From 3f982b9b18c23900da10956b91036a3f6fe3f5bc Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 13 Jan 2025 14:16:10 +0100 Subject: [PATCH 01/16] mm/hugetlb-cgroup: convert hugetlb_cgroup_css_offline() to work on folios Let's convert hugetlb_cgroup_css_offline() and hugetlb_cgroup_move_parent() to work on folios. hugepage_activelist contains folios, not pages. While at it, rename page_hcg simply to hcg, removing most of the "page" terminology. This removes an unnecessary call to compound_head(). Link: https://lkml.kernel.org/r/20250113131611.2554758-6-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Matthew Wilcox (Oracle) Cc: Baolin Wang Cc: Muchun Song Cc: Sidhartha Kumar Signed-off-by: Andrew Morton --- mm/hugetlb_cgroup.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 89a8ad45a533..bb9578bd99f9 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -195,24 +195,23 @@ static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css) * cannot fail. */ static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg, - struct page *page) + struct folio *folio) { unsigned int nr_pages; struct page_counter *counter; - struct hugetlb_cgroup *page_hcg; + struct hugetlb_cgroup *hcg; struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg); - struct folio *folio = page_folio(page); - page_hcg = hugetlb_cgroup_from_folio(folio); + hcg = hugetlb_cgroup_from_folio(folio); /* * We can have pages in active list without any cgroup * ie, hugepage with less than 3 pages. We can safely * ignore those pages. */ - if (!page_hcg || page_hcg != h_cg) + if (!hcg || hcg != h_cg) goto out; - nr_pages = compound_nr(page); + nr_pages = folio_nr_pages(folio); if (!parent) { parent = root_h_cgroup; /* root has no limit */ @@ -235,13 +234,13 @@ static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) { struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); struct hstate *h; - struct page *page; + struct folio *folio; do { for_each_hstate(h) { spin_lock_irq(&hugetlb_lock); - list_for_each_entry(page, &h->hugepage_activelist, lru) - hugetlb_cgroup_move_parent(hstate_index(h), h_cg, page); + list_for_each_entry(folio, &h->hugepage_activelist, lru) + hugetlb_cgroup_move_parent(hstate_index(h), h_cg, folio); spin_unlock_irq(&hugetlb_lock); } -- 2.51.0 From 89a41a0263293856678189981e5407375261c4ff Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 13 Jan 2025 14:16:11 +0100 Subject: [PATCH 02/16] mm/hugetlb: use folio->lru int demote_free_hugetlb_folios() We are demoting hugetlb folios to smaller hugetlb folios; let's avoid messing with pages where avoidable and handle it more similar to __split_huge_page_tail(). Link: https://lkml.kernel.org/r/20250113131611.2554758-7-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Sidhartha Kumar Cc: Baolin Wang Cc: Matthew Wilcox (Oracle) Cc: Muchun Song Signed-off-by: Andrew Morton --- mm/hugetlb.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 308b0e3876b5..87761b042ed0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3826,13 +3826,15 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) { struct page *page = folio_page(folio, i); + /* Careful: see __split_huge_page_tail() */ + struct folio *new_folio = (struct folio *)page; - page->mapping = NULL; clear_compound_head(page); prep_compound_page(page, dst->order); - init_new_hugetlb_folio(dst, page_folio(page)); - list_add(&page->lru, &dst_list); + new_folio->mapping = NULL; + init_new_hugetlb_folio(dst, new_folio); + list_add(&new_folio->lru, &dst_list); } } -- 2.51.0 From 9ad6344568cc31ede9741795b3e3c41c21e3156f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Dec 2024 08:47:39 -0700 Subject: [PATCH 03/16] mm/filemap: change filemap_create_folio() to take a struct kiocb Patch series "Uncached buffered IO", v8. 5 years ago I posted patches adding support for RWF_UNCACHED, as a way to do buffered IO that isn't page cache persistent. The approach back then was to have private pages for IO, and then get rid of them once IO was done. But that then runs into all the issues that O_DIRECT has, in terms of synchronizing with the page cache. So here's a new approach to the same concent, but using the page cache as synchronization. Due to excessive bike shedding on the naming, this is now named RWF_DONTCACHE, and is less special in that it's just page cache IO, except it prunes the ranges once IO is completed. Why do this, you may ask? The tldr is that device speeds are only getting faster, while reclaim is not. Doing normal buffered IO can be very unpredictable, and suck up a lot of resources on the reclaim side. This leads people to use O_DIRECT as a work-around, which has its own set of restrictions in terms of size, offset, and length of IO. It's also inherently synchronous, and now you need async IO as well. While the latter isn't necessarily a big problem as we have good options available there, it also should not be a requirement when all you want to do is read or write some data without caching. Even on desktop type systems, a normal NVMe device can fill the entire page cache in seconds. On the big system I used for testing, there's a lot more RAM, but also a lot more devices. As can be seen in some of the results in the following patches, you can still fill RAM in seconds even when there's 1TB of it. Hence this problem