diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index b266f734bd5394a092edcf288fcd29d54e55df13..b39a0468829b317d8e5aa93e9d2a53a816f8524f 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -288,7 +288,8 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des new_pos = desc->current_index + i; if (ctx->attr_gencount != nfsi->attr_gencount - || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))) { + || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA)) + || test_bit(NFS_INO_INVALIDATING, &nfsi->flags)) { ctx->duped = 0; ctx->attr_gencount = nfsi->attr_gencount; } else if (new_pos < desc->ctx->pos) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index c63e152244665990ce20603c8658ec87119f74a1..0a972ee9ccc1217ff76b90bfa63b6ad51503ebbe 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -977,11 +977,11 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map if (ret < 0) return ret; } - spin_lock(&inode->i_lock); - nfsi->cache_validity &= ~NFS_INO_INVALID_DATA; - if (S_ISDIR(inode->i_mode)) + if (S_ISDIR(inode->i_mode)) { + spin_lock(&inode->i_lock); memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); - spin_unlock(&inode->i_lock); + spin_unlock(&inode->i_lock); + } nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); nfs_fscache_wait_on_invalidate(inode); @@ -1008,6 +1008,7 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode) int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) { struct nfs_inode *nfsi = NFS_I(inode); + unsigned long *bitlock = &nfsi->flags; int ret = 0; /* swapfiles are not supposed to be shared. */ @@ -1019,12 +1020,45 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) if (ret < 0) goto out; } + + /* + * We must clear NFS_INO_INVALID_DATA first to ensure that + * invalidations that come in while we're shooting down the mappings + * are respected. But, that leaves a race window where one revalidator + * can clear the flag, and then another checks it before the mapping + * gets invalidated. Fix that by serializing access to this part of + * the function. + * + * At the same time, we need to allow other tasks to see whether we + * might be in the middle of invalidating the pages, so we only set + * the bit lock here if it looks like we're going to be doing that. + */ + for (;;) { + ret = wait_on_bit(bitlock, NFS_INO_INVALIDATING, + nfs_wait_bit_killable, TASK_KILLABLE); + if (ret) + goto out; + if (!(nfsi->cache_validity & NFS_INO_INVALID_DATA)) + goto out; + if (!test_and_set_bit_lock(NFS_INO_INVALIDATING, bitlock)) + break; + } + + spin_lock(&inode->i_lock); if (nfsi->cache_validity & NFS_INO_INVALID_DATA) { + nfsi->cache_validity &= ~NFS_INO_INVALID_DATA; + spin_unlock(&inode->i_lock); trace_nfs_invalidate_mapping_enter(inode); ret = nfs_invalidate_mapping(inode, mapping); trace_nfs_invalidate_mapping_exit(inode, ret); + } else { + /* something raced in and cleared the flag */ + spin_unlock(&inode->i_lock); } + clear_bit_unlock(NFS_INO_INVALIDATING, bitlock); + smp_mb__after_clear_bit(); + wake_up_bit(bitlock, NFS_INO_INVALIDATING); out: return ret; } diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 89fe741e58b1f7280f44e882f640259b8a8af144..59f838cdc009307f539bb94ee75f3447bfd79a56 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -36,6 +36,7 @@ __print_flags(v, "|", \ { 1 << NFS_INO_ADVISE_RDPLUS, "ADVISE_RDPLUS" }, \ { 1 << NFS_INO_STALE, "STALE" }, \ + { 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \ { 1 << NFS_INO_FLUSHING, "FLUSHING" }, \ { 1 << NFS_INO_FSCACHE, "FSCACHE" }, \ { 1 << NFS_INO_COMMIT, "COMMIT" }, \ diff --git a/fs/nfs/write.c b/fs/nfs/write.c index a44a87268a6ef640c454600873489cc4e4e1e058..5511a42471901b913fc795136d52edaaae4776c5 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -909,9 +909,13 @@ bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx) */ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode) { + struct nfs_inode *nfsi = NFS_I(inode); + if (nfs_have_delegated_attributes(inode)) goto out; - if (NFS_I(inode)->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE)) + if (nfsi->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE)) + return false; + if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags)) return false; out: return PageUptodate(page) != 0; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 48997374eaf04eac0d52b8bf8d60c61c35944df3..18fb16f4b9393dd7c97e90df9ed3cd385dda8225 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -215,6 +215,7 @@ struct nfs_inode { #define NFS_INO_ADVISE_RDPLUS (0) /* advise readdirplus */ #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ +#define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_FLUSHING (4) /* inode is flushing out data */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */