summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_fsops.c
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--fs/xfs/xfs_fsops.c580
1 files changed, 580 insertions, 0 deletions
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
new file mode 100644
index 000000000..09fd60250
--- /dev/null
+++ b/fs/xfs/xfs_fsops.c
@@ -0,0 +1,580 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_trans.h"
+#include "xfs_error.h"
+#include "xfs_btree.h"
+#include "xfs_alloc.h"
+#include "xfs_fsops.h"
+#include "xfs_trans_space.h"
+#include "xfs_rtalloc.h"
+#include "xfs_trace.h"
+#include "xfs_log.h"
+#include "xfs_ag.h"
+#include "xfs_ag_resv.h"
+
+/*
+ * growfs operations
+ */
+static int
+xfs_growfs_data_private(
+ xfs_mount_t *mp, /* mount point for filesystem */
+ xfs_growfs_data_t *in) /* growfs data input struct */
+{
+ xfs_buf_t *bp;
+ int error;
+ xfs_agnumber_t nagcount;
+ xfs_agnumber_t nagimax = 0;
+ xfs_rfsblock_t nb, nb_mod;
+ xfs_rfsblock_t new;
+ xfs_agnumber_t oagcount;
+ xfs_trans_t *tp;
+ LIST_HEAD (buffer_list);
+ struct aghdr_init_data id = {};
+
+ nb = in->newblocks;
+ if (nb < mp->m_sb.sb_dblocks)
+ return -EINVAL;
+ if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
+ return error;
+ error = xfs_buf_read_uncached(mp->m_ddev_targp,
+ XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
+ XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
+ if (error)
+ return error;
+ xfs_buf_relse(bp);
+
+ new = nb; /* use new as a temporary here */
+ nb_mod = do_div(new, mp->m_sb.sb_agblocks);
+ nagcount = new + (nb_mod != 0);
+ if (nb_mod && nb_mod < XFS_MIN_AG_BLOCKS) {
+ nagcount--;
+ nb = (xfs_rfsblock_t)nagcount * mp->m_sb.sb_agblocks;
+ if (nb < mp->m_sb.sb_dblocks)
+ return -EINVAL;
+ }
+ new = nb - mp->m_sb.sb_dblocks;
+ oagcount = mp->m_sb.sb_agcount;
+
+ /* allocate the new per-ag structures */
+ if (nagcount > oagcount) {
+ error = xfs_initialize_perag(mp, nagcount, &nagimax);
+ if (error)
+ return error;
+ }
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
+ XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
+ if (error)
+ return error;
+
+ /*
+ * Write new AG headers to disk. Non-transactional, but need to be
+ * written and completed prior to the growfs transaction being logged.
+ * To do this, we use a delayed write buffer list and wait for
+ * submission and IO completion of the list as a whole. This allows the
+ * IO subsystem to merge all the AG headers in a single AG into a single
+ * IO and hide most of the latency of the IO from us.
+ *
+ * This also means that if we get an error whilst building the buffer
+ * list to write, we can cancel the entire list without having written
+ * anything.
+ */
+ INIT_LIST_HEAD(&id.buffer_list);
+ for (id.agno = nagcount - 1;
+ id.agno >= oagcount;
+ id.agno--, new -= id.agsize) {
+
+ if (id.agno == nagcount - 1)
+ id.agsize = nb -
+ (id.agno * (xfs_rfsblock_t)mp->m_sb.sb_agblocks);
+ else
+ id.agsize = mp->m_sb.sb_agblocks;
+
+ error = xfs_ag_init_headers(mp, &id);
+ if (error) {
+ xfs_buf_delwri_cancel(&id.buffer_list);
+ goto out_trans_cancel;
+ }
+ }
+ error = xfs_buf_delwri_submit(&id.buffer_list);
+ if (error)
+ goto out_trans_cancel;
+
+ xfs_trans_agblocks_delta(tp, id.nfree);
+
+ /* If there are new blocks in the old last AG, extend it. */
+ if (new) {
+ error = xfs_ag_extend_space(mp, tp, &id, new);
+ if (error)
+ goto out_trans_cancel;
+ }
+
+ /*
+ * Update changed superblock fields transactionally. These are not
+ * seen by the rest of the world until the transaction commit applies
+ * them atomically to the superblock.
