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/9p/vfs_file.c | 711 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 711 insertions(+) create mode 100644 fs/9p/vfs_file.c (limited to 'fs/9p/vfs_file.c') diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c new file mode 100644 index 000000000..b6ba22975 --- /dev/null +++ b/fs/9p/vfs_file.c @@ -0,0 +1,711 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This file contians vfs file ops for 9P2000. + * + * Copyright (C) 2004 by Eric Van Hensbergen + * Copyright (C) 2002 by Ron Minnich + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "v9fs.h" +#include "v9fs_vfs.h" +#include "fid.h" +#include "cache.h" + +static const struct vm_operations_struct v9fs_file_vm_ops; +static const struct vm_operations_struct v9fs_mmap_file_vm_ops; + +/** + * v9fs_file_open - open a file (or directory) + * @inode: inode to be opened + * @file: file being opened + * + */ + +int v9fs_file_open(struct inode *inode, struct file *file) +{ + int err; + struct v9fs_inode *v9inode; + struct v9fs_session_info *v9ses; + struct p9_fid *fid, *writeback_fid; + int omode; + + p9_debug(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, file); + v9inode = V9FS_I(inode); + v9ses = v9fs_inode2v9ses(inode); + if (v9fs_proto_dotl(v9ses)) + omode = v9fs_open_to_dotl_flags(file->f_flags); + else + omode = v9fs_uflags2omode(file->f_flags, + v9fs_proto_dotu(v9ses)); + fid = file->private_data; + if (!fid) { + fid = v9fs_fid_clone(file_dentry(file)); + if (IS_ERR(fid)) + return PTR_ERR(fid); + + err = p9_client_open(fid, omode); + if (err < 0) { + p9_fid_put(fid); + return err; + } + if ((file->f_flags & O_APPEND) && + (!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses))) + generic_file_llseek(file, 0, SEEK_END); + + file->private_data = fid; + } + + mutex_lock(&v9inode->v_mutex); + if ((v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) && + !v9inode->writeback_fid && + ((file->f_flags & O_ACCMODE) != O_RDONLY)) { + /* + * clone a fid and add it to writeback_fid + * we do it during open time instead of + * page dirty time via write_begin/page_mkwrite + * because we want write after unlink usecase + * to work. + */ + writeback_fid = v9fs_writeback_fid(file_dentry(file)); + if (IS_ERR(writeback_fid)) { + err = PTR_ERR(writeback_fid); + mutex_unlock(&v9inode->v_mutex); + goto out_error; + } + v9inode->writeback_fid = (void *) writeback_fid; + } + mutex_unlock(&v9inode->v_mutex); + if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) + fscache_use_cookie(v9fs_inode_cookie(v9inode), + file->f_mode & FMODE_WRITE); + v9fs_open_fid_add(inode, &fid); + return 0; +out_error: + p9_fid_put(file->private_data); + file->private_data = NULL; + return err; +} + +/** + * v9fs_file_lock - lock a file (or directory) + * @filp: file to be locked + * @cmd: lock command + * @fl: file lock structure + * + * Bugs: this looks like a local only lock, we should extend into 9P + * by using open exclusive + */ + +static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl) +{ + struct inode *inode = file_inode(filp); + + p9_debug(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl); + + if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) { + filemap_write_and_wait(inode->i_mapping); + invalidate_mapping_pages(&inode->i_data, 0, -1); + } + + return 0; +} + +static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) +{ + struct p9_flock flock; + struct p9_fid *fid; + uint8_t status = P9_LOCK_ERROR; + int res = 0; + unsigned char fl_type; + struct v9fs_session_info *v9ses; + + fid = filp->private_data; + BUG_ON(fid == NULL); + + BUG_ON((fl->fl_flags & FL_POSIX) != FL_POSIX); + + res = locks_lock_file_wait(filp, fl); + if (res < 0) + goto out; + + /* convert posix lock to p9 tlock args */ + memset(&flock, 0, sizeof(flock)); + /* map the lock type */ + switch (fl->fl_type) { + case F_RDLCK: + flock.type = P9_LOCK_TYPE_RDLCK; + break; + case F_WRLCK: + flock.type = P9_LOCK_TYPE_WRLCK; + break; + case F_UNLCK: + flock.type = P9_LOCK_TYPE_UNLCK; + break; + } + flock.start = fl->fl_start; + if (fl->fl_end == OFFSET_MAX) + flock.length = 0; + else + flock.length = fl->fl_end - fl->fl_start + 1; + flock.proc_id = fl->fl_pid; + flock.client_id = fid->clnt->name; + if (IS_SETLKW(cmd)) + flock.flags = P9_LOCK_FLAGS_BLOCK; + + v9ses = v9fs_inode2v9ses(file_inode(filp)); + + /* + * if its a blocked request and we get P9_LOCK_BLOCKED as the status + * for lock request, keep on trying + */ + for (;;) { + res = p9_client_lock_dotl(fid, &flock, &status); + if (res < 0) + goto out_unlock; + + if (status != P9_LOCK_BLOCKED) + break; + if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd)) + break; + if (schedule_timeout_interruptible(v9ses->session_lock_timeout) + != 0) + break; + /* + * p9_client_lock_dotl overwrites flock.client_id with the + * server message, free and reuse the client name + */ + if (flock.client_id != fid->clnt->name) { + kfree(flock.client_id); + flock.client_id = fid->clnt->name; + } + } + + /* map 9p status to VFS status */ + switch (status) { + case P9_LOCK_SUCCESS: + res = 0; + break; + case P9_LOCK_BLOCKED: + res = -EAGAIN; + break; + default: + WARN_ONCE(1, "unknown lock status code: %d\n", status); + fallthrough; + case P9_LOCK_ERROR: + case P9_LOCK_GRACE: + res = -ENOLCK; + break; + } + +out_unlock: + /* + * incase server returned error for lock request, revert + * it locally + */ + if (res < 0 && fl->fl_type != F_UNLCK) { + fl_type = fl->fl_type; + fl->fl_type = F_UNLCK; + /* Even if this fails we want to return the remote error */ + locks_lock_file_wait(filp, fl); + fl->fl_type = fl_type; + } + if (flock.client_id != fid->clnt->name) + kfree(flock.client_id); +out: + return res; +} + +static int v9fs_file_getlock(struct file *filp, struct file_lock *fl) +{ + struct p9_getlock glock; + struct p9_fid *fid; + int res = 0; + + fid = filp->private_data; + BUG_ON(fid == NULL); + + posix_test_lock(filp, fl); + /* + * if we have a conflicting lock locally, no need to validate + * with server + */ + if (fl->fl_type != F_UNLCK) + return res; + + /* convert posix lock to p9 tgetlock args */ + memset(&glock, 0, sizeof(glock)); + glock.type = P9_LOCK_TYPE_UNLCK; + glock.start = fl->fl_start; + if (fl->fl_end == OFFSET_MAX) + glock.length = 0; + else + glock.length = fl->fl_end - fl->fl_start + 1; + glock.proc_id = fl->fl_pid; + glock.client_id = fid->clnt->name; + + res = p9_client_getlock_dotl(fid, &glock); + if (res < 0) + goto out; + /* map 9p lock type to os lock type */ + switch (glock.type) { + case P9_LOCK_TYPE_RDLCK: + fl->fl_type = F_RDLCK; + break; + case P9_LOCK_TYPE_WRLCK: + fl->fl_type = F_WRLCK; + break; + case P9_LOCK_TYPE_UNLCK: + fl->fl_type = F_UNLCK; + break; + } + if (glock.type != P9_LOCK_TYPE_UNLCK) { + fl->fl_start = glock.start; + if (glock.length == 0) + fl->fl_end = OFFSET_MAX; + else + fl->fl_end = glock.start + glock.length - 1; + fl->fl_pid = -glock.proc_id; + } +out: + if (glock.client_id != fid->clnt->name) + kfree(glock.client_id); + return res; +} + +/** + * v9fs_file_lock_dotl - lock a file (or directory) + * @filp: file to be locked + * @cmd: lock command + * @fl: file lock structure + * + */ + +static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl) +{ + struct inode *inode = file_inode(filp); + int ret = -ENOLCK; + + p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n", + filp, cmd, fl, filp); + + if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) { + filemap_write_and_wait(inode->i_mapping); + invalidate_mapping_pages(&inode->i_data, 0, -1); + } + + if (IS_SETLK(cmd) || IS_SETLKW(cmd)) + ret = v9fs_file_do_lock(filp, cmd, fl); + else if (IS_GETLK(cmd)) + ret = v9fs_file_getlock(filp, fl); + else + ret = -EINVAL; + return ret; +} + +/** + * v9fs_file_flock_dotl - lock a file + * @filp: file to be locked + * @cmd: lock command + * @fl: file lock structure + * + */ + +static int v9fs_file_flock_dotl(struct file *filp, int cmd, + struct file_lock *fl) +{ + struct inode *inode = file_inode(filp); + int ret = -ENOLCK; + + p9_debug(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %pD\n", + filp, cmd, fl, filp); + + if (!(fl->fl_flags & FL_FLOCK)) + goto out_err; + + if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) { + filemap_write_and_wait(inode->i_mapping); + invalidate_mapping_pages(&inode->i_data, 0, -1); + } + /* Convert flock to posix lock */ + fl->fl_flags |= FL_POSIX; + fl->fl_flags ^= FL_FLOCK; + + if (IS_SETLK(cmd) | IS_SETLKW(cmd)) + ret = v9fs_file_do_lock(filp, cmd, fl); + else + ret = -EINVAL; +out_err: + return ret; +} + +/** + * v9fs_file_read_iter - read from a file + * @iocb: The operation parameters + * @to: The buffer to read into + * + */ +static ssize_t +v9fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct p9_fid *fid = iocb->ki_filp->private_data; + int ret, err = 0; + + p9_debug(P9_DEBUG_VFS, "count %zu offset %lld\n", + iov_iter_count(to), iocb->ki_pos); + + if (iocb->ki_filp->f_flags & O_NONBLOCK) + ret = p9_client_read_once(fid, iocb->ki_pos, to, &err); + else + ret = p9_client_read(fid, iocb->ki_pos, to, &err); + if (!ret) + return err; + + iocb->ki_pos += ret; + return ret; +} + +/** + * v9fs_file_write_iter - write to a file + * @iocb: The operation parameters + * @from: The data to write + * + */ +static ssize_t +v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + ssize_t retval; + loff_t origin; + int err = 0; + + retval = generic_write_checks(iocb, from); + if (retval <= 0) + return retval; + + origin = iocb->ki_pos; + retval = p9_client_write(file->private_data, iocb->ki_pos, from, &err); + if (retval > 0) { + struct inode *inode = file_inode(file); + loff_t i_size; + unsigned long pg_start, pg_end; + + pg_start = origin >> PAGE_SHIFT; + pg_end = (origin + retval - 1) >> PAGE_SHIFT; + if (inode->i_mapping && inode->i_mapping->nrpages) + invalidate_inode_pages2_range(inode->i_mapping, + pg_start, pg_end); + iocb->ki_pos += retval; + i_size = i_size_read(inode); + if (iocb->ki_pos > i_size) { + inode_add_bytes(inode, iocb->ki_pos - i_size); + /* + * Need to serialize against i_size_write() in + * v9fs_stat2inode() + */ + v9fs_i_size_write(inode, iocb->ki_pos); + } + return retval; + } + return err; +} + +static int v9fs_file_fsync(struct file *filp, loff_t start, loff_t end, + int datasync) +{ + struct p9_fid *fid; + struct