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/ceph/locks.c | 510 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 510 insertions(+) create mode 100644 fs/ceph/locks.c (limited to 'fs/ceph/locks.c') diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c new file mode 100644 index 000000000..cb51c7e9c --- /dev/null +++ b/fs/ceph/locks.c @@ -0,0 +1,510 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +#include +#include +#include + +#include "super.h" +#include "mds_client.h" +#include +#include + +static u64 lock_secret; +static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc, + struct ceph_mds_request *req); + +static inline u64 secure_addr(void *addr) +{ + u64 v = lock_secret ^ (u64)(unsigned long)addr; + /* + * Set the most significant bit, so that MDS knows the 'owner' + * is sufficient to identify the owner of lock. (old code uses + * both 'owner' and 'pid') + */ + v |= (1ULL << 63); + return v; +} + +void __init ceph_flock_init(void) +{ + get_random_bytes(&lock_secret, sizeof(lock_secret)); +} + +static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src) +{ + struct inode *inode = file_inode(dst->fl_file); + atomic_inc(&ceph_inode(inode)->i_filelock_ref); + dst->fl_u.ceph.inode = igrab(inode); +} + +/* + * Do not use the 'fl->fl_file' in release function, which + * is possibly already released by another thread. + */ +static void ceph_fl_release_lock(struct file_lock *fl) +{ + struct inode *inode = fl->fl_u.ceph.inode; + struct ceph_inode_info *ci; + + /* + * If inode is NULL it should be a request file_lock, + * nothing we can do. + */ + if (!inode) + return; + + ci = ceph_inode(inode); + if (atomic_dec_and_test(&ci->i_filelock_ref)) { + /* clear error when all locks are released */ + spin_lock(&ci->i_ceph_lock); + ci->i_ceph_flags &= ~CEPH_I_ERROR_FILELOCK; + spin_unlock(&ci->i_ceph_lock); + } + fl->fl_u.ceph.inode = NULL; + iput(inode); +} + +static const struct file_lock_operations ceph_fl_lock_ops = { + .fl_copy_lock = ceph_fl_copy_lock, + .fl_release_private = ceph_fl_release_lock, +}; + +/* + * Implement fcntl and flock locking functions. + */ +static int ceph_lock_message(u8 lock_type, u16 operation, struct inode *inode, + int cmd, u8 wait, struct file_lock *fl) +{ + struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb); + struct ceph_mds_request *req; + int err; + u64 length = 0; + u64 owner; + + if (operation == CEPH_MDS_OP_SETFILELOCK) { + /* + * increasing i_filelock_ref closes race window between + * handling request reply and adding file_lock struct to + * inode. Otherwise, auth caps may get trimmed in the + * window. Caller function will decrease the counter. + */ + fl->fl_ops = &ceph_fl_lock_ops; + fl->fl_ops->fl_copy_lock(fl, NULL); + } + + if (operation != CEPH_MDS_OP_SETFILELOCK || cmd == CEPH_LOCK_UNLOCK) + wait = 0; + + req = ceph_mdsc_create_request(mdsc, operation, USE_AUTH_MDS); + if (IS_ERR(req)) + return PTR_ERR(req); + req->r_inode = inode; + ihold(inode); + req->r_num_caps = 1; + + /* mds requires start and length rather than start and end */ + if (LLONG_MAX == fl->fl_end) + length = 0; + else + length = fl->fl_end - fl->fl_start + 1; + + owner = secure_addr(fl->fl_owner); + + dout("ceph_lock_message: rule: %d, op: %d, owner: %llx, pid: %llu, " + "start: %llu, length: %llu, wait: %d, type: %d\n", (int)lock_type, + (int)operation, owner, (u64)fl->fl_pid, fl->fl_start, length, + wait, fl->fl_type); + + req->r_args.filelock_change.rule = lock_type; + req->r_args.filelock_change.type = cmd; + req->r_args.filelock_change.owner = cpu_to_le64(owner); + req->r_args.filelock_change.pid = cpu_to_le64((u64)fl->fl_pid); + req->r_args.filelock_change.start = cpu_to_le64(fl->fl_start); + req->r_args.filelock_change.length = cpu_to_le64(length); + req->r_args.filelock_change.wait = wait; + + err = ceph_mdsc_submit_request(mdsc, inode, req); + if (!err) + err = ceph_mdsc_wait_request(mdsc, req, wait ? + ceph_lock_wait_for_completion : NULL); + if (!err && operation == CEPH_MDS_OP_GETFILELOCK) { + fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid); + if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type) + fl->fl_type = F_RDLCK; + else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type) + fl->fl_type = F_WRLCK; + else + fl->fl_type = F_UNLCK; + + fl->fl_start = le64_to_cpu(req->r_reply_info.filelock_reply->start); + length = le64_to_cpu(req->r_reply_info.filelock_reply->start) + + le64_to_cpu(req->r_reply_info.filelock_reply->length); + if (length >= 1) + fl->fl_end = length -1; + else + fl->fl_end = 0; + + } + ceph_mdsc_put_request(req); + dout("ceph_lock_message: rule: %d, op: %d, pid: %llu, start: %llu, " + "length: %llu, wait: %d, type: %d, err code %d\n", (int)lock_type, + (int)operation, (u64)fl->fl_pid, fl->fl_start, + length, wait, fl->fl_type, err); + return err; +} + +static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc, + struct ceph_mds_request *req) +{ + struct ceph_mds_request *intr_req; + struct inode *inode = req->r_inode; + int err, lock_type; + + BUG_ON(req->r_op != CEPH_MDS_OP_SETFILELOCK); + if (req->r_args.filelock_change.rule == CEPH_LOCK_FCNTL) + lock_type = CEPH_LOCK_FCNTL_INTR; + else if (req->r_args.filelock_change.rule == CEPH_LOCK_FLOCK) + lock_type = CEPH_LOCK_FLOCK_INTR; + else + BUG_ON(1); + BUG_ON(req->r_args.filelock_change.type == CEPH_LOCK_UNLOCK); + + err = wait_for_completion_interruptible(&req->r_completion); + if (!err) + return 0; + + dout("ceph_lock_wait_for_completion: request %llu was interrupted\n", + req->r_tid); + + mutex_lock(&mdsc->mutex); + if (test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags)) { + err = 0; + } else { + /* + * ensure we aren't running concurrently with + * ceph_fill_trace or ceph_readdir_prepopulate, which + * rely on locks (dir mutex) held by our caller. + */ + mutex_lock(&req->r_fill_mutex); + req->r_err = err; + set_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags); + mutex_unlock(&req->r_fill_mutex); + + if (!req->r_session) { + // haven't sent the request + err = 0; + } + } + mutex_unlock(&mdsc->mutex); + if (!err) + return 0; + + intr_req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETFILELOCK, + USE_AUTH_MDS); + if (IS_ERR(intr_req)) + return PTR_ERR(intr_req); + + intr_req->r_inode = inode; + ihold(inode); + intr_req->r_num_caps = 1; + + intr_req->r_args.filelock_change = req->r_args.filelock_change; + intr_req->r_args.filelock_change.rule = lock_type; + intr_req->r_args.filelock_change.type = CEPH_LOCK_UNLOCK; + + err = ceph_mdsc_do_request(mdsc, inode, intr_req); + ceph_mdsc_put_request(intr_req); + + if (err && err != -ERESTARTSYS) + return err; + + wait_for_completion_killable(&req->r_safe_completion); + return 0; +} + +static int try_unlock_file(struct file *file, struct file_lock *fl) +{ + int err; + unsigned int orig_flags = fl->fl_flags; + fl->fl_flags |= FL_EXISTS; + err = locks_lock_file_wait(file, fl); + fl->fl_flags = orig_flags; + if (err == -ENOENT) { + if (!