linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Dennis Zhou <dennisz@fb.com>
To: Tejun Heo <tj@kernel.org>, Christoph Lameter <cl@linux.com>,
	Josef Bacik <josef@toxicpanda.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	kernel-team@fb.com, Dennis Zhou <dennisszhou@gmail.com>
Subject: [PATCH v2 21/23] percpu: use metadata blocks to update the chunk contig hint
Date: Mon, 24 Jul 2017 19:02:18 -0400	[thread overview]
Message-ID: <20170724230220.21774-22-dennisz@fb.com> (raw)
In-Reply-To: <20170724230220.21774-1-dennisz@fb.com>

From: "Dennis Zhou (Facebook)" <dennisszhou@gmail.com>

The largest free region will either be a block level contig hint or an
aggregate over the left_free and right_free areas of blocks. This is a
much smaller set of free areas that need to be checked than a full
traverse.

Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>
---
 mm/percpu.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 70 insertions(+), 10 deletions(-)

diff --git a/mm/percpu.c b/mm/percpu.c
index 426548a..9e4192c 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -306,6 +306,67 @@ static unsigned long pcpu_block_off_to_off(int index, int off)
 }
 
 /**
+ * pcpu_next_md_free_region - finds the next hint free area
+ * @chunk: chunk of interest
+ * @bit_off: chunk offset
+ * @bits: size of free area
+ *
+ * Helper function for pcpu_for_each_md_free_region.  It checks
+ * block->contig_hint and performs aggregation across blocks to find the
+ * next hint.  It modifies bit_off and bits in-place to be consumed in the
+ * loop.
+ */
+static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off,
+				     int *bits)
+{
+	int i = pcpu_off_to_block_index(*bit_off);
+	int block_off = pcpu_off_to_block_off(*bit_off);
+	struct pcpu_block_md *block;
+
+	*bits = 0;
+	for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk);
+	     block++, i++) {
+		/* handles contig area across blocks */
+		if (*bits) {
+			*bits += block->left_free;
+			if (block->left_free == PCPU_BITMAP_BLOCK_BITS)
+				continue;
+			return;
+		}
+
+		/*
+		 * This checks three things.  First is there a contig_hint to
+		 * check.  Second, have we checked this hint before by
+		 * comparing the block_off.  Third, is this the same as the
+		 * right contig hint.  In the last case, it spills over into
+		 * the next block and should be handled by the contig area
+		 * across blocks code.
+		 */
+		*bits = block->contig_hint;
+		if (*bits && block->contig_hint_start >= block_off &&
+		    *bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) {
+			*bit_off = pcpu_block_off_to_off(i,
+					block->contig_hint_start);
+			return;
+		}
+
+		*bits = block->right_free;
+		*bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free;
+	}
+}
+
+/*
+ * Metadata free area iterators.  These perform aggregation of free areas
+ * based on the metadata blocks and return the offset @bit_off and size in
+ * bits of the free area @bits.
+ */
+#define pcpu_for_each_md_free_region(chunk, bit_off, bits)		\
+	for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits));	\
+	     (bit_off) < pcpu_chunk_map_bits((chunk));			\
+	     (bit_off) += (bits) + 1,					\
+	     pcpu_next_md_free_region((chunk), &(bit_off), &(bits)))
+
+/**
  * pcpu_mem_zalloc - allocate memory
  * @size: bytes to allocate
  *
@@ -418,29 +479,28 @@ static void pcpu_chunk_update(struct pcpu_chunk *chunk, int bit_off, int bits)
  * pcpu_chunk_refresh_hint - updates metadata about a chunk
  * @chunk: chunk of interest
  *
- * Iterates over the chunk to find the largest free area.
+ * Iterates over the metadata blocks to find the largest contig area.
+ * It also counts the populated pages and uses the delta to update the
+ * global count.
  *
  * Updates:
  *      chunk->contig_bits
  *      chunk->contig_bits_start
- *      nr_empty_pop_pages
+ *      nr_empty_pop_pages (chunk and global)
  */
 static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk)
 {
-	int bits, nr_empty_pop_pages;
-	int rs, re; /* region start, region end */
+	int bit_off, bits, nr_empty_pop_pages;
 
 	/* clear metadata */
 	chunk->contig_bits = 0;
 
+	bit_off = chunk->first_bit;
 	bits = nr_empty_pop_pages = 0;
-	pcpu_for_each_unpop_region(chunk->alloc_map, rs, re, chunk->first_bit,
-				   pcpu_chunk_map_bits(chunk)) {
-		bits = re - rs;
-
-		pcpu_chunk_update(chunk, rs, bits);
+	pcpu_for_each_md_free_region(chunk, bit_off, bits) {
+		pcpu_chunk_update(chunk, bit_off, bits);
 
