Return-Path: Received: from mail-io0-f195.google.com ([209.85.223.195]:35056 "EHLO mail-io0-f195.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759727AbcLAWTf (ORCPT ); Thu, 1 Dec 2016 17:19:35 -0500 Received: by mail-io0-f195.google.com with SMTP id h133so4680718ioe.2 for ; Thu, 01 Dec 2016 14:19:34 -0800 (PST) From: Trond Myklebust To: linux-nfs@vger.kernel.org Subject: [PATCH 09/26] pNFS: Do not free layout segments that are marked for return Date: Thu, 1 Dec 2016 17:19:05 -0500 Message-Id: <20161201221922.15657-10-trond.myklebust@primarydata.com> In-Reply-To: <20161201221922.15657-9-trond.myklebust@primarydata.com> References: <20161201221922.15657-1-trond.myklebust@primarydata.com> <20161201221922.15657-2-trond.myklebust@primarydata.com> <20161201221922.15657-3-trond.myklebust@primarydata.com> <20161201221922.15657-4-trond.myklebust@primarydata.com> <20161201221922.15657-5-trond.myklebust@primarydata.com> <20161201221922.15657-6-trond.myklebust@primarydata.com> <20161201221922.15657-7-trond.myklebust@primarydata.com> <20161201221922.15657-8-trond.myklebust@primarydata.com> <20161201221922.15657-9-trond.myklebust@primarydata.com> Sender: linux-nfs-owner@vger.kernel.org List-ID: We may want to process and transmit layout stat information for the layout segments that are being returned, so we should defer freeing them until after the layoutreturn has completed. Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 15 +++-------- fs/nfs/pnfs.c | 74 ++++++++++++++++++++++++++++++++++++++++++++++++------- fs/nfs/pnfs.h | 6 ++++- 3 files changed, 73 insertions(+), 22 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 917a6db5c84f..561b21e4a930 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8572,21 +8572,12 @@ static void nfs4_layoutreturn_release(void *calldata) { struct nfs4_layoutreturn *lrp = calldata; struct pnfs_layout_hdr *lo = lrp->args.layout; - LIST_HEAD(freeme); dprintk("--> %s\n", __func__); - spin_lock(&lo->plh_inode->i_lock); - if (lrp->res.lrs_present) { - pnfs_mark_matching_lsegs_invalid(lo, &freeme, - &lrp->args.range, - be32_to_cpu(lrp->args.stateid.seqid)); - pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); - } else - pnfs_mark_layout_stateid_invalid(lo, &freeme); - pnfs_clear_layoutreturn_waitbit(lo); - spin_unlock(&lo->plh_inode->i_lock); + pnfs_layoutreturn_free_lsegs(lo, &lrp->args.range, + be32_to_cpu(lrp->args.stateid.seqid), + lrp->res.lrs_present ? &lrp->res.stateid : NULL); nfs4_sequence_free_slot(&lrp->res.seq_res); - pnfs_free_lseg_list(&freeme); pnfs_put_layout_hdr(lrp->args.layout); nfs_iput_and_deactive(lrp->inode); kfree(calldata); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index d70cc467a87b..555151b6d31b 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -54,6 +54,10 @@ static DEFINE_SPINLOCK(pnfs_spinlock); static LIST_HEAD(pnfs_modules_tbl); static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo); +static void pnfs_free_returned_lsegs(struct pnfs_layout_hdr *lo, + struct list_head *free_me, + const struct pnfs_layout_range *range, + u32 seq); /* Return the registered pnfs layout driver module matching given id */ static struct pnfs_layoutdriver_type * @@ -326,6 +330,7 @@ pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); pnfs_clear_layoutreturn_info(lo); + pnfs_free_returned_lsegs(lo, lseg_list, &range, 0); return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range, 0); } @@ -405,9 +410,10 @@ pnfs_init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg, static void pnfs_free_lseg(struct pnfs_layout_segment *lseg) { - struct inode *ino = lseg->pls_layout->plh_inode; - - NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg); + if (lseg != NULL) { + struct inode *inode = lseg->pls_layout->plh_inode; + NFS_SERVER(inode)->pnfs_curr_ld->free_lseg(lseg); + } } static void @@ -430,6 +436,18 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo, rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq); } +static bool +pnfs_cache_lseg_for_layoutreturn(struct pnfs_layout_hdr *lo, + struct pnfs_layout_segment *lseg) +{ + if (test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags) && + pnfs_layout_is_valid(lo)) { + list_move_tail(&lseg->pls_list, &lo->plh_return_segs); + return true; + } + return false; +} + void pnfs_put_lseg(struct pnfs_layout_segment *lseg) { @@ -453,6 +471,8 