aboutsummaryrefslogtreecommitdiff
path: root/fs/nilfs2/mdt.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /fs/nilfs2/mdt.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
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(). ...
Diffstat (limited to 'fs/nilfs2/mdt.c')
-rw-r--r--fs/nilfs2/mdt.c665
1 files changed, 665 insertions, 0 deletions
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
new file mode 100644
index 000000000..cbf4fa60e
--- /dev/null
+++ b/fs/nilfs2/mdt.c
@@ -0,0 +1,665 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Meta data file for NILFS
+ *
+ * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
+ *
+ * Written by Ryusuke Konishi.
+ */
+
+#include <linux/buffer_head.h>
+#include <linux/mpage.h>
+#include <linux/mm.h>
+#include <linux/writeback.h>
+#include <linux/backing-dev.h>
+#include <linux/swap.h>
+#include <linux/slab.h>
+#include "nilfs.h"
+#include "btnode.h"
+#include "segment.h"
+#include "page.h"
+#include "mdt.h"
+#include "alloc.h" /* nilfs_palloc_destroy_cache() */
+
+#include <trace/events/nilfs2.h>
+
+#define NILFS_MDT_MAX_RA_BLOCKS (16 - 1)
+
+
+static int
+nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block,
+ struct buffer_head *bh,
+ void (*init_block)(struct inode *,
+ struct buffer_head *, void *))
+{
+ struct nilfs_inode_info *ii = NILFS_I(inode);
+ void *kaddr;
+ int ret;
+
+ /* Caller exclude read accesses using page lock */
+
+ /* set_buffer_new(bh); */
+ bh->b_blocknr = 0;
+
+ ret = nilfs_bmap_insert(ii->i_bmap, block, (unsigned long)bh);
+ if (unlikely(ret))
+ return ret;
+
+ set_buffer_mapped(bh);
+
+ kaddr = kmap_atomic(bh->b_page);
+ memset(kaddr + bh_offset(bh), 0, i_blocksize(inode));
+ if (init_block)
+ init_block(inode, bh, kaddr);
+ flush_dcache_page(bh->b_page);
+ kunmap_atomic(kaddr);
+
+ set_buffer_uptodate(bh);
+ mark_buffer_dirty(bh);
+ nilfs_mdt_mark_dirty(inode);
+
+ trace_nilfs2_mdt_insert_new_block(inode, inode->i_ino, block);
+
+ return 0;
+}
+
+static int nilfs_mdt_create_block(struct inode *inode, unsigned long block,
+ struct buffer_head **out_bh,
+ void (*init_block)(struct inode *,
+ struct buffer_head *,
+ void *))
+{
+ struct super_block *sb = inode->i_sb;
+ struct nilfs_transaction_info ti;
+ struct buffer_head *bh;
+ int err;
+
+ nilfs_transaction_begin(sb, &ti, 0);
+
+ err = -ENOMEM;
+ bh = nilfs_grab_buffer(inode, inode->i_mapping, block, 0);
+ if (unlikely(!bh))
+ goto failed_unlock;
+
+ err = -EEXIST;
+ if (buffer_uptodate(bh))
+ goto failed_bh;
+
+ wait_on_buffer(bh);
+ if (buffer_uptodate(bh))
+ goto failed_bh;
+
+ bh->b_bdev = sb->s_bdev;
+ err = nilfs_mdt_insert_new_block(inode, block, bh, init_block);
+ if (likely(!err)) {
+ get_bh(bh);
+ *out_bh = bh;
+ }
+
+ failed_bh:
+ unlock_page(bh->b_page);
+ put_page(bh->b_page);
+ brelse(bh);
+
+ failed_unlock:
+ if (likely(!err))
+ err = nilfs_transaction_commit(sb);
+ else
+ nilfs_transaction_abort(sb);
+
+ return err;
+}
+
+static int
+nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff, blk_opf_t opf,
+ struct buffer_head **out_bh)
+{
+ struct buffer_head *bh;
+ __u64 blknum = 0;
+ int ret = -ENOMEM;
+
+ bh = nilfs_grab_buffer(inode, inode->i_mapping, blkoff, 0);
+ if (unlikely(!bh))
+ goto failed;
+
+ ret = -EEXIST; /* internal code */
+ if (buffer_uptodate(bh))
+ goto out;
+
+ if (opf & REQ_RAHEAD) {
+ if (!trylock_buffer(bh)) {
+ ret = -EBUSY;
+ goto failed_bh;
+ }
+ } else /* opf == REQ_OP_READ */
+ lock_buffer(bh);
+
+ if (buffer_uptodate(bh)) {
+ unlock_buffer(bh);
+ goto out;
+ }
+
+ ret = nilfs_bmap_lookup(NILFS_I(inode)->i_bmap, blkoff, &blknum);
