diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-17 09:51:57 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-17 09:51:57 -0800 |
commit | a3841f94c7ecb3ede0f888d3fcfe8fb6368ddd7a (patch) | |
tree | 6625eedf10d0672068ee218bb893a5a0e1803df2 /drivers/nvdimm/badrange.c | |
parent | adeba81ac2a6451f44545874da3d181081f0ab04 (diff) | |
parent | 4247f24c23589bcc3bc3490515ef8c9497e9ae55 (diff) |
Merge tag 'libnvdimm-for-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm and dax updates from Dan Williams:
"Save for a few late fixes, all of these commits have shipped in -next
releases since before the merge window opened, and 0day has given a
build success notification.
The ext4 touches came from Jan, and the xfs touches have Darrick's
reviewed-by. An xfstest for the MAP_SYNC feature has been through
a few round of reviews and is on track to be merged.
- Introduce MAP_SYNC and MAP_SHARED_VALIDATE, a mechanism to enable
'userspace flush' of persistent memory updates via filesystem-dax
mappings. It arranges for any filesystem metadata updates that may
be required to satisfy a write fault to also be flushed ("on disk")
before the kernel returns to userspace from the fault handler.
Effectively every write-fault that dirties metadata completes an
fsync() before returning from the fault handler. The new
MAP_SHARED_VALIDATE mapping type guarantees that the MAP_SYNC flag
is validated as supported by the filesystem's ->mmap() file
operation.
- Add support for the standard ACPI 6.2 label access methods that
replace the NVDIMM_FAMILY_INTEL (vendor specific) label methods.
This enables interoperability with environments that only implement
the standardized methods.
- Add support for the ACPI 6.2 NVDIMM media error injection methods.
- Add support for the NVDIMM_FAMILY_INTEL v1.6 DIMM commands for
latch last shutdown status, firmware update, SMART error injection,
and SMART alarm threshold control.
- Cleanup physical address information disclosures to be root-only.
- Fix revalidation of the DIMM "locked label area" status to support
dynamic unlock of the label area.
- Expand unit test infrastructure to mock the ACPI 6.2 Translate SPA
(system-physical-address) command and error injection commands.
Acknowledgements that came after the commits were pushed to -next:
- 957ac8c421ad ("dax: fix PMD faults on zero-length files"):
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
- a39e596baa07 ("xfs: support for synchronous DAX faults") and
7b565c9f965b ("xfs: Implement xfs_filemap_pfn_mkwrite() using __xfs_filemap_fault()")
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>"
* tag 'libnvdimm-for-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (49 commits)
acpi, nfit: add 'Enable Latch System Shutdown Status' command support
dax: fix general protection fault in dax_alloc_inode
dax: fix PMD faults on zero-length files
dax: stop requiring a live device for dax_flush()
brd: remove dax support
dax: quiet bdev_dax_supported()
fs, dax: unify IOMAP_F_DIRTY read vs write handling policy in the dax core
tools/testing/nvdimm: unit test clear-error commands
acpi, nfit: validate commands against the device type
tools/testing/nvdimm: stricter bounds checking for error injection commands
xfs: support for synchronous DAX faults
xfs: Implement xfs_filemap_pfn_mkwrite() using __xfs_filemap_fault()
ext4: Support for synchronous DAX faults
ext4: Simplify error handling in ext4_dax_huge_fault()
dax: Implement dax_finish_sync_fault()
dax, iomap: Add support for synchronous faults
mm: Define MAP_SYNC and VM_SYNC flags
dax: Allow tuning whether dax_insert_mapping_entry() dirties entry
dax: Allow dax_iomap_fault() to return pfn
dax: Fix comment describing dax_iomap_fault()
...
