[deliverable/linux.git] / drivers / nvdimm / pmem.c

/*
 * Persistent Memory Driver
 *
 * Copyright (c) 2014-2015, 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>
#include <linux/nd.h>
#include "nd.h"

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 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, int id)
{
	struct pmem_device *pmem;
	struct gendisk *disk;
	int 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%pa: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(0);
	if (!disk)
		goto out_free_queue;

	disk->major		= pmem_major;
	disk->first_minor	= 0;
	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", id);
	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 nd_pmem_probe(struct device *dev)
{
	struct nd_region *nd_region = to_nd_region(dev->parent);
	struct nd_namespace_io *nsio = to_nd_namespace_io(dev);
	struct pmem_device *pmem;

	if (resource_size(&nsio->res) < ND_MIN_NAMESPACE_SIZE) {
		resource_size_t size = resource_size(&nsio->res);

		dev_dbg(dev, "%s: size: %pa, too small must be at least %#x\n",
				__func__, &size, ND_MIN_NAMESPACE_SIZE);
		return -ENODEV;
	}

	if (nd_region_to_nstype(nd_region) == ND_DEVICE_NAMESPACE_PMEM) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

		if (!nspm->uuid) {
			dev_dbg(dev, "%s: uuid not set\n", __func__);
			return -ENODEV;
		}
	}

	pmem = pmem_alloc(dev, &nsio->res, nd_region->id);
	if (IS_ERR(pmem))
		return PTR_ERR(pmem);

	dev_set_drvdata(dev, pmem);

	return 0;
}

static int nd_pmem_remove(struct device *dev)
{
	struct pmem_device *pmem = dev_get_drvdata(dev);

	pmem_free(pmem);
	return 0;
}

MODULE_ALIAS("pmem");
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO);
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM);
static struct nd_device_driver nd_pmem_driver = {
	.probe = nd_pmem_probe,
	.remove = nd_pmem_remove,
	.drv = {
		.name = "nd_pmem",
	},
	.type = ND_DRIVER_NAMESPACE_IO | ND_DRIVER_NAMESPACE_PMEM,
};

static int __init pmem_init(void)
{
	int error;

	pmem_major = register_blkdev(0, "pmem");
	if (pmem_major < 0)
		return pmem_major;

	error = nd_driver_register(&nd_pmem_driver);
	if (error) {
		unregister_blkdev(pmem_major, "pmem");
		return error;
	}

	return 0;
}
module_init(pmem_init);

static void pmem_exit(void)
{
	driver_unregister(&nd_pmem_driver.drv);
	unregister_blkdev(pmem_major, "pmem");
}
module_exit(pmem_exit);

MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
MODULE_LICENSE("GPL v2");
Commit	Line	Data
9e853f23 RZ	1	/*
	2	* Persistent Memory Driver
	3	*
9f53f9fa	4	* Copyright (c) 2014-2015, Intel Corporation.
9e853f23 RZ	5	* Copyright (c) 2015, Christoph Hellwig <hch@lst.de>.
	6	* Copyright (c) 2015, Boaz Harrosh <boaz@plexistor.com>.
	7	*
	8	* This program is free software; you can redistribute it and/or modify it
	9	* under the terms and conditions of the GNU General Public License,
	10	* version 2, as published by the Free Software Foundation.
	11	*
	12	* This program is distributed in the hope it will be useful, but WITHOUT
	13	* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
	14	* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
	15	* more details.
	16	*/
	17
	18	#include <asm/cacheflush.h>
	19	#include <linux/blkdev.h>
	20	#include <linux/hdreg.h>
	21	#include <linux/init.h>
	22	#include <linux/platform_device.h>
	23	#include <linux/module.h>
	24	#include <linux/moduleparam.h>
	25	#include <linux/slab.h>
9f53f9fa DW	26	#include <linux/nd.h>
9f53f9fa DW	27	#include "nd.h"
9e853f23 RZ	28
	29	struct pmem_device {
	30	struct request_queue *pmem_queue;
	31	struct gendisk *pmem_disk;
	32
	33	/* One contiguous memory region per device */
	34	phys_addr_t phys_addr;
	35	void *virt_addr;
	36	size_t size;
	37	};
	38
	39	static int pmem_major;
9e853f23 RZ	40
	41	static void pmem_do_bvec(struct pmem_device pmem, struct page page,
	42	unsigned int len, unsigned int off, int rw,
	43	sector_t sector)
	44	{
	45	void *mem = kmap_atomic(page);
	46	size_t pmem_off = sector << 9;
	47
	48	if (rw == READ) {
	49	memcpy(mem + off, pmem->virt_addr + pmem_off, len);
	50	flush_dcache_page(page);
	51	} else {
	52	flush_dcache_page(page);
	53	memcpy(pmem->virt_addr + pmem_off, mem + off, len);
	54	}
	55
	56	kunmap_atomic(mem);
	57	}
	58
	59	static void pmem_make_request(struct request_queue q, struct bio bio)
	60	{
	61	struct block_device *bdev = bio->bi_bdev;
	62	struct pmem_device *pmem = bdev->bd_disk->private_data;
	63	int rw;
	64	struct bio_vec bvec;
	65	sector_t sector;
	66	struct bvec_iter iter;
	67	int err = 0;
	68
	69	if (bio_end_sector(bio) > get_capacity(bdev->bd_disk)) {
	70	err = -EIO;
	71	goto out;
	72	}
	73
	74	BUG_ON(bio->bi_rw & REQ_DISCARD);
	75
	76	rw = bio_data_dir(bio);
	77	sector = bio->bi_iter.bi_sector;
	78	bio_for_each_segment(bvec, bio, iter) {
	79	pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len, bvec.bv_offset,
	80	rw, sector);
	81	sector += bvec.bv_len >> 9;
	82	}
	83
	84	out:
	85	bio_endio(bio, err);
	86	}
	87
	88	static int pmem_rw_page(struct block_device *bdev, sector_t sector,
	89	struct page *page, int rw)
	90	{
	91	struct pmem_device *pmem = bdev->bd_disk->private_data;
	92
	93	pmem_do_bvec(pmem, page, PAGE_CACHE_SIZE, 0, rw, sector);
	94	page_endio(page, rw & WRITE, 0);
	95
	96	return 0;
	97	}
	98
	99	static long pmem_direct_access(struct block_device *bdev, sector_t sector,
	100	void *kaddr, unsigned long pfn, long size)
	101	{
	102	struct pmem_device *pmem = bdev->bd_disk->private_data;
	103	size_t offset = sector << 9;
104
105	if (!pmem)
106	return -ENODEV;
107
108	*kaddr = pmem->virt_addr + offset;
109	*pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT;
110
111	return pmem->size - offset;
112	}
113
114	static const struct block_device_operations pmem_fops = {
115	.owner = THIS_MODULE,
116	.rw_page = pmem_rw_page,
117	.direct_access = pmem_direct_access,
118	};
119
9f53f9fa DW	120	static struct pmem_device pmem_alloc(struct device dev,
9f53f9fa DW	121	struct resource *res, int id)
9e853f23 RZ	122	{
	123	struct pmem_device *pmem;
	124	struct gendisk *disk;
9f53f9fa	125	int err;
9e853f23 RZ	126
	127	err = -ENOMEM;
	128	pmem = kzalloc(sizeof(*pmem), GFP_KERNEL);
	129	if (!pmem)
	130	goto out;
	131
	132	pmem->phys_addr = res->start;
	133	pmem->size = resource_size(res);
	134
	135	err = -EINVAL;
	136	if (!request_mem_region(pmem->phys_addr, pmem->size, "pmem")) {
9f53f9fa DW	137	dev_warn(dev, "could not reserve region [0x%pa:0x%zx]\n",
9f53f9fa DW	138	&pmem->phys_addr, pmem->size);
