Commit 98ac9a60 authored by Linus Torvalds's avatar Linus Torvalds

Merge branch 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm fixes from Dan Williams:
 "nvdimm fixes for v4.8, two of them are tagged for -stable:

   - Fix devm_memremap_pages() to use track_pfn_insert().  Otherwise,
     DAX pmd mappings end up with an uncached pgprot, and unusable
     performance for the device-dax interface.  The device-dax interface
     appeared in 4.7 so this is tagged for -stable.

   - Fix a couple VM_BUG_ON() checks in the show_smaps() path to
     understand DAX pmd entries.  This fix is tagged for -stable.

   - Fix a mis-merge of the nfit machine-check handler to flip the
     polarity of an if() to match the final version of the patch that
     Vishal sent for 4.8-rc1.  Without this the nfit machine check
     handler never detects / inserts new 'badblocks' entries which
     applications use to identify lost portions of files.

   - For test purposes, fix the nvdimm_clear_poison() path to operate on
     legacy / simulated nvdimm memory ranges.  Without this fix a test
     can set badblocks, but never clear them on these ranges.

   - Fix the range checking done by dax_dev_pmd_fault().  This is not
     tagged for -stable since this problem is mitigated by specifying
     aligned resources at device-dax setup time.

  These patches have appeared in a next release over the past week.  The
  recent rebase you can see in the timestamps was to drop an invalid fix
  as identified by the updated device-dax unit tests [1].  The -mm
  touches have an ack from Andrew"

[1]: "[ndctl PATCH 0/3] device-dax test for recent kernel bugs"
   https://lists.01.org/pipermail/linux-nvdimm/2016-September/006855.html

* 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  libnvdimm: allow legacy (e820) pmem region to clear bad blocks
  nfit, mce: Fix SPA matching logic in MCE handler
  mm: fix cache mode of dax pmd mappings
  mm: fix show_smap() for zone_device-pmd ranges
  dax: fix mapping size check
parents b8db3714 1e8b8d96
......@@ -927,9 +927,10 @@ int track_pfn_copy(struct vm_area_struct *vma)
}
/*
* prot is passed in as a parameter for the new mapping. If the vma has a
* linear pfn mapping for the entire range reserve the entire vma range with
* single reserve_pfn_range call.
* prot is passed in as a parameter for the new mapping. If the vma has
* a linear pfn mapping for the entire range, or no vma is provided,
* reserve the entire pfn + size range with single reserve_pfn_range
* call.
*/
int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long addr, unsigned long size)
......@@ -938,11 +939,12 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
enum page_cache_mode pcm;
/* reserve the whole chunk starting from paddr */
if (addr == vma->vm_start && size == (vma->vm_end - vma->vm_start)) {
if (!vma || (addr == vma->vm_start
&& size == (vma->vm_end - vma->vm_start))) {
int ret;
ret = reserve_pfn_range(paddr, size, prot, 0);
if (!ret)
if (ret == 0 && vma)
vma->vm_flags |= VM_PAT;
return ret;
}
......@@ -997,7 +999,7 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
resource_size_t paddr;
unsigned long prot;
if (!(vma->vm_flags & VM_PAT))
if (vma && !(vma->vm_flags & VM_PAT))
return;
/* free the chunk starting from pfn or the whole chunk */
......@@ -1011,6 +1013,7 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
size = vma->vm_end - vma->vm_start;
}
free_pfn_range(paddr, size);
if (vma)
vma->vm_flags &= ~VM_PAT;
}
......
......@@ -42,7 +42,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
struct acpi_nfit_system_address *spa = nfit_spa->spa;
if (nfit_spa_type(spa) == NFIT_SPA_PM)
if (nfit_spa_type(spa) != NFIT_SPA_PM)
continue;
/* find the spa that covers the mce addr */
if (spa->address > mce->addr)
......
......@@ -459,7 +459,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
}
pgoff = linear_page_index(vma, pmd_addr);
phys = pgoff_to_phys(dax_dev, pgoff, PAGE_SIZE);
phys = pgoff_to_phys(dax_dev, pgoff, PMD_SIZE);
if (phys == -1) {
dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
pgoff);
......
......@@ -185,8 +185,12 @@ long nvdimm_clear_poison(struct device *dev, phys_addr_t phys,
return -ENXIO;
nd_desc = nvdimm_bus->nd_desc;
/*
* if ndctl does not exist, it's PMEM_LEGACY and
* we want to just pretend everything is handled.
*/
if (!nd_desc->ndctl)
return -ENXIO;
return len;
memset(&ars_cap, 0, sizeof(ars_cap));
ars_cap.address = phys;
......
......@@ -581,6 +581,8 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
mss->anonymous_thp += HPAGE_PMD_SIZE;
else if (PageSwapBacked(page))
mss->shmem_thp += HPAGE_PMD_SIZE;
else if (is_zone_device_page(page))
/* pass */;
else
VM_BUG_ON_PAGE(1, page);
smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
......
......@@ -247,6 +247,7 @@ static void devm_memremap_pages_release(struct device *dev, void *data)
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(resource_size(res), SECTION_SIZE);
arch_remove_memory(align_start, align_size);
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
pgmap_radix_release(res);
dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
"%s: failed to free all reserved pages\n", __func__);
......@@ -282,6 +283,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
struct percpu_ref *ref, struct vmem_altmap *altmap)
{
resource_size_t key, align_start, align_size, align_end;
pgprot_t pgprot = PAGE_KERNEL;
struct dev_pagemap *pgmap;
struct page_map *page_map;
int error, nid, is_ram;
......@@ -351,6 +353,11 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
if (nid < 0)
nid = numa_mem_id();
error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0,
align_size);
if (error)
goto err_pfn_remap;
error = arch_add_memory(nid, align_start, align_size, true);
if (error)
goto err_add_memory;
......@@ -371,6 +378,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res,
return __va(res->start);
err_add_memory:
untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
err_pfn_remap:
err_radix:
pgmap_radix_release(res);
devres_free(page_map);
......
......@@ -1078,7 +1078,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
goto out;
page = pmd_page(*pmd);
VM_BUG_ON_PAGE(!PageHead(page), page);
VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
if (flags & FOLL_TOUCH)
touch_pmd(vma, addr, pmd);
if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
......@@ -1116,7 +1116,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
}
skip_mlock:
page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
VM_BUG_ON_PAGE(!PageCompound(page), page);
VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);
if (flags & FOLL_GET)
get_page(page);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment