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/nfs/nfs4file.c | 469 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 469 insertions(+) create mode 100644 fs/nfs/nfs4file.c (limited to 'fs/nfs/nfs4file.c') diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c new file mode 100644 index 000000000..2563ed858 --- /dev/null +++ b/fs/nfs/nfs4file.c @@ -0,0 +1,469 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/nfs/file.c + * + * Copyright (C) 1992 Rick Sladkey + */ +#include +#include +#include +#include +#include +#include +#include "delegation.h" +#include "internal.h" +#include "iostat.h" +#include "fscache.h" +#include "pnfs.h" + +#include "nfstrace.h" + +#ifdef CONFIG_NFS_V4_2 +#include "nfs42.h" +#endif + +#define NFSDBG_FACILITY NFSDBG_FILE + +static int +nfs4_file_open(struct inode *inode, struct file *filp) +{ + struct nfs_open_context *ctx; + struct dentry *dentry = file_dentry(filp); + struct dentry *parent = NULL; + struct inode *dir; + unsigned openflags = filp->f_flags; + struct iattr attr; + int err; + + /* + * If no cached dentry exists or if it's negative, NFSv4 handled the + * opens in ->lookup() or ->create(). + * + * We only get this far for a cached positive dentry. We skipped + * revalidation, so handle it here by dropping the dentry and returning + * -EOPENSTALE. The VFS will retry the lookup/create/open. + */ + + dprintk("NFS: open file(%pd2)\n", dentry); + + err = nfs_check_flags(openflags); + if (err) + return err; + + /* We can't create new files here */ + openflags &= ~(O_CREAT|O_EXCL); + + parent = dget_parent(dentry); + dir = d_inode(parent); + + ctx = alloc_nfs_open_context(file_dentry(filp), + flags_to_mode(openflags), filp); + err = PTR_ERR(ctx); + if (IS_ERR(ctx)) + goto out; + + attr.ia_valid = ATTR_OPEN; + if (openflags & O_TRUNC) { + attr.ia_valid |= ATTR_SIZE; + attr.ia_size = 0; + filemap_write_and_wait(inode->i_mapping); + } + + inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr, NULL); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + switch (err) { + default: + goto out_put_ctx; + case -ENOENT: + case -ESTALE: + case -EISDIR: + case -ENOTDIR: + case -ELOOP: + goto out_drop; + } + } + if (inode != d_inode(dentry)) + goto out_drop; + + nfs_file_set_open_context(filp, ctx); + nfs_fscache_open_file(inode, filp); + err = 0; + filp->f_mode |= FMODE_CAN_ODIRECT; + +out_put_ctx: + put_nfs_open_context(ctx); +out: + dput(parent); + return err; + +out_drop: + d_drop(dentry); + err = -EOPENSTALE; + goto out_put_ctx; +} + +/* + * Flush all dirty pages, and check for write errors. + */ +static int +nfs4_file_flush(struct file *file, fl_owner_t id) +{ + struct inode *inode = file_inode(file); + errseq_t since; + + dprintk("NFS: flush(%pD2)\n", file); + + nfs_inc_stats(inode, NFSIOS_VFSFLUSH); + if ((file->f_mode & FMODE_WRITE) == 0) + return 0; + + /* + * If we're holding a write delegation, then check if we're required + * to flush the i/o on close. If not, then just start the i/o now. + */ + if (!nfs4_delegation_flush_on_close(inode)) + return filemap_fdatawrite(file->f_mapping); + + /* Flush writes to the server and return any errors */ + since = filemap_sample_wb_err(file->f_mapping); + nfs_wb_all(inode); + return filemap_check_wb_err(file->f_mapping, since); +} + +#ifdef CONFIG_NFS_V4_2 +static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t count, unsigned int flags) +{ + struct nfs42_copy_notify_res *cn_resp = NULL; + struct nl4_server *nss = NULL; + nfs4_stateid *cnrs = NULL; + ssize_t ret; + bool sync = false; + + /* Only offload copy if superblock is the same */ + if (file_in->f_op != &nfs4_file_operations) + return -EXDEV; + if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY) || + !nfs_server_capable(file_inode(file_in), NFS_CAP_COPY)) + return -EOPNOTSUPP; + if (file_inode(file_in) == file_inode(file_out)) + return -EOPNOTSUPP; + /* if the