net: intel: start The Great Code Dedup + Page Pool for iavf
Subsystems (8)
Alexander Lobakin
maintainerv10 cover net: intel: start The Great Code Dedup + Page Pool for iavf
Here's a two-shot: introduce {,Intel} Ethernet common library (libeth and libie) and switch iavf to Page Pool. Details are in the commit messages; here's a summary:
Not a secret there's a ton of code duplication between two and more Intel ethernet modules. Before introducing new changes, which would need to be copied over again, start decoupling the already existing duplicate functionality into a new module, which will be shared between several Intel Ethernet drivers. The first name that came to my mind was "libie" -- "Intel Ethernet common library". Also this sounds like "lovelie" (-> one word, no "lib I E" pls) and can be expanded as "lib Internet Explorer" :P
The "generic", pure-software part is placed separately, so that it can be easily reused in any driver by any vendor without linking to the Intel pre-200G guts. In a few words, it's something any modern driver does the same way, but nobody moved it level up (yet).
The series is only the beginning. From now on, adding every new feature or doing any good driver refactoring will remove much more lines than add for quite some time. There's a basic roadmap with some deduplications planned already, not speaking of that touching every line now asks:
"can I share this?". The final destination is very ambitious: have only one unified driver for at least i40e, ice, iavf, and idpf with a struct ops for each generation. That's never gonna happen, right? But you still can at least try.
PP conversion for iavf lands within the same series as these two are tied closely. libie will support Page Pool model only, so that a driver can't use much of the lib until it's converted. iavf is only the example, the rest will eventually be converted soon on a per-driver basis. That is when it gets really interesting. Stay tech.
Alexander Lobakin (10):
net: intel: introduce {,Intel} Ethernet common library
iavf: kill "legacy-rx" for good
iavf: drop page splitting and recycling
slab: introduce kvmalloc_array_node() and kvcalloc_node()
page_pool: constify some read-only function arguments
page_pool: add DMA-sync-for-CPU inline helper
libeth: add Rx buffer management
iavf: pack iavf_ring more efficiently
iavf: switch to Page Pool
MAINTAINERS: add entry for libeth and libie
MAINTAINERS | 20 + drivers/net/ethernet/intel/Kconfig | 7 + drivers/net/ethernet/intel/libeth/Kconfig | 9 + drivers/net/ethernet/intel/libie/Kconfig | 10 + drivers/net/ethernet/intel/Makefile | 3 + drivers/net/ethernet/intel/libeth/Makefile | 6 + drivers/net/ethernet/intel/libie/Makefile | 6 + include/net/page_pool/types.h | 4 +- .../net/ethernet/intel/i40e/i40e_prototype.h | 7 - drivers/net/ethernet/intel/i40e/i40e_type.h | 88 --- drivers/net/ethernet/intel/iavf/iavf.h | 2 +- .../net/ethernet/intel/iavf/iavf_prototype.h | 7 - drivers/net/ethernet/intel/iavf/iavf_txrx.h | 146 +---- drivers/net/ethernet/intel/iavf/iavf_type.h | 90 --- .../net/ethernet/intel/ice/ice_lan_tx_rx.h | 320 ---------- include/linux/net/intel/libie/rx.h | 50 ++ include/linux/slab.h | 17 +- include/net/libeth/rx.h | 242 ++++++++ include/net/page_pool/helpers.h | 34 +- drivers/net/ethernet/intel/i40e/i40e_common.c | 253 -------- drivers/net/ethernet/intel/i40e/i40e_main.c | 1 + drivers/net/ethernet/intel/i40e/i40e_txrx.c | 72 +-- drivers/net/ethernet/intel/iavf/iavf_common.c | 253 -------- .../net/ethernet/intel/iavf/iavf_ethtool.c | 140 ----- drivers/net/ethernet/intel/iavf/iavf_main.c | 40 +- drivers/net/ethernet/intel/iavf/iavf_txrx.c | 551 +++--------------- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 17 +- drivers/net/ethernet/intel/ice/ice_main.c | 1 + drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 111 +--- drivers/net/ethernet/intel/libeth/rx.c | 150 +++++ drivers/net/ethernet/intel/libie/rx.c | 124 ++++ net/core/page_pool.c | 10 +- 32 files changed, 836 insertions(+), 1955 deletions(-) create mode 100644 drivers/net/ethernet/intel/libeth/Kconfig create mode 100644 drivers/net/ethernet/intel/libie/Kconfig create mode 100644 drivers/net/ethernet/intel/libeth/Makefile create mode 100644 drivers/net/ethernet/intel/libie/Makefile create mode 100644 include/linux/net/intel/libie/rx.h create mode 100644 include/net/libeth/rx.h create mode 100644 drivers/net/ethernet/intel/libeth/rx.c create mode 100644 drivers/net/ethernet/intel/libie/rx.c
---
libeth has way more generic functionality and code in the idpf XDP tree[0], take a look if you want to have more complete picture of what this really is about.
From v9[1]:
* pick Acked-by from Vlastimil and a couple Reviewed-by from Przemek;
* mention that the libeth_fq::fp kernel-doc generates a warning and the fix for that is pending on the linux-doc ML (Jakub);
* no functional changes.
From v8[2]:
* rebase on top of net-next (6.9-rc1+);
* introduce kvmalloc_array_node() and kvcalloc_node();
* make Rx buffer management NUMA-aware;
* resolve kdoc issues (Jakub, me).
From v7[3]:
* drop Page Pool optimization prereqs;
* drop generic stats part: will redo to the new per-queue stats later;
* split libie into "generic" and "fnic" (i40e, ice, iavf) parts;
* use shorter and modern struct names;
* #1: allow to compile-out hotpath IPv6 code when !CONFIG_IPV6;
* #1: generate XDP RSS hash directly in the lookup table;
* #8: fix rare skb nullptr deref bug.
From v6[4]:
* #04: resolve ethtool_puts() Git conflict (Jakub);
* #06: pick RB from Ilias;
* no functional changes.
From v5[5]:
* drop Page Pool DMA shortcut: will pick up Eric's more global DMA sync optimization[6] and expand it to cover both IOMMU and direct DMA a bit later (Yunsheng);
* drop per-queue Page Pool Ethtool stats: they are now exported via generic Netlink interface (Jakub);
* #01: leave a comment why exactly this alignment (Jakub, Yunsheng);
* #08: make use of page_pool_params::netdev when calculating PP params;
* #08: rename ``libie_rx_queue`` -> ``libie_buf_queue``.
From v4[7]:
* make use of Jakub's &page_pool_params split;
* #01: prevent frag fields from spanning into 2 cachelines after splitting &page_pool_params into fast and slow;
* #02-03: bring back the DMA sync shortcut, now as a per-page flag (me, Yunsheng);
* #04: let libie have its own Kconfig to stop further bloating of poor intel/Kconfig;
* #06: merge page split-reuse-recycle drop into one commit (Alex);
* #07: decouple constifying of several Page Pool function arguments into a separate commit, constify some more;
* #09: stop abusing internal PP fields in the driver code (Yunsheng);
* #09: calculate DMA sync size (::max_len) correctly: within one page, not one buffer (Yunsheng);
* #10: decouple rearranging &iavf_ring into separate commit, optimize it even more;
* #11: let the driver get back to the last descriptor to process after an skb allocation fail, don't drop it (Alex);
* #11: stop touching unrelated stuff like watchdog timeout etc. (Alex);
* fix "Return:" in the kdoc (now W=12 C=1 is clean), misc typos.
From v3[8]:
* base on the latest net-next, update bloat-o-meter and perf stats;
* split generic PP optimizations into a separate series;
* drop "optimize hotpath a bunch" commit: a lot of [controversial] changes in one place, worth own series (Alex);
* 02: pick Rev-by (Alex);
* 03: move in-place recycling removal here from the dropped patch;
* 05: new, add libie Rx buffer API separatelly from IAVF changes;
* 05-06: use new "hybrid" allocation API from[8] to reduce memory usage when a page can fit more than 1 truesize (also asked by David);
* 06: merge with "always use order-0 page" commit to reduce diffs and simplify things (Alex);
* 09: fix page_alloc_fail counter.
From v2[10]:
* 0006: fix page_pool.h include in OcteonTX2 files (Jakub, Patchwork);
* no functional changes.
From v1[11]:
* 0006: new (me, Jakub);
* 0008: give the helpers more intuitive names (Jakub, Ilias);
* -^-: also expand their kdoc a bit for the same reason;
* -^-: fix kdoc copy-paste issue (Patchwork, Jakub);
* 0011: drop inline from C file (Patchwork, Jakub).