+ */
+ if (nagcount > oagcount)
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_AGCOUNT, nagcount - oagcount);
+ if (nb > mp->m_sb.sb_dblocks)
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS,
+ nb - mp->m_sb.sb_dblocks);
+ if (id.nfree)
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, id.nfree);
+ xfs_trans_set_sync(tp);
+ error = xfs_trans_commit(tp);
+ if (error)
+ return error;
+
+ /* New allocation groups fully initialized, so update mount struct */
+ if (nagimax)
+ mp->m_maxagi = nagimax;
+ xfs_set_low_space_thresholds(mp);
+ mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
+
+ /*
+ * If we expanded the last AG, free the per-AG reservation
+ * so we can reinitialize it with the new size.
+ */
+ if (new) {
+ struct xfs_perag *pag;
+
+ pag = xfs_perag_get(mp, id.agno);
+ error = xfs_ag_resv_free(pag);
+ xfs_perag_put(pag);
+ if (error)
+ return error;
+ }
+
+ /*
+ * Reserve AG metadata blocks. ENOSPC here does not mean there was a
+ * growfs failure, just that there still isn't space for new user data
+ * after the grow has been run.
+ */
+ error = xfs_fs_reserve_ag_blocks(mp);
+ if (error == -ENOSPC)
+ error = 0;
+ return error;
+
+out_trans_cancel:
+ xfs_trans_cancel(tp);
+ return error;
+}
+
+static int
+xfs_growfs_log_private(
+ xfs_mount_t *mp, /* mount point for filesystem */
+ xfs_growfs_log_t *in) /* growfs log input struct */
+{
+ xfs_extlen_t nb;
+
+ nb = in->newblocks;
+ if (nb < XFS_MIN_LOG_BLOCKS || nb < XFS_B_TO_FSB(mp, XFS_MIN_LOG_BYTES))
+ return -EINVAL;
+ if (nb == mp->m_sb.sb_logblocks &&
+ in->isint == (mp->m_sb.sb_logstart != 0))
+ return -EINVAL;
+ /*
+ * Moving the log is hard, need new interfaces to sync
+ * the log first, hold off all activity while moving it.
+ * Can have shorter or longer log in the same space,
+ * or transform internal to external log or vice versa.
+ */
+ return -ENOSYS;
+}
+
+static int
+xfs_growfs_imaxpct(
+ struct xfs_mount *mp,
+ __u32 imaxpct)
+{
+ struct xfs_trans *tp;
+ int dpct;
+ int error;
+
+ if (imaxpct > 100)
+ return -EINVAL;
+
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
+ XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
+ if (error)
+ return error;
+
+ dpct = imaxpct - mp->m_sb.sb_imax_pct;
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct);
+ xfs_trans_set_sync(tp);
+ return xfs_trans_commit(tp);
+}
+
+/*
+ * protected versions of growfs function acquire and release locks on the mount
+ * point - exported through ioctls: XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG,
+ * XFS_IOC_FSGROWFSRT
+ */
+int
+xfs_growfs_data(
+ struct xfs_mount *mp,
+ struct xfs_growfs_data *in)
+{
+ int error = 0;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ if (!mutex_trylock(&mp->m_growlock))
+ return -EWOULDBLOCK;
+
+ /* update imaxpct separately to the physical grow of the filesystem */
+ if (in->imaxpct != mp->m_sb.sb_imax_pct) {
+ error = xfs_growfs_imaxpct(mp, in->imaxpct);
+ if (error)
+ goto out_error;
+ }
+
+ if (in->newblocks != mp->m_sb.sb_dblocks) {
+ error = xfs_growfs_data_private(mp, in);
+ if (error)
+ goto out_error;
+ }
+
+ /* Post growfs calculations needed to reflect new state in operations */
+ if (mp->m_sb.sb_imax_pct) {
+ uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct;
+ do_div(icount, 100);
+ mp->m_maxicount = icount << mp->m_sb.sb_inopblog;
+ } else
+ mp->m_maxicount = 0;
+
+ /* Update secondary superblocks now the physical grow has completed */
+ error = xfs_update_secondary_sbs(mp);
+
+out_error:
+ /*
+ * Increment the generation unconditionally, the error could be from
+ * updating the secondary superblocks, in which case the new size
+ * is live already.
