cregit-Linux how code gets into the kernel

Release 4.10 fs/xfs/xfs_mount.c

Directory: fs/xfs
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#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_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_dir2.h"
#include "xfs_ialloc.h"
#include "xfs_alloc.h"
#include "xfs_rtalloc.h"
#include "xfs_bmap.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_log.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_fsops.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_sysfs.h"
#include "xfs_rmap_btree.h"
#include "xfs_refcount_btree.h"
#include "xfs_reflink.h"


static DEFINE_MUTEX(xfs_uuid_table_mutex);

static int xfs_uuid_table_size;

static uuid_t *xfs_uuid_table;


void xfs_uuid_table_free(void) { if (xfs_uuid_table_size == 0) return; kmem_free(xfs_uuid_table); xfs_uuid_table = NULL; xfs_uuid_table_size = 0; }

Contributors

PersonTokensPropCommitsCommitProp
darrick j. wongdarrick j. wong27100.00%1100.00%
Total27100.00%1100.00%

/* * See if the UUID is unique among mounted XFS filesystems. * Mount fails if UUID is nil or a FS with the same UUID is already mounted. */
STATIC int xfs_uuid_mount( struct xfs_mount *mp) { uuid_t *uuid = &mp->m_sb.sb_uuid; int hole, i; if (mp->m_flags & XFS_MOUNT_NOUUID) return 0; if (uuid_is_nil(uuid)) { xfs_warn(mp, "Filesystem has nil UUID - can't mount"); return -EINVAL; } mutex_lock(&xfs_uuid_table_mutex); for (i = 0, hole = -1; i < xfs_uuid_table_size; i++) { if (uuid_is_nil(&xfs_uuid_table[i])) { hole = i; continue; } if (uuid_equal(uuid, &xfs_uuid_table[i])) goto out_duplicate; } if (hole < 0) { xfs_uuid_table = kmem_realloc(xfs_uuid_table, (xfs_uuid_table_size + 1) * sizeof(*xfs_uuid_table), KM_SLEEP); hole = xfs_uuid_table_size++; } xfs_uuid_table[hole] = *uuid; mutex_unlock(&xfs_uuid_table_mutex); return 0; out_duplicate: mutex_unlock(&xfs_uuid_table_mutex); xfs_warn(mp, "Filesystem has duplicate UUID %pU - can't mount", uuid); return -EINVAL; }

Contributors

PersonTokensPropCommitsCommitProp
dave chinnerdave chinner15481.05%480.00%
christoph hellwigchristoph hellwig3618.95%120.00%
Total190100.00%5100.00%


STATIC void xfs_uuid_unmount( struct xfs_mount *mp) { uuid_t *uuid = &mp->m_sb.sb_uuid; int i; if (mp->m_flags & XFS_MOUNT_NOUUID) return; mutex_lock(&xfs_uuid_table_mutex); for (i = 0; i < xfs_uuid_table_size; i++) { if (uuid_is_nil(&xfs_uuid_table[i])) continue; if (!uuid_equal(uuid, &xfs_uuid_table[i])) continue; memset(&xfs_uuid_table[i], 0, sizeof(uuid_t)); break; } ASSERT(i < xfs_uuid_table_size); mutex_unlock(&xfs_uuid_table_mutex); }

Contributors

PersonTokensPropCommitsCommitProp
dave chinnerdave chinner112100.00%3100.00%
Total112100.00%3100.00%


STATIC void __xfs_free_perag( struct rcu_head *head) { struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head); ASSERT(atomic_read(&pag->pag_ref) == 0); kmem_free(pag); }

Contributors

PersonTokensPropCommitsCommitProp
dave chinnerdave chinner44100.00%3100.00%
Total44100.00%3100.00%

/* * Free up the per-ag resources associated with the mount structure. */
STATIC void xfs_free_perag( xfs_mount_t *mp) { xfs_agnumber_t agno; struct xfs_perag *pag; for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) { spin_lock(&mp->m_perag_lock); pag = radix_tree_delete(&mp->m_perag_tree, agno); spin_unlock(&mp->m_perag_lock); ASSERT(pag); ASSERT(atomic_read(&pag->pag_ref) == 0); xfs_buf_hash_destroy(pag); call_rcu(&pag->rcu_head, __xfs_free_perag); } }

Contributors

PersonTokensPropCommitsCommitProp
dave chinnerdave chinner9394.90%375.00%
lucas stachlucas stach55.10%125.00%
Total98100.00%4100.00%

/* * Check size of device based on the (data/realtime) block count. * Note: this check is used by the growfs code as well as mount. */
int xfs_sb_validate_fsb_count( xfs_sb_t *sbp, __uint64_t nblocks) { ASSERT(PAGE_SHIFT >= sbp->sb_blocklog); ASSERT(sbp->sb_blocklog >= BBSHIFT); /* Limited by ULONG_MAX of page cache index */ if (nblocks >> (PAGE_SHIFT - sbp->sb_blocklog) > ULONG_MAX) return -EFBIG; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
dave chinnerdave chinner5198.08%480.00%
kirill a. shutemovkirill a. shutemov11.92%120.00%
Total52100.00%5100.00%


