cacd33359c76 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -123,6 +123,7 @@ enum { NETDEV_A_NAPI_IRQ, NETDEV_A_NAPI_PID, NETDEV_A_NAPI_DEFER_HARD_IRQS, + NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) -- cgit v1.2.3 From 1287c1ae0fc227e5acef11a539eb4e75646e31c7 Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Fri, 11 Oct 2024 18:45:01 +0000 Subject: netdev-genl: Support setting per-NAPI config values Add support to set per-NAPI defer_hard_irqs and gro_flush_timeout. Signed-off-by: Joe Damato Reviewed-by: Jakub Kicinski Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20241011184527.16393-7-jdamato@fastly.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 11 ++++++++ include/uapi/linux/netdev.h | 1 + net/core/netdev-genl-gen.c | 18 +++++++++++++ net/core/netdev-genl-gen.h | 1 + net/core/netdev-genl.c | 45 +++++++++++++++++++++++++++++++++ tools/include/uapi/linux/netdev.h | 1 + 6 files changed, 77 insertions(+) (limited to 'include/uapi/linux/netdev.h') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 7b47454c51dd..f9cb97d6106c 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -693,6 +693,17 @@ operations: reply: attributes: - id + - + name: napi-set + doc: Set configurable NAPI instance settings. + attribute-set: napi + flags: [ admin-perm ] + do: + request: + attributes: + - id + - defer-hard-irqs + - gro-flush-timeout kernel-family: headers: [ "linux/list.h"] diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index cacd33359c76..e3ebb49f60d2 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -201,6 +201,7 @@ enum { NETDEV_CMD_NAPI_GET, NETDEV_CMD_QSTATS_GET, NETDEV_CMD_BIND_RX, + NETDEV_CMD_NAPI_SET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index b28424ae06d5..e197bd84997c 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -22,6 +22,10 @@ static const struct netlink_range_validation netdev_a_page_pool_ifindex_range = .max = 2147483647ULL, }; +static const struct netlink_range_validation netdev_a_napi_defer_hard_irqs_range = { + .max = 2147483647ULL, +}; + /* Common nested types */ const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1] = { [NETDEV_A_PAGE_POOL_ID] = NLA_POLICY_FULL_RANGE(NLA_UINT, &netdev_a_page_pool_id_range), @@ -87,6 +91,13 @@ static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1] [NETDEV_A_DMABUF_QUEUES] = NLA_POLICY_NESTED(netdev_queue_id_nl_policy), }; +/* NETDEV_CMD_NAPI_SET - do */ +static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT + 1] = { + [NETDEV_A_NAPI_ID] = { .type = NLA_U32, }, + [NETDEV_A_NAPI_DEFER_HARD_IRQS] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_napi_defer_hard_irqs_range), + [NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT] = { .type = NLA_UINT, }, +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -171,6 +182,13 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_DMABUF_FD, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, + { + .cmd = NETDEV_CMD_NAPI_SET, + .doit = netdev_nl_napi_set_doit, + .policy = netdev_napi_set_nl_policy, + .maxattr = NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index 8cda334fd042..e09dd7539ff2 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -33,6 +33,7 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index ac19f2e6cfbe..b49c3b4e5fbe 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -303,6 +303,51 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) return err; } +static int +netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info) +{ + u64 gro_flush_timeout = 0; + u32 defer = 0; + + if (info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]) { + defer = nla_get_u32(info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]); + napi_set_defer_hard_irqs(napi, defer); + } + + if (info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]) { + gro_flush_timeout = nla_get_uint(info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]); + napi_set_gro_flush_timeout(napi, gro_flush_timeout); + } + + return 0; +} + +int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct napi_struct *napi; + unsigned int napi_id; + int err; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_NAPI_ID)) + return -EINVAL; + + napi_id = nla_get_u32(info->attrs[NETDEV_A_NAPI_ID]); + + rtnl_lock(); + + napi = napi_by_id(napi_id); + if (napi) { + err = netdev_nl_napi_set_config(napi, info); + } else { + NL_SET_BAD_ATTR(info->extack, info->attrs[NETDEV_A_NAPI_ID]); + err = -ENOENT; + } + + rtnl_unlock(); + + return err; +} + static int netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev, u32 q_idx, u32 q_type, const struct genl_info *info) diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index cacd33359c76..e3ebb49f60d2 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -201,6 +201,7 @@ enum { NETDEV_CMD_NAPI_GET, NETDEV_CMD_QSTATS_GET, NETDEV_CMD_BIND_RX, + NETDEV_CMD_NAPI_SET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) -- cgit v1.2.3 From 5dc51ec86df6e2214d8398079c1e31736593ab53 Mon Sep 17 00:00:00 2001 From: Martin Karsten Date: Sat, 9 Nov 2024 05:02:31 +0000 Subject: net: Add napi_struct parameter irq_suspend_timeout Add a per-NAPI IRQ suspension parameter, which can be get/set with netdev-genl. This patch doesn't change any behavior but prepares the code for other changes in the following commits which use irq_suspend_timeout as a timeout for IRQ suspension. Signed-off-by: Martin Karsten Co-developed-by: Joe Damato Signed-off-by: Joe Damato Tested-by: Joe Damato Tested-by: Martin Karsten Acked-by: Stanislav Fomichev Reviewed-by: Sridhar Samudrala Link: https://patch.msgid.link/20241109050245.191288-2-jdamato@fastly.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/netdev.yaml | 7 +++++++ include/linux/netdevice.h | 2 ++ include/uapi/linux/netdev.h | 1 + net/core/dev.c | 2 ++ net/core/dev.h | 25 +++++++++++++++++++++++++ net/core/netdev-genl-gen.c | 5 +++-- net/core/netdev-genl.c | 12 ++++++++++++ tools/include/uapi/linux/netdev.h | 1 + 8 files changed, 53 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux/netdev.h') diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index f9cb97d6106c..cbb544bd6c84 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -263,6 +263,11 @@ attribute-sets: the end of a NAPI cycle. This may add receive latency in exchange for reducing the number of frames processed by the network stack. type: uint + - + name: irq-suspend-timeout + doc: The timeout, in nanoseconds, of how long to suspend irq + processing, if event polling finds events + type: uint - name: queue attributes: @@ -653,6 +658,7 @@ operations: - pid - defer-hard-irqs - gro-flush-timeout + - irq-suspend-timeout dump: request: attributes: @@ -704,6 +710,7 @@ operations: - id - defer-hard-irqs - gro-flush-timeout + - irq-suspend-timeout kernel-family: headers: [ "linux/list.h"] diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index df4483598628..0aae346d919e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -348,6 +348,7 @@ struct gro_list { */ struct napi_config { u64 gro_flush_timeout; + u64 irq_suspend_timeout; u32 defer_hard_irqs; unsigned int napi_id; }; @@ -384,6 +385,7 @@ struct napi_struct { struct hrtimer timer; struct task_struct *thread; unsigned long gro_flush_timeout; + unsigned long irq_suspend_timeout; u32 defer_hard_irqs; /* control-path-only fields follow */ struct list_head dev_list; diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index e3ebb49f60d2..e4be227d3ad6 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -124,6 +124,7 @@ enum { NETDEV_A_NAPI_PID, NETDEV_A_NAPI_DEFER_HARD_IRQS, NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, + NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) diff --git a/net/core/dev.c b/net/core/dev.c index 6a31152e4606..4d910872963f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6666,6 +6666,7 @@ static void napi_restore_config(struct napi_struct *n) { n->defer_hard_irqs = n->config->defer_hard_irqs; n->gro_flush_timeout = n->config->gro_flush_timeout; + n->irq_suspend_timeout = n->config->irq_suspend_timeout; /* a NAPI ID might be stored in the config, if so use it. if not, use * napi_hash_add to generate one for us. It will be saved to the config * in napi_disable. @@ -6680,6 +6681,7 @@ static void napi_save_config(struct napi_struct *n) { n->config->defer_hard_irqs = n->defer_hard_irqs; n->config->gro_flush_timeout = n->gro_flush_timeout; + n->config->irq_suspend_timeout = n->irq_suspend_timeout; n->config->napi_id = n->napi_id; napi_hash_del(n); } diff --git a/net/core/dev.h b/net/core/dev.h index 7881bced70a9..d043dee25a68 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -236,6 +236,31 @@ static inline void netdev_set_gro_flush_timeout(struct net_device *netdev, netdev->napi_config[i].gro_flush_timeout = timeout; } +/** + * napi_get_irq_suspend_timeout - get the irq_suspend_timeout + * @n: napi struct to get the irq_suspend_timeout from + * + * Return: the per-NAPI value of the irq_suspend_timeout field. + */ +static inline unsigned long +napi_get_irq_suspend_timeout(const struct napi_struct *n) +{ + return READ_ONCE(n->irq_suspend_timeout); +} + +/** + * napi_set_irq_suspend_timeout - set the irq_suspend_timeout for a napi + * @n: napi struct to set the irq_suspend_timeout + * @timeout: timeout value to set + * + * napi_set_irq_suspend_timeout sets the per-NAPI irq_suspend_timeout + */ +static inline void napi_set_irq_suspend_timeout(struct napi_struct *n, + unsigned long timeout) +{ + WRITE_ONCE(n->irq_suspend_timeout, timeout); +} + int rps_cpumask_housekeeping(struct cpumask *mask); #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL) diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index 21de7e10be16..a89cbd8d87c3 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -92,10 +92,11 @@ static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1] }; /* NETDEV_CMD_NAPI_SET - do */ -static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT + 1] = { +static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT + 1] = { [NETDEV_A_NAPI_ID] = { .type = NLA_U32, }, [NETDEV_A_NAPI_DEFER_HARD_IRQS] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_napi_defer_hard_irqs_range), [NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT] = { .type = NLA_UINT, }, + [NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT] = { .type = NLA_UINT, }, }; /* Ops table for netdev */ @@ -186,7 +187,7 @@ static const struct genl_split_ops netdev_nl_ops[] = { .cmd = NETDEV_CMD_NAPI_SET, .doit = netdev_nl_napi_set_doit, .policy = netdev_napi_set_nl_policy, - .maxattr = NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, + .maxattr = NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, }, }; diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index b49c3b4e5fbe..765ce7c9d73b 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -161,6 +161,7 @@ static int netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, const struct genl_info *info) { + unsigned long irq_suspend_timeout; unsigned long gro_flush_timeout; u32 napi_defer_hard_irqs; void *hdr; @@ -196,6 +197,11 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi, napi_defer_hard_irqs)) goto nla_put_failure; + irq_suspend_timeout = napi_get_irq_suspend_timeout(napi); + if (nla_put_uint(rsp, NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, + irq_suspend_timeout)) + goto nla_put_failure; + gro_flush_timeout = napi_get_gro_flush_timeout(napi); if (nla_put_uint(rsp, NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, gro_flush_timeout)) @@ -306,6 +312,7 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) static int netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info) { + u64 irq_suspend_timeout = 0; u64 gro_flush_timeout = 0; u32 defer = 0; @@ -314,6 +321,11 @@ netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info) napi_set_defer_hard_irqs(napi, defer); } + if (info->attrs[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT]) { + irq_suspend_timeout = nla_get_uint(info->attrs[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT]); + napi_set_irq_suspend_timeout(napi, irq_suspend_timeout); + } + if (info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]) { gro_flush_timeout = nla_get_uint(info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]); napi_set_gro_flush_timeout(napi, gro_flush_timeout); diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index e3ebb49f60d2..e4be227d3ad6 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -124,6 +124,7 @@ enum { NETDEV_A_NAPI_PID, NETDEV_A_NAPI_DEFER_HARD_IRQS, NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT, + NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT, __NETDEV_A_NAPI_MAX, NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1) -- cgit v1.2.3