inode *inode = filp->f_mapping->host; + struct p9_wstat wstat; + int retval; + + retval = file_write_and_wait_range(filp, start, end); + if (retval) + return retval; + + inode_lock(inode); + p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync); + + fid = filp->private_data; + v9fs_blank_wstat(&wstat); + + retval = p9_client_wstat(fid, &wstat); + inode_unlock(inode); + + return retval; +} + +int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end, + int datasync) +{ + struct p9_fid *fid; + struct inode *inode = filp->f_mapping->host; + int retval; + + retval = file_write_and_wait_range(filp, start, end); + if (retval) + return retval; + + inode_lock(inode); + p9_debug(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync); + + fid = filp->private_data; + + retval = p9_client_fsync(fid, datasync); + inode_unlock(inode); + + return retval; +} + +static int +v9fs_file_mmap(struct file *filp, struct vm_area_struct *vma) +{ + int retval; + + + retval = generic_file_mmap(filp, vma); + if (!retval) + vma->vm_ops = &v9fs_file_vm_ops; + + return retval; +} + +static int +v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma) +{ + int retval; + struct inode *inode; + struct v9fs_inode *v9inode; + struct p9_fid *fid; + + inode = file_inode(filp); + v9inode = V9FS_I(inode); + mutex_lock(&v9inode->v_mutex); + if (!v9inode->writeback_fid && + (vma->vm_flags & VM_SHARED) && + (vma->vm_flags & VM_WRITE)) { + /* + * clone a fid and add it to writeback_fid + * we do it during mmap instead of + * page dirty time via write_begin/page_mkwrite + * because we want write after unlink usecase + * to work. + */ + fid = v9fs_writeback_fid(file_dentry(filp)); + if (IS_ERR(fid)) { + retval = PTR_ERR(fid); + mutex_unlock(&v9inode->v_mutex); + return retval; + } + v9inode->writeback_fid = (void *) fid; + } + mutex_unlock(&v9inode->v_mutex); + + retval = generic_file_mmap(filp, vma); + if (!retval) + vma->vm_ops = &v9fs_mmap_file_vm_ops; + + return retval; +} + +static vm_fault_t +v9fs_vm_page_mkwrite(struct vm_fault *vmf) +{ + struct v9fs_inode *v9inode; + struct folio *folio = page_folio(vmf->page); + struct file *filp = vmf->vma->vm_file; + struct inode *inode = file_inode(filp); + + + p9_debug(P9_DEBUG_VFS, "folio %p fid %lx\n", + folio, (unsigned long)filp->private_data); + + v9inode = V9FS_I(inode); + + /* Wait for the page to be written to the cache before we allow it to + * be modified. We then assume the entire page will need writing back. + */ +#ifdef CONFIG_9P_FSCACHE + if (folio_test_fscache(folio) && + folio_wait_fscache_killable(folio) < 0) + return VM_FAULT_NOPAGE; +#endif + + /* Update file times before taking page lock */ + file_update_time(filp); + + BUG_ON(!v9inode->writeback_fid); + if (folio_lock_killable(folio) < 0) + return VM_FAULT_RETRY; + if (folio_mapping(folio) != inode->i_mapping) + goto out_unlock; + folio_wait_stable(folio); + + return VM_FAULT_LOCKED; +out_unlock: + folio_unlock(folio); + return VM_FAULT_NOPAGE; +} + +/** + * v9fs_mmap_file_read_iter - read from a file + * @iocb: The operation parameters + * @to: The buffer to read into + * + */ +static ssize_t +v9fs_mmap_file_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + /* TODO: Check if there are dirty pages */ + return v9fs_file_read_iter(iocb, to); +} + +/** + * v9fs_mmap_file_write_iter - write to a file + * @iocb: The operation parameters + * @from: The data to write + * + */ +static ssize_t +v9fs_mmap_file_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + /* + * TODO: invalidate mmaps on filp's inode between + * offset and offset+count + */ + return v9fs_file_write_iter(iocb, from); +} + +static void v9fs_mmap_vm_close(struct vm_area_struct *vma) +{ + struct inode *inode; + + struct writeback_control wbc = { + .nr_to_write = LONG_MAX, + .sync_mode = WB_SYNC_ALL, + .range_start = (loff_t)vma->vm_pgoff * PAGE_SIZE, + /* absolute end, byte at end included */ + .range_end = (loff_t)vma->vm_pgoff * PAGE_SIZE + + (vma->vm_end - vma->vm_start - 1), + }; + + if (!(vma->vm_flags & VM_SHARED)) + return; + + p9_debug(P9_DEBUG_VFS, "9p VMA close, %p, flushing", vma); + + inode = file_inode(vma->vm_file); + filemap_fdatawrite_wbc(inode->i_mapping, &wbc); +} + + +static const struct vm_operations_struct v9fs_file_vm_ops = { + .fault = filemap_fault, + .map_pages = filemap_map_pages, + .page_mkwrite = v9fs_vm_page_mkwrite, +}; + +static const struct vm_operations_struct v9fs_mmap_file_vm_ops = { + .close = v9fs_mmap_vm_close, + .fault = filemap_fault, + .map_pages = filemap_map_pages, + .page_mkwrite = v9fs_vm_page_mkwrite, +}; + + +const struct file_operations v9fs_cached_file_operations = { + .llseek = generic_file_llseek, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, + .open = v9fs_file_open, + .release = v9fs_dir_release, + .lock = v9fs_file_lock, + .mmap = v9fs_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, + .fsync = v9fs_file_fsync, +}; + +const struct file_operations v9fs_cached_file_operations_dotl = { + .llseek = generic_file_llseek, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, + .open = v9fs_file_open, + .release = v9fs_dir_release, + .lock = v9fs_file_lock_dotl, + .flock = v9fs_file_flock_dotl, + .mmap = v9fs_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, + .fsync = v9fs_file_fsync_dotl, +}; + +const struct file_operations v9fs_file_operations = { + .llseek = generic_file_llseek, + .read_iter = v9fs_file_read_iter, + .write_iter = v9fs_file_write_iter, + .open = v9fs_file_open, + .release = v9fs_dir_release, + .lock = v9fs_file_lock, + .mmap = generic_file_readonly_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, + .fsync = v9fs_file_fsync, +}; + +const struct file_operations v9fs_file_operations_dotl = { + .llseek = generic_file_llseek, + .read_iter = v9fs_file_read_iter, + .write_iter = v9fs_file_write_iter, + .open = v9fs_file_open, + .release = v9fs_dir_release, + .lock = v9fs_file_lock_dotl, + .flock = v9fs_file_flock_dotl, + .mmap = generic_file_readonly_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, + .fsync = v9fs_file_fsync_dotl, +}; + +const struct file_operations v9fs_mmap_file_operations = { + .llseek = generic_file_llseek, + .read_iter = v9fs_mmap_file_read_iter, + .write_iter = v9fs_mmap_file_write_iter, + .open = v9fs_file_open, + .release = v9fs_dir_release, + .lock = v9fs_file_lock, + .mmap = v9fs_mmap_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, + .fsync = v9fs_file_fsync, +}; + +const struct file_operations v9fs_mmap_file_operations_dotl = { + .llseek = generic_file_llseek, + .read_iter = v9fs_mmap_file_read_iter, + .write_iter = v9fs_mmap_file_write_iter, + .open = v9fs_file_open, + .release = v9fs_dir_release, + .lock = v9fs_file_lock_dotl, + .flock = v9fs_file_flock_dotl, + .mmap = v9fs_mmap_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, + .fsync = v9fs_file_fsync_dotl, +}; -- cgit v1.2.3