[PATCH v4 0/6] Fixes related namespace alignment/page size/big endian

[PATCH v4 0/6] Fixes related namespace alignment/page size/big endian

[Aneesh Kumar K.V]

This series handle configs where hugepage support is not enabled by default.
Also, we update some of the information messages to make sure we use PAGE_SIZE instead
of SZ_4K. We now store page size and struct page size in pfn_sb and do extra check
before enabling namespace. There also an endianness fix.

The patch series is on top of subsection v10 patchset

http://lore.kernel.org/linux-mm/156092349300.979959.17603710711957735135.stgit@dwillia2-desk3.amr.corp.intel.com

Changes from V3:
* Dropped the change related PFN_MIN_VERSION
* for pfn_sb minor version < 4, we default page_size to PAGE_SIZE instead of SZ_4k.

Aneesh Kumar K.V (6):
  nvdimm: Consider probe return -EOPNOTSUPP as success
  mm/nvdimm: Add page size and struct page size to pfn superblock
  mm/nvdimm: Use correct #defines instead of open coding
  mm/nvdimm: Pick the right alignment default when creating dax devices
  mm/nvdimm: Use correct alignment when looking at first pfn from a
    region
  mm/nvdimm: Fix endian conversion issues 

 arch/powerpc/include/asm/libnvdimm.h |  9 ++++
 arch/powerpc/mm/Makefile             |  1 +
 arch/powerpc/mm/nvdimm.c             | 34 +++++++++++++++
 arch/x86/include/asm/libnvdimm.h     | 19 +++++++++
 drivers/nvdimm/btt.c                 |  8 ++--
 drivers/nvdimm/bus.c                 |  4 +-
 drivers/nvdimm/label.c               |  2 +-
 drivers/nvdimm/namespace_devs.c      | 13 +++---
 drivers/nvdimm/nd-core.h             |  3 +-
 drivers/nvdimm/nd.h                  |  6 ---
 drivers/nvdimm/pfn.h                 |  5 ++-
 drivers/nvdimm/pfn_devs.c            | 62 ++++++++++++++++++++++++++--
 drivers/nvdimm/pmem.c                | 26 ++++++++++--
 drivers/nvdimm/region_devs.c         | 27 ++++++++----
 include/linux/huge_mm.h              |  7 +++-
 kernel/memremap.c                    |  8 ++--
 16 files changed, 194 insertions(+), 40 deletions(-)
 create mode 100644 arch/powerpc/include/asm/libnvdimm.h
 create mode 100644 arch/powerpc/mm/nvdimm.c
 create mode 100644 arch/x86/include/asm/libnvdimm.h

-- 
2.21.0

[PATCH v4 1/6] nvdimm: Consider probe return -EOPNOTSUPP as success

[Aneesh Kumar K.V]

This patch add -EOPNOTSUPP as return from probe callback to
indicate we were not able to initialize a namespace due to pfn superblock
feature/version mismatch. We want to consider this a probe success so that
we can create new namesapce seed and there by avoid marking the failed
namespace as the seed namespace.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 drivers/nvdimm/bus.c         |  4 ++--
 drivers/nvdimm/nd-core.h     |  3 ++-
 drivers/nvdimm/pmem.c        | 26 ++++++++++++++++++++++----
 drivers/nvdimm/region_devs.c | 19 +++++++++++++++----
 4 files changed, 41 insertions(+), 11 deletions(-)

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 2dca3034fee0..3b8ffb3966ab 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -92,8 +92,8 @@ static int nvdimm_bus_probe(struct device *dev)
 
 	nvdimm_bus_probe_start(nvdimm_bus);
 	rc = nd_drv->probe(dev);
-	if (rc == 0)
-		nd_region_probe_success(nvdimm_bus, dev);
+	if (rc == 0 || rc == -EOPNOTSUPP)
+		nd_region_probe_success(nvdimm_bus, dev, rc);
 	else
 		nd_region_disable(nvdimm_bus, dev);
 	nvdimm_bus_probe_end(nvdimm_bus);
diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h
index 391e88de3a29..4e6ffa0d89bb 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -126,7 +126,8 @@ int __init nvdimm_bus_init(void);
 void nvdimm_bus_exit(void);
 void nvdimm_devs_exit(void);
 void nd_region_devs_exit(void);
-void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev);
+void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus,
+			     struct device *dev, int ret);
 struct nd_region;
 void nd_region_create_ns_seed(struct nd_region *nd_region);
 void nd_region_create_btt_seed(struct nd_region *nd_region);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 24d7fe7c74ed..422b11c01301 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -497,6 +497,7 @@ static int pmem_attach_disk(struct device *dev,
 
 static int nd_pmem_probe(struct device *dev)
 {
+	int ret;
 	struct nd_namespace_common *ndns;
 
 	ndns = nvdimm_namespace_common_probe(dev);
@@ -512,12 +513,29 @@ static int nd_pmem_probe(struct device *dev)
 	if (is_nd_pfn(dev))
 		return pmem_attach_disk(dev, ndns);
 
