From: Dave Chinner Date: Tue, 9 May 2023 09:29:49 +0000 (+0200) Subject: xfs: perags need atomic operational state X-Git-Tag: v6.3.0~31 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=03dc2ef2a52715ca7557b9c35b0d39ee1ccddfff;p=thirdparty%2Fxfsprogs-dev.git xfs: perags need atomic operational state Source kernel commit: 7ac2ff8bb3713c7cb43564c04384af2ee7cc1f8d We currently don't have any flags or operational state in the xfs_perag except for the pagf_init and pagi_init flags. And the agflreset flag. Oh, there's also the pagf_metadata and pagi_inodeok flags, too. For controlling per-ag operations, we are going to need some atomic state flags. Hence add an opstate field similar to what we already have in the mount and log, and convert all these state flags across to atomic bit operations. Signed-off-by: Dave Chinner Reviewed-by: Allison Henderson Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- diff --git a/include/libxfs.h b/include/libxfs.h index 915bf5113..b28781d19 100644 --- a/include/libxfs.h +++ b/include/libxfs.h @@ -17,6 +17,7 @@ #include "bitops.h" #include "kmem.h" #include "libfrog/radix-tree.h" +#include "libfrog/bitmask.h" #include "atomic.h" #include "spinlock.h" diff --git a/libfrog/bitmask.h b/libfrog/bitmask.h new file mode 100644 index 000000000..719a6bfd2 --- /dev/null +++ b/libfrog/bitmask.h @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2000-2005 Silicon Graphics, Inc. + * All Rights Reserved. + */ +#ifndef __LIBFROG_BITMASK_H_ +#define __LIBFROG_BITMASK_H_ + +#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) +#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) + +static inline void set_bit(int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + + *p |= mask; +} + +static inline void clear_bit(int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + + *p &= ~mask; +} + +static inline int test_bit(int nr, const volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + + return *p & mask; +} + +/* Sets and returns original value of the bit */ +static inline int test_and_set_bit(int nr, volatile unsigned long *addr) +{ + if (test_bit(nr, addr)) + return 1; + set_bit(nr, addr); + return 0; +} + +#endif /* __LIBFROG_BITMASK_H_ */ diff --git a/libxfs/init.c b/libxfs/init.c index ae9636a8c..fda36ba0f 100644 --- a/libxfs/init.c +++ b/libxfs/init.c @@ -498,6 +498,32 @@ rtmount_init( return 0; } +static bool +xfs_set_inode_alloc_perag( + struct xfs_perag *pag, + xfs_ino_t ino, + xfs_agnumber_t max_metadata) +{ + if (!xfs_is_inode32(pag->pag_mount)) { + set_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate); + clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate); + return false; + } + + if (ino > XFS_MAXINUMBER_32) { + clear_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate); + clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate); + return false; + } + + set_bit(XFS_AGSTATE_ALLOWS_INODES, &pag->pag_opstate); + if (pag->pag_agno < max_metadata) + set_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate); + else + clear_bit(XFS_AGSTATE_PREFERS_METADATA, &pag->pag_opstate); + return true; +} + /* * Set parameters for inode allocation heuristics, taking into account * filesystem size and inode32/inode64 mount options; i.e. specifically @@ -554,9 +580,9 @@ xfs_set_inode_alloc( * the allocator to accommodate the request. */ if (xfs_has_small_inums(mp) && ino > XFS_MAXINUMBER_32) - xfs_set_inode32(mp); + set_bit(XFS_OPSTATE_INODE32, &mp->m_opstate); else - xfs_clear_inode32(mp); + clear_bit(XFS_OPSTATE_INODE32, &mp->m_opstate); for (index = 0; index < agcount; index++) { struct xfs_perag *pag; @@ -564,24 +590,8 @@ xfs_set_inode_alloc( ino = XFS_AGINO_TO_INO(mp, index, agino); pag = xfs_perag_get(mp, index); - - if (xfs_is_inode32(mp)) { - if (ino > XFS_MAXINUMBER_32) { - pag->pagi_inodeok = 0; - pag->pagf_metadata = 0; - } else { - pag->pagi_inodeok = 1; - maxagi++; - if (index < max_metadata) - pag->pagf_metadata = 1; - else - pag->pagf_metadata = 0; - } - } else { - pag->pagi_inodeok = 1; - pag->pagf_metadata = 0; - } - + if (xfs_set_inode_alloc_perag(pag, ino, max_metadata)) + maxagi++; xfs_perag_put(pag); } diff --git a/libxfs/libxfs_priv.h b/libxfs/libxfs_priv.h index 456c82d70..32a6be124 100644 --- a/libxfs/libxfs_priv.h +++ b/libxfs/libxfs_priv.h @@ -47,6 +47,7 @@ #include "bitops.h" #include "kmem.h" #include "libfrog/radix-tree.h" +#include "libfrog/bitmask.h" #include "atomic.h" #include "spinlock.h" #include "linux-err.h" @@ -630,42 +631,6 @@ unsigned int hweight8(unsigned int w); unsigned int hweight32(unsigned int w); unsigned int hweight64(__u64 w); -#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG)) -#define BIT_WORD(nr) ((nr) / BITS_PER_LONG) - -static inline void set_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - *p |= mask; -} - -static inline void clear_bit(int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - *p &= ~mask; -} - -static inline int test_bit(int nr, const volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - return *p & mask; -} - -/* Sets and returns original value of the bit */ -static inline int test_and_set_bit(int nr, volatile unsigned long *addr) -{ - if (test_bit(nr, addr)) - return 1; - set_bit(nr, addr); - return 0; -} - static inline int xfs_buf_hash_init(struct xfs_perag *pag) { return 0; } static inline void xfs_buf_hash_destroy(struct xfs_perag *pag) { } diff --git a/libxfs/xfs_ag.h b/libxfs/xfs_ag.h index aeb21c8df..187d30d9b 100644 --- a/libxfs/xfs_ag.h +++ b/libxfs/xfs_ag.h @@ -35,13 +35,9 @@ struct xfs_perag { atomic_t pag_ref; /* passive reference count */ atomic_t pag_active_ref; /* active reference count */ wait_queue_head_t pag_active_wq;/* woken active_ref falls to zero */ - 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 */ + unsigned long pag_opstate; 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 */ @@ -108,6 +104,27 @@ struct xfs_perag { #endif /* __KERNEL__ */ }; +/* + * Per-AG operational state. These are atomic flag bits. + */ +#define XFS_AGSTATE_AGF_INIT 0 +#define XFS_AGSTATE_AGI_INIT 1 +#define XFS_AGSTATE_PREFERS_METADATA 2 +#define XFS_AGSTATE_ALLOWS_INODES 3 +#define XFS_AGSTATE_AGFL_NEEDS_RESET 4 + +#define __XFS_AG_OPSTATE(name, NAME) \ +static inline bool xfs_perag_ ## name (struct xfs_perag *pag) \ +{ \ + return test_bit(XFS_AGSTATE_ ## NAME, &pag->pag_opstate); \ +} + +__XFS_AG_OPSTATE(initialised_agf, AGF_INIT) +__XFS_AG_OPSTATE(initialised_agi, AGI_INIT) +__XFS_AG_OPSTATE(prefers_metadata, PREFERS_METADATA) +__XFS_AG_OPSTATE(allows_inodes, ALLOWS_INODES) +__XFS_AG_OPSTATE(agfl_needs_reset, AGFL_NEEDS_RESET) + int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount, xfs_rfsblock_t dcount, xfs_agnumber_t *maxagi); int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno); diff --git a/libxfs/xfs_alloc.c b/libxfs/xfs_alloc.c index 82449ba97..db24632e9 100644 --- a/libxfs/xfs_alloc.c +++ b/libxfs/xfs_alloc.c @@ -2431,7 +2431,7 @@ xfs_agfl_reset( struct xfs_mount *mp = tp->t_mountp; struct xfs_agf *agf = agbp->b_addr; - ASSERT(pag->pagf_agflreset); + ASSERT(xfs_perag_agfl_needs_reset(pag)); trace_xfs_agfl_reset(mp, agf, 