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/cachefiles/namei.c | 860 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 860 insertions(+) create mode 100644 fs/cachefiles/namei.c (limited to 'fs/cachefiles/namei.c') diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c new file mode 100644 index 000000000..82219a8f6 --- /dev/null +++ b/fs/cachefiles/namei.c @@ -0,0 +1,860 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* CacheFiles path walking and related routines + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include "internal.h" + +/* + * Mark the backing file as being a cache file if it's not already in use. The + * mark tells the culling request command that it's not allowed to cull the + * file or directory. The caller must hold the inode lock. + */ +static bool __cachefiles_mark_inode_in_use(struct cachefiles_object *object, + struct inode *inode) +{ + bool can_use = false; + + if (!(inode->i_flags & S_KERNEL_FILE)) { + inode->i_flags |= S_KERNEL_FILE; + trace_cachefiles_mark_active(object, inode); + can_use = true; + } else { + trace_cachefiles_mark_failed(object, inode); + } + + return can_use; +} + +static bool cachefiles_mark_inode_in_use(struct cachefiles_object *object, + struct inode *inode) +{ + bool can_use; + + inode_lock(inode); + can_use = __cachefiles_mark_inode_in_use(object, inode); + inode_unlock(inode); + return can_use; +} + +/* + * Unmark a backing inode. The caller must hold the inode lock. + */ +static void __cachefiles_unmark_inode_in_use(struct cachefiles_object *object, + struct inode *inode) +{ + inode->i_flags &= ~S_KERNEL_FILE; + trace_cachefiles_mark_inactive(object, inode); +} + +static void cachefiles_do_unmark_inode_in_use(struct cachefiles_object *object, + struct inode *inode) +{ + inode_lock(inode); + __cachefiles_unmark_inode_in_use(object, inode); + inode_unlock(inode); +} + +/* + * Unmark a backing inode and tell cachefilesd that there's something that can + * be culled. + */ +void cachefiles_unmark_inode_in_use(struct cachefiles_object *object, + struct file *file) +{ + struct cachefiles_cache *cache = object->volume->cache; + struct inode *inode = file_inode(file); + + cachefiles_do_unmark_inode_in_use(object, inode); + + if (!test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags)) { + atomic_long_add(inode->i_blocks, &cache->b_released); + if (atomic_inc_return(&cache->f_released)) + cachefiles_state_changed(cache); + } +} + +/* + * get a subdirectory + */ +struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache, + struct dentry *dir, + const char *dirname, + bool *_is_new) +{ + struct dentry *subdir; + struct path path; + int ret; + + _enter(",,%s", dirname); + + /* search the current directory for the element name */ + inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); + +retry: + ret = cachefiles_inject_read_error(); + if (ret == 0) + subdir = lookup_one_len(dirname, dir, strlen(dirname)); + else + subdir = ERR_PTR(ret); + trace_cachefiles_lookup(NULL, dir, subdir); + if (IS_ERR(subdir)) { + trace_cachefiles_vfs_error(NULL, d_backing_inode(dir), + PTR_ERR(subdir), + cachefiles_trace_lookup_error); + if (PTR_ERR(subdir) == -ENOMEM) + goto nomem_d_alloc; + goto lookup_error; + } + + _debug("subdir -> %pd %s", + subdir, d_backing_inode(subdir) ? "positive" : "negative"); + + /* we need to create the subdir if it doesn't exist yet */ + if (d_is_negative(subdir)) { + ret = cachefiles_has_space(cache, 1, 0, + cachefiles_has_space_for_create); + if (ret < 0) + goto mkdir_error; + + _debug("attempt mkdir"); + + path.mnt = cache->mnt; + path.dentry = dir; + ret = security_path_mkdir(&path, subdir, 0700); + if (ret < 0) + goto mkdir_error; + ret = cachefiles_inject_write_error(); + if (ret == 0) + ret = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700); + if (ret < 0) { + trace_cachefiles_vfs_error(NULL, d_inode(dir), ret, + cachefiles_trace_mkdir_error); + goto mkdir_error; + } + trace_cachefiles_mkdir(dir, subdir); + + if (unlikely(d_unhashed(subdir))) { + cachefiles_put_directory(subdir); + goto retry; + } + ASSERT(d_backing_inode(subdir)); + + _debug("mkdir -> %pd{ino=%lu}", + subdir, d_backing_inode(subdir)->i_ino); + if (_is_new) + *_is_new = true; + } + + /* Tell rmdir() it's not allowed to delete the subdir */ + inode_lock(d_inode(subdir)); + inode_unlock(d_inode(dir)); + + if (!__cachefiles_mark_inode_in_use(NULL, d_inode(subdir))) { + pr_notice("cachefiles: Inode already in use: %pd (B=%lx)\n", + subdir, d_inode(subdir)->i_ino); + goto mark_error; + } + + inode_unlock(d_inode(subdir)); + + /* we need to make sure the subdir is a directory */ + ASSERT(d_backing_inode(subdir)); + + if (!d_can_lookup(subdir)) { + pr_err("%s is not a directory\n", dirname); + ret = -EIO; + goto check_error; + } + + ret = -EPERM; + if (!(d_backing_inode(subdir)->i_opflags & IOP_XATTR) || + !d_backing_inode(subdir)->i_op->lookup || + !d_backing_inode(subdir)->i_op->mkdir || + !d_backing_inode(subdir)->i_op->rename || + !d_backing_inode(subdir)->i_op->rmdir || + !d_backing_inode(subdir)->i_op->unlink) + goto check_error; + + _leave(" = [%lu]", d_backing_inode(subdir)->i_ino); + return subdir; + +check_error: + cachefiles_put_directory(subdir); + _leave(" = %d [check]", ret); + return ERR_PTR(ret); + +mark_error: + inode_unlock(d_inode(subdir)); + dput(subdir); + return ERR_PTR(-EBUSY); + +mkdir_error: + inode_unlock(d_inode(dir)); + dput(subdir); + pr_err("mkdir %s failed with error %d\n", dirname, ret); + return ERR_PTR(ret); + +lookup_error: + inode_unlock(d_inode(dir)); + ret = PTR_ERR(subdir); + pr_err("Lookup %s failed with error %d\n", dirname, ret); + return ERR_PTR(ret); + +nomem_d_alloc: + inode_unlock(d_inode(dir)); + _leave(" = -ENOMEM"); + return ERR_PTR(-ENOMEM); +} + +/* + * Put a subdirectory. + */ +void cachefiles_put_directory(struct dentry *dir) +{ + if (dir) { + cachefiles_do_unmark_inode_in_use(NULL, d_inode(dir)); + dput(dir); + } +} + +/* + * Remove a regular file from the cache. + */ +static int cachefiles_unlink(struct cachefiles_cache *cache, + struct cachefiles_object *object, + struct dentry *dir, struct dentry *dentry, + enum fscache_why_object_killed why) +{ + struct path path = { + .mnt = cache->mnt, + .dentry = dir, + }; + int ret; + + trace_cachefiles_unlink(object, d_inode(dentry)->i_ino, why); + ret = security_path_unlink(&path, dentry); + if (ret < 0) { + cachefiles_io_error(cache, "Unlink security error"); + return ret; + } + + ret = cachefiles_inject_remove_error(); + if (ret == 0) { + ret = vfs_unlink(&nop_mnt_idmap, d_backing_inode(dir), dentry, NULL); + if (ret == -EIO) + cachefiles_io_error(cache, "Unlink failed"); + } + if (ret != 0) + trace_cachefiles_vfs_error(object, d_backing_inode(dir), ret, + cachefiles_trace_unlink_error); + return ret; +} + +/* + * Delete an object representation from the cache + * - File backed objects are unlinked + * - Directory backed objects are stuffed into the graveyard for userspace to + * delete + */ +int cachefiles_bury_object(struct cachefiles_cache *cache, + struct cachefiles_object *object, + struct dentry *dir, + struct dentry *rep, + enum fscache_why_object_killed why) +{ + struct dentry *grave, *trap; + struct path path, path_to_graveyard; + char nbuffer[8 + 8 + 1]; + int ret; + + _enter(",'%pd','%pd'", dir, rep); + + if (rep->d_parent != dir) { + inode_unlock(d_inode(dir)); + _leave(" = -ESTALE"); + return -ESTALE; + } + + /* non-directories can just be unlinked */ + if (!d_is_dir(rep)) { + dget(rep); /* Stop