Commit a3841f94 authored by Linus Torvalds's avatar Linus Torvalds

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:

   - 957ac8c4 ("dax: fix PMD faults on zero-length files"):
Reviewed-by: 's avatarRoss Zwisler <ross.zwisler@linux.intel.com>

   - a39e596b ("xfs: support for synchronous DAX faults") and
     7b565c9f ("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()
  ...
parents adeba81a 4247f24c
......@@ -4208,7 +4208,7 @@ L: linux-i2c@vger.kernel.org
S: Maintained
F: drivers/i2c/busses/i2c-diolan-u2c.c
DIRECT ACCESS (DAX)
FILESYSTEM DIRECT ACCESS (DAX)
M: Matthew Wilcox <mawilcox@microsoft.com>
M: Ross Zwisler <ross.zwisler@linux.intel.com>
L: linux-fsdevel@vger.kernel.org
......@@ -4217,6 +4217,12 @@ F: fs/dax.c
F: include/linux/dax.h
F: include/trace/events/fs_dax.h
DEVICE DIRECT ACCESS (DAX)
M: Dan Williams <dan.j.williams@intel.com>
L: linux-nvdimm@lists.01.org
S: Supported
F: drivers/dax/
DIRECTORY NOTIFICATION (DNOTIFY)
M: Jan Kara <jack@suse.cz>
R: Amir Goldstein <amir73il@gmail.com>
......
......@@ -12,6 +12,7 @@
#define MAP_SHARED 0x01 /* Share changes */
#define MAP_PRIVATE 0x02 /* Changes are private */
#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
#define MAP_TYPE 0x0f /* Mask for type of mapping (OSF/1 is _wrong_) */
#define MAP_FIXED 0x100 /* Interpret addr exactly */
#define MAP_ANONYMOUS 0x10 /* don't use a file */
......
......@@ -29,6 +29,7 @@
*/
#define MAP_SHARED 0x001 /* Share changes */
#define MAP_PRIVATE 0x002 /* Changes are private */
#define MAP_SHARED_VALIDATE 0x003 /* share + validate extension flags */
#define MAP_TYPE 0x00f /* Mask for type of mapping */
#define MAP_FIXED 0x010 /* Interpret addr exactly */
......
......@@ -12,6 +12,7 @@
#define MAP_SHARED 0x01 /* Share changes */
#define MAP_PRIVATE 0x02 /* Changes are private */
#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
#define MAP_TYPE 0x03 /* Mask for type of mapping */
#define MAP_FIXED 0x04 /* Interpret addr exactly */
#define MAP_ANONYMOUS 0x10 /* don't use a file */
......
......@@ -36,6 +36,7 @@
*/
#define MAP_SHARED 0x001 /* Share changes */
#define MAP_PRIVATE 0x002 /* Changes are private */
#define MAP_SHARED_VALIDATE 0x003 /* share + validate extension flags */
#define MAP_TYPE 0x00f /* Mask for type of mapping */
#define MAP_FIXED 0x010 /* Interpret addr exactly */
......
This diff is collapsed.
......@@ -67,7 +67,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
continue;
/* If this fails due to an -ENOMEM, there is little we can do */
nvdimm_bus_add_poison(acpi_desc->nvdimm_bus,
nvdimm_bus_add_badrange(acpi_desc->nvdimm_bus,
ALIGN(mce->addr, L1_CACHE_BYTES),
L1_CACHE_BYTES);
nvdimm_region_notify(nfit_spa->nd_region,
......
