564 lines
14 KiB
C
564 lines
14 KiB
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/badblocks.h>
|
|
#include <linux/memremap.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/blk-mq.h>
|
|
#include <linux/pfn_t.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/uio.h>
|
|
#include <linux/dax.h>
|
|
#include <linux/nd.h>
|
|
#include <linux/backing-dev.h>
|
|
#include "pmem.h"
|
|
#include "pfn.h"
|
|
#include "nd.h"
|
|
#include "nd-core.h"
|
|
|
|
static struct device *to_dev(struct pmem_device *pmem)
|
|
{
|
|
/*
|
|
* nvdimm bus services need a 'dev' parameter, and we record the device
|
|
* at init in bb.dev.
|
|
*/
|
|
return pmem->bb.dev;
|
|
}
|
|
|
|
static struct nd_region *to_region(struct pmem_device *pmem)
|
|
{
|
|
return to_nd_region(to_dev(pmem)->parent);
|
|
}
|
|
|
|
static blk_status_t pmem_clear_poison(struct pmem_device *pmem,
|
|
phys_addr_t offset, unsigned int len)
|
|
{
|
|
struct device *dev = to_dev(pmem);
|
|
sector_t sector;
|
|
long cleared;
|
|
blk_status_t rc = BLK_STS_OK;
|
|
|
|
sector = (offset - pmem->data_offset) / 512;
|
|
|
|
cleared = nvdimm_clear_poison(dev, pmem->phys_addr + offset, len);
|
|
if (cleared < len)
|
|
rc = BLK_STS_IOERR;
|
|
if (cleared > 0 && cleared / 512) {
|
|
cleared /= 512;
|
|
dev_dbg(dev, "%s: %#llx clear %ld sector%s\n", __func__,
|
|
(unsigned long long) sector, cleared,
|
|
cleared > 1 ? "s" : "");
|
|
badblocks_clear(&pmem->bb, sector, cleared);
|
|
if (pmem->bb_state)
|
|
sysfs_notify_dirent(pmem->bb_state);
|
|
}
|
|
|
|
arch_invalidate_pmem(pmem->virt_addr + offset, len);
|
|
|
|
return rc;
|
|
}
|
|
|
|
static void write_pmem(void *pmem_addr, struct page *page,
|
|
unsigned int off, unsigned int len)
|
|
{
|
|
unsigned int chunk;
|
|
void *mem;
|
|
|
|
while (len) {
|
|
mem = kmap_atomic(page);
|
|
chunk = min_t(unsigned int, len, PAGE_SIZE);
|
|
memcpy_flushcache(pmem_addr, mem + off, chunk);
|
|
kunmap_atomic(mem);
|
|
len -= chunk;
|
|
off = 0;
|
|
page++;
|
|
pmem_addr += PAGE_SIZE;
|
|
}
|
|
}
|
|
|
|
static blk_status_t read_pmem(struct page *page, unsigned int off,
|
|
void *pmem_addr, unsigned int len)
|
|
{
|
|
unsigned int chunk;
|
|
int rc;
|
|
void *mem;
|
|
|
|
while (len) {
|
|
mem = kmap_atomic(page);
|
|
chunk = min_t(unsigned int, len, PAGE_SIZE);
|
|
rc = memcpy_mcsafe(mem + off, pmem_addr, chunk);
|
|
kunmap_atomic(mem);
|
|
if (rc)
|
|
return BLK_STS_IOERR;
|
|
len -= chunk;
|
|
off = 0;
|
|
page++;
|
|
pmem_addr += PAGE_SIZE;
|
|
}
|
|
return BLK_STS_OK;
|
|
}
|
|
|
|
static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
|
|
unsigned int len, unsigned int off, bool is_write,
|
|
sector_t sector)
|
|
{
|
|
blk_status_t rc = BLK_STS_OK;
|
|
bool bad_pmem = false;
|
|
phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
|
|
void *pmem_addr = pmem->virt_addr + pmem_off;
|
|
|
|
if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
|
|
bad_pmem = true;
|
|
|
|
if (!is_write) {
|
|
if (unlikely(bad_pmem))
|
|
rc = BLK_STS_IOERR;
|
|
else {
|
|
rc = read_pmem(page, off, pmem_addr, len);
|
|
flush_dcache_page(page);
|
|
}
|
|
} else {
|
|
/*
|
|
* Note that we write the data both before and after
|
|
* clearing poison. The write before clear poison
|
|
* handles situations where the latest written data is
|
|
* preserved and the clear poison operation simply marks
|
|
* the address range as valid without changing the data.
