Linux-Fsdevel Archive on lore.kernel.org
 help / color / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: linux-nvdimm@ml01.01.org, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org, x86@kernel.org, axboe@kernel.dk
Cc: ross.zwisler@linux.intel.com, boaz@plexistor.com
Subject: [PATCH 2/2] pmem: add a driver for persistent memory
Date: Wed,  1 Apr 2015 09:12:19 +0200
Message-ID: <1427872339-6688-3-git-send-email-hch@lst.de> (raw)
In-Reply-To: <1427872339-6688-1-git-send-email-hch@lst.de>

From: Ross Zwisler <ross.zwisler@linux.intel.com>

PMEM is a new driver that presents a reserved range of memory as a
block device.  This is useful for developing with NV-DIMMs, and
can be used with volatile memory as a development platform.

This patch contains the initial driver from Ross Zwisler, with
various changes from Boaz Harrosh and me.

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
[hch: convert to use a platform_device for discovery, fix partition
 support, merged various patches from Boaz]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
---
 MAINTAINERS            |   6 ++
 drivers/block/Kconfig  |  11 +++
 drivers/block/Makefile |   1 +
 drivers/block/pmem.c   | 260 +++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 278 insertions(+)
 create mode 100644 drivers/block/pmem.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 1de6afa..4517613 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8071,6 +8071,12 @@ S:	Maintained
 F:	Documentation/blockdev/ramdisk.txt
 F:	drivers/block/brd.c
 
+PERSISTENT MEMORY DRIVER
+M:	Ross Zwisler <ross.zwisler@linux.intel.com>
+L:	linux-nvdimm@lists.01.org
+S:	Supported
+F:	drivers/block/pmem.c
+
 RANDOM NUMBER DRIVER
 M:	"Theodore Ts'o" <tytso@mit.edu>
 S:	Maintained
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 1b8094d..34753cf 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -404,6 +404,17 @@ config BLK_DEV_RAM_DAX
 	  and will prevent RAM block device backing store memory from being
 	  allocated from highmem (only a problem for highmem systems).
 