[0] https://github.com/alobakin/linux/commits/idpf-libie-new
[1] https://lore.kernel.org/netdev/[email protected]
[2] https://lore.kernel.org/netdev/[email protected]
[3] https://lore.kernel.org/netdev/[email protected]
[4] https://lore.kernel.org/netdev/[email protected]
[5] https://lore.kernel.org/netdev/[email protected]
[6] https://lore.kernel.org/netdev/[email protected]
[7] https://lore.kernel.org/netdev/[email protected]
[8] https://lore.kernel.org/netdev/[email protected]
[9] https://lore.kernel.org/netdev/[email protected]
[10] https://lore.kernel.org/netdev/[email protected]
[11] https://lore.kernel.org/netdev/[email protected]
Signature · 1 line
2.44.0
Alexander Lobakin
maintainerPATCH v10 1/10 net: intel: introduce {,Intel} Ethernet common library
Not a secret there's a ton of code duplication between two and more Intel ethernet modules.
Before introducing new changes, which would need to be copied over again, start decoupling the already existing duplicate functionality into a new module, which will be shared between several Intel Ethernet drivers. Add the lookup table which converts 8/10-bit hardware packet type into a parsed bitfield structure for easy checking packet format parameters, such as payload level, IP version, etc. This is currently used by i40e, ice and iavf and it's all the same in all three drivers.
The only difference introduced in this implementation is that instead of defining a 256 (or 1024 in case of ice) element array, add unlikely() condition to limit the input to 154 (current maximum non-reserved packet type). There's no reason to waste 600 (or even 3600) bytes only to not hurt very unlikely exception packets.
The hash computation function now takes payload level directly as a pkt_hash_type. There's a couple cases when non-IP ptypes are marked as L3 payload and in the previous versions their hash level would be 2, not
3. But skb_set_hash() only sees difference between L4 and non-L4, thus this won't change anything at all.
The module is behind the hidden Kconfig symbol, which the drivers will select when needed. The exports are behind 'LIBIE' namespace to limit the scope of the functions.
Not that non-HW-specific symbols will live in yet another module, libeth. This is done to easily distinguish pretty generic code ready for reusing by any other vendor and/or for moving the layer up from the code useful in Intel's 1-100G drivers only.
--- drivers/net/ethernet/intel/Kconfig | 7 + drivers/net/ethernet/intel/libeth/Kconfig | 8 + drivers/net/ethernet/intel/libie/Kconfig | 10 + drivers/net/ethernet/intel/Makefile | 3 + drivers/net/ethernet/intel/libeth/Makefile | 6 + drivers/net/ethernet/intel/libie/Makefile | 6 + .../net/ethernet/intel/i40e/i40e_prototype.h | 7 - drivers/net/ethernet/intel/i40e/i40e_type.h | 88 ----- .../net/ethernet/intel/iavf/iavf_prototype.h | 7 - drivers/net/ethernet/intel/iavf/iavf_type.h | 88 ----- .../net/ethernet/intel/ice/ice_lan_tx_rx.h | 320 ------------------ include/linux/net/intel/libie/rx.h | 33 ++ include/net/libeth/rx.h | 125 +++++++ drivers/net/ethernet/intel/i40e/i40e_common.c | 253 -------------- drivers/net/ethernet/intel/i40e/i40e_main.c | 1 + drivers/net/ethernet/intel/i40e/i40e_txrx.c | 72 +--- drivers/net/ethernet/intel/iavf/iavf_common.c | 253 -------------- drivers/net/ethernet/intel/iavf/iavf_main.c | 1 + drivers/net/ethernet/intel/iavf/iavf_txrx.c | 70 +--- drivers/net/ethernet/intel/ice/ice_main.c | 1 + drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 111 +----- drivers/net/ethernet/intel/libeth/rx.c | 52 +++ drivers/net/ethernet/intel/libie/rx.c | 124 +++++++ 23 files changed, 426 insertions(+), 1220 deletions(-) create mode 100644 drivers/net/ethernet/intel/libeth/Kconfig create mode 100644 drivers/net/ethernet/intel/libie/Kconfig create mode 100644 drivers/net/ethernet/intel/libeth/Makefile create mode 100644 drivers/net/ethernet/intel/libie/Makefile create mode 100644 include/linux/net/intel/libie/rx.h create mode 100644 include/net/libeth/rx.h create mode 100644 drivers/net/ethernet/intel/libeth/rx.c create mode 100644 drivers/net/ethernet/intel/libie/rx.c
drivers/net/ethernet/intel/Kconfig +7 -0
@@ -16,6 +16,9 @@ config NET_VENDOR_INTEL if NET_VENDOR_INTEL +source "drivers/net/ethernet/intel/libeth/Kconfig" +source "drivers/net/ethernet/intel/libie/Kconfig" + config E100 tristate "Intel(R) PRO/100+ support" depends on PCI
@@ -225,6 +228,7 @@ config I40E depends on PTP_1588_CLOCK_OPTIONAL depends on PCI select AUXILIARY_BUS + select LIBIE select NET_DEVLINK help This driver supports Intel(R) Ethernet Controller XL710 Family of
@@ -253,6 +257,8 @@ config I40E_DCB # so that CONFIG_IAVF symbol will always mirror the state of CONFIG_I40EVF config IAVF tristate + select LIBIE + config I40EVF tristate "Intel(R) Ethernet Adaptive Virtual Function support" select IAVF
@@ -283,6 +289,7 @@ config ICE depends on GNSS || GNSS = n select AUXILIARY_BUS select DIMLIB + select LIBIE select NET_DEVLINK select PLDMFW select DPLL
drivers/net/ethernet/intel/libeth/Kconfig new file +8 -0
@@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2024 Intel Corporation + +config LIBETH + tristate + help + libeth is a common library containing routines shared between several + drivers, but not yet promoted to the generic kernel API.
drivers/net/ethernet/intel/libie/Kconfig new file +10 -0
@@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2024 Intel Corporation + +config LIBIE + tristate + select LIBETH + help + libie (Intel Ethernet library) is a common library built on top of + libeth and containing vendor-specific routines shared between several + Intel Ethernet drivers.
