From 92764e8822d4e7f8efb5ad959fac195a7f8ea0c6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 14 Aug 2024 21:38:21 +0100 Subject: netfs, ceph: Partially revert "netfs: Replace PG_fscache by setting folio->private and marking dirty" This partially reverts commit 2ff1e97587f4d398686f52c07afde3faf3da4e5c. In addition to reverting the removal of PG_private_2 wrangling from the buffered read code[1][2], the removal of the waits for PG_private_2 from netfs_release_folio() and netfs_invalidate_folio() need reverting too. It also adds a wait into ceph_evict_inode() to wait for netfs read and copy-to-cache ops to complete. Fixes: 2ff1e97587f4 ("netfs: Replace PG_fscache by setting folio->private and marking dirty") Signed-off-by: David Howells Link: https://lore.kernel.org/r/3575457.1722355300@warthog.procyon.org.uk [1] Link: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=8e5ced7804cb9184c4a23f8054551240562a8eda [2] Link: https://lore.kernel.org/r/20240814203850.2240469-2-dhowells@redhat.com cc: Max Kellermann cc: Ilya Dryomov cc: Xiubo Li cc: Jeff Layton cc: Matthew Wilcox cc: ceph-devel@vger.kernel.org cc: netfs@lists.linux.dev cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org Signed-off-by: Christian Brauner --- fs/netfs/misc.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'fs/netfs/misc.c') diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 83e644bd518f..554a1a4615ad 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -101,6 +101,8 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) _enter("{%lx},%zx,%zx", folio->index, offset, length); + folio_wait_private_2(folio); /* [DEPRECATED] */ + if (!folio_test_private(folio)) return; @@ -165,6 +167,11 @@ bool netfs_release_folio(struct folio *folio, gfp_t gfp) if (folio_test_private(folio)) return false; + if (unlikely(folio_test_private_2(folio))) { /* [DEPRECATED] */ + if (current_is_kswapd() || !(gfp & __GFP_FS)) + return false; + folio_wait_private_2(folio); + } fscache_note_page_release(netfs_i_cookie(ctx)); return true; } -- cgit v1.2.3 From 7dfc8f0c6144c290dbeb01835a67e81b34dda8cd Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 23 Aug 2024 21:08:11 +0100 Subject: netfs: Fix netfs_release_folio() to say no if folio dirty Fix netfs_release_folio() to say no (ie. return false) if the folio is dirty (analogous with iomap's behaviour). Without this, it will say yes to the release of a dirty page by split_huge_page_to_list_to_order(), which will result in the loss of untruncated data in the folio. Without this, the generic/075 and generic/112 xfstests (both fsx-based tests) fail with minimum folio size patches applied[1]. Fixes: c1ec4d7c2e13 ("netfs: Provide invalidate_folio and release_folio calls") Signed-off-by: David Howells Link: https://lore.kernel.org/r/20240815090849.972355-1-kernel@pankajraghav.com/ [1] Link: https://lore.kernel.org/r/20240823200819.532106-4-dhowells@redhat.com cc: Matthew Wilcox (Oracle) cc: Pankaj Raghav cc: Jeff Layton cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: netfs@lists.linux.dev cc: linux-mm@kvack.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/misc.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs/netfs/misc.c') diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 554a1a4615ad..69324761fcf7 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -161,6 +161,9 @@ bool netfs_release_folio(struct folio *folio, gfp_t gfp) struct netfs_inode *ctx = netfs_inode(folio_inode(folio)); unsigned long long end; + if (folio_test_dirty(folio)) + return false; + end = folio_pos(folio) + folio_size(folio); if (end > ctx->zero_point) ctx->zero_point = end; -- cgit v1.2.3 From cce6bfa6ca0e30af9927b0074c97fe6a92f28092 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 23 Aug 2024 21:08:12 +0100 Subject: netfs: Fix trimming of streaming-write folios in netfs_inval_folio() When netfslib writes to a folio that it doesn't have data