int xfs_initialize_perag( xfs_mount_t *mp, xfs_agnumber_t agcount, xfs_agnumber_t *maxagi) { xfs_agnumber_t index; xfs_agnumber_t first_initialised = 0; xfs_perag_t *pag; int error = -ENOMEM; /* * Walk the current per-ag tree so we don't try to initialise AGs * that already exist (growfs case). Allocate and insert all the * AGs we don't find ready for initialisation. */ for (index = 0; index < agcount; index++) { pag = xfs_perag_get(mp, index); if (pag) { xfs_perag_put(pag); continue; } if (!first_initialised) first_initialised = index; pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL); if (!pag) goto out_unwind; pag->pag_agno = index; pag->pag_mount = mp; spin_lock_init(&pag->pag_ici_lock); mutex_init(&pag->pag_ici_reclaim_lock); INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); if (xfs_buf_hash_init(pag)) goto out_unwind; if (radix_tree_preload(GFP_NOFS)) goto out_unwind; spin_lock(&mp->m_perag_lock); if (radix_tree_insert(&mp->m_perag_tree, index, pag)) { BUG(); spin_unlock(&mp->m_perag_lock); radix_tree_preload_end(); error = -EEXIST; goto out_unwind; } spin_unlock(&mp->m_perag_lock); radix_tree_preload_end(); } index = xfs_set_inode_alloc(mp, agcount); if (maxagi) *maxagi = index; mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp); return 0; out_unwind: xfs_buf_hash_destroy(pag); kmem_free(pag); for (; index > first_initialised; index--) { pag = radix_tree_delete(&mp->m_perag_tree, index); xfs_buf_hash_destroy(pag); kmem_free(pag); } return error; }

Contributors

PersonTokensPropCommitsCommitProp
dave chinnerdave chinner18763.39%630.00%
christoph hellwigchristoph hellwig4816.27%315.00%
nathan scottnathan scott258.47%525.00%
lucas stachlucas stach175.76%15.00%
darrick j. wongdarrick j. wong93.05%15.00%
chandra seetharamanchandra seetharaman51.69%15.00%
eric sandeeneric sandeen31.02%210.00%
david chinnerdavid chinner10.34%15.00%
Total295100.00%20100.00%

/* * xfs_readsb * * Does the initial read of the superblock. */
int xfs_readsb( struct xfs_mount *mp, int flags) { unsigned int sector_size; struct xfs_buf *bp; struct xfs_sb *sbp = &mp->m_sb; int error; int loud = !(flags & XFS_MFSI_QUIET); const struct xfs_buf_ops *buf_ops; ASSERT(mp->m_sb_bp == NULL); ASSERT(mp->m_ddev_targp != NULL); /* * For the initial read, we must guess at the sector * size based on the block device. It's enough to * get the sb_sectsize out of the superblock and * then reread with the proper length. * We don't verify it yet, because it may not be complete. */ sector_size = xfs_getsize_buftarg(mp->m_ddev_targp); buf_ops = NULL; /* * Allocate a (locked) buffer to hold the superblock. This will be kept * around at all times to optimize access to the superblock. Therefore, * set XBF_NO_IOACCT to make sure it doesn't hold the buftarg count * elevated. */ reread: error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR, BTOBB(sector_size), XBF_NO_IOACCT, &bp, buf_ops); if (error) { if (loud) xfs_warn(mp, "SB validate failed with error %d.", error); /* bad CRC means corrupted metadata */ if (error == -EFSBADCRC) error = -EFSCORRUPTED; return error; } /* * Initialize the mount structure from the superblock. */ xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp)); /* * If we haven't validated the superblock, do so now before we try * to check the sector size and reread the superblock appropriately. */ if (sbp->sb_magicnum != XFS_SB_MAGIC) { if (loud) xfs_warn(mp, "Invalid superblock magic number"); error = -EINVAL; goto release_buf; } /* * We must be able to do sector-sized and sector-aligned IO. */ if (sector_size > sbp->sb_sectsize) { if (loud) xfs_warn(mp, "device supports %u byte sectors (not %u)", sector_size, sbp->sb_sectsize); error = -ENOSYS; goto release_buf; } if (buf_ops == NULL) { /* * Re-read the superblock so the buffer is correctly sized, * and properly verified. */ xfs_buf_relse(bp); sector_size = sbp->sb_sectsize; buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops; goto reread; } xfs_reinit_percpu_counters(mp); /* no need to be quiet anymore, so reset the buf ops */ bp->b_ops = &xfs_sb_buf_ops; mp->m_sb_bp = bp; xfs_buf_unlock(bp); return 0; release_buf: xfs_buf_relse(bp); return error; }

Contributors

PersonTokensPropCommitsCommitProp
dave chinnerdave chinner19265.98%650.00%
david chinnerdavid chinner4013.75%216.67%
christoph hellwigchristoph hellwig3311.34%216.67%
eric sandeeneric sandeen248.25%18.33%
brian fosterbrian foster20.69%18.33%
Total291100.00%12100.00%

