linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To: "Theodore Ts'o" <tytso@mit.edu>,
	Andreas Dilger <adilger.kernel@dilger.ca>,
	Jan Kara <jack@suse.com>,
	Andrew Morton <akpm@linux-foundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>,
	Hugh Dickins <hughd@google.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Dave Hansen <dave.hansen@intel.com>,
	Vlastimil Babka <vbabka@suse.cz>,
	Matthew Wilcox <willy@infradead.org>,
	Ross Zwisler <ross.zwisler@linux.intel.com>,
	linux-ext4@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	linux-block@vger.kernel.org,
	Matthew Wilcox <willy@linux.intel.com>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCHv4 05/43] radix-tree: Add radix_tree_split_preload()
Date: Tue, 25 Oct 2016 03:13:04 +0300	[thread overview]
Message-ID: <20161025001342.76126-6-kirill.shutemov@linux.intel.com> (raw)
In-Reply-To: <20161025001342.76126-1-kirill.shutemov@linux.intel.com>

From: Matthew Wilcox <willy@linux.intel.com>

Calculate how many nodes we need to allocate to split an old_order entry
into multiple entries, each of size new_order.  The test suite checks that
we allocated exactly the right number of nodes; neither too many (checked
by rtp->nr == 0), nor too few (checked by comparing nr_allocated before
and after the call to radix_tree_split()).

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 include/linux/radix-tree.h            |  1 +
 lib/radix-tree.c                      | 22 ++++++++++++++++++++++
 tools/testing/radix-tree/multiorder.c | 28 ++++++++++++++++++++++++++--
 tools/testing/radix-tree/test.h       |  9 +++++++++
 4 files changed, 58 insertions(+), 2 deletions(-)

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index f5518f1fe3d7..8ffb0518ae9a 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -319,6 +319,7 @@ static inline void radix_tree_preload_end(void)
 	preempt_enable();
 }
 
+int radix_tree_split_preload(unsigned old_order, unsigned new_order, gfp_t);
 int radix_tree_split(struct radix_tree_root *, unsigned long index,
 			unsigned new_order);
 int radix_tree_join(struct radix_tree_root *, unsigned long index,
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index c1b835c979ed..d36cff71d225 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -410,6 +410,28 @@ int radix_tree_maybe_preload(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(radix_tree_maybe_preload);
 
+#ifdef CONFIG_RADIX_TREE_MULTIORDER
+/*
+ * Preload with enough objects to ensure that we can split a single entry
+ * of order @old_order into many entries of size @new_order
+ */
+int radix_tree_split_preload(unsigned int old_order, unsigned int new_order,
+							gfp_t gfp_mask)
+{
+	unsigned top = 1 << (old_order % RADIX_TREE_MAP_SHIFT);
+	unsigned layers = (old_order / RADIX_TREE_MAP_SHIFT) -
+				(new_order / RADIX_TREE_MAP_SHIFT);
+	unsigned nr = 0;
+
+	WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask));
+	BUG_ON(new_order >= old_order);
+
+	while (layers--)
+		nr = nr * RADIX_TREE_MAP_SIZE + 1;
+	return __radix_tree_preload(gfp_mask, top * nr);
+}
+#endif
+
 /*
  * The same as function above, but preload number of nodes required to insert
  * (1 << order) continuous naturally-aligned elements.
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index d9e81553c682..1cac86e74bdc 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -356,18 +356,42 @@ static void multiorder_join(void)
 	}
 }
 
+static void check_mem(unsigned old_order, unsigned new_order, unsigned alloc)
+{
+	struct radix_tree_preload *rtp = &radix_tree_preloads;
+	if (rtp->nr != 0)
+		printf("split(%u %u) remaining %u\n", old_order, new_order,
+							rtp->nr);
+	/*
+	 * Can't check for equality here as some nodes may have been
+	 * RCU-freed while we ran.  But we should never finish with more
+	 * nodes allocated since they should have all been preloaded.
+	 */
+	if (nr_allocated > alloc)
+		printf("split(%u %u) allocated %u %u\n", old_order, new_order,
+							alloc, nr_allocated);
+}
+
 static void __multiorder_split(int old_order, int new_order)
 {
-	RADIX_TREE(tree, GFP_KERNEL);
+	RADIX_TREE(tree, GFP_ATOMIC);
 	void **slot;
 	struct radix_tree_iter iter;
+	unsigned alloc;
 