......@@ -24,7 +24,7 @@
/* ACPI 6.1 */
#define UUID_NFIT_BUS "2f10e7a4-9e91-11e4-89d3-123b93f75cba"
/* http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf */
/* http://pmem.io/documents/NVDIMM_DSM_Interface-V1.6.pdf */
#define UUID_NFIT_DIMM "4309ac30-0d11-11e4-9191-0800200c9a66"
/* https://github.com/HewlettPackard/hpe-nvm/blob/master/Documentation/ */
......@@ -38,6 +38,37 @@
| ACPI_NFIT_MEM_RESTORE_FAILED | ACPI_NFIT_MEM_FLUSH_FAILED \
| ACPI_NFIT_MEM_NOT_ARMED | ACPI_NFIT_MEM_MAP_FAILED)
#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_MSFT
#define NVDIMM_STANDARD_CMDMASK \
(1 << ND_CMD_SMART | 1 << ND_CMD_SMART_THRESHOLD | 1 << ND_CMD_DIMM_FLAGS \
| 1 << ND_CMD_GET_CONFIG_SIZE | 1 << ND_CMD_GET_CONFIG_DATA \
| 1 << ND_CMD_SET_CONFIG_DATA | 1 << ND_CMD_VENDOR_EFFECT_LOG_SIZE \
| 1 << ND_CMD_VENDOR_EFFECT_LOG | 1 << ND_CMD_VENDOR)
/*
* Command numbers that the kernel needs to know about to handle
* non-default DSM revision ids
*/
enum nvdimm_family_cmds {
NVDIMM_INTEL_LATCH_SHUTDOWN = 10,
NVDIMM_INTEL_GET_MODES = 11,
NVDIMM_INTEL_GET_FWINFO = 12,
NVDIMM_INTEL_START_FWUPDATE = 13,
NVDIMM_INTEL_SEND_FWUPDATE = 14,
NVDIMM_INTEL_FINISH_FWUPDATE = 15,
NVDIMM_INTEL_QUERY_FWUPDATE = 16,
NVDIMM_INTEL_SET_THRESHOLD = 17,
NVDIMM_INTEL_INJECT_ERROR = 18,
};
#define NVDIMM_INTEL_CMDMASK \
(NVDIMM_STANDARD_CMDMASK | 1 << NVDIMM_INTEL_GET_MODES \
| 1 << NVDIMM_INTEL_GET_FWINFO | 1 << NVDIMM_INTEL_START_FWUPDATE \
| 1 << NVDIMM_INTEL_SEND_FWUPDATE | 1 << NVDIMM_INTEL_FINISH_FWUPDATE \
| 1 << NVDIMM_INTEL_QUERY_FWUPDATE | 1 << NVDIMM_INTEL_SET_THRESHOLD \
| 1 << NVDIMM_INTEL_INJECT_ERROR | 1 << NVDIMM_INTEL_LATCH_SHUTDOWN)
enum nfit_uuids {
/* for simplicity alias the uuid index with the family id */
NFIT_DEV_DIMM = NVDIMM_FAMILY_INTEL,
......@@ -140,6 +171,9 @@ struct nfit_mem {
struct resource *flush_wpq;
unsigned long dsm_mask;
int family;
u32 has_lsi:1;
u32 has_lsr:1;
u32 has_lsw:1;
};
struct acpi_nfit_desc {
......@@ -167,6 +201,7 @@ struct acpi_nfit_desc {
unsigned int init_complete:1;
unsigned long dimm_cmd_force_en;
unsigned long bus_cmd_force_en;
unsigned long bus_nfit_cmd_force_en;
int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa,
void *iobuf, u64 len, int rw);
};
......
......@@ -302,7 +302,6 @@ config BLK_DEV_SX8
config BLK_DEV_RAM
tristate "RAM block device support"
select DAX if BLK_DEV_RAM_DAX
---help---
Saying Y here will allow you to use a portion of your RAM memory as
a block device, so that you can make file systems on it, read and
......@@ -338,17 +337,6 @@ config BLK_DEV_RAM_SIZE
The default value is 4096 kilobytes. Only change this if you know
what you are doing.
config BLK_DEV_RAM_DAX
bool "Support Direct Access (DAX) to RAM block devices"
depends on BLK_DEV_RAM && FS_DAX
default n
help
Support filesystems using DAX to access RAM block devices. This
avoids double-buffering data in the page cache before copying it
to the block device. Answering Y will slightly enlarge the kernel,
and will prevent RAM block device backing store memory from being
allocated from highmem (only a problem for highmem systems).
config CDROM_PKTCDVD
tristate "Packet writing on CD/DVD media (DEPRECATED)"
depends on !UML
......
