From 0e942053e4dc42a760f48c1981f3239825430f15 Mon Sep 17 00:00:00 2001 From: Heng Qi Date: Fri, 21 Jun 2024 18:13:49 +0800 Subject: linux/dim: move useful macros to .h file Useful macros will be used effectively elsewhere. These will be utilized in subsequent patches. Signed-off-by: Heng Qi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240621101353.107425-2-hengqi@linux.alibaba.com Signed-off-by: Jakub Kicinski --- include/linux/dim.h | 7 +++++++ lib/dim/net_dim.c | 6 ------ 2 files changed, 7 insertions(+), 6 deletions(-) diff --git a/include/linux/dim.h b/include/linux/dim.h index f343bc9aa2ec..43398f5eade2 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -10,6 +10,13 @@ #include #include +/* Number of DIM profiles and period mode. */ +#define NET_DIM_PARAMS_NUM_PROFILES 5 +#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128 +#define NET_DIM_DEF_PROFILE_CQE 1 +#define NET_DIM_DEF_PROFILE_EQE 1 + /* * Number of events between DIM iterations. * Causes a moderation of the algorithm run. diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 4e32f7aaac86..67d5beb34dc3 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -11,12 +11,6 @@ * There are different set of profiles for RX/TX CQs. * Each profile size must be of NET_DIM_PARAMS_NUM_PROFILES */ -#define NET_DIM_PARAMS_NUM_PROFILES 5 -#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 -#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128 -#define NET_DIM_DEF_PROFILE_CQE 1 -#define NET_DIM_DEF_PROFILE_EQE 1 - #define NET_DIM_RX_EQE_PROFILES { \ {.usec = 1, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ {.usec = 8, .pkts = NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE,}, \ -- cgit v1.2.3 From b65e697a7c9e0ae28a6255257d8b9b3271960426 Mon Sep 17 00:00:00 2001 From: Heng Qi Date: Fri, 21 Jun 2024 18:13:50 +0800 Subject: dim: make DIMLIB dependent on NET DIMLIB's capabilities are supplied by the dim, net_dim, and rdma_dim objects, and dim's interfaces solely act as a base for net_dim and rdma_dim and are not explicitly used anywhere else. rdma_dim is utilized by the infiniband driver, while net_dim is for network devices, excluding the soc/fsl driver. In this patch, net_dim relies on some NET's interfaces, thus DIMLIB needs to explicitly depend on the NET Kconfig. The soc/fsl driver uses the functions provided by net_dim, so it also needs to depend on NET. Signed-off-by: Heng Qi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240621101353.107425-3-hengqi@linux.alibaba.com Signed-off-by: Jakub Kicinski --- drivers/soc/fsl/Kconfig | 2 +- lib/Kconfig | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/soc/fsl/Kconfig b/drivers/soc/fsl/Kconfig index fcec6ed83d5e..a1e0bc8c1757 100644 --- a/drivers/soc/fsl/Kconfig +++ b/drivers/soc/fsl/Kconfig @@ -22,7 +22,7 @@ config FSL_GUTS config FSL_MC_DPIO tristate "QorIQ DPAA2 DPIO driver" - depends on FSL_MC_BUS + depends on FSL_MC_BUS && NET select SOC_BUS select FSL_GUTS select DIMLIB diff --git a/lib/Kconfig b/lib/Kconfig index b0a76dff5c18..b38849af6f13 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -623,6 +623,7 @@ config SIGNATURE config DIMLIB tristate + depends on NET help Dynamic Interrupt Moderation library. Implements an algorithm for dynamically changing CQ moderation values -- cgit v1.2.3 From f750dfe825b904164688adeb147950e0e0c4d262 Mon Sep 17 00:00:00 2001 From: Heng Qi Date: Fri, 21 Jun 2024 18:13:51 +0800 Subject: ethtool: provide customized dim profile management The NetDIM library, currently leveraged by an array of NICs, delivers excellent acceleration benefits. Nevertheless, NICs vary significantly in their dim profile list prerequisites. Specifically, virtio-net backends may present diverse sw or hw device implementation, making a one-size-fits-all parameter list impractical. On Alibaba Cloud, the virtio DPU's performance under the default DIM profile falls short of expectations, partly due to a mismatch in parameter configuration. I also noticed that ice/idpf/ena and other NICs have customized profilelist or placed some restrictions on dim capabilities. Motivated by this, I tried adding new params for "ethtool -C" that provides a per-device control to modify and access a device's interrupt parameters. Usage ======== The target NIC is named ethx. Assume that ethx only declares support for rx profile setting (with DIM_PROFILE_RX flag set in profile_flags) and supports modification of usec and pkt fields. 