-	/* if we find a valid info-block we'll come back as that personality */
-	if (nd_btt_probe(dev, ndns) == 0 || nd_pfn_probe(dev, ndns) == 0
-			|| nd_dax_probe(dev, ndns) == 0)
+	ret = nd_btt_probe(dev, ndns);
+	if (ret == 0)
 		return -ENXIO;
+	else if (ret == -EOPNOTSUPP)
+		return ret;
 
-	/* ...otherwise we're just a raw pmem device */
+	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;
+	/*
+	 * 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.
+	 * Don't create a raw pmem disk for the second case.
+	 */
 	return pmem_attach_disk(dev, ndns);
 }
 
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index 4fed9ce9c2fe..1e74a1c9fdac 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -715,7 +715,7 @@ void nd_mapping_free_labels(struct nd_mapping *nd_mapping)
  * disable the region.
  */
 static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
-		struct device *dev, bool probe)
+					   struct device *dev, bool probe, int ret)
 {
 	struct nd_region *nd_region;
 
@@ -745,6 +745,16 @@ static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
 			nd_region_create_ns_seed(nd_region);
 		nvdimm_bus_unlock(dev);
 	}
+
+	if (dev->parent && is_nd_region(dev->parent) &&
+	    !probe && (ret == -EOPNOTSUPP)) {
+		nd_region = to_nd_region(dev->parent);
+		nvdimm_bus_lock(dev);
+		if (nd_region->ns_seed == dev)
+			nd_region_create_ns_seed(nd_region);
+		nvdimm_bus_unlock(dev);
+	}
+
 	if (is_nd_btt(dev) && probe) {
 		struct nd_btt *nd_btt = to_nd_btt(dev);
 
@@ -780,14 +790,15 @@ static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
 	}
 }
 
-void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev)
+void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus,
+			     struct device *dev, int ret)
 {
-	nd_region_notify_driver_action(nvdimm_bus, dev, true);
+	nd_region_notify_driver_action(nvdimm_bus, dev, true, ret);
 }
 
 void nd_region_disable(struct nvdimm_bus *nvdimm_bus, struct device *dev)
 {
-	nd_region_notify_driver_action(nvdimm_bus, dev, false);
+	nd_region_notify_driver_action(nvdimm_bus, dev, false, 0);
 }
 
 static ssize_t mappingN(struct device *dev, char *buf, int n)
-- 
2.21.0

[PATCH v4 2/6] mm/nvdimm: Add page size and struct page size to pfn superblock

[Aneesh Kumar K.V]

This is needed so that we don't wrongly initialize a namespace
which doesn't have enough space reserved for holding struct pages
with the current kernel.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 drivers/nvdimm/pfn.h      |  5 ++++-
 drivers/nvdimm/pfn_devs.c | 27 ++++++++++++++++++++++++++-
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/drivers/nvdimm/pfn.h b/drivers/nvdimm/pfn.h
index 7381673b7b70..acb19517f678 100644
--- a/drivers/nvdimm/pfn.h
+++ b/drivers/nvdimm/pfn.h
@@ -29,7 +29,10 @@ struct nd_pfn_sb {
 	/* minor-version-2 record the base alignment of the mapping */
 	__le32 align;
 	/* minor-version-3 guarantee the padding and flags are zero */
-	u8 padding[4000];
+	/* minor-version-4 record the page size and struct page size */
+	__le32 page_size;
+	__le16 page_struct_size;
+	u8 padding[3994];
 	__le64 checksum;
 };
 
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 2537aa338bd0..cd722de0ae03 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -460,6 +460,15 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 	if (__le16_to_cpu(pfn_sb->version_minor) < 2)
 		pfn_sb->align = 0;
 
