Linux-Fsdevel Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Matthew Wilcox <willy@infradead.org>
To: linux-fsdevel@vger.kernel.org
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: [PATCH v6 42/51] mm: Handle truncates that split THPs
Date: Wed, 10 Jun 2020 13:13:36 -0700	[thread overview]
Message-ID: <20200610201345.13273-43-willy@infradead.org> (raw)
In-Reply-To: <20200610201345.13273-1-willy@infradead.org>

From: "Matthew Wilcox (Oracle)" <willy@infradead.org>

Move shmem_punch_compound() to truncate.c and rename it to punch_thp().
Change its arguments to loff_t to make calling do_invalidatepage()
easier.  Call it when we find a THP in the cache.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 mm/internal.h |  2 ++
 mm/shmem.c    | 30 ++-------------------------
 mm/truncate.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 59 insertions(+), 30 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index ac3c79408045..cd7038a36354 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -613,4 +613,6 @@ static inline bool is_migrate_highatomic_page(struct page *page)
 
 void setup_zone_pageset(struct zone *zone);
 extern struct page *alloc_new_node_page(struct page *page, unsigned long node);
+
+bool punch_thp(struct page *page, loff_t start, loff_t end);
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/shmem.c b/mm/shmem.c
index 55405d811cfd..495b8684d94a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -804,32 +804,6 @@ void shmem_unlock_mapping(struct address_space *mapping)
 	}
 }
 
-/*
- * Check whether a hole-punch or truncation needs to split a huge page,
- * returning true if no split was required, or the split has been successful.
- *
- * Eviction (or truncation to 0 size) should never need to split a huge page;
- * but in rare cases might do so, if shmem_undo_range() failed to trylock on
- * head, and then succeeded to trylock on tail.
- *
- * A split can only succeed when there are no additional references on the
- * huge page: so the split below relies upon find_get_entries() having stopped
- * when it found a subpage of the huge page, without getting further references.
- */
-static bool shmem_punch_compound(struct page *page, pgoff_t start, pgoff_t end)
-{
-	if (!PageTransCompound(page))
-		return true;
-
-	/* Just proceed to delete a huge page wholly within the range punched */
-	if (PageHead(page) &&
-	    page->index >= start && page->index + HPAGE_PMD_NR <= end)
-		return true;
-
-	/* Try to split huge page, so we can truly punch the hole or truncate */
-	return split_huge_page(page) >= 0;
-}
-
 /*
  * Remove range of pages and swap entries from page cache, and free them.
  * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
@@ -883,7 +857,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			if ((!unfalloc || !PageUptodate(page)) &&
 			    page_mapping(page) == mapping) {
 				VM_BUG_ON_PAGE(PageWriteback(page), page);
-				if (shmem_punch_compound(page, start, end))
+				if (punch_thp(page, lstart, lend))
 					truncate_inode_page(mapping, page);
 			}
 			unlock_page(page);
@@ -973,7 +947,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 					break;
 				}
 				VM_BUG_ON_PAGE(PageWriteback(page), page);
-				if (shmem_punch_compound(page, start, end))
+				if (punch_thp(page, lstart, lend))
 					truncate_inode_page(mapping, page);
 				else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
 					/* Wipe the page and don't get stuck */
diff --git a/mm/truncate.c b/mm/truncate.c
index a9fde773179b..0ef2001c2f65 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -229,6 +229,55 @@ int truncate_inode_page(struct address_space *mapping, struct page *page)
 	return 0;
 }
 
+/*
+ * Check whether a hole-punch or truncation needs to split a huge page,
+ * returning true if no split was required, or the split has been
+ * successful.
+ *
+ * Eviction (or truncation to 0 size) should never need to split a huge
+ * page; but in rare cases might do so, if shmem_undo_range() failed to
+ * trylock on head, and then succeeded to trylock on tail.
+ *
+ * A split can only succeed when there are no additional references on
+ * the huge page: so the split below relies upon find_get_entries()
+ * having stopped when it found a subpage of the huge page, without
+ * getting further references.
+ */
+bool punch_thp(struct page *page, loff_t start, loff_t end)
+{
+	struct page *head = thp_head(page);
+	loff_t pos = page_offset(head);
+	unsigned int offset, length;
+
+	if (!PageTransCompound(page))
+		return true;
+
+	if (pos < start)
+		offset = start - pos;
+	else
+		offset = 0;
+	length = thp_size(head);
+	if (pos + length < end)
+		length = length - offset;
+	else
+		length = end - pos - offset;
+
+	/* Just proceed to delete a huge page wholly within the range punched */
+	if (length == thp_size(head))
+		return true;
+
+	/*
+	 * We're going to split the page into order-0 pages.  Tell the
+	 * filesystem which range of the page is going to be punched out
+	 * so it can discard unnecessary private data.
+	 */
+	if (page_has_private(head))
+		do_invalidatepage(head, offset, length);
+
+	/* Try to split huge page, so we can truly punch the hole or truncate */
+	return split_huge_page(page) >= 0;
+}
+
 /*
  * Used to get rid of pages on hardware memory corruption.
  */
@@ -359,7 +408,10 @@ void truncate_inode_pages_range(struct address_space *mapping,
 				unlock_page(page);
 				continue;
 			}
-			pagevec_add(&locked_pvec, page);
+			if (punch_thp(page, lstart, lend))
+				pagevec_add(&locked_pvec, page);
+			else
+				unlock_page(page);
 		}
 		for (i = 0; i < pagevec_count(&locked_pvec); i++)
 			truncate_cleanup_page(mapping, locked_pvec.pages[i]);
@@ -453,7 +505,8 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			lock_page(page);
 			WARN_ON(page_to_index(page) != index);
 			wait_on_page_writeback(page);
-			truncate_inode_page(mapping, page);
+			if (punch_thp(page, lstart, lend))
+				truncate_inode_page(mapping, page);
 			unlock_page(page);
 		}
 		truncate_exceptional_pvec_entries(mapping, &pvec, indices, end);
-- 
2.26.2