1. Query the currently customized list of the device $ ethtool -c ethx ... rx-profile: {.usec = 1, .pkts = 256, .comps = n/a,}, {.usec = 8, .pkts = 256, .comps = n/a,}, {.usec = 64, .pkts = 256, .comps = n/a,}, {.usec = 128, .pkts = 256, .comps = n/a,}, {.usec = 256, .pkts = 256, .comps = n/a,} tx-profile: n/a 2. Tune $ ethtool -C ethx rx-profile 1,1,n_2,n,n_3,3,n_4,4,n_n,5,n "n" means do not modify this field. $ ethtool -c ethx ... rx-profile: {.usec = 1, .pkts = 1, .comps = n/a,}, {.usec = 2, .pkts = 256, .comps = n/a,}, {.usec = 3, .pkts = 3, .comps = n/a,}, {.usec = 4, .pkts = 4, .comps = n/a,}, {.usec = 256, .pkts = 5, .comps = n/a,} tx-profile: n/a 3. Hint If the device does not support some type of customized dim profiles, the corresponding "n/a" will display. If the "n/a" field is being modified, -EOPNOTSUPP will be reported. Signed-off-by: Heng Qi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240621101353.107425-4-hengqi@linux.alibaba.com Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/ethtool.yaml | 31 +++ Documentation/networking/ethtool-netlink.rst | 8 + Documentation/networking/net_dim.rst | 42 +++++ include/linux/dim.h | 58 ++++++ include/linux/ethtool.h | 4 +- include/linux/netdevice.h | 3 + include/uapi/linux/ethtool_netlink.h | 22 +++ lib/dim/net_dim.c | 70 +++++++ net/Kconfig | 1 + net/ethtool/coalesce.c | 273 ++++++++++++++++++++++++++- 10 files changed, 509 insertions(+), 3 deletions(-) diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 00dc61358be8..6c2ab3d1c22f 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -414,6 +414,26 @@ attribute-sets: name: combined-count type: u32 + - + name: irq-moderation + attributes: + - + name: usec + type: u32 + - + name: pkts + type: u32 + - + name: comps + type: u32 + - + name: profile + attributes: + - + name: irq-moderation + type: nest + multi-attr: true + nested-attributes: irq-moderation - name: coalesce attributes: @@ -502,6 +522,15 @@ attribute-sets: - name: tx-aggr-time-usecs type: u32 + - + name: rx-profile + type: nest + nested-attributes: profile + - + name: tx-profile + type: nest + nested-attributes: profile + - name: pause-stat attributes: @@ -1325,6 +1354,8 @@ operations: - tx-aggr-max-bytes - tx-aggr-max-frames - tx-aggr-time-usecs + - rx-profile + - tx-profile dump: *coalesce-get-op - name: coalesce-set diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 160bfb0ae8ba..7ec08e903bab 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -1033,6 +1033,8 @@ Kernel response contents: ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` u32 max aggr size, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` u32 max aggr packets, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx + ``ETHTOOL_A_COALESCE_RX_PROFILE`` nested profile of DIM, Rx + ``ETHTOOL_A_COALESCE_TX_PROFILE`` nested profile of DIM, Tx =========================================== ====== ======================= Attributes are only included in reply if their value is not zero or the @@ -1062,6 +1064,10 @@ block should be sent. This feature is mainly of interest for specific USB devices which does not cope well with frequent small-sized URBs transmissions. +``ETHTOOL_A_COALESCE_RX_PROFILE`` and ``ETHTOOL_A_COALESCE_TX_PROFILE`` refer +to DIM parameters, see `Generic Network Dynamic Interrupt Moderation (Net DIM) +`_. + COALESCE_SET ============ @@ -1098,6 +1104,8 @@ Request contents: ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES`` u32 max aggr size, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES`` u32 max aggr packets, Tx ``ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS`` u32 time (us), aggr, Tx + ``ETHTOOL_A_COALESCE_RX_PROFILE`` nested profile of DIM, Rx + ``ETHTOOL_A_COALESCE_TX_PROFILE`` nested profile of DIM, Tx =========================================== ====== ======================= Request is rejected if it attributes declared as unsupported by driver (i.e. diff --git a/Documentation/networking/net_dim.rst b/Documentation/networking/net_dim.rst index 3bed9fd95336..8908fd7b0a8d 100644 --- a/Documentation/networking/net_dim.rst +++ b/Documentation/networking/net_dim.rst @@ -169,6 +169,48 @@ usage is not complete but it should make the outline of the usage clear. ... } + +Tuning DIM +========== + +Net DIM serves a range of network devices and delivers excellent acceleration +benefits. Yet, it has been observed that some preset configurations of DIM may +not align seamlessly with the varying specifications of network devices, and +this discrepancy has been identified as a factor to the suboptimal performance +outcomes of DIM-enabled network devices, related to a mismatch in