the dentry being negated if it's only pinned + * by a file struct. + */ + ret = cachefiles_unlink(cache, object, dir, rep, why); + dput(rep); + + inode_unlock(d_inode(dir)); + _leave(" = %d", ret); + return ret; + } + + /* directories have to be moved to the graveyard */ + _debug("move stale object to graveyard"); + inode_unlock(d_inode(dir)); + +try_again: + /* first step is to make up a grave dentry in the graveyard */ + sprintf(nbuffer, "%08x%08x", + (uint32_t) ktime_get_real_seconds(), + (uint32_t) atomic_inc_return(&cache->gravecounter)); + + /* do the multiway lock magic */ + trap = lock_rename(cache->graveyard, dir); + + /* do some checks before getting the grave dentry */ + if (rep->d_parent != dir || IS_DEADDIR(d_inode(rep))) { + /* the entry was probably culled when we dropped the parent dir + * lock */ + unlock_rename(cache->graveyard, dir); + _leave(" = 0 [culled?]"); + return 0; + } + + if (!d_can_lookup(cache->graveyard)) { + unlock_rename(cache->graveyard, dir); + cachefiles_io_error(cache, "Graveyard no longer a directory"); + return -EIO; + } + + if (trap == rep) { + unlock_rename(cache->graveyard, dir); + cachefiles_io_error(cache, "May not make directory loop"); + return -EIO; + } + + if (d_mountpoint(rep)) { + unlock_rename(cache->graveyard, dir); + cachefiles_io_error(cache, "Mountpoint in cache"); + return -EIO; + } + + grave = lookup_one_len(nbuffer, cache->graveyard, strlen(nbuffer)); + if (IS_ERR(grave)) { + unlock_rename(cache->graveyard, dir); + trace_cachefiles_vfs_error(object, d_inode(cache->graveyard), + PTR_ERR(grave), + cachefiles_trace_lookup_error); + + if (PTR_ERR(grave) == -ENOMEM) { + _leave(" = -ENOMEM"); + return -ENOMEM; + } + + cachefiles_io_error(cache, "Lookup error %ld", PTR_ERR(grave)); + return -EIO; + } + + if (d_is_positive(grave)) { + unlock_rename(cache->graveyard, dir); + dput(grave); + grave = NULL; + cond_resched(); + goto try_again; + } + + if (d_mountpoint(grave)) { + unlock_rename(cache->graveyard, dir); + dput(grave); + cachefiles_io_error(cache, "Mountpoint in graveyard"); + return -EIO; + } + + /* target should not be an ancestor of source */ + if (trap == grave) { + unlock_rename(cache->graveyard, dir); + dput(grave); + cachefiles_io_error(cache, "May not make directory loop"); + return -EIO; + } + + /* attempt the rename */ + path.mnt = cache->mnt; + path.dentry = dir; + path_to_graveyard.mnt = cache->mnt; + path_to_graveyard.dentry = cache->graveyard; + ret = security_path_rename(&path, rep, &path_to_graveyard, grave, 0); + if (ret < 0) { + cachefiles_io_error(cache, "Rename security error %d", ret); + } else { + struct renamedata rd = { + .old_mnt_idmap = &nop_mnt_idmap, + .old_dir = d_inode(dir), + .old_dentry = rep, + .new_mnt_idmap = &nop_mnt_idmap, + .new_dir = d_inode(cache->graveyard), + .new_dentry = grave, + }; + trace_cachefiles_rename(object, d_inode(rep)->i_ino, why); + ret = cachefiles_inject_read_error(); + if (ret == 0) + ret = vfs_rename(&rd); + if (ret != 0) + trace_cachefiles_vfs_error(object, d_inode(dir), ret, + cachefiles_trace_rename_error); + if (ret != 0 && ret != -ENOMEM) + cachefiles_io_error(cache, + "Rename failed with error %d", ret); + } + + __cachefiles_unmark_inode_in_use(object, d_inode(rep)); + unlock_rename(cache->graveyard, dir); + dput(grave); + _leave(" = 0"); + return 0; +} + +/* + * Delete a cache file. + */ +int cachefiles_delete_object(struct cachefiles_object *object, + enum fscache_why_object_killed why) +{ + struct cachefiles_volume *volume = object->volume; + struct dentry *dentry = object->file->f_path.dentry; + struct dentry *fan = volume->fanout[(u8)object->cookie->key_hash]; + int ret; + + _enter(",OBJ%x{%pD}", object->debug_id, object->file); + + /* Stop the dentry being