/* * Update alignment values based on mount options and sb values */
STATIC int xfs_update_alignment(xfs_mount_t *mp) { xfs_sb_t *sbp = &(mp->m_sb); if (mp->m_dalign) { /* * If stripe unit and stripe width are not multiples * of the fs blocksize turn off alignment. */ if ((BBTOB(mp->m_dalign) & mp->m_blockmask) || (BBTOB(mp->m_swidth) & mp->m_blockmask)) { xfs_warn(mp, "alignment check failed: sunit/swidth vs. blocksize(%d)", sbp->sb_blocksize); return -EINVAL; } else { /* * Convert the stripe unit and width to FSBs. */ mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign); if (mp->m_dalign && (sbp->sb_agblocks % mp->m_dalign)) { xfs_warn(mp, "alignment check failed: sunit/swidth vs. agsize(%d)", sbp->sb_agblocks); return -EINVAL; } else if (mp->m_dalign) { mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth); } else { xfs_warn(mp, "alignment check failed: sunit(%d) less than bsize(%d)", mp->m_dalign, sbp->sb_blocksize); return -EINVAL; } } /* * Update superblock with new values * and log changes */ if (xfs_sb_version_hasdalign(sbp)) { if (sbp->sb_unit != mp->m_dalign) { sbp->sb_unit = mp->m_dalign; mp->m_update_sb = true; } if (sbp->sb_width != mp->m_swidth) { sbp->sb_width = mp->m_swidth; mp->m_update_sb = true; } } else { xfs_warn(mp, "cannot change alignment: superblock does not support data alignment"); return -EINVAL; } } else if ((mp->m_flags & XFS_MOUNT_NOALIGN) != XFS_MOUNT_NOALIGN && xfs_sb_version_hasdalign(&mp->m_sb)) { mp->m_dalign = sbp->sb_unit; mp->m_swidth = sbp->sb_width; } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig22076.66%216.67%
jeff liujeff liu269.06%216.67%
eric sandeeneric sandeen206.97%325.00%
dave chinnerdave chinner134.53%433.33%
john krueger* (same as john keller?)*john krueger* (same as john keller?)*82.79%18.33%
Total287100.00%12100.00%

/* * Set the maximum inode count for this filesystem */
STATIC void xfs_set_maxicount(xfs_mount_t *mp) { xfs_sb_t *sbp = &(mp->m_sb); __uint64_t icount; if (sbp->sb_imax_pct) { /* * Make sure the maximum inode count is a multiple * of the units we allocate inodes in. */ icount = sbp->sb_dblocks * sbp->sb_imax_pct; do_div(icount, 100); do_div(icount, mp->m_ialloc_blks); mp->m_maxicount = (icount * mp->m_ialloc_blks) << sbp->sb_inopblog; } else { mp->m_maxicount = 0; } }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig5970.24%150.00%
eric sandeeneric sandeen2529.76%150.00%
Total84100.00%2100.00%

/* * Set the default minimum read and write sizes unless * already specified in a mount option. * We use smaller I/O sizes when the file system * is being used for NFS service (wsync mount option). */
STATIC void xfs_set_rw_sizes(xfs_mount_t *mp) { xfs_sb_t *sbp = &(mp->m_sb); int readio_log, writeio_log; if (!(mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)) { if (mp->m_flags & XFS_MOUNT_WSYNC) { readio_log = XFS_WSYNC_READIO_LOG; writeio_log = XFS_WSYNC_WRITEIO_LOG; } else { readio_log = XFS_READIO_LOG_LARGE; writeio_log = XFS_WRITEIO_LOG_LARGE; } } else { readio_log = mp->m_readio_log; writeio_log = mp->m_writeio_log; } if (sbp->sb_blocklog > readio_log) { mp->m_readio_log = sbp->sb_blocklog; } else { mp->m_readio_log = readio_log; } mp->m_readio_blocks = 1 << (mp->m_readio_log - sbp->sb_blocklog); if (sbp->sb_blocklog > writeio_log) { mp->m_writeio_log = sbp->sb_blocklog; } else { mp->m_writeio_log = writeio_log; } mp->m_writeio_blocks = 1 << (mp->m_writeio_log - sbp->sb_blocklog); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig14887.57%133.33%
eric sandeeneric sandeen1911.24%133.33%
stephen lordstephen lord21.18%133.33%
Total169100.00%3100.00%

/* * precalculate the low space thresholds for dynamic speculative preallocation. */
void xfs_set_low_space_thresholds( struct xfs_mount *mp) { int i; for (i = 0; i < XFS_LOWSP_MAX; i++) { __uint64_t space = mp->m_sb.sb_dblocks; do_div(space, 100); mp->m_low_space[i] = space * (i + 1); } }

Contributors

PersonTokensPropCommitsCommitProp
dave chinnerdave chinner59100.00%1100.00%
Total59100.00%1100.00%

/* * Set whether we're using inode alignment. */
STATIC void xfs_set_inoalignment(xfs_mount_t *mp) { if (xfs_sb_version_hasalign(&mp->m_sb) && mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size)) mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1; else mp->m_inoalign_mask = 0; /* * If we are using stripe alignment, check whether * the stripe unit is a multiple of the inode alignment */ if (mp->m_dalign && mp->m_inoalign_mask && !(mp->m_dalign & mp->m_inoalign_mask)) mp->m_sinoalign = mp->m_dalign; else mp->m_sinoalign = 0; }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig7885.71%133.33%
eric sandeeneric sandeen1314.29%266.67%
Total91100.00%3100.00%

/* * Check that the data (and log if separate) is an ok size. */
STATIC int xfs_check_sizes( struct xfs_mount *mp) { struct xfs_buf *bp; xfs_daddr_t d; int error; d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks); if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) { xfs_warn(mp, "filesystem size mismatch detected"); return -EFBIG; } error = xfs_buf_read_uncached(mp->m_ddev_targp, d - XFS_FSS_TO_BB(mp, 1), XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL); if (error) { xfs_warn(mp, "last sector read failed"); return error; } xfs_buf_relse(bp); if (mp->m_logdev_targp == mp->m_ddev_targp) return 0; d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks); if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) { xfs_warn(mp, "log size mismatch detected"); return -EFBIG; } error = xfs_buf_read_uncached(mp->m_logdev_targp, d - XFS_FSB_TO_BB(mp, 1), XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL); if (error) { xfs_warn(mp, "log device read failed"); return error; } xfs_buf_relse(bp); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
eric sandeeneric sandeen14462.07%222.22%
dave chinnerdave chinner5624.14%666.67%
christoph hellwigchristoph hellwig3213.79%111.11%
Total232100.00%9100.00%