isn't solely a "big hyperscaler system" issue, it's common across the board. Common for both reads and writes with RWF_DONTCACHE is that they use the page cache for IO. Reads work just like a normal buffered read would, with the only exception being that the touched ranges will get pruned after data has been copied. For writes, the ranges will get writeback kicked off before the syscall returns, and then writeback completion will prune the range. Hence writes aren't synchronous, and it's easy to pipeline writes using RWF_DONTCACHE. Folios that aren't instantiated by RWF_DONTCACHE IO are left untouched. This means you that uncached IO will take advantage of the page cache for uptodate data, but not leave anything it instantiated/created in cache. File systems need to support this. This patchset adds support for the generic read path, which covers file systems like ext4. Patches exist to add support for iomap/XFS and btrfs as well, which sit on top of this series. If RWF_DONTCACHE IO is attempted on a file system that doesn't support it, -EOPNOTSUPP is returned. Hence the user can rely on it either working as designed, or flagging and error if that's not the case. The intent here is to give the application a sensible fallback path - eg, it may fall back to O_DIRECT if appropriate, or just live with the fact that uncached IO isn't available and do normal buffered IO. Adding "support" to other file systems should be trivial, most of the time just a one-liner adding FOP_DONTCACHE to the fop_flags in the file_operations struct, if the file system is using either iomap or the generic filemap helpers for reading and writing. Performance results are in patch 8 for reads, and you can find the write side results in the XFS patch adding support for DONTCACHE writes for XFS: https://git.kernel.dk/cgit/linux/commit/?h=buffered-uncached-fs.10&id=257e92de795fdff7d7e256501e024fac6da6a7f4 with the tldr being that I see about a 65% improvement in performance for both, with fully predictable IO times. CPU reduction is substantial as well, with no kswapd activity at all for reclaim when using uncached IO. Using it from applications is trivial - just set RWF_DONTCACHE for the read or write, using pwritev2(2) or preadv2(2). For io_uring, same thing, just set RWF_DONTCACHE in sqe->rw_flags for a buffered read/write operation. And that's it. Patches 1..7 are just prep patches, and should have no functional changes at all. Patch 8 adds support for the filemap path for RWF_DONTCACHE reads, and patches 9..12 are just prep patches for supporting the write side of uncached writes. In the below mentioned branch, there are then patches to adopt uncached reads and writes for xfs, btrfs, and ext4. The latter currently relies on bit of a hack for passing whether this is an uncached write or not through ->write_begin(), which can hopefully go away once ext4 adopts iomap for buffered writes. I say this is a hack as it's not the prettiest way to do it, however it is fully solid and will work just fine. Passes full xfstests and fsx overnight runs, no issues observed. That includes the vm running the testing also using RWF_DONTCACHE on the host. I'll post fsstress and fsx patches for RWF_DONTCACHE separately. As far as I'm concerned, no further work needs doing here. And git tree for the patches is here: https://git.kernel.dk/cgit/linux/log/?h=buffered-uncached.10 with the file system patches on top adding support for xfs/btrfs/ext4 here: https://git.kernel.dk/cgit/linux/log/?h=buffered-uncached-fs.10 This patch (of 12): Rather than pass in both the file and position directly from the kiocb, just take a struct kiocb instead. With the kiocb being passed in, skip passing in the address_space separately as well. While doing so, move the ki_flags checking into filemap_create_folio() as well. In preparation for actually needing the kiocb in the function. No functional changes in this patch. Link: https://lkml.kernel.org/r/20241220154831.1086649-1-axboe@kernel.dk Link: https://lkml.kernel.org/r/20241220154831.1086649-2-axboe@kernel.dk Signed-off-by: Jens Axboe Reviewed-by: Kirill A. Shutemov Reviewed-by: Matthew Wilcox (Oracle) Cc: Brian Foster Cc: Chris Mason Cc: Johannes Weiner Cc: Christoph Hellwig Signed-off-by: Andrew Morton --- mm/filemap.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index b6494d2d3bc2..904d8fa2bfc0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2431,15 +2431,17 @@ unlock_mapping: return error; } -static int filemap_create_folio(struct file *file, - struct address_space *mapping, loff_t pos, - struct folio_batch *fbatch) +static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch) { + struct address_space *mapping = iocb->ki_filp->f_mapping; struct folio *folio; int error; unsigned int min_order = mapping_min_folio_order(mapping); pgoff_t index; + if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) + return -EAGAIN; + folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order); if (!folio) return -ENOMEM; @@ -2458,7 +2460,7 @@ static int filemap_create_folio(struct file *file, * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); - index = (pos >> (PAGE_SHIFT + min_order)) << min_order; + index = (iocb->ki_pos >> (PAGE_SHIFT + min_order)) << min_order; error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) @@ -2466,7 +2468,8 @@ static int filemap_create_folio(struct file *file, if (error) goto error; - error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); + error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, + folio); if (error) goto error; @@ -2522,9 +2525,7 @@ retry: filemap_get_read_batch(mapping, index, last_index - 1, fbatch); } if (!folio_batch_count(fbatch)) { - if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) - return -EAGAIN; - err = filemap_create_folio(filp, mapping, iocb->ki_pos, fbatch); + err = filemap_create_folio(iocb, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; -- 2.51.0 From f598cdaafc370a797ae883d370a7c18c1ffc43ef Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Dec 2024 08:47:40 -0700 Subject: [PATCH 04/16] mm/filemap: use page_cache_sync_ra() to kick off read-ahead Rather than use the page_cache_sync_readahead() helper, define our own ractl and use page_cache_sync_ra() directly. In preparation for needing to modify ractl inside filemap_get_pages(). No functional changes in this patch. Link: https://lkml.kernel.org/r/20241220154831.1086649-3-axboe@kernel.dk Signed-off-by: Jens Axboe Reviewed-by: Kirill A. Shutemov Reviewed-by: Christoph Hellwig Reviewed-by: Matthew Wilcox (Oracle) Cc: Brian Foster Cc: Chris Mason Cc: Johannes Weiner Signed-off-by: Andrew Morton --- mm/filemap.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index 904d8fa2bfc0..a1fda00aa6bc 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2499,7 +2499,6 @@ static int filemap_get_pages(struct kiocb *iocb, size_t count, { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; - struct file_ra_state *ra = &filp->f_ra; pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; struct folio *folio; @@ -2514,12 +2513,13 @@ retry: filemap_get_read_batch(mapping, index, last_index - 1, fbatch); if (!folio_batch_count(fbatch)) { + DEFINE_READAHEAD(ractl, filp, &filp->f_ra, mapping, index); + if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; if (iocb->ki_flags & IOCB_NOWAIT) flags = memalloc_noio_save(); - page_cache_sync_readahead(mapping, ra, filp, index, - last_index - index); + page_cache_sync_ra(&ractl, last_index - index); if (iocb->ki_flags & IOCB_NOWAIT) memalloc_noio_restore(flags); filemap_get_read_batch(mapping, index, last_index - 1, fbatch); -- 2.51.0 From 1963de79d3a3bc12b7a17a922d508b733ca8fa9e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Dec 2024 08:47:41 -0700 Subject: [PATCH 05/16] mm/readahead: add folio allocation helper Just a wrapper around filemap_alloc_folio() for now, but add it in preparation for modifying the folio based on the 'ractl' being passed in. No functional changes in this patch. Link: https://lkml.kernel.org/r/20241220154831.1086649-4-axboe@kernel.dk Signed-off-by: Jens Axboe Reviewed-by: Kirill A. Shutemov Reviewed-by: Matthew Wilcox (Oracle) Cc: Brian Foster Cc: Chris Mason Cc: Christoph Hellwig Cc: Johannes Weiner Signed-off-by: Andrew Morton --- mm/readahead.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/mm/readahead.c b/mm/readahead.c index 2bc3abf07828..722b541c7137 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -178,6 +178,12 @@ static void read_pages(struct readahead_control *rac) BUG_ON(readahead_count(rac)); } +static struct folio *ractl_alloc_folio(struct readahead_control *ractl, + gfp_t gfp_mask, unsigned int order) +{ + return filemap_alloc_folio(gfp_mask, order); +} + /** * page_cache_ra_unbounded - Start unchecked readahead. * @ractl: Readahead control. @@ -255,8 +261,8 @@ void page_cache_ra_unbounded(struct readahead_control *ractl, continue; } - folio = filemap_alloc_folio(gfp_mask, - mapping_min_folio_order(mapping)); + folio = ractl_alloc_folio(ractl, gfp_mask, + mapping_min_folio_order(mapping)); if (!folio) break; @@ -426,7 +432,7 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index, pgoff_t mark, unsigned int order, gfp_t gfp) { int err; - struct folio *folio = filemap_alloc_folio(gfp, order); + struct folio *folio = ractl_alloc_folio(ractl, gfp, order); if (!folio) return -ENOMEM; @@ -751,7 +757,7 @@ void readahead_expand(struct readahead_control *ractl, if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ - folio = filemap_alloc_folio(gfp_mask, min_order); + folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; @@ -780,7 +786,7 @@ void readahead_expand(struct readahead_control *ractl, if (folio && !xa_is_value(folio)) return; /* Folio apparently present */ - folio = filemap_alloc_folio(gfp_mask, min_order); + folio = ractl_alloc_folio(ractl, gfp_mask, min_order); if (!folio) return; -- 2.51.0 From cceba6f7e46c48deca433030d80fc34599fb9fd8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Dec 2024 08:47:42 -0700 Subject: [PATCH 06/16] mm: add PG_dropbehind folio flag Add a folio flag that file IO can use to indicate that the cached IO being done should be dropped from the page cache upon completion. Link: https://lkml.kernel.org/r/20241220154831.1086649-5-axboe@kernel.dk Signed-off-by: Jens Axboe Reviewed-by: Kirill A. Shutemov Cc: Brian Foster Cc: Chris Mason Cc: Christoph Hellwig Cc: Johannes Weiner Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/page-flags.h | 5 +++++ include/trace/events/mmflags.h | 3 ++- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 616b57ddc3fe..36d283552f80 