libnvdimm fixes v5.4-rc1

- Complete the reworks to interoperate with powerpc dynamic huge page sizes
 
 - Fix a crash due to missed accounting for the powerpc 'struct
   page'-memmap mapping granularity.
 
 - Fix badblock initialization for volatile (DRAM emulated) pmem ranges.
 
 - Stop triggering request_key() notifications to userspace when
   NVDIMM-security is disabled / not present.
 
 - Miscellaneous small fixups.
 -----BEGIN PGP SIGNATURE-----
 
 iQIcBAABAgAGBQJdkAprAAoJEB7SkWpmfYgCjXoQAIwJE1VzNP1V+ARxfs1rTGVz
 pbNJiBnj4gxDaCkcKoatiadRkytUxeUNEcPslEKsfoNinXYqkpjMQoWm2VpILOMU
 nY+SvIudGRnuesq2/Y+CP8zrX6rV4eBDfHK05RN/Zp1IlW7pTDItUx8mJ7glmDwG
 PW0vkvK7yZ+dRFnpQ7QFjhA0Q3oudO5YcTVBDK5YYtDGlv69xfXqc9LW8SszJ1kU
 rhCIT1kdoL5of0TIgG5pTfmggPSQ9y1xPsKjllOHNa3m50eGOkkQLELOVzQb1frW
 cjAsPLjRDSzvdHHSLyu0Is04Q5JU2CucxHl2SXGHiOt5tigH8dk5XFxWt0Pc8EXx
 acYYiBqUXC3MomSYWeLK4BdO2cRTqcPPXgJYAqXblqr+/0ys+rFepjw+j8JkiLZa
 5UCC30l1GXEpw9u6gdCMqvvHN2gHvDB0BV82Sx8wTewJpeL18wCUJoKVuFmpsHko
 p1cCe7St1TzcK3eO+xfeW1rxNrcXUpKVYXVa/WOJW0vwErqAZ6YCdNuyJHocZzXn
 vNyIQmVDOlubsgBAI2ExxeZO6xc8UIwLhLg7XEJ0mg3k6UXA8HZxH2B2THJk1BSF
 RppodkYiMknh11sqgpGp+Hz5XSEg/jvmCdL/qRDGAwhsFhFaxDH37Kg4Qncj2/dg
 uDvDHXNCjbGpzCo3tyNx
 =Z6Fa
 -----END PGP SIGNATURE-----

Merge tag 'libnvdimm-fixes-5.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

More libnvdimm updates from Dan Williams:

 - Complete the reworks to interoperate with powerpc dynamic huge page
   sizes

 - Fix a crash due to missed accounting for the powerpc 'struct
   page'-memmap mapping granularity

 - Fix badblock initialization for volatile (DRAM emulated) pmem ranges

 - Stop triggering request_key() notifications to userspace when
   NVDIMM-security is disabled / not present

 - Miscellaneous small fixups

* tag 'libnvdimm-fixes-5.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  libnvdimm/region: Enable MAP_SYNC for volatile regions
  libnvdimm: prevent nvdimm from requesting key when security is disabled
  libnvdimm/region: Initialize bad block for volatile namespaces
  libnvdimm/nfit_test: Fix acpi_handle redefinition
  libnvdimm/altmap: Track namespace boundaries in altmap
  libnvdimm: Fix endian conversion issues 
  libnvdimm/dax: Pick the right alignment default when creating dax devices
  powerpc/book3s64: Export has_transparent_hugepage() related functions.

arch/powerpc/include/asm/book3s/64/radix.h

@@ -254,7 +254,13 @@ extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 extern pgtable_t radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm,
 				      unsigned long addr, pmd_t *pmdp);
-extern int radix__has_transparent_hugepage(void);
+static inline int radix__has_transparent_hugepage(void)
+{
+	/* For radix 2M at PMD level means thp */
+	if (mmu_psize_defs[MMU_PAGE_2M].shift == PMD_SHIFT)
+		return 1;
+	return 0;
+}
 #endif
 
 extern int __meminit radix__vmemmap_create_mapping(unsigned long start,

arch/powerpc/mm/book3s64/hash_pgtable.c

@@ -406,6 +406,8 @@ int hash__has_transparent_hugepage(void)
 
 	return 1;
 }
+EXPORT_SYMBOL_GPL(hash__has_transparent_hugepage);
+
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #ifdef CONFIG_STRICT_KERNEL_RWX

arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -1027,13 +1027,6 @@ pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm,
 	return old_pmd;
 }
 