drivers/net/ethernet/intel/Makefile +3 -0
@@ -3,6 +3,9 @@ # Makefile for the Intel network device drivers. # +obj-$(CONFIG_LIBETH) += libeth/ +obj-$(CONFIG_LIBIE) += libie/ + obj-$(CONFIG_E100) += e100.o obj-$(CONFIG_E1000) += e1000/ obj-$(CONFIG_E1000E) += e1000e/
drivers/net/ethernet/intel/libeth/Makefile new file +6 -0
@@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2024 Intel Corporation + +obj-$(CONFIG_LIBETH) += libeth.o + +libeth-objs += rx.o
drivers/net/ethernet/intel/libie/Makefile new file +6 -0
@@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copyright (C) 2024 Intel Corporation + +obj-$(CONFIG_LIBIE) += libie.o + +libie-objs += rx.o
drivers/net/ethernet/intel/i40e/i40e_prototype.h +0 -7
@@ -371,13 +371,6 @@ void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status);int i40e_set_mac_type (struct i40e_hw *hw); -extern struct i40e_rx_ptype_decoded i40e_ptype_lookup[]; - -static inline struct i40e_rx_ptype_decoded decode_rx_desc_ptype (u8 ptype) -{ -return i40e_ptype_lookup[ptype]; -} -/** * i40e_virtchnl_link_speed - Convert AdminQ link_speed to virtchnl definition * @link_speed: the speed to convert
drivers/net/ethernet/intel/i40e/i40e_type.h +0 -88
94 lines not on this page · raw message
drivers/net/ethernet/intel/iavf/iavf_prototype.h +0 -7
@@ -45,13 +45,6 @@ enum iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 seid,enum iavf_status iavf_aq_set_rss_key (struct iavf_hw *hw,u16 seid,struct iavf_aqc_get_set_rss_key_data *key); -extern struct iavf_rx_ptype_decoded iavf_ptype_lookup[]; - -static inline struct iavf_rx_ptype_decoded decode_rx_desc_ptype (u8 ptype) -{ -return iavf_ptype_lookup[ptype]; -} -void iavf_vf_parse_hw_config (struct iavf_hw *hw,struct virtchnl_vf_resource *msg); enum iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw,
drivers/net/ethernet/intel/iavf/iavf_type.h +0 -88
94 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +0 -320
330 lines not on this page · raw message
include/linux/net/intel/libie/rx.h new file +33 -0
@@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBIE_RX_H +#define __LIBIE_RX_H + +#include <net/libeth/rx.h> + +/* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed +* bitfield struct. +*/ + +#define LIBIE_RX_PT_NUM 154 + +extern const struct libeth_rx_pt libie_rx_pt_lut[LIBIE_RX_PT_NUM ]; + +/** +* libie_rx_pt_parse - convert HW packet type to software bitfield structure +* @pt: 10-bit hardware packet type value from the descriptor +* +* ```libie_rx_pt_lut``` must be accessed only using this wrapper. +* +* Return: parsed bitfield struct corresponding to the provided ptype. +*/ +static inline struct libeth_rx_pt libie_rx_pt_parse (u32 pt) +{ +if (unlikely (pt >=LIBIE_RX_PT_NUM )) + pt =0 ; + +return libie_rx_pt_lut[pt]; +} + +#endif /* __LIBIE_RX_H */
include/net/libeth/rx.h new file +125 -0
125 lines not on this page · raw message
drivers/net/ethernet/intel/i40e/i40e_common.c +0 -253
259 lines not on this page · raw message
drivers/net/ethernet/intel/i40e/i40e_main.c +1 -0
@@ -100,6 +100,7 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all), Debug mask (0x8XXXXXXXMODULE_AUTHOR ("Intel Corporation, <[email protected]>" );MODULE_DESCRIPTION ("Intel(R) Ethernet Connection XL710 Network Driver" ); +MODULE_IMPORT_NS (LIBIE );MODULE_LICENSE ("GPL v2" );static struct workqueue_struct *i40e_wq;
drivers/net/ethernet/intel/i40e/i40e_txrx.c +17 -55
127 lines not on this page · raw message
drivers/net/ethernet/intel/iavf/iavf_common.c +0 -253
259 lines not on this page · raw message
drivers/net/ethernet/intel/iavf/iavf_main.c +1 -0
@@ -45,6 +45,7 @@ MODULE_DEVICE_TABLE(pci, iavf_pci_tbl);MODULE_ALIAS ("i40evf" );MODULE_AUTHOR ("Intel Corporation, <[email protected]>" );MODULE_DESCRIPTION ("Intel(R) Ethernet Adaptive Virtual Function Network Driver" ); +MODULE_IMPORT_NS (LIBIE );MODULE_LICENSE ("GPL v2" );static const struct net_device_ops iavf_netdev_ops;
drivers/net/ethernet/intel/iavf/iavf_txrx.c +16 -54
123 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_main.c +1 -0
@@ -37,6 +37,7 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation.";MODULE_AUTHOR ("Intel Corporation, <[email protected]>" );MODULE_DESCRIPTION (DRV_SUMMARY ); +MODULE_IMPORT_NS (LIBIE );MODULE_LICENSE ("GPL v2" );MODULE_FIRMWARE (ICE_DDP_PKG_FILE );
drivers/net/ethernet/intel/ice/ice_txrx_lib.c +16 -95
173 lines not on this page · raw message
drivers/net/ethernet/intel/libeth/rx.c new file +52 -0
52 lines not on this page · raw message
drivers/net/ethernet/intel/libie/rx.c new file +124 -0
124 lines not on this page · raw message
Signature · 1 line
2.44.0
Alexander Lobakin
maintainerPATCH v10 2/10 iavf: kill "legacy-rx" for good
In reply to Alexander LobakinEver since build_skb() became stable, the old way with allocating an skb for storing the headers separately, which will be then copied manually, was slower, less flexible, and thus obsolete.
* It had higher pressure on MM since it actually allocates new pages, which then get split and refcount-biased (NAPI page cache);
* It implies memcpy() of packet headers (40+ bytes per each frame);
* the actual header length was calculated via eth_get_headlen(), which invokes Flow Dissector and thus wastes a bunch of CPU cycles;
* XDP makes it even more weird since it requires headroom for long and also tailroom for some time (since mbuf landed). Take a look at the ice driver, which is built around work-arounds to make XDP work with it.
Even on some quite low-end hardware (not a common case for 100G NICs) it was performing worse.
The only advantage "legacy-rx" had is that it didn't require any reserved headroom and tailroom. But iavf didn't use this, as it always splits pages into two halves of 2k, while that save would only be useful when striding. And again, XDP effectively removes that sole pro.
There's a train of features to land in IAVF soon: Page Pool, XDP, XSk, multi-buffer etc. Each new would require adding more and more Danse Macabre for absolutely no reason, besides making hotpath less and less effective.
Remove the "feature" with all the related code. This includes at least one very hot branch (typically hit on each new frame), which was either always-true or always-false at least for a complete NAPI bulk of 64 frames, the whole private flags cruft, and so on. Some stats:
Function: add/remove: 0/4 grow/shrink: 0/7 up/down: 0/-721 (-721) RO Data: add/remove: 0/1 grow/shrink: 0/0 up/down: 0/-40 (-40)
--- drivers/net/ethernet/intel/iavf/iavf.h | 2 +- drivers/net/ethernet/intel/iavf/iavf_txrx.h | 27 +--- .../net/ethernet/intel/iavf/iavf_ethtool.c | 140 ------------------ drivers/net/ethernet/intel/iavf/iavf_main.c | 10 +- drivers/net/ethernet/intel/iavf/iavf_txrx.c | 82 +--------- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 3 +- 6 files changed, 8 insertions(+), 256 deletions(-)
drivers/net/ethernet/intel/iavf/iavf.h +1 -1
@@ -287,7 +287,7 @@ struct iavf_adapter {#define IAVF_FLAG_RESET_PENDING BIT(4)#define IAVF_FLAG_RESET_NEEDED BIT(5)#define IAVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) -#define IAVF_FLAG_LEGACY_RX BIT(15) +/* BIT(15) is free, was IAVF_FLAG_LEGACY_RX */ #define IAVF_FLAG_REINIT_ITR_NEEDED BIT(16)#define IAVF_FLAG_QUEUES_DISABLED BIT(17)#define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18)
drivers/net/ethernet/intel/iavf/iavf_txrx.h +2 -25
@@ -81,20 +81,11 @@ enum iavf_dyn_idx_t { BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))/* Supported Rx Buffer Sizes (a multiple of 128) */ -#define IAVF_RXBUFFER_256 256#define IAVF_RXBUFFER_1536 1536/* 128B aligned standard Ethernet frame */ #define IAVF_RXBUFFER_2048 2048#define IAVF_RXBUFFER_3072 3072/* Used for large frames w/ padding */ #define IAVF_MAX_RXBUFFER 9728/* largest size for single descriptor */ -/* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we -* reserve 2 more, and skb_shared_info adds an additional 384 bytes more, -* this adds up to 512 bytes of extra data meaning the smallest allocation -* we could have is 1K. -* i.e. RXBUFFER_256 --> 960 byte skb (size-1024 slab) -* i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab) -*/ -#define IAVF_RX_HDR_SIZE IAVF_RXBUFFER_256#define IAVF_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2))#define iavf_rx_desc iavf_32byte_rx_desc
@@ -361,7 +352,8 @@ struct iavf_ring {u16 flags;#define IAVF_TXR_FLAGS_WB_ON_ITR BIT(0) -#define IAVF_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) +/* BIT(1) is free, was IAVF_RXR_FLAGS_BUILD_SKB_ENABLED */ +/* BIT(2) is free */ #define IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1 BIT(3)#define IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2 BIT(4)#define IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2 BIT(5)
@@ -392,21 +384,6 @@ struct iavf_ring {*/ }____cacheline_internodealigned_in_smp ; -static inline bool ring_uses_build_skb (struct iavf_ring *ring) -{ -return !!(ring->flags &IAVF_RXR_FLAGS_BUILD_SKB_ENABLED ); -} - -static inline void set_ring_build_skb_enabled (struct iavf_ring *ring) -{ - ring->flags |=IAVF_RXR_FLAGS_BUILD_SKB_ENABLED ; -} - -static inline void clear_ring_build_skb_enabled (struct iavf_ring *ring) -{ - ring->flags &= ~IAVF_RXR_FLAGS_BUILD_SKB_ENABLED ; -} -#define IAVF_ITR_ADAPTIVE_MIN_INC 0x0002#define IAVF_ITR_ADAPTIVE_MIN_USECS 0x0002#define IAVF_ITR_ADAPTIVE_MAX_USECS 0x007e
drivers/net/ethernet/intel/iavf/iavf_ethtool.c +0 -140
181 lines not on this page · raw message
drivers/net/ethernet/intel/iavf/iavf_main.c +1 -9
@@ -719,9 +719,7 @@ static void iavf_configure_rx(struct iavf_adapter *adapter)struct iavf_hw *hw = &adapter->hw;int i; -/* Legacy Rx will always default to a 2048 buffer size. */ -#if (PAGE_SIZE <8192 ) -if (!(adapter->flags &IAVF_FLAG_LEGACY_RX )) { +if (PAGE_SIZE <8192 ) {struct net_device *netdev = adapter->netdev;/* For jumbo frames on systems with 4K pages we have to use
@@ -738,16 +736,10 @@ static void iavf_configure_rx(struct iavf_adapter *adapter) (netdev->mtu <= ETH_DATA_LEN)) rx_buf_len =IAVF_RXBUFFER_1536 -NET_IP_ALIGN ; } -#endif for (i =0 ; i < adapter->num_active_queues; i++) { adapter->rx_rings[i].tail = hw->hw_addr +IAVF_QRX_TAIL1 (i); adapter->rx_rings[i].rx_buf_len = rx_buf_len; - -if (adapter->flags &IAVF_FLAG_LEGACY_RX ) -clear_ring_build_skb_enabled (&adapter->rx_rings[i]); -else -set_ring_build_skb_enabled (&adapter->rx_rings[i]); } }
drivers/net/ethernet/intel/iavf/iavf_txrx.c +3 -79
113 lines not on this page · raw message
drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +1 -2
@@ -289,8 +289,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter)return ;/* Limit maximum frame size when jumbo frames is not enabled */ -if (!(adapter->flags &IAVF_FLAG_LEGACY_RX ) && - (adapter->netdev->mtu <=ETH_DATA_LEN )) +if (adapter->netdev->mtu <=ETH_DATA_LEN ) max_frame =IAVF_RXBUFFER_1536 -NET_IP_ALIGN ; vqci->vsi_id = adapter->vsi_res->vsi_id;
Signature · 1 line
2.44.0
Alexander Lobakin
maintainerPATCH v10 3/10 iavf: drop page splitting and recycling
In reply to Alexander LobakinAs an intermediate step, remove all page splitting/recycling code. Just always allocate a new page and don't touch its refcount, so that it gets freed by the core stack later.