copy size if smaller than 2 RPC payloads, make it + * synchronous + */ + if (count <= 2 * NFS_SERVER(file_inode(file_in))->rsize) + sync = true; +retry: + if (!nfs42_files_from_same_server(file_in, file_out)) { + /* + * for inter copy, if copy size is too small + * then fallback to generic copy. + */ + if (sync) + return -EOPNOTSUPP; + cn_resp = kzalloc(sizeof(struct nfs42_copy_notify_res), + GFP_KERNEL); + if (unlikely(cn_resp == NULL)) + return -ENOMEM; + + ret = nfs42_proc_copy_notify(file_in, file_out, cn_resp); + if (ret) { + ret = -EOPNOTSUPP; + goto out; + } + nss = &cn_resp->cnr_src; + cnrs = &cn_resp->cnr_stateid; + } + ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count, + nss, cnrs, sync); +out: + kfree(cn_resp); + + if (ret == -EAGAIN) + goto retry; + return ret; +} + +static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + size_t count, unsigned int flags) +{ + ssize_t ret; + + ret = __nfs4_copy_file_range(file_in, pos_in, file_out, pos_out, count, + flags); + if (ret == -EOPNOTSUPP || ret == -EXDEV) + ret = generic_copy_file_range(file_in, pos_in, file_out, + pos_out, count, flags); + return ret; +} + +static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence) +{ + loff_t ret; + + switch (whence) { + case SEEK_HOLE: + case SEEK_DATA: + ret = nfs42_proc_llseek(filep, offset, whence); + if (ret != -EOPNOTSUPP) + return ret; + fallthrough; + default: + return nfs_file_llseek(filep, offset, whence); + } +} + +static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t len) +{ + struct inode *inode = file_inode(filep); + long ret; + + if (!S_ISREG(inode->i_mode)) + return -EOPNOTSUPP; + + if ((mode != 0) && (mode != (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE))) + return -EOPNOTSUPP; + + ret = inode_newsize_ok(inode, offset + len); + if (ret < 0) + return ret; + + if (mode & FALLOC_FL_PUNCH_HOLE) + return nfs42_proc_deallocate(filep, offset, len); + return nfs42_proc_allocate(filep, offset, len); +} + +static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off, + struct file *dst_file, loff_t dst_off, loff_t count, + unsigned int remap_flags) +{ + struct inode *dst_inode = file_inode(dst_file); + struct nfs_server *server = NFS_SERVER(dst_inode); + struct inode *src_inode = file_inode(src_file); + unsigned int bs = server->clone_blksize; + bool same_inode = false; + int ret; + + /* NFS does not support deduplication. */ + if (remap_flags & REMAP_FILE_DEDUP) + return -EOPNOTSUPP; + + if (remap_flags & ~REMAP_FILE_ADVISORY) + return -EINVAL; + + if (IS_SWAPFILE(dst_inode) || IS_SWAPFILE(src_inode)) + return -ETXTBSY; + + /* check alignment w.r.t. clone_blksize */ + ret = -EINVAL; + if (bs) { + if (!IS_ALIGNED(src_off, bs) || !IS_ALIGNED(dst_off, bs)) + goto out; + if (!IS_ALIGNED(count, bs) && i_size_read(src_inode) != (src_off + count)) + goto out; + } + + if (src_inode == dst_inode) + same_inode = true; + + /* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */ + if (same_inode) { + inode_lock(src_inode); + } else if (dst_inode < src_inode) { + inode_lock_nested(dst_inode, I_MUTEX_PARENT); + inode_lock_nested(src_inode, I_MUTEX_CHILD); + } else { + inode_lock_nested(src_inode, I_MUTEX_PARENT); + inode_lock_nested(dst_inode, I_MUTEX_CHILD); + } + + /* flush all pending writes on both src and dst so that server + * has the latest data */ + ret = nfs_sync_inode(src_inode); + if (ret) + goto out_unlock; + ret = nfs_sync_inode(dst_inode); + if (ret) + goto out_unlock; + + ret = nfs42_proc_clone(src_file, dst_file, src_off, dst_off, count); + + /* truncate inode page cache of the dst range so that future reads can fetch + * new data from server */ + if (!ret) + truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1); + +out_unlock: + if (same_inode) { + inode_unlock(src_inode); + } else if (dst_inode < src_inode) { + inode_unlock(src_inode); + inode_unlock(dst_inode); + } else { + inode_unlock(dst_inode); + inode_unlock(src_inode); + } +out: + return ret < 0 ? ret : count; +} + +static int read_name_gen = 1; +#define SSC_READ_NAME_BODY "ssc_read_%d" + +static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, + struct nfs_fh *src_fh, nfs4_stateid *stateid) +{ + struct nfs_fattr *fattr = nfs_alloc_fattr(); + struct file *filep, *res; + struct nfs_server *server; + struct inode *r_ino = NULL; + struct nfs_open_context *ctx; + struct nfs4_state_owner *sp; + char *read_name = NULL; + int len, status = 0; + + server = NFS_SB(ss_mnt->mnt_sb); + + if (!fattr) + return ERR_PTR(-ENOMEM); + + status = nfs4_proc_getattr(server, src_fh, fattr, NULL); + if (status < 0) { + res = ERR_PTR(status); + goto out; + } + + if (!S_ISREG(fattr->mode)) { + res = ERR_PTR(-EBADF); + goto out; + } + + res = ERR_PTR(-ENOMEM); + len = strlen(SSC_READ_NAME_BODY) + 16; + read_name = kzalloc(len, GFP_KERNEL); + if (read_name == NULL) + goto out; + snprintf(read_name, len, SSC_READ_NAME_BODY, read_name_gen++); + + r_ino = nfs_fhget(ss_mnt->mnt_sb, src_fh, fattr); + if (IS_ERR(r_ino)) { + res = ERR_CAST(r_ino); + goto out_free_name; + } + + filep = alloc_file_pseudo(r_ino, ss_mnt, read_name, O_RDONLY, + r_ino->i_fop); + if (IS_ERR(filep)) { + res = ERR_CAST(filep); + iput(r_ino); + goto out_free_name; + } + + ctx = alloc_nfs_open_context(filep->f_path.dentry, + flags_to_mode(filep->f_flags), filep); + if (IS_ERR(ctx)) { + res = ERR_CAST(ctx); + goto out_filep; + } + + res = ERR_PTR(-EINVAL); + sp = nfs4_get_state_owner(server, ctx->cred, GFP_KERNEL); + if (sp == NULL) + goto out_ctx; + + ctx->state = nfs4_get_open_state(r_ino, sp); + if (ctx->state == NULL) + goto out_stateowner; + + set_bit(NFS_SRV_SSC_COPY_STATE, &ctx->state->flags); + memcpy(&ctx->state->open_stateid.other, &stateid->other, + NFS4_STATEID_OTHER_SIZE); + update_open_stateid(ctx->state, stateid, NULL, filep->f_mode); + set_bit(NFS_OPEN_STATE, &ctx->state->flags); + + nfs_file_set_open_context(filep, ctx); + put_nfs_open_context(ctx); + + file_ra_state_init(&filep->f_ra, filep->f_mapping->host->i_mapping); + res = filep; +out_free_name: + kfree(read_name); +out: + nfs_free_fattr(fattr); + return res; +out_stateowner: + nfs4_put_state_owner(sp); +out_ctx: + put_nfs_open_context(ctx); +out_filep: + fput(filep); + goto out_free_name; +} + +static void __nfs42_ssc_close(struct file *filep) +{ + struct nfs_open_context *ctx = nfs_file_open_context(filep); + + ctx->state->flags = 0; +} + +static const struct nfs4_ssc_client_ops nfs4_ssc_clnt_ops_tbl = { + .sco_open = __nfs42_ssc_open, + .sco_close = __nfs42_ssc_close, +}; + +/** + * nfs42_ssc_register_ops - Wrapper to register NFS_V4 ops in nfs_common + * + * Return values: + * None + */ +void nfs42_ssc_register_ops(void) +{ + nfs42_ssc_register(&nfs4_ssc_clnt_ops_tbl); +} + +/** + * nfs42_ssc_unregister_ops - wrapper to un-register NFS_V4 ops in nfs_common + * + * Return values: + * None. + */ +void nfs42_ssc_unregister_ops(void) +{ + nfs42_ssc_unregister(&nfs4_ssc_clnt_ops_tbl); +} +#endif /* CONFIG_NFS_V4_2 */ + +static int nfs4_setlease(struct file *file, long arg, struct file_lock **lease, + void **priv) +{ + return nfs4_proc_setlease(file, arg, lease, priv); +} + +const struct file_operations nfs4_file_operations = { + .read_iter = nfs_file_read, + .write_iter = nfs_file_write, + .mmap = nfs_file_mmap, + .open = nfs4_file_open, + .flush = nfs4_file_flush, + .release = nfs_file_release, + .fsync = nfs_file_fsync, + .lock = nfs_lock, + .flock = nfs_flock, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, + .check_flags = nfs_check_flags, + .setlease = nfs4_setlease, +#ifdef CONFIG_NFS_V4_2 + .copy_file_range = nfs4_copy_file_range, + .llseek = nfs4_file_llseek, + .fallocate = nfs42_fallocate, + .remap_file_range = nfs42_remap_file_range, +#else + .llseek = nfs_file_llseek, +#endif +}; -- cgit v1.2.3