+	if (__le16_to_cpu(pfn_sb->version_minor) < 4) {
+		/*
+		 * For a large part we use PAGE_SIZE. But we
+		 * do have some accounting code using SZ_4K.
+		 */
+		pfn_sb->page_struct_size = cpu_to_le16(64);
+		pfn_sb->page_size = cpu_to_le32(PAGE_SIZE);
+	}
+
 	switch (le32_to_cpu(pfn_sb->mode)) {
 	case PFN_MODE_RAM:
 	case PFN_MODE_PMEM:
@@ -475,6 +484,20 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 		align = 1UL << ilog2(offset);
 	mode = le32_to_cpu(pfn_sb->mode);
 
+	if (le32_to_cpu(pfn_sb->page_size) != PAGE_SIZE) {
+		dev_err(&nd_pfn->dev,
+			"init failed, page size mismatch %d\n",
+			le32_to_cpu(pfn_sb->page_size));
+		return -EOPNOTSUPP;
+	}
+
+	if (le16_to_cpu(pfn_sb->page_struct_size) != sizeof(struct page)) {
+		dev_err(&nd_pfn->dev,
+			"init failed, struct page size mismatch %d\n",
+			le16_to_cpu(pfn_sb->page_struct_size));
+		return -EOPNOTSUPP;
+	}
+
 	if (!nd_pfn->uuid) {
 		/*
 		 * When probing a namepace via nd_pfn_probe() the uuid
@@ -723,8 +746,10 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
 	memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
 	pfn_sb->version_major = cpu_to_le16(1);
-	pfn_sb->version_minor = cpu_to_le16(3);
+	pfn_sb->version_minor = cpu_to_le16(4);
 	pfn_sb->align = cpu_to_le32(nd_pfn->align);
+	pfn_sb->page_struct_size = cpu_to_le16(sizeof(struct page));
+	pfn_sb->page_size = cpu_to_le32(PAGE_SIZE);
 	checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
 	pfn_sb->checksum = cpu_to_le64(checksum);
 
-- 
2.21.0

[PATCH v4 3/6] mm/nvdimm: Use correct #defines instead of open coding

[Aneesh Kumar K.V]

Use PAGE_SIZE instead of SZ_4K and sizeof(struct page) instead of 64.
If we have a kernel built with different struct page size the previous
patch should handle marking the namespace disabled.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 drivers/nvdimm/label.c          | 2 +-
 drivers/nvdimm/namespace_devs.c | 6 +++---
 drivers/nvdimm/pfn_devs.c       | 3 ++-
 drivers/nvdimm/region_devs.c    | 8 ++++----
 4 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c
index 73e197babc2f..7ee037063be7 100644
--- a/drivers/nvdimm/label.c
+++ b/drivers/nvdimm/label.c
@@ -355,7 +355,7 @@ static bool slot_valid(struct nvdimm_drvdata *ndd,
 
 	/* check that DPA allocations are page aligned */
 	if ((__le64_to_cpu(nd_label->dpa)
-				| __le64_to_cpu(nd_label->rawsize)) % SZ_4K)
+				| __le64_to_cpu(nd_label->rawsize)) % PAGE_SIZE)
 		return false;
 
 	/* check checksum */
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index a434a5964cb9..007027202542 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -1006,10 +1006,10 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 		return -ENXIO;
 	}
 
-	div_u64_rem(val, SZ_4K * nd_region->ndr_mappings, &remainder);
+	div_u64_rem(val, PAGE_SIZE * nd_region->ndr_mappings, &remainder);
 	if (remainder) {
-		dev_dbg(dev, "%llu is not %dK aligned\n", val,
-				(SZ_4K * nd_region->ndr_mappings) / SZ_1K);
+		dev_dbg(dev, "%llu is not %ldK aligned\n", val,
+				(PAGE_SIZE * nd_region->ndr_mappings) / SZ_1K);
 		return -EINVAL;
 	}
 
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index cd722de0ae03..9410d2692913 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -726,7 +726,8 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 		 * when populating the vmemmap. This *should* be equal to
 		 * PMD_SIZE for most architectures.
 		 */
-		offset = ALIGN(start + SZ_8K + 64 * npfns, align) - start;
+		offset = ALIGN(start + SZ_8K + sizeof(struct page) * npfns,
+			       align) - start;
 	} else if (nd_pfn->mode == PFN_MODE_RAM)
 		offset = ALIGN(start + SZ_8K, align) - start;
 	else
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index 1e74a1c9fdac..b9992499a035 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -997,10 +997,10 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
 		struct nvdimm *nvdimm = mapping->nvdimm;
 