-		nr_empty_pop_pages += pcpu_cnt_pop_pages(chunk, rs, bits);
+		nr_empty_pop_pages += pcpu_cnt_pop_pages(chunk, bit_off, bits);
 	}
 
 	/*
-- 
2.9.3

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2017-07-24 23:03 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-07-24 23:01 [PATCH v2 00/23] percpu: replace percpu area map allocator with bitmap allocator Dennis Zhou
2017-07-24 23:01 ` [PATCH v2 01/23] percpu: setup_first_chunk enforce dynamic region must exist Dennis Zhou
2017-07-25 18:03   ` Josef Bacik
2017-07-24 23:01 ` [PATCH v2 02/23] percpu: introduce start_offset to pcpu_chunk Dennis Zhou
2017-07-25 18:04   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 03/23] percpu: remove has_reserved from pcpu_chunk Dennis Zhou
2017-07-25 18:05   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 04/23] percpu: setup_first_chunk remove dyn_size and consolidate logic Dennis Zhou
2017-07-25 18:07   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 05/23] percpu: unify allocation of schunk and dchunk Dennis Zhou
2017-07-25 18:10   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 06/23] percpu: end chunk area maps page aligned for the populated bitmap Dennis Zhou
2017-07-25 18:14   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 07/23] percpu: setup_first_chunk rename schunk/dchunk to chunk Dennis Zhou
2017-07-25 18:15   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 08/23] percpu: modify base_addr to be region specific Dennis Zhou
2017-07-25 18:24   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 09/23] percpu: combine percpu address checks Dennis Zhou
2017-07-25 18:25   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 10/23] percpu: change the number of pages marked in the first_chunk pop bitmap Dennis Zhou
2017-07-25 18:27   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 11/23] percpu: introduce nr_empty_pop_pages to help empty page accounting Dennis Zhou
2017-07-25 18:29   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 12/23] percpu: increase minimum percpu allocation size and align first regions Dennis Zhou
2017-07-25 18:33   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 13/23] percpu: generalize bitmap (un)populated iterators Dennis Zhou
2017-07-25 18:35   ` Josef Bacik
2017-07-26 14:08   ` Tejun Heo
2017-07-24 23:02 ` [PATCH v2 14/23] percpu: replace area map allocator with bitmap allocator Dennis Zhou
2017-07-25 17:36   ` [percpu] ec1f2e572e: WARNING:at_lib/list_debug.c:#__list_add_valid kernel test robot
2017-07-25 19:15   ` [PATCH v2 14/23] percpu: replace area map allocator with bitmap allocator Josef Bacik
2017-07-25 20:24   ` [PATCH updated 14/23] percpu: replace area map allocator with bitmap Dennis Zhou
2017-07-24 23:02 ` [PATCH v2 15/23] percpu: introduce bitmap metadata blocks Dennis Zhou
2017-07-25 19:20   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 16/23] percpu: add first_bit to keep track of the first free in the bitmap Dennis Zhou
2017-07-25 19:21   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 17/23] percpu: skip chunks if the alloc does not fit in the contig hint Dennis Zhou
2017-07-25 19:25   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 18/23] percpu: keep track of the best offset for contig hints Dennis Zhou
2017-07-25 19:29   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 19/23] percpu: update alloc path to only scan if contig hints are broken Dennis Zhou
2017-07-25 19:32   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 20/23] percpu: update free path to take advantage of contig hints Dennis Zhou
2017-07-25 19:38   ` Josef Bacik
2017-07-24 23:02 ` Dennis Zhou [this message]
2017-07-25 19:40   ` [PATCH v2 21/23] percpu: use metadata blocks to update the chunk contig hint Josef Bacik
2017-07-24 23:02 ` [PATCH v2 22/23] percpu: update pcpu_find_block_fit to use an iterator Dennis Zhou
2017-07-25 19:47   ` Josef Bacik
2017-07-24 23:02 ` [PATCH v2 23/23] percpu: update header to contain bitmap allocator explanation Dennis Zhou
2017-07-25 19:49   ` Josef Bacik
2017-07-26 21:42   ` Tejun Heo

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=20170724230220.21774-22-dennisz@fb.com \
    --to=dennisz@fb.com \
    --cc=cl@linux.com \
    --cc=dennisszhou@gmail.com \
    --cc=josef@toxicpanda.com \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=tj@kernel.org \
    /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).