OpenCloudOS-Kernel/drivers/nvdimm/pmem.c

686 lines
17 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* 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>.
*/
#include <linux/blkdev.h>
#include <linux/pagemap.h>
#include <linux/hdreg.h>
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/set_memory.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/badblocks.h>
#include <linux/memremap.h>
#include <linux/vmalloc.h>
mm, zone_device: Replace {get, put}_zone_device_page() with a single reference to fix pmem crash The x86 conversion to the generic GUP code included a small change which causes crashes and data corruption in the pmem code - not good. The root cause is that the /dev/pmem driver code implicitly relies on the x86 get_user_pages() implementation doing a get_page() on the page refcount, because get_page() does a get_zone_device_page() which properly refcounts pmem's separate page struct arrays that are not present in the regular page struct structures. (The pmem driver does this because it can cover huge memory areas.) But the x86 conversion to the generic GUP code changed the get_page() to page_cache_get_speculative() which is faster but doesn't do the get_zone_device_page() call the pmem code relies on. One way to solve the regression would be to change the generic GUP code to use get_page(), but that would slow things down a bit and punish other generic-GUP using architectures for an x86-ism they did not care about. (Arguably the pmem driver was probably not working reliably for them: but nvdimm is an Intel feature, so non-x86 exposure is probably still limited.) So restructure the pmem code's interface with the MM instead: get rid of the get/put_zone_device_page() distinction, integrate put_zone_device_page() into __put_page() and and restructure the pmem completion-wait and teardown machinery: Kirill points out that the calls to {get,put}_dev_pagemap() can be removed from the mm fast path if we take a single get_dev_pagemap() reference to signify that the page is alive and use the final put of the page to drop that reference. This does require some care to make sure that any waits for the percpu_ref to drop to zero occur *after* devm_memremap_page_release(), since it now maintains its own elevated reference. This speeds up things while also making the pmem refcounting more robust going forward. Suggested-by: Kirill Shutemov <kirill.shutemov@linux.intel.com> Tested-by: Kirill Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Logan Gunthorpe <logang@deltatee.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/149339998297.24933.1129582806028305912.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-04-29 01:23:37 +08:00
#include <linux/blk-mq.h>
#include <linux/pfn_t.h>
#include <linux/slab.h>
x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations The pmem driver has a need to transfer data with a persistent memory destination and be able to rely on the fact that the destination writes are not cached. It is sufficient for the writes to be flushed to a cpu-store-buffer (non-temporal / "movnt" in x86 terms), as we expect userspace to call fsync() to ensure data-writes have reached a power-fail-safe zone in the platform. The fsync() triggers a REQ_FUA or REQ_FLUSH to the pmem driver which will turn around and fence previous writes with an "sfence". Implement a __copy_from_user_inatomic_flushcache, memcpy_page_flushcache, and memcpy_flushcache, that guarantee that the destination buffer is not dirty in the cpu cache on completion. The new copy_from_iter_flushcache and sub-routines will be used to replace the "pmem api" (include/linux/pmem.h + arch/x86/include/asm/pmem.h). The availability of copy_from_iter_flushcache() and memcpy_flushcache() are gated by the CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE config symbol, and fallback to copy_from_iter_nocache() and plain memcpy() otherwise. This is meant to satisfy the concern from Linus that if a driver wants to do something beyond the normal nocache semantics it should be something private to that driver [1], and Al's concern that anything uaccess related belongs with the rest of the uaccess code [2]. The first consumer of this interface is a new 'copy_from_iter' dax operation so that pmem can inject cache maintenance operations without imposing this overhead on other dax-capable drivers. [1]: https://lists.01.org/pipermail/linux-nvdimm/2017-January/008364.html [2]: https://lists.01.org/pipermail/linux-nvdimm/2017-April/009942.html Cc: <x86@kernel.org> Cc: Jan Kara <jack@suse.cz> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Matthew Wilcox <mawilcox@microsoft.com> Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2017-05-30 03:22:50 +08:00