+ */
+ mp->m_generation++;
+ mutex_unlock(&mp->m_growlock);
+ return error;
+}
+
+int
+xfs_growfs_log(
+ xfs_mount_t *mp,
+ xfs_growfs_log_t *in)
+{
+ int error;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ if (!mutex_trylock(&mp->m_growlock))
+ return -EWOULDBLOCK;
+ error = xfs_growfs_log_private(mp, in);
+ mutex_unlock(&mp->m_growlock);
+ return error;
+}
+
+/*
+ * exported through ioctl XFS_IOC_FSCOUNTS
+ */
+
+int
+xfs_fs_counts(
+ xfs_mount_t *mp,
+ xfs_fsop_counts_t *cnt)
+{
+ cnt->allocino = percpu_counter_read_positive(&mp->m_icount);
+ cnt->freeino = percpu_counter_read_positive(&mp->m_ifree);
+ cnt->freedata = percpu_counter_read_positive(&mp->m_fdblocks) -
+ mp->m_alloc_set_aside;
+
+ spin_lock(&mp->m_sb_lock);
+ cnt->freertx = mp->m_sb.sb_frextents;
+ spin_unlock(&mp->m_sb_lock);
+ return 0;
+}
+
+/*
+ * exported through ioctl XFS_IOC_SET_RESBLKS & XFS_IOC_GET_RESBLKS
+ *
+ * xfs_reserve_blocks is called to set m_resblks
+ * in the in-core mount table. The number of unused reserved blocks
+ * is kept in m_resblks_avail.
+ *
+ * Reserve the requested number of blocks if available. Otherwise return
+ * as many as possible to satisfy the request. The actual number
+ * reserved are returned in outval
+ *
+ * A null inval pointer indicates that only the current reserved blocks
+ * available should be returned no settings are changed.
+ */
+
+int
+xfs_reserve_blocks(
+ xfs_mount_t *mp,
+ uint64_t *inval,
+ xfs_fsop_resblks_t *outval)
+{
+ int64_t lcounter, delta;
+ int64_t fdblks_delta = 0;
+ uint64_t request;
+ int64_t free;
+ int error = 0;
+
+ /* If inval is null, report current values and return */
+ if (inval == (uint64_t *)NULL) {
+ if (!outval)
+ return -EINVAL;
+ outval->resblks = mp->m_resblks;
+ outval->resblks_avail = mp->m_resblks_avail;
+ return 0;
+ }
+
+ request = *inval;
+
+ /*
+ * With per-cpu counters, this becomes an interesting problem. we need
+ * to work out if we are freeing or allocation blocks first, then we can
+ * do the modification as necessary.
+ *
+ * We do this under the m_sb_lock so that if we are near ENOSPC, we will
+ * hold out any changes while we work out what to do. This means that
+ * the amount of free space can change while we do this, so we need to
+ * retry if we end up trying to reserve more space than is available.
+ */
+ spin_lock(&mp->m_sb_lock);
+
+ /*
+ * If our previous reservation was larger than the current value,
+ * then move any unused blocks back to the free pool. Modify the resblks
+ * counters directly since we shouldn't have any problems unreserving
+ * space.
+ */
+ if (mp->m_resblks > request) {
+ lcounter = mp->m_resblks_avail - request;
+ if (lcounter > 0) { /* release unused blocks */
+ fdblks_delta = lcounter;
+ mp->m_resblks_avail -= lcounter;
+ }
+ mp->m_resblks = request;
+ if (fdblks_delta) {
+ spin_unlock(&mp->m_sb_lock);
+ error = xfs_mod_fdblocks(mp, fdblks_delta, 0);
+ spin_lock(&mp->m_sb_lock);
+ }
+
+ goto out;
+ }
+
+ /*
+ * If the request is larger than the current reservation, reserve the
+ * blocks before we update the reserve counters. Sample m_fdblocks and
+ * perform a partial reservation if the request exceeds free space.
+ */
+ error = -ENOSPC;
+ do {
+ free = percpu_counter_sum(&mp->m_fdblocks) -
+ mp->m_alloc_set_aside;
+ if (free <= 0)
+ break;
+
+ delta = request - mp->m_resblks;
+ lcounter = free - delta;
+ if (lcounter < 0)
+ /* We can't satisfy the request, just get what we can */
+ fdblks_delta = free;
+ else
+ fdblks_delta = delta;
+
+ /*
+ * We'll either succeed in getting space from the free block
+ * count or we'll get an ENOSPC. If we get a ENOSPC, it means
+ * things changed while we were calculating fdblks_delta and so
+ * we should try again to see if there is anything left to
+ * reserve.
+ *
+ * Don't set the reserved flag here - we don't want to reserve
+ * the extra reserve blocks from the reserve.....
+ */
+ spin_unlock(&mp->m_sb_lock);
+ error = xfs_mod_fdblocks(mp, -fdblks_delta, 0);
+ spin_lock(&mp->m_sb_lock);
+ } while (error == -ENOSPC);
+
+ /*
+ * Update the reserve counters if blocks have been successfully
+ * allocated.