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -110,6 +110,7 @@ enum pageflags { PG_reclaim, /* To be reclaimed asap */ PG_swapbacked, /* Page is backed by RAM/swap */ PG_unevictable, /* Page is "unevictable" */ + PG_dropbehind, /* drop pages on IO completion */ #ifdef CONFIG_MMU PG_mlocked, /* Page is vma mlocked */ #endif @@ -562,6 +563,10 @@ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE) +FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(dropbehind, FOLIO_HEAD_PAGE) + __FOLIO_SET_FLAG(dropbehind, FOLIO_HEAD_PAGE) + #ifdef CONFIG_HIGHMEM /* * Must use a macro here due to header dependency issues. page_zone() is not diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index bb8a59c6caa2..3bc8656c8359 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -116,7 +116,8 @@ DEF_PAGEFLAG_NAME(head), \ DEF_PAGEFLAG_NAME(reclaim), \ DEF_PAGEFLAG_NAME(swapbacked), \ - DEF_PAGEFLAG_NAME(unevictable) \ + DEF_PAGEFLAG_NAME(unevictable), \ + DEF_PAGEFLAG_NAME(dropbehind) \ IF_HAVE_PG_MLOCK(mlocked) \ IF_HAVE_PG_HWPOISON(hwpoison) \ IF_HAVE_PG_IDLE(idle) \ -- 2.51.0 From 77d075221ae777296e2b18a0a4f5fea6f75daf2c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Dec 2024 08:47:43 -0700 Subject: [PATCH 07/16] mm/readahead: add readahead_control->dropbehind member If ractl->dropbehind is set to true, then folios created are marked as dropbehind as well. Link: https://lkml.kernel.org/r/20241220154831.1086649-6-axboe@kernel.dk Signed-off-by: Jens Axboe Reviewed-by: Kirill A. Shutemov Cc: Brian Foster Cc: Chris Mason Cc: Christoph Hellwig Cc: Johannes Weiner Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 1 + mm/readahead.c | 8 +++++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index fc2e1319c7bb..d53c49abead6 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1358,6 +1358,7 @@ struct readahead_control { pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; + bool dropbehind; bool _workingset; unsigned long _pflags; }; diff --git a/mm/readahead.c b/mm/readahead.c index 722b541c7137..6a4e96b69702 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -181,7 +181,13 @@ static void read_pages(struct readahead_control *rac) static struct folio *ractl_alloc_folio(struct readahead_control *ractl, gfp_t gfp_mask, unsigned int order) { - return filemap_alloc_folio(gfp_mask, order); + struct folio *folio; + + folio = filemap_alloc_folio(gfp_mask, order); + if (folio && ractl->dropbehind) + __folio_set_dropbehind(folio); + + return folio; } /** -- 2.51.0 From 4a9e23159fd37677efc0c2c53e3b45a5d260a90a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Dec 2024 08:47:44 -0700 Subject: [PATCH 08/16] mm/truncate: add folio_unmap_invalidate() helper Add a folio_unmap_invalidate() helper, which unmaps and invalidates a given folio. The caller must already have locked the folio. Embed the old invalidate_complete_folio2() helper in there as well, as nobody else calls it. Use this new helper in invalidate_inode_pages2_range(), rather than duplicate the code there. In preparation for using this elsewhere as well, have it take a gfp_t mask rather than assume GFP_KERNEL is the right choice. This bubbles back to invalidate_complete_folio2() as well. Link: https://lkml.kernel.org/r/20241220154831.1086649-7-axboe@kernel.dk Signed-off-by: Jens Axboe Cc: Brian Foster Cc: Chris Mason Cc: Christoph Hellwig Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- mm/internal.h | 2 ++ mm/truncate.c | 53 +++++++++++++++++++++++++++------------------------ 2 files changed, 30 insertions(+), 25 deletions(-) diff --git a/mm/internal.h b/mm/internal.h index 4d4028d74e5d..109ef30fee11 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -392,6 +392,8 @@ void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); +int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio, + gfp_t gfp); void page_cache_ra_order(struct readahead_control *, struct file_ra_state *, unsigned int order); diff --git a/mm/truncate.c b/mm/truncate.c index 7c304d2f0052..e2e115adfbc5 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -525,6 +525,15 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, } EXPORT_SYMBOL(invalidate_mapping_pages); +static int folio_launder(struct address_space *mapping, struct folio *folio) +{ + if (!folio_test_dirty(folio)) + return 0; + if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL) + return 0; + return mapping->a_ops->launder_folio(folio); +} + /* * This is like mapping_evict_folio(), except it ignores the folio's * refcount. We do this because invalidate_inode_pages2() needs stronger @@ -532,14 +541,26 @@ EXPORT_SYMBOL(invalidate_mapping_pages); * shrink_folio_list() has a temp ref on them, or because they're transiently * sitting in the folio_add_lru() caches. */ -static int invalidate_complete_folio2(struct address_space *mapping, - struct folio *folio) +int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio, + gfp_t gfp) { - if (folio->mapping != mapping) - return 0; + int ret; + + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - if (!filemap_release_folio(folio, GFP_KERNEL)) + if (folio_test_dirty(folio)) return 0; + if (folio_mapped(folio)) + unmap_mapping_folio(folio); + BUG_ON(folio_mapped(folio)); + + ret = folio_launder(mapping, folio); + if (ret) + return ret; + if (folio->mapping != mapping) + return -EBUSY; + if (!filemap_release_folio(folio, gfp)) + return -EBUSY; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); @@ -558,16 +579,7 @@ static int invalidate_complete_folio2(struct address_space *mapping, failed: xa_unlock_irq(&mapping->i_pages); spin_unlock(&mapping->host->i_lock); - return 0; -} - -static int folio_launder(struct address_space *mapping, struct folio *folio) -{ - if (!folio_test_dirty(folio)) - return 0; - if (folio->mapping != mapping || mapping->a_ops->launder_folio == NULL) - return 0; - return mapping->a_ops->launder_folio(folio); + return -EBUSY; } /** @@ -631,16 +643,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, } VM_BUG_ON_FOLIO(!folio_contains(folio, indices[i]), folio); folio_wait_writeback(folio); - - if (folio_mapped(folio)) - unmap_mapping_folio(folio); - BUG_ON(folio_mapped(folio)); - - ret2 = folio_launder(mapping, folio); - if (ret2 == 0) { - if (!invalidate_complete_folio2(mapping, folio)) - ret2 = -EBUSY; - } + ret2 = folio_unmap_invalidate(mapping, folio, GFP_KERNEL); if (ret2 < 0) ret = ret2; folio_unlock(folio); -- 2.51.0 From b9f958d4f146bd11be33a5f2bc3ced50f86d6b23 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Dec 2024 08:47:45 -0700 Subject: [PATCH 09/16] fs: add RWF_DONTCACHE iocb and FOP_DONTCACHE file_operations flag If a file system supports uncached buffered IO, it may set FOP_DONTCACHE and enable support for RWF_DONTCACHE. If RWF_DONTCACHE is attempted without the file system supporting it, it'll get errored with -EOPNOTSUPP. Link: https://lkml.kernel.org/r/20241220154831.1086649-8-axboe@kernel.dk Signed-off-by: Jens Axboe Cc: Brian Foster Cc: Chris Mason Cc: Christoph Hellwig Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/fs.h | 14 +++++++++++++- include/uapi/linux/fs.h | 6 +++++- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/include/linux/fs.h b/include/linux/fs.h index 7e29433c5ecc..6a838b5479a6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -322,6 +322,7 @@ struct readahead_control; #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND #define IOCB_ATOMIC (__force int) RWF_ATOMIC +#define IOCB_DONTCACHE (__force int) RWF_DONTCACHE /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) @@ -356,7 +357,8 @@ struct readahead_control; { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ - { IOCB_ATOMIC, "ATOMIC"}, \ + { IOCB_ATOMIC, "ATOMIC" }, \ + { IOCB_DONTCACHE, "DONTCACHE" }, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ @@ -2127,6 +2129,8 @@ struct file_operations { #define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) /* Supports asynchronous lock callbacks */ #define FOP_ASYNC_LOCK ((__force fop_flags_t)(1 << 6)) +/* File system supports uncached read/write buffered IO */ +#define FOP_DONTCACHE ((__force fop_flags_t)(1 << 7)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, @@ -3614,6 +3618,14 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) return -EOPNOTSUPP; } + if (flags & RWF_DONTCACHE) { + /* file system must support it */ + if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE)) + return -EOPNOTSUPP; + /* DAX mappings not supported */ + if (IS_DAX(ki->ki_filp->f_mapping->host)) + return -EOPNOTSUPP; + } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 753971770733..56a4f93a08f4 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -332,9 +332,13 @@ typedef int __bitwise __kernel_rwf_t; /* Atomic Write */ #define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040) +/* buffered IO that drops the cache after reading or writing data */ +#define RWF_DONTCACHE ((__force __kernel_rwf_t)0x00000080) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC) + RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC |\ + RWF_DONTCACHE) #define PROCFS_IOCTL_MAGIC 'f' -- 2.51.0 From 8026e49bff9b151609da4cae20e9da7f1833dde6 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Dec 2024 08:47:46 -0700 Subject: [PATCH 10/16] mm/filemap: add read support for RWF_DONTCACHE Add RWF_DONTCACHE as a read operation flag, which means that any data read wil be removed from the page cache upon completion. Uses the page cache to synchronize, and simply prunes folios that were instantiated when the operation completes. While it would be possible to use private pages for this, using the page cache as synchronization is handy for a variety of reasons: 1) No special truncate magic is needed 2) Async buffered reads need some place to serialize, using the page cache is a lot easier than writing extra code for this 3) The pruning cost is pretty reasonable and the code to support this is much simpler as a result. You can think of uncached buffered IO as being the much more attractive cousin of O_DIRECT - it has none of the restrictions of O_DIRECT. Yes, it will copy the data, but unlike regular buffered IO, it doesn't run into the unpredictability of the page cache in terms of reclaim. As an example, on a test box with 32 drives, reading them with buffered IO looks as follows: Reading bs 65536, uncached 0 1s: 145945MB/sec 2s: 158067MB/sec 3s: 157007MB/sec 4s: 148622MB/sec 5s: 118824MB/sec 6s: 70494MB/sec 7s: 41754MB/sec 8s: 90811MB/sec 9s: 92204MB/sec 10s: 95178MB/sec 11s: 95488MB/sec 12s: 95552MB/sec 13s: 96275MB/sec where it's quite easy to see where the page cache filled up, and performance went from good to erratic, and finally settles at a much lower rate. Looking at top while this is ongoing, we see: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7535 root 20 0 267004 0 0 S 3199 0.0 8:40.65 uncached 3326 root 20 0 0 0 0 R 100.0 0.0 0:16.40 kswapd4 3327 root 20 0 0 0 0 R 100.0 0.0 0:17.22 kswapd5 3328 root 20 0 0 0 0 R 100.0 0.0 0:13.29 kswapd6 3332 root 20 0 0 0 0 R 100.0 0.0 0:11.11 kswapd10 3339 root 20 0 0 0 0 R 100.0 0.0 0:16.25 kswapd17 3348 root 20 0 0 0 0 R 100.0 0.0 0:16.40 kswapd26 3343 root 20 0 0 0 0 R 100.0 0.0 0:16.30 kswapd21 3344 root 20 0 0 0 0 R 100.0 0.0 0:11.92 kswapd22 3349 root 20 0 0 0 0 R 100.0 0.0 0:16.28 kswapd27 3352 root 20 0 0 0 0 R 99.7 0.0 0:11.89 kswapd30 3353 root 20 0 0 0 0 R 96.7 0.0 0:16.04 kswapd31 3329 root 20 0 0 0 0 R 96.4 0.0 0:11.41 kswapd7 3345 root 20 0 0 0 0 R 96.4 0.0 0:13.40 kswapd23 3330 root 20 0 0 0 0 S 91.1 0.0 0:08.28 kswapd8 3350 root 20 0 0 0 0 S 86.8 0.0 0:11.13 kswapd28 3325 root 20 0 0 0 0 S 76.3 0.0 0:07.43 kswapd3 3341 root 20 0 0 0 0 S 74.7 0.0 0:08.85 kswapd19 3334 root 20 0 0 0 0 S 71.7 0.0 0:10.04 kswapd12 3351 root 20 0 0 0 0 R 60.5 0.0 0:09.59 kswapd29 3323 root 20 0 0 0 0 R 57.6 0.0 0:11.50 kswapd1 [...] which is just showing a partial list of the 32 kswapd threads that are running mostly full tilt, burning ~28 full CPU cores. If the same test case is run with RWF_DONTCACHE set for the buffered read, the output looks as follows: Reading bs 65536, uncached 0 1s: 153144MB/sec 2s: 156760MB/sec 3s: 158110MB/sec 4s: 158009MB/sec 5s: 158043MB/sec 6s: 157638MB/sec 7s: 157999MB/sec 8s: 158024MB/sec 9s: 157764MB/sec 10s: 157477MB/sec 11s: 157417MB/sec 12s: 157455MB/sec 13s: 157233MB/sec 14s: 156692MB/sec which is just chugging along at ~155GB/sec of read performance. Looking at top, we see: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 7961 root 20 0 267004 0 0 S 3180 0.0 5:37.95 uncached 8024 axboe 20 0 14292 4096 0 R 1.0 0.0 0:00.13 top where just the test app is using CPU, no reclaim is taking place outside of the main thread. Not only is performance 65% better, it's also using half the CPU to do it. Link: https://lkml.kernel.org/r/20241220154831.1086649-9-axboe@kernel.dk Signed-off-by: Jens Axboe Cc: Brian Foster Cc: Chris Mason Cc: Christoph Hellwig Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- mm/filemap.c | 28 ++++++++++++++++++++++++++-- mm/swap.c | 2 ++ 2 files changed, 28 insertions(+), 2 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index a1fda00aa6bc..9eade935a48c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2445,6 +2445,8 @@ static int filemap_create_folio(struct kiocb *iocb, struct folio_batch *fbatch) folio = filemap_alloc_folio(mapping_gfp_mask(mapping), min_order); if (!folio) return -ENOMEM; + if (iocb->ki_flags & IOCB_DONTCACHE) + __folio_set_dropbehind(folio); /* * Protect against truncate / hole punch. Grabbing invalidate_lock @@ -2490,6 +2492,8 @@ static int filemap_readahead(struct kiocb *iocb, struct file *file, if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; + if (iocb->ki_flags & IOCB_DONTCACHE) + ractl.dropbehind = 1; page_cache_async_ra(&ractl, folio, last_index - folio->index); return 0; } @@ -2519,6 +2523,8 @@ retry: return -EAGAIN; if (iocb->ki_flags & IOCB_NOWAIT) flags = memalloc_noio_save(); + if (iocb->ki_flags & IOCB_DONTCACHE) + ractl.dropbehind = 1; page_cache_sync_ra(&ractl, last_index - index); if (iocb->ki_flags & IOCB_NOWAIT) memalloc_noio_restore(flags); @@ -2566,6 +2572,20 @@ static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio) return (pos1 >> shift == pos2 >> shift); } +static void filemap_end_dropbehind_read(struct address_space *mapping, + struct folio *folio) +{ + if (!folio_test_dropbehind(folio)) + return; + if (folio_test_writeback(folio) || folio_test_dirty(folio)) + return; + if (folio_trylock(folio)) { + if (folio_test_clear_dropbehind(folio)) + folio_unmap_invalidate(mapping, folio, 0); + folio_unlock(folio); + } +} + /** * filemap_read - Read data from the page cache. * @iocb: The iocb to read. @@ -2679,8 +2699,12 @@ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, } } put_folios: - for (i = 0; i < folio_batch_count(&fbatch); i++) - folio_put(fbatch.folios[i]); + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; + + filemap_end_dropbehind_read(mapping, folio); + folio_put(folio); + } folio_batch_init(&fbatch); } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); diff --git a/mm/swap.c b/mm/swap.c index 746a5ceba42c..fc8281ef4241 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -448,6 +448,8 @@ static bool lru_gen_clear_refs(struct folio *folio) */ void folio_mark_accessed(struct folio *folio) { + if (folio_test_dropbehind(folio)) + return; if (lru_gen_enabled()) { lru_gen_inc_refs(folio); return; -- 2.51.0 From fb7d3bc4149395c1ae99029c852eab6c28fc3c88 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Dec 2024 08:47:47 -0700 Subject: [PATCH 11/16] mm/filemap: drop streaming/uncached pages when writeback completes If the folio is marked as streaming, drop pages when writeback completes. Intended to be used with RWF_DONTCACHE, to avoid needing sync writes for uncached IO. Link: https://lkml.kernel.org/r/20241220154831.1086649-10-axboe@kernel.dk Signed-off-by: Jens Axboe Cc: Brian Foster Cc: Chris Mason Cc: Christoph Hellwig Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- mm/filemap.