linux/drivers/md/dm-linear.c
Linus Torvalds 9f3a0941fb libnvdimm for 4.17
* A rework of the filesytem-dax implementation provides for detection of
   unmap operations (truncate / hole punch) colliding with in-progress
   device-DMA. A fix for these collisions remains a work-in-progress
   pending resolution of truncate latency and starvation regressions.
 
 * The of_pmem driver expands the users of libnvdimm outside of x86 and
   ACPI to describe an implementation of persistent memory on PowerPC with
   Open Firmware / Device tree.
 
 * Address Range Scrub (ARS) handling is completely rewritten to account for
   the fact that ARS may run for 100s of seconds and there is no platform
   defined way to cancel it. ARS will now no longer block namespace
   initialization.
 
 * The NVDIMM Namespace Label implementation is updated to handle label
   areas as small as 1K, down from 128K.
 
 * Miscellaneous cleanups and updates to unit test infrastructure.
 -----BEGIN PGP SIGNATURE-----
 
 iQIcBAABAgAGBQJazDt5AAoJEB7SkWpmfYgCqGMQALLwdPeY87cUK7AvQ2IXj46B
 lJgeVuHPzyQDbC03AS5uUYnnU3I5lFd7i4y7ZrywNpFs4lsb/bNmbUpQE5xp+Yvc
 1MJ/JYDIP5X4misWYm3VJo85N49+VqSRgAQk52PBigwnZ7M6/u4cSptXM9//c9JL
 /NYbat6IjjY6Tx49Tec6+F3GMZjsFLcuTVkQcREoOyOqVJE4YpP0vhNjEe0vq6vr
 EsSWiqEI5VFH4PfJwKdKj/64IKB4FGKj2A5cEgjQBxW2vw7tTJnkRkdE3jDUjqtg
 xYAqGp/Dqs4+bgdYlT817YhiOVrcr5mOHj7TKWQrBPgzKCbcG5eKDmfT8t+3NEga
 9kBlgisqIcG72lwZNA7QkEHxq1Omy9yc1hUv9qz2YA0G+J1WE8l1T15k1DOFwV57
 qIrLLUypklNZLxvrzNjclempboKc4JCUlj+TdN5E5Y6pRs55UWTXaP7Xf5O7z0vf
 l/uiiHkc3MPH73YD2PSEGFJ8m8EU0N8xhrcz3M9E2sHgYCnbty1Lw3FH0/GhThVA
 ya1mMeDdb8A2P7gWCBk1Lqeig+rJKXSey4hKM6D0njOEtMQO1H4tFqGjyfDX1xlJ
 3plUR9WBVEYzN5+9xWbwGag/ezGZ+NfcVO2gmy6yXiEph796BxRAZx/18zKRJr0m
 9eGJG1H+JspcbtLF9iHn
 =acZQ
 -----END PGP SIGNATURE-----

Merge tag 'libnvdimm-for-4.17' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "This cycle was was not something I ever want to repeat as there were
  several late changes that have only now just settled.

  Half of the branch up to commit d2c997c0f1 ("fs, dax: use
  page->mapping to warn...") have been in -next for several releases.
  The of_pmem driver and the address range scrub rework were late
  arrivals, and the dax work was scaled back at the last moment.

  The of_pmem driver missed a previous merge window due to an oversight.
  A sense of obligation to rectify that miss is why it is included for
  4.17. It has acks from PowerPC folks. Stephen reported a build failure
  that only occurs when merging it with your latest tree, for now I have
  fixed that up by disabling modular builds of of_pmem. A test merge
  with your tree has received a build success report from the 0day robot
  over 156 configs.

  An initial version of the ARS rework was submitted before the merge
  window. It is self contained to libnvdimm, a net code reduction, and
  passing all unit tests.

  The filesystem-dax changes are based on the wait_var_event()
  functionality from tip/sched/core. However, late review feedback
  showed that those changes regressed truncate performance to a large
  degree. The branch was rewound to drop the truncate behavior change
  and now only includes preparation patches and cleanups (with full acks
  and reviews). The finalization of this dax-dma-vs-trnucate work will
  need to wait for 4.18.

  Summary:

   - A rework of the filesytem-dax implementation provides for detection
     of unmap operations (truncate / hole punch) colliding with
     in-progress device-DMA. A fix for these collisions remains a
     work-in-progress pending resolution of truncate latency and
     starvation regressions.

   - The of_pmem driver expands the users of libnvdimm outside of x86
     and ACPI to describe an implementation of persistent memory on
     PowerPC with Open Firmware / Device tree.

   - Address Range Scrub (ARS) handling is completely rewritten to
     account for the fact that ARS may run for 100s of seconds and there
     is no platform defined way to cancel it. ARS will now no longer
     block namespace initialization.

   - The NVDIMM Namespace Label implementation is updated to handle
     label areas as small as 1K, down from 128K.

   - Miscellaneous cleanups and updates to unit test infrastructure"

* tag 'libnvdimm-for-4.17' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (39 commits)
  libnvdimm, of_pmem: workaround OF_NUMA=n build error
  nfit, address-range-scrub: add module option to skip initial ars
  nfit, address-range-scrub: rework and simplify ARS state machine
  nfit, address-range-scrub: determine one platform max_ars value
  powerpc/powernv: Create platform devs for nvdimm buses
  doc/devicetree: Persistent memory region bindings
  libnvdimm: Add device-tree based driver
  libnvdimm: Add of_node to region and bus descriptors
  libnvdimm, region: quiet region probe
  libnvdimm, namespace: use a safe lookup for dimm device name
  libnvdimm, dimm: fix dpa reservation vs uninitialized label area
  libnvdimm, testing: update the default smart ctrl_temperature
  libnvdimm, testing: Add emulation for smart injection commands
  nfit, address-range-scrub: introduce nfit_spa->ars_state
  libnvdimm: add an api to cast a 'struct nd_region' to its 'struct device'
  nfit, address-range-scrub: fix scrub in-progress reporting
  dax, dm: allow device-mapper to operate without dax support
  dax: introduce CONFIG_DAX_DRIVER
  fs, dax: use page->mapping to warn if truncate collides with a busy page
  ext2, dax: introduce ext2_dax_aops
  ...
2018-04-10 10:25:57 -07:00

