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

arch/x86/mm/pat.c

···
 }
 
 /*
- * 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)
···
 	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;
 	}
···
 	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 */
···
 		size = vma->vm_end - vma->vm_start;
 	}
 	free_pfn_range(paddr, size);
-	vma->vm_flags &= ~VM_PAT;
+	if (vma)
+		vma->vm_flags &= ~VM_PAT;
 }
 
 /*

drivers/acpi/nfit/mce.c

···
 		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)

drivers/dax/dax.c

···
 	}
 
 	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);

drivers/nvdimm/bus.c

···
 		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;

fs/proc/task_mmu.c

···
 		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));

kernel/memremap.c

···
 	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__);
···
 		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;
···
 	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;
···
 	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);

mm/huge_memory.c

···
 		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)) {
···
 	}
 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);