|
|
* In this case application software can assume that an
|
|
* interrupted write will either return the new good
|
|
* data or an error.
|
|
*
|
|
* However, if pmem_clear_poison() leaves the data in an
|
|
* indeterminate state we need to perform the write
|
|
* after clear poison.
|
|
*/
|
|
flush_dcache_page(page);
|
|
write_pmem(pmem_addr, page, off, len);
|
|
if (unlikely(bad_pmem)) {
|
|
rc = pmem_clear_poison(pmem, pmem_off, len);
|
|
write_pmem(pmem_addr, page, off, len);
|
|
}
|
|
}
|
|
|
|
return rc;
|
|
}
|
|
|
|
/* account for REQ_FLUSH rename, replace with REQ_PREFLUSH after v4.8-rc1 */
|
|
#ifndef REQ_FLUSH
|
|
#define REQ_FLUSH REQ_PREFLUSH
|
|
#endif
|
|
|
|
static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
|
|
{
|
|
blk_status_t rc = 0;
|
|
bool do_acct;
|
|
unsigned long start;
|
|
struct bio_vec bvec;
|
|
struct bvec_iter iter;
|
|
struct pmem_device *pmem = q->queuedata;
|
|
struct nd_region *nd_region = to_region(pmem);
|
|
|
|
if (bio->bi_opf & REQ_FLUSH)
|
|
nvdimm_flush(nd_region);
|
|
|
|
do_acct = nd_iostat_start(bio, &start);
|
|
bio_for_each_segment(bvec, bio, iter) {
|
|
rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
|
|
bvec.bv_offset, op_is_write(bio_op(bio)),
|
|
iter.bi_sector);
|
|
if (rc) {
|
|
bio->bi_status = rc;
|
|
break;
|
|
}
|
|
}
|
|
if (do_acct)
|
|
nd_iostat_end(bio, start);
|
|
|
|
if (bio->bi_opf & REQ_FUA)
|
|
nvdimm_flush(nd_region);
|
|
|
|
bio_endio(bio);
|
|
return BLK_QC_T_NONE;
|
|
}
|
|
|
|
static int pmem_rw_page(struct block_device *bdev, sector_t sector,
|
|
struct page *page, bool is_write)
|
|
{
|
|
struct pmem_device *pmem = bdev->bd_queue->queuedata;
|
|
blk_status_t rc;
|
|
|
|
rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE,
|
|
0, is_write, sector);
|
|
|
|
/*
|
|
* The ->rw_page interface is subtle and tricky. The core
|
|
* retries on any error, so we can only invoke page_endio() in
|
|
* the successful completion case. Otherwise, we'll see crashes
|
|
* caused by double completion.
|
|
*/
|
|
if (rc == 0)
|
|
page_endio(page, is_write, 0);
|
|
|
|
return blk_status_to_errno(rc);
|
|
}
|
|
|
|
/* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */
|
|
__weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
|
|
long nr_pages, void **kaddr, pfn_t *pfn)
|
|
{
|
|
resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
|
|
|
|
if (unlikely(is_bad_pmem(&pmem->bb, PFN_PHYS(pgoff) / 512,
|
|
PFN_PHYS(nr_pages))))
|
|
return -EIO;
|
|
*kaddr = pmem->virt_addr + offset;
|
|
*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
|
|
|
|
/*
|
|
* If badblocks are present, limit known good range to the
|
|
* requested range.