negated if it's only pinned by a file struct. */ + dget(dentry); + + inode_lock_nested(d_backing_inode(fan), I_MUTEX_PARENT); + ret = cachefiles_unlink(volume->cache, object, fan, dentry, why); + inode_unlock(d_backing_inode(fan)); + dput(dentry); + return ret; +} + +/* + * Create a temporary file and leave it unattached and un-xattr'd until the + * time comes to discard the object from memory. + */ +struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) +{ + struct cachefiles_volume *volume = object->volume; + struct cachefiles_cache *cache = volume->cache; + const struct cred *saved_cred; + struct dentry *fan = volume->fanout[(u8)object->cookie->key_hash]; + struct file *file; + const struct path parentpath = { .mnt = cache->mnt, .dentry = fan }; + uint64_t ni_size; + long ret; + + + cachefiles_begin_secure(cache, &saved_cred); + + ret = cachefiles_inject_write_error(); + if (ret == 0) { + file = vfs_tmpfile_open(&nop_mnt_idmap, &parentpath, S_IFREG, + O_RDWR | O_LARGEFILE | O_DIRECT, + cache->cache_cred); + ret = PTR_ERR_OR_ZERO(file); + } + if (ret) { + trace_cachefiles_vfs_error(object, d_inode(fan), ret, + cachefiles_trace_tmpfile_error); + if (ret == -EIO) + cachefiles_io_error_obj(object, "Failed to create tmpfile"); + goto err; + } + + trace_cachefiles_tmpfile(object, file_inode(file)); + + /* This is a newly created file with no other possible user */ + if (!cachefiles_mark_inode_in_use(object, file_inode(file))) + WARN_ON(1); + + ret = cachefiles_ondemand_init_object(object); + if (ret < 0) + goto err_unuse; + + ni_size = object->cookie->object_size; + ni_size = round_up(ni_size, CACHEFILES_DIO_BLOCK_SIZE); + + if (ni_size > 0) { + trace_cachefiles_trunc(object, file_inode(file), 0, ni_size, + cachefiles_trunc_expand_tmpfile); + ret = cachefiles_inject_write_error(); + if (ret == 0) + ret = vfs_truncate(&file->f_path, ni_size); + if (ret < 0) { + trace_cachefiles_vfs_error( + object, file_inode(file), ret, + cachefiles_trace_trunc_error); + goto err_unuse; + } + } + + ret = -EINVAL; + if (unlikely(!file->f_op->read_iter) || + unlikely(!file->f_op->write_iter)) { + fput(file); + pr_notice("Cache does not support read_iter and write_iter\n"); + goto err_unuse; + } +out: + cachefiles_end_secure(cache, saved_cred); + return file; + +err_unuse: + cachefiles_do_unmark_inode_in_use(object, file_inode(file)); + fput(file); +err: + file = ERR_PTR(ret); + goto out; +} + +/* + * Create a new file. + */ +static bool cachefiles_create_file(struct cachefiles_object *object) +{ + struct file *file; + int ret; + + ret = cachefiles_has_space(object->volume->cache, 1, 0, + cachefiles_has_space_for_create); + if (ret < 0) + return false; + + file = cachefiles_create_tmpfile(object); + if (IS_ERR(file)) + return false; + + set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &object->cookie->flags); + set_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags); + _debug("create -> %pD{ino=%lu}", file, file_inode(file)->i_ino); + object->file = file; + return true; +} + +/* + * Open an existing file, checking its attributes and replacing it if it is + * stale. + */ +static bool cachefiles_open_file(struct cachefiles_object *object, + struct dentry *dentry) +{ + struct cachefiles_cache *cache = object->volume->cache; + struct file *file; + struct path path; + int ret; + + _enter("%pd", dentry); + + if (!cachefiles_mark_inode_in_use(object, d_inode(dentry))) { + pr_notice("cachefiles: Inode already in use: %pd (B=%lx)\n", + dentry, d_inode(dentry)->i_ino); + return false; + } + + /* We need to open a file interface onto a data file now as we can't do + * it on demand because writeback called from do_exit() sees + * current->fs == NULL - which breaks d_path() called from ext4 open. + */ + path.mnt = cache->mnt; + path.dentry = dentry; + file = open_with_fake_path(&path, O_RDWR | O_LARGEFILE | O_DIRECT, + d_backing_inode(dentry), cache->cache_cred); + if (IS_ERR(file)) { + trace_cachefiles_vfs_error(object, d_backing_inode(dentry), + PTR_ERR(file), + cachefiles_trace_open_error); + goto error; + } + + if (unlikely(!file->f_op->read_iter) || + unlikely(!file->f_op->write_iter)) { + pr_notice("Cache does not support read_iter and write_iter\n"); + goto error_fput; + } + _debug("file -> %pd positive", dentry); + + ret = cachefiles_ondemand_init_object(object); + if (ret < 0) + goto error_fput; + + ret = cachefiles_check_auxdata(object, file); + if (ret < 0) + goto check_failed; + + object->file = file; + + /* Always update the atime on an object we've just looked up (this is + * used to keep track of culling, and atimes are only updated by read, + * write and readdir but not lookup or open). + */ + touch_atime(&file->f_path); + dput(dentry); + return true; + +check_failed: + fscache_cookie_lookup_negative(object->cookie); + cachefiles_unmark_inode_in_use(object, file); + fput(file); + dput(dentry); + if (ret == -ESTALE) + return cachefiles_create_file(object); + return false; + +error_fput: + fput(file); +error: + cachefiles_do_unmark_inode_in_use(object, d_inode(dentry)); + dput(dentry); + return false; +} + +/* + * walk from the parent object to the child object through the backing + * filesystem, creating directories as we go + */ +bool cachefiles_look_up_object(struct cachefiles_object *object) +{ + struct cachefiles_volume *volume = object->volume; + struct dentry *dentry, *fan = volume->fanout[(u8)object->cookie->key_hash]; + int ret; + + _enter("OBJ%x,%s,", object->debug_id, object->d_name); + + /* Look up path "cache/vol/fanout/file". */ + ret = cachefiles_inject_read_error(); + if (ret == 0) + dentry = lookup_positive_unlocked(object->d_name, fan, + object->d_name_len); + else + dentry = ERR_PTR(ret); + trace_cachefiles_lookup(object, fan, dentry); + if (IS_ERR(dentry)) { + if (dentry == ERR_PTR(-ENOENT)) + goto new_file; + if (dentry == ERR_PTR(-EIO)) + cachefiles_io_error_obj(object, "Lookup failed"); + return false; + } + + if (!d_is_reg(dentry)) { + pr_err("%pd is not a file\n", dentry); + inode_lock_nested(d_inode(fan), I_MUTEX_PARENT); + ret = cachefiles_bury_object(volume->cache, object, fan, dentry, + FSCACHE_OBJECT_IS_WEIRD); + dput(dentry); + if (ret < 0) + return false; + goto new_file; + } + + if (!cachefiles_open_file(object, dentry)) + return false; + + _leave(" = t [%lu]", file_inode(object->file)->i_ino); + return true; + +new_file: + fscache_cookie_lookup_negative(object->cookie); + return cachefiles_create_file(object); +} + +/* + * Attempt to link a temporary file into its rightful place in the cache. + */ +bool cachefiles_commit_tmpfile(struct cachefiles_cache *cache, + struct cachefiles_object *object) +{ + struct cachefiles_volume *volume = object->volume; + struct dentry *dentry, *fan = volume->fanout[(u8)object->cookie->key_hash]; + bool success = false; + int ret; + + _enter(",%pD", object->file); + + inode_lock_nested(d_inode(fan), I_MUTEX_PARENT); + ret = cachefiles_inject_read_error(); + if (ret == 0) + dentry = lookup_one_len(object->d_name, fan, object->d_name_len); + else + dentry = ERR_PTR(ret); + if (IS_ERR(dentry)) { + trace_cachefiles_vfs_error(object, d_inode(fan), PTR_ERR(dentry), + cachefiles_trace_lookup_error); + _debug("lookup fail %ld", PTR_ERR(dentry)); + goto out_unlock; + } + + if (!d_is_negative(dentry)) { + if (d_backing_inode(dentry) == file_inode(object->file)) { + success = true; + goto out_dput; + } + + ret = cachefiles_unlink(volume->cache, object, fan, dentry, + FSCACHE_OBJECT_IS_STALE); + if (ret < 0) + goto