#include <linux/uio.h>
#include <linux/dax.h>
#include <linux/nd.h>
#include <linux/mm.h>
#include <asm/cacheflush.h>
#include "pmem.h"
#include "btt.h"
#include "pfn.h"
#include "nd.h"
libnvdimm: introduce nvdimm_flush() and nvdimm_has_flush() nvdimm_flush() is a replacement for the x86 'pcommit' instruction. It is an optional write flushing mechanism that an nvdimm bus can provide for the pmem driver to consume. In the case of the NFIT nvdimm-bus-provider nvdimm_flush() is implemented as a series of flush-hint-address [1] writes to each dimm in the interleave set (region) that backs the namespace. The nvdimm_has_flush() routine relies on platform firmware to describe the flushing capabilities of a platform. It uses the heuristic of whether an nvdimm bus provider provides flush address data to return a ternary result: 1: flush addresses defined 0: dimm topology described without flush addresses (assume ADR) -errno: no topology information, unable to determine flush mechanism The pmem driver is expected to take the following actions on this ternary result: 1: nvdimm_flush() in response to REQ_FUA / REQ_FLUSH and shutdown 0: do not set, WC or FUA on the queue, take no further action -errno: warn and then operate as if nvdimm_has_flush() returned '0' The caveat of this heuristic is that it can not distinguish the "dimm does not have flush address" case from the "platform firmware is broken and failed to describe a flush address". Given we are already explicitly trusting the NFIT there's not much more we can do beyond blacklisting broken firmwares if they are ever encountered. Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2016-07-08 10:44:50 +08:00
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 void hwpoison_clear(struct pmem_device *pmem,
phys_addr_t phys, unsigned int len)
{
unsigned long pfn_start, pfn_end, pfn;
/* only pmem in the linear map supports HWPoison */
if (is_vmalloc_addr(pmem->virt_addr))
return;
pfn_start = PHYS_PFN(phys);
pfn_end = pfn_start + PHYS_PFN(len);
for (pfn = pfn_start; pfn < pfn_end; pfn++) {
struct page *page = pfn_to_page(pfn);
/*
* Note, no need to hold a get_dev_pagemap() reference
* here since we're in the driver I/O path and
* outstanding I/O requests pin the dev_pagemap.
*/
if (test_and_clear_pmem_poison(page))
clear_mce_nospec(pfn);
}
}
static blk_status_t pmem_clear_poison(struct pmem_device *pmem,
phys_addr_t offset, unsigned int len)
{
libnvdimm: introduce nvdimm_flush() and nvdimm_has_flush() nvdimm_flush() is a replacement for the x86 'pcommit' instruction. It is an optional write flushing mechanism that an nvdimm bus can provide for the pmem driver to consume. In the case of the NFIT nvdimm-bus-provider nvdimm_flush() is implemented as a series of flush-hint-address [1] writes to each dimm in the interleave set (region) that backs the namespace. The nvdimm_has_flush() routine relies on platform firmware to describe the flushing capabilities of a platform. It uses the heuristic of whether an nvdimm bus provider provides flush address data to return a ternary result: 1: flush addresses defined 0: dimm topology described without flush addresses (assume ADR) -errno: no topology information, unable to determine flush mechanism The pmem driver is expected to take the following actions on this ternary result: 1: nvdimm_flush() in response to REQ_FUA / REQ_FLUSH and shutdown 0: do not set, WC or FUA on the queue, take no further action -errno: warn and then operate as if nvdimm_has_flush() returned '0' The caveat of this heuristic is that it can not distinguish the "dimm does not have flush address" case from the "platform firmware is broken and failed to describe a flush address". Given we are already explicitly trusting the NFIT there's not much more we can do beyond blacklisting broken firmwares if they are ever encountered. Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2016-07-08 10:44:50 +08:00