-int radix__has_transparent_hugepage(void)
-{
-	/* For radix 2M at PMD level means thp */
-	if (mmu_psize_defs[MMU_PAGE_2M].shift == PMD_SHIFT)
-		return 1;
-	return 0;
-}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,

arch/powerpc/mm/init_64.c

@@ -172,6 +172,21 @@ static __meminit void vmemmap_list_populate(unsigned long phys,
 	vmemmap_list = vmem_back;
 }
 
+static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start,
+				unsigned long page_size)
+{
+	unsigned long nr_pfn = page_size / sizeof(struct page);
+	unsigned long start_pfn = page_to_pfn((struct page *)start);
+
+	if ((start_pfn + nr_pfn) > altmap->end_pfn)
+		return true;
+
+	if (start_pfn < altmap->base_pfn)
+		return true;
+
+	return false;
+}
+
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
@@ -194,7 +209,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		 * fail due to alignment issues when using 16MB hugepages, so
 		 * fall back to system memory if the altmap allocation fail.
 		 */
-		if (altmap) {
+		if (altmap && !altmap_cross_boundary(altmap, start, page_size)) {
 			p = altmap_alloc_block_buf(page_size, altmap);
 			if (!p)
 				pr_debug("altmap block allocation failed, falling back to system memory");

drivers/nvdimm/btt.c

@@ -392,9 +392,9 @@ static int btt_flog_write(struct arena_info *arena, u32 lane, u32 sub,
 	arena->freelist[lane].sub = 1 - arena->freelist[lane].sub;
 	if (++(arena->freelist[lane].seq) == 4)
 		arena->freelist[lane].seq = 1;
-	if (ent_e_flag(ent->old_map))
+	if (ent_e_flag(le32_to_cpu(ent->old_map)))
 		arena->freelist[lane].has_err = 1;
-	arena->freelist[lane].block = le32_to_cpu(ent_lba(ent->old_map));
+	arena->freelist[lane].block = ent_lba(le32_to_cpu(ent->old_map));
 
 	return ret;
 }
@@ -560,8 +560,8 @@ static int btt_freelist_init(struct arena_info *arena)
 		 * FIXME: if error clearing fails during init, we want to make
 		 * the BTT read-only
 		 */
-		if (ent_e_flag(log_new.old_map) &&
-				!ent_normal(log_new.old_map)) {
+		if (ent_e_flag(le32_to_cpu(log_new.old_map)) &&
+		    !ent_normal(le32_to_cpu(log_new.old_map))) {
 			arena->freelist[i].has_err = 1;
 			ret = arena_clear_freelist_error(arena, i);
 			if (ret)

drivers/nvdimm/bus.c

@@ -180,7 +180,7 @@ static int nvdimm_clear_badblocks_region(struct device *dev, void *data)
 	sector_t sector;
 
 	/* make sure device is a region */
-	if (!is_nd_pmem(dev))
+	if (!is_memory(dev))
 		return 0;
 
 	nd_region = to_nd_region(dev);

drivers/nvdimm/namespace_devs.c

@@ -1987,7 +1987,7 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region,
 		nd_mapping = &nd_region->mapping[i];
 		label_ent = list_first_entry_or_null(&nd_mapping->labels,
 				typeof(*label_ent), list);
-		label0 = label_ent ? label_ent->label : 0;
+		label0 = label_ent ? label_ent->label : NULL;
 
 		if (!label0) {
 			WARN_ON(1);
@@ -2322,8 +2322,9 @@ static struct device **scan_labels(struct nd_region *nd_region)
 			continue;
 
 		/* skip labels that describe extents outside of the region */
-		if (nd_label->dpa < nd_mapping->start || nd_label->dpa > map_end)
-			continue;
+		if (__le64_to_cpu(nd_label->dpa) < nd_mapping->start ||
+		    __le64_to_cpu(nd_label->dpa) > map_end)
+				continue;
 
 		i = add_namespace_resource(nd_region, nd_label, devs, count);
 		if (i < 0)

drivers/nvdimm/nd.h

@@ -289,11 +289,7 @@ static inline struct device *nd_btt_create(struct nd_region *nd_region)
 struct nd_pfn *to_nd_pfn(struct device *dev);
 #if IS_ENABLED(CONFIG_NVDIMM_PFN)
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define PFN_DEFAULT_ALIGNMENT HPAGE_PMD_SIZE
-#else
-#define PFN_DEFAULT_ALIGNMENT PAGE_SIZE
-#endif
+#define MAX_NVDIMM_ALIGN	4
 
 int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns);
 bool is_nd_pfn(struct device *dev);

drivers/nvdimm/pfn_devs.c

@@ -103,39 +103,42 @@ static ssize_t align_show(struct device *dev,
 	return sprintf(buf, "%ld\n", nd_pfn->align);
 }
 