  parent reply	other threads:[~2020-06-10 20:16 UTC|newest]

Thread overview: 60+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-10 20:12 [RFC v6 00/51] Large pages in the page cache Matthew Wilcox
2020-06-10 20:12 ` [PATCH v6 01/51] mm: Print head flags in dump_page Matthew Wilcox
2020-06-10 20:12 ` [PATCH v6 02/51] mm: Print the inode number " Matthew Wilcox
2020-06-10 20:12 ` [PATCH v6 03/51] mm: Print hashed address of struct page Matthew Wilcox
2020-06-10 20:12 ` [PATCH v6 04/51] mm: Move PageDoubleMap bit Matthew Wilcox
2020-06-11 15:03   ` Zi Yan
2020-06-10 20:12 ` [PATCH v6 05/51] mm: Simplify PageDoubleMap with PF_SECOND policy Matthew Wilcox
2020-06-11 15:14   ` Zi Yan
2020-06-10 20:13 ` [PATCH v6 06/51] mm: Store compound_nr as well as compound_order Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 07/51] mm: Move page-flags include to top of file Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 08/51] mm: Add thp_order Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 09/51] mm: Add thp_size Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 10/51] mm: Replace hpage_nr_pages with thp_nr_pages Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 11/51] mm: Add thp_head Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 12/51] mm: Introduce offset_in_thp Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 13/51] mm: Support arbitrary THP sizes Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 14/51] fs: Add a filesystem flag for THPs Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 15/51] fs: Do not update nr_thps for mappings which support THPs Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 16/51] fs: Introduce i_blocks_per_page Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 17/51] fs: Make page_mkwrite_check_truncate thp-aware Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 18/51] mm: Support THPs in zero_user_segments Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 19/51] mm: Zero the head page, not the tail page Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 20/51] block: Add bio_for_each_thp_segment_all Matthew Wilcox
2020-06-11 18:20   ` Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 21/51] block: Support THPs in page_is_mergeable Matthew Wilcox
2020-06-12 16:17   ` Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 22/51] iomap: Support arbitrarily many blocks per page Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 23/51] iomap: Support THPs in iomap_adjust_read_range Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 24/51] iomap: Support THPs in invalidatepage Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 25/51] iomap: Support THPs in read paths Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 26/51] iomap: Convert iomap_write_end types Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 27/51] iomap: Change calling convention for zeroing Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 28/51] iomap: Change iomap_write_begin calling convention Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 29/51] iomap: Support THPs in write paths Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 30/51] iomap: Inline data shouldn't see THPs Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 31/51] iomap: Handle tail pages in iomap_page_mkwrite Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 32/51] xfs: Support THPs Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 33/51] mm: Make prep_transhuge_page return its argument Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 34/51] mm: Add __page_cache_alloc_order Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 35/51] mm: Allow THPs to be added to the page cache Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 36/51] mm: Allow THPs to be removed from " Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 37/51] mm: Remove page fault assumption of compound page size Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 38/51] mm: Fix total_mapcount assumption of " Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 39/51] mm: Remove assumptions of THP size Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 40/51] mm: Avoid splitting THPs Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 41/51] mm: Fix truncation for pages of arbitrary size Matthew Wilcox
2020-06-10 20:13 ` Matthew Wilcox [this message]
2020-06-10 20:13 ` [PATCH v6 43/51] mm: Support storing shadow entries for THPs Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 44/51] mm: Support retrieving tail pages from the page cache Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 45/51] mm: Support tail pages in wait_for_stable_page Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 46/51] mm: Add DEFINE_READAHEAD Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 47/51] mm: Make page_cache_readahead_unbounded take a readahead_control Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 48/51] mm: Make __do_page_cache_readahead " Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 49/51] mm: Allow PageReadahead to be set on head pages Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 50/51] mm: Add THP readahead Matthew Wilcox
2020-06-10 20:13 ` [PATCH v6 51/51] mm: Align THP mappings for non-DAX Matthew Wilcox
2020-06-11  6:59 ` [RFC v6 00/51] Large pages in the page cache Christoph Hellwig
2020-06-11 11:24   ` Matthew Wilcox
2020-06-15 13:32     ` Christoph Hellwig
2020-06-14 16:26 ` Matthew Wilcox

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=20200610201345.13273-43-willy@infradead.org \
    --to=willy@infradead.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --subject='Re: [PATCH v6 42/51] mm: Handle truncates that split THPs' \
    /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

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 NNTP newsgroup(s).