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/mm/filemap.c b/mm/filemap.c index 9eade935a48c..fb17b573ae51 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1571,6 +1571,27 @@ int folio_wait_private_2_killable(struct folio *folio) } EXPORT_SYMBOL(folio_wait_private_2_killable); +/* + * If folio was marked as dropbehind, then pages should be dropped when writeback + * completes. Do that now. If we fail, it's likely because of a big folio - + * just reset dropbehind for that case and latter completions should invalidate. + */ +static void folio_end_dropbehind_write(struct folio *folio) +{ + /* + * Hitting !in_task() should not happen off RWF_DONTCACHE writeback, + * but can happen if normal writeback just happens to find dirty folios + * that were created as part of uncached writeback, and that writeback + * would otherwise not need non-IRQ handling. Just skip the + * invalidation in that case. + */ + if (in_task() && folio_trylock(folio)) { + if (folio->mapping) + folio_unmap_invalidate(folio->mapping, folio, 0); + folio_unlock(folio); + } +} + /** * folio_end_writeback - End writeback against a folio. * @folio: The folio. @@ -1581,6 +1602,8 @@ EXPORT_SYMBOL(folio_wait_private_2_killable); */ void folio_end_writeback(struct folio *folio) { + bool folio_dropbehind = false; + VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* @@ -1602,9 +1625,14 @@ void folio_end_writeback(struct folio *folio) * reused before the folio_wake_bit(). */ folio_get(folio); + if (!folio_test_dirty(folio)) + folio_dropbehind = folio_test_clear_dropbehind(folio); if (__folio_end_writeback(folio)) folio_wake_bit(folio, PG_writeback); acct_reclaim_writeback(folio); + + if (folio_dropbehind) + folio_end_dropbehind_write(folio); folio_put(folio); } EXPORT_SYMBOL(folio_end_writeback); -- 2.51.0 From dddc559f2e7cff9c6525150cd29ef3a4f6692b26 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Dec 2024 08:47:48 -0700 Subject: [PATCH 12/16] mm/filemap: add filemap_fdatawrite_range_kick() helper Works like filemap_fdatawrite_range(), except it's a non-integrity data writeback and hence only starts writeback on the specified range. Will help facilitate generically starting uncached writeback from generic_write_sync(), as header dependencies preclude doing this inline from fs.h. Link: https://lkml.kernel.org/r/20241220154831.1086649-11-axboe@kernel.dk Signed-off-by: Jens Axboe Cc: Brian Foster Cc: Chris Mason Cc: Christoph Hellwig Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/fs.h | 2 ++ mm/filemap.c | 18 ++++++++++++++++++ 2 files changed, 20 insertions(+) diff --git a/include/linux/fs.h b/include/linux/fs.h index 6a838b5479a6..653b5efa3d3f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2878,6 +2878,8 @@ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); +int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, + loff_t end); static inline int file_write_and_wait(struct file *file) { diff --git a/mm/filemap.c b/mm/filemap.c index fb17b573ae51..0aa3861aed45 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -440,6 +440,24 @@ int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, } EXPORT_SYMBOL(filemap_fdatawrite_range); +/** + * filemap_fdatawrite_range_kick - start writeback on a range + * @mapping: target address_space + * @start: index to start writeback on + * @end: last (non-inclusive) index for writeback + * + * This is a non-integrity writeback helper, to start writing back folios + * for the indicated range. + * + * Return: %0 on success, negative error code otherwise. + */ +int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, + loff_t end) +{ + return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_NONE); +} +EXPORT_SYMBOL_GPL(filemap_fdatawrite_range_kick); + /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space -- 2.51.0 From 1d4457576570627e1702614bc060b55d95b85e39 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Dec 2024 08:47:49 -0700 Subject: [PATCH 13/16] mm: call filemap_fdatawrite_range_kick() after IOCB_DONTCACHE issue When a buffered write submitted with IOCB_DONTCACHE has been successfully submitted, call filemap_fdatawrite_range_kick() to kick off the IO. File systems call generic_write_sync() for any successful buffered write submission, hence add the logic here rather than needing to modify the file system. Link: https://lkml.kernel.org/r/20241220154831.1086649-12-axboe@kernel.dk Signed-off-by: Jens Axboe Cc: Brian Foster Cc: Chris Mason Cc: Christoph Hellwig Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/linux/fs.h b/include/linux/fs.h index 653b5efa3d3f..58a618853574 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2912,6 +2912,11 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) (iocb->ki_flags & IOCB_SYNC) ? 