-	item_insert_order(&tree, 0, old_order);
+	radix_tree_preload(GFP_KERNEL);
+	assert(item_insert_order(&tree, 0, old_order) == 0);
+	radix_tree_callback(NULL, CPU_DEAD, NULL);
 	radix_tree_tag_set(&tree, 0, 2);
+
+	radix_tree_split_preload(old_order, new_order, GFP_KERNEL);
+	alloc = nr_allocated;
 	radix_tree_split(&tree, 0, new_order);
+	check_mem(old_order, new_order, alloc);
 	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
 		radix_tree_replace_slot(slot, item_create(iter.index));
 	}
+	radix_tree_preload_end();
 
 	item_kill_tree(&tree);
 }
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index 217fb2403f09..91ed0e3bd275 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -2,6 +2,8 @@
 #include <linux/types.h>
 #include <linux/radix-tree.h>
 #include <linux/rcupdate.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
 
 struct item {
 	unsigned long index;
@@ -44,3 +46,10 @@ void radix_tree_dump(struct radix_tree_root *root);
 int root_tag_get(struct radix_tree_root *root, unsigned int tag);
 unsigned long node_maxindex(struct radix_tree_node *);
 unsigned long shift_maxindex(unsigned int shift);
+int radix_tree_callback(struct notifier_block *nfb,
+			unsigned long action, void *hcpu);
+struct radix_tree_preload {
+	unsigned nr;
+	struct radix_tree_node *nodes;
+};
+extern struct radix_tree_preload radix_tree_preloads;
-- 
2.9.3

  parent reply	other threads:[~2016-10-25  0:14 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-10-25  0:12 [PATCHv4 00/43] ext4: support of huge pages Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 01/43] tools: Add WARN_ON_ONCE Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 02/43] radix tree test suite: Allow GFP_ATOMIC allocations to fail Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 03/43] radix-tree: Add radix_tree_join Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 04/43] radix-tree: Add radix_tree_split Kirill A. Shutemov
2016-10-25  0:13 ` Kirill A. Shutemov [this message]
2016-10-25  0:13 ` [PATCHv4 06/43] mm, shmem: swich huge tmpfs to multi-order radix-tree entries Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 07/43] Revert "radix-tree: implement radix_tree_maybe_preload_order()" Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 08/43] page-flags: relax page flag policy for few flags Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 09/43] mm, rmap: account file thp pages Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 10/43] thp: try to free page's buffers before attempt split Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 11/43] thp: handle write-protection faults for file THP Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 12/43] truncate: make sure invalidate_mapping_pages() can discard huge pages Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 13/43] filemap: allocate huge page in page_cache_read(), if allowed Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 14/43] filemap: handle huge pages in do_generic_file_read() Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 15/43] filemap: allocate huge page in pagecache_get_page(), if allowed Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 16/43] filemap: handle huge pages in filemap_fdatawait_range() Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 17/43] HACK: readahead: alloc huge pages, if allowed Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 18/43] block: define BIO_MAX_PAGES to HPAGE_PMD_NR if huge page cache enabled Kirill A. Shutemov
2016-10-25  7:21   ` Christoph Hellwig
2016-10-25 12:54     ` Kirill A. Shutemov
2016-10-26  4:13       ` Andreas Dilger
2016-10-26  7:30         ` Ming Lei
2016-10-26  7:36           ` Christoph Hellwig
2016-10-26  7:36         ` Christoph Hellwig
2016-10-26  7:35       ` Christoph Hellwig
2016-10-25  0:13 ` [PATCHv4 19/43] brd: make it handle huge pages Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 20/43] mm: make write_cache_pages() work on " Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 21/43] thp: introduce hpage_size() and hpage_mask() Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 22/43] thp: do not threat slab pages as huge in hpage_{nr_pages,size,mask} Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 23/43] thp: make thp_get_unmapped_area() respect S_HUGE_MODE Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 24/43] fs: make block_read_full_page() be able to read huge page Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 25/43] fs: make block_write_{begin,end}() be able to handle huge pages Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 26/43] fs: make block_page_mkwrite() aware about " Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 27/43] truncate: make truncate_inode_pages_range() " Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 28/43] truncate: make invalidate_inode_pages2_range() " Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 29/43] mm, hugetlb: switch hugetlbfs to multi-order radix-tree entries Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 30/43] mm: account huge pages to dirty, writaback, reclaimable, etc Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 31/43] ext4: make ext4_mpage_readpages() hugepage-aware Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 32/43] ext4: make ext4_writepage() work on huge pages Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 33/43] ext4: handle huge pages in ext4_page_mkwrite() Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 34/43] ext4: handle huge pages in __ext4_block_zero_page_range() Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 35/43] ext4: make ext4_block_write_begin() aware about huge pages Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 36/43] ext4: handle huge pages in ext4_da_write_end() Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 37/43] ext4: make ext4_da_page_release_reservation() aware about huge pages Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 38/43] ext4: handle writeback with " Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 39/43] ext4: make EXT4_IOC_MOVE_EXT work " Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 40/43] ext4: fix SEEK_DATA/SEEK_HOLE for " Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 41/43] ext4: make fallocate() operations work with " Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 42/43] mm, fs, ext4: expand use of page_mapping() and page_to_pgoff() Kirill A. Shutemov
2016-10-25  0:13 ` [PATCHv4 43/43] ext4, vfs: add huge= mount option Kirill A. Shutemov

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=20161025001342.76126-6-kirill.shutemov@linux.intel.com \
    --to=kirill.shutemov@linux.intel.com \
    --cc=aarcange@redhat.com \
    --cc=adilger.kernel@dilger.ca \
    --cc=akpm@linux-foundation.org \
    --cc=dave.hansen@intel.com \
    --cc=hughd@google.com \
    --cc=jack@suse.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ross.zwisler@linux.intel.com \
    --cc=tytso@mit.edu \
    --cc=vbabka@suse.cz \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    --cc=willy@linux.intel.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 NNTP newsgroup(s).