/* * Clear the quotaflags in memory and in the superblock. */
int xfs_mount_reset_sbqflags( struct xfs_mount *mp) { mp->m_qflags = 0; /* It is OK to look at sb_qflags in the mount path without m_sb_lock. */ if (mp->m_sb.sb_qflags == 0) return 0; spin_lock(&mp->m_sb_lock); mp->m_sb.sb_qflags = 0; spin_unlock(&mp->m_sb_lock); if (!xfs_fs_writable(mp, SB_FREEZE_WRITE)) return 0; return xfs_sync_sb(mp, false); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig6688.00%133.33%
dave chinnerdave chinner810.67%133.33%
jeff liujeff liu11.33%133.33%
Total75100.00%3100.00%


__uint64_t xfs_default_resblks(xfs_mount_t *mp) { __uint64_t resblks; /* * We default to 5% or 8192 fsbs of space reserved, whichever is * smaller. This is intended to cover concurrent allocation * transactions when we initially hit enospc. These each require a 4 * block reservation. Hence by default we cover roughly 2000 concurrent * allocation reservations. */ resblks = mp->m_sb.sb_dblocks; do_div(resblks, 20); resblks = min_t(__uint64_t, resblks, 8192); return resblks; }

Contributors

PersonTokensPropCommitsCommitProp
eric sandeeneric sandeen4095.24%150.00%
david chinnerdavid chinner24.76%150.00%
Total42100.00%2100.00%

