forked from Minki/linux
53ef7d0e20
* Region media error reporting: A libnvdimm region device is the parent to one or more namespaces. To date, media errors have been reported via the "badblocks" attribute attached to pmem block devices for namespaces in "raw" or "memory" mode. Given that namespaces can be in "device-dax" or "btt-sector" mode this new interface reports media errors generically, i.e. independent of namespace modes or state. This subsequently allows userspace tooling to craft "ACPI 6.1 Section 9.20.7.6 Function Index 4 - Clear Uncorrectable Error" requests and submit them via the ioctl path for NVDIMM root bus devices. * Introduce 'struct dax_device' and 'struct dax_operations': Prompted by a request from Linus and feedback from Christoph this allows for dax capable drivers to publish their own custom dax operations. This fixes the broken assumption that all dax operations are related to a persistent memory device, and makes it easier for other architectures and platforms to add customized persistent memory support. * 'libnvdimm' core updates: A new "deep_flush" sysfs attribute is available for storage appliance applications to manually trigger memory controllers to drain write-pending buffers that would otherwise be flushed automatically by the platform ADR (asynchronous-DRAM-refresh) mechanism at a power loss event. Support for "locked" DIMMs is included to prevent namespaces from surfacing when the namespace label data area is locked. Finally, fixes for various reported deadlocks and crashes, also tagged for -stable. * ACPI / nfit driver updates: General updates of the nfit driver to add DSM command overrides, ACPI 6.1 health state flags support, DSM payload debug available by default, and various fixes. Acknowledgements that came after the branch was pushed: commmit565851c972
"device-dax: fix sysfs attribute deadlock" Tested-by: Yi Zhang <yizhan@redhat.com> commit23f4984483
"libnvdimm: rework region badblocks clearing" Tested-by: Toshi Kani <toshi.kani@hpe.com> -----BEGIN PGP SIGNATURE----- iQIcBAABAgAGBQJZDONJAAoJEB7SkWpmfYgC3SsP/2KrLvTUcz646ViuPOgZ2cC4 W6wAx6cvDSt+H52kLnFEsYoFt7WAj20ggPirb/Bc5jkGlvwE0lT9Xtmso9GpVkYT J9ZJ9pP/4YaAD3II1gmTwaUjYi0FxoOdx3Eb92yuWkO/8ylz4b2Nu3cBpYwyziGQ nIfEVwDXRLE86u6x0bWuf6TlVuvsbdiAI55CDqDMVQC6xIOLbSez7b8QIHlpiKEb Mw+xqdQva0esoreZEOXEhWNO+qtfILx8/ceBEGTNMp4e/JjZ2FbrSNplM+9bH5k7 ywqP8lW+mBEw0fmBBkYoVG/xyesiiBb55JLnbi8Ew+7IUxw8a3iV7wftRi62lHcK zAjsHe4L+MansgtZsCL8wluvIPaktAdtB4xr7l9VNLKRYRUG73jEWU0gcUNryHIL BkQJ52pUS1PkClyAsWbBBHl1I/CvzVPd21VW0YELmLR4OywKy1c+eKw2bcYgjrb4 59HZSv6S6EoKaQC+2qvVNpePil7cdfg5V2ubH/ki9HoYVyoxDptEWHnvf0NNatIH Y7mNcOPvhOksJmnKSyHbDjtRur7WoHIlC9D7UjEFkSBWsKPjxJHoidN4SnCMRtjQ WKQU0seoaKj04b68Bs/Qm9NozVgnsPFIUDZeLMikLFX2Jt7YSPu+Jmi2s4re6WLh TmJQ3Ly9t3o3/weHSzmn =Ox0s -----END PGP SIGNATURE----- Merge tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm Pull libnvdimm updates from Dan Williams: "The bulk of this has been in multiple -next releases. There were a few late breaking fixes and small features that got added in the last couple days, but the whole set has received a build success notification from the kbuild robot. Change summary: - Region media error reporting: A libnvdimm region device is the parent to one or more namespaces. To date, media errors have been reported via the "badblocks" attribute attached to pmem block devices for namespaces in "raw" or "memory" mode. Given that namespaces can be in "device-dax" or "btt-sector" mode this new interface reports media errors generically, i.e. independent of namespace modes