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) {
hwpoison_clear(pmem, pmem->phys_addr + offset, cleared);
cleared /= 512;
dev_dbg(dev, "%#llx clear %ld sector%s\n",
(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 - off);
memcpy_flushcache(pmem_addr, mem + off, chunk);
kunmap_atomic(mem);
len -= chunk;
off = 0;
page++;
pmem_addr += chunk;
}
}
static blk_status_t read_pmem(struct page *page, unsigned int off,
void *pmem_addr, unsigned int len)
{
unsigned int chunk;
unsigned long rem;
void *mem;
while (len) {
mem = kmap_atomic(page);
chunk = min_t(unsigned int, len, PAGE_SIZE - off);
x86, powerpc: Rename memcpy_mcsafe() to copy_mc_to_{user, kernel}() In reaction to a proposal to introduce a memcpy_mcsafe_fast() implementation Linus points out that memcpy_mcsafe() is poorly named relative to communicating the scope of the interface. Specifically what addresses are valid to pass as source, destination, and what faults / exceptions are handled. Of particular concern is that even though x86 might be able to handle the semantics of copy_mc_to_user() with its common copy_user_generic() implementation other archs likely need / want an explicit path for this case: On Fri, May 1, 2020 at 11:28 AM Linus Torvalds <torvalds@linux-foundation.org> wrote: > > On Thu, Apr 30, 2020 at 6:21 PM Dan Williams <dan.j.williams@intel.com> wrote: > > > > However now I see that copy_user_generic() works for the wrong reason. > > It works because the exception on the source address due to poison > > looks no different than a write fault on the user address to the > > caller, it's still just a short copy. So it makes copy_to_user() work > > for the wrong reason relative to the name. > > Right. > > And it won't work that way on other architectures. On x86, we have a > generic function that can take faults on either side, and we use it > for both cases (and for the "in_user" case too), but that's an > artifact of the architecture oddity. > > In fact, it's probably wrong even on x86 - because it can hide bugs - > but writing those things is painful enough that everybody prefers > having just one function. Replace a single top-level memcpy_mcsafe() with either copy_mc_to_user(), or copy_mc_to_kernel(). Introduce an x86 copy_mc_fragile() name as the rename for the low-level x86 implementation formerly named memcpy_mcsafe(). It is used as the slow / careful backend that is supplanted by a fast copy_mc_generic() in a follow-on patch. One side-effect of this reorganization is that separating copy_mc_64.S to its own file means that perf no longer needs to track dependencies for its memcpy_64.S benchmarks. [ bp: Massage a bit. ] Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Tony Luck <tony.luck@intel.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> Cc: <stable@vger.kernel.org> Link: http://lore.kernel.org/r/CAHk-=wjSqtXAqfUJxFtWNwmguFASTgB0dz1dT3V-78Quiezqbg@mail.gmail.com Link: https://lkml.kernel.org/r/160195561680.2163339.11574962055305783722.stgit@dwillia2-desk3.amr.corp.intel.com
2020-10-06 11:40:16 +08:00
rem = copy_mc_to_kernel(mem + off, pmem_addr, chunk);
kunmap_atomic(mem);
if (rem)
return BLK_STS_IOERR;
len -= chunk;
off = 0;
page++;
pmem_addr += chunk;
}
return BLK_STS_OK;
}
static blk_status_t pmem_do_read(struct pmem_device *pmem,
struct page *page, unsigned int page_off,
sector_t sector, unsigned int len)
{
blk_status_t rc;
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)))
return BLK_STS_IOERR;
rc = read_pmem(page, page_off, pmem_addr, len);
flush_dcache_page(page);
return rc;
}
static blk_status_t pmem_do_write(struct pmem_device *pmem,
struct page *page, unsigned int page_off,
sector_t sector, unsigned int len)
{
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;
/*
* 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, page_off, len);
if (unlikely(bad_pmem)) {
rc = pmem_clear_poison(pmem, pmem_off, len);
write_pmem(pmem_addr, page, page_off, len);
}
return rc;
}
static void pmem_submit_bio(struct bio *bio)
{
int ret = 0;
blk_status_t rc = 0;
bool do_acct;
unsigned long start;
struct bio_vec bvec;
struct bvec_iter iter;
struct pmem_device *pmem = bio->bi_bdev->bd_disk->private_data;
