LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Minchan Kim <minchan@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org, Juneho Choi <juno.choi@lge.com>,
	Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
	kernel-team <kernel-team@lge.com>,
	Minchan Kim <minchan@kernel.org>
Subject: [PATCH v1 8/9] zram: read page from backing device
Date: Mon, 26 Jun 2017 15:53:06 +0900
Message-ID: <1498459987-24562-9-git-send-email-minchan@kernel.org> (raw)
In-Reply-To: <1498459987-24562-1-git-send-email-minchan@kernel.org>

This patch enables read IO from backing device. For the feature,
it implements two IO read functions to transfer data from backing
storage.

One is asynchronous IO function and other is synchronous one.

A reason I need synchrnous IO is due to partial write which need to
complete read IO before the overwriting partial data.

We can make the partial IO's case asynchronous, too but at the moment,
I don't feel adding more complexity to support such rare use cases
so want to go with simple.

Signed-off-by: Minchan Kim <minchan@kernel.org>
---
 drivers/block/zram/zram_drv.c | 123 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 118 insertions(+), 5 deletions(-)

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 99e46ae..a1e8c73 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -454,6 +454,95 @@ void zram_page_end_io(struct bio *bio)
 	bio_put(bio);
 }
 
+/*
+ * Returns 0 if the submission is successful.
+ */
+static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec,
+			unsigned long entry, struct bio *parent)
+{
+	struct bio *bio;
+
+	bio = bio_alloc(GFP_ATOMIC, 1);
+	if (!bio)
+		return -ENOMEM;
+
+	bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9);
+	bio->bi_bdev = zram->bdev;
+	if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset)) {
+		bio_put(bio);
+		return -EIO;
+	}
+
+	if (!parent) {
+		bio->bi_opf = REQ_OP_READ;
+		bio->bi_end_io = zram_page_end_io;
+	} else {
+		bio->bi_opf = parent->bi_opf;
+		bio_chain(bio, parent);
+	}
+
+	submit_bio(bio);
+	return 1;
+}
+
+struct zram_work {
+	struct work_struct work;
+	struct zram *zram;
+	unsigned long entry;
+	struct bio *bio;
+};
+
+#if PAGE_SIZE != 4096
+static void zram_sync_read(struct work_struct *work)
+{
+	struct bio_vec bvec;
+	struct zram_work *zw = container_of(work, struct zram_work, work);
+	struct zram *zram = zw->zram;
+	unsigned long entry = zw->entry;
+	struct bio *bio = zw->bio;
+
+	read_from_bdev_async(zram, &bvec, entry, bio);
+}
+
+/*
+ * Block layer want one ->make_request_fn to be active at a time
+ * so if we use chained IO with parent IO in same context,
+ * it's a deadlock. To avoid, it, it uses worker thread context.
+ */
+static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
+				unsigned long entry, struct bio *bio)
+{
+	struct zram_work work;
+
+	work.zram = zram;
+	work.entry = entry;
+	work.bio = bio;
+
+	INIT_WORK_ONSTACK(&work.work, zram_sync_read);
+	queue_work(system_unbound_wq, &work.work);
+	flush_work(&work.work);
+	destroy_work_on_stack(&work.work);
+
+	return 1;
+}
+#else
+static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
+				unsigned long entry, struct bio *bio)
+{
+	WARN_ON(1);
+	return -EIO;
+}
+#endif
+
+static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
+			unsigned long entry, struct bio *parent, bool sync)
+{
+	if (sync)
+		return read_from_bdev_sync(zram, bvec, entry, parent);
+	else
+		return read_from_bdev_async(zram, bvec, entry, parent);
+}
+
 static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
 					u32 index, struct bio *parent,
 					unsigned long *pentry)
@@ -514,6 +603,12 @@ static int write_to_bdev(struct zram *zram, struct bio_vec *bvec,
 {
 	return -EIO;
 }
+
+static int read_from_bdev(struct zram *zram, struct bio_vec *bvec,
+			unsigned long entry, struct bio *parent, bool sync)
+{
+	return -EIO;
+}
 static void zram_wb_clear(struct zram *zram, u32 index) {}
 #endif
 