222 lines
5 KiB
C

/*
* Copyright (C) 2001-2003 Sistina Software (UK) Limited.
*
* This file is released under the GPL.
*/
#include "dm.h"
#include <linux/module.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/dax.h>
#include <linux/slab.h>
#include <linux/device-mapper.h>
#define DM_MSG_PREFIX "linear"
/*
* Linear: maps a linear range of a device.
*/
struct linear_c {
struct dm_dev *dev;
sector_t start;
};
/*
* Construct a linear mapping: <dev_path> <offset>
*/
static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
struct linear_c *lc;
unsigned long long tmp;
char dummy;
int ret;
if (argc != 2) {
ti->error = "Invalid argument count";
return -EINVAL;
}
lc = kmalloc(sizeof(*lc), GFP_KERNEL);
if (lc == NULL) {
ti->error = "Cannot allocate linear context";
return -ENOMEM;
}
ret = -EINVAL;
if (sscanf(argv[1], "%llu%c", &tmp, &dummy) != 1) {
ti->error = "Invalid device sector";
goto bad;
}
lc->start = tmp;
ret = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &lc->dev);
if (ret) {
ti->error = "Device lookup failed";
goto bad;
}
ti->num_flush_bios = 1;
ti->num_discard_bios = 1;
ti->num_secure_erase_bios = 1;
ti->num_write_same_bios = 1;
ti->num_write_zeroes_bios = 1;
ti->private = lc;
return 0;
bad:
kfree(lc);
return ret;
}
static void linear_dtr(struct dm_target *ti)
{
struct linear_c *lc = (struct linear_c *) ti->private;
dm_put_device(ti, lc->dev);
kfree(lc);
}
static sector_t linear_map_sector(struct dm_target *ti, sector_t bi_sector)
{
struct linear_c *lc = ti->private;
return lc->start + dm_target_offset(ti, bi_sector);
}
static void linear_map_bio(struct dm_target *ti, struct bio *bio)
{
struct linear_c *lc = ti->private;
bio_set_dev(bio, lc->dev->bdev);
if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET)
bio->bi_iter.bi_sector =
linear_map_sector(ti, bio->bi_iter.bi_sector);
}
static int linear_map(struct dm_target *ti, struct bio *bio)
{
linear_map_bio(ti, bio);
return DM_MAPIO_REMAPPED;
}
static int linear_end_io(struct dm_target *ti, struct bio *bio,
blk_status_t *error)
{
struct linear_c *lc = ti->private;
if (!*error && bio_op(bio) == REQ_OP_ZONE_REPORT)
dm_remap_zone_report(ti, bio, lc->start);
return DM_ENDIO_DONE;
}
static void linear_status(struct dm_target *ti, status_type_t type,
unsigned status_flags, char *result, unsigned maxlen)
{
struct linear_c *lc = (struct linear_c *) ti->private;
switch (type) {
case STATUSTYPE_INFO:
result[0] = '\0';
break;
case STATUSTYPE_TABLE:
snprintf(result, maxlen, "%s %llu", lc->dev->name,
(unsigned long long)lc->start);
break;
}
}
static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
{
struct linear_c *lc = (struct linear_c *) ti->private;
struct dm_dev *dev = lc->dev;
*bdev = dev->bdev;
/*
* Only pass ioctls through if the device sizes match exactly.
*/
if (lc->start ||
ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT)
return 1;
return 0;
}
static int linear_iterate_devices(struct dm_target *ti,
iterate_devices_callout_fn fn, void *data)
{
struct linear_c *lc = ti->private;
return fn(ti, lc->dev, lc->start, ti->len, data);
}
#if IS_ENABLED(CONFIG_DAX_DRIVER)
static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
long nr_pages, void **kaddr, pfn_t *pfn)
{
long ret;
struct linear_c *lc = ti->private;
struct block_device *bdev = lc->dev->bdev;
struct dax_device *dax_dev = lc->dev->dax_dev;
sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
dev_sector = linear_map_sector(ti, sector);
ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff);
if (ret)
return ret;
return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
}
static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
void *addr, size_t bytes, struct iov_iter *i)
{
struct linear_c *lc = ti->private;
struct block_device *bdev = lc->dev->bdev;
struct dax_device *dax_dev = lc->dev->dax_dev;
sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
dev_sector = linear_map_sector(ti, sector);
if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
return 0;
return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
}
#else
#define linear_dax_direct_access NULL
#define linear_dax_copy_from_iter NULL
#endif
static struct target_type linear_target = {
.name = "linear",
.version = {1, 4, 0},
.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM,
.module = THIS_MODULE,
.ctr = linear_ctr,
.dtr = linear_dtr,
.map = linear_map,
.end_io = linear_end_io,
.status = linear_status,
.prepare_ioctl = linear_prepare_ioctl,
.iterate_devices = linear_iterate_devices,
.direct_access = linear_dax_direct_access,
.dax_copy_from_iter = linear_dax_copy_from_iter,
};
int __init dm_linear_init(void)
{
int r = dm_register_target(&linear_target);
if (r < 0)
DMERR("register failed %d", r);
return r;
}
void dm_linear_exit(void)
{
dm_unregister_target(&linear_target);
}