aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_rtalloc.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/xfs_rtalloc.c')
-rw-r--r--fs/xfs/xfs_rtalloc.c1025
1 files changed, 814 insertions, 211 deletions
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 3a2005a1e673..0cb534d71119 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -25,6 +25,11 @@
#include "xfs_quota.h"
#include "xfs_log_priv.h"
#include "xfs_health.h"
+#include "xfs_da_format.h"
+#include "xfs_metafile.h"
+#include "xfs_rtgroup.h"
+#include "xfs_error.h"
+#include "xfs_trace.h"
/*
* Return whether there are any free extents in the size range given
@@ -38,14 +43,14 @@ xfs_rtany_summary(
xfs_fileoff_t bbno, /* bitmap block number */
int *maxlog) /* out: max log2 extent size free */
{
- struct xfs_mount *mp = args->mp;
+ uint8_t *rsum_cache = args->rtg->rtg_rsum_cache;
int error;
int log; /* loop counter, log2 of ext. size */
xfs_suminfo_t sum; /* summary data */
- /* There are no extents at levels >= m_rsum_cache[bbno]. */
- if (mp->m_rsum_cache) {
- high = min(high, mp->m_rsum_cache[bbno] - 1);
+ /* There are no extents at levels >= rsum_cache[bbno]. */
+ if (rsum_cache) {
+ high = min(high, rsum_cache[bbno] - 1);
if (low > high) {
*maxlog = -1;
return 0;
@@ -77,12 +82,11 @@ xfs_rtany_summary(
*maxlog = -1;
out:
/* There were no extents at levels > log. */
- if (mp->m_rsum_cache && log + 1 < mp->m_rsum_cache[bbno])
- mp->m_rsum_cache[bbno] = log + 1;
+ if (rsum_cache && log + 1 < rsum_cache[bbno])
+ rsum_cache[bbno] = log + 1;
return 0;
}
-
/*
* Copy and transform the summary file, given the old and new
* parameters in the mount structures.
@@ -149,7 +153,7 @@ xfs_rtallocate_range(
/*
* Find the next allocated block (end of free extent).
*/
- error = xfs_rtfind_forw(args, end, mp->m_sb.sb_rextents - 1,
+ error = xfs_rtfind_forw(args, end, args->rtg->rtg_extents - 1,
&postblock);
if (error)
return error;
@@ -211,14 +215,14 @@ xfs_rtalloc_align_len(
*/
static inline xfs_rtxlen_t
xfs_rtallocate_clamp_len(
- struct xfs_mount *mp,
+ struct xfs_rtgroup *rtg,
xfs_rtxnum_t startrtx,
xfs_rtxlen_t rtxlen,
xfs_rtxlen_t prod)
{
xfs_rtxlen_t ret;
- ret = min(mp->m_sb.sb_rextents, startrtx + rtxlen) - startrtx;
+ ret = min(rtg->rtg_extents, startrtx + rtxlen) - startrtx;
return xfs_rtalloc_align_len(ret, prod);
}
@@ -253,10 +257,11 @@ xfs_rtallocate_extent_block(
* Loop over all the extents starting in this bitmap block up to the
* end of the rt volume, looking for one that's long enough.
*/
- end = min(mp->m_sb.sb_rextents, xfs_rbmblock_to_rtx(mp, bbno + 1)) - 1;
+ end = min(args->rtg->rtg_extents, xfs_rbmblock_to_rtx(mp, bbno + 1)) -
+ 1;
for (i = xfs_rbmblock_to_rtx(mp, bbno); i <= end; i++) {
/* Make sure we don't scan off the end of the rt volume. */
- scanlen = xfs_rtallocate_clamp_len(mp, i, maxlen, prod);
+ scanlen = xfs_rtallocate_clamp_len(args->rtg, i, maxlen, prod);
if (scanlen < minlen)
break;
@@ -341,7 +346,6 @@ xfs_rtallocate_extent_exact(
xfs_rtxlen_t prod, /* extent product factor */
xfs_rtxnum_t *rtx) /* out: start rtext allocated */
{
- struct xfs_mount *mp = args->mp;
xfs_rtxnum_t next; /* next rtext to try (dummy) */
xfs_rtxlen_t alloclen; /* candidate length */
xfs_rtxlen_t scanlen; /* number of free rtx to look for */
@@ -352,7 +356,7 @@ xfs_rtallocate_extent_exact(
ASSERT(maxlen % prod == 0);
/* Make sure we don't run off the end of the rt volume. */
- scanlen = xfs_rtallocate_clamp_len(mp, start, maxlen, prod);
+ scanlen = xfs_rtallocate_clamp_len(args->rtg, start, maxlen, prod);
if (scanlen < minlen)
return -ENOSPC;
@@ -413,11 +417,10 @@ xfs_rtallocate_extent_near(
ASSERT(maxlen % prod == 0);
/*
- * If the block number given is off the end, silently set it to
- * the last block.
+ * If the block number given is off the end, silently set it to the last
+ * block.
*/
- if (start >= mp->m_sb.sb_rextents)
- start = mp->m_sb.sb_rextents - 1;
+ start = min(start, args->rtg->rtg_extents - 1);
/*
* Try the exact allocation first.
@@ -649,19 +652,30 @@ xfs_rtallocate_extent_size(
return -ENOSPC;
}
+static void
+xfs_rtunmount_rtg(
+ struct xfs_rtgroup *rtg)
+{
+ int i;
+
+ for (i = 0; i < XFS_RTGI_MAX; i++)
+ xfs_rtginode_irele(&rtg->rtg_inodes[i]);
+ kvfree(rtg->rtg_rsum_cache);
+}
+
static int
xfs_alloc_rsum_cache(
- struct xfs_mount *mp,
+ struct xfs_rtgroup *rtg,
xfs_extlen_t rbmblocks)
{
/*
* The rsum cache is initialized to the maximum value, which is
* trivially an upper bound on the maximum level with any free extents.
