From: Luis Chamberlain <mcgrof@kernel.org>
To: akpm@linux-foundation.org, willy@infradead.org,
djwong@kernel.org, brauner@kernel.org, david@fromorbit.com,
chandan.babu@oracle.com
Cc: hare@suse.de, ritesh.list@gmail.com, john.g.garry@oracle.com,
ziy@nvidia.com, linux-fsdevel@vger.kernel.org,
linux-xfs@vger.kernel.org, linux-mm@kvack.org,
linux-block@vger.kernel.org, gost.dev@samsung.com,
p.raghav@samsung.com, kernel@pankajraghav.com, mcgrof@kernel.org
Subject: [PATCH v5 02/11] fs: Allow fine-grained control of folio sizes
Date: Fri, 3 May 2024 02:53:44 -0700 [thread overview]
Message-ID: <20240503095353.3798063-3-mcgrof@kernel.org> (raw)
In-Reply-To: <20240503095353.3798063-1-mcgrof@kernel.org>
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Some filesystems want to be able to ensure that folios that are added to
the page cache are at least a certain size.
Add mapping_set_folio_min_order() to allow this level of control.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Co-developed-by: Pankaj Raghav <p.raghav@samsung.com>
Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
include/linux/pagemap.h | 116 +++++++++++++++++++++++++++++++++-------
1 file changed, 96 insertions(+), 20 deletions(-)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 2df35e65557d..2e5612de1749 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -202,13 +202,18 @@ enum mapping_flags {
AS_EXITING = 4, /* final truncate in progress */
/* writeback related tags are not used */
AS_NO_WRITEBACK_TAGS = 5,
- AS_LARGE_FOLIO_SUPPORT = 6,
- AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */
- AS_STABLE_WRITES, /* must wait for writeback before modifying
+ AS_RELEASE_ALWAYS = 6, /* Call ->release_folio(), even if no private data */
+ AS_STABLE_WRITES = 7, /* must wait for writeback before modifying
folio contents */
- AS_UNMOVABLE, /* The mapping cannot be moved, ever */
+ AS_FOLIO_ORDER_MIN = 8,
+ AS_FOLIO_ORDER_MAX = 13, /* Bit 8-17 are used for FOLIO_ORDER */
+ AS_UNMOVABLE = 18, /* The mapping cannot be moved, ever */
};
+#define AS_FOLIO_ORDER_MIN_MASK 0x00001f00
+#define AS_FOLIO_ORDER_MAX_MASK 0x0003e000
+#define AS_FOLIO_ORDER_MASK (AS_FOLIO_ORDER_MIN_MASK | AS_FOLIO_ORDER_MAX_MASK)
+
/**
* mapping_set_error - record a writeback error in the address_space
* @mapping: the mapping in which an error should be set
@@ -344,9 +349,63 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
m->gfp_mask = mask;
}
+/*
+ * There are some parts of the kernel which assume that PMD entries
+ * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then,
+ * limit the maximum allocation order to PMD size. I'm not aware of any
+ * assumptions about maximum order if THP are disabled, but 8 seems like
+ * a good order (that's 1MB if you're using 4kB pages)
+ */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER
+#else
+#define MAX_PAGECACHE_ORDER 8
+#endif
+
+/*
+ * mapping_set_folio_order_range() - Set the folio order range
+ * @mapping: The address_space.
+ * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive).
+ * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive).
+ *
+ * The filesystem should call this function in its inode constructor to
+ * indicate which base size (min) and maximum size (max) of folio the VFS
+ * can use to cache the contents of the file. This should only be used
+ * if the filesystem needs special handling of folio sizes (ie there is
+ * something the core cannot know).
+ * Do not tune it based on, eg, i_size.
+ *
+ * Context: This should not be called while the inode is active as it
+ * is non-atomic.
+ */
+static inline void mapping_set_folio_order_range(struct address_space *mapping,
+ unsigned int min_order,
+ unsigned int max_order)
+{
+ if (min_order > MAX_PAGECACHE_ORDER)
+ min_order = MAX_PAGECACHE_ORDER;
+
+ if (max_order > MAX_PAGECACHE_ORDER)
+ max_order = MAX_PAGECACHE_ORDER;
+
+ max_order = max(max_order, min_order);
+ /*
+ * TODO: max_order is not yet supported in filemap.
+ */
+ mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) |
+ (min_order << AS_FOLIO_ORDER_MIN) |
+ (max_order << AS_FOLIO_ORDER_MAX);
+}
+
+static inline void mapping_set_folio_min_order(struct address_space *mapping,
+ unsigned int min)
+{
+ mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER);
+}
+
/**
* mapping_set_large_folios() - Indicate the file supports large folios.
- * @mapping: The file.
+ * @mapping: The address_space.
*
* The filesystem should call this function in its inode constructor to
* indicate that the VFS can use large folios to cache the contents of
@@ -357,7 +416,37 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
*/
static inline void mapping_set_large_folios(struct address_space *mapping)
{
- __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
+ mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER);
+}
+
+static inline unsigned int mapping_max_folio_order(struct address_space *mapping)
+{
+ return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX;
+}
+
+static inline unsigned int mapping_min_folio_order(struct address_space *mapping)
+{
+ return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN;
+}
+
+static inline unsigned long mapping_min_folio_nrpages(struct address_space *mapping)
+{
+ return 1UL << mapping_min_folio_order(mapping);
+}
+
+/**
+ * mapping_align_start_index() - Align starting index based on the min
+ * folio order of the page cache.
+ * @mapping: The address_space.
+ *
+ * Ensure the index used is aligned to the minimum folio order when adding
+ * new folios to the page cache by rounding down to the nearest minimum
+ * folio number of pages.