+ if (unlikely(ret)) {
+ unlock_buffer(bh);
+ goto failed_bh;
+ }
+ map_bh(bh, inode->i_sb, (sector_t)blknum);
+
+ bh->b_end_io = end_buffer_read_sync;
+ get_bh(bh);
+ submit_bh(opf, bh);
+ ret = 0;
+
+ trace_nilfs2_mdt_submit_block(inode, inode->i_ino, blkoff,
+ opf & REQ_OP_MASK);
+ out:
+ get_bh(bh);
+ *out_bh = bh;
+
+ failed_bh:
+ unlock_page(bh->b_page);
+ put_page(bh->b_page);
+ brelse(bh);
+ failed:
+ return ret;
+}
+
+static int nilfs_mdt_read_block(struct inode *inode, unsigned long block,
+ int readahead, struct buffer_head **out_bh)
+{
+ struct buffer_head *first_bh, *bh;
+ unsigned long blkoff;
+ int i, nr_ra_blocks = NILFS_MDT_MAX_RA_BLOCKS;
+ int err;
+
+ err = nilfs_mdt_submit_block(inode, block, REQ_OP_READ, &first_bh);
+ if (err == -EEXIST) /* internal code */
+ goto out;
+
+ if (unlikely(err))
+ goto failed;
+
+ if (readahead) {
+ blkoff = block + 1;
+ for (i = 0; i < nr_ra_blocks; i++, blkoff++) {
+ err = nilfs_mdt_submit_block(inode, blkoff,
+ REQ_OP_READ | REQ_RAHEAD, &bh);
+ if (likely(!err || err == -EEXIST))
+ brelse(bh);
+ else if (err != -EBUSY)
+ break;
+ /* abort readahead if bmap lookup failed */
+ if (!buffer_locked(first_bh))
+ goto out_no_wait;
+ }
+ }
+
+ wait_on_buffer(first_bh);
+
+ out_no_wait:
+ err = -EIO;
+ if (!buffer_uptodate(first_bh)) {
+ nilfs_err(inode->i_sb,
+ "I/O error reading meta-data file (ino=%lu, block-offset=%lu)",
+ inode->i_ino, block);
+ goto failed_bh;
+ }
+ out:
+ *out_bh = first_bh;
+ return 0;
+
+ failed_bh:
+ brelse(first_bh);
+ failed:
+ return err;
+}
+
+/**
+ * nilfs_mdt_get_block - read or create a buffer on meta data file.
+ * @inode: inode of the meta data file
+ * @blkoff: block offset
+ * @create: create flag
+ * @init_block: initializer used for newly allocated block
+ * @out_bh: output of a pointer to the buffer_head
+ *
+ * nilfs_mdt_get_block() looks up the specified buffer and tries to create
+ * a new buffer if @create is not zero. On success, the returned buffer is
+ * assured to be either existing or formatted using a buffer lock on success.
+ * @out_bh is substituted only when zero is returned.
+ *
+ * Return Value: On success, it returns 0. On error, the following negative
+ * error code is returned.
+ *
+ * %-ENOMEM - Insufficient memory available.
+ *
+ * %-EIO - I/O error
+ *
+ * %-ENOENT - the specified block does not exist (hole block)
+ *
+ * %-EROFS - Read only filesystem (for create mode)
+ */
+int nilfs_mdt_get_block(struct inode *inode, unsigned long blkoff, int create,
+ void (*init_block)(struct inode *,
+ struct buffer_head *, void *),
+ struct buffer_head **out_bh)
+{
+ int ret;
+
+ /* Should be rewritten with merging nilfs_mdt_read_block() */
+ retry:
+ ret = nilfs_mdt_read_block(inode, blkoff, !create, out_bh);
+ if (!create || ret != -ENOENT)
+ return ret;
+
+ ret = nilfs_mdt_create_block(inode, blkoff, out_bh, init_block);
+ if (unlikely(ret == -EEXIST)) {
+ /* create = 0; */ /* limit read-create loop retries */
+ goto retry;
+ }
+ return ret;
+}
+
+/**
+ * nilfs_mdt_find_block - find and get a buffer on meta data file.
+ * @inode: inode of the meta data file
+ * @start: start block offset (inclusive)
+ * @end: end block offset (inclusive)
+ * @blkoff: block offset
+ * @out_bh: place to store a pointer to buffer_head struct
+ *
+ * nilfs_mdt_find_block() looks up an existing block in range of
+ * [@start, @end] and stores pointer to a buffer head of the block to
+ * @out_bh, and block offset to @blkoff, respectively. @out_bh and
+ * @blkoff are substituted only when zero is returned.
+ *
+ * Return Value: On success, it returns 0. On error, the following negative
+ * error code is returned.
+ *
+ * %-ENOMEM - Insufficient memory available.
+ *
+ * %-EIO - I/O error
+ *
+ * %-ENOENT - no block was found in the range
+ */
+int nilfs_mdt_find_block(struct inode *inode, unsigned long start,
+ unsigned long end, unsigned long *blkoff,
+ struct buffer_head **out_bh)
+{
+ __u64 next;
+ int ret;
+
+ if (unlikely(start > end))
+ return -ENOENT;
+
+ ret = nilfs_mdt_read_block(inode, start, true, out_bh);
+ if (!ret) {
+ *blkoff = start;
+ goto out;
+ }
+ if (unlikely(ret != -ENOENT || start == ULONG_MAX))
+ goto out;
+
+ ret = nilfs_bmap_seek_key(NILFS_I(inode)->i_bmap, start + 1, &next);
+ if (!ret) {
+ if (next <= end) {
+ ret = nilfs_mdt_read_block(inode, next, true, out_bh);
+ if (!ret)
+ *blkoff = next;
+ } else {
+ ret = -ENOENT;
+ }
+ }
+out:
+ return ret;
+}
+
+/**
+ * nilfs_mdt_delete_block - make a hole on the meta data file.
+ * @inode: inode of the meta data file
+ * @block: block offset
+ *
+ * Return Value: On success, zero is returned.
+ * On error, one of the following negative error code is returned.
+ *
+ * %-ENOMEM - Insufficient memory available.
+ *
+ * %-EIO - I/O error
+ */
+int nilfs_mdt_delete_block(struct inode *inode, unsigned long block)
+{
+ struct nilfs_inode_info *ii = NILFS_I(inode);
+ int err;
+
+ err = nilfs_bmap_delete(ii->i_bmap, block);
+ if (!err || err == -ENOENT) {
+ nilfs_mdt_mark_dirty(inode);
+ nilfs_mdt_forget_block(inode, block);
+ }
+ return err;
+}
+
+/**
+ * nilfs_mdt_forget_block - discard dirty state and try to remove the page
+ * @inode: inode of the meta data file
+ * @block: block offset
+ *
+ * nilfs_mdt_forget_block() clears a dirty flag of the specified buffer, and
+ * tries to release the page including the buffer from a page cache.
+ *
+ * Return Value: On success, 0 is returned. On error, one of the following
+ * negative error code is returned.
+ *
+ * %-EBUSY - page has an active buffer.
+ *
+ * %-ENOENT - page cache has no page addressed by the offset.
+ */
+int nilfs_mdt_forget_block(struct inode *inode, unsigned long block)
+{
+ pgoff_t index = (pgoff_t)block >>
+ (PAGE_SHIFT - inode->i_blkbits);
+ struct page *page;
+ unsigned long first_block;
+ int ret = 0;
+ int still_dirty;
+
+ page = find_lock_page(inode->i_mapping, index);
+ if (!page)
+ return -ENOENT;
+
+ wait_on_page_writeback(page);
+
+ first_block = (unsigned long)index <<
+ (PAGE_SHIFT - inode->i_blkbits);
+ if (page_has_buffers(page)) {
+ struct buffer_head *bh;
+
+ bh = nilfs_page_get_nth_block(page, block - first_block);
+ nilfs_forget_buffer(bh);
+ }
+ still_dirty = PageDirty(page);
+ unlock_page(page);
+ put_page(page);
+
+ if (still_dirty ||
+ invalidate_inode_pages2_range(inode->i_mapping, index, index) != 0)
+ ret = -EBUSY;
+ return ret;
+}
+
+int nilfs_mdt_fetch_dirty(struct inode *inode)
+{
+ struct nilfs_inode_info *ii = NILFS_I(inode);
+
+ if (nilfs_bmap_test_and_clear_dirty(ii->i_bmap)) {
+ set_bit(NILFS_I_DIRTY, &ii->i_state);
+ return 1;
+ }
+ return test_bit(NILFS_I_DIRTY, &ii->i_state);
+}
+
+static int
+nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc)
+{
+ struct inode *inode = page->mapping->host;
+ struct super_block *sb;
+ int err = 0;
+
+ if (inode && sb_rdonly(inode->i_sb)) {
+ /*
+ * It means that filesystem was remounted in read-only
+ * mode because of error or metadata corruption. But we
+ * have dirty pages that try to be flushed in background.