9e853f23 RZ	139	goto out_free_dev;
	140	}
	141
	142	/*
	143	* Map the memory as non-cachable, as we can't write back the contents
	144	* of the CPU caches in case of a crash.
	145	*/
	146	err = -ENOMEM;
	147	pmem->virt_addr = ioremap_nocache(pmem->phys_addr, pmem->size);
	148	if (!pmem->virt_addr)
	149	goto out_release_region;
	150
	151	pmem->pmem_queue = blk_alloc_queue(GFP_KERNEL);
	152	if (!pmem->pmem_queue)
	153	goto out_unmap;
	154
	155	blk_queue_make_request(pmem->pmem_queue, pmem_make_request);
	156	blk_queue_max_hw_sectors(pmem->pmem_queue, 1024);
	157	blk_queue_bounce_limit(pmem->pmem_queue, BLK_BOUNCE_ANY);
	158
9f53f9fa	159	disk = alloc_disk(0);
9e853f23 RZ	160	if (!disk)
	161	goto out_free_queue;
	162
9e853f23	163	disk->major = pmem_major;
9f53f9fa	164	disk->first_minor = 0;
9e853f23 RZ	165	disk->fops = &pmem_fops;
	166	disk->private_data = pmem;
	167	disk->queue = pmem->pmem_queue;
	168	disk->flags = GENHD_FL_EXT_DEVT;
9f53f9fa	169	sprintf(disk->disk_name, "pmem%d", id);
9e853f23 RZ	170	disk->driverfs_dev = dev;
	171	set_capacity(disk, pmem->size >> 9);
	172	pmem->pmem_disk = disk;
	173
	174	add_disk(disk);
	175
	176	return pmem;
	177
	178	out_free_queue:
	179	blk_cleanup_queue(pmem->pmem_queue);
	180	out_unmap:
	181	iounmap(pmem->virt_addr);
	182	out_release_region:
	183	release_mem_region(pmem->phys_addr, pmem->size);
	184	out_free_dev:
	185	kfree(pmem);
	186	out:
	187	return ERR_PTR(err);
	188	}
	189
	190	static void pmem_free(struct pmem_device *pmem)
	191	{
	192	del_gendisk(pmem->pmem_disk);
	193	put_disk(pmem->pmem_disk);
	194	blk_cleanup_queue(pmem->pmem_queue);
	195	iounmap(pmem->virt_addr);
	196	release_mem_region(pmem->phys_addr, pmem->size);
	197	kfree(pmem);
	198	}
	199
9f53f9fa	200	static int nd_pmem_probe(struct device *dev)
9e853f23	201	{
9f53f9fa DW	202	struct nd_region *nd_region = to_nd_region(dev->parent);
9f53f9fa DW	203	struct nd_namespace_io *nsio = to_nd_namespace_io(dev);
9e853f23	204	struct pmem_device *pmem;
9e853f23	205
bf9bccc1 DW	206	if (resource_size(&nsio->res) < ND_MIN_NAMESPACE_SIZE) {
	207	resource_size_t size = resource_size(&nsio->res);
	208
	209	dev_dbg(dev, "%s: size: %pa, too small must be at least %#x\n",
	210	__func__, &size, ND_MIN_NAMESPACE_SIZE);
	211	return -ENODEV;
	212	}
	213
	214	if (nd_region_to_nstype(nd_region) == ND_DEVICE_NAMESPACE_PMEM) {
	215	struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
	216
	217	if (!nspm->uuid) {
	218	dev_dbg(dev, "%s: uuid not set\n", __func__);
	219	return -ENODEV;
	220	}
	221	}
	222
9f53f9fa	223	pmem = pmem_alloc(dev, &nsio->res, nd_region->id);
9e853f23 RZ	224	if (IS_ERR(pmem))
	225	return PTR_ERR(pmem);
	226
9f53f9fa	227	dev_set_drvdata(dev, pmem);
9e853f23 RZ	228
	229	return 0;
	230	}
	231
9f53f9fa	232	static int nd_pmem_remove(struct device *dev)
9e853f23	233	{
9f53f9fa	234	struct pmem_device *pmem = dev_get_drvdata(dev);
9e853f23 RZ	235
	236	pmem_free(pmem);
	237	return 0;
	238	}
	239
9f53f9fa DW	240	MODULE_ALIAS("pmem");
9f53f9fa DW	241	MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO);
bf9bccc1	242	MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM);
9f53f9fa DW	243	static struct nd_device_driver nd_pmem_driver = {
	244	.probe = nd_pmem_probe,
	245	.remove = nd_pmem_remove,
	246	.drv = {
	247	.name = "nd_pmem",
9e853f23	248	},
bf9bccc1	249	.type = ND_DRIVER_NAMESPACE_IO \| ND_DRIVER_NAMESPACE_PMEM,
9e853f23 RZ	250	};
	251
	252	static int __init pmem_init(void)
	253	{
	254	int error;
	255
	256	pmem_major = register_blkdev(0, "pmem");
	257	if (pmem_major < 0)
	258	return pmem_major;
	259
9f53f9fa DW	260	error = nd_driver_register(&nd_pmem_driver);
9f53f9fa DW	261	if (error) {
9e853f23	262	unregister_blkdev(pmem_major, "pmem");
9f53f9fa DW	263	return error;
	264	}
	265
	266	return 0;
9e853f23 RZ	267	}
	268	module_init(pmem_init);
	269
	270	static void pmem_exit(void)
	271	{
9f53f9fa	272	driver_unregister(&nd_pmem_driver.drv);
9e853f23 RZ	273	unregister_blkdev(pmem_major, "pmem");
	274	}
	275	module_exit(pmem_exit);
	276
	277	MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
	278	MODULE_LICENSE("GPL v2");