out_dput; + + dput(dentry); + ret = cachefiles_inject_read_error(); + if (ret == 0) + dentry = lookup_one_len(object->d_name, fan, object->d_name_len); + else + dentry = ERR_PTR(ret); + if (IS_ERR(dentry)) { + trace_cachefiles_vfs_error(object, d_inode(fan), PTR_ERR(dentry), + cachefiles_trace_lookup_error); + _debug("lookup fail %ld", PTR_ERR(dentry)); + goto out_unlock; + } + } + + ret = cachefiles_inject_read_error(); + if (ret == 0) + ret = vfs_link(object->file->f_path.dentry, &nop_mnt_idmap, + d_inode(fan), dentry, NULL); + if (ret < 0) { + trace_cachefiles_vfs_error(object, d_inode(fan), ret, + cachefiles_trace_link_error); + _debug("link fail %d", ret); + } else { + trace_cachefiles_link(object, file_inode(object->file)); + spin_lock(&object->lock); + /* TODO: Do we want to switch the file pointer to the new dentry? */ + clear_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags); + spin_unlock(&object->lock); + success = true; + } + +out_dput: + dput(dentry); +out_unlock: + inode_unlock(d_inode(fan)); + _leave(" = %u", success); + return success; +} + +/* + * Look up an inode to be checked or culled. Return -EBUSY if the inode is + * marked in use. + */ +static struct dentry *cachefiles_lookup_for_cull(struct cachefiles_cache *cache, + struct dentry *dir, + char *filename) +{ + struct dentry *victim; + int ret = -ENOENT; + + inode_lock_nested(d_inode(dir), I_MUTEX_PARENT); + + victim = lookup_one_len(filename, dir, strlen(filename)); + if (IS_ERR(victim)) + goto lookup_error; + if (d_is_negative(victim)) + goto lookup_put; + if (d_inode(victim)->i_flags & S_KERNEL_FILE) + goto lookup_busy; + return victim; + +lookup_busy: + ret = -EBUSY; +lookup_put: + inode_unlock(d_inode(dir)); + dput(victim); + return ERR_PTR(ret); + +lookup_error: + inode_unlock(d_inode(dir)); + ret = PTR_ERR(victim); + if (ret == -ENOENT) + return ERR_PTR(-ESTALE); /* Probably got retired by the netfs */ + + if (ret == -EIO) { + cachefiles_io_error(cache, "Lookup failed"); + } else if (ret != -ENOMEM) { + pr_err("Internal error: %d\n", ret); + ret = -EIO; + } + + return ERR_PTR(ret); +} + +/* + * Cull an object if it's not in use + * - called only by cache manager daemon + */ +int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir, + char *filename) +{ + struct dentry *victim; + struct inode *inode; + int ret; + + _enter(",%pd/,%s", dir, filename); + + victim = cachefiles_lookup_for_cull(cache, dir, filename); + if (IS_ERR(victim)) + return PTR_ERR(victim); + + /* check to see if someone is using this object */ + inode = d_inode(victim); + inode_lock(inode); + if (inode->i_flags & S_KERNEL_FILE) { + ret = -EBUSY; + } else { + /* Stop the cache from picking it back up */ + inode->i_flags |= S_KERNEL_FILE; + ret = 0; + } + inode_unlock(inode); + if (ret < 0) + goto error_unlock; + + ret = cachefiles_bury_object(cache, NULL, dir, victim, + FSCACHE_OBJECT_WAS_CULLED); + if (ret < 0) + goto error; + + fscache_count_culled(); + dput(victim); + _leave(" = 0"); + return 0; + +error_unlock: + inode_unlock(d_inode(dir)); +error: + dput(victim); + if (ret == -ENOENT) + return -ESTALE; /* Probably got retired by the netfs */ + + if (ret != -ENOMEM) { + pr_err("Internal error: %d\n", ret); + ret = -EIO; + } + + _leave(" = %d", ret); + return ret; +} + +/* + * Find out if an object is in use or not + * - called only by cache manager daemon + * - returns -EBUSY or 0 to indicate whether an object is in use or not + */ +int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir, + char *filename) +{ + struct dentry *victim; + int ret = 0; + + victim = cachefiles_lookup_for_cull(cache, dir, filename); + if (IS_ERR(victim)) + return PTR_ERR(victim); + + inode_unlock(d_inode(dir)); + dput(victim); + return ret; +} -- cgit v1.2.3