0 : 1); if (ret) return ret; + } else if (iocb->ki_flags & IOCB_DONTCACHE) { + struct address_space *mapping = iocb->ki_filp->f_mapping; + + filemap_fdatawrite_range_kick(mapping, iocb->ki_pos, + iocb->ki_pos + count); } return count; -- 2.51.0 From d94d23fdd7529f1f3218235d1e0a69e9856907b7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 20 Dec 2024 08:47:50 -0700 Subject: [PATCH 14/16] mm: add FGP_DONTCACHE folio creation flag Callers can pass this in for uncached folio creation, in which case if a folio is newly created it gets marked as uncached. If a folio exists for this index and lookup succeeds, then it will not get marked as uncached. If an !uncached lookup finds a cached folio, clear the flag. For that case, there are competeting uncached and cached users of the folio, and it should not get pruned. Link: https://lkml.kernel.org/r/20241220154831.1086649-13-axboe@kernel.dk Signed-off-by: Jens Axboe Cc: Brian Foster Cc: Chris Mason Cc: Christoph Hellwig Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- include/linux/pagemap.h | 2 ++ mm/filemap.c | 5 +++++ 2 files changed, 7 insertions(+) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d53c49abead6..47bfc6b1b632 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -710,6 +710,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, * * %FGP_NOFS - __GFP_FS will get cleared in gfp. * * %FGP_NOWAIT - Don't block on the folio lock. * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) + * * %FGP_DONTCACHE - Uncached buffered IO * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin() * implementation. */ @@ -723,6 +724,7 @@ typedef unsigned int __bitwise fgf_t; #define FGP_NOWAIT ((__force fgf_t)0x00000020) #define FGP_FOR_MMAP ((__force fgf_t)0x00000040) #define FGP_STABLE ((__force fgf_t)0x00000080) +#define FGP_DONTCACHE ((__force fgf_t)0x00000100) #define FGF_GET_ORDER(fgf) (((__force unsigned)fgf) >> 26) /* top 6 bits */ #define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) diff --git a/mm/filemap.c b/mm/filemap.c index 0aa3861aed45..279959cf9300 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1973,6 +1973,8 @@ no_page: /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __folio_set_referenced(folio); + if (fgp_flags & FGP_DONTCACHE) + __folio_set_dropbehind(folio); err = filemap_add_folio(mapping, folio, index, gfp); if (!err) @@ -1995,6 +1997,9 @@ no_page: if (!folio) return ERR_PTR(-ENOENT); + /* not an uncached lookup, clear uncached if set */ + if (folio_test_dropbehind(folio) && !(fgp_flags & FGP_DONTCACHE)) + folio_clear_dropbehind(folio); return folio; } EXPORT_SYMBOL(__filemap_get_folio); -- 2.51.0 From 73519ded992fc9dda2807450d6931002bb93cb16 Mon Sep 17 00:00:00 2001 From: liuye Date: Tue, 14 Jan 2025 11:21:15 +0800 Subject: [PATCH 15/16] selftests/memfd/memfd_test: fix possible NULL pointer dereference If `name' is NULL, a NULL pointer may be accessed in printf. Link: https://lkml.kernel.org/r/20250114032115.58638-1-liuye@kylinos.cn Signed-off-by: liuye Reviewed-by: Lorenzo Stoakes Cc: Greg Thelen Cc: "Isaac J. Manjarres" Cc: Jeff Xu Cc: Saurav Shah Cc: Shuah Khan (Samsung OSG) Signed-off-by: Andrew Morton --- tools/testing/selftests/memfd/memfd_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index c0c53451a16d..5b993924cc3f 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -171,7 +171,7 @@ static void mfd_fail_new(const char *name, unsigned int flags) r = sys_memfd_create(name, flags); if (r >= 0) { printf("memfd_create(\"%s\", %u) succeeded, but failure expected\n", - name, flags); + name ? name : "NULL", flags); close(r); abort(); } -- 2.51.0 From a005145b9c969651a8997725e1df35c81040f76b Mon Sep 17 00:00:00 2001 From: =?utf8?q?Thomas=20Wei=C3=9Fschuh?= Date: Tue, 14 Jan 2025 17:06:45 +0100 Subject: [PATCH 16/16] selftests/mm: virtual_address_range: mmap() without PROT_WRITE MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Patch series "selftests/mm: virtual_address_range: Reduce memory", v4. The selftest started failing since commit e93d2521b27f ("x86/vdso: Split virtual clock pages into dedicated mapping") was merged. While debugging I stumbled upon some memory usage optimizations. With these test now runs on a VM with only 60MiB of memory. This patch (of 4): When mapping a larger chunk than physical memory is available with PROT_WRITE and overcommit is disabled, the mapping will fail. This will prevent the test from running on systems with less then ~1GiB of memory and triggering an inscrutinable test failure. As the mappings are never written to anyways, the flag can be removed. Link: https://lkml.kernel.org/r/20250114-virtual_address_range-tests-v4-0-6fd7269934a5@linutronix.de Link: https://lkml.kernel.org/r/20250114-virtual_address_range-tests-v4-1-6fd7269934a5@linutronix.de Fixes: 4e5ce33ceb32 ("selftests/vm: add a test for virtual address range mapping") Signed-off-by: Thomas Weißschuh Acked-by: David Hildenbrand Acked-by: Dev Jain Cc: Thomas Gleixner Cc: Anshuman Khandual Cc: Shuah Khan (Samsung OSG) Cc: kernel test robot Signed-off-by: Andrew Morton --- tools/testing/selftests/mm/virtual_address_range.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index 2a2b69e91950..ea6ccf49ef4c 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -166,7 +166,7 @@ int main(int argc, char *argv[]) ksft_set_plan(1); for (i = 0; i < NR_CHUNKS_LOW; i++) { - ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, + ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (ptr[i] == MAP_FAILED) { @@ -186,7 +186,7 @@ int main(int argc, char *argv[]) for (i = 0; i < NR_CHUNKS_HIGH; i++) { hint = hint_addr(); - hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, + hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (hptr[i] == MAP_FAILED) -- 2.51.0