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/hfs/mdb.c | 372 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 372 insertions(+) create mode 100644 fs/hfs/mdb.c (limited to 'fs/hfs/mdb.c') diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c new file mode 100644 index 000000000..8082eb011 --- /dev/null +++ b/fs/hfs/mdb.c @@ -0,0 +1,372 @@ +/* + * linux/fs/hfs/mdb.c + * + * Copyright (C) 1995-1997 Paul H. Hargrove + * (C) 2003 Ardis Technologies + * This file may be distributed under the terms of the GNU General Public License. + * + * This file contains functions for reading/writing the MDB. + */ + +#include +#include +#include +#include + +#include "hfs_fs.h" +#include "btree.h" + +/*================ File-local data types ================*/ + +/* + * The HFS Master Directory Block (MDB). + * + * Also known as the Volume Information Block (VIB), this structure is + * the HFS equivalent of a superblock. + * + * Reference: _Inside Macintosh: Files_ pages 2-59 through 2-62 + * + * modified for HFS Extended + */ + +static int hfs_get_last_session(struct super_block *sb, + sector_t *start, sector_t *size) +{ + struct cdrom_device_info *cdi = disk_to_cdi(sb->s_bdev->bd_disk); + + /* default values */ + *start = 0; + *size = bdev_nr_sectors(sb->s_bdev); + + if (HFS_SB(sb)->session >= 0) { + struct cdrom_tocentry te; + + if (!cdi) + return -EINVAL; + + te.cdte_track = HFS_SB(sb)->session; + te.cdte_format = CDROM_LBA; + if (cdrom_read_tocentry(cdi, &te) || + (te.cdte_ctrl & CDROM_DATA_TRACK) != 4) { + pr_err("invalid session number or type of track\n"); + return -EINVAL; + } + + *start = (sector_t)te.cdte_addr.lba << 2; + } else if (cdi) { + struct cdrom_multisession ms_info; + + ms_info.addr_format = CDROM_LBA; + if (cdrom_multisession(cdi, &ms_info) == 0 && ms_info.xa_flag) + *start = (sector_t)ms_info.addr.lba << 2; + } + + return 0; +} + +/* + * hfs_mdb_get() + * + * Build the in-core MDB for a filesystem, including + * the B-trees and the volume bitmap. + */ +int hfs_mdb_get(struct super_block *sb) +{ + struct buffer_head *bh; + struct hfs_mdb *mdb, *mdb2; + unsigned int block; + char *ptr; + int off2, len, size, sect; + sector_t part_start, part_size; + loff_t off; + __be16 attrib; + + /* set the device driver to 512-byte blocks */ + size = sb_min_blocksize(sb, HFS_SECTOR_SIZE); + if (!size) + return -EINVAL; + + if (hfs_get_last_session(sb, &part_start, &part_size)) + return -EINVAL; + while (1) { + /* See if this is an HFS filesystem */ + bh = sb_bread512(sb, part_start + HFS_MDB_BLK, mdb); + if (!bh) + goto out; + + if (mdb->drSigWord == cpu_to_be16(HFS_SUPER_MAGIC)) + break; + brelse(bh); + + /* check for a partition block + * (should do this only for cdrom/loop though) + */ + if (hfs_part_find(sb, &part_start, &part_size)) + goto out; + } + + HFS_SB(sb)->alloc_blksz = size = be32_to_cpu(mdb->drAlBlkSiz); + if (!size || (size & (HFS_SECTOR_SIZE - 1))) { + pr_err("bad allocation block size %d\n", size); + goto out_bh; + } + + size = min(HFS_SB(sb)->alloc_blksz, (u32)PAGE_SIZE); + /* size must be a multiple of 512 */ + while (size & (size - 1)) + size -= HFS_SECTOR_SIZE; + sect = be16_to_cpu(mdb->drAlBlSt) + part_start; + /* align block size to first sector */ + while (sect & ((size - 1) >> HFS_SECTOR_SIZE_BITS)) + size >>= 1; + /* align block size to weird alloc size */ + while (HFS_SB(sb)->alloc_blksz & (size - 1)) + size >>= 1; + brelse(bh); + if (!sb_set_blocksize(sb, size)) { + pr_err("unable to set blocksize to %u\n", size); + goto out; + } + + bh = sb_bread512(sb, part_start + HFS_MDB_BLK, mdb); + if (!bh) + goto