profiles. + +To address this issue, Net DIM introduces a per-device control to modify and +access a device's ``rx-profile`` and ``tx-profile`` parameters: +Assume that the target network device is named ethx, and ethx only declares +support for RX profile setting and supports modification of ``usec`` field +and ``pkts`` field (See the data structure: +:c:type:`struct dim_cq_moder `). + +You can use ethtool to modify the current RX DIM profile where all +values are 64:: + + $ ethtool -C ethx rx-profile 1,1,n_2,2,n_3,n,n_n,4,n_n,n,n + +``n`` means do not modify this field, and ``_`` separates structure +elements of the profile array. + +Querying the current profiles using:: + + $ ethtool -c ethx + ... + rx-profile: + {.usec = 1, .pkts = 1, .comps = n/a,}, + {.usec = 2, .pkts = 2, .comps = n/a,}, + {.usec = 3, .pkts = 64, .comps = n/a,}, + {.usec = 64, .pkts = 4, .comps = n/a,}, + {.usec = 64, .pkts = 64, .comps = n/a,} + tx-profile: n/a + +If the network device does not support specific fields of DIM profiles, +the corresponding ``n/a`` will display. If the ``n/a`` field is being +modified, error messages will be reported. + + Dynamic Interrupt Moderation (DIM) library API ============================================== diff --git a/include/linux/dim.h b/include/linux/dim.h index 43398f5eade2..e0f39bd85432 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -10,6 +10,8 @@ #include #include +struct net_device; + /* Number of DIM profiles and period mode. */ #define NET_DIM_PARAMS_NUM_PROFILES 5 #define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 @@ -45,12 +47,45 @@ * @pkts: CQ packet counter suggestion (by DIM) * @comps: Completion counter * @cq_period_mode: CQ period count mode (from CQE/EQE) + * @rcu: for asynchronous kfree_rcu */ struct dim_cq_moder { u16 usec; u16 pkts; u16 comps; u8 cq_period_mode; + struct rcu_head rcu; +}; + +#define DIM_PROFILE_RX BIT(0) /* support rx profile modification */ +#define DIM_PROFILE_TX BIT(1) /* support tx profile modification */ + +#define DIM_COALESCE_USEC BIT(0) /* support usec field modification */ +#define DIM_COALESCE_PKTS BIT(1) /* support pkts field modification */ +#define DIM_COALESCE_COMPS BIT(2) /* support comps field modification */ + +/** + * struct dim_irq_moder - Structure for irq moderation information. + * Used to collect irq moderation related information. + * + * @profile_flags: DIM_PROFILE_* + * @coal_flags: DIM_COALESCE_* for Rx and Tx + * @dim_rx_mode: Rx DIM period count mode: CQE or EQE + * @dim_tx_mode: Tx DIM period count mode: CQE or EQE + * @rx_profile: DIM profile list for Rx + * @tx_profile: DIM profile list for Tx + * @rx_dim_work: Rx DIM worker scheduled by net_dim() + * @tx_dim_work: Tx DIM worker scheduled by net_dim() + */ +struct dim_irq_moder { + u8 profile_flags; + u8 coal_flags; + u8 dim_rx_mode; + u8 dim_tx_mode; + struct dim_cq_moder __rcu *rx_profile; + struct dim_cq_moder __rcu *tx_profile; + void (*rx_dim_work)(struct work_struct *work); + void (*tx_dim_work)(struct work_struct *work); }; /** @@ -198,6 +233,29 @@ enum dim_step_result { DIM_ON_EDGE, }; +/** + * net_dim_init_irq_moder - collect information to initialize irq moderation + * @dev: target network device + * @profile_flags: Rx or Tx profile modification capability + * @coal_flags: irq moderation params flags + * @rx_mode: CQ period mode for Rx + * @tx_mode: CQ period mode for Tx + * @rx_dim_work: Rx worker called after dim decision + * @tx_dim_work: Tx worker called after dim decision + * + * Return: 0 on success or a negative error code. + */ +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)); + +/** + * net_dim_free_irq_moder - free fields for irq moderation + * @dev: target network device + */ +void net_dim_free_irq_moder(struct net_device *dev); + /** * dim_on_top - check if current state is a good place to stop (top location) * @dim: DIM context diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 6fd9107d3cc0..959196af7f5a 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -284,7 +284,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, #define ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES BIT(24) #define ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES BIT(25) #define ETHTOOL_COALESCE_TX_AGGR_TIME_USECS BIT(26) -#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(26, 0) +#define ETHTOOL_COALESCE_RX_PROFILE BIT(27) +#define ETHTOOL_COALESCE_TX_PROFILE BIT(28) +#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(28, 0) #define ETHTOOL_COALESCE_USECS \ (ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4e81660b4462..cc18acd3c58b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2402,6 +2402,9 @@ struct net_device { /** @page_pools: page pools created for this netdevice */ struct hlist_head page_pools; #endif + + /** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */ + struct dim_irq_moder *irq_moder; }; #define to_net_dev(d) container_of(d, struct net_device, dev) diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index b49b804b9495..d15856c7e001 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -415,12 +415,34 @@ enum { ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES, /* u32 */ ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES, /* u32 */ ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS, /* u32 */ + /* nest - _A_PROFILE_IRQ_MODERATION */ + ETHTOOL_A_COALESCE_RX_PROFILE, + /* nest - _A_PROFILE_IRQ_MODERATION */ + ETHTOOL_A_COALESCE_TX_PROFILE, /* add new constants above here */ __ETHTOOL_A_COALESCE_CNT, ETHTOOL_A_COALESCE_MAX = (__ETHTOOL_A_COALESCE_CNT - 1) }; +enum { + ETHTOOL_A_PROFILE_UNSPEC, + /* nest, _A_IRQ_MODERATION_* */ + ETHTOOL_A_PROFILE_IRQ_MODERATION, + __ETHTOOL_A_PROFILE_CNT, + ETHTOOL_A_PROFILE_MAX = (__ETHTOOL_A_PROFILE_CNT - 1) +}; + +enum { + ETHTOOL_A_IRQ_MODERATION_UNSPEC, + ETHTOOL_A_IRQ_MODERATION_USEC, /* u32 */ + ETHTOOL_A_IRQ_MODERATION_PKTS, /* u32 */ + ETHTOOL_A_IRQ_MODERATION_COMPS, /* u32 */ + + __ETHTOOL_A_IRQ_MODERATION_CNT, + ETHTOOL_A_IRQ_MODERATION_MAX = (__ETHTOOL_A_IRQ_MODERATION_CNT - 1) +}; + /* PAUSE */ enum { diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 67d5beb34dc3..0cd41277c7a3 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -4,6 +4,7 @@ */ #include +#include /* * Net DIM profiles: @@ -95,6 +96,75 @@ net_dim_get_def_tx_moderation(u8 cq_period_mode) } EXPORT_SYMBOL(net_dim_get_def_tx_moderation); +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)) +{ + struct dim_cq_moder *rxp = NULL, *txp; + struct dim_irq_moder *moder; + int len; + + dev->irq_moder = kzalloc(sizeof(*dev->irq_moder), GFP_KERNEL); + if (!dev->irq_moder) + return -ENOMEM; + + moder = dev->irq_moder; + len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*moder->rx_profile); + + moder->coal_flags = coal_flags; + moder->profile_flags = profile_flags; + + if (profile_flags & DIM_PROFILE_RX) { + moder->rx_dim_work = rx_dim_work; + moder->dim_rx_mode = rx_mode; + rxp = kmemdup(rx_profile[rx_mode], len, GFP_KERNEL); + if (!rxp) + goto free_moder; + + rcu_assign_pointer(moder->rx_profile, rxp); + } + + if (profile_flags & DIM_PROFILE_TX) { + moder->tx_dim_work = tx_dim_work; + moder->dim_tx_mode = tx_mode; + txp = kmemdup(tx_profile[tx_mode], len, GFP_KERNEL); + if (!txp) + goto free_rxp; + + rcu_assign_pointer(moder->tx_profile, txp); + } + + return 0; + +free_rxp: + kfree(rxp); +free_moder: + kfree(moder); + return -ENOMEM; +} +EXPORT_SYMBOL(net_dim_init_irq_moder); + +/* RTNL lock is held. */ +void net_dim_free_irq_moder(struct net_device *dev) +{ + struct dim_cq_moder *rxp, *txp; + + if (!dev->irq_moder) + return; + + rxp = rtnl_dereference(dev->irq_moder->rx_profile); + txp = rtnl_dereference(dev->irq_moder->tx_profile); + + rcu_assign_pointer(dev->irq_moder->rx_profile, NULL); + rcu_assign_pointer(dev->irq_moder->tx_profile, NULL); + + kfree_rcu(rxp, rcu); + kfree_rcu(txp, rcu); + kfree(dev->irq_moder); +} +EXPORT_SYMBOL(net_dim_free_irq_moder); + static int net_dim_step(struct dim *dim) { if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) diff --git a/net/Kconfig b/net/Kconfig index 9fe65fa26e48..d27d0deac0bf 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -508,6 +508,7 @@ config FAILOVER config ETHTOOL_NETLINK bool "Netlink interface for ethtool" + select DIMLIB default y help An alternative userspace interface for ethtool based on generic diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c index 83112c1a71ae..759b16e3d134 100644 --- a/net/ethtool/coalesce.c +++ b/net/ethtool/coalesce.