diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-04 13:38:03 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-04 13:38:03 -0700 |
commit | 0326074ff4652329f2a1a9c8685104576bd8d131 (patch) | |
tree | 9a7574c7ccb05bf4c7cb34fc5a65457bb8f495cb /drivers/net/ipa/gsi_trans.c | |
parent | 522667b24f08009591c90e75bfe2ffb67f555498 (diff) | |
parent | 681bf011b9b5989c6e9db6beb64494918aab9a43 (diff) |
Merge tag 'net-next-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski:
"Core:
- Introduce and use a single page frag cache for allocating small skb
heads, clawing back the 10-20% performance regression in UDP flood
test from previous fixes.
- Run packets which already went thru HW coalescing thru SW GRO. This
significantly improves TCP segment coalescing and simplifies
deployments as different workloads benefit from HW or SW GRO.
- Shrink the size of the base zero-copy send structure.
- Move TCP init under a new slow / sleepable version of DO_ONCE().
BPF:
- Add BPF-specific, any-context-safe memory allocator.
- Add helpers/kfuncs for PKCS#7 signature verification from BPF
programs.
- Define a new map type and related helpers for user space -> kernel
communication over a ring buffer (BPF_MAP_TYPE_USER_RINGBUF).
- Allow targeting BPF iterators to loop through resources of one
task/thread.
- Add ability to call selected destructive functions. Expose
crash_kexec() to allow BPF to trigger a kernel dump. Use
CAP_SYS_BOOT check on the loading process to judge permissions.
- Enable BPF to collect custom hierarchical cgroup stats efficiently
by integrating with the rstat framework.
- Support struct arguments for trampoline based programs. Only
structs with size <= 16B and x86 are supported.
- Invoke cgroup/connect{4,6} programs for unprivileged ICMP ping
sockets (instead of just TCP and UDP sockets).
- Add a helper for accessing CLOCK_TAI for time sensitive network
related programs.
- Support accessing network tunnel metadata's flags.
- Make TCP SYN ACK RTO tunable by BPF programs with TCP Fast Open.
- Add support for writing to Netfilter's nf_conn:mark.
Protocols:
- WiFi: more Extremely High Throughput (EHT) and Multi-Link Operation
(MLO) work (802.11be, WiFi 7).
- vsock: improve support for SO_RCVLOWAT.
- SMC: support SO_REUSEPORT.
- Netlink: define and document how to use netlink in a "modern" way.
Support reporting missing attributes via extended ACK.
- IPSec: support collect metadata mode for xfrm interfaces.
- TCPv6: send consistent autoflowlabel in SYN_RECV state and RST
packets.
- TCP: introduce optional per-netns connection hash table to allow
better isolation between namespaces (opt-in, at the cost of memory
and cache pressure).
- MPTCP: support TCP_FASTOPEN_CONNECT.
- Add NEXT-C-SID support in Segment Routing (SRv6) End behavior.
- Adjust IP_UNICAST_IF sockopt behavior for connected UDP sockets.
- Open vSwitch:
- Allow specifying ifindex of new interfaces.
- Allow conntrack and metering in non-initial user namespace.
- TLS: support the Korean ARIA-GCM crypto algorithm.
- Remove DECnet support.
Driver API:
- Allow selecting the conduit interface used by each port in DSA
switches, at runtime.
- Ethernet Power Sourcing Equipment and Power Device support.
- Add tc-taprio support for queueMaxSDU parameter, i.e. setting per
traffic class max frame size for time-based packet schedules.
- Support PHY rate matching - adapting between differing host-side
and link-side speeds.
- Introduce QUSGMII PHY mode and 1000BASE-KX interface mode.
- Validate OF (device tree) nodes for DSA shared ports; make
phylink-related properties mandatory on DSA and CPU ports.
Enforcing more uniformity should allow transitioning to phylink.
- Require that flash component name used during update matches one of
the components for which version is reported by info_get().
- Remove "weight" argument from driver-facing NAPI API as much as
possible. It's one of those magic knobs which seemed like a good
idea at the time but is too indirect to use in practice.
- Support offload of TLS connections with 256 bit keys.
New hardware / drivers:
- Ethernet:
- Microchip KSZ9896 6-port Gigabit Ethernet Switch
- Renesas Ethernet AVB (EtherAVB-IF) Gen4 SoCs
- Analog Devices ADIN1110 and ADIN2111 industrial single pair
Ethernet (10BASE-T1L) MAC+PHY.
- Rockchip RV1126 Gigabit Ethernet (a version of stmmac IP).
- Ethernet SFPs / modules:
- RollBall / Hilink / Turris 10G copper SFPs
- HALNy GPON module
- WiFi:
- CYW43439 SDIO chipset (brcmfmac)
- CYW89459 PCIe chipset (brcmfmac)
- BCM4378 on Apple platforms (brcmfmac)
Drivers:
- CAN:
- gs_usb: HW timestamp support
- Ethernet PHYs:
- lan8814: cable diagnostics
- Ethernet NICs:
- Intel (100G):
- implement control of FCS/CRC stripping
- port splitting via devlink
- L2TPv3 filtering offload
- nVidia/Mellanox:
- tunnel offload for sub-functions
- MACSec offload, w/ Extended packet number and replay window
offload
- significantly restructure, and optimize the AF_XDP support,
align the behavior with other vendors
- Huawei:
- configuring DSCP map for traffic class selection
- querying standard FEC statistics
- querying SerDes lane number via ethtool
- Marvell/Cavium:
- egress priority flow control
- MACSec offload
- AMD/SolarFlare:
- PTP over IPv6 and raw Ethernet
- small / embedded:
- ax88772: convert to phylink (to support SFP cages)
- altera: tse: convert to phylink
- ftgmac100: support fixed link
- enetc: standard Ethtool counters
- macb: ZynqMP SGMII dynamic configuration support
- tsnep: support multi-queue and use page pool
- lan743x: Rx IP & TCP checksum offload
- igc: add xdp frags support to ndo_xdp_xmit
- Ethernet high-speed switches:
- Marvell (prestera):
- support SPAN port features (traffic mirroring)
- nexthop object offloading
- Microchip (sparx5):
- multicast forwarding offload
- QoS queuing offload (tc-mqprio, tc-tbf, tc-ets)
- Ethernet embedded switches:
- Marvell (mv88e6xxx):
- support RGMII cmode
- NXP (felix):
- standardized ethtool counters
- Microchip (lan966x):
- QoS queuing offload (tc-mqprio, tc-tbf, tc-cbs, tc-ets)
- traffic policing and mirroring
- link aggregation / bonding offload
- QUSGMII PHY mode support
- Qualcomm 802.11ax WiFi (ath11k):
- cold boot calibration support on WCN6750
- support to connect to a non-transmit MBSSID AP profile
- enable remain-on-channel support on WCN6750
- Wake-on-WLAN support for WCN6750
- support to provide transmit power from firmware via nl80211
- support to get power save duration for each client
- spectral scan support for 160 MHz
- MediaTek WiFi (mt76):
- WiFi-to-Ethernet bridging offload for MT7986 chips
- RealTek WiFi (rtw89):
- P2P support"
* tag 'net-next-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1864 commits)
eth: pse: add missing static inlines
once: rename _SLOW to _SLEEPABLE
net: pse-pd: add regulator based PSE driver
dt-bindings: net: pse-dt: add bindings for regulator based PoDL PSE controller
ethtool: add interface to interact with Ethernet Power Equipment
net: mdiobus: search for PSE nodes by parsing PHY nodes.
net: mdiobus: fwnode_mdiobus_register_phy() rework error handling
net: add framework to support Ethernet PSE and PDs devices
dt-bindings: net: phy: add PoDL PSE property
net: marvell: prestera: Propagate nh state from hw to kernel
net: marvell: prestera: Add neighbour cache accounting
net: marvell: prestera: add stub handler neighbour events
net: marvell: prestera: Add heplers to interact with fib_notifier_info
net: marvell: prestera: Add length macros for prestera_ip_addr
net: marvell: prestera: add delayed wq and flush wq on deinit
net: marvell: prestera: Add strict cleanup of fib arbiter
net: marvell: prestera: Add cleanup of allocated fib_nodes
net: marvell: prestera: Add router nexthops ABI
eth: octeon: fix build after netif_napi_add() changes
net/mlx5: E-Switch, Return EBUSY if can't get mode lock
...