|
|
*/
|
|
if (unlikely(pmem->bb.count))
|
|
return nr_pages;
|
|
return PHYS_PFN(pmem->size - pmem->pfn_pad - offset);
|
|
}
|
|
|
|
static const struct block_device_operations pmem_fops = {
|
|
.owner = THIS_MODULE,
|
|
.rw_page = pmem_rw_page,
|
|
.revalidate_disk = nvdimm_revalidate_disk,
|
|
};
|
|
|
|
static long pmem_dax_direct_access(struct dax_device *dax_dev,
|
|
pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn)
|
|
{
|
|
struct pmem_device *pmem = dax_get_private(dax_dev);
|
|
|
|
return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn);
|
|
}
|
|
|
|
static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
|
|
void *addr, size_t bytes, struct iov_iter *i)
|
|
{
|
|
return copy_from_iter_flushcache(addr, bytes, i);
|
|
}
|
|
|
|
static const struct dax_operations pmem_dax_ops = {
|
|
.direct_access = pmem_dax_direct_access,
|
|
.copy_from_iter = pmem_copy_from_iter,
|
|
};
|
|
|
|
static const struct attribute_group *pmem_attribute_groups[] = {
|
|
&dax_attribute_group,
|
|
NULL,
|
|
};
|
|
|
|
static void pmem_release_queue(void *q)
|
|
{
|
|
blk_cleanup_queue(q);
|
|
}
|
|
|
|
static void pmem_freeze_queue(void *q)
|
|
{
|
|
blk_freeze_queue_start(q);
|
|
}
|
|
|
|
static void pmem_release_disk(void *__pmem)
|
|
{
|
|
struct pmem_device *pmem = __pmem;
|
|
|
|
kill_dax(pmem->dax_dev);
|
|
put_dax(pmem->dax_dev);
|
|
del_gendisk(pmem->disk);
|
|
put_disk(pmem->disk);
|
|
}
|
|
|
|
static int pmem_attach_disk(struct device *dev,
|
|
struct nd_namespace_common *ndns)
|
|
{
|
|
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
|
|
struct nd_region *nd_region = to_nd_region(dev->parent);
|
|
int nid = dev_to_node(dev), fua, wbc;
|
|
struct resource *res = &nsio->res;
|
|
struct resource bb_res;
|
|
struct nd_pfn *nd_pfn = NULL;
|
|
struct dax_device *dax_dev;
|
|
struct nd_pfn_sb *pfn_sb;
|
|
struct pmem_device *pmem;
|
|
struct request_queue *q;
|
|
struct device *gendev;
|
|
struct gendisk *disk;
|
|
void *addr;
|
|
int rc;
|
|
|
|
pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
|
|
if (!pmem)
|
|
return -ENOMEM;
|
|
|
|
/* while nsio_rw_bytes is active, parse a pfn info block if present */
|
|
if (is_nd_pfn(dev)) {
|
|
nd_pfn = to_nd_pfn(dev);
|
|
rc = nvdimm_setup_pfn(nd_pfn, &pmem->pgmap);
|
|
if (rc)
|
|
return rc;
|
|
}
|
|
|
|
/* we're attaching a block device, disable raw namespace access */
|
|
devm_nsio_disable(dev, nsio);
|
|
|
|
dev_set_drvdata(dev, pmem);
|
|
pmem->phys_addr = res->start;
|
|
pmem->size = resource_size(res);
|
|
fua = nvdimm_has_flush(nd_region);
|
|
if (!IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) || fua < 0) {
|
|
dev_warn(dev, "unable to guarantee persistence of writes\n");
|
|
fua = 0;
|
|
}
|
|
wbc = nvdimm_has_cache(nd_region);
|
|
|
|
if (!devm_request_mem_region(dev, res->start, resource_size(res),
|
|
dev_name(&ndns->dev))) {
|
|
dev_warn(dev, "could not reserve region %pR\n", res);
|
|
return -EBUSY;
|
|
}
|
|
|
|
q = blk_alloc_queue_node(GFP_KERNEL, dev_to_node(dev));