*/
- mp->m_rsum_cache = kvmalloc(rbmblocks, GFP_KERNEL);
- if (!mp->m_rsum_cache)
+ rtg->rtg_rsum_cache = kvmalloc(rbmblocks, GFP_KERNEL);
+ if (!rtg->rtg_rsum_cache)
return -ENOMEM;
- memset(mp->m_rsum_cache, -1, rbmblocks);
+ memset(rtg->rtg_rsum_cache, -1, rbmblocks);
return 0;
}
@@ -698,44 +712,175 @@ out_iolock:
return error;
}
+/* Ensure that the rtgroup metadata inode is loaded, creating it if neeeded. */
+static int
+xfs_rtginode_ensure(
+ struct xfs_rtgroup *rtg,
+ enum xfs_rtg_inodes type)
+{
+ struct xfs_trans *tp;
+ int error;
+
+ if (rtg->rtg_inodes[type])
+ return 0;
+
+ error = xfs_trans_alloc_empty(rtg_mount(rtg), &tp);
+ if (error)
+ return error;
+ error = xfs_rtginode_load(rtg, type, tp);
+ xfs_trans_cancel(tp);
+
+ if (error != -ENOENT)
+ return 0;
+ return xfs_rtginode_create(rtg, type, true);
+}
+
+static struct xfs_mount *
+xfs_growfs_rt_alloc_fake_mount(
+ const struct xfs_mount *mp,
+ xfs_rfsblock_t rblocks,
+ xfs_agblock_t rextsize)
+{
+ struct xfs_mount *nmp;
+
+ nmp = kmemdup(mp, sizeof(*mp), GFP_KERNEL);
+ if (!nmp)
+ return NULL;
+ xfs_mount_sb_set_rextsize(nmp, &nmp->m_sb, rextsize);
+ nmp->m_sb.sb_rblocks = rblocks;
+ nmp->m_sb.sb_rextents = xfs_blen_to_rtbxlen(nmp, nmp->m_sb.sb_rblocks);
+ nmp->m_sb.sb_rbmblocks = xfs_rtbitmap_blockcount(nmp);
+ nmp->m_sb.sb_rextslog = xfs_compute_rextslog(nmp->m_sb.sb_rextents);
+ if (xfs_has_rtgroups(nmp))
+ nmp->m_sb.sb_rgcount = howmany_64(nmp->m_sb.sb_rextents,
+ nmp->m_sb.sb_rgextents);
+ else
+ nmp->m_sb.sb_rgcount = 1;
+ nmp->m_rsumblocks = xfs_rtsummary_blockcount(nmp, &nmp->m_rsumlevels);
+
+ if (rblocks > 0)
+ nmp->m_features |= XFS_FEAT_REALTIME;
+
+ /* recompute growfsrt reservation from new rsumsize */
+ xfs_trans_resv_calc(nmp, &nmp->m_resv);
+ return nmp;
+}
+
+/* Free all the new space and return the number of extents actually freed. */
+static int
+xfs_growfs_rt_free_new(
+ struct xfs_rtgroup *rtg,
+ struct xfs_rtalloc_args *nargs,
+ xfs_rtbxlen_t *freed_rtx)
+{
+ struct xfs_mount *mp = rtg_mount(rtg);
+ xfs_rgnumber_t rgno = rtg_rgno(rtg);
+ xfs_rtxnum_t start_rtx = 0, end_rtx;
+
+ if (rgno < mp->m_sb.sb_rgcount)
+ start_rtx = xfs_rtgroup_extents(mp, rgno);
+ end_rtx = xfs_rtgroup_extents(nargs->mp, rgno);
+
+ /*
+ * Compute the first new extent that we want to free, being careful to
+ * skip past a realtime superblock at the start of the realtime volume.
+ */
+ if (xfs_has_rtsb(nargs->mp) && rgno == 0 && start_rtx == 0)
+ start_rtx++;
+ *freed_rtx = end_rtx - start_rtx;
+ return xfs_rtfree_range(nargs, start_rtx, *freed_rtx);
+}
+
+static xfs_rfsblock_t
+xfs_growfs_rt_nrblocks(
+ struct xfs_rtgroup *rtg,
+ xfs_rfsblock_t nrblocks,
+ xfs_agblock_t rextsize,
+ xfs_fileoff_t bmbno)
+{
+ struct xfs_mount *mp = rtg_mount(rtg);
+ xfs_rfsblock_t step;
+
+ step = (bmbno + 1) * mp->m_rtx_per_rbmblock * rextsize;
+ if (xfs_has_rtgroups(mp)) {
+ xfs_rfsblock_t rgblocks = mp->m_sb.sb_rgextents * rextsize;
+
+ step = min(rgblocks, step) + rgblocks * rtg_rgno(rtg);
+ }
+
+ return min(nrblocks, step);
+}
+
+/*
+ * If the post-grow filesystem will have an rtsb; we're initializing the first
+ * rtgroup; and the filesystem didn't have a realtime section, write the rtsb
+ * now, and attach the rtsb buffer to the real mount.
+ */
+static int
+xfs_growfs_rt_init_rtsb(
+ const struct xfs_rtalloc_args *nargs,
+ const struct xfs_rtgroup *rtg,
+ const struct xfs_rtalloc_args *args)
+{
+ struct xfs_mount *mp = args->mp;
+ struct xfs_buf *rtsb_bp;
+ int error;
+
+ if (!xfs_has_rtsb(nargs->mp))
+ return 0;
+ if (rtg_rgno(rtg) > 0)
+ return 0;
+ if (mp->m_sb.sb_rblocks)
+ return 0;
+
+ error = xfs_buf_get_uncached(mp->m_rtdev_targp, XFS_FSB_TO_BB(mp, 1),
+ 0, &rtsb_bp);
+ if (error)
+ return error;
+
+ rtsb_bp->b_maps[0].bm_bn = XFS_RTSB_DADDR;
+ rtsb_bp->b_ops = &xfs_rtsb_buf_ops;
+
+ xfs_update_rtsb(rtsb_bp, mp->m_sb_bp);
+ mp->m_rtsb_bp = rtsb_bp;
+ error = xfs_bwrite(rtsb_bp);
+ xfs_buf_unlock(rtsb_bp);
+ return error;
+}
+
static int
xfs_growfs_rt_bmblock(
- struct xfs_mount *mp,
+ struct xfs_rtgroup *rtg,
xfs_rfsblock_t nrblocks,
xfs_agblock_t rextsize,
xfs_fileoff_t bmbno)
{
- struct xfs_inode *rbmip = mp->m_rbmip;
- struct xfs_inode *rsumip = mp->m_rsumip;
+ struct xfs_mount *mp = rtg_mount(rtg);
+ struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
+ struct xfs_inode *rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY];
struct xfs_rtalloc_args args = {
.mp = mp,
+ .rtg = rtg,
};
struct xfs_rtalloc_args nargs = {
+ .rtg = rtg,
};
struct xfs_mount *nmp;
- xfs_rfsblock_t nrblocks_step;
xfs_rtbxlen_t freed_rtx;
int error;
-
- nrblocks_step = (bmbno + 1) * NBBY * mp->m_sb.sb_blocksize * rextsize;
-
- nmp = nargs.mp = kmemdup(mp, sizeof(*mp), GFP_KERNEL);
+ /*
+ * Calculate new sb and mount fields for this round. Also ensure the
+ * rtg_extents value is uptodate as the rtbitmap code relies on it.
