From: Christoph Hellwig <hch@xxxxxx> Add a helper to contain the per-rtbitmap block logic in xfs_growfs_rt. Note that this helper now allocates a new fake mount structure for each rtbitmap block iteration instead of reusing the memory for an entire growfs call. Compared to all the other work done when freeing the blocks the overhead for this is in the noise and it keeps the code nicely modular. Signed-off-by: Christoph Hellwig <hch@xxxxxx> Reviewed-by: Darrick J. Wong <djwong@xxxxxxxxxx> Signed-off-by: Darrick J. Wong <djwong@xxxxxxxxxx> --- fs/xfs/xfs_rtalloc.c | 317 +++++++++++++++++++++++++------------------------- 1 file changed, 158 insertions(+), 159 deletions(-) diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index a98e22c76280b..5a637166cc788 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -807,9 +807,148 @@ xfs_growfs_rt_fixup_extsize( return error; } -/* - * Visible (exported) functions. - */ +static int +xfs_growfs_rt_bmblock( + struct xfs_mount *mp, + 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_rtalloc_args args = { + .mp = mp, + }; + struct xfs_rtalloc_args nargs = { + }; + 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); + if (!nmp) + return -ENOMEM; + + /* + * Calculate new sb and mount fields for this round. + */ + nmp->m_rtxblklog = -1; /* don't use shift or masking */ + nmp->m_sb.sb_rextsize = rextsize; + 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_rsumsize = XFS_FSB_TO_B(mp, + xfs_rtsummary_blockcount(mp, nmp->m_rsumlevels, + nmp->m_sb.sb_rbmblocks)); + + /* recompute growfsrt reservation from new rsumsize */ + xfs_trans_resv_calc(nmp, &nmp->m_resv); + + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growrtfree, 0, 0, 0, + &args.tp); + if (error) + goto out_free; + nargs.tp = args.tp; + + xfs_rtbitmap_lock(args.tp, mp); + + /* + * Update the bitmap inode's size ondisk and incore. We need to update + * the incore size so that inode inactivation won't punch what it thinks + * are "posteof" blocks. + */ + rbmip->i_disk_size = nmp->m_sb.sb_rbmblocks * nmp->m_sb.sb_blocksize; + i_size_write(VFS_I(rbmip), rbmip->i_disk_size); + xfs_trans_log_inode(args.tp, rbmip, XFS_ILOG_CORE); + + /* + * Update the summary inode's size. We need to update the incore size + * so that inode inactivation won't punch what it thinks are "posteof" + * blocks. + */ + rsumip->i_disk_size = nmp->m_rsumsize; + i_size_write(VFS_I(rsumip), rsumip->i_disk_size); + xfs_trans_log_inode(args.tp, rsumip, XFS_ILOG_CORE); + + /* + * Copy summary data from old to new sizes when the real size (not + * block-aligned) changes. + */ + if (mp->m_sb.sb_rbmblocks != nmp->m_sb.sb_rbmblocks || + mp->m_rsumlevels != nmp->m_rsumlevels) { + error = xfs_rtcopy_summary(&args, &nargs); + if (error) + goto out_cancel; + } + + /* + * Update superblock fields. + */ + if (nmp->m_sb.sb_rextsize != mp->m_sb.sb_rextsize) + xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_REXTSIZE, + nmp->m_sb.sb_rextsize - mp->m_sb.sb_rextsize); + if (nmp->m_sb.sb_rbmblocks != mp->m_sb.sb_rbmblocks) + xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_RBMBLOCKS, + nmp->m_sb.sb_rbmblocks - mp->m_sb.sb_rbmblocks); + if (nmp->m_sb.sb_rblocks != mp->m_sb.sb_rblocks) + xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_RBLOCKS, + nmp->m_sb.sb_rblocks - mp->m_sb.sb_rblocks); + if (nmp->m_sb.sb_rextents != mp->m_sb.sb_rextents) + xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_REXTENTS, + nmp->m_sb.sb_rextents - mp->m_sb.sb_rextents); + 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); + + /* + * 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); + xfs_rtbuf_cache_relse(&nargs); + if (error) + goto out_cancel; + + /* + * Mark more blocks free in the superblock. + */ + xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_FREXTENTS, freed_rtx); + + /* + * Update mp values into the real mp structure. + */ + mp->m_rsumlevels = nmp->m_rsumlevels; + mp->m_rsumsize = nmp->m_rsumsize; + + /* + * Recompute the growfsrt reservation from the new