Same for the "in-place" recycling, i.e. when an unused buffer gets assigned to a first needs-refilling descriptor. In some cases, this was leading to moving up to 63 &iavf_rx_buf structures around the ring on a per-field basis -- not something wanted on hotpath.
The change allows to greatly simplify certain parts of the code:
Function: add/remove: 0/2 grow/shrink: 0/7 up/down: 0/-744 (-744)
Although the array of &iavf_rx_buf is barely used now and could be replaced with just page pointer array, don't touch it now to not complicate replacing it with libie Rx buffer struct later on. No surprise perf loses up to 30% here, but that regression will go away once PP lands.
Note that iavf_rx_pg_*() definitions are left to reduce diffstat. They will be removed with the conversion to Page Pool.
--- drivers/net/ethernet/intel/iavf/iavf_txrx.h | 65 -------- drivers/net/ethernet/intel/iavf/iavf_type.h | 2 - drivers/net/ethernet/intel/iavf/iavf_main.c | 24 +-- drivers/net/ethernet/intel/iavf/iavf_txrx.c | 152 +----------------- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 8 +- 5 files changed, 10 insertions(+), 241 deletions(-)
drivers/net/ethernet/intel/iavf/iavf_txrx.h +0 -65
@@ -81,8 +81,6 @@ enum iavf_dyn_idx_t { BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))/* Supported Rx Buffer Sizes (a multiple of 128) */ -#define IAVF_RXBUFFER_1536 1536/* 128B aligned standard Ethernet frame */ -#define IAVF_RXBUFFER_2048 2048#define IAVF_RXBUFFER_3072 3072/* Used for large frames w/ padding */ #define IAVF_MAX_RXBUFFER 9728/* largest size for single descriptor */
@@ -92,57 +90,7 @@ enum iavf_dyn_idx_t {#define IAVF_RX_DMA_ATTR \ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) -/* Attempt to maximize the headroom available for incoming frames. We -* use a 2K buffer for receives and need 1536/1534 to store the data for -* the frame. This leaves us with 512 bytes of room. From that we need -* to deduct the space needed for the shared info and the padding needed -* to IP align the frame. -* -* Note: For cache line sizes 256 or larger this value is going to end -* up negative. In these cases we should fall back to the legacy -* receive path. -*/ -#if (PAGE_SIZE <8192 ) -#define IAVF_2K_TOO_SMALL_WITH_PADDING \ -((NET_SKB_PAD + IAVF_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IAVF_RXBUFFER_2048)) - -static inline int iavf_compute_pad (int rx_buf_len) -{ -int page_size, pad_size; - - page_size =ALIGN (rx_buf_len,PAGE_SIZE /2 ); - pad_size =SKB_WITH_OVERHEAD (page_size) - rx_buf_len; - -return pad_size; -} - -static inline int iavf_skb_pad (void ) -{ -int rx_buf_len; - -/* If a 2K buffer cannot handle a standard Ethernet frame then -* optimize padding for a 3K buffer instead of a 1.5K buffer. -* -* For a 3K buffer we need to add enough padding to allow for -* tailroom due to NET_IP_ALIGN possibly shifting us out of -* cache-line alignment. -*/ -if (IAVF_2K_TOO_SMALL_WITH_PADDING ) - rx_buf_len =IAVF_RXBUFFER_3072 +SKB_DATA_ALIGN (NET_IP_ALIGN ); -else - rx_buf_len =IAVF_RXBUFFER_1536 ; - -/* if needed make room for NET_IP_ALIGN */ - rx_buf_len -=NET_IP_ALIGN ; - -return iavf_compute_pad (rx_buf_len); -} - -#define IAVF_SKB_PAD iavf_skb_pad() -#else -#define IAVF_2K_TOO_SMALL_WITH_PADDING false#define IAVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) -#endif /** * iavf_test_staterr - tests bits in Rx descriptor status and error fields
@@ -265,12 +213,7 @@ struct iavf_tx_buffer {struct iavf_rx_buffer {dma_addr_t dma;struct page *page; -#if (BITS_PER_LONG >32 ) || (PAGE_SIZE >=65536 )__u32 page_offset; -#else -__u16 page_offset; -#endif -__u16 pagecnt_bias; };struct iavf_queue_stats {
@@ -292,8 +235,6 @@ struct iavf_rx_queue_stats {u64 non_eop_descs;u64 alloc_page_failed;u64 alloc_buff_failed; -u64 page_reuse_count; -u64 realloc_count; };enum iavf_ring_state_t {
@@ -337,7 +278,6 @@ struct iavf_ring {u16 count;/* Number of descriptors */ u16 reg_idx;/* HW register index of the ring */ -u16 rx_buf_len;/* used in interrupt processing */ u16 next_to_use;
@@ -373,7 +313,6 @@ struct iavf_ring {struct iavf_q_vector *q_vector;/* Backreference to associated vector */ struct rcu_head rcu;/* to avoid race on free */ -u16 next_to_alloc;struct sk_buff *skb;/* When iavf_clean_rx_ring_irq() must * return before it sees the EOP for * the current packet, we save that skb
@@ -407,10 +346,6 @@ struct iavf_ring_container {static inline unsigned int iavf_rx_pg_order (struct iavf_ring *ring) { -#if (PAGE_SIZE <8192 ) -if (ring->rx_buf_len > (PAGE_SIZE /2 )) -return 1 ; -#endif return 0 ; }
drivers/net/ethernet/intel/iavf/iavf_type.h +0 -2
@@ -10,8 +10,6 @@#include "iavf_adminq.h" #include "iavf_devids.h" -#define IAVF_RXQ_CTX_DBUFF_SHIFT 7 -/* IAVF_MASK is a macro used on 32 bit registers */ #define IAVF_MASK (mask, shift) ((u32)(mask) << (shift))
drivers/net/ethernet/intel/iavf/iavf_main.c +1 -23
@@ -715,32 +715,10 @@ static void iavf_configure_tx(struct iavf_adapter *adapter)**/ static void iavf_configure_rx (struct iavf_adapter *adapter) { -unsigned int rx_buf_len =IAVF_RXBUFFER_2048 ;struct iavf_hw *hw = &adapter->hw; -int i; - -if (PAGE_SIZE <8192 ) { -struct net_device *netdev = adapter->netdev; -/* For jumbo frames on systems with 4K pages we have to use -* an order 1 page, so we might as well increase the size -* of our Rx buffer to make better use of the available space -*/ - rx_buf_len =IAVF_RXBUFFER_3072 ; - -/* We use a 1536 buffer size for configurations with -* standard Ethernet mtu. On x86 this gives us enough room -* for shared info and 192 bytes of padding. -*/ -if (!IAVF_2K_TOO_SMALL_WITH_PADDING && - (netdev->mtu <=ETH_DATA_LEN )) - rx_buf_len =IAVF_RXBUFFER_1536 -NET_IP_ALIGN ; - } - -for (i =0 ; i < adapter->num_active_queues; i++) { +for (u32 i =0 ; i < adapter->num_active_queues; i++) adapter->rx_rings[i].tail = hw->hw_addr +IAVF_QRX_TAIL1 (i); - adapter->rx_rings[i].rx_buf_len = rx_buf_len; - } }/**
drivers/net/ethernet/intel/iavf/iavf_txrx.c +8 -144
258 lines not on this page · raw message
drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +1 -7
@@ -288,10 +288,6 @@ void iavf_configure_queues(struct iavf_adapter *adapter)if (!vqci)return ; -/* Limit maximum frame size when jumbo frames is not enabled */ -if (adapter->netdev->mtu <=ETH_DATA_LEN ) - max_frame =IAVF_RXBUFFER_1536 -NET_IP_ALIGN ; - vqci->vsi_id = adapter->vsi_res->vsi_id; vqci->num_queue_pairs = pairs; vqpi = vqci->qpair;
@@ -308,9 +304,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter) vqpi->rxq.ring_len = adapter->rx_rings[i].count; vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma; vqpi->rxq.max_pkt_size = max_frame; - vqpi->rxq.databuffer_size = -ALIGN (adapter->rx_rings[i].rx_buf_len, -BIT_ULL (IAVF_RXQ_CTX_DBUFF_SHIFT )); + vqpi->rxq.databuffer_size =IAVF_RXBUFFER_3072 ;if (CRC_OFFLOAD_ALLOWED (adapter)) vqpi->rxq.crc_disable = !!(adapter->netdev->features &NETIF_F_RXFCS );
Signature · 1 line
2.44.0
Alexander Lobakin
maintainerPATCH v10 4/10 slab: introduce kvmalloc_array_node() and kvcalloc_node()
In reply to Alexander LobakinAdd NUMA-aware counterparts for kvmalloc_array() and kvcalloc() to be able to flexibly allocate arrays for a particular node. Rewrite kvmalloc_array() to kvmalloc_array_node(NUMA_NO_NODE) call.