struct nd_region *nd_region = to_region(pmem);
if (bio->bi_opf & REQ_PREFLUSH)
ret = nvdimm_flush(nd_region, bio);
do_acct = blk_queue_io_stat(bio->bi_bdev->bd_disk->queue);
if (do_acct)
start = bio_start_io_acct(bio);
bio_for_each_segment(bvec, bio, iter) {
if (op_is_write(bio_op(bio)))
rc = pmem_do_write(pmem, bvec.bv_page, bvec.bv_offset,
iter.bi_sector, bvec.bv_len);
else
rc = pmem_do_read(pmem, bvec.bv_page, bvec.bv_offset,
iter.bi_sector, bvec.bv_len);
if (rc) {
bio->bi_status = rc;
break;
}
}
if (do_acct)
bio_end_io_acct(bio, start);
if (bio->bi_opf & REQ_FUA)
ret = nvdimm_flush(nd_region, bio);
if (ret)
bio->bi_status = errno_to_blk_status(ret);
bio_endio(bio);
}
static int pmem_rw_page(struct block_device *bdev, sector_t sector,
struct page *page, unsigned int op)
{
struct pmem_device *pmem = bdev->bd_disk->private_data;
blk_status_t rc;
if (op_is_write(op))
rc = pmem_do_write(pmem, page, 0, sector, thp_size(page));
else
rc = pmem_do_read(pmem, page, 0, sector, thp_size(page));
/*
* 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, op_is_write(op), 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;
if (kaddr)
*kaddr = pmem->virt_addr + offset;
if (pfn)
*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,
.submit_bio = pmem_submit_bio,
.rw_page = pmem_rw_page,
};
static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
size_t nr_pages)
{
struct pmem_device *pmem = dax_get_private(dax_dev);
return blk_status_to_errno(pmem_do_write(pmem, ZERO_PAGE(0), 0,
PFN_PHYS(pgoff) >> SECTOR_SHIFT,
PAGE_SIZE));
}
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 const struct dax_operations pmem_dax_ops = {
.direct_access = pmem_dax_direct_access,
.zero_page_range = pmem_dax_zero_page_range,
};
static ssize_t write_cache_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct pmem_device *pmem = dev_to_disk(dev)->private_data;
return sprintf(buf, "%d\n", !!dax_write_cache_enabled(pmem->dax_dev));
}
static ssize_t write_cache_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct pmem_device *pmem = dev_to_disk(dev)->private_data;
bool write_cache;
int rc;
rc = strtobool(buf, &write_cache);
if (rc)
return rc;
dax_write_cache(pmem->dax_dev, write_cache);
return len;
}
static DEVICE_ATTR_RW(write_cache);
static umode_t dax_visible(struct kobject *kobj, struct attribute *a, int n)
{
#ifndef CONFIG_ARCH_HAS_PMEM_API
if (a == &dev_attr_write_cache.attr)
return 0;
#endif
return a->mode;
}
static struct attribute *dax_attributes[] = {
&dev_attr_write_cache.attr,
NULL,
};
static const struct attribute_group dax_attribute_group = {
.name = "dax",
.attrs = dax_attributes,
.is_visible = dax_visible,
};
static const struct attribute_group *pmem_attribute_groups[] = {
&dax_attribute_group,
NULL,
};
static void pmem_release_disk(void *__pmem)
{
struct pmem_device *pmem = __pmem;
dax_remove_host(pmem->disk);
kill_dax(pmem->dax_dev);
put_dax(pmem->dax_dev);
del_gendisk(pmem->disk);
blk_cleanup_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);
libnvdimm: introduce nvdimm_flush() and nvdimm_has_flush() nvdimm_flush() is a replacement for the x86 'pcommit' instruction. It is an optional write flushing mechanism that an nvdimm bus can provide for the pmem driver to consume. In the case of the NFIT nvdimm-bus-provider nvdimm_flush() is implemented as a series of flush-hint-address [1] writes to each dimm in the interleave set (region) that backs the namespace. The nvdimm_has_flush() routine relies on platform firmware to describe the flushing capabilities of a platform. It uses the heuristic of whether an nvdimm bus provider provides flush address data to return a ternary result: 1: flush addresses defined 0: dimm topology described without flush addresses (assume ADR) -errno: no topology information, unable to determine flush mechanism The pmem driver is expected to take the following actions on this ternary result: 1: nvdimm_flush() in response to REQ_FUA / REQ_FLUSH and shutdown 0: do not set, WC or FUA on the queue, take no further action -errno: warn and then operate as if nvdimm_has_flush() returned '0' The caveat of this heuristic is that it can not distinguish the "dimm does not have flush address" case from the "platform firmware is broken and failed to describe a flush address". Given we are already explicitly trusting the NFIT there's not much more we can do beyond blacklisting broken firmwares if they are ever encountered. Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2016-07-08 10:44:50 +08:00