rsumsize. + */ + xfs_trans_resv_calc(mp, &mp->m_resv); + + error = xfs_trans_commit(args.tp); + if (error) + goto out_free; + + /* + * Ensure the mount RT feature flag is now set. + */ + mp->m_features |= XFS_FEAT_REALTIME; + + kfree(nmp); + return 0; + +out_cancel: + xfs_trans_cancel(args.tp); +out_free: + kfree(nmp); + return error; +} /* * Grow the realtime area of the filesystem. @@ -822,23 +961,14 @@ xfs_growfs_rt( xfs_fileoff_t bmbno; /* bitmap block number */ struct xfs_buf *bp; /* temporary buffer */ int error; /* error return value */ - xfs_mount_t *nmp; /* new (fake) mount structure */ - xfs_rfsblock_t nrblocks; /* new number of realtime blocks */ xfs_extlen_t nrbmblocks; /* new number of rt bitmap blocks */ xfs_rtxnum_t nrextents; /* new number of realtime extents */ - uint8_t nrextslog; /* new log2 of sb_rextents */ xfs_extlen_t nrsumblocks; /* new number of summary blocks */ - uint nrsumlevels; /* new rt summary levels */ - uint nrsumsize; /* new size of rt summary, bytes */ - xfs_sb_t *nsbp; /* new superblock */ xfs_extlen_t rbmblocks; /* current number of rt bitmap blocks */ xfs_extlen_t rsumblocks; /* current number of rt summary blks */ - xfs_sb_t *sbp; /* old superblock */ uint8_t *rsum_cache; /* old summary cache */ xfs_agblock_t old_rextsize = mp->m_sb.sb_rextsize; - sbp = &mp->m_sb; - if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -857,11 +987,10 @@ xfs_growfs_rt( goto out_unlock; /* Shrink not supported. */ - if (in->newblocks <= sbp->sb_rblocks) + if (in->newblocks <= mp->m_sb.sb_rblocks) goto out_unlock; - /* Can only change rt extent size when adding rt volume. */ - if (sbp->sb_rblocks > 0 && in->extsize != sbp->sb_rextsize) + if (mp->m_sb.sb_rblocks > 0 && in->extsize != mp->m_sb.sb_rextsize) goto out_unlock; /* Range check the extent size. */ @@ -874,15 +1003,14 @@ xfs_growfs_rt( if (xfs_has_rmapbt(mp) || xfs_has_reflink(mp) || xfs_has_quota(mp)) goto out_unlock; - nrblocks = in->newblocks; - error = xfs_sb_validate_fsb_count(sbp, nrblocks); + error = xfs_sb_validate_fsb_count(&mp->m_sb, in->newblocks); if (error) goto out_unlock; /* * Read in the last block of the device, make sure it exists. */ error = xfs_buf_read_uncached(mp->m_rtdev_targp, - XFS_FSB_TO_BB(mp, nrblocks - 1), + XFS_FSB_TO_BB(mp, in->newblocks - 1), XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL); if (error) goto out_unlock; @@ -891,17 +1019,15 @@ xfs_growfs_rt( /* * Calculate new parameters. These are the final values to be reached. */ - nrextents = nrblocks; - do_div(nrextents, in->extsize); + nrextents = div_u64(in->newblocks, in->extsize); if (nrextents == 0) { error = -EINVAL; goto out_unlock; } nrbmblocks = xfs_rtbitmap_blockcount(mp, nrextents); - nrextslog = xfs_compute_rextslog(nrextents); - nrsumlevels = nrextslog + 1; - nrsumblocks = xfs_rtsummary_blockcount(mp, nrsumlevels, nrbmblocks); - nrsumsize = XFS_FSB_TO_B(mp, nrsumblocks); + 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, @@ -929,149 +1055,27 @@ xfs_growfs_rt( goto out_unlock; rsum_cache = mp->m_rsum_cache; - if (nrbmblocks != sbp->sb_rbmblocks) { + if (nrbmblocks != mp->m_sb.sb_rbmblocks) { error = xfs_alloc_rsum_cache(mp, nrbmblocks); if (error) goto out_unlock; } - /* - * Allocate a new (fake) mount/sb. - */ - nmp = kmalloc(sizeof(*nmp), GFP_KERNEL | __GFP_NOFAIL); /* * Loop over the bitmap blocks. * We will do everything one bitmap block at a time. * Skip the current block if it is exactly full. * This also deals with the case where there were no rtextents before. */ - for (bmbno = sbp->sb_rbmblocks - - ((sbp->sb_rextents & ((1 << mp->m_blkbit_log) - 1)) != 0); - bmbno < nrbmblocks; - bmbno++) { - struct xfs_rtalloc_args args = { - .mp = mp, - }; - struct xfs_rtalloc_args nargs = { - .mp = nmp, - }; - struct xfs_trans *tp; - xfs_rfsblock_t nrblocks_step; - - *nmp = *mp; - nsbp = &nmp->m_sb; - /* - * Calculate new sb and mount fields for this round. - */ - nsbp->sb_rextsize = in->extsize; - nmp->m_rtxblklog = -1; /* don't use shift or masking */ - nsbp->sb_rbmblocks = bmbno + 1; - nrblocks_step = (bmbno + 1) * NBBY * nsbp->sb_blocksize * - nsbp->sb_rextsize; - nsbp->sb_rblocks = min(nrblocks, nrblocks_step); - nsbp->sb_rextents = xfs_rtb_to_rtx(nmp, nsbp->sb_rblocks); - ASSERT(nsbp->sb_rextents != 0); - nsbp->sb_rextslog = xfs_compute_rextslog(nsbp->sb_rextents); - nrsumlevels = nmp->m_rsumlevels = nsbp->sb_rextslog + 1; - nrsumblocks = xfs_rtsummary_blockcount(mp, nrsumlevels, - nsbp->sb_rbmblocks); - nmp->m_rsumsize = nrsumsize = XFS_FSB_TO_B(mp, nrsumblocks); - /* recompute growfsrt reservation from new rsumsize */ - xfs_trans_resv_calc(nmp, &nmp->m_resv); - - /* - * Start a transaction, get the log reservation. - */ - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growrtfree, 0, 0, 0, - &tp); + bmbno = mp->m_sb.sb_rbmblocks; + if (xfs_rtx_to_rbmword(mp, mp->m_sb.sb_rextents) != 0) + bmbno--; + for (; bmbno < nrbmblocks; bmbno++) { + error = xfs_growfs_rt_bmblock(mp, in->newblocks, in->extsize, + bmbno); if (error) - break; - args.tp = tp; - nargs.tp = tp; - - /* - * Lock out other callers by grabbing the bitmap and summary - * inode locks and joining them to the transaction. - */ - xfs_rtbitmap_lock(tp, mp); - /* - * Update the bitmap inode's size ondisk and incore. We need - * to update the incore size so that inode inactivation won't - * punch what it thinks are "posteof" blocks. - */ - mp->m_rbmip->i_disk_size = - nsbp->sb_rbmblocks * nsbp->sb_blocksize; - i_size_write(VFS_I(mp->m_rbmip), mp->m_rbmip->i_disk_size); - xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE); - /* - * Update the summary inode's size. We need to update the - * incore size so that inode inactivation won't punch what it - * thinks are "posteof" blocks. - */ - mp->m_rsumip->i_disk_size = nmp->m_rsumsize; - i_size_write(VFS_I(mp->m_rsumip), mp->m_rsumip->i_disk_size); - xfs_trans_log_inode(tp, mp->m_rsumip, XFS_ILOG_CORE); - /* - * Copy summary data from old to new sizes. - * Do this when the real size (not block-aligned) changes. - */ - if (sbp->sb_rbmblocks != nsbp->sb_rbmblocks || - mp->m_rsumlevels != nmp->m_rsumlevels) { - error = xfs_rtcopy_summary(&args, &nargs); - if (error) - goto error_cancel; - } - /* - * Update superblock fields. - */ - if (nsbp->sb_rextsize != sbp->sb_rextsize) - xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTSIZE, - nsbp->sb_rextsize - sbp->sb_rextsize); - if (nsbp->sb_rbmblocks != sbp->sb_rbmblocks) - xfs_trans_mod_sb(tp, XFS_TRANS_SB_RBMBLOCKS, - nsbp->sb_rbmblocks - sbp->sb_rbmblocks); - if (nsbp->sb_rblocks != sbp->sb_rblocks) - xfs_trans_mod_sb(tp, XFS_TRANS_SB_RBLOCKS, - nsbp->sb_rblocks - sbp->sb_rblocks); - if (nsbp->sb_rextents != sbp->sb_rextents) - xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTENTS, - nsbp->sb_rextents - sbp->sb_rextents); - if (nsbp->sb_rextslog != sbp->sb_rextslog) - xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTSLOG, - nsbp->sb_rextslog - sbp->sb_rextslog); - /* - * Free new extent. - */ - error = xfs_rtfree_range(&nargs, sbp->sb_rextents, - nsbp->sb_rextents - sbp->sb_rextents); - xfs_rtbuf_cache_relse(&nargs); - if (error) { -error_cancel: - xfs_trans_cancel(tp); - break; - } - /* - * Mark more blocks free in the superblock. - */ - xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, - nsbp->sb_rextents - sbp->sb_rextents); - /* - * Update mp values into the real mp structure. - */ - mp->m_rsumlevels = nrsumlevels; - mp->m_rsumsize = nrsumsize; - /* recompute growfsrt reservation from new rsumsize */ - xfs_trans_resv_calc(mp, &mp->m_resv); - - error = xfs_trans_commit(tp); - if (error) - break; - - /* Ensure the mount RT feature flag is now set. */ - mp->m_features |= XFS_FEAT_REALTIME; + goto out_free; } - if (error) - goto out_free; if (old_rextsize != in->extsize) { error = xfs_growfs_rt_fixup_extsize(mp); @@ -1083,11 +1087,6 @@ xfs_growfs_rt( error = xfs_update_secondary_sbs(mp); out_free: - /* - * Free the fake mp structure. - */ - kfree(nmp); - /* * 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