for, but that data exists on the server, it will make a 'streaming write' whereby it stores data in a folio that is marked dirty, but not uptodate. When it does this, it attaches a record to folio->private to track the dirty region. When truncate() or fallocate() wants to invalidate part of such a folio, it will call into ->invalidate_folio(), specifying the part of the folio that is to be invalidated. netfs_invalidate_folio(), on behalf of the filesystem, must then determine how to trim the streaming write record. In a couple of cases, however, it does this incorrectly (the reduce-length and move-start cases are switched over and don't, in any case, calculate the value correctly). Fix this by making the logic tree more obvious and fixing the cases. Fixes: 9ebff83e6481 ("netfs: Prep to use folio->private for write grouping and streaming write") Signed-off-by: David Howells Link: https://lore.kernel.org/r/20240823200819.532106-5-dhowells@redhat.com cc: Matthew Wilcox (Oracle) cc: Pankaj Raghav cc: Jeff Layton cc: Marc Dionne cc: linux-afs@lists.infradead.org cc: netfs@lists.linux.dev cc: linux-mm@kvack.org cc: linux-fsdevel@vger.kernel.org Signed-off-by: Christian Brauner --- fs/netfs/misc.c | 50 +++++++++++++++++++++++++++++++++++--------------- 1 file changed, 35 insertions(+), 15 deletions(-) (limited to 'fs/netfs/misc.c') diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 69324761fcf7..c1f321cf5999 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -97,10 +97,20 @@ EXPORT_SYMBOL(netfs_clear_inode_writeback); void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) { struct netfs_folio *finfo; + struct netfs_inode *ctx = netfs_inode(folio_inode(folio)); size_t flen = folio_size(folio); _enter("{%lx},%zx,%zx", folio->index, offset, length); + if (offset == 0 && length == flen) { + unsigned long long i_size = i_size_read(&ctx->inode); + unsigned long long fpos = folio_pos(folio), end; + + end = umin(fpos + flen, i_size); + if (fpos < i_size && end > ctx->zero_point) + ctx->zero_point = end; + } + folio_wait_private_2(folio); /* [DEPRECATED] */ if (!folio_test_private(folio)) @@ -115,18 +125,34 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) /* We have a partially uptodate page from a streaming write. */ unsigned int fstart = finfo->dirty_offset; unsigned int fend = fstart + finfo->dirty_len; - unsigned int end = offset + length; + unsigned int iend = offset + length; if (offset >= fend) return; - if (end <= fstart) + if (iend <= fstart) + return; + + /* The invalidation region overlaps the data. If the region + * covers the start of the data, we either move along the start + * or just erase the data entirely. + */ + if (offset <= fstart) { + if (iend >= fend) + goto erase_completely; + /* Move the start of the data. */ + finfo->dirty_len = fend - iend; + finfo->dirty_offset = offset; + return; + } + + /* Reduce the length of the data if the invalidation region + * covers the tail part. + */ + if (iend >= fend) { + finfo->dirty_len = offset - fstart; return; - if (offset <= fstart && end >= fend) - goto erase_completely; - if (offset <= fstart && end > fstart) - goto reduce_len; - if (offset > fstart && end >= fend) - goto move_start; + } + /* A partial write was split. The caller has already zeroed * it, so just absorb the hole. */ @@ -139,12 +165,6 @@ erase_completely: folio_clear_uptodate(folio); kfree(finfo); return; -reduce_len: - finfo->dirty_len = offset + length - finfo->dirty_offset; - return; -move_start: - finfo->dirty_len -= offset - finfo->dirty_offset; - finfo->dirty_offset = offset; } EXPORT_SYMBOL(netfs_invalidate_folio); @@ -164,7 +184,7 @@ bool netfs_release_folio(struct folio *folio, gfp_t gfp) if (folio_test_dirty(folio)) return false; - end = folio_pos(folio) + folio_size(folio); + end = umin(folio_pos(folio) + folio_size(folio), i_size_read(&ctx->inode)); if (end > ctx->zero_point) ctx->zero_point = end; -- cgit v1.2.3