+ * So, here we simply discard this dirty page.
+ */
+ nilfs_clear_dirty_page(page, false);
+ unlock_page(page);
+ return -EROFS;
+ }
+
+ redirty_page_for_writepage(wbc, page);
+ unlock_page(page);
+
+ if (!inode)
+ return 0;
+
+ sb = inode->i_sb;
+
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ err = nilfs_construct_segment(sb);
+ else if (wbc->for_reclaim)
+ nilfs_flush_segment(sb, inode->i_ino);
+
+ return err;
+}
+
+
+static const struct address_space_operations def_mdt_aops = {
+ .dirty_folio = block_dirty_folio,
+ .invalidate_folio = block_invalidate_folio,
+ .writepage = nilfs_mdt_write_page,
+};
+
+static const struct inode_operations def_mdt_iops;
+static const struct file_operations def_mdt_fops;
+
+
+int nilfs_mdt_init(struct inode *inode, gfp_t gfp_mask, size_t objsz)
+{
+ struct nilfs_mdt_info *mi;
+
+ mi = kzalloc(max(sizeof(*mi), objsz), GFP_NOFS);
+ if (!mi)
+ return -ENOMEM;
+
+ init_rwsem(&mi->mi_sem);
+ inode->i_private = mi;
+
+ inode->i_mode = S_IFREG;
+ mapping_set_gfp_mask(inode->i_mapping, gfp_mask);
+
+ inode->i_op = &def_mdt_iops;
+ inode->i_fop = &def_mdt_fops;
+ inode->i_mapping->a_ops = &def_mdt_aops;
+
+ return 0;
+}
+
+/**
+ * nilfs_mdt_clear - do cleanup for the metadata file
+ * @inode: inode of the metadata file
+ */
+void nilfs_mdt_clear(struct inode *inode)
+{
+ struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
+ struct nilfs_shadow_map *shadow = mdi->mi_shadow;
+
+ if (mdi->mi_palloc_cache)
+ nilfs_palloc_destroy_cache(inode);
+
+ if (shadow) {
+ struct inode *s_inode = shadow->inode;
+
+ shadow->inode = NULL;
+ iput(s_inode);
+ mdi->mi_shadow = NULL;
+ }
+}
+
+/**
+ * nilfs_mdt_destroy - release resources used by the metadata file
+ * @inode: inode of the metadata file
+ */
+void nilfs_mdt_destroy(struct inode *inode)
+{
+ struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
+
+ kfree(mdi->mi_bgl); /* kfree(NULL) is safe */
+ kfree(mdi);
+}
+
+void nilfs_mdt_set_entry_size(struct inode *inode, unsigned int entry_size,
+ unsigned int header_size)
+{
+ struct nilfs_mdt_info *mi = NILFS_MDT(inode);
+
+ mi->mi_entry_size = entry_size;
+ mi->mi_entries_per_block = i_blocksize(inode) / entry_size;
+ mi->mi_first_entry_offset = DIV_ROUND_UP(header_size, entry_size);
+}
+
+/**
+ * nilfs_mdt_setup_shadow_map - setup shadow map and bind it to metadata file
+ * @inode: inode of the metadata file
+ * @shadow: shadow mapping
+ */
+int nilfs_mdt_setup_shadow_map(struct inode *inode,
+ struct nilfs_shadow_map *shadow)
+{
+ struct nilfs_mdt_info *mi = NILFS_MDT(inode);
+ struct inode *s_inode;
+
+ INIT_LIST_HEAD(&shadow->frozen_buffers);
+
+ s_inode = nilfs_iget_for_shadow(inode);
+ if (IS_ERR(s_inode))
+ return PTR_ERR(s_inode);
+
+ shadow->inode = s_inode;
+ mi->mi_shadow = shadow;
+ return 0;
+}
+
+/**
+ * nilfs_mdt_save_to_shadow_map - copy bmap and dirty pages to shadow map
+ * @inode: inode of the metadata file
+ */
+int nilfs_mdt_save_to_shadow_map(struct inode *inode)
+{
+ struct nilfs_mdt_info *mi = NILFS_MDT(inode);
+ struct nilfs_inode_info *ii = NILFS_I(inode);
+ struct nilfs_shadow_map *shadow = mi->mi_shadow;
+ struct inode *s_inode = shadow->inode;
+ int ret;
+
+ ret = nilfs_copy_dirty_pages(s_inode->i_mapping, inode->i_mapping);
+ if (ret)
+ goto out;
+