+config BLK_DEV_PMEM
+	tristate "Persistent memory block device support"
+	help
+	  Saying Y here will allow you to use a contiguous range of reserved
+	  memory as one or more block devices.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called pmem.
+
+	  If unsure, say N.
+
 config CDROM_PKTCDVD
 	tristate "Packet writing on CD/DVD media"
 	depends on !UML
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 02b688d..9cc6c18 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_PS3_VRAM)		+= ps3vram.o
 obj-$(CONFIG_ATARI_FLOPPY)	+= ataflop.o
 obj-$(CONFIG_AMIGA_Z2RAM)	+= z2ram.o
 obj-$(CONFIG_BLK_DEV_RAM)	+= brd.o
+obj-$(CONFIG_BLK_DEV_PMEM)	+= pmem.o
 obj-$(CONFIG_BLK_DEV_LOOP)	+= loop.o
 obj-$(CONFIG_BLK_CPQ_DA)	+= cpqarray.o
 obj-$(CONFIG_BLK_CPQ_CISS_DA)  += cciss.o
diff --git a/drivers/block/pmem.c b/drivers/block/pmem.c
new file mode 100644
index 0000000..0232ab7
--- /dev/null
+++ b/drivers/block/pmem.c
@@ -0,0 +1,260 @@
+/*
+ * Persistent Memory Driver
+ * Copyright (c) 2014, Intel Corporation.
+ * Copyright (c) 2015, Christoph Hellwig <hch@lst.de>.
+ * Copyright (c) 2015, Boaz Harrosh <boaz@plexistor.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <asm/cacheflush.h>
+#include <linux/blkdev.h>
+#include <linux/hdreg.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+
+#define PMEM_MINORS		16
+
+struct pmem_device {
+	struct request_queue	*pmem_queue;
+	struct gendisk		*pmem_disk;
+
+	/* One contiguous memory region per device */
+	phys_addr_t		phys_addr;
+	void			*virt_addr;
+	size_t			size;
+};
+
+static int pmem_major;
+static atomic_t pmem_index;
+
+static void pmem_do_bvec(struct pmem_device *pmem, struct page *page,
+			unsigned int len, unsigned int off, int rw,
+			sector_t sector)
+{
+	void *mem = kmap_atomic(page);
+	size_t pmem_off = sector << 9;
+
+	if (rw == READ) {
+		memcpy(mem + off, pmem->virt_addr + pmem_off, len);
+		flush_dcache_page(page);
+	} else {
+		flush_dcache_page(page);
+		memcpy(pmem->virt_addr + pmem_off, mem + off, len);
+	}
+
+	kunmap_atomic(mem);
+}
+
+static void pmem_make_request(struct request_queue *q, struct bio *bio)
+{
+	struct block_device *bdev = bio->bi_bdev;
+	struct pmem_device *pmem = bdev->bd_disk->private_data;
+	int rw;
+	struct bio_vec bvec;
+	sector_t sector;
+	struct bvec_iter iter;
+	int err = 0;
+
+	if (bio_end_sector(bio) > get_capacity(bdev->bd_disk)) {
+		err = -EIO;
+		goto out;
+	}
+
+	BUG_ON(bio->bi_rw & REQ_DISCARD);
+
+	rw = bio_data_dir(bio);
+	sector = bio->bi_iter.bi_sector;
+	bio_for_each_segment(bvec, bio, iter) {
+		pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len, bvec.bv_offset,
+			     rw, sector);
+		sector += bvec.bv_len >> 9;
+	}
+
+out:
+	bio_endio(bio, err);
+}
+
+static int pmem_rw_page(struct block_device *bdev, sector_t sector,
+		       struct page *page, int rw)
+{
+	struct pmem_device *pmem = bdev->bd_disk->private_data;
+
+	pmem_do_bvec(pmem, page, PAGE_CACHE_SIZE, 0, rw, sector);
+	page_endio(page, rw & WRITE, 0);
+	return 0;
+}
+
+static long pmem_direct_access(struct block_device *bdev, sector_t sector,
+			      void **kaddr, unsigned long *pfn, long size)
+{
+	struct pmem_device *pmem = bdev->bd_disk->private_data;
+	size_t offset = sector << 9;
+
+	if (!pmem)
+		return -ENODEV;
+
+	*kaddr = pmem->virt_addr + offset;
+	*pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT;
+
+	return pmem->size - offset;
+}
+
+static const struct block_device_operations pmem_fops = {
+	.owner =		THIS_MODULE,
+	.rw_page =		pmem_rw_page,
+	.direct_access =	pmem_direct_access,
+};
+
+static struct pmem_device *pmem_alloc(struct device *dev, struct resource *res)
+{
+	struct pmem_device *pmem;
+	struct gendisk *disk;
+	int idx, err;
+
+	err = -ENOMEM;
+	pmem = kzalloc(sizeof(*pmem), GFP_KERNEL);
+	if (!pmem)
+		goto out;
+
+	pmem->phys_addr = res->start;
+	pmem->size = resource_size(res);
+
+	err = -EINVAL;
+	if (!request_mem_region(pmem->phys_addr, pmem->size, "pmem")) {
+		dev_warn(dev, "could not reserve region [0x%llx:0x%zx]\n",
+			   pmem->phys_addr, pmem->size);
+		goto out_free_dev;
+	}
+
+	/*
+	 * Map the memory as non-cachable, as we can't write back the contents
+	 * of the CPU caches in case of a crash.
+	 */
+	err = -ENOMEM;
+	pmem->virt_addr = ioremap_nocache(pmem->phys_addr, pmem->size);
+	if (!pmem->virt_addr)
+		goto out_release_region;
+
+	pmem->pmem_queue = blk_alloc_queue(GFP_KERNEL);
+	if (!pmem->pmem_queue)
+		goto out_unmap;
+
+	blk_queue_make_request(pmem->pmem_queue, pmem_make_request);
+	blk_queue_max_hw_sectors(pmem->pmem_queue, 1024);
+	blk_queue_bounce_limit(pmem->pmem_queue, BLK_BOUNCE_ANY);
+
+	disk = alloc_disk(PMEM_MINORS);
+	if (!disk)
+		goto out_free_queue;
+
+	idx = atomic_inc_return(&pmem_index) - 1;
+
+	disk->major		= pmem_major;
+	disk->first_minor	= PMEM_MINORS * idx;
+	disk->fops		= &pmem_fops;
+	disk->private_data	= pmem;
+	disk->queue		= pmem->pmem_queue;
+	disk->flags		= GENHD_FL_EXT_DEVT;
+	sprintf(disk->disk_name, "pmem%d", idx);
+	disk->driverfs_dev = dev;
+	set_capacity(disk, pmem->size >> 9);
+	pmem->pmem_disk = disk;
+
+	add_disk(disk);
+	return pmem;
+
+out_free_queue:
+	blk_cleanup_queue(pmem->pmem_queue);
+out_unmap:
+	iounmap(pmem->virt_addr);
+out_release_region:
+	release_mem_region(pmem->phys_addr, pmem->size);
+out_free_dev:
+	kfree(pmem);
+out:
+	return ERR_PTR(err);
+}
+
+static void pmem_free(struct pmem_device *pmem)
+{
+	del_gendisk(pmem->pmem_disk);
+	put_disk(pmem->pmem_disk);
+	blk_cleanup_queue(pmem->pmem_queue);
+	iounmap(pmem->virt_addr);
+	release_mem_region(pmem->phys_addr, pmem->size);
+	kfree(pmem);
+}
+
+static int pmem_probe(struct platform_device *pdev)
+{
+	struct pmem_device *pmem;
+	struct resource *res;
+
+	if (WARN_ON(pdev->num_resources > 1))
+		return -ENXIO;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENXIO;
+
+	pmem = pmem_alloc(&pdev->dev, res);
+	if (IS_ERR(pmem))
+		return PTR_ERR(pmem);
+
+	platform_set_drvdata(pdev, pmem);
+	return 0;
+}
+
+static int pmem_remove(struct platform_device *pdev)
+{
+	struct pmem_device *pmem = platform_get_drvdata(pdev);
+
+	pmem_free(pmem);
+	return 0;
+}
+
+static struct platform_driver pmem_driver = {
+	.probe		= pmem_probe,
+	.remove		= pmem_remove,
+	.driver		= {
+		.owner	= THIS_MODULE,
+		.name	= "pmem",
+	},
+};
+
+static int __init pmem_init(void)
+{
+	int error;
+
+	pmem_major = register_blkdev(0, "pmem");
+	if (pmem_major < 0)
+		return pmem_major;
+
+	error = platform_driver_register(&pmem_driver);
+	if (error)
+		unregister_blkdev(pmem_major, "pmem");
+	return error;
+}
+
+static void pmem_exit(void)
+{
+	platform_driver_unregister(&pmem_driver);
+	unregister_blkdev(pmem_major, "pmem");
+}
+
+MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
+
+module_init(pmem_init);
+module_exit(pmem_exit);
-- 
1.9.1