|
|
if (!q)
|
|
return -ENOMEM;
|
|
|
|
if (devm_add_action_or_reset(dev, pmem_release_queue, q))
|
|
return -ENOMEM;
|
|
|
|
pmem->pfn_flags = PFN_DEV;
|
|
pmem->pgmap.ref = &q->q_usage_counter;
|
|
if (is_nd_pfn(dev)) {
|
|
addr = devm_memremap_pages(dev, &pmem->pgmap);
|
|
pfn_sb = nd_pfn->pfn_sb;
|
|
pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
|
|
pmem->pfn_pad = resource_size(res) -
|
|
resource_size(&pmem->pgmap.res);
|
|
pmem->pfn_flags |= PFN_MAP;
|
|
memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
|
|
bb_res.start += pmem->data_offset;
|
|
} else if (pmem_should_map_pages(dev)) {
|
|
memcpy(&pmem->pgmap.res, &nsio->res, sizeof(pmem->pgmap.res));
|
|
pmem->pgmap.altmap_valid = false;
|
|
addr = devm_memremap_pages(dev, &pmem->pgmap);
|
|
pmem->pfn_flags |= PFN_MAP;
|
|
memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
|
|
} else
|
|
addr = devm_memremap(dev, pmem->phys_addr,
|
|
pmem->size, ARCH_MEMREMAP_PMEM);
|
|
|
|
/*
|
|
* At release time the queue must be frozen before
|
|
* devm_memremap_pages is unwound
|
|
*/
|
|
if (devm_add_action_or_reset(dev, pmem_freeze_queue, q))
|
|
return -ENOMEM;
|
|
|
|
if (IS_ERR(addr))
|
|
return PTR_ERR(addr);
|
|
pmem->virt_addr = addr;
|
|
|
|
blk_queue_write_cache(q, wbc, fua);
|
|
blk_queue_make_request(q, pmem_make_request);
|
|
blk_queue_physical_block_size(q, PAGE_SIZE);
|
|
blk_queue_logical_block_size(q, pmem_sector_size(ndns));
|
|
blk_queue_max_hw_sectors(q, UINT_MAX);
|
|
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
|
|
queue_flag_set_unlocked(QUEUE_FLAG_DAX, q);
|
|
q->queuedata = pmem;
|
|
|
|
disk = alloc_disk_node(0, nid);
|
|
if (!disk)
|
|
return -ENOMEM;
|
|
pmem->disk = disk;
|
|
|
|
disk->fops = &pmem_fops;
|
|
disk->queue = q;
|
|
disk->flags = GENHD_FL_EXT_DEVT;
|
|
disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
|
|
nvdimm_namespace_disk_name(ndns, disk->disk_name);
|
|
set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset)
|
|
/ 512);
|
|
if (devm_init_badblocks(dev, &pmem->bb))
|
|
return -ENOMEM;
|
|
nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_res);
|
|
disk->bb = &pmem->bb;
|
|
|
|
dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops);
|
|
if (!dax_dev) {
|
|
put_disk(disk);
|
|
return -ENOMEM;
|
|
}
|
|
dax_write_cache(dax_dev, wbc);
|
|
pmem->dax_dev = dax_dev;
|
|
|
|
gendev = disk_to_dev(disk);
|
|
gendev->groups = pmem_attribute_groups;
|
|
|
|
device_add_disk(dev, disk);
|
|
if (devm_add_action_or_reset(dev, pmem_release_disk, pmem))
|
|
return -ENOMEM;
|
|
|
|
revalidate_disk(disk);
|
|
|
|
pmem->bb_state = sysfs_get_dirent(disk_to_dev(disk)->kobj.sd,
|
|
"badblocks");
|
|
if (!pmem->bb_state)
|
|
dev_warn(dev, "'badblocks' notification disabled\n");
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int nd_pmem_probe(struct device *dev)
|
|
{
|
|
struct nd_namespace_common *ndns;
|
|
|
|
ndns = nvdimm_namespace_common_probe(dev);
|
|
if (IS_ERR(ndns))
|
|
return PTR_ERR(ndns);
|
|
|
|