/* * This function does the following on an initial mount of a file system: * - reads the superblock from disk and init the mount struct * - if we're a 32-bit kernel, do a size check on the superblock * so we don't mount terabyte filesystems * - init mount struct realtime fields * - allocate inode hash table for fs * - init directory manager * - perform recovery and init the log manager */
int xfs_mountfs( struct xfs_mount *mp) { struct xfs_sb *sbp = &(mp->m_sb); struct xfs_inode *rip; __uint64_t resblks; uint quotamount = 0; uint quotaflags = 0; int error = 0; xfs_sb_mount_common(mp, sbp); /* * Check for a mismatched features2 values. Older kernels read & wrote * into the wrong sb offset for sb_features2 on some platforms due to * xfs_sb_t not being 64bit size aligned when sb_features2 was added, * which made older superblock reading/writing routines swap it as a * 64-bit value. * * For backwards compatibility, we make both slots equal. * * If we detect a mismatched field, we OR the set bits into the existing * features2 field in case it has already been modified; we don't want * to lose any features. We then update the bad location with the ORed * value so that older kernels will see any features2 flags. The * superblock writeback code ensures the new sb_features2 is copied to * sb_bad_features2 before it is logged or written to disk. */ if (xfs_sb_has_mismatched_features2(sbp)) { xfs_warn(mp, "correcting sb_features alignment problem"); sbp->sb_features2 |= sbp->sb_bad_features2; mp->m_update_sb = true; /* * Re-check for ATTR2 in case it was found in bad_features2 * slot. */ if (xfs_sb_version_hasattr2(&mp->m_sb) && !(mp->m_flags & XFS_MOUNT_NOATTR2)) mp->m_flags |= XFS_MOUNT_ATTR2; } if (xfs_sb_version_hasattr2(&mp->m_sb) && (mp->m_flags & XFS_MOUNT_NOATTR2)) { xfs_sb_version_removeattr2(&mp->m_sb); mp->m_update_sb = true; /* update sb_versionnum for the clearing of the morebits */ if (!sbp->sb_features2) mp->m_update_sb = true; } /* always use v2 inodes by default now */ if (!(mp->m_sb.sb_versionnum & XFS_SB_VERSION_NLINKBIT)) { mp->m_sb.sb_versionnum |= XFS_SB_VERSION_NLINKBIT; mp->m_update_sb = true; } /* * Check if sb_agblocks is aligned at stripe boundary * If sb_agblocks is NOT aligned turn off m_dalign since * allocator alignment is within an ag, therefore ag has * to be aligned at stripe boundary. */ error = xfs_update_alignment(mp); if (error) goto out; xfs_alloc_compute_maxlevels(mp); xfs_bmap_compute_maxlevels(mp, XFS_DATA_FORK); xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK); xfs_ialloc_compute_maxlevels(mp); xfs_rmapbt_compute_maxlevels(mp); xfs_refcountbt_compute_maxlevels(mp); xfs_set_maxicount(mp); /* enable fail_at_unmount as default */ mp->m_fail_unmount = 1; error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, NULL, mp->m_fsname); if (error) goto out; error = xfs_sysfs_init(&mp->m_stats.xs_kobj, &xfs_stats_ktype, &mp->m_kobj, "stats"); if (error) goto out_remove_sysfs; error = xfs_error_sysfs_init(mp); if (error) goto out_del_stats; error = xfs_uuid_mount(mp); if (error) goto out_remove_error_sysfs; /* * Set the minimum read and write sizes */ xfs_set_rw_sizes(mp); /* set the low space thresholds for dynamic preallocation */ xfs_set_low_space_thresholds(mp); /* * Set the inode cluster size. * This may still be overridden by the file system * block size if it is larger than the chosen cluster size. * * For v5 filesystems, scale the cluster size with the inode size to * keep a constant ratio of inode per cluster buffer, but only if mkfs * has set the inode alignment value appropriately for larger cluster * sizes. */ mp->m_inode_cluster_size = XFS_INODE_BIG_CLUSTER_SIZE; if (xfs_sb_version_hascrc(&mp->m_sb)) { int new_size = mp->m_inode_cluster_size; new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE; if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size)) mp->m_inode_cluster_size = new_size; } /* * If enabled, sparse inode chunk alignment is expected to match the * cluster size. Full inode chunk alignment must match the chunk size, * but that is checked on sb read verification... */ if (xfs_sb_version_hassparseinodes(&mp->m_sb) && mp->m_sb.sb_spino_align != XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size)) { xfs_warn(mp, "Sparse inode block alignment (%u) must match cluster size (%llu).", mp->m_sb.sb_spino_align, XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size)); error = -EINVAL; goto out_remove_uuid; } /* * Set inode alignment fields */ xfs_set_inoalignment(mp); /* * Check that the data (and log if separate) is an ok size. */ error = xfs_check_sizes(mp); if (error) goto out_remove_uuid; /* * Initialize realtime fields in the mount structure */ error = xfs_rtmount_init(mp); if (error) { xfs_warn(mp, "RT mount failed"); goto out_remove_uuid; } /* * Copies the low order bits of the timestamp and the randomly * set "sequence" number out of a UUID. */ uuid_getnodeuniq(&sbp->sb_uuid, mp->m_fixedfsid); mp->m_dmevmask = 0; /* not persistent; set after each mount */ error = xfs_da_mount(mp); if (error) { xfs_warn(mp, "Failed dir/attr init: %d", error); goto out_remove_uuid; } /* * Initialize the precomputed transaction reservations values. */ xfs_trans_init(mp); /* * Allocate and initialize the per-ag data. */ spin_lock_init(&mp->m_perag_lock); INIT_RADIX_TREE(&mp->m_perag_tree, GFP_ATOMIC); error = xfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi); if (error) { xfs_warn(mp, "Failed per-ag init: %d", error); goto out_free_dir; } if (!sbp->sb_logblocks) { xfs_warn(mp, "no log defined"); XFS_ERROR_REPORT("xfs_mountfs", XFS_ERRLEVEL_LOW, mp); error = -EFSCORRUPTED; goto out_free_perag; } /* * Log's mount-time initialization. The first part of recovery can place * some items on the AIL, to be handled when recovery is finished or * cancelled. */ error = xfs_log_mount(mp, mp->m_logdev_targp, XFS_FSB_TO_DADDR(mp, sbp->sb_logstart), XFS_FSB_TO_BB(mp, sbp->sb_logblocks)); if (error) { xfs_warn(mp, "log mount failed"); goto out_fail_wait; } /* * Now the log is mounted, we know if it was an unclean shutdown or * not. If it was, with the first phase of recovery has completed, we * have consistent AG blocks on disk. We have not recovered EFIs yet, * but they are recovered transactionally in the second recovery phase * later. * * Hence we can safely re-initialise incore superblock counters from * the per-ag data. These may not be correct if the filesystem was not * cleanly unmounted, so we need to wait for recovery to finish before * doing this. * * If the filesystem was cleanly unmounted, then we can trust the * values in the superblock to be correct and we don't need to do * anything here. * * If we are currently making the filesystem, the initialisation will * fail as the perag data is in an undefined state. */ if (xfs_sb_version_haslazysbcount(&mp->m_sb) && !XFS_LAST_UNMOUNT_WAS_CLEAN(mp) && !mp->m_sb.sb_inprogress) { error = xfs_initialize_perag_data(mp, sbp->sb_agcount); if (error) goto out_log_dealloc; } /* * Get and sanity-check the root inode. * Save the pointer to it in the mount structure. */ error = xfs_iget(mp, NULL, sbp->sb_rootino, 0, XFS_ILOCK_EXCL, &rip); if (error) { xfs_warn(mp, "failed to read root inode"); goto out_log_dealloc; } ASSERT(rip != NULL); if (unlikely(!S_ISDIR(VFS_I(rip)->i_mode))) { xfs_warn(mp, "corrupted root inode %llu: not a directory", (unsigned long long)rip->i_ino); xfs_iunlock(rip, XFS_ILOCK_EXCL); XFS_ERROR_REPORT("xfs_mountfs_int(2)", XFS_ERRLEVEL_LOW, mp); error = -EFSCORRUPTED; goto out_rele_rip; } mp->m_rootip = rip; /* save it */ xfs_iunlock(rip, XFS_ILOCK_EXCL); /* * Initialize realtime inode pointers in the mount structure */ error = xfs_rtmount_inodes(mp); if (error) { /* * Free up the root inode. */ xfs_warn(mp, "failed to read RT inodes"); goto out_rele_rip; } /* * If this is a read-only mount defer the superblock updates until * the next remount into writeable mode. Otherwise we would never * perform the update e.g. for the root filesystem. */ if (mp->m_update_sb && !(mp->m_flags & XFS_MOUNT_RDONLY)) { error = xfs_sync_sb(mp, false); if (error) { xfs_warn(mp, "failed to write sb changes"); goto out_rtunmount; } } /* * Initialise the XFS quota management subsystem for this mount */ if (XFS_IS_QUOTA_RUNNING(mp)) { error = xfs_qm_newmount(mp, &quotamount, &quotaflags); if (error) goto out_rtunmount; } else { ASSERT(!XFS_IS_QUOTA_ON(mp)); /* * If a file system had quotas running earlier, but decided to * mount without -o uquota/pquota/gquota options, revoke the * quotachecked license. */ if (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_ACCT) { xfs_notice(mp, "resetting quota flags"); error = xfs_mount_reset_sbqflags(mp); if (error) goto out_rtunmount; } } /* * During the second phase of log recovery, we need iget and * iput to behave like they do for an active filesystem. * xfs_fs_drop_inode needs to be able to prevent the deletion * of inodes before we're done replaying log items on those * inodes. */ mp->m_super->s_flags |= MS_ACTIVE; /* * Finish recovering the file system. This part needed to be delayed * until after the root and real-time bitmap inodes were consistently * read in. */ error = xfs_log_mount_finish(mp); if (error) { xfs_warn(mp, "log mount finish failed"); goto out_rtunmount; } /* * Now the log is fully replayed, we can transition to full read-only * mode for read-only mounts. This will sync all the metadata and clean * the log so that the recovery we just performed does not have to be * replayed again on the next mount. * * We use the same quiesce mechanism as the rw->ro remount, as they are * semantically identical operations. */ if ((mp->m_flags & (XFS_MOUNT_RDONLY|XFS_MOUNT_NORECOVERY)) == XFS_MOUNT_RDONLY) { xfs_quiesce_attr(mp); } /* * Complete the quota initialisation, post-log-replay component. */ if (quotamount) { ASSERT(mp->m_qflags == 0); mp->m_qflags = quotaflags; xfs_qm_mount_quotas(mp); } /* * Now we are mounted, reserve a small amount of unused space for * privileged transactions. This is needed so that transaction * space required for critical operations can dip into this pool * when at ENOSPC. This is needed for operations like create with * attr, unwritten extent conversion at ENOSPC, etc. Data allocations * are not allowed to use this reserved space. * * This may drive us straight to ENOSPC on mount, but that implies * we were already there on the last unmount. Warn if this occurs. */ if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { resblks = xfs_default_resblks(mp); error = xfs_reserve_blocks(mp, &resblks, NULL); if (error) xfs_warn(mp, "Unable to allocate reserve blocks. Continuing without reserve pool."); /* Recover any CoW blocks that never got remapped. */ error = xfs_reflink_recover_cow(mp); if (error) { xfs_err(mp, "Error %d recovering leftover CoW allocations.", error); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); goto out_quota; } /* Reserve AG blocks for future btree expansion. */ error = xfs_fs_reserve_ag_blocks(mp); if (error && error != -ENOSPC) goto out_agresv; } return 0; out_agresv: xfs_fs_unreserve_ag_blocks(mp); out_quota: xfs_qm_unmount_quotas(mp); out_rtunmount: mp->m_super->s_flags &= ~MS_ACTIVE; xfs_rtunmount_inodes(mp); out_rele_rip: IRELE(rip); cancel_delayed_work_sync(&mp->m_reclaim_work); xfs_reclaim_inodes(mp, SYNC_WAIT); out_log_dealloc: mp->m_flags |= XFS_MOUNT_UNMOUNTING; xfs_log_mount_cancel(mp); out_fail_wait: if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) xfs_wait_buftarg(mp->m_logdev_targp); xfs_wait_buftarg(mp->m_ddev_targp); out_free_perag: xfs_free_perag(mp); out_free_dir: xfs_da_unmount(mp); out_remove_uuid: xfs_uuid_unmount(mp); out_remove_error_sysfs: xfs_error_sysfs_del(mp); out_del_stats: xfs_sysfs_del(&mp->m_stats.xs_kobj); out_remove_sysfs: xfs_sysfs_del(&mp->m_kobj); out: return error; }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig47936.18%1322.81%
dave chinnerdave chinner22717.15%1322.81%
david chinnerdavid chinner1299.74%712.28%
eric sandeeneric sandeen1239.29%47.02%
brian fosterbrian foster1229.21%58.77%
darrick j. wongdarrick j. wong957.18%610.53%
timothy shimmintimothy shimmin473.55%11.75%
bill o'donnellbill o'donnell413.10%11.75%
carlos maiolinocarlos maiolino352.64%23.51%
glen overbyglen overby120.91%11.75%
nathan scottnathan scott90.68%23.51%
al viroal viro40.30%11.75%
zhi yong wuzhi yong wu10.08%11.75%
Total1324100.00%57100.00%