+ */
+ nmp = nargs.mp = xfs_growfs_rt_alloc_fake_mount(mp,
+ xfs_growfs_rt_nrblocks(rtg, nrblocks, rextsize, bmbno),
+ rextsize);
if (!nmp)
return -ENOMEM;
- /*
- * Calculate new sb and mount fields for this round.
- */
- nmp->m_sb.sb_rextsize = rextsize;
- xfs_mount_sb_set_rextsize(nmp, &nmp->m_sb);
- nmp->m_sb.sb_rbmblocks = bmbno + 1;
- nmp->m_sb.sb_rblocks = min(nrblocks, nrblocks_step);
- nmp->m_sb.sb_rextents = xfs_rtb_to_rtx(nmp, nmp->m_sb.sb_rblocks);
- nmp->m_sb.sb_rextslog = xfs_compute_rextslog(nmp->m_sb.sb_rextents);
- nmp->m_rsumlevels = nmp->m_sb.sb_rextslog + 1;
- nmp->m_rsumblocks = xfs_rtsummary_blockcount(mp, nmp->m_rsumlevels,
- nmp->m_sb.sb_rbmblocks);
+ xfs_rtgroup_calc_geometry(nmp, rtg, rtg_rgno(rtg),
+ nmp->m_sb.sb_rgcount, nmp->m_sb.sb_rextents);
/*
* Recompute the growfsrt reservation from the new rsumsize, so that the
@@ -748,8 +893,8 @@ xfs_growfs_rt_bmblock(
goto out_free;
nargs.tp = args.tp;
- xfs_rtbitmap_lock(mp);
- xfs_rtbitmap_trans_join(args.tp);
+ xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP);
+ xfs_rtgroup_trans_join(args.tp, args.rtg, XFS_RTGLOCK_BITMAP);
/*
* Update the bitmap inode's size ondisk and incore. We need to update
@@ -780,6 +925,10 @@ xfs_growfs_rt_bmblock(
goto out_cancel;
}
+ error = xfs_growfs_rt_init_rtsb(&nargs, rtg, &args);
+ if (error)
+ goto out_cancel;
+
/*
* Update superblock fields.
*/
@@ -798,12 +947,14 @@ xfs_growfs_rt_bmblock(
if (nmp->m_sb.sb_rextslog != mp->m_sb.sb_rextslog)
xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_REXTSLOG,
nmp->m_sb.sb_rextslog - mp->m_sb.sb_rextslog);
+ if (nmp->m_sb.sb_rgcount != mp->m_sb.sb_rgcount)
+ xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_RGCOUNT,
+ nmp->m_sb.sb_rgcount - mp->m_sb.sb_rgcount);
/*
* Free the new extent.
*/
- freed_rtx = nmp->m_sb.sb_rextents - mp->m_sb.sb_rextents;
- error = xfs_rtfree_range(&nargs, mp->m_sb.sb_rextents, freed_rtx);
+ error = xfs_growfs_rt_free_new(rtg, &nargs, &freed_rtx);
xfs_rtbuf_cache_relse(&nargs);
if (error)
goto out_cancel;
@@ -818,7 +969,6 @@ xfs_growfs_rt_bmblock(
*/
mp->m_rsumlevels = nmp->m_rsumlevels;
mp->m_rsumblocks = nmp->m_rsumblocks;
- xfs_mount_sb_set_rextsize(mp, &mp->m_sb);
/*
* Recompute the growfsrt reservation from the new rsumsize.
@@ -844,6 +994,15 @@ out_free:
return error;
}
+static xfs_rtxnum_t
+xfs_last_rtgroup_extents(
+ struct xfs_mount *mp)
+{
+ return mp->m_sb.sb_rextents -
+ ((xfs_rtxnum_t)(mp->m_sb.sb_rgcount - 1) *
+ mp->m_sb.sb_rgextents);
+}
+
/*
* Calculate the last rbmblock currently used.
*
@@ -851,34 +1010,235 @@ out_free:
*/
static xfs_fileoff_t
xfs_last_rt_bmblock(
- struct xfs_mount *mp)
+ struct xfs_rtgroup *rtg)
{
- xfs_fileoff_t bmbno = mp->m_sb.sb_rbmblocks;
+ struct xfs_mount *mp = rtg_mount(rtg);
+ xfs_rgnumber_t rgno = rtg_rgno(rtg);
+ xfs_fileoff_t bmbno = 0;
+
+ ASSERT(!mp->m_sb.sb_rgcount || rgno >= mp->m_sb.sb_rgcount - 1);
+
+ if (mp->m_sb.sb_rgcount && rgno == mp->m_sb.sb_rgcount - 1) {
+ xfs_rtxnum_t nrext = xfs_last_rtgroup_extents(mp);
+
+ /* Also fill up the previous block if not entirely full. */
+ bmbno = xfs_rtbitmap_blockcount_len(mp, nrext);
+ if (xfs_rtx_to_rbmword(mp, nrext) != 0)
+ bmbno--;
+ }
- /* Skip the current block if it is exactly full. */
- if (xfs_rtx_to_rbmword(mp, mp->m_sb.sb_rextents) != 0)
- bmbno--;
return bmbno;
}
/*
+ * Allocate space to the bitmap and summary files, as necessary.
+ */
+static int
+xfs_growfs_rt_alloc_blocks(
+ struct xfs_rtgroup *rtg,
+ xfs_rfsblock_t nrblocks,
+ xfs_agblock_t rextsize,
+ xfs_extlen_t *nrbmblocks)
+{
+ struct xfs_mount *mp = rtg_mount(rtg);
+ struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
+ struct xfs_inode *rsumip = rtg->rtg_inodes[XFS_RTGI_SUMMARY];
+ xfs_extlen_t orbmblocks = 0;
+ xfs_extlen_t orsumblocks = 0;
+ struct xfs_mount *nmp;
+ int error = 0;
+
+ nmp = xfs_growfs_rt_alloc_fake_mount(mp, nrblocks, rextsize);
+ if (!nmp)
+ return -ENOMEM;
+ *nrbmblocks = nmp->m_sb.sb_rbmblocks;
+
+ if (xfs_has_rtgroups(mp)) {
+ /*
+ * For file systems with the rtgroups feature, the RT bitmap and
+ * summary are always fully allocated, which means that we never
+ * need to grow the existing files.
+ *
+ * But we have to be careful to only fill the bitmap until the
+ * end of the actually used range.
+ */
+ if (rtg_rgno(rtg) == nmp->m_sb.sb_rgcount - 1)
+ *nrbmblocks = xfs_rtbitmap_blockcount_len(nmp,
+ xfs_last_rtgroup_extents(nmp));
+
+ if (mp->m_sb.sb_rgcount &&
+ rtg_rgno(rtg) == mp->m_sb.sb_rgcount - 1)
+ goto out_free;
+ } else {
+ /*
+ * Get the old block counts for bitmap and summary inodes.