or state. This subsequently allows userspace tooling to craft "ACPI 6.1 Section 9.20.7.6 Function Index 4 - Clear Uncorrectable Error" requests and submit them via the ioctl path for NVDIMM root bus devices. - Introduce 'struct dax_device' and 'struct dax_operations': Prompted by a request from Linus and feedback from Christoph this allows for dax capable drivers to publish their own custom dax operations. This fixes the broken assumption that all dax operations are related to a persistent memory device, and makes it easier for other architectures and platforms to add customized persistent memory support. - 'libnvdimm' core updates: A new "deep_flush" sysfs attribute is available for storage appliance applications to manually trigger memory controllers to drain write-pending buffers that would otherwise be flushed automatically by the platform ADR (asynchronous-DRAM-refresh) mechanism at a power loss event. Support for "locked" DIMMs is included to prevent namespaces from surfacing when the namespace label data area is locked. Finally, fixes for various reported deadlocks and crashes, also tagged for -stable. - ACPI / nfit driver updates: General updates of the nfit driver to add DSM command overrides, ACPI 6.1 health state flags support, DSM payload debug available by default, and various fixes. Acknowledgements that came after the branch was pushed: - commmit565851c972
"device-dax: fix sysfs attribute deadlock": Tested-by: Yi Zhang <yizhan@redhat.com> - commit23f4984483
"libnvdimm: rework region badblocks clearing" Tested-by: Toshi Kani <toshi.kani@hpe.com>" * tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (52 commits) libnvdimm, pfn: fix 'npfns' vs section alignment libnvdimm: handle locked label storage areas libnvdimm: convert NDD_ flags to use bitops, introduce NDD_LOCKED brd: fix uninitialized use of brd->dax_dev block, dax: use correct format string in bdev_dax_supported device-dax: fix sysfs attribute deadlock libnvdimm: restore "libnvdimm: band aid btt vs clear poison locking" libnvdimm: fix nvdimm_bus_lock() vs device_lock() ordering libnvdimm: rework region badblocks clearing acpi, nfit: kill ACPI_NFIT_DEBUG libnvdimm: fix clear length of nvdimm_forget_poison() libnvdimm, pmem: fix a NULL pointer BUG in nd_pmem_notify libnvdimm, region: sysfs trigger for nvdimm_flush() libnvdimm: fix phys_addr for nvdimm_clear_poison x86, dax, pmem: remove indirection around memcpy_from_pmem() block: remove block_device_operations ->direct_access() block, dax: convert bdev_dax_supported() to dax_direct_access() filesystem-dax: convert to dax_direct_access() Revert "block: use DAX for partition table reads" ext2, ext4, xfs: retrieve dax_device for iomap operations ...
164 lines
4.0 KiB
C
164 lines
4.0 KiB
C
/*
|
|
* Copyright(c) 2016 Intel Corporation. All rights reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of version 2 of the GNU General Public License as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that 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 <linux/percpu-refcount.h>
|
|
#include <linux/memremap.h>
|
|
#include <linux/module.h>
|
|
#include <linux/pfn_t.h>
|
|
#include "../nvdimm/pfn.h"
|
|
#include "../nvdimm/nd.h"
|
|
#include "device-dax.h"
|
|
|
|
struct dax_pmem {
|
|
struct device *dev;
|
|
struct percpu_ref ref;
|
|
struct completion cmp;
|
|
};
|
|
|
|
static struct dax_pmem *to_dax_pmem(struct percpu_ref *ref)
|
|
{
|
|
return container_of(ref, struct dax_pmem, ref);
|
|
}
|
|
|
|
static void dax_pmem_percpu_release(struct percpu_ref *ref)
|
|
{
|
|