/* * This flushes out the inodes,dquots and the superblock, unmounts the * log and makes sure that incore structures are freed. */
void xfs_unmountfs( struct xfs_mount *mp) { __uint64_t resblks; int error; cancel_delayed_work_sync(&mp->m_eofblocks_work); cancel_delayed_work_sync(&mp->m_cowblocks_work); xfs_fs_unreserve_ag_blocks(mp); xfs_qm_unmount_quotas(mp); xfs_rtunmount_inodes(mp); IRELE(mp->m_rootip); /* * We can potentially deadlock here if we have an inode cluster * that has been freed has its buffer still pinned in memory because * the transaction is still sitting in a iclog. The stale inodes * on that buffer will have their flush locks held until the * transaction hits the disk and the callbacks run. the inode * flush takes the flush lock unconditionally and with nothing to * push out the iclog we will never get that unlocked. hence we * need to force the log first. */ xfs_log_force(mp, XFS_LOG_SYNC); /* * We now need to tell the world we are unmounting. This will allow * us to detect that the filesystem is going away and we should error * out anything that we have been retrying in the background. This will * prevent neverending retries in AIL pushing from hanging the unmount. */ mp->m_flags |= XFS_MOUNT_UNMOUNTING; /* * Flush all pending changes from the AIL. */ xfs_ail_push_all_sync(mp->m_ail); /* * And reclaim all inodes. At this point there should be no dirty * inodes and none should be pinned or locked, but use synchronous * reclaim just to be sure. We can stop background inode reclaim * here as well if it is still running. */ cancel_delayed_work_sync(&mp->m_reclaim_work); xfs_reclaim_inodes(mp, SYNC_WAIT); xfs_qm_unmount(mp); /* * Unreserve any blocks we have so that when we unmount we don't account * the reserved free space as used. This is really only necessary for * lazy superblock counting because it trusts the incore superblock * counters to be absolutely correct on clean unmount. * * We don't bother correcting this elsewhere for lazy superblock * counting because on mount of an unclean filesystem we reconstruct the * correct counter value and this is irrelevant. * * For non-lazy counter filesystems, this doesn't matter at all because * we only every apply deltas to the superblock and hence the incore * value does not matter.... */ resblks = 0; error = xfs_reserve_blocks(mp, &resblks, NULL); if (error) xfs_warn(mp, "Unable to free reserved block pool. " "Freespace may not be correct on next mount."); error = xfs_log_sbcount(mp); if (error) xfs_warn(mp, "Unable to update superblock counters. " "Freespace may not be correct on next mount."); xfs_log_unmount(mp); xfs_da_unmount(mp); xfs_uuid_unmount(mp); #if defined(DEBUG) xfs_errortag_clearall(mp, 0); #endif xfs_free_perag(mp); xfs_error_sysfs_del(mp); xfs_sysfs_del(&mp->m_stats.xs_kobj); xfs_sysfs_del(&mp->m_kobj); }