+ * These can't change since other growfs callers are locked out.
+ */
+ orbmblocks = XFS_B_TO_FSB(mp, rbmip->i_disk_size);
+ orsumblocks = XFS_B_TO_FSB(mp, rsumip->i_disk_size);
+ }
+
+ error = xfs_rtfile_initialize_blocks(rtg, XFS_RTGI_BITMAP, orbmblocks,
+ nmp->m_sb.sb_rbmblocks, NULL);
+ if (error)
+ goto out_free;
+ error = xfs_rtfile_initialize_blocks(rtg, XFS_RTGI_SUMMARY, orsumblocks,
+ nmp->m_rsumblocks, NULL);
+out_free:
+ kfree(nmp);
+ return error;
+}
+
+static int
+xfs_growfs_rtg(
+ struct xfs_mount *mp,
+ xfs_rgnumber_t rgno,
+ xfs_rfsblock_t nrblocks,
+ xfs_agblock_t rextsize)
+{
+ uint8_t *old_rsum_cache = NULL;
+ xfs_extlen_t bmblocks;
+ xfs_fileoff_t bmbno;
+ struct xfs_rtgroup *rtg;
+ unsigned int i;
+ int error;
+
+ rtg = xfs_rtgroup_grab(mp, rgno);
+ if (!rtg)
+ return -EINVAL;
+
+ for (i = 0; i < XFS_RTGI_MAX; i++) {
+ error = xfs_rtginode_ensure(rtg, i);
+ if (error)
+ goto out_rele;
+ }
+
+ error = xfs_growfs_rt_alloc_blocks(rtg, nrblocks, rextsize, &bmblocks);
+ if (error)
+ goto out_rele;
+
+ if (bmblocks != rtg_mount(rtg)->m_sb.sb_rbmblocks) {
+ old_rsum_cache = rtg->rtg_rsum_cache;
+ error = xfs_alloc_rsum_cache(rtg, bmblocks);
+ if (error)
+ goto out_rele;
+ }
+
+ for (bmbno = xfs_last_rt_bmblock(rtg); bmbno < bmblocks; bmbno++) {
+ error = xfs_growfs_rt_bmblock(rtg, nrblocks, rextsize, bmbno);
+ if (error)
+ goto out_error;
+ }
+
+ if (old_rsum_cache)
+ kvfree(old_rsum_cache);
+ xfs_rtgroup_rele(rtg);
+ return 0;
+
+out_error:
+ /*
+ * Reset rtg_extents to the old value if adding more blocks failed.
+ */
+ xfs_rtgroup_calc_geometry(mp, rtg, rtg_rgno(rtg), mp->m_sb.sb_rgcount,
+ mp->m_sb.sb_rextents);
+ if (old_rsum_cache) {
+ kvfree(rtg->rtg_rsum_cache);
+ rtg->rtg_rsum_cache = old_rsum_cache;
+ }
+out_rele:
+ xfs_rtgroup_rele(rtg);
+ return error;
+}
+
+static int
+xfs_growfs_check_rtgeom(
+ const struct xfs_mount *mp,
+ xfs_rfsblock_t rblocks,
+ xfs_extlen_t rextsize)
+{
+ struct xfs_mount *nmp;
+ int error = 0;
+
+ nmp = xfs_growfs_rt_alloc_fake_mount(mp, rblocks, rextsize);
+ if (!nmp)
+ return -ENOMEM;
+
+ /*
+ * New summary size can't be more than half the size of the log. This
+ * prevents us from getting a log overflow, since we'll log basically
+ * the whole summary file at once.
+ */
+ if (nmp->m_rsumblocks > (mp->m_sb.sb_logblocks >> 1))
+ error = -EINVAL;
+
+ kfree(nmp);
+ return error;
+}
+
+/*
+ * Compute the new number of rt groups and ensure that /rtgroups exists.
+ *
+ * Changing the rtgroup size is not allowed (even if the rt volume hasn't yet
+ * been initialized) because the userspace ABI doesn't support it.
+ */
+static int
+xfs_growfs_rt_prep_groups(
+ struct xfs_mount *mp,
+ xfs_rfsblock_t rblocks,
+ xfs_extlen_t rextsize,
+ xfs_rgnumber_t *new_rgcount)
+{
+ int error;
+
+ *new_rgcount = howmany_64(rblocks, mp->m_sb.sb_rgextents * rextsize);
+ if (*new_rgcount > XFS_MAX_RGNUMBER)
+ return -EINVAL;
+
+ /* Make sure the /rtgroups dir has been created */
+ if (!mp->m_rtdirip) {
+ struct xfs_trans *tp;
+
+ error = xfs_trans_alloc_empty(mp, &tp);
+ if (error)
+ return error;
+ error = xfs_rtginode_load_parent(tp);
+ xfs_trans_cancel(tp);
+
+ if (error == -ENOENT)
+ error = xfs_rtginode_mkdir_parent(mp);
+ if (error)
+ return error;
+ }
+
+ return 0;
+}
+
+static bool
+xfs_grow_last_rtg(
+ struct xfs_mount *mp)
+{
+ if (!xfs_has_rtgroups(mp))
+ return true;
+ if (mp->m_sb.sb_rgcount == 0)
+ return false;
+ return xfs_rtgroup_extents(mp, mp->m_sb.sb_rgcount - 1) <=
+ mp->m_sb.sb_rgextents;
+}
+
+/*
* Grow the realtime area of the filesystem.
*/
int
xfs_growfs_rt(
- xfs_mount_t *mp, /* mount point for filesystem */
- xfs_growfs_rt_t *in) /* growfs rt input struct */
+ struct xfs_mount *mp,
+ struct xfs_growfs_rt *in)
{
- xfs_fileoff_t bmbno; /* bitmap block number */
- struct xfs_buf *bp; /* temporary buffer */
- int error; /* error return value */
- xfs_extlen_t nrbmblocks; /* new number of rt bitmap blocks */
- xfs_rtxnum_t nrextents; /* new number of realtime extents */
- xfs_extlen_t nrsumblocks; /* new number of summary blocks */
- xfs_extlen_t rbmblocks; /* current number of rt bitmap blocks */
- xfs_extlen_t rsumblocks; /* current number of rt summary blks */
- uint8_t *rsum_cache; /* old summary cache */
- xfs_agblock_t old_rextsize = mp->m_sb.sb_rextsize;
+ xfs_rgnumber_t old_rgcount = mp->m_sb.sb_rgcount;
+ xfs_rgnumber_t new_rgcount = 1;
+ xfs_rgnumber_t rgno;
+ struct xfs_buf *bp;
+ xfs_agblock_t old_rextsize = mp->m_sb.sb_rextsize;
+ int error;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -889,15 +1249,9 @@ xfs_growfs_rt(
if (!mutex_trylock(&mp->m_growlock))
return -EWOULDBLOCK;
- /*
- * Mount should fail if the rt bitmap/summary files don't load, but
- * we'll check anyway.