+ */
+static inline pgoff_t mapping_align_start_index(struct address_space *mapping,
+ pgoff_t index)
+{
+ return round_down(index, mapping_min_folio_nrpages(mapping));
}
/*
@@ -367,7 +456,7 @@ static inline void mapping_set_large_folios(struct address_space *mapping)
static inline bool mapping_large_folio_support(struct address_space *mapping)
{
return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
- test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
+ (mapping_max_folio_order(mapping) > 0);
}
static inline int filemap_nr_thps(struct address_space *mapping)
@@ -528,19 +617,6 @@ static inline void *detach_page_private(struct page *page)
return folio_detach_private(page_folio(page));
}
-/*
- * There are some parts of the kernel which assume that PMD entries
- * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then,
- * limit the maximum allocation order to PMD size. I'm not aware of any
- * assumptions about maximum order if THP are disabled, but 8 seems like
- * a good order (that's 1MB if you're using 4kB pages)
- */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER
-#else
-#define MAX_PAGECACHE_ORDER 8
-#endif
-
#ifdef CONFIG_NUMA
struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order);
#else
--
2.43.0
next prev parent reply other threads:[~2024-05-03 11:34 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-03 9:53 [PATCH v5 00/11] enable bs > ps in XFS Luis Chamberlain
2024-05-03 9:53 ` [PATCH v5 01/11] readahead: rework loop in page_cache_ra_unbounded() Luis Chamberlain
2024-05-03 9:53 ` Luis Chamberlain [this message]
2024-05-03 9:53 ` [PATCH v5 03/11] filemap: allocate mapping_min_order folios in the page cache Luis Chamberlain
2024-05-03 9:53 ` [PATCH v5 04/11] readahead: allocate folios with mapping_min_order in readahead Luis Chamberlain
2024-05-03 14:32 ` Hannes Reinecke
2024-05-03 9:53 ` [PATCH v5 05/11] mm: split a folio in minimum folio order chunks Luis Chamberlain
2024-05-03 14:53 ` Zi Yan
2024-05-15 15:32 ` Matthew Wilcox
2024-05-16 14:56 ` Pankaj Raghav (Samsung)
2024-05-03 9:53 ` [PATCH v5 06/11] filemap: cap PTE range to be created to allowed zero fill in folio_map_range() Luis Chamberlain
2024-05-03 9:53 ` [PATCH v5 07/11] iomap: fix iomap_dio_zero() for fs bs > system page size Luis Chamberlain
2024-05-07 14:58 ` [RFC] iomap: use huge zero folio in iomap_dio_zero Pankaj Raghav (Samsung)
2024-05-07 15:11 ` Zi Yan
2024-05-07 16:11 ` Christoph Hellwig
2024-05-08 11:39 ` Pankaj Raghav (Samsung)
2024-05-08 11:43 ` Christoph Hellwig
2024-05-09 12:31 ` Pankaj Raghav (Samsung)
2024-05-09 12:46 ` Christoph Hellwig
2024-05-09 12:55 ` Pankaj Raghav (Samsung)
2024-05-09 12:58 ` Christoph Hellwig
2024-05-09 14:32 ` Darrick J. Wong
2024-05-09 15:05 ` Christoph Hellwig
2024-05-09 15:08 ` Darrick J. Wong
2024-05-09 15:09 ` Christoph Hellwig
2024-05-15 0:50 ` Matthew Wilcox
2024-05-15 2:34 ` Keith Busch
2024-05-15 4:04 ` Matthew Wilcox
2024-05-15 15:59 ` Pankaj Raghav (Samsung)
2024-05-15 18:03 ` Matthew Wilcox
2024-05-16 15:02 ` Pankaj Raghav (Samsung)
2024-05-17 12:36 ` Hannes Reinecke
2024-05-17 12:56 ` Hannes Reinecke
2024-05-17 13:30 ` Matthew Wilcox
2024-05-15 11:48 ` Christoph Hellwig
2024-05-07 16:00 ` [PATCH v5 07/11] iomap: fix iomap_dio_zero() for fs bs > system page size Matthew Wilcox
2024-05-07 16:10 ` Christoph Hellwig
2024-05-07 16:11 ` Matthew Wilcox
2024-05-07 16:13 ` Christoph Hellwig
2024-05-08 4:24 ` Matthew Wilcox
2024-05-08 11:22 ` Pankaj Raghav (Samsung)
2024-05-08 11:36 ` Christoph Hellwig
2024-05-08 11:20 ` Pankaj Raghav (Samsung)
2024-05-03 9:53 ` [PATCH v5 08/11] xfs: use kvmalloc for xattr buffers Luis Chamberlain
2024-05-03 9:53 ` [PATCH v5 09/11] xfs: expose block size in stat Luis Chamberlain
2024-05-03 9:53 ` [PATCH v5 10/11] xfs: make the calculation generic in xfs_sb_validate_fsb_count() Luis Chamberlain
2024-05-07 8:40 ` John Garry
2024-05-07 21:13 ` Darrick J. Wong
2024-05-08 11:28 ` Pankaj Raghav (Samsung)
2024-05-03 9:53 ` [PATCH v5 11/11] xfs: enable block size larger than page size support Luis Chamberlain
2024-05-07 0:05 ` Dave Chinner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240503095353.3798063-3-mcgrof@kernel.org \
--to=mcgrof@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=brauner@kernel.org \
--cc=chandan.babu@oracle.com \
--cc=david@fromorbit.com \
--cc=djwong@kernel.org \
--cc=gost.dev@samsung.com \
--cc=hare@suse.de \
--cc=john.g.garry@oracle.com \
--cc=kernel@pankajraghav.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@vger.kernel.org \
--cc=p.raghav@samsung.com \
--cc=ritesh.list@gmail.com \
--cc=willy@infradead.org \
--cc=ziy@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).