(orig_flags & FL_EXISTS)) + err = 0; + return err; + } + return 1; +} + +/* + * Attempt to set an fcntl lock. + * For now, this just goes away to the server. Later it may be more awesome. + */ +int ceph_lock(struct file *file, int cmd, struct file_lock *fl) +{ + struct inode *inode = file_inode(file); + struct ceph_inode_info *ci = ceph_inode(inode); + int err = 0; + u16 op = CEPH_MDS_OP_SETFILELOCK; + u8 wait = 0; + u8 lock_cmd; + + if (!(fl->fl_flags & FL_POSIX)) + return -ENOLCK; + + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + + dout("ceph_lock, fl_owner: %p\n", fl->fl_owner); + + /* set wait bit as appropriate, then make command as Ceph expects it*/ + if (IS_GETLK(cmd)) + op = CEPH_MDS_OP_GETFILELOCK; + else if (IS_SETLKW(cmd)) + wait = 1; + + spin_lock(&ci->i_ceph_lock); + if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) { + err = -EIO; + } + spin_unlock(&ci->i_ceph_lock); + if (err < 0) { + if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK == fl->fl_type) + posix_lock_file(file, fl, NULL); + return err; + } + + if (F_RDLCK == fl->fl_type) + lock_cmd = CEPH_LOCK_SHARED; + else if (F_WRLCK == fl->fl_type) + lock_cmd = CEPH_LOCK_EXCL; + else + lock_cmd = CEPH_LOCK_UNLOCK; + + if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK == fl->fl_type) { + err = try_unlock_file(file, fl); + if (err <= 0) + return err; + } + + err = ceph_lock_message(CEPH_LOCK_FCNTL, op, inode, lock_cmd, wait, fl); + if (!err) { + if (op == CEPH_MDS_OP_SETFILELOCK && F_UNLCK != fl->fl_type) { + dout("mds locked, locking locally\n"); + err = posix_lock_file(file, fl, NULL); + if (err) { + /* undo! This should only happen if + * the kernel detects local + * deadlock. */ + ceph_lock_message(CEPH_LOCK_FCNTL, op, inode, + CEPH_LOCK_UNLOCK, 0, fl); + dout("got %d on posix_lock_file, undid lock\n", + err); + } + } + } + return err; +} + +int ceph_flock(struct file *file, int cmd, struct file_lock *fl) +{ + struct inode *inode = file_inode(file); + struct ceph_inode_info *ci = ceph_inode(inode); + int err = 0; + u8 wait = 0; + u8 lock_cmd; + + if (!(fl->fl_flags & FL_FLOCK)) + return -ENOLCK; + + if (ceph_inode_is_shutdown(inode)) + return -ESTALE; + + dout("ceph_flock, fl_file: %p\n", fl->fl_file); + + spin_lock(&ci->i_ceph_lock); + if (ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) { + err = -EIO; + } + spin_unlock(&ci->i_ceph_lock); + if (err < 0) { + if (F_UNLCK == fl->fl_type) + locks_lock_file_wait(file, fl); + return err; + } + + if (IS_SETLKW(cmd)) + wait = 1; + + if (F_RDLCK == fl->fl_type) + lock_cmd = CEPH_LOCK_SHARED; + else if (F_WRLCK == fl->fl_type) + lock_cmd = CEPH_LOCK_EXCL; + else + lock_cmd = CEPH_LOCK_UNLOCK; + + if (F_UNLCK == fl->fl_type) { + err = try_unlock_file(file, fl); + if (err <= 0) + return err; + } + + err = ceph_lock_message(CEPH_LOCK_FLOCK, CEPH_MDS_OP_SETFILELOCK, + inode, lock_cmd, wait, fl); + if (!err && F_UNLCK != fl->fl_type) { + err = locks_lock_file_wait(file, fl); + if (err) { + ceph_lock_message(CEPH_LOCK_FLOCK, + CEPH_MDS_OP_SETFILELOCK, + inode, CEPH_LOCK_UNLOCK, 0, fl); + dout("got %d on locks_lock_file_wait, undid lock\n", err); + } + } + return err; +} + +/* + * Fills in the passed counter variables, so you can prepare pagelist metadata + * before calling ceph_encode_locks. + */ +void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count) +{ + struct file_lock *lock; + struct file_lock_context *ctx; + + *fcntl_count = 0; + *flock_count = 0; + + ctx = locks_inode_context(inode); + if (ctx) { + spin_lock(&ctx->flc_lock); + list_for_each_entry(lock, &ctx->flc_posix, fl_list) + ++(*fcntl_count); + list_for_each_entry(lock, &ctx->flc_flock, fl_list) + ++(*flock_count); + spin_unlock(&ctx->flc_lock); + } + dout("counted %d flock locks and %d fcntl locks\n", + *flock_count, *fcntl_count); +} + +/* + * Given a pointer to a lock, convert it to a ceph filelock + */ +static int lock_to_ceph_filelock(struct file_lock *lock, + struct ceph_filelock *cephlock) +{ + int err = 0; + cephlock->start = cpu_to_le64(lock->fl_start); + cephlock->length = cpu_to_le64(lock->fl_end - lock->fl_start + 1); + cephlock->client = cpu_to_le64(0); + cephlock->pid = cpu_to_le64((u64)lock->fl_pid); + cephlock->owner = cpu_to_le64(secure_addr(lock->fl_owner)); + + switch (lock->fl_type) { + case F_RDLCK: + cephlock->type = CEPH_LOCK_SHARED; + break; + case F_WRLCK: + cephlock->type = CEPH_LOCK_EXCL; + break; + case F_UNLCK: + cephlock->type = CEPH_LOCK_UNLOCK; + break; + default: + dout("Have unknown lock type %d\n", lock->fl_type); + err = -EINVAL; + } + + return err; +} + +/* + * Encode the flock and fcntl locks for the given inode into the ceph_filelock + * array. Must be called with inode->i_lock already held. + * If we encounter more of a specific lock type than expected, return -ENOSPC. + */ +int ceph_encode_locks_to_buffer(struct inode *inode, + struct ceph_filelock *flocks, + int num_fcntl_locks, int num_flock_locks) +{ + struct file_lock *lock; + struct file_lock_context *ctx = locks_inode_context(inode); + int err = 0; + int seen_fcntl = 0; + int seen_flock = 0; + int l = 0; + + dout("encoding %d flock and %d fcntl locks\n", num_flock_locks, + num_fcntl_locks); + + if (!ctx) + return 0; + + spin_lock(&ctx->flc_lock); + list_for_each_entry(lock, &ctx->flc_posix, fl_list) { + ++seen_fcntl; + if (seen_fcntl > num_fcntl_locks) { + err = -ENOSPC; + goto fail; + } + err = lock_to_ceph_filelock(lock, &flocks[l]); + if (err) + goto fail; + ++l; + } + list_for_each_entry(lock, &ctx->flc_flock, fl_list) { + ++seen_flock; + if (seen_flock > num_flock_locks) { + err = -ENOSPC; + goto fail; + } + err = lock_to_ceph_filelock(lock, &flocks[l]); + if (err) + goto fail; + ++l; + } +fail: + spin_unlock(&ctx->flc_lock); + return err; +} + +/* + * Copy the encoded flock and fcntl locks into the pagelist. + * Format is: #fcntl locks, sequential fcntl locks, #flock locks, + * sequential flock locks. + * Returns zero on success. + */ +int ceph_locks_to_pagelist(struct ceph_filelock *flocks, + struct ceph_pagelist *pagelist, + int num_fcntl_locks, int num_flock_locks) +{ + int err = 0; + __le32 nlocks; + + nlocks = cpu_to_le32(num_fcntl_locks); + err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks)); + if (err) + goto out_fail; + + if (num_fcntl_locks > 0) { + err = ceph_pagelist_append(pagelist, flocks, + num_fcntl_locks * sizeof(*flocks)); + if (err) + goto out_fail; + } + + nlocks = cpu_to_le32(num_flock_locks); + err = ceph_pagelist_append(pagelist, &nlocks, sizeof(nlocks)); + if (err) + goto out_fail; + + if (num_flock_locks > 0) { + err = ceph_pagelist_append(pagelist, &flocks[num_fcntl_locks], + num_flock_locks * sizeof(*flocks)); + } +out_fail: + return err; +} -- cgit v1.2.3