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>
next prev 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).