Diffstat (limited to 'drivers/nvdimm/badrange.c')
-rw-r--r-- | drivers/nvdimm/badrange.c | 293 |
1 files changed, 293 insertions, 0 deletions
diff --git a/drivers/nvdimm/badrange.c b/drivers/nvdimm/badrange.c new file mode 100644 index 000000000000..e068d72b4357 --- /dev/null +++ b/drivers/nvdimm/badrange.c @@ -0,0 +1,293 @@ +/* + * Copyright(c) 2017 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/libnvdimm.h> +#include <linux/badblocks.h> +#include <linux/export.h> +#include <linux/module.h> +#include <linux/blkdev.h> +#include <linux/device.h> +#include <linux/ctype.h> +#include <linux/ndctl.h> +#include <linux/mutex.h> +#include <linux/slab.h> +#include <linux/io.h> +#include "nd-core.h" +#include "nd.h" + +void badrange_init(struct badrange *badrange) +{ + INIT_LIST_HEAD(&badrange->list); + spin_lock_init(&badrange->lock); +} +EXPORT_SYMBOL_GPL(badrange_init); + +static void append_badrange_entry(struct badrange *badrange, + struct badrange_entry *bre, u64 addr, u64 length) +{ + lockdep_assert_held(&badrange->lock); + bre->start = addr; + bre->length = length; + list_add_tail(&bre->list, &badrange->list); +} + +static int alloc_and_append_badrange_entry(struct badrange *badrange, + u64 addr, u64 length, gfp_t flags) +{ + struct badrange_entry *bre; + + bre = kzalloc(sizeof(*bre), flags); + if (!bre) + return -ENOMEM; + + append_badrange_entry(badrange, bre, addr, length); + return 0; +} + +static int add_badrange(struct badrange *badrange, u64 addr, u64 length) +{ + struct badrange_entry *bre, *bre_new; + + spin_unlock(&badrange->lock); + bre_new = kzalloc(sizeof(*bre_new), GFP_KERNEL); + spin_lock(&badrange->lock); + + if (list_empty(&badrange->list)) { + if (!bre_new) + return -ENOMEM; + append_badrange_entry(badrange, bre_new, addr, length); + return 0; + } + + /* + * There is a chance this is a duplicate, check for those first. + * This will be the common case as ARS_STATUS returns all known + * errors in the SPA space, and we can't query it per region + */ + list_for_each_entry(bre, &badrange->list, list) + if (bre->start == addr) { + /* If length has changed, update this list entry */ + if (bre->length != length) + bre->length = length; + kfree(bre_new); + return 0; + } + + /* + * If not a duplicate or a simple length update, add the entry as is, + * as any overlapping ranges will get resolved when the list is consumed + * and converted to badblocks + */ + if (!bre_new) + return -ENOMEM; + append_badrange_entry(badrange, bre_new, addr, length); + + return 0; +} + +int badrange_add(struct badrange *badrange, u64 addr, u64 length) +{ + int rc; + + spin_lock(&badrange->lock); + rc = add_badrange(badrange, addr, length); + spin_unlock(&badrange->lock); + + return rc; +} +EXPORT_SYMBOL_GPL(badrange_add); + +void badrange_forget(struct badrange *badrange, phys_addr_t start, + unsigned int len) +{ + struct list_head *badrange_list = &badrange->list; + u64 clr_end = start + len - 1; + struct badrange_entry *bre, *next; + + spin_lock(&badrange->lock); + + /* + * [start, clr_end] is the badrange interval being cleared. + * [bre->start, bre_end] is the badrange_list entry we're comparing + * the above interval against. The badrange list entry may need + * to be modified (update either start or length), deleted, or + * split into two based on the overlap characteristics + */ + + list_for_each_entry_safe(bre, next, badrange_list, list) { + u64 bre_end = bre->start + bre->length - 1; + + /* Skip intervals with no intersection */ + if (bre_end < start) + continue; + if (bre->start > clr_end) + continue; + /* Delete completely overlapped badrange entries */ + if ((bre->start >= start) && (bre_end <= clr_end)) { + list_del(&bre->list); + kfree(bre); + continue; + } + /* Adjust start point of partially cleared entries */ + if ((start <= bre->start) && (clr_end > bre->start)) { + bre->length -= clr_end - bre->start + 1; + bre->start = clr_end + 1; + continue; + } + /* Adjust bre->length for partial clearing at the tail end */ + if ((bre->start < start) && (bre_end <= clr_end)) { + /* bre->start remains the same */ + bre->length = start - bre->start; + continue; + } + /* + * If