-static const unsigned long *nd_pfn_supported_alignments(void)
+static unsigned long *nd_pfn_supported_alignments(unsigned long *alignments)
 {
-	/*
-	 * This needs to be a non-static variable because the *_SIZE
-	 * macros aren't always constants.
-	 */
-	const unsigned long supported_alignments[] = {
-		PAGE_SIZE,
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		HPAGE_PMD_SIZE,
-#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-		HPAGE_PUD_SIZE,
-#endif
-#endif
-		0,
-	};
-	static unsigned long data[ARRAY_SIZE(supported_alignments)];
 
-	memcpy(data, supported_alignments, sizeof(data));
+	alignments[0] = PAGE_SIZE;
 
-	return data;
+	if (has_transparent_hugepage()) {
+		alignments[1] = HPAGE_PMD_SIZE;
+		if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
+			alignments[2] = HPAGE_PUD_SIZE;
+	}
+
+	return alignments;
+}
+
+/*
+ * Use pmd mapping if supported as default alignment
+ */
+static unsigned long nd_pfn_default_alignment(void)
+{
+
+	if (has_transparent_hugepage())
+		return HPAGE_PMD_SIZE;
+	return PAGE_SIZE;
 }
 
 static ssize_t align_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
 	struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
+	unsigned long aligns[MAX_NVDIMM_ALIGN] = { [0] = 0, };
 	ssize_t rc;
 
 	nd_device_lock(dev);
 	nvdimm_bus_lock(dev);
 	rc = nd_size_select_store(dev, buf, &nd_pfn->align,
-			nd_pfn_supported_alignments());
+			nd_pfn_supported_alignments(aligns));
 	dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
 			buf[len - 1] == '\n' ? "" : "\n");
 	nvdimm_bus_unlock(dev);
@@ -259,7 +262,10 @@ static DEVICE_ATTR_RO(size);
 static ssize_t supported_alignments_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	return nd_size_select_show(0, nd_pfn_supported_alignments(), buf);
+	unsigned long aligns[MAX_NVDIMM_ALIGN] = { [0] = 0, };
+
+	return nd_size_select_show(0,
+			nd_pfn_supported_alignments(aligns), buf);
 }
 static DEVICE_ATTR_RO(supported_alignments);
 
@@ -302,7 +308,7 @@ struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn,
 		return NULL;
 
 	nd_pfn->mode = PFN_MODE_NONE;
-	nd_pfn->align = PFN_DEFAULT_ALIGNMENT;
+	nd_pfn->align = nd_pfn_default_alignment();
 	dev = &nd_pfn->dev;
 	device_initialize(&nd_pfn->dev);
 	if (ndns && !__nd_attach_ndns(&nd_pfn->dev, ndns, &nd_pfn->ndns)) {
@@ -412,6 +418,21 @@ static int nd_pfn_clear_memmap_errors(struct nd_pfn *nd_pfn)
 	return 0;
 }
 
+static bool nd_supported_alignment(unsigned long align)
+{
+	int i;
+	unsigned long supported[MAX_NVDIMM_ALIGN] = { [0] = 0, };
+
+	if (align == 0)
+		return false;
+
+	nd_pfn_supported_alignments(supported);
+	for (i = 0; supported[i]; i++)
+		if (align == supported[i])
+			return true;
+	return false;
+}
+
 /**
  * nd_pfn_validate - read and validate info-block
  * @nd_pfn: fsdax namespace runtime state / properties
@@ -496,6 +517,18 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 		return -EOPNOTSUPP;
 	}
 
+	/*
+	 * Check whether the we support the alignment. For Dax if the
+	 * superblock alignment is not matching, we won't initialize
+	 * the device.
+	 */
+	if (!nd_supported_alignment(align) &&
+			!memcmp(pfn_sb->signature, DAX_SIG, PFN_SIG_LEN)) {
+		dev_err(&nd_pfn->dev, "init failed, alignment mismatch: "
+				"%ld:%ld\n", nd_pfn->align, align);
+		return -EOPNOTSUPP;
+	}
+
 	if (!nd_pfn->uuid) {
 		/*
 		 * When probing a namepace via nd_pfn_probe() the uuid
@@ -639,9 +672,11 @@ static int __nvdimm_setup_pfn(struct nd_pfn *nd_pfn, struct dev_pagemap *pgmap)
 	struct nd_namespace_common *ndns = nd_pfn->ndns;
 	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
 	resource_size_t base = nsio->res.start + start_pad;
+	resource_size_t end = nsio->res.end - end_trunc;
 	struct vmem_altmap __altmap = {
 		.base_pfn = init_altmap_base(base),
 		.reserve = init_altmap_reserve(base),
+		.end_pfn = PHYS_PFN(end),
 	};
 