struct nd_region *nd_region = to_nd_region(dev->parent);
int nid = dev_to_node(dev), fua;
struct resource *res = &nsio->res;
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
struct range bb_range;
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 gendisk *disk;
void *addr;
int rc;
pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
if (!pmem)
return -ENOMEM;
rc = devm_namespace_enable(dev, ndns, nd_info_block_reserve());
if (rc)
return rc;
/* 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_namespace_disable(dev, ndns);
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;
}
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;
}
disk = blk_alloc_disk(nid);
if (!disk)
return -ENOMEM;
q = disk->queue;
pmem->disk = disk;
libnvdimm/pmem: Fix blk_cleanup_disk() usage The queue_to_disk() helper can not be used after del_gendisk() communicate @disk via the pgmap->owner. Otherwise, queue_to_disk() returns NULL resulting in the splat below. Kernel attempted to read user page (330) - exploit attempt? (uid: 0) BUG: Kernel NULL pointer dereference on read at 0x00000330 Faulting instruction address: 0xc000000000906344 Oops: Kernel access of bad area, sig: 11 [#1] [..] NIP [c000000000906344] pmem_pagemap_cleanup+0x24/0x40 LR [c0000000004701d4] memunmap_pages+0x1b4/0x4b0 Call Trace: [c000000022cbb9c0] [c0000000009063c8] pmem_pagemap_kill+0x28/0x40 (unreliable) [c000000022cbb9e0] [c0000000004701d4] memunmap_pages+0x1b4/0x4b0 [c000000022cbba90] [c0000000008b28a0] devm_action_release+0x30/0x50 [c000000022cbbab0] [c0000000008b39c8] release_nodes+0x2f8/0x3e0 [c000000022cbbb60] [c0000000008ac440] device_release_driver_internal+0x190/0x2b0 [c000000022cbbba0] [c0000000008a8450] unbind_store+0x130/0x170 Reported-by: Sachin Sant <sachinp@linux.vnet.ibm.com> Fixes: 87eb73b2ca7c ("nvdimm-pmem: convert to blk_alloc_disk/blk_cleanup_disk") Link: http://lore.kernel.org/r/DFB75BA8-603F-4A35-880B-C5B23EF8FA7D@linux.vnet.ibm.com Cc: Christoph Hellwig <hch@lst.de> Cc: Ulf Hansson <ulf.hansson@linaro.org> Cc: Jens Axboe <axboe@kernel.dk> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com> Link: https://lore.kernel.org/r/162310994435.1571616.334551212901820961.stgit@dwillia2-desk3.amr.corp.intel.com [axboe: fold in compile warning fix] Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-06-08 07:52:43 +08:00
pmem->pgmap.owner = pmem;
pmem->pfn_flags = PFN_DEV;
if (is_nd_pfn(dev)) {
pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
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) -
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
range_len(&pmem->pgmap.range);
pmem->pfn_flags |= PFN_MAP;
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
bb_range = pmem->pgmap.range;
bb_range.start += pmem->data_offset;
} else if (pmem_should_map_pages(dev)) {
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
pmem->pgmap.range.start = res->start;
pmem->pgmap.range.end = res->end;
mm/memremap_pages: support multiple ranges per invocation In support of device-dax growing the ability to front physically dis-contiguous ranges of memory, update devm_memremap_pages() to track multiple ranges with a single reference counter and devm instance. Convert all [devm_]memremap_pages() users to specify the number of ranges they are mapping in their 'struct dev_pagemap' instance. Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.co Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103789.4062302.18426128170217903785.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106116293.30709.13350662794915396198.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:34 +08:00
pmem->pgmap.nr_range = 1;
pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
addr = devm_memremap_pages(dev, &pmem->pgmap);
pmem->pfn_flags |= PFN_MAP;
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
bb_range = pmem->pgmap.range;
} else {
addr = devm_memremap(dev, pmem->phys_addr,
pmem->size, ARCH_MEMREMAP_PMEM);
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
bb_range.start = res->start;
bb_range.end = res->end;
}