......@@ -21,11 +21,6 @@
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#ifdef CONFIG_BLK_DEV_RAM_DAX
#include <linux/pfn_t.h>
#include <linux/dax.h>
#include <linux/uio.h>
#endif
#include <linux/uaccess.h>
......@@ -45,9 +40,6 @@ struct brd_device {
struct request_queue *brd_queue;
struct gendisk *brd_disk;
#ifdef CONFIG_BLK_DEV_RAM_DAX
struct dax_device *dax_dev;
#endif
struct list_head brd_list;
/*
......@@ -112,9 +104,6 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector)
* restriction might be able to be lifted.
*/
gfp_flags = GFP_NOIO | __GFP_ZERO;
#ifndef CONFIG_BLK_DEV_RAM_DAX
gfp_flags |= __GFP_HIGHMEM;
#endif
page = alloc_page(gfp_flags);
if (!page)
return NULL;
......@@ -334,43 +323,6 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
return err;
}
#ifdef CONFIG_BLK_DEV_RAM_DAX
static long __brd_direct_access(struct brd_device *brd, pgoff_t pgoff,
long nr_pages, void **kaddr, pfn_t *pfn)
{
struct page *page;
if (!brd)
return -ENODEV;
page = brd_insert_page(brd, (sector_t)pgoff << PAGE_SECTORS_SHIFT);
if (!page)
return -ENOSPC;
*kaddr = page_address(page);
*pfn = page_to_pfn_t(page);
return 1;
}
static long brd_dax_direct_access(struct dax_device *dax_dev,
pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn)
{
struct brd_device *brd = dax_get_private(dax_dev);
return __brd_direct_access(brd, pgoff, nr_pages, kaddr, pfn);
}
static size_t brd_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
void *addr, size_t bytes, struct iov_iter *i)
{
return copy_from_iter(addr, bytes, i);
}
static const struct dax_operations brd_dax_ops = {
.direct_access = brd_dax_direct_access,
.copy_from_iter = brd_dax_copy_from_iter,
};
#endif
static const struct block_device_operations brd_fops = {
.owner = THIS_MODULE,
.rw_page = brd_rw_page,
......@@ -451,21 +403,8 @@ static struct brd_device *brd_alloc(int i)
set_capacity(disk, rd_size * 2);
disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
#ifdef CONFIG_BLK_DEV_RAM_DAX
queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue);
brd->dax_dev = alloc_dax(brd, disk->disk_name, &brd_dax_ops);
if (!brd->dax_dev)
goto out_free_inode;
#endif
return brd;
#ifdef CONFIG_BLK_DEV_RAM_DAX
out_free_inode:
kill_dax(brd->dax_dev);
put_dax(brd->dax_dev);
#endif
out_free_queue:
blk_cleanup_queue(brd->brd_queue);
out_free_dev:
......@@ -505,10 +444,6 @@ static struct brd_device *brd_init_one(int i, bool *new)
static void brd_del_one(struct brd_device *brd)
{
list_del(&brd->brd_list);
#ifdef CONFIG_BLK_DEV_RAM_DAX
kill_dax(brd->dax_dev);
put_dax(brd->dax_dev);
#endif
del_gendisk(brd->brd_disk);
brd_free(brd);
}
......
......@@ -222,7 +222,8 @@ __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
unsigned long size)
{
struct resource *res;
phys_addr_t phys;
/* gcc-4.6.3-nolibc for i386 complains that this is uninitialized */
phys_addr_t uninitialized_var(phys);
int i;
for (i = 0; i < dev_dax->num_resources; i++) {
......
......@@ -92,21 +92,21 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
long len;
if (blocksize != PAGE_SIZE) {
pr_err("VFS (%s): error: unsupported blocksize for dax\n",
pr_debug("VFS (%s): error: unsupported blocksize for dax\n",
sb->s_id);
return -EINVAL;
}
err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
if (err) {
pr_err("VFS (%s): error: unaligned partition for dax\n",
pr_debug("VFS (%s): error: unaligned partition for dax\n",
sb->s_id);
return err;
}
dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
if (!dax_dev) {
pr_err("VFS (%s): error: device does not support dax\n",
pr_debug("VFS (%s): error: device does not support dax\n",
sb->s_id);
return -EOPNOTSUPP;
}
......@@ -118,7 +118,7 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
put_dax(dax_dev);
if (len < 1) {
pr_err("VFS (%s): error: dax access failed (%ld)",
pr_debug("VFS (%s): error: dax access failed (%ld)\n",
sb->s_id, len);
return len < 0 ? len : -EIO;
}
......@@ -273,9 +273,6 @@ EXPORT_SYMBOL_GPL(dax_copy_from_iter);
void arch_wb_cache_pmem(void *addr, size_t size);
void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
{
if (unlikely(!dax_alive(dax_dev)))
return;
if (unlikely(!test_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags)))
return;
......@@ -344,6 +341,9 @@ static struct inode *dax_alloc_inode(struct super_block *sb)
struct inode *inode;
dax_dev = kmem_cache_alloc(dax_cache, GFP_KERNEL);
if (!dax_dev)
return NULL;
inode = &dax_dev->inode;
inode->i_rdev = 0;
return inode;
......