  parent reply index

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-04-01  7:12 another pmem variant V3 Christoph Hellwig
2015-04-01  7:12 ` [PATCH 1/2] x86: add support for the non-standard protected e820 type Christoph Hellwig
2015-04-01 14:25   ` [PATCH] SQUASHME: Fixes to e820 handling of pmem Boaz Harrosh
2015-04-02  9:30     ` Christoph Hellwig
2015-04-02  9:37       ` Ingo Molnar
2015-04-02  9:40         ` Christoph Hellwig
2015-04-02 11:18         ` Christoph Hellwig
2015-04-02 11:20       ` Boaz Harrosh
2015-04-02 20:23   ` [PATCH 1/2] x86: add support for the non-standard protected e820 type Yinghai Lu
2015-04-03 16:14   ` [Linux-nvdimm] " Toshi Kani
2015-04-03 17:12     ` Yinghai Lu
2015-04-03 20:54       ` Toshi Kani
2015-04-04  9:40         ` Ingo Molnar
2015-04-05  7:44           ` Yinghai Lu
2015-04-06  7:27             ` Ingo Molnar
2015-04-06 17:29           ` Toshi Kani
2015-04-06 18:26             ` Yinghai Lu
2015-04-06 18:23               ` Toshi Kani
2015-04-05  9:18       ` Boaz Harrosh
2015-04-05 20:06         ` Yinghai Lu
2015-04-06  7:16           ` Boaz Harrosh
2015-04-06 15:55       ` Christoph Hellwig
2015-04-01  7:12 ` Christoph Hellwig [this message]
2015-04-01 15:18   ` [PATCH 2/2] pmem: add a driver for persistent memory Boaz Harrosh
2015-04-02  9:32     ` Christoph Hellwig
2015-04-02 15:31 ` [PATCH] pmem: Add prints at module load and unload Boaz Harrosh
2015-04-02 15:39   ` [Linux-nvdimm] " Dan Williams
2015-04-02 15:47     ` Boaz Harrosh
2015-04-02 16:01       ` Dan Williams
2015-04-02 16:44         ` Christoph Hellwig
2015-04-05  8:50           ` Boaz Harrosh
2015-04-07 15:19             ` Christoph Hellwig
2015-04-07 15:34               ` Boaz Harrosh
2015-04-07 15:46 ` [PATCH A+B] " Boaz Harrosh
2015-04-07 15:47   ` [PATCH 1A] pmem: Add prints at pmem_probe/remove Boaz Harrosh
2015-04-07 15:47   ` [PATCH 1B] pmem: Add prints at module load and unload Boaz Harrosh
2015-04-13  9:05   ` [PATCH A+B] " Greg KH
2015-04-13 12:05     ` Boaz Harrosh
2015-04-13 12:36       ` Greg KH
2015-04-13 13:20         ` Boaz Harrosh
2015-04-13 13:36           ` Greg KH

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=1427872339-6688-3-git-send-email-hch@lst.de \
    --to=hch@lst.de \
    --cc=axboe@kernel.dk \
    --cc=boaz@plexistor.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@ml01.01.org \
    --cc=ross.zwisler@linux.intel.com \
    --cc=x86@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

Linux-Fsdevel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-fsdevel/0 linux-fsdevel/git/0.git

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

Example config snippet for mirrors

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


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