--- include/linux/slab.h | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-)
include/linux/slab.h +15 -2
@@ -774,14 +774,27 @@ static inline __alloc_size(1) void *kvzalloc(size_t size, gfp_t flags)return kvmalloc (size, flags | __GFP_ZERO); } -static inline __alloc_size(1, 2) void *kvmalloc_array (size_t n,size_t size,gfp_t flags) +static inline __alloc_size(1, 2) void * +kvmalloc_array_node (size_t n,size_t size,gfp_t flags,int node) {size_t bytes;if (unlikely (check_mul_overflow (n, size, &bytes)))return NULL ; -return kvmalloc (bytes, flags); +return kvmalloc_node (bytes, flags, node); +} + +static inline __alloc_size(1, 2) void * +kvmalloc_array (size_t n,size_t size,gfp_t flags) +{ +return kvmalloc_array_node (n, size, flags,NUMA_NO_NODE ); +} + +static inline __alloc_size(1, 2) void * +kvcalloc_node (size_t n,size_t size,gfp_t flags,int node) +{ +return kvmalloc_array_node (n, size, flags | __GFP_ZERO, node); }static inline __alloc_size(1, 2) void *kvcalloc (size_t n,size_t size,gfp_t flags)
Signature · 1 line
2.44.0
Alexander Lobakin
maintainerPATCH v10 5/10 page_pool: constify some read-only function arguments
In reply to Alexander LobakinThere are several functions taking pointers to data they don't modify. This includes statistics fetching, page and page_pool parameters, etc. Constify the pointers, so that call sites will be able to pass const pointers as well.
No functional changes, no visible changes in functions sizes.
--- include/net/page_pool/types.h | 4 ++-- include/net/page_pool/helpers.h | 10 +++++----- net/core/page_pool.c | 10 +++++----- 3 files changed, 12 insertions(+), 12 deletions(-)
include/net/page_pool/types.h +2 -2
@@ -213,7 +213,7 @@ struct xdp_mem_info;#ifdef CONFIG_PAGE_POOL void page_pool_destroy (struct page_pool *pool);void page_pool_use_xdp_mem (struct page_pool *pool,void (*disconnect)(void *), -struct xdp_mem_info *mem); +const struct xdp_mem_info *mem);void page_pool_put_page_bulk (struct page_pool *pool,void **data,int count);#else
@@ -223,7 +223,7 @@ static inline void page_pool_destroy(struct page_pool *pool)static inline void page_pool_use_xdp_mem (struct page_pool *pool,void (*disconnect)(void *), -struct xdp_mem_info *mem) +const struct xdp_mem_info *mem) { }
include/net/page_pool/helpers.h +5 -5
@@ -58,7 +58,7 @@/* Deprecated driver-facing API, use netlink instead */ int page_pool_ethtool_stats_get_count (void );u8 *page_pool_ethtool_stats_get_strings (u8 *data); -u64 *page_pool_ethtool_stats_get (u64 *data,void *stats); +u64 *page_pool_ethtool_stats_get (u64 *data,const void *stats);bool page_pool_get_stats (const struct page_pool *pool,struct page_pool_stats *stats);
@@ -73,7 +73,7 @@ static inline u8 *page_pool_ethtool_stats_get_strings(u8 *data)return data; } -static inline u64 *page_pool_ethtool_stats_get (u64 *data,void *stats) +static inline u64 *page_pool_ethtool_stats_get (u64 *data,const void *stats) {return data; }
@@ -204,8 +204,8 @@ static inline void *page_pool_dev_alloc_va(struct page_pool *pool,* Get the stored dma direction. A driver might decide to store this locally * and avoid the extra cache line from page_pool to determine the direction. */ -static -inline enum dma_data_direction page_pool_get_dma_dir (struct page_pool *pool) +static inline enum dma_data_direction +page_pool_get_dma_dir (const struct page_pool *pool) {return pool->p.dma_dir; }
@@ -370,7 +370,7 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va,* Fetch the DMA address of the page. The page pool to which the page belongs * must had been created with PP_FLAG_DMA_MAP. */ -static inline dma_addr_t page_pool_get_dma_addr (struct page *page) +static inline dma_addr_t page_pool_get_dma_addr (const struct page *page) {dma_addr_t ret = page->dma_addr;
net/core/page_pool.c +5 -5
@@ -123,9 +123,9 @@ int page_pool_ethtool_stats_get_count(void) }EXPORT_SYMBOL (page_pool_ethtool_stats_get_count); -u64 *page_pool_ethtool_stats_get (u64 *data,void *stats) +u64 *page_pool_ethtool_stats_get (u64 *data,const void *stats) { -struct page_pool_stats *pool_stats = stats; +const struct page_pool_stats *pool_stats = stats; *data++ = pool_stats->alloc_stats.fast; *data++ = pool_stats->alloc_stats.slow;
@@ -383,8 +383,8 @@ static struct page *__page_pool_get_cached(struct page_pool *pool)return page; } -static void page_pool_dma_sync_for_device (struct page_pool *pool, -struct page *page, +static void page_pool_dma_sync_for_device (const struct page_pool *pool, +const struct page *page,unsigned int dma_sync_size) {dma_addr_t dma_addr =page_pool_get_dma_addr (page);
@@ -987,7 +987,7 @@ static void page_pool_release_retry(struct work_struct *wq) }void page_pool_use_xdp_mem (struct page_pool *pool,void (*disconnect)(void *), -struct xdp_mem_info *mem) +const struct xdp_mem_info *mem) {refcount_inc (&pool->user_cnt); pool->disconnect = disconnect;
Signature · 1 line
2.44.0
Alexander Lobakin
maintainerPATCH v10 6/10 page_pool: add DMA-sync-for-CPU inline helper
In reply to Alexander LobakinEach driver is responsible for syncing buffers written by HW for CPU before accessing them. Almost each PP-enabled driver uses the same pattern, which could be shorthanded into a static inline to make driver code a little bit more compact.
Introduce a simple helper which performs DMA synchronization for the size passed from the driver. It can be used even when the pool doesn't manage DMA-syncs-for-device, just make sure the page has a correct DMA address set via page_pool_set_dma_addr().