@@ -773,13 +868,31 @@ static void zram_free_page(struct zram *zram, size_t index)
 	zram_set_obj_size(zram, index, 0);
 }
 
-static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index)
+static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
+				struct bio *bio, bool partial_io)
 {
 	int ret;
 	unsigned long handle;
 	unsigned int size;
 	void *src, *dst;
 
+	if (zram_wb_enabled(zram)) {
+		zram_slot_lock(zram, index);
+		if (zram_test_flag(zram, index, ZRAM_WB)) {
+			struct bio_vec bvec;
+
+			zram_slot_unlock(zram, index);
+
+			bvec.bv_page = page;
+			bvec.bv_len = PAGE_SIZE;
+			bvec.bv_offset = 0;
+			return read_from_bdev(zram, &bvec,
+					zram_get_element(zram, index),
+					bio, partial_io);
+		}
+		zram_slot_unlock(zram, index);
+	}
+
 	if (zram_same_page_read(zram, index, page, 0, PAGE_SIZE))
 		return 0;
 
@@ -812,7 +925,7 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index)
 }
 
 static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
-				u32 index, int offset)
+				u32 index, int offset, struct bio *bio)
 {
 	int ret;
 	struct page *page;
@@ -825,7 +938,7 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
 			return -ENOMEM;
 	}
 
-	ret = __zram_bvec_read(zram, page, index);
+	ret = __zram_bvec_read(zram, page, index, bio, is_partial_io(bvec));
 	if (unlikely(ret))
 		goto out;
 
@@ -987,7 +1100,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
 		if (!page)
 			return -ENOMEM;
 
-		ret = __zram_bvec_read(zram, page, index);
+		ret = __zram_bvec_read(zram, page, index, bio, true);
 		if (ret)
 			goto out;
 
@@ -1064,7 +1177,7 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 
 	if (!is_write) {
 		atomic64_inc(&zram->stats.num_reads);
-		ret = zram_bvec_read(zram, bvec, index, offset);
+		ret = zram_bvec_read(zram, bvec, index, offset, bio);
 		flush_dcache_page(bvec->bv_page);
 	} else {
 		atomic64_inc(&zram->stats.num_writes);
-- 
2.7.4

  parent reply index

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-26  6:52 [PATCH v1 0/7] writeback incompressible pages to storage Minchan Kim
2017-06-26  6:52 ` [PATCH v1 1/9] zram: clean up duplicated codes in __zram_bvec_write Minchan Kim
2017-06-26  6:53 ` [PATCH v1 2/9] zram: inlining zram_compress Minchan Kim
2017-06-26  6:53 ` [PATCH v1 3/9] zram: rename zram_decompress_page with __zram_bvec_read Minchan Kim
2017-06-26  6:53 ` [PATCH v1 4/9] zram: add interface to specify backing device Minchan Kim
2017-06-26  6:53 ` [PATCH v1 5/9] zram: add free space management in " Minchan Kim
2017-06-26  6:53 ` [PATCH v1 6/9] zram: identify asynchronous IO's return value Minchan Kim
2017-06-26  6:53 ` [PATCH v1 7/9] zram: write incompressible pages to backing device Minchan Kim
2017-06-26  6:53 ` Minchan Kim [this message]
2017-06-26  6:53 ` [PATCH v1 9/9] zram: add config and doc file for writeback feature Minchan Kim
2017-06-28 15:41 ` [PATCH v1 0/7] writeback incompressible pages to storage Sergey Senozhatsky
2017-06-29  8:47   ` Minchan Kim
2017-06-29  9:17     ` Sergey Senozhatsky
2017-06-29  9:29       ` Minchan Kim

Reply instructions:

You may reply publically 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=1498459987-24562-9-git-send-email-minchan@kernel.org \
    --to=minchan@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=juno.choi@lge.com \
    --cc=kernel-team@lge.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=sergey.senozhatsky@gmail.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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git