Diffstat (limited to 'drivers/net/ipa/gsi_trans.c')
-rw-r--r-- | drivers/net/ipa/gsi_trans.c | 221 |
1 files changed, 106 insertions, 115 deletions
diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index 18e7e8c405be..26b7f683a3e1 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved. - * Copyright (C) 2019-2020 Linaro Ltd. + * Copyright (C) 2019-2022 Linaro Ltd. */ #include <linux/types.h> @@ -22,37 +22,36 @@ * DOC: GSI Transactions * * A GSI transaction abstracts the behavior of a GSI channel by representing - * everything about a related group of IPA commands in a single structure. - * (A "command" in this sense is either a data transfer or an IPA immediate + * everything about a related group of IPA operations in a single structure. + * (A "operation" in this sense is either a data transfer or an IPA immediate * command.) Most details of interaction with the GSI hardware are managed - * by the GSI transaction core, allowing users to simply describe commands + * by the GSI transaction core, allowing users to simply describe operations * to be performed. When a transaction has completed a callback function * (dependent on the type of endpoint associated with the channel) allows * cleanup of resources associated with the transaction. * - * To perform a command (or set of them), a user of the GSI transaction + * To perform an operation (or set of them), a user of the GSI transaction * interface allocates a transaction, indicating the number of TREs required - * (one per command). If sufficient TREs are available, they are reserved + * (one per operation). If sufficient TREs are available, they are reserved * for use in the transaction and the allocation succeeds. This way - * exhaustion of the available TREs in a channel ring is detected - * as early as possible. All resources required to complete a transaction - * are allocated at transaction allocation time. + * exhaustion of the available TREs in a channel ring is detected as early + * as possible. Any other resources that might be needed to complete a + * transaction are also allocated when the transaction is allocated. * - * Commands performed as part of a transaction are represented in an array - * of Linux scatterlist structures. This array is allocated with the - * transaction, and its entries are initialized using standard scatterlist - * functions (such as sg_set_buf() or skb_to_sgvec()). + * Operations performed as part of a transaction are represented in an array + * of Linux scatterlist structures, allocated with the transaction. These + * scatterlist structures are initialized by "adding" operations to the + * transaction. If a buffer in an operation must be mapped for DMA, this is + * done at the time it is added to the transaction. It is possible for a + * mapping error to occur when an operation is added. In this case the + * transaction should simply be freed; this correctly releases resources + * associated with the transaction. * - * Once a transaction's scatterlist structures have been initialized, the - * transaction is committed. The caller is responsible for mapping buffers - * for DMA if necessary, and this should be done *before* allocating - * the transaction. Between a successful allocation and commit of a - * transaction no errors should occur. - * - * Committing transfers ownership of the entire transaction to the GSI - * transaction core. The GSI transaction code formats the content of - * the scatterlist array into the channel ring buffer and informs the - * hardware that new TREs are available to process. + * Once all operations have been successfully added to a transaction, the + * transaction is committed. Committing transfers ownership of the entire + * transaction to the GSI transaction core. The GSI transaction code + * formats the content of the scatterlist array into the channel ring + * buffer and informs the hardware that new TREs are available to process. * * The last TRE in each transaction is marked to interrupt the AP when the * GSI hardware has completed it. Because transfers described by TREs are @@ -125,11 +124,10 @@ void gsi_trans_pool_exit(struct gsi_trans_pool *pool) memset(pool, 0, sizeof(*pool)); } -/* Allocate the requested number of (zeroed) entries from the pool */ -/* Home-grown DMA pool. This way we can preallocate and use the tre_count - * to guarantee allocations will succeed. Even though we specify max_alloc - * (and it can be more than one), we only allow allocation of a single - * element from a DMA pool. +/* Home-grown DMA pool. This way we can preallocate the pool, and guarantee + * allocations will succeed. The immediate commands in a transaction can + * require up to max_alloc elements from the pool. But we only allow + * allocation of a single element from a DMA pool at a time. */ int gsi_trans_pool_init_dma(struct device *dev, struct gsi_trans_pool *pool, size_t size, u32 count, u32 max_alloc) @@ -237,68 +235,63 @@ gsi_channel_trans_mapped(struct gsi_channel *channel, u32 index) /* Return the oldest completed transaction for a channel (or null) */ struct gsi_trans *gsi_channel_trans_complete(struct gsi_channel *channel) { - return list_first_entry_or_null(&channel->trans_info.complete, - struct gsi_trans, links); + struct gsi_trans_info *trans_info = &channel->trans_info; + u16 trans_id = trans_info->completed_id; + + if (trans_id == trans_info->pending_id) { + gsi_channel_update(channel); + if (trans_id == trans_info->pending_id) + return NULL; + } + + return &trans_info->trans[trans_id %= channel->tre_count]; } -/* Move a transaction from the allocated list to the committed list */ +/* Move a transaction from allocated to committed state */ static void gsi_trans_move_committed(struct gsi_trans *trans) { struct gsi_channel *channel = &trans->gsi->channel[trans->channel_id]; struct gsi_trans_info *trans_info = &channel->trans_info; - spin_lock_bh(&trans_info->spinlock); - - list_move_tail(&trans->links, &trans_info->committed); - - spin_unlock_bh(&trans_info->spinlock); + /* This allocated transaction is now committed */ + trans_info->allocated_id++; } -/* Move transactions from the committed list to the pending list */ +/* Move committed transactions to pending state */ static void gsi_trans_move_pending(struct gsi_trans *trans) { struct gsi_channel *channel = &trans->gsi->channel[trans->channel_id]; struct gsi_trans_info *trans_info = &channel->trans_info; - struct list_head list; - - spin_lock_bh(&trans_info->spinlock); + u16 trans_index = trans - &trans_info->trans[0]; + u16 delta; - /* Move this transaction and all predecessors to the pending list */ - list_cut_position(&list, &trans_info->committed, &trans->links); - list_splice_tail(&list, &trans_info->pending); - - spin_unlock_bh(&trans_info->spinlock); + /* These committed transactions are now pending */ + delta = trans_index - trans_info->committed_id + 1; + trans_info->committed_id += delta % channel->tre_count; } -/* Move a transaction and all of its predecessors from the pending list - * to the completed list. - */ +/* Move pending transactions to completed state */ void gsi_trans_move_complete(struct gsi_trans *trans) { struct gsi_channel *channel = &trans->gsi->channel[trans->channel_id]; struct gsi_trans_info *trans_info = &channel->trans_info; - struct list_head list; + u16 trans_index = trans - trans_info->trans; + u16 delta; - spin_lock_bh(&trans_info->spinlock); - - /* Move this transaction and all predecessors to completed list */ - list_cut_position(&list, &trans_info->pending, &trans->links); - list_splice_tail(&list, &trans_info->complete); - - spin_unlock_bh(&trans_info->spinlock); + /* These pending transactions are now completed */ + delta = trans_index - trans_info->pending_id + 1; + delta %= channel->tre_count; + trans_info->pending_id += delta; } -/* Move a transaction from the completed list to the polled list */ +/* Move a transaction from completed to polled state */ void gsi_trans_move_polled(struct gsi_trans *trans) { struct gsi_channel *channel = &trans->gsi->channel[trans->channel_id]; struct gsi_trans_info *trans_info = &channel->trans_info; - spin_lock_bh(&trans_info->spinlock); - - list_move_tail(&trans->links, &trans_info->polled); - - spin_unlock_bh(&trans_info->spinlock); + /* This completed transaction is now polled */ + trans_info->completed_id++; } /* Reserve some number of TREs on a channel. Returns true if successful */ @@ -343,20 +336,22 @@ struct gsi_trans *gsi_channel_trans_alloc(struct gsi *gsi, u32 channel_id, struct gsi_channel *channel = &gsi->channel[channel_id]; struct gsi_trans_info *trans_info; struct gsi_trans *trans; + u16 trans_index; if (WARN_ON(tre_count > channel->trans_tre_max)) return NULL; trans_info = &channel->trans_info; - /* We reserve the TREs now, but consume them at commit time. - * If there aren't enough available, we're done. - */ + /* If we can't reserve the TREs for the transaction, we're done */ if (!gsi_trans_tre_reserve(trans_info, tre_count)) return NULL; - /* Allocate and initialize non-zero fields in the transaction */ - trans = gsi_trans_pool_alloc(&trans_info->pool, 1); + trans_index = trans_info->free_id % channel->tre_count; + trans = &trans_info->trans[trans_index]; + memset(trans, 0, sizeof(*trans)); + + /* Initialize non-zero fields in the transaction */ trans->gsi = gsi; trans->channel_id = channel_id; trans->rsvd_count = tre_count; @@ -367,45 +362,37 @@ struct gsi_trans *gsi_channel_trans_alloc(struct gsi *gsi, u32 channel_id, sg_init_marker(trans->sgl, tre_count); trans->direction = direction; - - spin_lock_bh(&trans_info->spinlock); - - list_add_tail(&trans->links, &trans_info->alloc); - - spin_unlock_bh(&trans_info->spinlock); - refcount_set(&trans->refcount, 