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/gfs2/meta_io.c | 554 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 554 insertions(+) create mode 100644 fs/gfs2/meta_io.c (limited to 'fs/gfs2/meta_io.c') diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c new file mode 100644 index 000000000..3c41b864e --- /dev/null +++ b/fs/gfs2/meta_io.c @@ -0,0 +1,554 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. + * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "gfs2.h" +#include "incore.h" +#include "glock.h" +#include "glops.h" +#include "inode.h" +#include "log.h" +#include "lops.h" +#include "meta_io.h" +#include "rgrp.h" +#include "trans.h" +#include "util.h" +#include "trace_gfs2.h" + +static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc) +{ + struct buffer_head *bh, *head; + int nr_underway = 0; + blk_opf_t write_flags = REQ_META | REQ_PRIO | wbc_to_write_flags(wbc); + + BUG_ON(!PageLocked(page)); + BUG_ON(!page_has_buffers(page)); + + head = page_buffers(page); + bh = head; + + do { + if (!buffer_mapped(bh)) + continue; + /* + * If it's a fully non-blocking write attempt and we cannot + * lock the buffer then redirty the page. Note that this can + * potentially cause a busy-wait loop from flusher thread and kswapd + * activity, but those code paths have their own higher-level + * throttling. + */ + if (wbc->sync_mode != WB_SYNC_NONE) { + lock_buffer(bh); + } else if (!trylock_buffer(bh)) { + redirty_page_for_writepage(wbc, page); + continue; + } + if (test_clear_buffer_dirty(bh)) { + mark_buffer_async_write(bh); + } else { + unlock_buffer(bh); + } + } while ((bh = bh->b_this_page) != head); + + /* + * The page and its buffers are protected by PageWriteback(), so we can + * drop the bh refcounts early. + */ + BUG_ON(PageWriteback(page)); + set_page_writeback(page); + + do { + struct buffer_head *next = bh->b_this_page; + if (buffer_async_write(bh)) { + submit_bh(REQ_OP_WRITE | write_flags, bh); + nr_underway++; + } + bh = next; + } while (bh != head); + unlock_page(page); + + if (nr_underway == 0) + end_page_writeback(page); + + return 0; +} + +const struct address_space_operations gfs2_meta_aops = { + .dirty_folio = block_dirty_folio, + .invalidate_folio = block_invalidate_folio, + .writepage = gfs2_aspace_writepage, + .release_folio = gfs2_release_folio, +}; + +const struct address_space_operations gfs2_rgrp_aops = { + .dirty_folio = block_dirty_folio, + .invalidate_folio = block_invalidate_folio, + .writepage = gfs2_aspace_writepage, + .release_folio = gfs2_release_folio, +}; + +/** + * gfs2_getbuf - Get a buffer with a given address space + * @gl: the glock + * @blkno: the block number (filesystem scope) + * @create: 1 if the buffer should be created + * + * Returns: the buffer + */ + +struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create) +{ + struct address_space *mapping = gfs2_glock2aspace(gl); + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct page *page; + struct buffer_head *bh; + unsigned int shift; + unsigned long index; + unsigned int bufnum; + + if (mapping == NULL) + mapping = &sdp->sd_aspace; + + shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift; + index = blkno >> shift; /* convert block to page */ + bufnum = blkno - (index << shift); /* block buf index within page */ + + if (create) { + for (;;) { + page = grab_cache_page(mapping, index); + if (page) + break; + yield(); + } + if (!page_has_buffers(page)) + create_empty_buffers(page, sdp->sd_sb.sb_bsize, 0); + } else { + page = find_get_page_flags(mapping, index, + FGP_LOCK|FGP_ACCESSED); + if (!page) + return NULL; + if (!page_has_buffers(page)) { + bh = NULL; + goto out_unlock; + } + } + + /* Locate header for our buffer within our page */ + for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page) + /* Do nothing */; + get_bh(bh); + + if (!buffer_mapped(bh)) + map_bh(bh, sdp->sd_vfs, blkno); + +out_unlock: + unlock_page(page); + put_page(page); + + return bh; +} + +static void meta_prep_new(struct buffer_head *bh) +{ + struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data; + + lock_buffer(bh); + clear_buffer_dirty(bh); + set_buffer_uptodate(bh); + unlock_buffer(bh); + + mh->mh_magic = cpu_to_be32(GFS2_MAGIC); +} + +/** + * gfs2_meta_new - Get a block + * @gl: The glock associated with this block + * @blkno: The block number + * + * Returns: The buffer + */ + +struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno) +{ + struct buffer_head *bh; + bh = gfs2_getbuf(gl, blkno, CREATE); + meta_prep_new(bh); + return bh; +} + +static void gfs2_meta_read_endio(struct bio *bio) +{ + struct bio_vec *bvec; + struct bvec_iter_all iter_all; + + bio_for_each_segment_all(bvec, bio, iter_all) { + struct page *page = bvec->bv_page; + struct buffer_head *bh = page_buffers(page); + unsigned int len = bvec->bv_len; + + while (bh_offset(bh) < bvec->bv_offset) + bh = bh->b_this_page; + do { + struct buffer_head *next = bh->b_this_page; + len -= bh->b_size; + bh->b_end_io(bh, !bio->bi_status); + bh = next; + } while (bh && len); + } + bio_put(bio); +} + +/* + * Submit several consecutive buffer head I/O requests as a single bio I/O + * request. (See submit_bh_wbc.) + */ +static void gfs2_submit_bhs(blk_opf_t opf, struct buffer_head *bhs[], int num) +{ + while (num > 0) { + struct buffer_head *bh = *bhs; + struct bio *bio; + + bio = bio_alloc(bh->b_bdev, num, opf, GFP_NOIO); + bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); + while (num > 0) { + bh = *bhs; + if (!bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh))) { + BUG_ON(bio->bi_iter.bi_size == 0); + break; + } + bhs++; + num--; + } + bio->bi_end_io = gfs2_meta_read_endio; + submit_bio(bio); + } +} + +/** + * gfs2_meta_read - Read a block from disk + * @gl: The glock covering the block + * @blkno: The block number + * @flags: flags + * @rahead: Do read-ahead + * @bhp: the place where the buffer is returned (NULL on failure) + * + * Returns: errno + */ + +int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, + int rahead, struct buffer_head **bhp) +{ + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct buffer_head *bh, *bhs[2]; + int num = 0; + + if (unlikely(gfs2_withdrawn(sdp)) && !gfs2_withdraw_in_prog(sdp)) { + *bhp = NULL; + return -EIO; + } + + *bhp = bh = gfs2_getbuf(gl, blkno, CREATE); + + lock_buffer(bh); + if (buffer_uptodate(bh)) { + unlock_buffer(bh); + flags &= ~DIO_WAIT; + } else { + bh->b_end_io = end_buffer_read_sync; + get_bh(bh); + bhs[num++] = bh; + } + + if (rahead) { + bh = gfs2_getbuf(gl, blkno + 1, CREATE); + + lock_buffer(bh); + if (buffer_uptodate(bh)) { + unlock_buffer(bh); + brelse(bh); + } else { + bh->b_end_io = end_buffer_read_sync; + bhs[num++] = bh; + } + } + + gfs2_submit_bhs(REQ_OP_READ | REQ_META | REQ_PRIO, bhs, num); + if (!(flags & DIO_WAIT)) + return 0; + + bh = *bhp; + wait_on_buffer(bh); + if (unlikely(!buffer_uptodate(bh))) { + struct gfs2_trans *tr = current->journal_info; + if (tr && test_bit(TR_TOUCHED, &tr->tr_flags)) + gfs2_io_error_bh_wd(sdp, bh); + brelse(bh); + *bhp = NULL; + return -EIO; + } + + return 0; +} + +/** + * gfs2_meta_wait - Reread a block from disk + * @sdp: the filesystem + * @bh: The block to wait for + * + * Returns: errno + */ + +int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh) +{ + if (unlikely(gfs2_withdrawn(sdp)) && !gfs2_withdraw_in_prog(sdp)) + return -EIO; + + wait_on_buffer(bh); + + if (!buffer_uptodate(bh)) { + struct gfs2_trans *tr = current->journal_info; + if (tr && test_bit(TR_TOUCHED, &tr->tr_flags)) + gfs2_io_error_bh_wd(sdp, bh); + return -EIO; + } + if (unlikely(gfs2_withdrawn(sdp)) && !gfs2_withdraw_in_prog(sdp)) + return -EIO; + + return 0; +} + +void gfs2_remove_from_journal(struct buffer_head *bh, int meta) +{ + struct address_space *mapping = bh->b_page->mapping; + struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping); + struct gfs2_bufdata *bd = bh->b_private; + struct gfs2_trans *tr = current->journal_info; + int was_pinned = 0; + + if (test_clear_buffer_pinned(bh)) { + trace_gfs2_pin(bd, 0); + atomic_dec(&sdp->sd_log_pinned); + list_del_init(&bd->bd_list); + if (meta == REMOVE_META) + tr->tr_num_buf_rm++; + else + tr->tr_num_databuf_rm++; + set_bit(TR_TOUCHED, &tr->tr_flags); + was_pinned = 1; + brelse(bh); + } + if (bd) { + if (bd->bd_tr) { + gfs2_trans_add_revoke(sdp, bd); + } else if (was_pinned) { + bh->b_private = NULL; + kmem_cache_free(gfs2_bufdata_cachep, bd); + } else if (!list_empty(&bd->bd_ail_st_list) && + !list_empty(&bd->bd_ail_gl_list)) { + gfs2_remove_from_ail(bd); + } + } + clear_buffer_dirty(bh); + clear_buffer_uptodate(bh); +} + +/** + * gfs2_ail1_wipe - remove deleted/freed buffers from the ail1 list + * @sdp: superblock + * @bstart: starting block address of buffers to remove + * @blen: length of buffers to be removed + * + * This function is called from gfs2_journal wipe, whose job