#include "xfs_defer.h"
#include "xfs_log_format.h"
#include "xfs_trans.h"
- int tag)
+#include "xfs_trace.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+
+
+/*
+ * Passive reference counting access wrappers to the perag structures. If the
+ * per-ag structure is to be freed, the freeing code is responsible for cleaning
+ * up objects with passive references before freeing the structure. This is
+ * things like cached buffers.
+ */
+struct xfs_perag *
+xfs_perag_get(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agno)
+{
+ struct xfs_perag *pag;
+ int ref = 0;
+
+ rcu_read_lock();
+ pag = radix_tree_lookup(&mp->m_perag_tree, agno);
+ if (pag) {
+ ASSERT(atomic_read(&pag->pag_ref) >= 0);
+ ref = atomic_inc_return(&pag->pag_ref);
+ }
+ rcu_read_unlock();
+ trace_xfs_perag_get(mp, agno, ref, _RET_IP_);
+ return pag;
+}
+
+/*
+ * search from @first to find the next perag with the given tag set.
+ */
+struct xfs_perag *
+xfs_perag_get_tag(
+ struct xfs_mount *mp,
+ xfs_agnumber_t first,
++ unsigned int tag)
+{
+ struct xfs_perag *pag;
+ int found;
+ int ref;
+
+ rcu_read_lock();
+ found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
+ (void **)&pag, first, 1, tag);
+ if (found <= 0) {
+ rcu_read_unlock();
+ return NULL;
+ }
+ ref = atomic_inc_return(&pag->pag_ref);
+ rcu_read_unlock();
+ trace_xfs_perag_get_tag(mp, pag->pag_agno, ref, _RET_IP_);
+ return pag;
+}
+
+void
+xfs_perag_put(
+ struct xfs_perag *pag)
+{
+ int ref;
+
+ ASSERT(atomic_read(&pag->pag_ref) > 0);
+ ref = atomic_dec_return(&pag->pag_ref);
+ trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_);
+}
+
+/*
+ * xfs_initialize_perag_data
+ *
+ * Read in each per-ag structure so we can count up the number of
+ * allocated inodes, free inodes and used filesystem blocks as this
+ * information is no longer persistent in the superblock. Once we have
+ * this information, write it into the in-core superblock structure.
+ */
+int
+xfs_initialize_perag_data(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agcount)
+{
+ xfs_agnumber_t index;
+ struct xfs_perag *pag;
+ struct xfs_sb *sbp = &mp->m_sb;
+ uint64_t ifree = 0;
+ uint64_t ialloc = 0;
+ uint64_t bfree = 0;
+ uint64_t bfreelst = 0;
+ uint64_t btree = 0;
+ uint64_t fdblocks;
+ int error = 0;
+
+ for (index = 0; index < agcount; index++) {
+ /*
+ * read the agf, then the agi. This gets us
+ * all the information we need and populates the
+ * per-ag structures for us.
+ */
+ error = xfs_alloc_pagf_init(mp, NULL, index, 0);
+ if (error)
+ return error;
+
+ error = xfs_ialloc_pagi_init(mp, NULL, index);
+ if (error)
+ return error;
+ pag = xfs_perag_get(mp, index);
+ ifree += pag->pagi_freecount;
+ ialloc += pag->pagi_count;
+ bfree += pag->pagf_freeblks;
+ bfreelst += pag->pagf_flcount;
+ btree += pag->pagf_btreeblks;
+ xfs_perag_put(pag);
+ }
+ fdblocks = bfree + bfreelst + btree;
+
+ /*
+ * If the new summary counts are obviously incorrect, fail the
+ * mount operation because that implies the AGFs are also corrupt.
+ * Clear FS_COUNTERS so that we don't unmount with a dirty log, which
+ * will prevent xfs_repair from fixing anything.
+ */
+ if (fdblocks > sbp->sb_dblocks || ifree > ialloc) {
+ xfs_alert(mp, "AGF corruption. Please run xfs_repair.");
+ error = -EFSCORRUPTED;
+ goto out;
+ }
+
+ /* Overwrite incore superblock counters with just-read data */
+ spin_lock(&mp->m_sb_lock);
+ sbp->sb_ifree = ifree;
+ sbp->sb_icount = ialloc;
+ sbp->sb_fdblocks = fdblocks;
+ spin_unlock(&mp->m_sb_lock);
+
+ xfs_reinit_percpu_counters(mp);
+out:
+ xfs_fs_mark_healthy(mp, XFS_SICK_FS_COUNTERS);
+ return error;
+}
+
+STATIC void
+__xfs_free_perag(
+ struct rcu_head *head)
+{
+ struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head);
+
+ ASSERT(!delayed_work_pending(&pag->pag_blockgc_work));
+ ASSERT(atomic_read(&pag->pag_ref) == 0);
+ kmem_free(pag);
+}
+
+/*
+ * Free up the per-ag resources associated with the mount structure.