- */
- error = -EINVAL;
- if (!mp->m_rbmip || !mp->m_rsumip)
- goto out_unlock;
/* Shrink not supported. */
+ error = -EINVAL;
if (in->newblocks <= mp->m_sb.sb_rblocks)
goto out_unlock;
/* Can only change rt extent size when adding rt volume. */
@@ -911,7 +1265,9 @@ xfs_growfs_rt(
/* Unsupported realtime features. */
error = -EOPNOTSUPP;
- if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp) || xfs_has_quota(mp))
+ if (xfs_has_quota(mp) && !xfs_has_rtgroups(mp))
+ goto out_unlock;
+ if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp))
goto out_unlock;
error = xfs_sb_validate_fsb_count(&mp->m_sb, in->newblocks);
@@ -930,80 +1286,64 @@ xfs_growfs_rt(
/*
* Calculate new parameters. These are the final values to be reached.
*/
- nrextents = div_u64(in->newblocks, in->extsize);
- if (nrextents == 0) {
- error = -EINVAL;
- goto out_unlock;
- }
- nrbmblocks = xfs_rtbitmap_blockcount(mp, nrextents);
- nrsumblocks = xfs_rtsummary_blockcount(mp,
- xfs_compute_rextslog(nrextents) + 1, nrbmblocks);
-
- /*
- * New summary size can't be more than half the size of
- * the log. This prevents us from getting a log overflow,
- * since we'll log basically the whole summary file at once.
- */
- if (nrsumblocks > (mp->m_sb.sb_logblocks >> 1)) {
- error = -EINVAL;
+ error = -EINVAL;
+ if (in->newblocks < in->extsize)
goto out_unlock;
- }
- /*
- * Get the old block counts for bitmap and summary inodes.
- * These can't change since other growfs callers are locked out.
- */
- rbmblocks = XFS_B_TO_FSB(mp, mp->m_rbmip->i_disk_size);
- rsumblocks = XFS_B_TO_FSB(mp, mp->m_rsumip->i_disk_size);
- /*
- * Allocate space to the bitmap and summary files, as necessary.
- */
- error = xfs_rtfile_initialize_blocks(mp->m_rbmip, rbmblocks,
- nrbmblocks, NULL);
- if (error)
- goto out_unlock;
- error = xfs_rtfile_initialize_blocks(mp->m_rsumip, rsumblocks,
- nrsumblocks, NULL);
+ /* Make sure the new fs size won't cause problems with the log. */
+ error = xfs_growfs_check_rtgeom(mp, in->newblocks, in->extsize);
if (error)
goto out_unlock;
- rsum_cache = mp->m_rsum_cache;
- if (nrbmblocks != mp->m_sb.sb_rbmblocks) {
- error = xfs_alloc_rsum_cache(mp, nrbmblocks);
+ if (xfs_has_rtgroups(mp)) {
+ error = xfs_growfs_rt_prep_groups(mp, in->newblocks,
+ in->extsize, &new_rgcount);
if (error)
goto out_unlock;
}
- /* Initialize the free space bitmap one bitmap block at a time. */
- for (bmbno = xfs_last_rt_bmblock(mp); bmbno < nrbmblocks; bmbno++) {
- error = xfs_growfs_rt_bmblock(mp, in->newblocks, in->extsize,
- bmbno);
+ if (xfs_grow_last_rtg(mp)) {
+ error = xfs_growfs_rtg(mp, old_rgcount - 1, in->newblocks,
+ in->extsize);
if (error)
- goto out_free;
+ goto out_unlock;
}
- if (old_rextsize != in->extsize) {
- error = xfs_growfs_rt_fixup_extsize(mp);
+ for (rgno = old_rgcount; rgno < new_rgcount; rgno++) {
+ xfs_rtbxlen_t rextents = div_u64(in->newblocks, in->extsize);
+
+ error = xfs_rtgroup_alloc(mp, rgno, new_rgcount, rextents);
if (error)
- goto out_free;
+ goto out_unlock;
+
+ error = xfs_growfs_rtg(mp, rgno, in->newblocks, in->extsize);
+ if (error) {
+ struct xfs_rtgroup *rtg;
+
+ rtg = xfs_rtgroup_grab(mp, rgno);
+ if (!WARN_ON_ONCE(!rtg)) {
+ xfs_rtunmount_rtg(rtg);
+ xfs_rtgroup_rele(rtg);
+ xfs_rtgroup_free(mp, rgno);
+ }
+ break;
+ }
}
- /* Update secondary superblocks now the physical grow has completed */
- error = xfs_update_secondary_sbs(mp);
+ if (!error && old_rextsize != in->extsize)
+ error = xfs_growfs_rt_fixup_extsize(mp);
-out_free:
/*
- * If we had to allocate a new rsum_cache, we either need to free the
- * old one (if we succeeded) or free the new one and restore the old one
- * (if there was an error).
+ * Update secondary superblocks now the physical grow has completed.
+ *
+ * Also do this in case of an error as we might have already
+ * successfully updated one or more RTGs and incremented sb_rgcount.
*/
- if (rsum_cache != mp->m_rsum_cache) {
- if (error) {
- kvfree(mp->m_rsum_cache);
- mp->m_rsum_cache = rsum_cache;
- } else {
- kvfree(rsum_cache);
- }
+ if (!xfs_is_shutdown(mp)) {
+ int error2 = xfs_update_secondary_sbs(mp);
+
+ if (!error)
+ error = error2;
}
out_unlock:
@@ -1011,6 +1351,56 @@ out_unlock:
return error;
}
+/* Read the realtime superblock and attach it to the mount. */
+int
+xfs_rtmount_readsb(
+ struct xfs_mount *mp)
+{
+ struct xfs_buf *bp;
+ int error;
+
+ if (!xfs_has_rtsb(mp))
+ return 0;
+ if (mp->m_sb.sb_rblocks == 0)
+ return 0;
+ if (mp->m_rtdev_targp == NULL) {
+ xfs_warn(mp,
+ "Filesystem has a realtime volume, use rtdev=device option");
+ return -ENODEV;
+ }
+
+ /* m_blkbb_log is not set up yet */
+ error = xfs_buf_read_uncached(mp->m_rtdev_targp, XFS_RTSB_DADDR,
+ mp->m_sb.sb_blocksize >> BBSHIFT, XBF_NO_IOACCT, &bp,
+ &xfs_rtsb_buf_ops);
+ if (error) {
+ xfs_warn(mp, "rt sb validate failed with error %d.", error);
+ /* bad CRC means corrupted metadata */
+ if (error == -EFSBADCRC)
+ error = -EFSCORRUPTED;
+ return error;
+ }
+
+ mp->m_rtsb_bp = bp;
+ xfs_buf_unlock(bp);
+ return 0;
+}
+
+/* Detach the realtime superblock from the mount and free it. */
+void
+xfs_rtmount_freesb(
+ struct xfs_mount *mp)
+{
+ struct xfs_buf *bp = mp->m_rtsb_bp;
+
+ if (!bp)
+ return;
+
+ xfs_buf_lock(bp);
+ mp->m_rtsb_bp = NULL;
+ xfs_buf_relse(bp);
+}
+
/*
* Initialize realtime fields in the mount structure.