is to remove + * buffers, corresponding to deleted blocks, from the journal. If we find any + * bufdata elements on the system ail1 list, they haven't been written to + * the journal yet. So we remove them. + */ +static void gfs2_ail1_wipe(struct gfs2_sbd *sdp, u64 bstart, u32 blen) +{ + struct gfs2_trans *tr, *s; + struct gfs2_bufdata *bd, *bs; + struct buffer_head *bh; + u64 end = bstart + blen; + + gfs2_log_lock(sdp); + spin_lock(&sdp->sd_ail_lock); + list_for_each_entry_safe(tr, s, &sdp->sd_ail1_list, tr_list) { + list_for_each_entry_safe(bd, bs, &tr->tr_ail1_list, + bd_ail_st_list) { + bh = bd->bd_bh; + if (bh->b_blocknr < bstart || bh->b_blocknr >= end) + continue; + + gfs2_remove_from_journal(bh, REMOVE_JDATA); + } + } + spin_unlock(&sdp->sd_ail_lock); + gfs2_log_unlock(sdp); +} + +static struct buffer_head *gfs2_getjdatabuf(struct gfs2_inode *ip, u64 blkno) +{ + struct address_space *mapping = ip->i_inode.i_mapping; + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + struct page *page; + struct buffer_head *bh; + unsigned int shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift; + unsigned long index = blkno >> shift; /* convert block to page */ + unsigned int bufnum = blkno - (index << shift); + + page = find_get_page_flags(mapping, index, FGP_LOCK|FGP_ACCESSED); + if (!page) + return NULL; + if (!page_has_buffers(page)) { + unlock_page(page); + put_page(page); + return NULL; + } + /* Locate header for our buffer within our page */ + for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page) + /* Do nothing */; + get_bh(bh); + unlock_page(page); + put_page(page); + return bh; +} + +/** + * gfs2_journal_wipe - make inode's buffers so they aren't dirty/pinned anymore + * @ip: the inode who owns the buffers + * @bstart: the first buffer in the run + * @blen: the number of buffers in the run + * + */ + +void gfs2_journal_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen) +{ + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + struct buffer_head *bh; + int ty; + + if (!ip->i_gl) { + /* This can only happen during incomplete inode creation. */ + BUG_ON(!test_bit(GIF_ALLOC_FAILED, &ip->i_flags)); + return; + } + + gfs2_ail1_wipe(sdp, bstart, blen); + while (blen) { + ty = REMOVE_META; + bh = gfs2_getbuf(ip->i_gl, bstart, NO_CREATE); + if (!bh && gfs2_is_jdata(ip)) { + bh = gfs2_getjdatabuf(ip, bstart); + ty = REMOVE_JDATA; + } + if (bh) { + lock_buffer(bh); + gfs2_log_lock(sdp); + spin_lock(&sdp->sd_ail_lock); + gfs2_remove_from_journal(bh, ty); + spin_unlock(&sdp->sd_ail_lock); + gfs2_log_unlock(sdp); + unlock_buffer(bh); + brelse(bh); + } + + bstart++; + blen--; + } +} + +/** + * gfs2_meta_buffer - Get a metadata buffer + * @ip: The GFS2 inode + * @mtype: The block type (GFS2_METATYPE_*) + * @num: The block number (device relative) of the buffer + * @bhp: the buffer is returned here + * + * Returns: errno + */ + +int gfs2_meta_buffer(struct gfs2_inode *ip, u32 mtype, u64 num, + struct buffer_head **bhp) +{ + struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); + struct gfs2_glock *gl = ip->i_gl; + struct buffer_head *bh; + int ret = 0; + int rahead = 0; + + if (num == ip->i_no_addr) + rahead = ip->i_rahead; + + ret = gfs2_meta_read(gl, num, DIO_WAIT, rahead, &bh); + if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) { + brelse(bh); + ret = -EIO; + } else { + *bhp = bh; + } + return ret; +} + +/** + * gfs2_meta_ra - start readahead on an extent of a file + * @gl: the glock the blocks belong to + * @dblock: the starting disk block + * @extlen: the number of blocks in the extent + * + * returns: the first buffer in the extent + */ + +struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen) +{ + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct buffer_head *first_bh, *bh; + u32 max_ra = gfs2_tune_get(sdp, gt_max_readahead) >> + sdp->sd_sb.sb_bsize_shift; + + BUG_ON(!extlen); + + if (max_ra < 1) + max_ra = 1; + if (extlen > max_ra) + extlen = max_ra; + + first_bh = gfs2_getbuf(gl, dblock, CREATE); + + if (buffer_uptodate(first_bh)) + goto out; + bh_read_nowait(first_bh, REQ_META | REQ_PRIO); + + dblock++; + extlen--; + + while (extlen) { + bh = gfs2_getbuf(gl, dblock, CREATE); + + bh_readahead(bh, REQ_RAHEAD | REQ_META | REQ_PRIO); + brelse(bh); + dblock++; + extlen--; + if (!buffer_locked(first_bh) && buffer_uptodate(first_bh)) + goto out; + } + + wait_on_buffer(first_bh); +out: + return first_bh; +} + -- cgit v1.2.3