1); + /* This free transaction is now allocated */ + trans_info->free_id++; + return trans; } /* Free a previously-allocated transaction */ void gsi_trans_free(struct gsi_trans *trans) { - refcount_t *refcount = &trans->refcount; struct gsi_trans_info *trans_info; - bool last; - /* We must hold the lock to release the last reference */ - if (refcount_dec_not_one(refcount)) + if (!refcount_dec_and_test(&trans->refcount)) return; + /* Unused transactions are allocated but never committed, pending, + * completed, or polled. + */ trans_info = &trans->gsi->channel[trans->channel_id].trans_info; - - spin_lock_bh(&trans_info->spinlock); - - /* Reference might have been added before we got the lock */ - last = refcount_dec_and_test(refcount); - if (last) - list_del(&trans->links); - - spin_unlock_bh(&trans_info->spinlock); - - if (!last) - return; - - if (trans->used_count) + if (!trans->used_count) { + trans_info->allocated_id++; + trans_info->committed_id++; + trans_info->pending_id++; + trans_info->completed_id++; + } else { ipa_gsi_trans_release(trans); + } + + /* This transaction is now free */ + trans_info->polled_id++; /* Releasing the reserved TREs implicitly frees the sgl[] and * (if present) info[] arrays, plus the transaction itself. @@ -548,8 +535,8 @@ static void gsi_trans_tre_fill(struct gsi_tre *dest_tre, dma_addr_t addr, * * Formats channel ring TRE entries based on the content of the scatterlist. * Maps a transaction pointer to the last ring entry used for the transaction, - * so it can be recovered when it completes. Moves the transaction to the - * pending list. Finally, updates the channel ring pointer and optionally + * so it can be recovered when it completes. Moves the transaction to + * pending state. Finally, updates the channel ring pointer and optionally * rings the doorbell. */ static void __gsi_trans_commit(struct gsi_trans *trans, bool ring_db) @@ -654,23 +641,27 @@ void gsi_trans_complete(struct gsi_trans *trans) void gsi_channel_trans_cancel_pending(struct gsi_channel *channel) { struct gsi_trans_info *trans_info = &channel->trans_info; - struct gsi_trans *trans; - bool cancelled; + u16 trans_id = trans_info->pending_id; /* channel->gsi->mutex is held by caller */ - spin_lock_bh(&trans_info->spinlock); - cancelled = !list_empty(&trans_info->pending); - list_for_each_entry(trans, &trans_info->pending, links) - trans->cancelled = true; + /* If there are no pending transactions, we're done */ + if (trans_id == trans_info->committed_id) + return; - list_splice_tail_init(&trans_info->pending, &trans_info->complete); + /* Mark all pending transactions cancelled */ + do { + struct gsi_trans *trans; + + trans = &trans_info->trans[trans_id % channel->tre_count]; + trans->cancelled = true; + } while (++trans_id != trans_info->committed_id); - spin_unlock_bh(&trans_info->spinlock); + /* All pending transactions are now completed */ + trans_info->pending_id = trans_info->committed_id; /* Schedule NAPI polling to complete the cancelled transactions */ - if (cancelled) - napi_schedule(&channel->napi); + napi_schedule(&channel->napi); } /* Issue a command to read a single byte from a channel */ @@ -736,10 +727,16 @@ int gsi_channel_trans_init(struct gsi *gsi, u32 channel_id) * modulo that number to determine the next one that's free. * Transactions are allocated one at a time. */ - ret = gsi_trans_pool_init(&trans_info->pool, sizeof(struct gsi_trans), - tre_max, 1); - if (ret) + trans_info->trans = kcalloc(tre_count, sizeof(*trans_info->trans), + GFP_KERNEL); + if (!trans_info->trans) return -ENOMEM; + trans_info->free_id = 0; /* all modulo channel->tre_count */ + trans_info->allocated_id = 0; + trans_info->committed_id = 0; + trans_info->pending_id = 0; + trans_info->completed_id = 0; + trans_info->polled_id = 0; /* A completion event contains a pointer to the TRE that caused * the event (which will be the last one used by the transaction). @@ -765,19 +762,13 @@ int gsi_channel_trans_init(struct gsi *gsi, u32 channel_id) if (ret) goto err_map_free; - spin_lock_init(&trans_info->spinlock); - INIT_LIST_HEAD(&trans_info->alloc); - INIT_LIST_HEAD(&trans_info->committed); - INIT_LIST_HEAD(&trans_info->pending); - INIT_LIST_HEAD(&trans_info->complete); - INIT_LIST_HEAD(&trans_info->polled); return 0; err_map_free: kfree(trans_info->map); err_trans_free: - gsi_trans_pool_exit(&trans_info->pool); + kfree(trans_info->trans); dev_err(gsi->dev, "error %d initializing channel %u transactions\n", ret, channel_id); @@ -791,6 +782,6 @@ void gsi_channel_trans_exit(struct gsi_channel *channel) struct gsi_trans_info *trans_info = &channel->trans_info; gsi_trans_pool_exit(&trans_info->sg_pool); - gsi_trans_pool_exit(&trans_info->pool); + kfree(trans_info->trans); kfree(trans_info->map); } |