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg) } pnfs_get_layout_hdr(lo); pnfs_layout_remove_lseg(lo, lseg); + if (pnfs_cache_lseg_for_layoutreturn(lo, lseg)) + lseg = NULL; spin_unlock(&inode->i_lock); pnfs_free_lseg(lseg); pnfs_put_layout_hdr(lo); @@ -493,9 +513,11 @@ pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg) struct pnfs_layout_hdr *lo = lseg->pls_layout; if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) return; - pnfs_get_layout_hdr(lo); pnfs_layout_remove_lseg(lo, lseg); - pnfs_free_lseg_async(lseg); + if (!pnfs_cache_lseg_for_layoutreturn(lo, lseg)) { + pnfs_get_layout_hdr(lo); + pnfs_free_lseg_async(lseg); + } } } EXPORT_SYMBOL_GPL(pnfs_put_lseg_locked); @@ -619,6 +641,20 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, return remaining; } +static void +pnfs_free_returned_lsegs(struct pnfs_layout_hdr *lo, + struct list_head *free_me, + const struct pnfs_layout_range *range, + u32 seq) +{ + struct pnfs_layout_segment *lseg, *next; + + list_for_each_entry_safe(lseg, next, &lo->plh_return_segs, pls_list) { + if (pnfs_match_lseg_recall(lseg, range, seq)) + list_move_tail(&lseg->pls_list, free_me); + } +} + /* note free_me must contain lsegs from a single layout_hdr */ void pnfs_free_lseg_list(struct list_head *free_me) @@ -915,7 +951,7 @@ static void pnfs_clear_layoutcommit(struct inode *inode, } } -void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) +static void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) { clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags); clear_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags); @@ -924,6 +960,27 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); } +void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo, + const struct pnfs_layout_range *range, + u32 seq, + const nfs4_stateid *stateid) +{ + struct inode *inode = lo->plh_inode; + LIST_HEAD(freeme); + + spin_lock(&inode->i_lock); + if (stateid) { + pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq); + pnfs_free_returned_lsegs(lo, &freeme, range, seq); + pnfs_set_layout_stateid(lo, stateid, true); + } else + pnfs_mark_layout_stateid_invalid(lo, &freeme); + pnfs_clear_layoutreturn_waitbit(lo); + spin_unlock(&inode->i_lock); + pnfs_free_lseg_list(&freeme); + +} + static bool pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid *stateid, @@ -1349,6 +1406,7 @@ alloc_init_layout_hdr(struct inode *ino, atomic_set(&lo->plh_refcount, 1); INIT_LIST_HEAD(&lo->plh_layouts); INIT_LIST_HEAD(&lo->plh_segs); + INIT_LIST_HEAD(&lo->plh_return_segs); INIT_LIST_HEAD(&lo->plh_bulk_destroy); lo->plh_inode = ino; lo->plh_lc_cred = get_rpccred(ctx->cred); @@ -1920,7 +1978,6 @@ void pnfs_error_mark_layout_for_return(struct inode *inode, .offset = 0, .length = NFS4_MAX_UINT64, }; - LIST_HEAD(free_me); bool return_now = false; spin_lock(&inode->i_lock); @@ -1932,7 +1989,7 @@ void pnfs_error_mark_layout_for_return(struct inode *inode, * segments at hand when sending layoutreturn. See pnfs_put_lseg() * for how it works. */ - if (!pnfs_mark_matching_lsegs_return(lo, &free_me, &range, 0)) { + if (!pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, &range, 0)) { nfs4_stateid stateid; enum pnfs_iomode iomode; @@ -1944,7 +2001,6 @@ void pnfs_error_mark_layout_for_return(struct inode *inode, spin_unlock(&inode->i_lock); nfs_commit_inode(inode, 0); } - pnfs_free_lseg_list(&free_me); } EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 337dad382b6a..a382710edf40 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -191,6 +191,7 @@ struct pnfs_layout_hdr { struct list_head plh_layouts; /* other client layouts */ struct list_head plh_bulk_destroy; struct list_head plh_segs; /* layout segments list */ + struct list_head plh_return_segs; /* invalid layout segments */ unsigned long plh_block_lgets; /* block LAYOUTGET if >0 */ unsigned long plh_retry_timestamp; unsigned long plh_flags; @@ -293,7 +294,10 @@ struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino, enum pnfs_iomode iomode, bool strict_iomode, gfp_t gfp_flags); -void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo); +void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo, + const struct pnfs_layout_range *range, + u32 seq, + const nfs4_stateid *stateid); void pnfs_generic_layout_insert_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg, -- 2.9.3