......@@ -21,6 +21,7 @@ libnvdimm-y += region_devs.o
libnvdimm-y += region.o
libnvdimm-y += namespace_devs.o
libnvdimm-y += label.o
libnvdimm-y += badrange.o
libnvdimm-$(CONFIG_ND_CLAIM) += claim.o
libnvdimm-$(CONFIG_BTT) += btt_devs.o
libnvdimm-$(CONFIG_NVDIMM_PFN) += pfn_devs.o
......
/*
* 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);
......@@ -11,6 +11,7 @@
* General Public License for more details.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/libnvdimm.h>
#include <linux/sched/mm.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
......@@ -221,7 +222,7 @@ static void nvdimm_account_cleared_poison(struct nvdimm_bus *nvdimm_bus,
phys_addr_t phys, u64 cleared)
{
if (cleared > 0)
nvdimm_forget_poison(nvdimm_bus, phys, cleared);
badrange_forget(&nvdimm_bus->badrange, phys, cleared);
if (cleared > 0 && cleared / 512)
nvdimm_clear_badblocks_regions(nvdimm_bus, phys, cleared);
......@@ -344,11 +345,10 @@ struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
return NULL;
INIT_LIST_HEAD(&nvdimm_bus->list);
INIT_LIST_HEAD(&nvdimm_bus->mapping_list);
INIT_LIST_HEAD(&nvdimm_bus->poison_list);
init_waitqueue_head(&nvdimm_bus->probe_wait);
nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL);
mutex_init(&nvdimm_bus->reconfig_mutex);
spin_lock_init(&nvdimm_bus->poison_lock);
badrange_init(&nvdimm_bus->badrange);
if (nvdimm_bus->id < 0) {
kfree(nvdimm_bus);
return NULL;
......@@ -395,15 +395,15 @@ static int child_unregister(struct device *dev, void *data)
return 0;
}
static void free_poison_list(struct list_head *poison_list)
static void free_badrange_list(struct list_head *badrange_list)
{
struct nd_poison *pl, *next;
struct badrange_entry *bre, *next;
list_for_each_entry_safe(pl, next, poison_list, list) {
list_del(&pl->list);
kfree(pl);
list_for_each_entry_safe(bre, next, badrange_list, list) {
list_del(&bre->list);
kfree(bre);
}
list_del_init(poison_list);
list_del_init(badrange_list);
}
static int nd_bus_remove(struct device *dev)
......@@ -417,9 +417,9 @@ static int nd_bus_remove(struct device *dev)
nd_synchronize();
device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister);
spin_lock(&nvdimm_bus->poison_lock);
free_poison_list(&nvdimm_bus->poison_list);
spin_unlock(&nvdimm_bus->poison_lock);
spin_lock(&nvdimm_bus->badrange.lock);
free_badrange_list(&nvdimm_bus->badrange.list);
spin_unlock(&nvdimm_bus->badrange.lock);
nvdimm_bus_destroy_ndctl(nvdimm_bus);
......
......@@ -398,265 +398,11 @@ struct attribute_group nvdimm_bus_attribute_group = {
};
EXPORT_SYMBOL_GPL(nvdimm_bus_attribute_group);
static void set_badblock(struct badblocks *bb, sector_t s, int num)
int nvdimm_bus_add_badrange(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
{
dev_dbg(bb->dev, "Found a poison 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);
return badrange_add(&nvdimm_bus->badrange, addr, length);
}
/**
* __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 poison 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