+ ret = nilfs_copy_dirty_pages(NILFS_I(s_inode)->i_assoc_inode->i_mapping,
+ ii->i_assoc_inode->i_mapping);
+ if (ret)
+ goto out;
+
+ nilfs_bmap_save(ii->i_bmap, &shadow->bmap_store);
+ out:
+ return ret;
+}
+
+int nilfs_mdt_freeze_buffer(struct inode *inode, struct buffer_head *bh)
+{
+ struct nilfs_shadow_map *shadow = NILFS_MDT(inode)->mi_shadow;
+ struct buffer_head *bh_frozen;
+ struct page *page;
+ int blkbits = inode->i_blkbits;
+
+ page = grab_cache_page(shadow->inode->i_mapping, bh->b_page->index);
+ if (!page)
+ return -ENOMEM;
+
+ if (!page_has_buffers(page))
+ create_empty_buffers(page, 1 << blkbits, 0);
+
+ bh_frozen = nilfs_page_get_nth_block(page, bh_offset(bh) >> blkbits);
+
+ if (!buffer_uptodate(bh_frozen))
+ nilfs_copy_buffer(bh_frozen, bh);
+ if (list_empty(&bh_frozen->b_assoc_buffers)) {
+ list_add_tail(&bh_frozen->b_assoc_buffers,
+ &shadow->frozen_buffers);
+ set_buffer_nilfs_redirected(bh);
+ } else {
+ brelse(bh_frozen); /* already frozen */
+ }
+
+ unlock_page(page);
+ put_page(page);
+ return 0;
+}
+
+struct buffer_head *
+nilfs_mdt_get_frozen_buffer(struct inode *inode, struct buffer_head *bh)
+{
+ struct nilfs_shadow_map *shadow = NILFS_MDT(inode)->mi_shadow;
+ struct buffer_head *bh_frozen = NULL;
+ struct page *page;
+ int n;
+
+ page = find_lock_page(shadow->inode->i_mapping, bh->b_page->index);
+ if (page) {
+ if (page_has_buffers(page)) {
+ n = bh_offset(bh) >> inode->i_blkbits;
+ bh_frozen = nilfs_page_get_nth_block(page, n);
+ }
+ unlock_page(page);
+ put_page(page);
+ }
+ return bh_frozen;
+}
+
+static void nilfs_release_frozen_buffers(struct nilfs_shadow_map *shadow)
+{
+ struct list_head *head = &shadow->frozen_buffers;
+ struct buffer_head *bh;
+
+ while (!list_empty(head)) {
+ bh = list_first_entry(head, struct buffer_head,
+ b_assoc_buffers);
+ list_del_init(&bh->b_assoc_buffers);
+ brelse(bh); /* drop ref-count to make it releasable */
+ }
+}
+
+/**
+ * nilfs_mdt_restore_from_shadow_map - restore dirty pages and bmap state
+ * @inode: inode of the metadata file
+ */
+void nilfs_mdt_restore_from_shadow_map(struct inode *inode)
+{
+ struct nilfs_mdt_info *mi = NILFS_MDT(inode);
+ struct nilfs_inode_info *ii = NILFS_I(inode);
+ struct nilfs_shadow_map *shadow = mi->mi_shadow;
+
+ down_write(&mi->mi_sem);
+
+ if (mi->mi_palloc_cache)
+ nilfs_palloc_clear_cache(inode);
+
+ nilfs_clear_dirty_pages(inode->i_mapping, true);
+ nilfs_copy_back_pages(inode->i_mapping, shadow->inode->i_mapping);
+
+ nilfs_clear_dirty_pages(ii->i_assoc_inode->i_mapping, true);
+ nilfs_copy_back_pages(ii->i_assoc_inode->i_mapping,
+ NILFS_I(shadow->inode)->i_assoc_inode->i_mapping);
+
+ nilfs_bmap_restore(ii->i_bmap, &shadow->bmap_store);
+
+ up_write(&mi->mi_sem);
+}
+
+/**
+ * nilfs_mdt_clear_shadow_map - truncate pages in shadow map caches
+ * @inode: inode of the metadata file
+ */
+void nilfs_mdt_clear_shadow_map(struct inode *inode)
+{
+ struct nilfs_mdt_info *mi = NILFS_MDT(inode);
+ struct nilfs_shadow_map *shadow = mi->mi_shadow;
+ struct inode *shadow_btnc_inode = NILFS_I(shadow->inode)->i_assoc_inode;
+
+ down_write(&mi->mi_sem);
+ nilfs_release_frozen_buffers(shadow);
+ truncate_inode_pages(shadow->inode->i_mapping, 0);
+ truncate_inode_pages(shadow_btnc_inode->i_mapping, 0);
+ up_write(&mi->mi_sem);
+}