From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- fs/netfs/buffered_read.c | 433 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 433 insertions(+) create mode 100644 fs/netfs/buffered_read.c (limited to 'fs/netfs/buffered_read.c') diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c new file mode 100644 index 000000000..7679a68e8 --- /dev/null +++ b/fs/netfs/buffered_read.c @@ -0,0 +1,433 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Network filesystem high-level buffered read support. + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include "internal.h" + +/* + * Unlock the folios in a read operation. We need to set PG_fscache on any + * folios we're going to write back before we unlock them. + */ +void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t start_page = rreq->start / PAGE_SIZE; + pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; + size_t account = 0; + bool subreq_failed = false; + + XA_STATE(xas, &rreq->mapping->i_pages, start_page); + + if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) { + __clear_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags); + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); + } + } + + /* Walk through the pagecache and the I/O request lists simultaneously. + * We may have a mixture of cached and uncached sections and we only + * really want to write out the uncached sections. This is slightly + * complicated by the possibility that we might have huge pages with a + * mixture inside. + */ + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + subreq_failed = (subreq->error < 0); + + trace_netfs_rreq(rreq, netfs_rreq_trace_unlock); + + rcu_read_lock(); + xas_for_each(&xas, folio, last_page) { + loff_t pg_end; + bool pg_failed = false; + + if (xas_retry(&xas, folio)) + continue; + + pg_end = folio_pos(folio) + folio_size(folio) - 1; + + for (;;) { + loff_t sreq_end; + + if (!subreq) { + pg_failed = true; + break; + } + if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) + folio_start_fscache(folio); + pg_failed |= subreq_failed; + sreq_end = subreq->start + subreq->len - 1; + if (pg_end < sreq_end) + break; + + account += subreq->transferred; + if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + subreq = list_next_entry(subreq, rreq_link); + subreq_failed = (subreq->error < 0); + } else { + subreq = NULL; + subreq_failed = false; + } + + if (pg_end == sreq_end) + break; + } + + if (!pg_failed) { + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + } + + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio_index(folio) == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) + _debug("no unlock"); + else + folio_unlock(folio); + } + } + rcu_read_unlock(); + + task_io_account_read(account); + if (rreq->netfs_ops->done) + rreq->netfs_ops->done(rreq); +} + +static void netfs_cache_expand_readahead(struct netfs_io_request *rreq, + loff_t *_start, size_t *_len, loff_t i_size) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + + if (cres->ops && cres->ops->expand_readahead) + cres->ops->expand_readahead(cres, _start, _len, i_size); +} + +static void netfs_rreq_expand(struct netfs_io_request *rreq, + struct readahead_control *ractl) +{ + /* Give the cache a chance to change the request parameters. The + * resultant request must contain the original region. + */ + netfs_cache_expand_readahead(rreq, &rreq->start, &rreq->len, rreq->i_size); + + /* Give the netfs a chance to change the request parameters. The + * resultant request must contain the original region. + */ + if (rreq->netfs_ops->expand_readahead) + rreq->netfs_ops->expand_readahead(rreq); + + /* Expand the request if the cache wants it to start earlier. Note + * that the expansion may get further extended if the VM wishes to + * insert THPs and the preferred start and/or end wind up in the middle + * of THPs. + * + * If this is the case, however, the THP size should be an integer + * multiple of the cache granule size, so we get a whole number of + * granules to deal with. + */ + if (rreq->start != readahead_pos(ractl) || + rreq->len != readahead_length(ractl)) { + readahead_expand(ractl, rreq->start, rreq->len); + rreq->start = readahead_pos(ractl); + rreq->len = readahead_length(ractl); + + trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), + netfs_read_trace_expanded); + } +} + +/** + * netfs_readahead - Helper to manage a read request + * @ractl: The description of the readahead request + * + * Fulfil a readahead request by drawing data from the cache if possible, or + * the netfs if not. Space beyond the EOF is zero-filled. Multiple I/O + * requests from different sources will get munged together. If necessary, the + * readahead window can be expanded in either direction to a more convenient + * alighment for RPC efficiency or to make storage in the cache feasible. + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. + */ +void netfs_readahead(struct readahead_control *ractl) +{ + struct netfs_io_request *rreq; + struct netfs_inode *ctx = netfs_inode(ractl->mapping->host); + int ret; + + _enter("%lx,%x", readahead_index(ractl), readahead_count(ractl)); + + if (readahead_count(ractl) == 0) + return; + + rreq = netfs_alloc_request(ractl->mapping, ractl->file, + readahead_pos(ractl), + readahead_length(ractl), + NETFS_READAHEAD); + if (IS_ERR(rreq)) + return; + + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto cleanup_free; + } + + netfs_stat(&netfs_n_rh_readahead); + trace_netfs_read(rreq, readahead_pos(ractl), readahead_length(ractl), + netfs_read_trace_readahead); + + netfs_rreq_expand(rreq, ractl); + + /* Drop the refs on the folios here rather than in the cache or + * filesystem. The locks will be dropped in netfs_rreq_unlock(). + */ + while (readahead_folio(ractl)) + ; + + netfs_begin_read(rreq, false); + return; + +cleanup_free: + netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); + return; +} +EXPORT_SYMBOL(netfs_readahead); + +/** + * netfs_read_folio - Helper to manage a read_folio request + * @file: The file to read from + * @folio: The folio to read + * + * Fulfil a read_folio request by drawing data from the cache if + * possible, or the netfs if not. Space beyond the EOF is zero-filled. + * Multiple I/O requests from different sources will get munged together. + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. + */ +int netfs_read_folio(struct file *file, struct folio *folio) +{ + struct address_space *mapping = folio_file_mapping(folio); + struct netfs_io_request *rreq; + struct netfs_inode *ctx = netfs_inode(mapping->host); + int ret; + + _enter("%lx", folio_index(folio)); + + rreq = netfs_alloc_request(mapping, file, + folio_file_pos(folio), folio_size(folio), + NETFS_READPAGE); + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); + goto alloc_error; + } + + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto discard; + } + + netfs_stat(&netfs_n_rh_readpage); + trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage); + return netfs_begin_read(rreq, true); + +discard: + netfs_put_request(rreq, false, netfs_rreq_trace_put_discard); +alloc_error: + folio_unlock(folio); + return ret; +} +EXPORT_SYMBOL(netfs_read_folio); + +/* + * Prepare a folio for writing without reading first + * @folio: The folio being prepared + * @pos: starting position for the write + * @len: length of write + * @always_fill: T if the folio should always be completely filled/cleared + * + * In some cases, write_begin doesn't need to read at all: + * - full folio write + * - write that lies in a folio that is completely beyond EOF + * - write that covers the folio from start to EOF or beyond it + * + * If any of these criteria are met, then zero out the unwritten parts + * of the folio and return true. Otherwise, return false. + */ +static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len, + bool always_fill) +{ + struct inode *inode = folio_inode(folio); + loff_t i_size = i_size_read(inode); + size_t offset = offset_in_folio(folio, pos); + size_t plen = folio_size(folio); + + if (unlikely(always_fill)) { + if (pos - offset + len <= i_size) + return false; /* Page entirely before EOF */ + zero_user_segment(&folio->page, 0, plen); + folio_mark_uptodate(folio); + return true; + } + + /* Full folio write */ + if (offset == 0 && len >= plen) + return true; + + /* Page entirely beyond the end of the file */ + if (pos - offset >= i_size) + goto zero_out; + + /* Write that covers from the start of the folio to EOF or beyond */ + if (offset == 0 && (pos + len) >= i_size) + goto zero_out; + + return false; +zero_out: + zero_user_segments(&folio->page, 0, offset, offset + len, plen); + return true; +} + +/** + * netfs_write_begin - Helper to prepare for writing + * @ctx: The netfs context + * @file: The file to read from + * @mapping: The mapping to read from + * @pos: File position at which the write will begin + * @len: The length of the write (may extend beyond the end of the folio chosen) + * @_folio: Where to put the resultant folio + * @_fsdata: Place for the netfs to store a cookie + * + * Pre-read data for a write-begin request by drawing data from the cache if + * possible, or the netfs if not. Space beyond the EOF is zero-filled. + * Multiple I/O requests from different sources will get munged together. If + * necessary, the readahead window can be expanded in either direction to a + * more convenient alighment for RPC efficiency or to make storage in the cache + * feasible. + * + * The calling netfs must provide a table of operations, only one of which, + * issue_op, is mandatory. + * + * The check_write_begin() operation can be provided to check for and flush + * conflicting writes once the folio is grabbed and locked. It is passed a + * pointer to the fsdata cookie that gets returned to the VM to be passed to + * write_end. It is permitted to sleep. It should return 0 if the request + * should go ahead or it may return an error. It may also unlock and put the + * folio, provided it sets ``*foliop`` to NULL, in which case a return of 0 + * will cause the folio to be re-got and the process to be retried. + * + * The calling netfs must initialise a netfs context contiguous to the vfs + * inode before calling this. + * + * This is usable whether or not caching is enabled. + */ +int netfs_write_begin(struct netfs_inode *ctx, + struct file *file, struct address_space *mapping, + loff_t pos, unsigned int len, struct folio **_folio, + void **_fsdata) +{ + struct netfs_io_request *rreq; + struct folio *folio; + unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; + pgoff_t index = pos >> PAGE_SHIFT; + int ret; + + DEFINE_READAHEAD(ractl, file, NULL, mapping, index); + +retry: + folio = __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); + if (!folio) + return -ENOMEM; + + if (ctx->ops->check_write_begin) { + /* Allow the netfs (eg. ceph) to flush conflicts. */ + ret = ctx->ops->check_write_begin(file, pos, len, &folio, _fsdata); + if (ret < 0) { + trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin); + goto error; + } + if (!folio) + goto retry; + } + + if (folio_test_uptodate(folio)) + goto have_folio; + + /* If the page is beyond the EOF, we want to clear it - unless it's + * within the cache granule containing the EOF, in which case we need + * to preload the granule. + */ + if (!netfs_is_cache_enabled(ctx) && + netfs_skip_folio_read(folio, pos, len, false)) { + netfs_stat(&netfs_n_rh_write_zskip); + goto have_folio_no_wait; + } + + rreq = netfs_alloc_request(mapping, file, + folio_file_pos(folio), folio_size(folio), + NETFS_READ_FOR_WRITE); + if (IS_ERR(rreq)) { + ret = PTR_ERR(rreq); + goto error; + } + rreq->no_unlock_folio = folio_index(folio); + __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); + + if (ctx->ops->begin_cache_operation) { + ret = ctx->ops->begin_cache_operation(rreq); + if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) + goto error_put; + } + + netfs_stat(&netfs_n_rh_write_begin); + trace_netfs_read(rreq, pos, len, netfs_read_trace_write_begin); + + /* Expand the request to meet caching requirements and download + * preferences. + */ + ractl._nr_pages = folio_nr_pages(folio); + netfs_rreq_expand(rreq, &ractl); + + /* We hold the folio locks, so we can drop the references */ + folio_get(folio); + while (readahead_folio(&ractl)) + ; + + ret = netfs_begin_read(rreq, true); + if (ret < 0) + goto error; + +have_folio: + ret = folio_wait_fscache_killable(folio); + if (ret < 0) + goto error; +have_folio_no_wait: + *_folio = folio; + _leave(" = 0"); + return 0; + +error_put: + netfs_put_request(rreq, false, netfs_rreq_trace_put_failed); +error: + if (folio) { + folio_unlock(folio); + folio_put(folio); + } + _leave(" = %d", ret); + return ret; +} +EXPORT_SYMBOL(netfs_write_begin); -- cgit v1.2.3