0, _RET_IP_); xfs_warn(mp, @@ -2446,7 +2446,7 @@ xfs_agfl_reset( XFS_AGF_FLCOUNT); pag->pagf_flcount = 0; - pag->pagf_agflreset = false; + clear_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate); } /* @@ -2601,7 +2601,7 @@ xfs_alloc_fix_freelist( /* deferred ops (AGFL block frees) require permanent transactions */ ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); - if (!pag->pagf_init) { + if (!xfs_perag_initialised_agf(pag)) { error = xfs_alloc_read_agf(pag, tp, flags, &agbp); if (error) { /* Couldn't lock the AGF so skip this AG. */ @@ -2616,7 +2616,8 @@ xfs_alloc_fix_freelist( * somewhere else if we are not being asked to try harder at this * point */ - if (pag->pagf_metadata && (args->datatype & XFS_ALLOC_USERDATA) && + if (xfs_perag_prefers_metadata(pag) && + (args->datatype & XFS_ALLOC_USERDATA) && (flags & XFS_ALLOC_FLAG_TRYLOCK)) { ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING)); goto out_agbp_relse; @@ -2642,7 +2643,7 @@ xfs_alloc_fix_freelist( } /* reset a padding mismatched agfl before final free space check */ - if (pag->pagf_agflreset) + if (xfs_perag_agfl_needs_reset(pag)) xfs_agfl_reset(tp, agbp, pag); /* If there isn't enough total space or single-extent, reject it. */ @@ -2799,7 +2800,7 @@ xfs_alloc_get_freelist( if (be32_to_cpu(agf->agf_flfirst) == xfs_agfl_size(mp)) agf->agf_flfirst = 0; - ASSERT(!pag->pagf_agflreset); + ASSERT(!xfs_perag_agfl_needs_reset(pag)); be32_add_cpu(&agf->agf_flcount, -1); pag->pagf_flcount--; @@ -2888,7 +2889,7 @@ xfs_alloc_put_freelist( if (be32_to_cpu(agf->agf_fllast) == xfs_agfl_size(mp)) agf->agf_fllast = 0; - ASSERT(!pag->pagf_agflreset); + ASSERT(!xfs_perag_agfl_needs_reset(pag)); be32_add_cpu(&agf->agf_flcount, 1); pag->pagf_flcount++; @@ -3095,7 +3096,7 @@ xfs_alloc_read_agf( return error; agf = agfbp->b_addr; - if (!pag->pagf_init) { + if (!xfs_perag_initialised_agf(pag)) { pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks); pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks); pag->pagf_flcount = be32_to_cpu(agf->agf_flcount); @@ -3107,8 +3108,8 @@ xfs_alloc_read_agf( pag->pagf_levels[XFS_BTNUM_RMAPi] = be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]); pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level); - pag->pagf_init = 1; - pag->pagf_agflreset = xfs_agfl_needs_reset(pag->pag_mount, agf); + if (xfs_agfl_needs_reset(pag->pag_mount, agf)) + set_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate); /* * Update the in-core allocbt counter. Filter out the rmapbt @@ -3123,6 +3124,8 @@ xfs_alloc_read_agf( if (allocbt_blks > 0) atomic64_add(allocbt_blks, &pag->pag_mount->m_allocbt_blks); + + set_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate); } #ifdef DEBUG else if (!xfs_is_shutdown(pag->pag_mount)) { diff --git a/libxfs/xfs_alloc_btree.c b/libxfs/xfs_alloc_btree.c index 0d4a12494..f4ee585e9 100644 --- a/libxfs/xfs_alloc_btree.c +++ b/libxfs/xfs_alloc_btree.c @@ -313,7 +313,7 @@ xfs_allocbt_verify( level = be16_to_cpu(block->bb_level); if (bp->b_ops->magic[0] == cpu_to_be32(XFS_ABTC_MAGIC)) btnum = XFS_BTNUM_CNTi; - if (pag && pag->pagf_init) { + if (pag && xfs_perag_initialised_agf(pag)) { if (level >= pag->pagf_levels[btnum]) return __this_address; } else if (level >= mp->m_alloc_maxlevels) diff --git a/libxfs/xfs_bmap.c b/libxfs/xfs_bmap.c index 7ca1ff15b..badc15054 100644 --- a/libxfs/xfs_bmap.c +++ b/libxfs/xfs_bmap.c @@ -3140,7 +3140,7 @@ xfs_bmap_longest_free_extent( int error = 0; pag = xfs_perag_get(mp, ag); - if (!pag->pagf_init) { + if (!xfs_perag_initialised_agf(pag)) { error = xfs_alloc_read_agf(pag, tp, XFS_ALLOC_FLAG_TRYLOCK, NULL); if (error) { diff --git a/libxfs/xfs_ialloc.c b/libxfs/xfs_ialloc.c index d17825560..73add3b38 100644 --- a/libxfs/xfs_ialloc.c +++ b/libxfs/xfs_ialloc.c @@ -993,8 +993,8 @@ xfs_dialloc_ag_inobt( int i, j; int searchdistance = 10; - ASSERT(pag->pagi_init); - ASSERT(pag->pagi_inodeok); + ASSERT(xfs_perag_initialised_agi(pag)); + ASSERT(xfs_perag_allows_inodes(pag)); ASSERT(pag->pagi_freecount > 0); restart_pagno: @@ -1587,10 +1587,10 @@ xfs_dialloc_good_ag( if (!pag) return false; - if (!pag->pagi_inodeok) + if (!xfs_perag_allows_inodes(pag)) return false; - if (!pag->pagi_init) { + if (!xfs_perag_initialised_agi(pag)) { error = xfs_ialloc_read_agi(pag, tp, NULL); if (error) return false; @@ -1601,7 +1601,7 @@ xfs_dialloc_good_ag( if (!ok_alloc) return false; - if (!pag->pagf_init) { + if (!xfs_perag_initialised_agf(pag)) { error = xfs_alloc_read_agf(pag, tp, flags, NULL); if (error) return false; @@ -2598,10 +2598,10 @@ xfs_ialloc_read_agi( return error; agi = agibp->b_addr; - if (!pag->pagi_init) { + if (!xfs_perag_initialised_agi(pag)) { pag->pagi_freecount = be32_to_cpu(agi->agi_freecount); pag->pagi_count = be32_to_cpu(agi->agi_count); - pag->pagi_init = 1; + set_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate); } /* diff --git a/libxfs/xfs_ialloc_btree.c b/libxfs/xfs_ialloc_btree.c index 1f0840883..cc4f6d6e1 100644 --- a/libxfs/xfs_ialloc_btree.c +++ b/libxfs/xfs_ialloc_btree.c @@ -290,8 +290,8 @@ xfs_inobt_verify( * Similarly, during log recovery we will have a perag structure * attached, but the agi information will not yet have been initialised * from the on disk AGI. We don't currently use any of this information, - * but beware of the landmine (i.e. need to check pag->pagi_init) if we - * ever do. + * but beware of the landmine (i.e. need to check + * xfs_perag_initialised_agi(pag)) if we ever do. */ if (xfs_has_crc(mp)) { fa = xfs_btree_sblock_v5hdr_verify(bp); diff --git a/libxfs/xfs_refcount_btree.c b/libxfs/xfs_refcount_btree.c index 983d4276d..a91026037 100644 --- a/libxfs/xfs_refcount_btree.c +++ b/libxfs/xfs_refcount_btree.c @@ -226,7 +226,7 @@ xfs_refcountbt_verify( return fa; level = be16_to_cpu(block->bb_level); - if (pag && pag->pagf_init) { + if (pag && xfs_perag_initialised_agf(pag)) { if (level >= pag->pagf_refcount_level) return __this_address; } else if (level >= mp->m_refc_maxlevels) diff --git a/libxfs/xfs_rmap_btree.c b/libxfs/xfs_rmap_btree.c index d2d184304..a7e6e652f 100644 --- a/libxfs/xfs_rmap_btree.c +++ b/libxfs/xfs_rmap_btree.c @@ -311,7 +311,7 @@ xfs_rmapbt_verify( return fa; level = be16_to_cpu(block->bb_level); - if (pag && pag->pagf_init) { + if (pag && xfs_perag_initialised_agf(pag)) { if (level >= pag->pagf_levels[XFS_BTNUM_RMAPi]) return __this_address; } else if (level >= mp->m_rmap_maxlevels) diff --git a/repair/rmap.c b/repair/rmap.c index 52106fd42..9013daa2e 100644 --- a/repair/rmap.c +++ b/repair/rmap.c @@ -1008,7 +1008,7 @@ rmaps_verify_btree( } /* Leave the per-ag data "uninitialized" since we rewrite it later */ - pag->pagf_init = 0; + clear_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate); bt_cur = libxfs_rmapbt_init_cursor(mp, NULL, agbp, pag); if (!bt_cur) { @@ -1382,7 +1382,7 @@ check_refcounts( } /* Leave the per-ag data "uninitialized" since we rewrite it later */ - pag->pagf_init = 0; + clear_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate); bt_cur = libxfs_refcountbt_init_cursor(mp, NULL, agbp, pag); if (!bt_cur) {