 	memcpy(res, &nsio->res, sizeof(*res));

drivers/nvdimm/region.c

@@ -34,7 +34,7 @@ static int nd_region_probe(struct device *dev)
 	if (rc)
 		return rc;
 
-	if (is_nd_pmem(&nd_region->dev)) {
+	if (is_memory(&nd_region->dev)) {
 		struct resource ndr_res;
 
 		if (devm_init_badblocks(dev, &nd_region->bb))
@@ -123,7 +123,7 @@ static void nd_region_notify(struct device *dev, enum nvdimm_event event)
 		struct nd_region *nd_region = to_nd_region(dev);
 		struct resource res;
 
-		if (is_nd_pmem(&nd_region->dev)) {
+		if (is_memory(&nd_region->dev)) {
 			res.start = nd_region->ndr_start;
 			res.end = nd_region->ndr_start +
 				nd_region->ndr_size - 1;

drivers/nvdimm/region_devs.c

@@ -632,11 +632,11 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n)
 	if (!is_memory(dev) && a == &dev_attr_dax_seed.attr)
 		return 0;
 
-	if (!is_nd_pmem(dev) && a == &dev_attr_badblocks.attr)
+	if (!is_memory(dev) && a == &dev_attr_badblocks.attr)
 		return 0;
 
 	if (a == &dev_attr_resource.attr) {
-		if (is_nd_pmem(dev))
+		if (is_memory(dev))
 			return 0400;
 		else
 			return 0;
@@ -1168,6 +1168,9 @@ EXPORT_SYMBOL_GPL(nvdimm_has_cache);
 
 bool is_nvdimm_sync(struct nd_region *nd_region)
 {
+	if (is_nd_volatile(&nd_region->dev))
+		return true;
+
 	return is_nd_pmem(&nd_region->dev) &&
 		!test_bit(ND_REGION_ASYNC, &nd_region->flags);
 }

drivers/nvdimm/security.c

@@ -177,6 +177,10 @@ static int __nvdimm_security_unlock(struct nvdimm *nvdimm)
 			|| !nvdimm->sec.flags)
 		return -EIO;
 
+	/* No need to go further if security is disabled */
+	if (test_bit(NVDIMM_SECURITY_DISABLED, &nvdimm->sec.flags))
+		return 0;
+
 	if (test_bit(NDD_SECURITY_OVERWRITE, &nvdimm->flags)) {
 		dev_dbg(dev, "Security operation in progress.\n");
 		return -EBUSY;

include/linux/huge_mm.h

@@ -108,7 +108,12 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma)
 
 	if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG))
 		return true;
-
+	/*
+	 * For dax vmas, try to always use hugepage mappings. If the kernel does
+	 * not support hugepages, fsdax mappings will fallback to PAGE_SIZE
+	 * mappings, and device-dax namespaces, that try to guarantee a given
+	 * mapping size, will fail to enable
+	 */
 	if (vma_is_dax(vma))
 		return true;
 

include/linux/memremap.h

@@ -17,6 +17,7 @@ struct device;
  */
 struct vmem_altmap {
 	const unsigned long base_pfn;
+	const unsigned long end_pfn;
 	const unsigned long reserve;
 	unsigned long free;
 	unsigned long align;

tools/testing/nvdimm/test/nfit_test.h

@@ -4,6 +4,7 @@
  */
 #ifndef __NFIT_TEST_H__
 #define __NFIT_TEST_H__
+#include <linux/acpi.h>
 #include <linux/list.h>
 #include <linux/uuid.h>
 #include <linux/ioport.h>
@@ -202,9 +203,6 @@ struct nd_intel_lss {
 	__u32 status;
 } __packed;
 
-union acpi_object;
-typedef void *acpi_handle;
-
 typedef struct nfit_test_resource *(*nfit_test_lookup_fn)(resource_size_t);
 typedef union acpi_object *(*nfit_test_evaluate_dsm_fn)(acpi_handle handle,
 		 const guid_t *guid, u64 rev, u64 func,