+ */
+void
+xfs_free_perag(
+ struct xfs_mount *mp)
+{
+ struct xfs_perag *pag;
+ xfs_agnumber_t agno;
+
+ 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);
+
+ cancel_delayed_work_sync(&pag->pag_blockgc_work);
+ xfs_iunlink_destroy(pag);
+ xfs_buf_hash_destroy(pag);
+
+ call_rcu(&pag->rcu_head, __xfs_free_perag);
+ }
+}
+
+int
+xfs_initialize_perag(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agcount,
+ xfs_agnumber_t *maxagi)
+{
+ struct xfs_perag *pag;
+ xfs_agnumber_t index;
+ xfs_agnumber_t first_initialised = NULLAGNUMBER;
+ int error;
+
+ /*
+ * 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;
+ }
+
+ pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL);
+ if (!pag) {
+ error = -ENOMEM;
+ goto out_unwind_new_pags;
+ }
+ pag->pag_agno = index;
+ pag->pag_mount = mp;
+
+ error = radix_tree_preload(GFP_NOFS);
+ if (error)
+ goto out_free_pag;
+
+ spin_lock(&mp->m_perag_lock);
+ if (radix_tree_insert(&mp->m_perag_tree, index, pag)) {
+ WARN_ON_ONCE(1);
+ spin_unlock(&mp->m_perag_lock);
+ radix_tree_preload_end();
+ error = -EEXIST;
+ goto out_free_pag;
+ }
+ spin_unlock(&mp->m_perag_lock);
+ radix_tree_preload_end();
+
+ /* Place kernel structure only init below this point. */
+ spin_lock_init(&pag->pag_ici_lock);
+ spin_lock_init(&pag->pagb_lock);
+ spin_lock_init(&pag->pag_state_lock);
+ INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker);
+ INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
+ init_waitqueue_head(&pag->pagb_wait);
+ pag->pagb_count = 0;
+ pag->pagb_tree = RB_ROOT;
+
+ error = xfs_buf_hash_init(pag);
+ if (error)
+ goto out_remove_pag;
+
+ error = xfs_iunlink_init(pag);
+ if (error)
+ goto out_hash_destroy;
+
+ /* first new pag is fully initialized */
+ if (first_initialised == NULLAGNUMBER)
+ first_initialised = index;
+ }
+
+ index = xfs_set_inode_alloc(mp, agcount);
+
+ if (maxagi)
+ *maxagi = index;
+
+ mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp);
+ return 0;
+
+out_hash_destroy:
+ xfs_buf_hash_destroy(pag);
+out_remove_pag:
+ radix_tree_delete(&mp->m_perag_tree, index);
+out_free_pag:
+ kmem_free(pag);
+out_unwind_new_pags:
+ /* unwind any prior newly initialized pags */
+ for (index = first_initialised; index < agcount; index++) {
+ pag = radix_tree_delete(&mp->m_perag_tree, index);
+ if (!pag)
+ break;
+ xfs_buf_hash_destroy(pag);
+ xfs_iunlink_destroy(pag);
+ kmem_free(pag);
+ }
+ return error;
+}
static int
xfs_get_aghdr_buf(
struct xfs_mount;
struct xfs_trans;
- int xfs_initialize_perag_data(struct xfs_mount *, xfs_agnumber_t);
+struct xfs_perag;
+
+/*
+ * Per-ag infrastructure
+ */
+
+/* per-AG block reservation data structures*/
+struct xfs_ag_resv {
+ /* number of blocks originally reserved here */
+ xfs_extlen_t ar_orig_reserved;
+ /* number of blocks reserved here */
+ xfs_extlen_t ar_reserved;
+ /* number of blocks originally asked for */
+ xfs_extlen_t ar_asked;
+};
+
+/*
+ * Per-ag incore structure, copies of information in agf and agi, to improve the
+ * performance of allocation group selection.
+ */
+struct xfs_perag {
+ struct xfs_mount *pag_mount; /* owner filesystem */
+ xfs_agnumber_t pag_agno; /* AG this structure belongs to */
+ atomic_t pag_ref; /* perag reference count */
+ char pagf_init; /* this agf's entry is initialized */
+ char pagi_init; /* this agi's entry is initialized */
+ char pagf_metadata; /* the agf is preferred to be metadata */
+ char pagi_inodeok; /* The agi is ok for inodes */
+ uint8_t pagf_levels[XFS_BTNUM_AGF];
+ /* # of levels in bno & cnt btree */
+ bool pagf_agflreset; /* agfl requires reset before use */
+ uint32_t pagf_flcount; /* count of blocks in freelist */
+ xfs_extlen_t pagf_freeblks; /* total free blocks */
+ xfs_extlen_t pagf_longest; /* longest free space */
+ uint32_t pagf_btreeblks; /* # of blocks held in AGF btrees */
+ xfs_agino_t pagi_freecount; /* number of free inodes */
+ xfs_agino_t pagi_count; /* number of allocated inodes */
+
+ /*
+ * Inode allocation search lookup optimisation.