out; + if (mdb->drSigWord != cpu_to_be16(HFS_SUPER_MAGIC)) + goto out_bh; + + HFS_SB(sb)->mdb_bh = bh; + HFS_SB(sb)->mdb = mdb; + + /* These parameters are read from the MDB, and never written */ + HFS_SB(sb)->part_start = part_start; + HFS_SB(sb)->fs_ablocks = be16_to_cpu(mdb->drNmAlBlks); + HFS_SB(sb)->fs_div = HFS_SB(sb)->alloc_blksz >> sb->s_blocksize_bits; + HFS_SB(sb)->clumpablks = be32_to_cpu(mdb->drClpSiz) / + HFS_SB(sb)->alloc_blksz; + if (!HFS_SB(sb)->clumpablks) + HFS_SB(sb)->clumpablks = 1; + HFS_SB(sb)->fs_start = (be16_to_cpu(mdb->drAlBlSt) + part_start) >> + (sb->s_blocksize_bits - HFS_SECTOR_SIZE_BITS); + + /* These parameters are read from and written to the MDB */ + HFS_SB(sb)->free_ablocks = be16_to_cpu(mdb->drFreeBks); + HFS_SB(sb)->next_id = be32_to_cpu(mdb->drNxtCNID); + HFS_SB(sb)->root_files = be16_to_cpu(mdb->drNmFls); + HFS_SB(sb)->root_dirs = be16_to_cpu(mdb->drNmRtDirs); + HFS_SB(sb)->file_count = be32_to_cpu(mdb->drFilCnt); + HFS_SB(sb)->folder_count = be32_to_cpu(mdb->drDirCnt); + + /* TRY to get the alternate (backup) MDB. */ + sect = part_start + part_size - 2; + bh = sb_bread512(sb, sect, mdb2); + if (bh) { + if (mdb2->drSigWord == cpu_to_be16(HFS_SUPER_MAGIC)) { + HFS_SB(sb)->alt_mdb_bh = bh; + HFS_SB(sb)->alt_mdb = mdb2; + } else + brelse(bh); + } + + if (!HFS_SB(sb)->alt_mdb) { + pr_warn("unable to locate alternate MDB\n"); + pr_warn("continuing without an alternate MDB\n"); + } + + HFS_SB(sb)->bitmap = kmalloc(8192, GFP_KERNEL); + if (!HFS_SB(sb)->bitmap) + goto out; + + /* read in the bitmap */ + block = be16_to_cpu(mdb->drVBMSt) + part_start; + off = (loff_t)block << HFS_SECTOR_SIZE_BITS; + size = (HFS_SB(sb)->fs_ablocks + 8) / 8; + ptr = (u8 *)HFS_SB(sb)->bitmap; + while (size) { + bh = sb_bread(sb, off >> sb->s_blocksize_bits); + if (!bh) { + pr_err("unable to read volume bitmap\n"); + goto out; + } + off2 = off & (sb->s_blocksize - 1); + len = min((int)sb->s_blocksize - off2, size); + memcpy(ptr, bh->b_data + off2, len); + brelse(bh); + ptr += len; + off += len; + size -= len; + } + + HFS_SB(sb)->ext_tree = hfs_btree_open(sb, HFS_EXT_CNID, hfs_ext_keycmp); + if (!HFS_SB(sb)->ext_tree) { + pr_err("unable to open extent tree\n"); + goto out; + } + HFS_SB(sb)->cat_tree = hfs_btree_open(sb, HFS_CAT_CNID, hfs_cat_keycmp); + if (!HFS_SB(sb)->cat_tree) { + pr_err("unable to open catalog tree\n"); + goto out; + } + + attrib = mdb->drAtrb; + if (!(attrib & cpu_to_be16(HFS_SB_ATTRIB_UNMNT))) { + pr_warn("filesystem was not cleanly unmounted, running fsck.hfs is recommended. mounting read-only.\n"); + sb->s_flags |= SB_RDONLY; + } + if ((attrib & cpu_to_be16(HFS_SB_ATTRIB_SLOCK))) { + pr_warn("filesystem is marked locked, mounting read-only.\n"); + sb->s_flags |= SB_RDONLY; + } + if (!sb_rdonly(sb)) { + /* Mark the volume uncleanly unmounted in case we crash */ + attrib &= cpu_to_be16(~HFS_SB_ATTRIB_UNMNT); + attrib |= cpu_to_be16(HFS_SB_ATTRIB_INCNSTNT); + mdb->drAtrb = attrib; + be32_add_cpu(&mdb->drWrCnt, 1); + mdb->drLsMod = hfs_mtime(); + + mark_buffer_dirty(HFS_SB(sb)->mdb_bh); + sync_dirty_buffer(HFS_SB(sb)->mdb_bh); + } + + return 0; + +out_bh: + brelse(bh); +out: + hfs_mdb_put(sb); + return -EIO; +} + +/* + * hfs_mdb_commit() + * + * Description: + * This updates the MDB on disk. + * It does not check, if the superblock has been modified, or + * if the filesystem has been mounted read-only. It is mainly + * called by hfs_sync_fs() and flush_mdb(). + * Input Variable(s): + * struct hfs_mdb *mdb: Pointer to the hfs MDB + * int backup; + * Output Variable(s): + * NONE + * Returns: + * void + * Preconditions: + * 'mdb' points to a "valid" (struct hfs_mdb). + * Postconditions: + * The HFS MDB and on disk will be updated, by copying the possibly + * modified fields from the in memory MDB (in native byte order) to + * the disk block buffer. + * If 'backup' is non-zero then the alternate MDB is also written + * and the function doesn't return until it is actually on disk. + */ +void hfs_mdb_commit(struct super_block *sb) +{ + struct hfs_mdb *mdb = HFS_SB(sb)->mdb; + + if (sb_rdonly(sb)) + return; + + lock_buffer(HFS_SB(sb)->mdb_bh); + if (test_and_clear_bit(HFS_FLG_MDB_DIRTY, &HFS_SB(sb)->flags)) { + /* These parameters may have been modified, so write them back */ + mdb->drLsMod = hfs_mtime(); + mdb->drFreeBks = cpu_to_be16(HFS_SB(sb)->free_ablocks); + mdb->drNxtCNID = cpu_to_be32(HFS_SB(sb)->next_id); + mdb->drNmFls = cpu_to_be16(HFS_SB(sb)->root_files); + mdb->drNmRtDirs = cpu_to_be16(HFS_SB(sb)->root_dirs); + mdb->drFilCnt = cpu_to_be32(HFS_SB(sb)->file_count); + mdb->drDirCnt = cpu_to_be32(HFS_SB(sb)->folder_count); + + /* write MDB to disk */ + mark_buffer_dirty(HFS_SB(sb)->mdb_bh); + } + + /* write the backup MDB, not returning until it is written. + * we only do this when either the catalog or extents overflow + * files grow. */ + if (test_and_clear_bit(HFS_FLG_ALT_MDB_DIRTY, &HFS_SB(sb)->flags) && + HFS_SB(sb)->alt_mdb) { + hfs_inode_write_fork(HFS_SB(sb)->ext_tree->inode, mdb->drXTExtRec, + &mdb->drXTFlSize, NULL); + hfs_inode_write_fork(HFS_SB(sb)->cat_tree->inode, mdb->drCTExtRec, + &mdb->drCTFlSize, NULL); + + lock_buffer(HFS_SB(sb)->alt_mdb_bh); + memcpy(HFS_SB(sb)->alt_mdb, HFS_SB(sb)->mdb, HFS_SECTOR_SIZE); + HFS_SB(sb)->alt_mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT); + HFS_SB(sb)->alt_mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT); + unlock_buffer(HFS_SB(sb)->alt_mdb_bh); + + mark_buffer_dirty(HFS_SB(sb)->alt_mdb_bh); + sync_dirty_buffer(HFS_SB(sb)->alt_mdb_bh); + } + + if (test_and_clear_bit(HFS_FLG_BITMAP_DIRTY, &HFS_SB(sb)->flags)) { + struct buffer_head *bh; + sector_t block; + char *ptr; + int off, size, len; + + block = be16_to_cpu(HFS_SB(sb)->mdb->drVBMSt) + HFS_SB(sb)->part_start; + off = (block << HFS_SECTOR_SIZE_BITS) & (sb->s_blocksize - 1); + block >>= sb->s_blocksize_bits - HFS_SECTOR_SIZE_BITS; + size = (HFS_SB(sb)->fs_ablocks + 7) / 8; + ptr = (u8 *)HFS_SB(sb)->bitmap; + while (size) { + bh = sb_bread(sb, block); + if (!bh) { + pr_err("unable to read volume bitmap\n"); + break; + } + len = min((int)sb->s_blocksize - off, size); + + lock_buffer(bh); + memcpy(bh->b_data + off, ptr, len); + unlock_buffer(bh); + + mark_buffer_dirty(bh); + brelse(bh); + block++; + off = 0; + ptr += len; + size -= len; + } + } + unlock_buffer(HFS_SB(sb)->mdb_bh); +} + +void hfs_mdb_close(struct super_block *sb) +{ + /* update volume attributes */ + if (sb_rdonly(sb)) + return; + HFS_SB(sb)->mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT); + HFS_SB(sb)->mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT); + mark_buffer_dirty(HFS_SB(sb)->mdb_bh); +} + +/* + * hfs_mdb_put() + * + * Release the resources associated with the in-core MDB. */ +void hfs_mdb_put(struct super_block *sb) +{ + if (!HFS_SB(sb)) + return; + /* free the B-trees */ + hfs_btree_close(HFS_SB(sb)->ext_tree); + hfs_btree_close(HFS_SB(sb)->cat_tree); + + /* free the buffers holding the primary and alternate MDBs */ + brelse(HFS_SB(sb)->mdb_bh); + brelse(HFS_SB(sb)->alt_mdb_bh); + + unload_nls(HFS_SB(sb)->nls_io); + unload_nls(HFS_SB(sb)->nls_disk); + + kfree(HFS_SB(sb)->bitmap); + kfree(HFS_SB(sb)); + sb->s_fs_info = NULL; +} -- cgit v1.2.3