-		if ((mapping->start | mapping->size) % SZ_4K) {
-			dev_err(&nvdimm_bus->dev, "%s: %s mapping%d is not 4K aligned\n",
-					caller, dev_name(&nvdimm->dev), i);
-
+		if ((mapping->start | mapping->size) % PAGE_SIZE) {
+			dev_err(&nvdimm_bus->dev,
+				"%s: %s mapping%d is not %ld aligned\n",
+				caller, dev_name(&nvdimm->dev), i, PAGE_SIZE);
 			return NULL;
 		}
 
-- 
2.21.0

[PATCH v4 4/6] mm/nvdimm: Pick the right alignment default when creating dax devices

[Aneesh Kumar K.V]

Allow arch to provide the supported alignments and use hugepage alignment only
if we support hugepage. Right now we depend on compile time configs whereas this
patch switch this to runtime discovery.

Architectures like ppc64 can have THP enabled in code, but then can have
hugepage size disabled by the hypervisor. This allows us to create dax devices
with PAGE_SIZE alignment in this case.

Existing dax namespace with alignment larger than PAGE_SIZE will fail to
initialize in this specific case. We still allow fsdax namespace initialization.

With respect to identifying whether to enable hugepage fault for a dax device,
if THP is enabled during compile, we default to taking hugepage fault and in dax
fault handler if we find the fault size > alignment we retry with PAGE_SIZE
fault size.

This also addresses the below failure scenario on ppc64

ndctl create-namespace --mode=devdax  | grep align
 "align":16777216,
 "align":16777216

cat /sys/devices/ndbus0/region0/dax0.0/supported_alignments
 65536 16777216

daxio.static-debug  -z -o /dev/dax0.0
  Bus error (core dumped)

  $ dmesg | tail
   lpar: Failed hash pte insert with error -4
   hash-mmu: mm: Hashing failure ! EA=0x7fff17000000 access=0x8000000000000006 current=daxio
   hash-mmu:     trap=0x300 vsid=0x22cb7a3 ssize=1 base psize=2 psize 10 pte=0xc000000501002b86
   daxio[3860]: bus error (7) at 7fff17000000 nip 7fff973c007c lr 7fff973bff34 code 2 in libpmem.so.1.0.0[7fff973b0000+20000]
   daxio[3860]: code: 792945e4 7d494b78 e95f0098 7d494b78 f93f00a0 4800012c e93f0088 f93f0120
   daxio[3860]: code: e93f00a0 f93f0128 e93f0120 e95f0128 <f9490000> e93f0088 39290008 f93f0110

The failure was due to guest kernel using wrong page size.

The namespaces created with 16M alignment will appear as below on a config with
16M page size disabled.

$ ndctl list -Ni
[
  {
    "dev":"namespace0.1",
    "mode":"fsdax",
    "map":"dev",
    "size":5351931904,
    "uuid":"fc6e9667-461a-4718-82b4-69b24570bddb",
    "align":16777216,
    "blockdev":"pmem0.1",
    "supported_alignments":[
      65536
    ]
  },
  {
    "dev":"namespace0.0",
    "mode":"fsdax",    <==== devdax 16M alignment marked disabled.
    "map":"mem",
    "size":5368709120,
    "uuid":"a4bdf81a-f2ee-4bc6-91db-7b87eddd0484",
    "state":"disabled"
  }
]

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 arch/powerpc/include/asm/libnvdimm.h |  9 ++++++++
 arch/powerpc/mm/Makefile             |  1 +
 arch/powerpc/mm/nvdimm.c             | 34 ++++++++++++++++++++++++++++
 arch/x86/include/asm/libnvdimm.h     | 19 ++++++++++++++++
 drivers/nvdimm/nd.h                  |  6 -----
 drivers/nvdimm/pfn_devs.c            | 32 +++++++++++++++++++++++++-
 include/linux/huge_mm.h              |  7 +++++-
 7 files changed, 100 insertions(+), 8 deletions(-)
 create mode 100644 arch/powerpc/include/asm/libnvdimm.h
 create mode 100644 arch/powerpc/mm/nvdimm.c
 create mode 100644 arch/x86/include/asm/libnvdimm.h