+ */
+ if (!error && fdblks_delta) {
+ mp->m_resblks += fdblks_delta;
+ mp->m_resblks_avail += fdblks_delta;
+ }
+
+out:
+ if (outval) {
+ outval->resblks = mp->m_resblks;
+ outval->resblks_avail = mp->m_resblks_avail;
+ }
+
+ spin_unlock(&mp->m_sb_lock);
+ return error;
+}
+
+int
+xfs_fs_goingdown(
+ xfs_mount_t *mp,
+ uint32_t inflags)
+{
+ switch (inflags) {
+ case XFS_FSOP_GOING_FLAGS_DEFAULT: {
+ struct super_block *sb = freeze_bdev(mp->m_super->s_bdev);
+
+ if (sb && !IS_ERR(sb)) {
+ xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
+ thaw_bdev(sb->s_bdev, sb);
+ }
+
+ break;
+ }
+ case XFS_FSOP_GOING_FLAGS_LOGFLUSH:
+ xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
+ break;
+ case XFS_FSOP_GOING_FLAGS_NOLOGFLUSH:
+ xfs_force_shutdown(mp,
+ SHUTDOWN_FORCE_UMOUNT | SHUTDOWN_LOG_IO_ERROR);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/*
+ * Force a shutdown of the filesystem instantly while keeping the filesystem
+ * consistent. We don't do an unmount here; just shutdown the shop, make sure
+ * that absolutely nothing persistent happens to this filesystem after this
+ * point.
+ */
+void
+xfs_do_force_shutdown(
+ xfs_mount_t *mp,
+ int flags,
+ char *fname,
+ int lnnum)
+{
+ int logerror;
+
+ logerror = flags & SHUTDOWN_LOG_IO_ERROR;
+
+ if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
+ xfs_notice(mp,
+ "%s(0x%x) called from line %d of file %s. Return address = "PTR_FMT,
+ __func__, flags, lnnum, fname, __return_address);
+ }
+ /*
+ * No need to duplicate efforts.
+ */
+ if (XFS_FORCED_SHUTDOWN(mp) && !logerror)
+ return;
+
+ /*
+ * This flags XFS_MOUNT_FS_SHUTDOWN, makes sure that we don't
+ * queue up anybody new on the log reservations, and wakes up
+ * everybody who's sleeping on log reservations to tell them
+ * the bad news.
+ */
+ if (xfs_log_force_umount(mp, logerror))
+ return;
+
+ if (flags & SHUTDOWN_CORRUPT_INCORE) {
+ xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT,
+ "Corruption of in-memory data detected. Shutting down filesystem");
+ if (XFS_ERRLEVEL_HIGH <= xfs_error_level)
+ xfs_stack_trace();
+ } else if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
+ if (logerror) {
+ xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_LOGERROR,
+ "Log I/O Error Detected. Shutting down filesystem");
+ } else if (flags & SHUTDOWN_DEVICE_REQ) {
+ xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR,
+ "All device paths lost. Shutting down filesystem");
+ } else if (!(flags & SHUTDOWN_REMOTE_REQ)) {
+ xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR,
+ "I/O Error Detected. Shutting down filesystem");
+ }
+ }
+ if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
+ xfs_alert(mp,
+ "Please umount the filesystem and rectify the problem(s)");
+ }
+}
+
+/*
+ * Reserve free space for per-AG metadata.
+ */
+int
+xfs_fs_reserve_ag_blocks(
+ struct xfs_mount *mp)
+{
+ xfs_agnumber_t agno;
+ struct xfs_perag *pag;
+ int error = 0;
+ int err2;
+
+ mp->m_finobt_nores = false;
+ for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
+ pag = xfs_perag_get(mp, agno);
+ err2 = xfs_ag_resv_init(pag, NULL);
+ xfs_perag_put(pag);
+ if (err2 && !error)
+ error = err2;
+ }
+
+ if (error && error != -ENOSPC) {
+ xfs_warn(mp,
+ "Error %d reserving per-AG metadata reserve pool.", error);
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ }
+
+ return error;
+}
+
+/*
+ * Free space reserved for per-AG metadata.
+ */
+int
+xfs_fs_unreserve_ag_blocks(
+ struct xfs_mount *mp)
+{
+ xfs_agnumber_t agno;
+ struct xfs_perag *pag;
+ int error = 0;
+ int err2;
+
+ for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
+ pag = xfs_perag_get(mp, agno);
+ err2 = xfs_ag_resv_free(pag);
+ xfs_perag_put(pag);
+ if (err2 && !error)
+ error = err2;
+ }
+
+ if (error)
+ xfs_warn(mp,
+ "Error %d freeing per-AG metadata reserve pool.", error);
+
+ return error;
+}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-11 14:20:32 +0000