--- include/net/page_pool/helpers.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)
include/net/page_pool/helpers.h +24 -0
@@ -52,6 +52,8 @@#ifndef _NET_PAGE_POOL_HELPERS_H#define _NET_PAGE_POOL_HELPERS_H +#include <linux/dma-mapping.h> +#include <net/page_pool/types.h> #ifdef CONFIG_PAGE_POOL_STATS
@@ -395,6 +397,28 @@ static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr)return false; } +/** +* page_pool_dma_sync_for_cpu - sync Rx page for CPU after it's written by HW +* @pool: &page_pool the @page belongs to +* @page: page to sync +* @offset: offset from page start to "hard" start if using PP frags +* @dma_sync_size: size of the data written to the page +* +* Can be used as a shorthand to sync Rx pages before accessing them in the +* driver. Caller must ensure the pool was created with ``PP_FLAG_DMA_MAP``. +* Note that this version performs DMA sync unconditionally, even if the +* associated PP doesn't perform sync-for-device. +*/ +static inline void page_pool_dma_sync_for_cpu (const struct page_pool *pool, +const struct page *page, +u32 offset,u32 dma_sync_size) +{ +dma_sync_single_range_for_cpu (pool->p.dev, +page_pool_get_dma_addr (page), + offset + pool->p.offset, dma_sync_size, +page_pool_get_dma_dir (pool)); +} +static inline bool page_pool_put (struct page_pool *pool) {return refcount_dec_and_test (&pool->user_cnt);
Signature · 1 line
2.44.0
Re: [PATCH net-next v10 06/10] page_pool: add DMA-sync-for-CPU inline helper
Quoted 58 lines · Alexander Lobakin
Each driver is responsible for syncing buffers written by HW for CPU before accessing them. Almost each PP-enabled driver uses the same pattern, which could be shorthanded into a static inline to make driver code a little bit more compact.
Introduce a simple helper which performs DMA synchronization for the size passed from the driver. It can be used even when the pool doesn't manage DMA-syncs-for-device, just make sure the page has a correct DMA address set viapage_pool_set_dma_addr().Signed-off-by Alexander Lobakin <[email protected]>--- include/net/page_pool/helpers.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)include/net/page_pool/helpers.h +24
-1@@ -52,6 +52,8 @@#ifndef _NET_PAGE_POOL_HELPERS_H#define _NET_PAGE_POOL_HELPERS_H +#include <linux/dma-mapping.h> +#include <net/page_pool/types.h> #ifdef CONFIG_PAGE_POOL_STATS @@ -395,6 +397,28 @@ static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr)return false; } +/** +* page_pool_dma_sync_for_cpu - sync Rx page for CPU after it's written by HW +* @pool: &page_pool the @page belongs to +* @page: page to sync +* @offset: offset from page start to "hard" start if using PP frags +* @dma_sync_size: size of the data written to the page +* +* Can be used as a shorthand to sync Rx pages before accessing them in the +* driver. Caller must ensure the pool was created with ``PP_FLAG_DMA_MAP``. +* Note that this version performs DMA sync unconditionally, even if the +* associated PP doesn't perform sync-for-device. +*/ +static inline void page_pool_dma_sync_for_cpu (const struct page_pool *pool, +const struct page *page, +u32 offset,u32 dma_sync_size) +{ +dma_sync_single_range_for_cpu (pool->p.dev, +page_pool_get_dma_addr (page), + offset + pool->p.offset, dma_sync_size, +page_pool_get_dma_dir (pool)); +} +static inline bool page_pool_put (struct page_pool *pool) {return refcount_dec_and_test (&pool->user_cnt); --
Quoted 2 lines
2.44.0
Alexander Lobakin
maintainerPATCH v10 7/10 libeth: add Rx buffer management
In reply to Alexander LobakinAdd a couple intuitive helpers to hide Rx buffer implementation details in the library and not multiplicate it between drivers. The settings are sorta optimized for 100G+ NICs, but nothing really HW-specific here. Use the new page_pool_dev_alloc() to dynamically switch between split-page and full-page modes depending on MTU, page size, required headroom etc. For example, on x86_64 with the default driver settings each page is shared between 2 buffers. Turning on XDP (not in this series) -> increasing headroom requirement pushes truesize out of 2048 boundary, leading to that each buffer starts getting a full page. The "ceiling" limit is %PAGE_SIZE, as only order-0 pages are used to avoid compound overhead. For the above architecture, this means maximum linear frame size of 3712 w/o XDP.
Not that &libeth_buf_queue is not a complete queue/ring structure for now, rather a shim, but eventually the libeth-enabled drivers will move to it, with iavf being the first one.
---
kernel-doc for libeth_fq::fp generates an "Excess struct member" warning currently, here's patch which fixes the script: [0]
[0] https://lore.kernel.org/linux-doc/[email protected]
--- drivers/net/ethernet/intel/libeth/Kconfig | 1 + include/net/libeth/rx.h | 117 ++++++++++++++++++++++ drivers/net/ethernet/intel/libeth/rx.c | 98 ++++++++++++++++++ 3 files changed, 216 insertions(+)
drivers/net/ethernet/intel/libeth/Kconfig +1 -0
@@ -3,6 +3,7 @@ config LIBETH tristate + select PAGE_POOL help libeth is a common library containing routines shared between several drivers, but not yet promoted to the generic kernel API.
include/net/libeth/rx.h +117 -0
125 lines not on this page · raw message
drivers/net/ethernet/intel/libeth/rx.c +98 -0
104 lines not on this page · raw message
Signature · 1 line
2.44.0
Alexander Lobakin
maintainerPATCH v10 8/10 iavf: pack iavf_ring more efficiently
In reply to Alexander LobakinBefore replacing the Rx buffer management with libie, clean up &iavf_ring a bit.
There are several fields not used anywhere in the code -- simply remove them. Move ::tail up to remove a hole. Replace ::arm_wb boolean with 1-bit flag in ::flags to free 1 more byte. Finally, move ::prev_pkt_ctr out of &iavf_tx_queue_stats -- it doesn't belong there (used for Tx stall detection). Place it next to the stats on the ring itself to fill the 4-byte slot.
The result: no holes and all the hot fields fit into the first 64-byte cacheline.
--- drivers/net/ethernet/intel/iavf/iavf_txrx.h | 22 +++------------------ drivers/net/ethernet/intel/iavf/iavf_txrx.c | 12 +++++------ 2 files changed, 9 insertions(+), 25 deletions(-)
drivers/net/ethernet/intel/iavf/iavf_txrx.h +3 -19
@@ -227,7 +227,6 @@ struct iavf_tx_queue_stats {u64 tx_done_old;u64 tx_linearize;u64 tx_force_wb; -int prev_pkt_ctr;u64 tx_lost_interrupt; };
@@ -237,12 +236,6 @@ struct iavf_rx_queue_stats {u64 alloc_buff_failed; }; -enum iavf_ring_state_t { - __IAVF_TX_FDIR_INIT_DONE, - __IAVF_TX_XPS_INIT_DONE, - __IAVF_RING_STATE_NBITS/* must be last */ -}; -/* some useful defines for virtchannel interface, which * is the only remaining user of header split */
@@ -264,10 +257,8 @@ struct iavf_ring {struct iavf_tx_buffer *tx_bi;struct iavf_rx_buffer *rx_bi; }; -DECLARE_BITMAP (state, __IAVF_RING_STATE_NBITS); -u16 queue_index;/* Queue number of ring */ -u8 dcb_tc;/* Traffic class of ring */ u8 __iomem *tail; +u16 queue_index;/* Queue number of ring */ /* high bit set means dynamic, use accessors routines to read/write. * hardware only supports 2us resolution for the ITR registers.