diff --git a/arch/powerpc/include/asm/libnvdimm.h b/arch/powerpc/include/asm/libnvdimm.h
new file mode 100644
index 000000000000..d35fd7f48603
--- /dev/null
+++ b/arch/powerpc/include/asm/libnvdimm.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_LIBNVDIMM_H
+#define _ASM_POWERPC_LIBNVDIMM_H
+
+#define nd_pfn_supported_alignments nd_pfn_supported_alignments
+extern unsigned long *nd_pfn_supported_alignments(void);
+extern unsigned long nd_pfn_default_alignment(void);
+
+#endif
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 0f499db315d6..42e4a399ba5d 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -20,3 +20,4 @@ obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_PPC_COPRO_BASE)	+= copro_fault.o
 obj-$(CONFIG_PPC_PTDUMP)	+= ptdump/
 obj-$(CONFIG_KASAN)		+= kasan/
+obj-$(CONFIG_NVDIMM_PFN)		+= nvdimm.o
diff --git a/arch/powerpc/mm/nvdimm.c b/arch/powerpc/mm/nvdimm.c
new file mode 100644
index 000000000000..a29a4510715e
--- /dev/null
+++ b/arch/powerpc/mm/nvdimm.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <asm/pgtable.h>
+#include <asm/page.h>
+
+#include <linux/mm.h>
+/*
+ * We support only pte and pmd mappings for now.
+ */
+const unsigned long *nd_pfn_supported_alignments(void)
+{
+	static unsigned long supported_alignments[3];
+
+	supported_alignments[0] = PAGE_SIZE;
+
+	if (has_transparent_hugepage())
+		supported_alignments[1] = HPAGE_PMD_SIZE;
+	else
+		supported_alignments[1] = 0;
+
+	supported_alignments[2] = 0;
+	return supported_alignments;
+}
+
+/*
+ * Use pmd mapping if supported as default alignment
+ */
+unsigned long nd_pfn_default_alignment(void)
+{
+
+	if (has_transparent_hugepage())
+		return HPAGE_PMD_SIZE;
+	return PAGE_SIZE;
+}
diff --git a/arch/x86/include/asm/libnvdimm.h b/arch/x86/include/asm/libnvdimm.h
new file mode 100644
index 000000000000..3d5361db9164
--- /dev/null
+++ b/arch/x86/include/asm/libnvdimm.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_LIBNVDIMM_H
+#define _ASM_X86_LIBNVDIMM_H
+
+static inline unsigned long nd_pfn_default_alignment(void)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	return HPAGE_PMD_SIZE;
+#else
+	return PAGE_SIZE;
+#endif
+}
+
+static inline unsigned long nd_altmap_align_size(unsigned long nd_align)
+{
+	return PMD_SIZE;
+}
+
+#endif
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index d24304c0e6d7..e2fbb51fb361 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -288,12 +288,6 @@ 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
-
 int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns);
 bool is_nd_pfn(struct device *dev);
 struct device *nd_pfn_create(struct nd_region *nd_region);
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 9410d2692913..29bb46ca92f2 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <asm/libnvdimm.h>
 #include "nd-core.h"
 #include "pfn.h"
 #include "nd.h"
@@ -103,6 +104,8 @@ static ssize_t align_show(struct device *dev,
 	return sprintf(buf, "%ld\n", nd_pfn->align);
 }
 
+#ifndef nd_pfn_supported_alignments
+#define nd_pfn_supported_alignments nd_pfn_supported_alignments
 static const unsigned long *nd_pfn_supported_alignments(void)
 {
 	/*
@@ -125,6 +128,7 @@ static const unsigned long *nd_pfn_supported_alignments(void)
 
 	return data;
 }
+#endif
 
 static ssize_t align_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
@@ -302,7 +306,7 @@ 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 +416,20 @@ static int nd_pfn_clear_memmap_errors(struct nd_pfn *nd_pfn)
 	return 0;
 }
 
+static bool nd_supported_alignment(unsigned long align)
+{
+	int i;
+	const unsigned long *supported = nd_pfn_supported_alignments();
+
+	if (align == 0)
+		return false;
+
+	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
@@ -498,6 +516,18 @@ 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
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 7cd5c150c21d..64d16794bb27 100644
--- a/include/linux/huge_mm.h
+++ b/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 let's try to do hugepage fault always. If we don't support
+	 * hugepages we will not have enabled namespaces with hugepage alignment.
+	 * This also means we try to handle hugepage fault on device with
+	 * smaller alignment. But for then we will return with VM_FAULT_FALLBACK
+	 */
 	if (vma_is_dax(vma))
 		return true;
 
-- 
2.21.0

[PATCH v4 5/6] mm/nvdimm: Use correct alignment when looking at first pfn from a region

[Aneesh Kumar K.V]

vmem_altmap_offset() adjust the section aligned base_pfn offset.
So we need to make sure we account for the same when computing base_pfn.