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include #include "netlink.h" #include "common.h" @@ -82,6 +83,14 @@ static int coalesce_prepare_data(const struct ethnl_req_info *req_base, static int coalesce_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { + int modersz = nla_total_size(0) + /* _PROFILE_IRQ_MODERATION, nest */ + nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_USEC */ + nla_total_size(sizeof(u32)) + /* _IRQ_MODERATION_PKTS */ + nla_total_size(sizeof(u32)); /* _IRQ_MODERATION_COMPS */ + + int total_modersz = nla_total_size(0) + /* _{R,T}X_PROFILE, nest */ + modersz * NET_DIM_PARAMS_NUM_PROFILES; + return nla_total_size(sizeof(u32)) + /* _RX_USECS */ nla_total_size(sizeof(u32)) + /* _RX_MAX_FRAMES */ nla_total_size(sizeof(u32)) + /* _RX_USECS_IRQ */ @@ -108,7 +117,8 @@ static int coalesce_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u8)) + /* _USE_CQE_MODE_RX */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_BYTES */ nla_total_size(sizeof(u32)) + /* _TX_AGGR_MAX_FRAMES */ - nla_total_size(sizeof(u32)); /* _TX_AGGR_TIME_USECS */ + nla_total_size(sizeof(u32)) + /* _TX_AGGR_TIME_USECS */ + total_modersz * 2; /* _{R,T}X_PROFILE */ } static bool coalesce_put_u32(struct sk_buff *skb, u16 attr_type, u32 val, @@ -127,14 +137,84 @@ static bool coalesce_put_bool(struct sk_buff *skb, u16 attr_type, u32 val, return nla_put_u8(skb, attr_type, !!val); } +/** + * coalesce_put_profile - fill reply with a nla nest with four child nla nests. + * @skb: socket buffer the message is stored in + * @attr_type: nest attr type ETHTOOL_A_COALESCE_*X_PROFILE + * @profile: data passed to userspace + * @coal_flags: modifiable parameters supported by the driver + * + * Put a dim profile nest attribute. Refer to ETHTOOL_A_PROFILE_IRQ_MODERATION. + * + * Return: 0 on success or a negative error code. + */ +static int coalesce_put_profile(struct sk_buff *skb, u16 attr_type, + const struct dim_cq_moder *profile, + u8 coal_flags) +{ + struct nlattr *profile_attr, *moder_attr; + int i, ret; + + if (!profile || !coal_flags) + return 0; + + profile_attr = nla_nest_start(skb, attr_type); + if (!profile_attr) + return -EMSGSIZE; + + for (i = 0; i < NET_DIM_PARAMS_NUM_PROFILES; i++) { + moder_attr = nla_nest_start(skb, + ETHTOOL_A_PROFILE_IRQ_MODERATION); + if (!moder_attr) { + ret = -EMSGSIZE; + goto cancel_profile; + } + + if (coal_flags & DIM_COALESCE_USEC) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_USEC, + profile[i].usec); + if (ret) + goto cancel_moder; + } + + if (coal_flags & DIM_COALESCE_PKTS) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_PKTS, + profile[i].pkts); + if (ret) + goto cancel_moder; + } + + if (coal_flags & DIM_COALESCE_COMPS) { + ret = nla_put_u32(skb, ETHTOOL_A_IRQ_MODERATION_COMPS, + profile[i].comps); + if (ret) + goto cancel_moder; + } + + nla_nest_end(skb, moder_attr); + } + + nla_nest_end(skb, profile_attr); + + return 0; + +cancel_moder: + nla_nest_cancel(skb, moder_attr); +cancel_profile: + nla_nest_cancel(skb, profile_attr); + return ret; +} + static int coalesce_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct coalesce_reply_data *data = COALESCE_REPDATA(reply_base); const struct kernel_ethtool_coalesce *kcoal = &data->kernel_coalesce; + struct dim_irq_moder *moder = req_base->dev->irq_moder; const struct ethtool_coalesce *coal = &data->coalesce; u32 supported = data->supported_params; + int ret = 0; if (coalesce_put_u32(skb, ETHTOOL_A_COALESCE_RX_USECS, coal->rx_coalesce_usecs, supported) || @@ -192,11 +272,41 @@ static int coalesce_fill_reply(struct sk_buff *skb, kcoal->tx_aggr_time_usecs, supported)) return -EMSGSIZE; - return 0; + if (!moder) + return 0; + + rcu_read_lock(); + if (moder->profile_flags & DIM_PROFILE_RX) { + ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_RX_PROFILE, + rcu_dereference(moder->rx_profile), + moder->coal_flags); + if (ret) + goto out; + } + + if (moder->profile_flags & DIM_PROFILE_TX) + ret = coalesce_put_profile(skb, ETHTOOL_A_COALESCE_TX_PROFILE, + rcu_dereference(moder->tx_profile), + moder->coal_flags); + +out: + rcu_read_unlock(); + return ret; } /* COALESCE_SET */ +static const struct nla_policy coalesce_irq_moderation_policy[] = { + [ETHTOOL_A_IRQ_MODERATION_USEC] = { .type = NLA_U32 }, + [ETHTOOL_A_IRQ_MODERATION_PKTS] = { .type = NLA_U32 }, + [ETHTOOL_A_IRQ_MODERATION_COMPS] = { .type = NLA_U32 }, +}; + +static const struct nla_policy coalesce_profile_policy[] = { + [ETHTOOL_A_PROFILE_IRQ_MODERATION] = + NLA_POLICY_NESTED(coalesce_irq_moderation_policy), +}; + const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), @@ -227,6 +337,10 @@ const struct nla_policy ethnl_coalesce_set_policy[] = { [ETHTOOL_A_COALESCE_TX_AGGR_MAX_BYTES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_MAX_FRAMES] = { .type = NLA_U32 }, [ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS] = { .type = NLA_U32 }, + [ETHTOOL_A_COALESCE_RX_PROFILE] = + NLA_POLICY_NESTED(coalesce_profile_policy), + [ETHTOOL_A_COALESCE_TX_PROFILE] = + NLA_POLICY_NESTED(coalesce_profile_policy), }; static int @@ -234,6 +348,7 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; + struct dim_irq_moder *irq_moder = req_info->dev->irq_moder; struct nlattr **tb = info->attrs; u32 supported_params; u16 a; @@ -243,6 +358,12 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, /* make sure that only supported parameters are present */ supported_params = ops->supported_coalesce_params; + if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_RX) + supported_params |= ETHTOOL_COALESCE_RX_PROFILE; + + if (irq_moder && irq_moder->profile_flags & DIM_PROFILE_TX) + supported_params |= ETHTOOL_COALESCE_TX_PROFILE; + for (a = ETHTOOL_A_COALESCE_RX_USECS; a < __ETHTOOL_A_COALESCE_CNT; a++) if (tb[a] && !