+ * If the pagino matches, the search for new inodes
+ * doesn't need to search the near ones again straight away
+ */
+ xfs_agino_t pagl_pagino;
+ xfs_agino_t pagl_leftrec;
+ xfs_agino_t pagl_rightrec;
+
+ int pagb_count; /* pagb slots in use */
+ uint8_t pagf_refcount_level; /* recount btree height */
+
+ /* Blocks reserved for all kinds of metadata. */
+ struct xfs_ag_resv pag_meta_resv;
+ /* Blocks reserved for the reverse mapping btree. */
+ struct xfs_ag_resv pag_rmapbt_resv;
+
+ /* -- kernel only structures below this line -- */
+
+ /*
+ * Bitsets of per-ag metadata that have been checked and/or are sick.
+ * Callers should hold pag_state_lock before accessing this field.
+ */
+ uint16_t pag_checked;
+ uint16_t pag_sick;
+ spinlock_t pag_state_lock;
+
+ spinlock_t pagb_lock; /* lock for pagb_tree */
+ struct rb_root pagb_tree; /* ordered tree of busy extents */
+ unsigned int pagb_gen; /* generation count for pagb_tree */
+ wait_queue_head_t pagb_wait; /* woken when pagb_gen changes */
+
+ atomic_t pagf_fstrms; /* # of filestreams active in this AG */
+
+ spinlock_t pag_ici_lock; /* incore inode cache lock */
+ struct radix_tree_root pag_ici_root; /* incore inode cache root */
+ int pag_ici_reclaimable; /* reclaimable inodes */
+ unsigned long pag_ici_reclaim_cursor; /* reclaim restart point */
+
+ /* buffer cache index */
+ spinlock_t pag_buf_lock; /* lock for pag_buf_hash */
+ struct rhashtable pag_buf_hash;
+
+ /* for rcu-safe freeing */
+ struct rcu_head rcu_head;
+
+ /* background prealloc block trimming */
+ struct delayed_work pag_blockgc_work;
+
+ /*
+ * Unlinked inode information. This incore information reflects
+ * data stored in the AGI, so callers must hold the AGI buffer lock
+ * or have some other means to control concurrency.
+ */
+ struct rhashtable pagi_unlinked_hash;
+};
+
+int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount,
+ xfs_agnumber_t *maxagi);
- struct xfs_perag *xfs_perag_get(struct xfs_mount *, xfs_agnumber_t);
- struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *, xfs_agnumber_t,
- int tag);
- void xfs_perag_put(struct xfs_perag *pag);
++int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno);
+void xfs_free_perag(struct xfs_mount *mp);
+
++struct xfs_perag *xfs_perag_get(struct xfs_mount *mp, xfs_agnumber_t agno);
++struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *mp, xfs_agnumber_t agno,
++ unsigned int tag);
++void xfs_perag_put(struct xfs_perag *pag);
+
+/*
+ * Perag iteration APIs
+ *
+ * XXX: for_each_perag_range() usage really needs an iterator to clean up when
+ * we terminate at end_agno because we may have taken a reference to the perag
+ * beyond end_agno. Right now callers have to be careful to catch and clean that
+ * up themselves. This is not necessary for the callers of for_each_perag() and
+ * for_each_perag_from() because they terminate at sb_agcount where there are
+ * no perag structures in tree beyond end_agno.
+ */
+#define for_each_perag_range(mp, next_agno, end_agno, pag) \
+ for ((pag) = xfs_perag_get((mp), (next_agno)); \
+ (pag) != NULL && (next_agno) <= (end_agno); \
+ (next_agno) = (pag)->pag_agno + 1, \
+ xfs_perag_put(pag), \
+ (pag) = xfs_perag_get((mp), (next_agno)))
+
+#define for_each_perag_from(mp, next_agno, pag) \
+ for_each_perag_range((mp), (next_agno), (mp)->m_sb.sb_agcount, (pag))
+
+
+#define for_each_perag(mp, agno, pag) \
+ (agno) = 0; \
+ for_each_perag_from((mp), (agno), (pag))
+
+#define for_each_perag_tag(mp, agno, pag, tag) \
+ for ((agno) = 0, (pag) = xfs_perag_get_tag((mp), 0, (tag)); \
+ (pag) != NULL; \
+ (agno) = (pag)->pag_agno + 1, \
+ xfs_perag_put(pag), \
+ (pag) = xfs_perag_get_tag((mp), (agno), (tag)))
struct aghdr_init_data {
/* per ag data */
projects / users / hch / configfs.git / commitdiff