ie, for altmap_valid case, our pfn_first should be:

pfn_first = altmap->base_pfn + vmem_altmap_offset(altmap);

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 kernel/memremap.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/kernel/memremap.c b/kernel/memremap.c
index a0e5f6b91b04..63800128844b 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -58,9 +58,11 @@ static unsigned long pfn_first(struct dev_pagemap *pgmap)
 	struct vmem_altmap *altmap = &pgmap->altmap;
 	unsigned long pfn;
 
-	pfn = PHYS_PFN(res->start);
-	if (pgmap->altmap_valid)
-		pfn += vmem_altmap_offset(altmap);
+	if (pgmap->altmap_valid) {
+		pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
+	} else
+		pfn = PHYS_PFN(res->start);
+
 	return pfn;
 }
 
-- 
2.21.0

[PATCH v4 6/6] mm/nvdimm: Fix endian conversion issues

[Aneesh Kumar K.V]

nd_label->dpa issue was observed when trying to enable the namespace created
with little-endian kernel on a big-endian kernel. That made me run
`sparse` on the rest of the code and other changes are the result of that.

Fixes: d9b83c756953 ("libnvdimm, btt: rework error clearing")
Fixes: 9dedc73a4658 ("libnvdimm/btt: Fix LBA masking during 'free list' population")

Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 drivers/nvdimm/btt.c            | 8 ++++----
 drivers/nvdimm/namespace_devs.c | 7 ++++---
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index a8d56887ec88..3e9f45aec8d1 100644
--- a/drivers/nvdimm/btt.c
+++ b/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)
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 007027202542..839da9e43572 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/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)
-- 
2.21.0

Re: [PATCH v4 0/6] Fixes related namespace alignment/page size/big endian

[Aneesh Kumar K.V]

Hi Dan,

Can you merge this to your tree?

-aneesh
"Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> writes:

> This series handle configs where hugepage support is not enabled by default.
> Also, we update some of the information messages to make sure we use PAGE_SIZE instead
> of SZ_4K. We now store page size and struct page size in pfn_sb and do extra check
> before enabling namespace. There also an endianness fix.
>
> The patch series is on top of subsection v10 patchset
>
> http://lore.kernel.org/linux-mm/156092349300.979959.17603710711957735135.stgit@dwillia2-desk3.amr.corp.intel.com
>
> Changes from V3:
> * Dropped the change related PFN_MIN_VERSION
> * for pfn_sb minor version < 4, we default page_size to PAGE_SIZE instead of SZ_4k.
>
> Aneesh Kumar K.V (6):
>   nvdimm: Consider probe return -EOPNOTSUPP as success
>   mm/nvdimm: Add page size and struct page size to pfn superblock
>   mm/nvdimm: Use correct #defines instead of open coding
>   mm/nvdimm: Pick the right alignment default when creating dax devices
>   mm/nvdimm: Use correct alignment when looking at first pfn from a
>     region
>   mm/nvdimm: Fix endian conversion issues 
>
>  arch/powerpc/include/asm/libnvdimm.h |  9 ++++
>  arch/powerpc/mm/Makefile             |  1 +
>  arch/powerpc/mm/nvdimm.c             | 34 +++++++++++++++
>  arch/x86/include/asm/libnvdimm.h     | 19 +++++++++
>  drivers/nvdimm/btt.c                 |  8 ++--
>  drivers/nvdimm/bus.c                 |  4 +-
>  drivers/nvdimm/label.c               |  2 +-
>  drivers/nvdimm/namespace_devs.c      | 13 +++---
>  drivers/nvdimm/nd-core.h             |  3 +-
>  drivers/nvdimm/nd.h                  |  6 ---
>  drivers/nvdimm/pfn.h                 |  5 ++-
>  drivers/nvdimm/pfn_devs.c            | 62 ++++++++++++++++++++++++++--
>  drivers/nvdimm/pmem.c                | 26 ++++++++++--
>  drivers/nvdimm/region_devs.c         | 27 ++++++++----
>  include/linux/huge_mm.h              |  7 +++-
>  kernel/memremap.c                    |  8 ++--
>  16 files changed, 194 insertions(+), 40 deletions(-)
>  create mode 100644 arch/powerpc/include/asm/libnvdimm.h
>  create mode 100644 arch/powerpc/mm/nvdimm.c
>  create mode 100644 arch/x86/include/asm/libnvdimm.h
>
> -- 
> 2.21.0