if (devm_nsio_enable(dev, to_nd_namespace_io(&ndns->dev)))
|
|
return -ENXIO;
|
|
|
|
if (is_nd_btt(dev))
|
|
return nvdimm_namespace_attach_btt(ndns);
|
|
|
|
if (is_nd_pfn(dev))
|
|
return pmem_attach_disk(dev, ndns);
|
|
|
|
/* if we find a valid info-block we'll come back as that personality */
|
|
if (nd_btt_probe(dev, ndns) == 0 || nd_pfn_probe(dev, ndns) == 0
|
|
|| nd_dax_probe(dev, ndns) == 0)
|
|
return -ENXIO;
|
|
|
|
/* ...otherwise we're just a raw pmem device */
|
|
return pmem_attach_disk(dev, ndns);
|
|
}
|
|
|
|
static int nd_pmem_remove(struct device *dev)
|
|
{
|
|
struct pmem_device *pmem = dev_get_drvdata(dev);
|
|
|
|
if (is_nd_btt(dev))
|
|
nvdimm_namespace_detach_btt(to_nd_btt(dev));
|
|
else {
|
|
/*
|
|
* Note, this assumes device_lock() context to not race
|
|
* nd_pmem_notify()
|
|
*/
|
|
sysfs_put(pmem->bb_state);
|
|
pmem->bb_state = NULL;
|
|
}
|
|
nvdimm_flush(to_nd_region(dev->parent));
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void nd_pmem_shutdown(struct device *dev)
|
|
{
|
|
nvdimm_flush(to_nd_region(dev->parent));
|
|
}
|
|
|
|
static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
|
|
{
|
|
struct nd_region *nd_region;
|
|
resource_size_t offset = 0, end_trunc = 0;
|
|
struct nd_namespace_common *ndns;
|
|
struct nd_namespace_io *nsio;
|
|
struct resource res;
|
|
struct badblocks *bb;
|
|
struct kernfs_node *bb_state;
|
|
|
|
if (event != NVDIMM_REVALIDATE_POISON)
|
|
return;
|
|
|
|
if (is_nd_btt(dev)) {
|
|
struct nd_btt *nd_btt = to_nd_btt(dev);
|
|
|
|
ndns = nd_btt->ndns;
|
|
nd_region = to_nd_region(ndns->dev.parent);
|
|
nsio = to_nd_namespace_io(&ndns->dev);
|
|
bb = &nsio->bb;
|
|
bb_state = NULL;
|
|
} else {
|
|
struct pmem_device *pmem = dev_get_drvdata(dev);
|
|
|
|
nd_region = to_region(pmem);
|
|
bb = &pmem->bb;
|
|
bb_state = pmem->bb_state;
|
|
|
|
if (is_nd_pfn(dev)) {
|
|
struct nd_pfn *nd_pfn = to_nd_pfn(dev);
|
|
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
|
|
|
|
ndns = nd_pfn->ndns;
|
|
offset = pmem->data_offset +
|
|
__le32_to_cpu(pfn_sb->start_pad);
|
|
end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
|
|
} else {
|
|
ndns = to_ndns(dev);
|
|
}
|
|
|
|
nsio = to_nd_namespace_io(&ndns->dev);
|
|
}
|
|
|
|
res.start = nsio->res.start + offset;
|
|
res.end = nsio->res.end - end_trunc;
|
|
nvdimm_badblocks_populate(nd_region, bb, &res);
|
|
if (bb_state)
|
|
sysfs_notify_dirent(bb_state);
|
|
}
|
|
|
|
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,
|
|
.notify = nd_pmem_notify,
|
|
.shutdown = nd_pmem_shutdown,
|
|
.drv = {
|
|
.name = "nd_pmem",
|
|
},
|
|
.type = ND_DRIVER_NAMESPACE_IO | ND_DRIVER_NAMESPACE_PMEM,
|
|
};
|
|
|
|
static int __init pmem_init(void)
|
|
{
|
|
return nd_driver_register(&nd_pmem_driver);
|
|
}
|
|
module_init(pmem_init);
|
|
|
|
static void pmem_exit(void)
|
|
{
|
|
driver_unregister(&nd_pmem_driver.drv);
|
|
}
|
|
module_exit(pmem_exit);
|
|
|
|
MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
|
|
MODULE_LICENSE("GPL v2");
|