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/readdir.c | 552 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 552 insertions(+) create mode 100644 fs/readdir.c (limited to 'fs/readdir.c') diff --git a/fs/readdir.c b/fs/readdir.c new file mode 100644 index 000000000..9c53edb60 --- /dev/null +++ b/fs/readdir.c @@ -0,0 +1,552 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/readdir.c + * + * Copyright (C) 1995 Linus Torvalds + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +/* + * Note the "unsafe_put_user() semantics: we goto a + * label for errors. + */ +#define unsafe_copy_dirent_name(_dst, _src, _len, label) do { \ + char __user *dst = (_dst); \ + const char *src = (_src); \ + size_t len = (_len); \ + unsafe_put_user(0, dst+len, label); \ + unsafe_copy_to_user(dst, src, len, label); \ +} while (0) + + +int iterate_dir(struct file *file, struct dir_context *ctx) +{ + struct inode *inode = file_inode(file); + bool shared = false; + int res = -ENOTDIR; + if (file->f_op->iterate_shared) + shared = true; + else if (!file->f_op->iterate) + goto out; + + res = security_file_permission(file, MAY_READ); + if (res) + goto out; + + if (shared) + res = down_read_killable(&inode->i_rwsem); + else + res = down_write_killable(&inode->i_rwsem); + if (res) + goto out; + + res = -ENOENT; + if (!IS_DEADDIR(inode)) { + ctx->pos = file->f_pos; + if (shared) + res = file->f_op->iterate_shared(file, ctx); + else + res = file->f_op->iterate(file, ctx); + file->f_pos = ctx->pos; + fsnotify_access(file); + file_accessed(file); + } + if (shared) + inode_unlock_shared(inode); + else + inode_unlock(inode); +out: + return res; +} +EXPORT_SYMBOL(iterate_dir); + +/* + * POSIX says that a dirent name cannot contain NULL or a '/'. + * + * It's not 100% clear what we should really do in this case. + * The filesystem is clearly corrupted, but returning a hard + * error means that you now don't see any of the other names + * either, so that isn't a perfect alternative. + * + * And if you return an error, what error do you use? Several + * filesystems seem to have decided on EUCLEAN being the error + * code for EFSCORRUPTED, and that may be the error to use. Or + * just EIO, which is perhaps more obvious to users. + * + * In order to see the other file names in the directory, the + * caller might want to make this a "soft" error: skip the + * entry, and return the error at the end instead. + * + * Note that this should likely do a "memchr(name, 0, len)" + * check too, since that would be filesystem corruption as + * well. However, that case can't actually confuse user space, + * which has to do a strlen() on the name anyway to find the + * filename length, and the above "soft error" worry means + * that it's probably better left alone until we have that + * issue clarified. + * + * Note the PATH_MAX check - it's arbitrary but the real + * kernel limit on a possible path component, not NAME_MAX, + * which is the technical standard limit. + */ +static int verify_dirent_name(const char *name, int len) +{ + if (len <= 0 || len >= PATH_MAX) + return -EIO; + if (memchr(name, '/', len)) + return -EIO; + return 0; +} + +/* + * Traditional linux readdir() handling.. + * + * "count=1" is a special case, meaning that the buffer is one + * dirent-structure in size and that the code can't handle more + * anyway. Thus the special "fillonedir()" function for that + * case (the low-level handlers don't need to care about this). + */ + +#ifdef __ARCH_WANT_OLD_READDIR + +struct old_linux_dirent { + unsigned long d_ino; + unsigned long d_offset; + unsigned short d_namlen; + char d_name[1]; +}; + +struct readdir_callback { + struct dir_context ctx; + struct old_linux_dirent __user * dirent; + int result; +}; + +static bool fillonedir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct readdir_callback *buf = + container_of(ctx, struct readdir_callback, ctx); + struct old_linux_dirent __user * dirent; + unsigned long d_ino; + + if (buf->result) + return false; + buf->result = verify_dirent_name(name, namlen); + if (buf->result) + return false; + d_ino = ino; + if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { + buf->result = -EOVERFLOW; + return false; + } + buf->result++; + dirent = buf->dirent; + if (!user_write_access_begin(dirent, + (unsigned long)(dirent->d_name + namlen + 1) - + (unsigned long)dirent)) + goto efault; + unsafe_put_user(d_ino, &dirent->d_ino, efault_end); + unsafe_put_user(offset, &dirent->d_offset, efault_end); + unsafe_put_user(namlen, &dirent->d_namlen, efault_end); + unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); + user_write_access_end(); + return true; +efault_end: + user_write_access_end(); +efault: + buf->result = -EFAULT; + return