*/
@@ -1019,22 +1409,19 @@ xfs_rtmount_init(
struct xfs_mount *mp) /* file system mount structure */
{
struct xfs_buf *bp; /* buffer for last block of subvolume */
- struct xfs_sb *sbp; /* filesystem superblock copy in mount */
xfs_daddr_t d; /* address of last block of subvolume */
int error;
- sbp = &mp->m_sb;
- if (sbp->sb_rblocks == 0)
+ if (mp->m_sb.sb_rblocks == 0)
return 0;
if (mp->m_rtdev_targp == NULL) {
xfs_warn(mp,
"Filesystem has a realtime volume, use rtdev=device option");
return -ENODEV;
}
- mp->m_rsumlevels = sbp->sb_rextslog + 1;
- mp->m_rsumblocks = xfs_rtsummary_blockcount(mp, mp->m_rsumlevels,
- mp->m_sb.sb_rbmblocks);
- mp->m_rbmip = mp->m_rsumip = NULL;
+
+ mp->m_rsumblocks = xfs_rtsummary_blockcount(mp, &mp->m_rsumlevels);
+
/*
* Check that the realtime section is an ok size.
*/
@@ -1058,7 +1445,7 @@ xfs_rtmount_init(
static int
xfs_rtalloc_count_frextent(
- struct xfs_mount *mp,
+ struct xfs_rtgroup *rtg,
struct xfs_trans *tp,
const struct xfs_rtalloc_rec *rec,
void *priv)
@@ -1080,12 +1467,18 @@ xfs_rtalloc_reinit_frextents(
uint64_t val = 0;
int error;
- xfs_rtbitmap_lock_shared(mp, XFS_RBMLOCK_BITMAP);
- error = xfs_rtalloc_query_all(mp, NULL, xfs_rtalloc_count_frextent,
- &val);
- xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
- if (error)
- return error;
+ struct xfs_rtgroup *rtg = NULL;
+
+ while ((rtg = xfs_rtgroup_next(mp, rtg))) {
+ xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
+ error = xfs_rtalloc_query_all(rtg, NULL,
+ xfs_rtalloc_count_frextent, &val);
+ xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_BITMAP_SHARED);
+ if (error) {
+ xfs_rtgroup_rele(rtg);
+ return error;
+ }
+ }
spin_lock(&mp->m_sb_lock);
mp->m_sb.sb_frextents = val;
@@ -1101,17 +1494,12 @@ xfs_rtalloc_reinit_frextents(
*/
static inline int
xfs_rtmount_iread_extents(
- struct xfs_inode *ip,
- unsigned int lock_class)
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
{
- struct xfs_trans *tp;
int error;
- error = xfs_trans_alloc_empty(ip->i_mount, &tp);
- if (error)
- return error;
-
- xfs_ilock(ip, XFS_ILOCK_EXCL | lock_class);
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
if (error)
@@ -1124,54 +1512,67 @@ xfs_rtmount_iread_extents(
}
out_unlock:
- xfs_iunlock(ip, XFS_ILOCK_EXCL | lock_class);
- xfs_trans_cancel(tp);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
+static int
+xfs_rtmount_rtg(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ struct xfs_rtgroup *rtg)
+{
+ int error, i;
+
+ for (i = 0; i < XFS_RTGI_MAX; i++) {
+ error = xfs_rtginode_load(rtg, i, tp);
+ if (error)
+ return error;
+
+ if (rtg->rtg_inodes[i]) {
+ error = xfs_rtmount_iread_extents(tp,
+ rtg->rtg_inodes[i]);
+ if (error)
+ return error;
+ }
+ }
+
+ return xfs_alloc_rsum_cache(rtg, mp->m_sb.sb_rbmblocks);
+}
+
/*
* Get the bitmap and summary inodes and the summary cache into the mount
* structure at mount time.
*/
-int /* error */
+int
xfs_rtmount_inodes(
- xfs_mount_t *mp) /* file system mount structure */
+ struct xfs_mount *mp)
{
- int error; /* error return value */
- xfs_sb_t *sbp;
+ struct xfs_trans *tp;
+ struct xfs_rtgroup *rtg = NULL;
+ int error;
- sbp = &mp->m_sb;
- error = xfs_iget(mp, NULL, sbp->sb_rbmino, 0, 0, &mp->m_rbmip);
- if (xfs_metadata_is_sick(error))
- xfs_rt_mark_sick(mp, XFS_SICK_RT_BITMAP);
+ error = xfs_trans_alloc_empty(mp, &tp);
if (error)
return error;
- ASSERT(mp->m_rbmip != NULL);
- error = xfs_rtmount_iread_extents(mp->m_rbmip, XFS_ILOCK_RTBITMAP);
- if (error)
- goto out_rele_bitmap;
-
- error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip);
- if (xfs_metadata_is_sick(error))
- xfs_rt_mark_sick(mp, XFS_SICK_RT_SUMMARY);
- if (error)
- goto out_rele_bitmap;
- ASSERT(mp->m_rsumip != NULL);
-
- error = xfs_rtmount_iread_extents(mp->m_rsumip, XFS_ILOCK_RTSUM);
- if (error)
- goto out_rele_summary;
+ if (xfs_has_rtgroups(mp) && mp->m_sb.sb_rgcount > 0) {
+ error = xfs_rtginode_load_parent(tp);
+ if (error)
+ goto out_cancel;
+ }
- error = xfs_alloc_rsum_cache(mp, sbp->sb_rbmblocks);
- if (error)
- goto out_rele_summary;
- return 0;
+ while ((rtg = xfs_rtgroup_next(mp, rtg))) {
+ error = xfs_rtmount_rtg(mp, tp, rtg);
+ if (error) {
+ xfs_rtgroup_rele(rtg);
+ xfs_rtunmount_inodes(mp);
+ break;
+ }
+ }
-out_rele_summary:
- xfs_irele(mp->m_rsumip);
-out_rele_bitmap:
- xfs_irele(mp->m_rbmip);
+out_cancel:
+ xfs_trans_cancel(tp);
return error;