Contributors

PersonTokensPropCommitsCommitProp
david chinnerdavid chinner6431.37%620.69%
christoph hellwigchristoph hellwig6129.90%1034.48%
dave chinnerdave chinner209.80%310.34%
brian fosterbrian foster167.84%26.90%
darrick j. wongdarrick j. wong136.37%26.90%
carlos maiolinocarlos maiolino125.88%26.90%
bill o'donnellbill o'donnell104.90%13.45%
lachlan mcilroylachlan mcilroy41.96%13.45%
malcolm parsonsmalcolm parsons20.98%13.45%
felix blyakherfelix blyakher20.98%13.45%
Total204100.00%29100.00%

/* * Determine whether modifications can proceed. The caller specifies the minimum * freeze level for which modifications should not be allowed. This allows * certain operations to proceed while the freeze sequence is in progress, if * necessary. */
bool xfs_fs_writable( struct xfs_mount *mp, int level) { ASSERT(level > SB_UNFROZEN); if ((mp->m_super->s_writers.frozen >= level) || XFS_FORCED_SHUTDOWN(mp) || (mp->m_flags & XFS_MOUNT_RDONLY)) return false; return true; }

Contributors

PersonTokensPropCommitsCommitProp
brian fosterbrian foster2445.28%120.00%
david chinnerdavid chinner1935.85%120.00%
jan karajan kara611.32%120.00%
christoph hellwigchristoph hellwig47.55%240.00%
Total53100.00%5100.00%

/* * xfs_log_sbcount * * Sync the superblock counters to disk. * * Note this code can be called during the process of freezing, so we use the * transaction allocator that does not block when the transaction subsystem is * in its frozen state. */
int xfs_log_sbcount(xfs_mount_t *mp) { /* allow this to proceed during the freeze sequence... */ if (!xfs_fs_writable(mp, SB_FREEZE_COMPLETE)) return 0; /* * we don't need to do this if we are updating the superblock * counters on every modification. */ if (!xfs_sb_version_haslazysbcount(&mp->m_sb)) return 0; return xfs_sync_sb(mp, true); }

Contributors

PersonTokensPropCommitsCommitProp
david chinnerdavid chinner4086.96%133.33%
brian fosterbrian foster36.52%133.33%
dave chinnerdave chinner36.52%133.33%
Total46100.00%3100.00%

/* * Deltas for the inode count are +/-64, hence we use a large batch size * of 128 so we don't need to take the counter lock on every update. */ #define XFS_ICOUNT_BATCH 128
int xfs_mod_icount( struct xfs_mount *mp, int64_t delta) { __percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH); if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) { ASSERT(0); percpu_counter_add(&mp->m_icount, -delta); return -EINVAL; } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
david chinnerdavid chinner6293.94%150.00%
dave chinnerdave chinner46.06%150.00%
Total66100.00%2100.00%


int xfs_mod_ifree( struct xfs_mount *mp, int64_t delta) { percpu_counter_add(&mp->m_ifree, delta); if (percpu_counter_compare(&mp->m_ifree, 0) < 0) { ASSERT(0); percpu_counter_add(&mp->m_ifree, -delta); return -EINVAL; } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
dave chinnerdave chinner62100.00%1100.00%
Total62100.00%1100.00%