@@ -277,22 +268,14 @@ struct iavf_ring {u16 itr_setting;u16 count;/* Number of descriptors */ -u16 reg_idx;/* HW register index of the ring */ /* used in interrupt processing */ u16 next_to_use;u16 next_to_clean; -u8 atr_sample_rate; -u8 atr_count; - -bool ring_active;/* is ring online or not */ -bool arm_wb;/* do something to arm write back */ -u8 packet_stride; -u16 flags;#define IAVF_TXR_FLAGS_WB_ON_ITR BIT(0) -/* BIT(1) is free, was IAVF_RXR_FLAGS_BUILD_SKB_ENABLED */ +#define IAVF_TXR_FLAGS_ARM_WB BIT(1)/* BIT(2) is free */ #define IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1 BIT(3)#define IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2 BIT(4)
@@ -306,6 +289,7 @@ struct iavf_ring {struct iavf_rx_queue_stats rx_stats; }; +int prev_pkt_ctr;/* For Tx stall detection */ unsigned int size;/* length of descriptor ring in bytes */ dma_addr_t dma;/* physical address of ring */
drivers/net/ethernet/intel/iavf/iavf_txrx.c +6 -6
@@ -185,7 +185,7 @@ void iavf_detect_recover_hung(struct iavf_vsi *vsi)* pending work. */ packets = tx_ring->stats.packets &INT_MAX ; -if (tx_ring->tx_stats.prev_pkt_ctr == packets) { +if (tx_ring->prev_pkt_ctr == packets) {iavf_force_wb (vsi, tx_ring->q_vector);continue ; }
@@ -194,7 +194,7 @@ void iavf_detect_recover_hung(struct iavf_vsi *vsi)* to iavf_get_tx_pending() */ smp_rmb (); - tx_ring->tx_stats.prev_pkt_ctr = + tx_ring->prev_pkt_ctr =iavf_get_tx_pending (tx_ring, true) ? packets :-1 ; } }
@@ -320,7 +320,7 @@ static bool iavf_clean_tx_irq(struct iavf_vsi *vsi, ((j /WB_STRIDE ) ==0 ) && (j >0 ) && !test_bit (__IAVF_VSI_DOWN, vsi->state) && (IAVF_DESC_UNUSED(tx_ring) != tx_ring->count)) - tx_ring->arm_wb = true; + tx_ring->flags |= IAVF_TXR_FLAGS_ARM_WB; }/* notify netdev of completed buffers */
@@ -675,7 +675,7 @@ int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring) tx_ring->next_to_use =0 ; tx_ring->next_to_clean =0 ; - tx_ring->tx_stats.prev_pkt_ctr =-1 ; + tx_ring->prev_pkt_ctr =-1 ;return 0 ; err:
@@ -1491,8 +1491,8 @@ int iavf_napi_poll(struct napi_struct *napi, int budget) clean_complete = false;continue ; } - arm_wb |= ring->arm_wb; - ring->arm_wb = false; + arm_wb |= !!(ring->flags &IAVF_TXR_FLAGS_ARM_WB ); + ring->flags &= ~IAVF_TXR_FLAGS_ARM_WB ; }/* Handle case where we are called by netpoll with a budget of 0 */
Signature · 1 line
2.44.0
Alexander Lobakin
maintainerPATCH v10 9/10 iavf: switch to Page Pool
In reply to Alexander LobakinNow that the IAVF driver simply uses dev_alloc_page() + free_page() with no custom recycling logics, it can easily be switched to using Page Pool / libeth API instead.
This allows to removing the whole dancing around headroom, HW buffer size, and page order. All DMA-for-device is now done in the PP core, for-CPU -- in the libeth helper.
Use skb_mark_for_recycle() to bring back the recycling and restore the performance. Speaking of performance: on par with the baseline and faster with the PP optimization series applied. But the memory usage for 1500b MTU is now almost 2x lower (x86_64) thanks to allocating a page every second descriptor.
--- drivers/net/ethernet/intel/iavf/iavf_txrx.h | 34 +-- include/linux/net/intel/libie/rx.h | 17 ++ drivers/net/ethernet/intel/iavf/iavf_main.c | 7 +- drivers/net/ethernet/intel/iavf/iavf_txrx.c | 257 +++++------------- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 10 +- 5 files changed, 111 insertions(+), 214 deletions(-)
drivers/net/ethernet/intel/iavf/iavf_txrx.h +9 -25
@@ -80,18 +80,8 @@ enum iavf_dyn_idx_t { BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) -/* Supported Rx Buffer Sizes (a multiple of 128) */ -#define IAVF_RXBUFFER_3072 3072/* Used for large frames w/ padding */ -#define IAVF_MAX_RXBUFFER 9728/* largest size for single descriptor */ - -#define IAVF_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2))#define iavf_rx_desc iavf_32byte_rx_desc -#define IAVF_RX_DMA_ATTR \ - (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) - -#define IAVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) -/** * iavf_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format)
@@ -210,12 +200,6 @@ struct iavf_tx_buffer {u32 tx_flags; }; -struct iavf_rx_buffer { -dma_addr_t dma; -struct page *page; -__u32 page_offset; -}; -struct iavf_queue_stats {u64 packets;u64 bytes;
@@ -251,13 +235,18 @@ struct iavf_rx_queue_stats {struct iavf_ring {struct iavf_ring *next;/* pointer to next ring in q_vector */ void *desc;/* Descriptor ring memory */ -struct device *dev;/* Used for DMA mapping */ +union { +struct page_pool *pp;/* Used on Rx for buffer management */ +struct device *dev;/* Used on Tx for DMA mapping */ + };struct net_device *netdev;/* netdev ring maps to */ union { +struct libeth_fqe *rx_fqes;struct iavf_tx_buffer *tx_bi; -struct iavf_rx_buffer *rx_bi; };u8 __iomem *tail; +u32 truesize; +u16 queue_index;/* Queue number of ring */ /* high bit set means dynamic, use accessors routines to read/write.
@@ -305,6 +294,8 @@ struct iavf_ring {* iavf_clean_rx_ring_irq() is called * for this ring. */ + +u32 rx_buf_len; }____cacheline_internodealigned_in_smp ;#define IAVF_ITR_ADAPTIVE_MIN_INC 0x0002
@@ -328,13 +319,6 @@ struct iavf_ring_container {#define iavf_for_each_ring (pos, head) \ for (pos = (head).ring; pos != NULL; pos = pos->next) -static inline unsigned int iavf_rx_pg_order (struct iavf_ring *ring) -{ -return 0 ; -} - -#define iavf_rx_pg_size (_ring) (PAGE_SIZE << iavf_rx_pg_order(_ring)) -bool iavf_alloc_rx_buffers (struct iavf_ring *rxr,u16 cleaned_count);netdev_tx_t iavf_xmit_frame (struct sk_buff *skb,struct net_device *netdev);int iavf_setup_tx_descriptors (struct iavf_ring *tx_ring);
include/linux/net/intel/libie/rx.h +17 -0
@@ -6,6 +6,23 @@#include <net/libeth/rx.h> +/* Rx buffer management */ + +/* The largest size for a single descriptor as per HW */ +#define LIBIE_MAX_RX_BUF_LEN 9728U +/* "True" HW-writeable space: minimum from SW and HW values */ +#define LIBIE_RX_BUF_LEN (hr) min_t(u32, LIBETH_RX_PAGE_LEN(hr), \ + LIBIE_MAX_RX_BUF_LEN) + +/* The maximum frame size as per HW (S/G) */ +#define __LIBIE_MAX_RX_FRM_LEN 16382U +/* ATST, HW can chain up to 5 Rx descriptors */ +#define LIBIE_MAX_RX_FRM_LEN (hr) \ + min_t(u32, __LIBIE_MAX_RX_FRM_LEN, LIBIE_RX_BUF_LEN(hr) * 5) +/* Maximum frame size minus LL overhead */ +#define LIBIE_MAX_MTU \ + (LIBIE_MAX_RX_FRM_LEN(LIBETH_MAX_HEADROOM) - LIBETH_RX_LL_LEN) +/* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed * bitfield struct. */
drivers/net/ethernet/intel/iavf/iavf_main.c +4 -3
@@ -1,6 +1,8 @@// SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include <linux/net/intel/libie/rx.h> +#include "iavf.h" #include "iavf_prototype.h" /* All iavf tracepoints are defined by the include below, which must
@@ -45,6 +47,7 @@ MODULE_DEVICE_TABLE(pci, iavf_pci_tbl);MODULE_ALIAS ("i40evf" );MODULE_AUTHOR ("Intel Corporation, <[email protected]>" );MODULE_DESCRIPTION ("Intel(R) Ethernet Adaptive Virtual Function Network Driver" ); +MODULE_IMPORT_NS (LIBETH );MODULE_IMPORT_NS (LIBIE );MODULE_LICENSE ("GPL v2" );
@@ -1586,7 +1589,6 @@ static int iavf_alloc_queues(struct iavf_adapter *adapter) rx_ring = &adapter->rx_rings[i]; rx_ring->queue_index = i; rx_ring->netdev = adapter->netdev; - rx_ring->dev = &adapter->pdev->dev; rx_ring->count = adapter->rx_desc_count; rx_ring->itr_setting =IAVF_ITR_RX_DEF ; }
@@ -2613,9 +2615,8 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)iavf_set_ethtool_ops (netdev); netdev->watchdog_timeo =5 *HZ ; -/* MTU range: 68 - 9710 */ netdev->min_mtu =ETH_MIN_MTU ; - netdev->max_mtu =IAVF_MAX_RXBUFFER -IAVF_PACKET_HDR_PAD ; + netdev->max_mtu =LIBIE_MAX_MTU ;if (!is_valid_ether_addr (adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n",
drivers/net/ethernet/intel/iavf/iavf_txrx.c +75 -182
413 lines not on this page · raw message
drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +6 -4
@@ -1,6 +1,8 @@// SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include <linux/net/intel/libie/rx.h> +#include "iavf.h" #include "iavf_prototype.h"
@@ -268,13 +270,13 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter)void iavf_configure_queues (struct iavf_adapter *adapter) {struct virtchnl_vsi_queue_config_info *vqci; -int i, max_frame = adapter->vf_res->max_mtu;int pairs = adapter->num_active_queues;struct virtchnl_queue_pair_info *vqpi; +u32 i, max_frame;size_t len; -if (max_frame >IAVF_MAX_RXBUFFER || !max_frame) - max_frame =IAVF_MAX_RXBUFFER ; + max_frame =LIBIE_MAX_RX_FRM_LEN (adapter->rx_rings->pp->p.offset); + max_frame =min_not_zero (adapter->vf_res->max_mtu, max_frame);if (adapter->current_op !=VIRTCHNL_OP_UNKNOWN ) {/* bail because we already have a command pending */
@@ -304,7 +306,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter) vqpi->rxq.ring_len = adapter->rx_rings[i].count; vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma; vqpi->rxq.max_pkt_size = max_frame; - vqpi->rxq.databuffer_size =IAVF_RXBUFFER_3072 ; + vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len;if (CRC_OFFLOAD_ALLOWED (adapter)) vqpi->rxq.crc_disable = !!(adapter->netdev->features &NETIF_F_RXFCS );
Signature · 1 line
2.44.0
Alexander Lobakin
maintainerPATCH v10 10/10 MAINTAINERS: add entry for libeth and libie
In reply to Alexander LobakinAdd myself as a maintainer/supporter for libeth and libie. Let they have separate entries from the Intel ethernet code as it's a bit different case and all patches will go through me rather than Tony.