}
@@ -1179,11 +1580,11 @@ void
xfs_rtunmount_inodes(
struct xfs_mount *mp)
{
- kvfree(mp->m_rsum_cache);
- if (mp->m_rbmip)
- xfs_irele(mp->m_rbmip);
- if (mp->m_rsumip)
- xfs_irele(mp->m_rsumip);
+ struct xfs_rtgroup *rtg = NULL;
+
+ while ((rtg = xfs_rtgroup_next(mp, rtg)))
+ xfs_rtunmount_rtg(rtg);
+ xfs_rtginode_irele(&mp->m_rtdirip);
}
/*
@@ -1195,28 +1596,29 @@ xfs_rtunmount_inodes(
*/
static xfs_rtxnum_t
xfs_rtpick_extent(
- xfs_mount_t *mp, /* file system mount point */
- xfs_trans_t *tp, /* transaction pointer */
+ struct xfs_rtgroup *rtg,
+ struct xfs_trans *tp,
xfs_rtxlen_t len) /* allocation length (rtextents) */
{
- xfs_rtxnum_t b; /* result rtext */
+ struct xfs_mount *mp = rtg_mount(rtg);
+ struct xfs_inode *rbmip = rtg->rtg_inodes[XFS_RTGI_BITMAP];
+ xfs_rtxnum_t b = 0; /* result rtext */
int log2; /* log of sequence number */
uint64_t resid; /* residual after log removed */
uint64_t seq; /* sequence number of file creation */
struct timespec64 ts; /* timespec in inode */
- xfs_assert_ilocked(mp->m_rbmip, XFS_ILOCK_EXCL);
+ xfs_assert_ilocked(rbmip, XFS_ILOCK_EXCL);
- ts = inode_get_atime(VFS_I(mp->m_rbmip));
- if (!(mp->m_rbmip->i_diflags & XFS_DIFLAG_NEWRTBM)) {
- mp->m_rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
+ ts = inode_get_atime(VFS_I(rbmip));
+ if (!(rbmip->i_diflags & XFS_DIFLAG_NEWRTBM)) {
+ rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
seq = 0;
} else {
seq = ts.tv_sec;
}
- if ((log2 = xfs_highbit64(seq)) == -1)
- b = 0;
- else {
+ log2 = xfs_highbit64(seq);
+ if (log2 != -1) {
resid = seq - (1ULL << log2);
b = (mp->m_sb.sb_rextents * ((resid << 1) + 1ULL)) >>
(log2 + 1);
@@ -1226,8 +1628,8 @@ xfs_rtpick_extent(
b = mp->m_sb.sb_rextents - len;
}
ts.tv_sec = seq + 1;
- inode_set_atime_to_ts(VFS_I(mp->m_rbmip), ts);
- xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
+ inode_set_atime_to_ts(VFS_I(rbmip), ts);
+ xfs_trans_log_inode(tp, rbmip, XFS_ILOG_CORE);
return b;
}
@@ -1260,9 +1662,118 @@ xfs_rtalloc_align_minmax(
*raminlen = newminlen;
}
+/* Given a free extent, find any part of it that isn't busy, if possible. */
+STATIC bool
+xfs_rtalloc_check_busy(
+ struct xfs_rtalloc_args *args,
+ xfs_rtxnum_t start,
+ xfs_rtxlen_t minlen_rtx,
+ xfs_rtxlen_t maxlen_rtx,
+ xfs_rtxlen_t len_rtx,
+ xfs_rtxlen_t prod,
+ xfs_rtxnum_t rtx,
+ xfs_rtxlen_t *reslen,
+ xfs_rtxnum_t *resrtx,
+ unsigned *busy_gen)
+{
+ struct xfs_rtgroup *rtg = args->rtg;
+ struct xfs_mount *mp = rtg_mount(rtg);
+ xfs_agblock_t rgbno = xfs_rtx_to_rgbno(rtg, rtx);
+ xfs_rgblock_t min_rgbno = xfs_rtx_to_rgbno(rtg, start);
+ xfs_extlen_t minlen = xfs_rtxlen_to_extlen(mp, minlen_rtx);
+ xfs_extlen_t len = xfs_rtxlen_to_extlen(mp, len_rtx);
+ xfs_extlen_t diff;
+ bool busy;
+
+ busy = xfs_extent_busy_trim(rtg_group(rtg), minlen,
+ xfs_rtxlen_to_extlen(mp, maxlen_rtx), &rgbno, &len,
+ busy_gen);
+
+ /*
+ * If we have a largish extent that happens to start before min_rgbno,
+ * see if we can shift it into range...
+ */
+ if (rgbno < min_rgbno && rgbno + len > min_rgbno) {
+ diff = min_rgbno - rgbno;
+ if (len > diff) {
+ rgbno += diff;
+ len -= diff;
+ }
+ }
+
+ if (prod > 1 && len >= minlen) {
+ xfs_rgblock_t aligned_rgbno = roundup(rgbno, prod);
+
+ diff = aligned_rgbno - rgbno;
+
+ *resrtx = xfs_rgbno_to_rtx(mp, aligned_rgbno);
+ *reslen = xfs_extlen_to_rtxlen(mp,
+ diff >= len ? 0 : len - diff);
+ } else {
+ *resrtx = xfs_rgbno_to_rtx(mp, rgbno);
+ *reslen = xfs_extlen_to_rtxlen(mp, len);
+ }
+
+ return busy;
+}
+
+/*
+ * Adjust the given free extent so that it isn't busy, or flush the log and
+ * wait for the space to become unbusy. Only needed for rtgroups.
+ */
+STATIC int
+xfs_rtallocate_adjust_for_busy(
+ struct xfs_rtalloc_args *args,
+ xfs_rtxnum_t start,
+ xfs_rtxlen_t minlen,
+ xfs_rtxlen_t maxlen,
+ xfs_rtxlen_t *len,
+ xfs_rtxlen_t prod,
+ xfs_rtxnum_t *rtx)
+{
+ xfs_rtxnum_t resrtx;
+ xfs_rtxlen_t reslen;
+ unsigned busy_gen;
+ bool busy;
+ int error;
+
+again:
+ busy = xfs_rtalloc_check_busy(args, start, minlen, maxlen, *len, prod,
+ *rtx, &reslen, &resrtx, &busy_gen);
+ if (!busy)
+ return 0;
+
+ if (reslen < minlen || (start != 0 && resrtx != *rtx)) {
+ /*
+ * Enough of the extent was busy that we cannot satisfy the
+ * allocation, or this is a near allocation and the start of
+ * the extent is busy. Flush the log and wait for the busy
+ * situation to resolve.