/* * Deltas for the block count can vary from 1 to very large, but lock contention * only occurs on frequent small block count updates such as in the delayed * allocation path for buffered writes (page a time updates). Hence we set * a large batch count (1024) to minimise global counter updates except when * we get near to ENOSPC and we have to be very accurate with our updates. */ #define XFS_FDBLOCKS_BATCH 1024
int xfs_mod_fdblocks( struct xfs_mount *mp, int64_t delta, bool rsvd) { int64_t lcounter; long long res_used; s32 batch; if (delta > 0) { /* * If the reserve pool is depleted, put blocks back into it * first. Most of the time the pool is full. */ if (likely(mp->m_resblks == mp->m_resblks_avail)) { percpu_counter_add(&mp->m_fdblocks, delta); return 0; } spin_lock(&mp->m_sb_lock); res_used = (long long)(mp->m_resblks - mp->m_resblks_avail); if (res_used > delta) { mp->m_resblks_avail += delta; } else { delta -= res_used; mp->m_resblks_avail = mp->m_resblks; percpu_counter_add(&mp->m_fdblocks, delta); } spin_unlock(&mp->m_sb_lock); return 0; } /* * Taking blocks away, need to be more accurate the closer we * are to zero. * * If the counter has a value of less than 2 * max batch size, * then make everything serialise as we are real close to * ENOSPC. */ if (__percpu_counter_compare(&mp->m_fdblocks, 2 * XFS_FDBLOCKS_BATCH, XFS_FDBLOCKS_BATCH) < 0) batch = 1; else batch = XFS_FDBLOCKS_BATCH; __percpu_counter_add(&mp->m_fdblocks, delta, batch); if (__percpu_counter_compare(&mp->m_fdblocks, mp->m_alloc_set_aside, XFS_FDBLOCKS_BATCH) >= 0) { /* we had space! */ return 0; } /* * lock up the sb for dipping into reserves before releasing the space * that took us to ENOSPC. */ spin_lock(&mp->m_sb_lock); percpu_counter_add(&mp->m_fdblocks, -delta); if (!rsvd) goto fdblocks_enospc; lcounter = (long long)mp->m_resblks_avail + delta; if (lcounter >= 0) { mp->m_resblks_avail = lcounter; spin_unlock(&mp->m_sb_lock); return 0; } printk_once(KERN_WARNING "Filesystem \"%s\": reserve blocks depleted! " "Consider increasing reserve pool size.", mp->m_fsname); fdblocks_enospc: spin_unlock(&mp->m_sb_lock); return -ENOSPC; }

Contributors

PersonTokensPropCommitsCommitProp
david chinnerdavid chinner16757.39%450.00%
christoph hellwigchristoph hellwig11238.49%112.50%
dave chinnerdave chinner103.44%225.00%
darrick j. wongdarrick j. wong20.69%112.50%
Total291100.00%8100.00%


int xfs_mod_frextents( struct xfs_mount *mp, int64_t delta) { int64_t lcounter; int ret = 0; spin_lock(&mp->m_sb_lock); lcounter = mp->m_sb.sb_frextents + delta; if (lcounter < 0) ret = -ENOSPC; else mp->m_sb.sb_frextents = lcounter; spin_unlock(&mp->m_sb_lock); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
dave chinnerdave chinner70100.00%1100.00%
Total70100.00%1100.00%

/* * xfs_getsb() is called to obtain the buffer for the superblock. * The buffer is returned locked and read in from disk. * The buffer should be released with a call to xfs_brelse(). * * If the flags parameter is BUF_TRYLOCK, then we'll only return * the superblock buffer if it can be locked without sleeping. * If it can't then we'll return NULL. */
struct xfs_buf * xfs_getsb( struct xfs_mount *mp, int flags) { struct xfs_buf *bp = mp->m_sb_bp; if (!xfs_buf_trylock(bp)) { if (flags & XBF_TRYLOCK) return NULL; xfs_buf_lock(bp); } xfs_buf_hold(bp); ASSERT(bp->b_flags & XBF_DONE); return bp; }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig6092.31%250.00%
dave chinnerdave chinner46.15%125.00%
chandra seetharamanchandra seetharaman11.54%125.00%
Total65100.00%4100.00%

/* * Used to free the superblock along various error paths. */
void xfs_freesb( struct xfs_mount *mp) { struct xfs_buf *bp = mp->m_sb_bp; xfs_buf_lock(bp); mp->m_sb_bp = NULL; xfs_buf_relse(bp); }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig2160.00%150.00%
dave chinnerdave chinner1440.00%150.00%
Total35100.00%2100.00%

/* * If the underlying (data/log/rt) device is readonly, there are some * operations that cannot proceed. */
int xfs_dev_is_read_only( struct xfs_mount *mp, char *message) { if (xfs_readonly_buftarg(mp->m_ddev_targp) || xfs_readonly_buftarg(mp->m_logdev_targp) || (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp))) { xfs_notice(mp, "%s required on read-only device.", message); xfs_notice(mp, "write access unavailable, cannot proceed."); return -EROFS; } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig6189.71%133.33%
dave chinnerdave chinner710.29%266.67%
Total68100.00%3100.00%


Overall Contributors

PersonTokensPropCommitsCommitProp
christoph hellwigchristoph hellwig153233.55%2417.27%
dave chinnerdave chinner144831.71%4129.50%
david chinnerdavid chinner52411.48%1510.79%
eric sandeeneric sandeen4159.09%107.19%
brian fosterbrian foster1703.72%85.76%
darrick j. wongdarrick j. wong1583.46%117.91%
bill o'donnellbill o'donnell511.12%10.72%
timothy shimmintimothy shimmin471.03%10.72%
carlos maiolinocarlos maiolino471.03%21.44%
russell cattelanrussell cattelan400.88%10.72%
nathan scottnathan scott360.79%85.76%
jeff liujeff liu270.59%32.16%
lucas stachlucas stach220.48%10.72%
glen overbyglen overby120.26%10.72%
john krueger* (same as john keller?)*john krueger* (same as john keller?)*80.18%10.72%
chandra seetharamanchandra seetharaman60.13%21.44%
jan karajan kara60.13%10.72%
lachlan mcilroylachlan mcilroy40.09%10.72%
al viroal viro40.09%10.72%
zhi yong wuzhi yong wu20.04%21.44%
stephen lordstephen lord20.04%10.72%
malcolm parsonsmalcolm parsons20.04%10.72%
felix blyakherfelix blyakher20.04%10.72%
kirill a. shutemovkirill a. shutemov10.02%10.72%
Total4566100.00%139100.00%
Directory: fs/xfs
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.