clearing in the middle of an entry, we split it into + * two by modifying the current entry to represent one half of + * the split, and adding a new entry for the second half. + */ + if ((bre->start < start) && (bre_end > clr_end)) { + u64 new_start = clr_end + 1; + u64 new_len = bre_end - new_start + 1; + + /* Add new entry covering the right half */ + alloc_and_append_badrange_entry(badrange, new_start, + new_len, GFP_NOWAIT); + /* Adjust this entry to cover the left half */ + bre->length = start - bre->start; + continue; + } + } + spin_unlock(&badrange->lock); +} +EXPORT_SYMBOL_GPL(badrange_forget); + +static void set_badblock(struct badblocks *bb, sector_t s, int num) +{ + dev_dbg(bb->dev, "Found a bad range (0x%llx, 0x%llx)\n", + (u64) s * 512, (u64) num * 512); + /* this isn't an error as the hardware will still throw an exception */ + if (badblocks_set(bb, s, num, 1)) + dev_info_once(bb->dev, "%s: failed for sector %llx\n", + __func__, (u64) s); +} + +/** + * __add_badblock_range() - Convert a physical address range to bad sectors + * @bb: badblocks instance to populate + * @ns_offset: namespace offset where the error range begins (in bytes) + * @len: number of bytes of badrange to be added + * + * This assumes that the range provided with (ns_offset, len) is within + * the bounds of physical addresses for this namespace, i.e. lies in the + * interval [ns_start, ns_start + ns_size) + */ +static void __add_badblock_range(struct badblocks *bb, u64 ns_offset, u64 len) +{ + const unsigned int sector_size = 512; + sector_t start_sector, end_sector; + u64 num_sectors; + u32 rem; + + start_sector = div_u64(ns_offset, sector_size); + end_sector = div_u64_rem(ns_offset + len, sector_size, &rem); + if (rem) + end_sector++; + num_sectors = end_sector - start_sector; + + if (unlikely(num_sectors > (u64)INT_MAX)) { + u64 remaining = num_sectors; + sector_t s = start_sector; + + while (remaining) { + int done = min_t(u64, remaining, INT_MAX); + + set_badblock(bb, s, done); + remaining -= done; + s += done; + } + } else + set_badblock(bb, start_sector, num_sectors); +} + +static void badblocks_populate(struct badrange *badrange, + struct badblocks *bb, const struct resource *res) +{ + struct badrange_entry *bre; + + if (list_empty(&badrange->list)) + return; + + list_for_each_entry(bre, &badrange->list, list) { + u64 bre_end = bre->start + bre->length - 1; + + /* Discard intervals with no intersection */ + if (bre_end < res->start) + continue; + if (bre->start > res->end) + continue; + /* Deal with any overlap after start of the namespace */ + if (bre->start >= res->start) { + u64 start = bre->start; + u64 len; + + if (bre_end <= res->end) + len = bre->length; + else + len = res->start + resource_size(res) + - bre->start; + __add_badblock_range(bb, start - res->start, len); + continue; + } + /* + * Deal with overlap for badrange starting before + * the namespace. + */ + if (bre->start < res->start) { + u64 len; + + if (bre_end < res->end) + len = bre->start + bre->length - res->start; + else + len = resource_size(res); + __add_badblock_range(bb, 0, len); + } + } +} + +/** + * nvdimm_badblocks_populate() - Convert a list of badranges to badblocks + * @region: parent region of the range to interrogate + * @bb: badblocks instance to populate + * @res: resource range to consider + * + * The badrange list generated during bus initialization may contain + * multiple, possibly overlapping physical address ranges. Compare each + * of these ranges to the resource range currently being initialized, + * and add badblocks entries for all matching sub-ranges + */ +void nvdimm_badblocks_populate(struct nd_region *nd_region, + struct badblocks *bb, const struct resource *res) +{ + struct nvdimm_bus *nvdimm_bus; + + if (!is_memory(&nd_region->dev)) { + dev_WARN_ONCE(&nd_region->dev, 1, + "%s only valid for pmem regions\n", __func__); + return; + } + nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev); + + nvdimm_bus_lock(&nvdimm_bus->dev); + badblocks_populate(&nvdimm_bus->badrange, bb, res); + nvdimm_bus_unlock(&nvdimm_bus->dev); +} +EXPORT_SYMBOL_GPL(nvdimm_badblocks_populate); |