false; +} + +SYSCALL_DEFINE3(old_readdir, unsigned int, fd, + struct old_linux_dirent __user *, dirent, unsigned int, count) +{ + int error; + struct fd f = fdget_pos(fd); + struct readdir_callback buf = { + .ctx.actor = fillonedir, + .dirent = dirent + }; + + if (!f.file) + return -EBADF; + + error = iterate_dir(f.file, &buf.ctx); + if (buf.result) + error = buf.result; + + fdput_pos(f); + return error; +} + +#endif /* __ARCH_WANT_OLD_READDIR */ + +/* + * New, all-improved, singing, dancing, iBCS2-compliant getdents() + * interface. + */ +struct linux_dirent { + unsigned long d_ino; + unsigned long d_off; + unsigned short d_reclen; + char d_name[1]; +}; + +struct getdents_callback { + struct dir_context ctx; + struct linux_dirent __user * current_dir; + int prev_reclen; + int count; + int error; +}; + +static bool filldir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct linux_dirent __user *dirent, *prev; + struct getdents_callback *buf = + container_of(ctx, struct getdents_callback, ctx); + unsigned long d_ino; + int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2, + sizeof(long)); + int prev_reclen; + + buf->error = verify_dirent_name(name, namlen); + if (unlikely(buf->error)) + return false; + buf->error = -EINVAL; /* only used if we fail.. */ + if (reclen > buf->count) + return false; + d_ino = ino; + if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { + buf->error = -EOVERFLOW; + return false; + } + prev_reclen = buf->prev_reclen; + if (prev_reclen && signal_pending(current)) + return false; + dirent = buf->current_dir; + prev = (void __user *) dirent - prev_reclen; + if (!user_write_access_begin(prev, reclen + prev_reclen)) + goto efault; + + /* This might be 'dirent->d_off', but if so it will get overwritten */ + unsafe_put_user(offset, &prev->d_off, efault_end); + unsafe_put_user(d_ino, &dirent->d_ino, efault_end); + unsafe_put_user(reclen, &dirent->d_reclen, efault_end); + unsafe_put_user(d_type, (char __user *) dirent + reclen - 1, efault_end); + unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); + user_write_access_end(); + + buf->current_dir = (void __user *)dirent + reclen; + buf->prev_reclen = reclen; + buf->count -= reclen; + return true; +efault_end: + user_write_access_end(); +efault: + buf->error = -EFAULT; + return false; +} + +SYSCALL_DEFINE3(getdents, unsigned int, fd, + struct linux_dirent __user *, dirent, unsigned int, count) +{ + struct fd f; + struct getdents_callback buf = { + .ctx.actor = filldir, + .count = count, + .current_dir = dirent + }; + int error; + + f = fdget_pos(fd); + if (!f.file) + return -EBADF; + + error = iterate_dir(f.file, &buf.ctx); + if (error >= 0) + error = buf.error; + if (buf.prev_reclen) { + struct linux_dirent __user * lastdirent; + lastdirent = (void __user *)buf.current_dir - buf.prev_reclen; + + if (put_user(buf.ctx.pos, &lastdirent->d_off)) + error = -EFAULT; + else + error = count - buf.count; + } + fdput_pos(f); + return error; +} + +struct getdents_callback64 { + struct dir_context ctx; + struct linux_dirent64 __user * current_dir; + int prev_reclen; + int count; + int error; +}; + +static bool filldir64(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct linux_dirent64 __user *dirent, *prev; + struct getdents_callback64 *buf = + container_of(ctx, struct getdents_callback64, ctx); + int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, + sizeof(u64)); + int prev_reclen; + + buf->error = verify_dirent_name(name, namlen); + if (unlikely(buf->error)) + return false; + buf->error = -EINVAL; /* only used if we fail.. */ + if (reclen > buf->count) + return false; + prev_reclen = buf->prev_reclen; + if (prev_reclen && signal_pending(current)) + return false; + dirent = buf->current_dir; + prev = (void __user *)dirent - prev_reclen; + if (!user_write_access_begin(prev, reclen + prev_reclen)) + goto efault; + + /* This might be 'dirent->d_off', but if so it will get overwritten */ + unsafe_put_user(offset, &prev->d_off, efault_end); + unsafe_put_user(ino, &dirent->d_ino, efault_end); + unsafe_put_user(reclen, &dirent->d_reclen, efault_end); + unsafe_put_user(d_type, &dirent->d_type, efault_end); + unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); + user_write_access_end(); + + buf->prev_reclen = reclen; + buf->current_dir = (void __user *)dirent + reclen; + buf->count -= reclen; + return true; + +efault_end: + user_write_access_end(); +efault: + buf->error = -EFAULT; + return false; +} + +SYSCALL_DEFINE3(getdents64, unsigned int, fd, + struct linux_dirent64 __user *, dirent, unsigned int, count) +{ + struct fd f; + struct getdents_callback64 buf = { + .ctx.actor = filldir64, + .count = count, + .current_dir = dirent + }; + int error; + + f = fdget_pos(fd); + if (!f.file) + return -EBADF; + + error = iterate_dir(f.file, &buf.ctx); + if (error >= 0) + error = buf.error; + if (buf.prev_reclen) { + struct linux_dirent64 __user * lastdirent; + typeof(lastdirent->d_off) d_off = buf.ctx.pos; + + lastdirent = (void __user *) buf.current_dir - buf.prev_reclen; + if (put_user(d_off, &lastdirent->d_off)) + error = -EFAULT; + else + error = count - buf.count; + } + fdput_pos(f); + return error; +} + +#ifdef CONFIG_COMPAT +struct compat_old_linux_dirent { + compat_ulong_t d_ino; + compat_ulong_t d_offset; + unsigned short d_namlen; + char d_name[1]; +}; + +struct compat_readdir_callback { + struct dir_context ctx; + struct compat_old_linux_dirent __user *dirent; + int result; +}; + +static bool compat_fillonedir(struct dir_context *ctx, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) +{ + struct compat_readdir_callback *buf = + container_of(ctx, struct compat_readdir_callback, ctx); + struct compat_old_linux_dirent __user *dirent; + compat_ulong_t d_ino; + + if (buf->result) + return false; + buf->result = verify_dirent_name(name, namlen); + if (buf->result) + return false; + d_ino = ino; + if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { + buf->result = -EOVERFLOW; + return false; + } + buf->result++; + dirent = buf->dirent; + if (!user_write_access_begin(dirent, + (unsigned long)(dirent->d_name + namlen + 1) - + (unsigned long)dirent)) + goto efault; + unsafe_put_user(d_ino, &dirent->d_ino, efault_end); + unsafe_put_user(offset, &dirent->d_offset, efault_end); + unsafe_put_user(namlen, &dirent->d_namlen, efault_end); + unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); + user_write_access_end(); + return true; +efault_end: + user_write_access_end(); +efault: + buf->result = -EFAULT; + return false; +} + +COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd, + struct compat_old_linux_dirent __user *, dirent, unsigned int, count) +{ + int error; + struct fd f = fdget_pos(fd); + struct compat_readdir_callback buf = { + .ctx.actor = compat_fillonedir, + .dirent = dirent + }; + + if (!f.file) + return -EBADF; + + error = iterate_dir(f.file, &buf.ctx); + if (buf.result) + error = buf.result; + + fdput_pos(f); + return error; +} + +struct compat_linux_dirent { + compat_ulong_t d_ino; + compat_ulong_t d_off; + unsigned short d_reclen; + char d_name[1]; +}; + +struct compat_getdents_callback { + struct dir_context ctx; + struct compat_linux_dirent __user *current_dir; + int prev_reclen; + int count; + int error; +}; + +static bool compat_filldir(struct dir_context *ctx, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) +{ + struct compat_linux_dirent __user *dirent, *prev; + struct compat_getdents_callback *buf = + container_of(ctx, struct compat_getdents_callback, ctx); + compat_ulong_t d_ino; + int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) + + namlen + 2, sizeof(compat_long_t)); + int prev_reclen; + + buf->error = verify_dirent_name(name, namlen); + if (unlikely(buf->error)) + return false; + buf->error = -EINVAL; /* only used if we fail.. */ + if (reclen > buf->count) + return false; + d_ino = ino; + if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { + buf->error = -EOVERFLOW; + return false; + } + prev_reclen = buf->prev_reclen; + if (prev_reclen && signal_pending(current)) + return false; + dirent = buf->current_dir; + prev = (void __user *) dirent - prev_reclen; + if (!user_write_access_begin(prev, reclen + prev_reclen)) + goto efault; + + unsafe_put_user(offset, &prev->d_off, efault_end); + unsafe_put_user(d_ino, &dirent->d_ino, efault_end); + unsafe_put_user(reclen, &dirent->d_reclen, efault_end); + unsafe_put_user(d_type, (char __user *) dirent + reclen - 1, efault_end); + unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); + user_write_access_end(); + + buf->prev_reclen = reclen; + buf->current_dir = (void __user *)dirent + reclen; + buf->count -= reclen; + return true; +efault_end: + user_write_access_end(); +efault: + buf->error = -EFAULT; + return false; +} + +COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, + struct compat_linux_dirent __user *, dirent, unsigned int, count) +{ + struct fd f; + struct compat_getdents_callback buf = { + .ctx.actor = compat_filldir, + .current_dir = dirent, + .count = count + }; + int error; + + f = fdget_pos(fd); + if (!f.file) + return -EBADF; + + error = iterate_dir(f.file, &buf.ctx); + if (error >= 0) + error = buf.error; + if (buf.prev_reclen) { + struct compat_linux_dirent __user * lastdirent; + lastdirent = (void __user *)buf.current_dir - buf.prev_reclen; + + if (put_user(buf.ctx.pos, &lastdirent->d_off)) + error = -EFAULT; + else + error = count - buf.count; + } + fdput_pos(f); + return error; +} +#endif -- cgit v1.2.3