--- MAINTAINERS | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+)
MAINTAINERS +20 -0
@@ -12392,6 +12392,26 @@ F: drivers/ata/ F: include/linux/ata.h F: include/linux/libata.h +LIBETH COMMON ETHERNET LIBRARY +M: Alexander Lobakin <[email protected]> +L: [email protected] +L: [email protected] (moderated for non-subscribers) +S: Supported +T: git https://github.com/alobakin/linux.git +F: drivers/net/ethernet/intel/libeth/ +F: include/net/libeth/ +K: libeth + +LIBIE COMMON INTEL ETHERNET LIBRARY +M: Alexander Lobakin <[email protected]> +L: [email protected] (moderated for non-subscribers) +L: [email protected] +S: Supported +T: git https://github.com/alobakin/linux.git +F: drivers/net/ethernet/intel/libie/ +F: include/linux/net/intel/libie/ +K: libie + LIBNVDIMM BTT: BLOCK TRANSLATION TABLE M: Vishal Verma <[email protected]> M: Dan Williams <[email protected]>
Signature · 1 line
2.44.0
Quoted 84 lines · Alexander Lobakin
Here's a two-shot: introduce {,Intel} Ethernet common library (libeth and libie) and switch iavf to Page Pool. Details are in the commit messages; here's a summary:
Not a secret there's a ton of code duplication between two and more Intel ethernet modules. Before introducing new changes, which would need to be copied over again, start decoupling the already existing duplicate functionality into a new module, which will be shared between several Intel Ethernet drivers. The first name that came to my mind was "libie" -- "Intel Ethernet common library". Also this sounds like "lovelie" (-> one word, no "lib I E" pls) and can be expanded as "lib Internet Explorer" :P
The "generic", pure-software part is placed separately, so that it can be easily reused in any driver by any vendor without linking to the Intel pre-200G guts. In a few words, it's something any modern driver does the same way, but nobody moved it level up (yet).
The series is only the beginning. From now on, adding every new feature or doing any good driver refactoring will remove much more lines than add for quite some time. There's a basic roadmap with some deduplications planned already, not speaking of that touching every line now asks:
"can I share this?". The final destination is very ambitious: have only one unified driver for at least i40e, ice, iavf, and idpf with a struct ops for each generation. That's never gonna happen, right? But you still can at least try.
PP conversion for iavf lands within the same series as these two are tied closely. libie will support Page Pool model only, so that a driver can't use much of the lib until it's converted. iavf is only the example, the rest will eventually be converted soon on a per-driver basis. That is when it gets really interesting. Stay tech.Alexander Lobakin (10):
net: intel: introduce {,Intel} Ethernet common library
iavf: kill "legacy-rx" for good
iavf: drop page splitting and recycling
slab: introducekvmalloc_array_node()andkvcalloc_node()
page_pool: constify some read-only function arguments
page_pool: add DMA-sync-for-CPU inline helper
libeth: add Rx buffer management
iavf: packiavf_ringmore efficiently
iavf: switch to Page Pool
MAINTAINERS: add entry for libeth and libieMAINTAINERS | 20 + drivers/net/ethernet/intel/Kconfig | 7 + drivers/net/ethernet/intel/libeth/Kconfig | 9 + drivers/net/ethernet/intel/libie/Kconfig | 10 + drivers/net/ethernet/intel/Makefile | 3 + drivers/net/ethernet/intel/libeth/Makefile | 6 + drivers/net/ethernet/intel/libie/Makefile | 6 + include/net/page_pool/types.h | 4 +- .../net/ethernet/intel/i40e/i40e_prototype.h | 7 - drivers/net/ethernet/intel/i40e/i40e_type.h | 88 --- drivers/net/ethernet/intel/iavf/iavf.h | 2 +- .../net/ethernet/intel/iavf/iavf_prototype.h | 7 - drivers/net/ethernet/intel/iavf/iavf_txrx.h | 146 +---- drivers/net/ethernet/intel/iavf/iavf_type.h | 90 --- .../net/ethernet/intel/ice/ice_lan_tx_rx.h | 320 ---------- include/linux/net/intel/libie/rx.h | 50 ++ include/linux/slab.h | 17 +- include/net/libeth/rx.h | 242 ++++++++ include/net/page_pool/helpers.h | 34 +- drivers/net/ethernet/intel/i40e/i40e_common.c | 253 -------- drivers/net/ethernet/intel/i40e/i40e_main.c | 1 + drivers/net/ethernet/intel/i40e/i40e_txrx.c | 72 +-- drivers/net/ethernet/intel/iavf/iavf_common.c | 253 -------- .../net/ethernet/intel/iavf/iavf_ethtool.c | 140 ----- drivers/net/ethernet/intel/iavf/iavf_main.c | 40 +- drivers/net/ethernet/intel/iavf/iavf_txrx.c | 551 +++--------------- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 17 +- drivers/net/ethernet/intel/ice/ice_main.c | 1 + drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 111 +--- drivers/net/ethernet/intel/libeth/rx.c | 150 +++++ drivers/net/ethernet/intel/libie/rx.c | 124 ++++ net/core/page_pool.c | 10 +- 32 files changed, 836 insertions(+), 1955 deletions(-)create mode 100644
drivers/net/ethernet/intel/libeth/Kconfigcreate mode 100644drivers/net/ethernet/intel/libie/Kconfigcreate mode 100644drivers/net/ethernet/intel/libeth/Makefilecreate mode 100644drivers/net/ethernet/intel/libie/Makefilecreate mode 100644include/linux/net/intel/libie/rx.hcreate mode 100644include/net/libeth/rx.h
create mode 100644drivers/net/ethernet/intel/libeth/rx.ccreate mode 100644drivers/net/ethernet/intel/libie/rx.c
Quoted 7 lines
---
libeth has way more generic functionality and code in the idpf XDP tree[0], take a look if you want to have more complete picture of what this really is about.From v9[1]:
* pick Acked-by from Vlastimil and a couple Reviewed-by from Przemek;
thanks for the updates too!
I've read the code ~two times across the life of this series, nothing bad spot, so for the series:
Quoted 3 lines
* mention that the
libeth_fq::fpkernel-doc generates a warning and the fix for that is pending on the linux-doc ML (Jakub);
* no functional changes.
// ...