struct dax_pmem *dax_pmem = to_dax_pmem(ref);
|
|
|
|
dev_dbg(dax_pmem->dev, "%s\n", __func__);
|
|
complete(&dax_pmem->cmp);
|
|
}
|
|
|
|
static void dax_pmem_percpu_exit(void *data)
|
|
{
|
|
struct percpu_ref *ref = data;
|
|
struct dax_pmem *dax_pmem = to_dax_pmem(ref);
|
|
|
|
dev_dbg(dax_pmem->dev, "%s\n", __func__);
|
|
wait_for_completion(&dax_pmem->cmp);
|
|
percpu_ref_exit(ref);
|
|
}
|
|
|
|
static void dax_pmem_percpu_kill(void *data)
|
|
{
|
|
struct percpu_ref *ref = data;
|
|
struct dax_pmem *dax_pmem = to_dax_pmem(ref);
|
|
|
|
dev_dbg(dax_pmem->dev, "%s\n", __func__);
|
|
percpu_ref_kill(ref);
|
|
}
|
|
|
|
static int dax_pmem_probe(struct device *dev)
|
|
{
|
|
int rc;
|
|
void *addr;
|
|
struct resource res;
|
|
struct nd_pfn_sb *pfn_sb;
|
|
struct dev_dax *dev_dax;
|
|
struct dax_pmem *dax_pmem;
|
|
struct nd_region *nd_region;
|
|
struct nd_namespace_io *nsio;
|
|
struct dax_region *dax_region;
|
|
struct nd_namespace_common *ndns;
|
|
struct nd_dax *nd_dax = to_nd_dax(dev);
|
|
struct nd_pfn *nd_pfn = &nd_dax->nd_pfn;
|
|
struct vmem_altmap __altmap, *altmap = NULL;
|
|
|
|
ndns = nvdimm_namespace_common_probe(dev);
|
|
if (IS_ERR(ndns))
|
|
return PTR_ERR(ndns);
|
|
nsio = to_nd_namespace_io(&ndns->dev);
|
|
|
|
/* parse the 'pfn' info block via ->rw_bytes */
|
|
rc = devm_nsio_enable(dev, nsio);
|
|
if (rc)
|
|
return rc;
|
|
altmap = nvdimm_setup_pfn(nd_pfn, &res, &__altmap);
|
|
if (IS_ERR(altmap))
|
|
return PTR_ERR(altmap);
|
|
devm_nsio_disable(dev, nsio);
|
|
|
|
pfn_sb = nd_pfn->pfn_sb;
|
|
|
|
if (!devm_request_mem_region(dev, nsio->res.start,
|
|
resource_size(&nsio->res),
|
|
dev_name(&ndns->dev))) {
|
|
dev_warn(dev, "could not reserve region %pR\n", &nsio->res);
|
|
return -EBUSY;
|
|
}
|
|
|
|
dax_pmem = devm_kzalloc(dev, sizeof(*dax_pmem), GFP_KERNEL);
|
|
if (!dax_pmem)
|
|
return -ENOMEM;
|
|
|
|
dax_pmem->dev = dev;
|
|
init_completion(&dax_pmem->cmp);
|
|
rc = percpu_ref_init(&dax_pmem->ref, dax_pmem_percpu_release, 0,
|
|
GFP_KERNEL);
|
|
if (rc)
|
|
return rc;
|
|
|
|
rc = devm_add_action_or_reset(dev, dax_pmem_percpu_exit,
|
|
&dax_pmem->ref);
|
|
if (rc)
|
|
return rc;
|
|
|
|
addr = devm_memremap_pages(dev, &res, &dax_pmem->ref, altmap);
|
|
if (IS_ERR(addr))
|
|
return PTR_ERR(addr);
|
|
|
|
rc = devm_add_action_or_reset(dev, dax_pmem_percpu_kill,
|
|
&dax_pmem->ref);
|
|
if (rc)
|
|
return rc;
|
|
|
|
/* adjust the dax_region resource to the start of data */
|
|
res.start += le64_to_cpu(pfn_sb->dataoff);
|
|
|
|
nd_region = to_nd_region(dev->parent);
|
|
dax_region = alloc_dax_region(dev, nd_region->id, &res,
|
|
le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP);
|
|
if (!dax_region)
|
|
return -ENOMEM;
|
|
|
|
/* TODO: support for subdividing a dax region... */
|
|
dev_dax = devm_create_dev_dax(dax_region, &res, 1);
|
|
|
|
/* child dev_dax instances now own the lifetime of the dax_region */
|
|
dax_region_put(dax_region);
|
|
|
|
return PTR_ERR_OR_ZERO(dev_dax);
|
|
}
|
|
|
|
static struct nd_device_driver dax_pmem_driver = {
|
|
.probe = dax_pmem_probe,
|
|
.drv = {
|
|
.name = "dax_pmem",
|
|
},
|
|
.type = ND_DRIVER_DAX_PMEM,
|
|
};
|
|
|
|
static int __init dax_pmem_init(void)
|
|
{
|
|
return nd_driver_register(&dax_pmem_driver);
|
|
}
|
|
module_init(dax_pmem_init);
|
|
|
|
static void __exit dax_pmem_exit(void)
|
|
{
|
|
driver_unregister(&dax_pmem_driver.drv);
|
|
}
|
|
module_exit(dax_pmem_exit);
|
|
|
|
MODULE_LICENSE("GPL v2");
|
|
MODULE_AUTHOR("Intel Corporation");
|
|
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DAX_PMEM);
|