if (IS_ERR(addr)) {
rc = PTR_ERR(addr);
goto out;
}
pmem->virt_addr = addr;
blk_queue_write_cache(q, true, fua);
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);
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
if (pmem->pfn_flags & PFN_MAP)
blk_queue_flag_set(QUEUE_FLAG_DAX, q);
disk->fops = &pmem_fops;
disk->private_data = pmem;
nd_btt: atomic sector updates BTT stands for Block Translation Table, and is a way to provide power fail sector atomicity semantics for block devices that have the ability to perform byte granularity IO. It relies on the capability of libnvdimm namespace devices to do byte aligned IO. The BTT works as a stacked blocked device, and reserves a chunk of space from the backing device for its accounting metadata. It is a bio-based driver because all IO is done synchronously, and there is no queuing or asynchronous completions at either the device or the driver level. The BTT uses 'lanes' to index into various 'on-disk' data structures, and lanes also act as a synchronization mechanism in case there are more CPUs than available lanes. We did a comparison between two lane lock strategies - first where we kept an atomic counter around that tracked which was the last lane that was used, and 'our' lane was determined by atomically incrementing that. That way, for the nr_cpus > nr_lanes case, theoretically, no CPU would be blocked waiting for a lane. The other strategy was to use the cpu number we're scheduled on to and hash it to a lane number. Theoretically, this could block an IO that could've otherwise run using a different, free lane. But some fio workloads showed that the direct cpu -> lane hash performed faster than tracking 'last lane' - my reasoning is the cache thrash caused by moving the atomic variable made that approach slower than simply waiting out the in-progress IO. This supports the conclusion that the driver can be a very simple bio-based one that does synchronous IOs instead of queuing. Cc: Andy Lutomirski <luto@amacapital.net> Cc: Boaz Harrosh <boaz@plexistor.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jens Axboe <axboe@fb.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Neil Brown <neilb@suse.de> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg KH <gregkh@linuxfoundation.org> [jmoyer: fix nmi watchdog timeout in btt_map_init] [jmoyer: move btt initialization to module load path] [jmoyer: fix memory leak in the btt initialization path] [jmoyer: Don't overwrite corrupted arenas] Signed-off-by: Vishal Verma <vishal.l.verma@linux.intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2015-06-25 16:20:32 +08:00
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;
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_range);
disk->bb = &pmem->bb;
dax_dev = alloc_dax(pmem, &pmem_dax_ops);
if (IS_ERR(dax_dev)) {
rc = PTR_ERR(dax_dev);
goto out;
}
set_dax_nocache(dax_dev);
set_dax_nomc(dax_dev);
if (is_nvdimm_sync(nd_region))
set_dax_synchronous(dax_dev);
rc = dax_add_host(dax_dev, disk);
if (rc)
goto out_cleanup_dax;
dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
pmem->dax_dev = dax_dev;
rc = device_add_disk(dev, disk, pmem_attribute_groups);
if (rc)
goto out_remove_host;
if (devm_add_action_or_reset(dev, pmem_release_disk, pmem))
return -ENOMEM;
nvdimm_check_and_set_ro(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;
out_remove_host:
dax_remove_host(pmem->disk);
out_cleanup_dax:
kill_dax(pmem->dax_dev);
put_dax(pmem->dax_dev);
out:
blk_cleanup_disk(pmem->disk);
return rc;
}
static int nd_pmem_probe(struct device *dev)
{
int ret;
struct nd_namespace_common *ndns;
ndns = nvdimm_namespace_common_probe(dev);
if (IS_ERR(ndns))
return PTR_ERR(ndns);
if (is_nd_btt(dev))
return nvdimm_namespace_attach_btt(ndns);
if (is_nd_pfn(dev))
return pmem_attach_disk(dev, ndns);
ret = devm_namespace_enable(dev, ndns, nd_info_block_reserve());
if (ret)
return ret;
ret = nd_btt_probe(dev, ndns);
if (ret == 0)
return -ENXIO;
/*
* We have two failure conditions here, there is no
* info reserver block or we found a valid info reserve block
* but failed to initialize the pfn superblock.
*
* For the first case consider namespace as a raw pmem namespace
* and attach a disk.
*
* For the latter, consider this a success and advance the namespace
* seed.
