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/nilfs2/segment.h | 249 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 249 insertions(+) create mode 100644 fs/nilfs2/segment.h (limited to 'fs/nilfs2/segment.h') diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h new file mode 100644 index 000000000..1060f72eb --- /dev/null +++ b/fs/nilfs2/segment.h @@ -0,0 +1,249 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * NILFS Segment constructor prototypes and definitions + * + * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. + * + * Written by Ryusuke Konishi. + * + */ +#ifndef _NILFS_SEGMENT_H +#define _NILFS_SEGMENT_H + +#include +#include +#include +#include +#include "nilfs.h" + +struct nilfs_root; + +/** + * struct nilfs_recovery_info - Recovery information + * @ri_need_recovery: Recovery status + * @ri_super_root: Block number of the last super root + * @ri_ri_cno: Number of the last checkpoint + * @ri_lsegs_start: Region for roll-forwarding (start block number) + * @ri_lsegs_end: Region for roll-forwarding (end block number) + * @ri_lseg_start_seq: Sequence value of the segment at ri_lsegs_start + * @ri_used_segments: List of segments to be mark active + * @ri_pseg_start: Block number of the last partial segment + * @ri_seq: Sequence number on the last partial segment + * @ri_segnum: Segment number on the last partial segment + * @ri_nextnum: Next segment number on the last partial segment + */ +struct nilfs_recovery_info { + int ri_need_recovery; + sector_t ri_super_root; + __u64 ri_cno; + + sector_t ri_lsegs_start; + sector_t ri_lsegs_end; + u64 ri_lsegs_start_seq; + struct list_head ri_used_segments; + sector_t ri_pseg_start; + u64 ri_seq; + __u64 ri_segnum; + __u64 ri_nextnum; +}; + +/* ri_need_recovery */ +#define NILFS_RECOVERY_SR_UPDATED 1 /* The super root was updated */ +#define NILFS_RECOVERY_ROLLFORWARD_DONE 2 /* Rollforward was carried out */ + +/** + * struct nilfs_cstage - Context of collection stage + * @scnt: Stage count, must be accessed via wrappers: + * nilfs_sc_cstage_inc(), nilfs_sc_cstage_set(), nilfs_sc_cstage_get() + * @flags: State flags + * @dirty_file_ptr: Pointer on dirty_files list, or inode of a target file + * @gc_inode_ptr: Pointer on the list of gc-inodes + */ +struct nilfs_cstage { + int scnt; + unsigned int flags; + struct nilfs_inode_info *dirty_file_ptr; + struct nilfs_inode_info *gc_inode_ptr; +}; + +struct nilfs_segment_buffer; + +struct nilfs_segsum_pointer { + struct buffer_head *bh; + unsigned int offset; /* offset in bytes */ +}; + +/** + * struct nilfs_sc_info - Segment constructor information + * @sc_super: Back pointer to super_block struct + * @sc_root: root object of the current filesystem tree + * @sc_nblk_inc: Block count of current generation + * @sc_dirty_files: List of files to be written + * @sc_gc_inodes: List of GC inodes having blocks to be written + * @sc_iput_queue: list of inodes for which iput should be done + * @sc_iput_work: work struct to defer iput call + * @sc_freesegs: array of segment numbers to be freed + * @sc_nfreesegs: number of segments on @sc_freesegs + * @sc_dsync_inode: inode whose data pages are written for a sync operation + * @sc_dsync_start: start byte offset of data pages + * @sc_dsync_end: end byte offset of data pages (inclusive) + * @sc_segbufs: List of segment buffers + * @sc_write_logs: List of segment buffers to hold logs under writing + * @sc_segbuf_nblocks: Number of available blocks in segment buffers. + * @sc_curseg: Current segment buffer + * @sc_stage: Collection stage + * @sc_finfo_ptr: pointer to the current finfo struct in the segment summary + * @sc_binfo_ptr: pointer to the current binfo struct in the segment summary + * @sc_blk_cnt: Block count of a file + * @sc_datablk_cnt: Data block count of a file + * @sc_nblk_this_inc: Number of blocks included in the current logical segment + * @sc_seg_ctime: Creation time + * @sc_cno: checkpoint number of current log + * @sc_flags: Internal flags + * @sc_state_lock: spinlock for sc_state and so on + * @sc_state: Segctord state flags + * @sc_flush_request: inode bitmap of metadata files to be flushed + * @sc_wait_request: Client request queue + * @sc_wait_daemon: Daemon wait queue + * @sc_wait_task: Start/end wait queue to control segctord task + * @sc_seq_request: Request counter + * @sc_seq_accept: Accepted request count + * @sc_seq_done: Completion counter + * @sc_sync: Request of explicit sync operation + * @sc_interval: Timeout value of background construction + * @sc_mjcp_freq: Frequency of creating checkpoints + * @sc_lseg_stime: Start time of the latest logical segment + * @sc_watermark: Watermark for the number of dirty buffers + * @sc_timer: Timer for segctord + * @sc_task: current thread of segctord + */ +struct nilfs_sc_info { + struct super_block *sc_super; + struct nilfs_root *sc_root; + + unsigned long sc_nblk_inc; + + struct list_head sc_dirty_files; + struct list_head sc_gc_inodes; + struct list_head sc_iput_queue; + struct work_struct sc_iput_work; + + __u64 *sc_freesegs; + size_t sc_nfreesegs; + + struct nilfs_inode_info *sc_dsync_inode; + loff_t sc_dsync_start; + loff_t sc_dsync_end; + + /* Segment buffers */ + struct list_head sc_segbufs; + struct list_head sc_write_logs; + unsigned long sc_segbuf_nblocks; + struct nilfs_segment_buffer *sc_curseg; + + struct nilfs_cstage sc_stage; + + struct nilfs_segsum_pointer sc_finfo_ptr; + struct nilfs_segsum_pointer sc_binfo_ptr; + unsigned long sc_blk_cnt; + unsigned long sc_datablk_cnt; + unsigned long sc_nblk_this_inc; + time64_t sc_seg_ctime; + __u64 sc_cno; + unsigned long sc_flags; + + spinlock_t sc_state_lock; + unsigned long sc_state; + unsigned long sc_flush_request; + + wait_queue_head_t sc_wait_request; + wait_queue_head_t sc_wait_daemon; + wait_queue_head_t sc_wait_task; + + __u32 sc_seq_request; + __u32 sc_seq_accepted; + __u32 sc_seq_done; + + int sc_sync; + unsigned long sc_interval; + unsigned long sc_mjcp_freq; + unsigned long sc_lseg_stime; /* in 1/HZ seconds */ + unsigned long sc_watermark; + + struct timer_list sc_timer; + struct task_struct *sc_timer_task; + struct task_struct *sc_task; +}; + +/* sc_flags */ +enum { + NILFS_SC_DIRTY, /* One or more dirty meta-data blocks exist */ + NILFS_SC_UNCLOSED, /* Logical segment is not closed */ + NILFS_SC_SUPER_ROOT, /* The latest segment has a super root */ + NILFS_SC_PRIOR_FLUSH, /* + * Requesting immediate flush without making a + * checkpoint + */ + NILFS_SC_HAVE_DELTA, /* + * Next checkpoint will have update of files + * other than DAT, cpfile, sufile, or files + * moved by GC. + */ +}; + +/* sc_state */ +#define NILFS_SEGCTOR_QUIT 0x0001 /* segctord is being destroyed */ +#define NILFS_SEGCTOR_COMMIT 0x0004 /* committed transaction exists */ + +/* + * Constant parameters + */ +#define NILFS_SC_CLEANUP_RETRY 3 /* + * Retry count of construction when + * destroying segctord + */ + +/* + * Default values of timeout, in seconds. + */ +#define NILFS_SC_DEFAULT_TIMEOUT 5 /* + * Timeout value of dirty blocks. + * It triggers construction of a + * logical segment with a super root. + */ +#define NILFS_SC_DEFAULT_SR_FREQ 30 /* + * Maximum frequency of super root + * creation + */ + +/* + * The default threshold amount of data, in block counts. + */ +#define NILFS_SC_DEFAULT_WATERMARK 3600 + +/* super.c */ +extern struct kmem_cache *nilfs_transaction_cachep; + +/* segment.c */ +extern void nilfs_relax_pressure_in_lock(struct super_block *); + +extern int nilfs_construct_segment(struct super_block *); +extern int nilfs_construct_dsync_segment(struct super_block *, struct inode *, + loff_t, loff_t); +extern void nilfs_flush_segment(struct super_block *, ino_t); +extern int nilfs_clean_segments(struct super_block *, struct nilfs_argv *, + void **); + +int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root); +void nilfs_detach_log_writer(struct super_block *sb); + +/* recovery.c */ +extern int nilfs_read_super_root_block(struct the_nilfs *, sector_t, + struct buffer_head **, int); +extern int nilfs_search_super_root(struct the_nilfs *, + struct nilfs_recovery_info *); +int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs, struct super_block *sb, + struct nilfs_recovery_info *ri); +extern void nilfs_dispose_segment_list(struct list_head *); + +#endif /* _NILFS_SEGMENT_H */ -- cgit v1.2.3