+ */
+ trace_xfs_rtalloc_extent_busy(args->rtg, start, minlen, maxlen,
+ *len, prod, *rtx, busy_gen);
+
+ error = xfs_extent_busy_flush(args->tp, rtg_group(args->rtg),
+ busy_gen, 0);
+ if (error)
+ return error;
+
+ goto again;
+ }
+
+ /* Some of the free space wasn't busy, hand that back to the caller. */
+ trace_xfs_rtalloc_extent_busy_trim(args->rtg, *rtx, *len, resrtx,
+ reslen);
+ *len = reslen;
+ *rtx = resrtx;
+
+ return 0;
+}
+
static int
-xfs_rtallocate(
+xfs_rtallocate_rtg(
struct xfs_trans *tp,
+ xfs_rgnumber_t rgno,
xfs_rtblock_t bno_hint,
xfs_rtxlen_t minlen,
xfs_rtxlen_t maxlen,
@@ -1282,12 +1793,33 @@ xfs_rtallocate(
xfs_rtxlen_t len = 0;
int error = 0;
+ args.rtg = xfs_rtgroup_grab(args.mp, rgno);
+ if (!args.rtg)
+ return -ENOSPC;
+
/*
- * Lock out modifications to both the RT bitmap and summary inodes.
+ * We need to lock out modifications to both the RT bitmap and summary
+ * inodes for finding free space in xfs_rtallocate_extent_{near,size}
+ * and join the bitmap and summary inodes for the actual allocation
+ * down in xfs_rtallocate_range.
+ *
+ * For RTG-enabled file system we don't want to join the inodes to the
+ * transaction until we are committed to allocate to allocate from this
+ * RTG so that only one inode of each type is locked at a time.
+ *
+ * But for pre-RTG file systems we need to already to join the bitmap
+ * inode to the transaction for xfs_rtpick_extent, which bumps the
+ * sequence number in it, so we'll have to join the inode to the
+ * transaction early here.
+ *
+ * This is all a bit messy, but at least the mess is contained in
+ * this function.
*/
if (!*rtlocked) {
- xfs_rtbitmap_lock(args.mp);
- xfs_rtbitmap_trans_join(tp);
+ xfs_rtgroup_lock(args.rtg, XFS_RTGLOCK_BITMAP);
+ if (!xfs_has_rtgroups(args.mp))
+ xfs_rtgroup_trans_join(tp, args.rtg,
+ XFS_RTGLOCK_BITMAP);
*rtlocked = true;
}
@@ -1297,8 +1829,8 @@ xfs_rtallocate(
*/
if (bno_hint)
start = xfs_rtb_to_rtx(args.mp, bno_hint);
- else if (initial_user_data)
- start = xfs_rtpick_extent(args.mp, tp, maxlen);
+ else if (!xfs_has_rtgroups(args.mp) && initial_user_data)
+ start = xfs_rtpick_extent(args.rtg, tp, maxlen);
if (start) {
error = xfs_rtallocate_extent_near(&args, start, minlen, maxlen,
@@ -1318,8 +1850,20 @@ xfs_rtallocate(
prod, &rtx);
}
- if (error)
+ if (error) {
+ if (xfs_has_rtgroups(args.mp))
+ goto out_unlock;
goto out_release;
+ }
+
+ if (xfs_has_rtgroups(args.mp)) {
+ error = xfs_rtallocate_adjust_for_busy(&args, start, minlen,
+ maxlen, &len, prod, &rtx);
+ if (error)
+ goto out_unlock;
+
+ xfs_rtgroup_trans_join(tp, args.rtg, XFS_RTGLOCK_BITMAP);
+ }
error = xfs_rtallocate_range(&args, rtx, len);
if (error)
@@ -1328,12 +1872,64 @@ xfs_rtallocate(
xfs_trans_mod_sb(tp, wasdel ?
XFS_TRANS_SB_RES_FREXTENTS : XFS_TRANS_SB_FREXTENTS,
-(long)len);
- *bno = xfs_rtx_to_rtb(args.mp, rtx);
+ *bno = xfs_rtx_to_rtb(args.rtg, rtx);
*blen = xfs_rtxlen_to_extlen(args.mp, len);
out_release:
+ xfs_rtgroup_rele(args.rtg);
xfs_rtbuf_cache_relse(&args);
return error;
+out_unlock:
+ xfs_rtgroup_unlock(args.rtg, XFS_RTGLOCK_BITMAP);
+ *rtlocked = false;
+ goto out_release;
+}
+
+static int
+xfs_rtallocate_rtgs(
+ struct xfs_trans *tp,
+ xfs_fsblock_t bno_hint,
+ xfs_rtxlen_t minlen,
+ xfs_rtxlen_t maxlen,
+ xfs_rtxlen_t prod,
+ bool wasdel,
+ bool initial_user_data,
+ xfs_rtblock_t *bno,
+ xfs_extlen_t *blen)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ xfs_rgnumber_t start_rgno, rgno;
+ int error;
+
+ /*
+ * For now this just blindly iterates over the RTGs for an initial
+ * allocation. We could try to keep an in-memory rtg_longest member
+ * to avoid the locking when just looking for big enough free space,
+ * but for now this keeps things simple.
+ */
+ if (bno_hint != NULLFSBLOCK)
+ start_rgno = xfs_rtb_to_rgno(mp, bno_hint);
+ else
+ start_rgno = (atomic_inc_return(&mp->m_rtgrotor) - 1) %
+ mp->m_sb.sb_rgcount;
+
+ rgno = start_rgno;
+ do {
+ bool rtlocked = false;
+
+ error = xfs_rtallocate_rtg(tp, rgno, bno_hint, minlen, maxlen,
+ prod, wasdel, initial_user_data, &rtlocked,
+ bno, blen);
+ if (error != -ENOSPC)
+ return error;
+ ASSERT(!rtlocked);
+
+ if (++rgno == mp->m_sb.sb_rgcount)
+ rgno = 0;
+ bno_hint = NULLFSBLOCK;
+ } while (rgno != start_rgno);
+
+ return -ENOSPC;
}
static int
@@ -1430,9 +2026,16 @@ retry:
if (xfs_bmap_adjacent(ap))
bno_hint = ap->blkno;
- error = xfs_rtallocate(ap->tp, bno_hint, raminlen, ralen, prod,
- ap->wasdel, initial_user_data, &rtlocked,
- &ap->blkno, &ap->length);
+ if (xfs_has_rtgroups(ap->ip->i_mount)) {
+ error = xfs_rtallocate_rtgs(ap->tp, bno_hint, raminlen, ralen,
+ prod, ap->wasdel, initial_user_data,
+ &ap->blkno, &ap->length);
+ } else {
+ error = xfs_rtallocate_rtg(ap->tp, 0, bno_hint, raminlen, ralen,
+ prod, ap->wasdel, initial_user_data,
+ &rtlocked, &ap->blkno, &ap->length);
+ }
+
if (error == -ENOSPC) {
if (!noalign) {
/*