(supported_params & attr_to_mask(a))) { NL_SET_ERR_MSG_ATTR(info->extack, tb[a], @@ -253,6 +374,138 @@ ethnl_set_coalesce_validate(struct ethnl_req_info *req_info, return 1; } +/** + * ethnl_update_irq_moder - update a specific field in the given profile + * @irq_moder: place that collects dim related information + * @irq_field: field in profile to modify + * @attr_type: attr type ETHTOOL_A_IRQ_MODERATION_* + * @tb: netlink attribute with new values or null + * @coal_bit: DIM_COALESCE_* bit from coal_flags + * @mod: pointer to bool for modification tracking + * @extack: netlink extended ack + * + * Return: 0 on success or a negative error code. + */ +static int ethnl_update_irq_moder(struct dim_irq_moder *irq_moder, + u16 *irq_field, u16 attr_type, + struct nlattr **tb, + u8 coal_bit, bool *mod, + struct netlink_ext_ack *extack) +{ + int ret = 0; + u32 val; + + if (!tb[attr_type]) + return 0; + + if (irq_moder->coal_flags & coal_bit) { + val = nla_get_u32(tb[attr_type]); + if (*irq_field == val) + return 0; + + *irq_field = val; + *mod = true; + } else { + NL_SET_BAD_ATTR(extack, tb[attr_type]); + ret = -EOPNOTSUPP; + } + + return ret; +} + +/** + * ethnl_update_profile - get a profile nest with child nests from userspace. + * @dev: netdevice to update the profile + * @dst: profile get from the driver and modified by ethnl_update_profile. + * @nests: nest attr ETHTOOL_A_COALESCE_*X_PROFILE to set profile. + * @mod: pointer to bool for modification tracking + * @extack: Netlink extended ack + * + * Layout of nests: + * Nested ETHTOOL_A_COALESCE_*X_PROFILE attr + * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr + * ETHTOOL_A_IRQ_MODERATION_USEC attr + * ETHTOOL_A_IRQ_MODERATION_PKTS attr + * ETHTOOL_A_IRQ_MODERATION_COMPS attr + * ... + * Nested ETHTOOL_A_PROFILE_IRQ_MODERATION attr + * ETHTOOL_A_IRQ_MODERATION_USEC attr + * ETHTOOL_A_IRQ_MODERATION_PKTS attr + * ETHTOOL_A_IRQ_MODERATION_COMPS attr + * + * Return: 0 on success or a negative error code. + */ +static int ethnl_update_profile(struct net_device *dev, + struct dim_cq_moder __rcu **dst, + const struct nlattr *nests, + bool *mod, + struct netlink_ext_ack *extack) +{ + int len_irq_moder = ARRAY_SIZE(coalesce_irq_moderation_policy); + struct nlattr *tb[ARRAY_SIZE(coalesce_irq_moderation_policy)]; + struct dim_irq_moder *irq_moder = dev->irq_moder; + struct dim_cq_moder *new_profile, *old_profile; + int ret, rem, i = 0, len; + struct nlattr *nest; + + if (!nests) + return 0; + + if (!*dst) + return -EOPNOTSUPP; + + old_profile = rtnl_dereference(*dst); + len = NET_DIM_PARAMS_NUM_PROFILES * sizeof(*old_profile); + new_profile = kmemdup(old_profile, len, GFP_KERNEL); + if (!new_profile) + return -ENOMEM; + + nla_for_each_nested_type(nest, ETHTOOL_A_PROFILE_IRQ_MODERATION, + nests, rem) { + ret = nla_parse_nested(tb, len_irq_moder - 1, nest, + coalesce_irq_moderation_policy, + extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].usec, + ETHTOOL_A_IRQ_MODERATION_USEC, + tb, DIM_COALESCE_USEC, + mod, extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].pkts, + ETHTOOL_A_IRQ_MODERATION_PKTS, + tb, DIM_COALESCE_PKTS, + mod, extack); + if (ret) + goto err_out; + + ret = ethnl_update_irq_moder(irq_moder, &new_profile[i].comps, + ETHTOOL_A_IRQ_MODERATION_COMPS, + tb, DIM_COALESCE_COMPS, + mod, extack); + if (ret) + goto err_out; + + i++; + } + + /* After the profile is modified, dim itself is a dynamic + * mechanism and will quickly fit to the appropriate + * coalescing parameters according to the new profile. + */ + rcu_assign_pointer(*dst, new_profile); + kfree_rcu(old_profile, rcu); + + return 0; + +err_out: + kfree(new_profile); + return ret; +} + static int __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, bool *dual_change) @@ -317,6 +570,22 @@ __ethnl_set_coalesce(struct ethnl_req_info *req_info, struct genl_info *info, ethnl_update_u32(&kernel_coalesce.tx_aggr_time_usecs, tb[ETHTOOL_A_COALESCE_TX_AGGR_TIME_USECS], &mod); + if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_RX) { + ret = ethnl_update_profile(dev, &dev->irq_moder->rx_profile, + tb[ETHTOOL_A_COALESCE_RX_PROFILE], + &mod, info->extack); + if (ret < 0) + return ret; + } + + if (dev->irq_moder && dev->irq_moder->profile_flags & DIM_PROFILE_TX) { + ret = ethnl_update_profile(dev, &dev->irq_moder->tx_profile, + tb[ETHTOOL_A_COALESCE_TX_PROFILE], + &mod, info->extack); + if (ret < 0) + return ret; + } + /* Update operation modes */ ethnl_update_bool32(&coalesce.use_adaptive_rx_coalesce, tb[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX], &mod_mode); -- cgit v1.2.3 From 13ba28c5cd047e272f9dbbeb5c62c403873d8987 Mon Sep 17 00:00:00 2001 From: Heng Qi Date: Fri, 21 Jun 2024 18:13:52 +0800 Subject: dim: add new interfaces for initialization and getting results DIM-related mode and work have been collected in one same place, so new interfaces are added to provide convenience. Signed-off-by: Heng Qi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240621101353.107425-5-hengqi@linux.alibaba.com Signed-off-by: Jakub Kicinski --- include/linux/dim.h | 48 +++++++++++++++++++++++++++++++++++++ lib/dim/net_dim.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 116 insertions(+) diff --git a/include/linux/dim.h b/include/linux/dim.h index e0f39bd85432..1b581ff25a15 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -256,6 +256,54 @@ int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, */ void net_dim_free_irq_moder(struct net_device *dev); +/** + * net_dim_setting - initialize DIM's cq mode and schedule worker + * @dev: target network device + * @dim: DIM context + * @is_tx: true indicates the tx direction, false indicates the rx direction + */ +void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx); + +/** + * net_dim_work_cancel - synchronously cancel dim's worker + * @dim: DIM context + */ +void net_dim_work_cancel(struct dim *dim); + +/** + * net_dim_get_rx_irq_moder - get DIM rx results based on profile_ix + * @dev: target network device + * @dim: DIM context + * + * Return: DIM irq moderation + */ +struct dim_cq_moder +net_dim_get_rx_irq_moder(struct net_device *dev, struct dim *dim); + +/** + * net_dim_get_tx_irq_moder - get DIM tx results based on profile_ix + * @dev: target network device + * @dim: DIM context + * + * Return: DIM irq moderation + */ +struct dim_cq_moder +net_dim_get_tx_irq_moder(struct net_device *dev, struct dim *dim); + +/** + * net_dim_set_rx_mode - set DIM rx cq mode + * @dev: target network device + * @rx_mode: target rx cq mode + */ +void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode); + +/** + * net_dim_set_tx_mode - set DIM tx cq mode + * @dev: target network device + * @tx_mode: target tx cq mode + */ +void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode); + /** * dim_on_top - check if current state is a good place to stop (top location) * @dim: DIM context diff --git a/lib/dim/net_dim.c b/lib/dim/net_dim.c index 0cd41277c7a3..d7e7028e9b19 100644 --- a/lib/dim/net_dim.c +++ b/lib/dim/net_dim.c @@ -165,6 +165,74 @@ void net_dim_free_irq_moder(struct net_device *dev) } EXPORT_SYMBOL(net_dim_free_irq_moder); +void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx) +{ + struct dim_irq_moder *irq_moder = dev->irq_moder; + + if (!irq_moder) + return; + + if (is_tx) { + INIT_WORK(&dim->work, irq_moder->tx_dim_work); + dim->mode = READ_ONCE(irq_moder->dim_tx_mode); + return; + } + + INIT_WORK(&dim->work, irq_moder->rx_dim_work); + dim->mode = READ_ONCE(irq_moder->dim_rx_mode); +} +EXPORT_SYMBOL(net_dim_setting); + +void net_dim_work_cancel(struct dim *dim) +{ + cancel_work_sync(&dim->work); +} +EXPORT_SYMBOL(net_dim_work_cancel); + +struct dim_cq_moder net_dim_get_rx_irq_moder(struct net_device *dev, + struct dim *dim) +{ + struct dim_cq_moder res, *profile; + + rcu_read_lock(); + profile = rcu_dereference(dev->irq_moder->rx_profile); + res = profile[dim->profile_ix]; + rcu_read_unlock(); + + res.cq_period_mode = dim->mode; + + return res; +} +EXPORT_SYMBOL(net_dim_get_rx_irq_moder); + +struct dim_cq_moder net_dim_get_tx_irq_moder(struct net_device *dev, + struct dim *dim) +{ + struct dim_cq_moder res, *profile; + + rcu_read_lock(); + profile = rcu_dereference(dev->irq_moder->tx_profile); + res = profile[dim->profile_ix]; + rcu_read_unlock(); + + res.cq_period_mode = dim->mode; + + return res; +} +EXPORT_SYMBOL(net_dim_get_tx_irq_moder); + +void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode) +{ + WRITE_ONCE(dev->irq_moder->dim_rx_mode, rx_mode); +} +EXPORT_SYMBOL(net_dim_set_rx_mode); + +void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode) +{ + WRITE_ONCE(dev->irq_moder->dim_tx_mode, tx_mode); +} +EXPORT_SYMBOL(net_dim_set_tx_mode); + static int net_dim_step(struct dim *dim) { if (dim->tired == (NET_DIM_PARAMS_NUM_PROFILES * 2)) -- cgit v1.2.3 From dcb67f6a9ead650360a60009ba8a68be385c2bde Mon Sep 17 00:00:00 2001 From: Heng Qi Date: Fri, 21 Jun 2024 18:13:53 +0800 Subject: virtio-net: support dim profile fine-tuning Virtio-net has different types of back-end device implementations. In order to effectively optimize the dim library's gains for different device implementations, let's use the new interface params to initialize and query dim results from a customized profile list. Signed-off-by: Heng Qi Reviewed-by: Simon Horman Link: https://patch.msgid.link/20240621101353.107425-6-hengqi@linux.alibaba.com Signed-off-by: Jakub Kicinski --- drivers/net/virtio_net.c | 54 +++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 47 insertions(+), 7 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index f21297751310..0b4747e81464 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2469,6 +2469,13 @@ err_xdp_reg_mem_model: return err; } +static void virtnet_cancel_dim(struct virtnet_info *vi, struct dim *dim) +{ + if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) + return; + net_dim_work_cancel(dim); +} + static int virtnet_open(struct net_device *dev) { struct virtnet_info *vi = netdev_priv(dev); @@ -2495,7 +2502,7 @@ err_enable_qp: for (i--; i >= 0; i--) { virtnet_disable_queue_pair(vi, i); - cancel_work_sync(&vi->rq[i].dim.work); + virtnet_cancel_dim(vi, &vi->rq[i].dim); } return err; @@ -2671,7 +2678,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi, if (running) { napi_disable(&rq->napi); - cancel_work_sync(&rq->dim.work); + virtnet_cancel_dim(vi, &rq->dim); } err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf); @@ -2932,7 +2939,7 @@ static int virtnet_close(struct net_device *dev) for (i = 0; i < vi->max_queue_pairs; i++) { virtnet_disable_queue_pair(vi, i); - cancel_work_sync(&vi->rq[i].dim.work); + virtnet_cancel_dim(vi, &vi->rq[i].dim); } return 0; @@ -4458,7 +4465,7 @@ static void virtnet_rx_dim_work(struct work_struct *work) if (!rq->dim_enabled) goto out; - update_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix); + update_moder = net_dim_get_rx_irq_moder(dev, dim); if (update_moder.usec != rq->intr_coal.max_usecs || update_moder.pkts != rq->intr_coal.max_packets) { err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, qnum, @@ -5158,6 +5165,36 @@ static void virtnet_tx_timeout(struct net_device *dev, unsigned int txqueue) jiffies_to_usecs(jiffies - READ_ONCE(txq->trans_start))); } +static int virtnet_init_irq_moder(struct virtnet_info *vi) +{ + u8 profile_flags = 0, coal_flags = 0; + int ret, i; + + profile_flags |= DIM_PROFILE_RX; + coal_flags |= DIM_COALESCE_USEC | DIM_COALESCE_PKTS; + ret = net_dim_init_irq_moder(vi->dev, profile_flags, coal_flags, + DIM_CQ_PERIOD_MODE_START_FROM_EQE, + 0, virtnet_rx_dim_work, NULL); + + if (ret) + return ret; + + for (i = 0; i < vi->max_queue_pairs; i++) + net_dim_setting(vi->dev, &vi->rq[i].dim, false); + + return 0; +} + +static void virtnet_free_irq_moder(struct virtnet_info *vi) +{ + if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL)) + return; + + rtnl_lock(); + net_dim_free_irq_moder(vi->dev); + rtnl_unlock(); +} + static const struct net_device_ops virtnet_netdev = { .ndo_open = virtnet_open, .ndo_stop = virtnet_close, @@ -5437,9 +5474,6 @@ static int virtnet_alloc_queues(struct virtnet_info *vi) virtnet_poll_tx, napi_tx ? napi_weight : 0); - INIT_WORK(&vi->rq[i].dim.work, virtnet_rx_dim_work); - vi->rq[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; - sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg)); ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len); sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg)); @@ -5868,6 +5902,10 @@ static int virtnet_probe(struct virtio_device *vdev) for (i = 0; i < vi->max_queue_pairs; i++) if (vi->sq[i].napi.weight) vi->sq[i].intr_coal.max_packets = 1; + + err = virtnet_init_irq_moder(vi); + if (err) + goto free; } #ifdef CONFIG_SYSFS @@ -6019,6 +6057,8 @@ static void virtnet_remove(struct virtio_device *vdev) disable_rx_mode_work(vi); flush_work(&vi->rx_mode_work); + virtnet_free_irq_moder(vi); + unregister_netdev(vi->dev); net_failover_destroy(vi->failover); -- cgit v1.2.3