*/
ret = nd_pfn_probe(dev, ndns);
if (ret == 0)
return -ENXIO;
else if (ret == -EOPNOTSUPP)
return ret;
ret = nd_dax_probe(dev, ndns);
if (ret == 0)
return -ENXIO;
else if (ret == -EOPNOTSUPP)
return ret;
/* probe complete, attach handles namespace enabling */
devm_namespace_disable(dev, ndns);
return pmem_attach_disk(dev, ndns);
}
static void 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
driver-core, libnvdimm: Let device subsystems add local lockdep coverage For good reason, the standard device_lock() is marked lockdep_set_novalidate_class() because there is simply no sane way to describe the myriad ways the device_lock() ordered with other locks. However, that leaves subsystems that know their own local device_lock() ordering rules to find lock ordering mistakes manually. Instead, introduce an optional / additional lockdep-enabled lock that a subsystem can acquire in all the same paths that the device_lock() is acquired. A conversion of the NFIT driver and NVDIMM subsystem to a lockdep-validate device_lock() scheme is included. The debug_nvdimm_lock() implementation implements the correct lock-class and stacking order for the libnvdimm device topology hierarchy. Yes, this is a hack, but hopefully it is a useful hack for other subsystems device_lock() debug sessions. Quoting Greg: "Yeah, it feels a bit hacky but it's really up to a subsystem to mess up using it as much as anything else, so user beware :) I don't object to it if it makes things easier for you to debug." Cc: Ingo Molnar <mingo@redhat.com> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Keith Busch <keith.busch@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Link: https://lore.kernel.org/r/156341210661.292348.7014034644265455704.stgit@dwillia2-desk3.amr.corp.intel.com
2019-07-18 09:08:26 +08:00
* race nd_pmem_notify()
*/
sysfs_put(pmem->bb_state);
pmem->bb_state = NULL;
}
nvdimm_flush(to_nd_region(dev->parent), NULL);
}
static void nd_pmem_shutdown(struct device *dev)
{
nvdimm_flush(to_nd_region(dev->parent), NULL);
}
static void pmem_revalidate_poison(struct device *dev)
{
struct nd_region *nd_region;
resource_size_t offset = 0, end_trunc = 0;
struct nd_namespace_common *ndns;
struct nd_namespace_io *nsio;
struct badblocks *bb;
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
struct range range;
struct kernfs_node *bb_state;
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);
}
mm/memremap_pages: convert to 'struct range' The 'struct resource' in 'struct dev_pagemap' is only used for holding resource span information. The other fields, 'name', 'flags', 'desc', 'parent', 'sibling', and 'child' are all unused wasted space. This is in preparation for introducing a multi-range extension of devm_memremap_pages(). The bulk of this change is unwinding all the places internal to libnvdimm that used 'struct resource' unnecessarily, and replacing instances of 'struct dev_pagemap'.res with 'struct dev_pagemap'.range. P2PDMA had a minor usage of the resource flags field, but only to report failures with "%pR". That is replaced with an open coded print of the range. [dan.carpenter@oracle.com: mm/hmm/test: use after free in dmirror_allocate_chunk()] Link: https://lkml.kernel.org/r/20200926121402.GA7467@kadam Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> [xen] Cc: Paul Mackerras <paulus@ozlabs.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Ben Skeggs <bskeggs@redhat.com> Cc: David Airlie <airlied@linux.ie> Cc: Daniel Vetter <daniel@ffwll.ch> Cc: Ira Weiny <ira.weiny@intel.com> Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: Juergen Gross <jgross@suse.com> Cc: Stefano Stabellini <sstabellini@kernel.org> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hulk Robot <hulkci@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Jason Yan <yanaijie@huawei.com> Cc: Jeff Moyer <jmoyer@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joao Martins <joao.m.martins@oracle.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: kernel test robot <lkp@intel.com> Cc: Mike Rapoport <rppt@linux.ibm.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tom Lendacky <thomas.lendacky@amd.com> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Link: https://lkml.kernel.org/r/159643103173.4062302.768998885691711532.stgit@dwillia2-desk3.amr.corp.intel.com Link: https://lkml.kernel.org/r/160106115761.30709.13539840236873663620.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-14 07:50:29 +08:00
range.start = nsio->res.start + offset;
range.end = nsio->res.end - end_trunc;
nvdimm_badblocks_populate(nd_region, bb, &range);
if (bb_state)
sysfs_notify_dirent(bb_state);
}
static void pmem_revalidate_region(struct device *dev)
{
struct pmem_device *pmem;
if (is_nd_btt(dev)) {
struct nd_btt *nd_btt = to_nd_btt(dev);
struct btt *btt = nd_btt->btt;
nvdimm_check_and_set_ro(btt->btt_disk);
return;
}
pmem = dev_get_drvdata(dev);
nvdimm_check_and_set_ro(pmem->disk);
}
static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
{
switch (event) {
case NVDIMM_REVALIDATE_POISON:
pmem_revalidate_poison(dev);
break;
case NVDIMM_REVALIDATE_REGION:
pmem_revalidate_region(dev);
break;
default:
dev_WARN_ONCE(dev, 1, "notify: unknown event: %d\n", event);
break;
}
}
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,
};
module_nd_driver(nd_pmem_driver);
MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
MODULE_LICENSE("GPL v2");