[PATCH v3 1/6] nvdimm: Consider probe return -EOPNOTSUPP as success

[PATCH v3 1/6] nvdimm: Consider probe return -EOPNOTSUPP as success

[Aneesh Kumar K.V]

With following patches we 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/region_devs.c | 19 +++++++++++++++----
 3 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 2eb6a6cfe9e4..792b3e90453b 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -100,8 +100,8 @@ 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 e5ffd5733540..9e67a79fb6d5 100644
--- a/drivers/nvdimm/nd-core.h
+++ b/drivers/nvdimm/nd-core.h
@@ -134,7 +134,8 @@ 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/region_devs.c b/drivers/nvdimm/region_devs.c
index b4ef7d9ff22e..fcf3d8828540 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -723,7 +723,7 @@ 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;
 
@@ -753,6 +753,16 @@ 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);
 
@@ -788,14 +798,15 @@ 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 v3 2/6] mm/nvdimm: Add PFN_MIN_VERSION support

[Aneesh Kumar K.V]

This allows us to make changes in a backward incompatible way. I have
kept the PFN_MIN_VERSION in this patch '0' because we are not introducing
any incompatible changes in this patch. We also may want to backport this
to older kernels.

The error looks like

  dax0.1: init failed, superblock min version 1, kernel support version 0

and the namespace is marked disabled

$ndctl list -Ni
[
  {
    "dev":"namespace0.0",
    "mode":"fsdax",
    "map":"mem",
    "size":10737418240,
    "uuid":"9605de6d-cefa-4a87-99cd-dec28b02cffe",
    "state":"disabled"
  }
]

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 drivers/nvdimm/pfn.h      |  9 ++++++++-
 drivers/nvdimm/pfn_devs.c |  9 +++++++++
 drivers/nvdimm/pmem.c     | 26 ++++++++++++++++++++++----
 3 files changed, 39 insertions(+), 5 deletions(-)

diff --git a/drivers/nvdimm/pfn.h b/drivers/nvdimm/pfn.h
index dde9853453d3..5fd29242745a 100644
--- a/drivers/nvdimm/pfn.h
+++ b/drivers/nvdimm/pfn.h
@@ -20,6 +20,12 @@
 #define PFN_SIG_LEN 16
 #define PFN_SIG "NVDIMM_PFN_INFO\0"
 #define DAX_SIG "NVDIMM_DAX_INFO\0"
+/*
+ * increment this when we are making changes such that older
+ * kernel should fail to initialize that namespace.
+ */
+
+#define PFN_MIN_VERSION 0
 
 struct nd_pfn_sb {
 	u8 signature[PFN_SIG_LEN];
@@ -36,7 +42,8 @@ struct nd_pfn_sb {
 	__le32 end_trunc;
 	/* minor-version-2 record the base alignment of the mapping */
 	__le32 align;
-	u8 padding[4000];
+	__le16 min_version;
+	u8 padding[3998];
 	__le64 checksum;
 };
 
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 01f40672507f..00c57805cad3 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -439,6 +439,14 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 	if (nvdimm_read_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb), 0))
 		return -ENXIO;
 
+	if (le16_to_cpu(pfn_sb->min_version) > PFN_MIN_VERSION) {
+		dev_err(&nd_pfn->dev,
+			"init failed, superblock min version %d kernel"
+			" support version %d\n",
+			le16_to_cpu(pfn_sb->min_version), PFN_MIN_VERSION);
+		return -EOPNOTSUPP;
+	}
+
 	if (memcmp(pfn_sb->signature, sig, PFN_SIG_LEN) != 0)
 		return -ENODEV;
 
@@ -769,6 +777,7 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	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(2);
+	pfn_sb->min_version = cpu_to_le16(PFN_MIN_VERSION);
 	pfn_sb->start_pad = cpu_to_le32(start_pad);
 	pfn_sb->end_trunc = cpu_to_le32(end_trunc);
 	pfn_sb->align = cpu_to_le32(nd_pfn->align);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index d9d845077b8b..eddc28e8c357 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -496,6 +496,7 @@ 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);
@@ -511,12 +512,29 @@ 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);
 }
 
-- 
2.21.0

_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

[PATCH v3 3/6] 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.

We also increment PFN_MIN_VERSION to make sure that older kernel
won't initialize namespace created with newer kernel.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
 drivers/nvdimm/pfn.h      |  7 +++++--
 drivers/nvdimm/pfn_devs.c | 27 ++++++++++++++++++++++++++-
 2 files changed, 31 insertions(+), 3 deletions(-)

diff --git a/drivers/nvdimm/pfn.h b/drivers/nvdimm/pfn.h
index 5fd29242745a..ba11738ca8a2 100644
--- a/drivers/nvdimm/pfn.h
+++ b/drivers/nvdimm/pfn.h
@@ -25,7 +25,7 @@
  * kernel should fail to initialize that namespace.
  */
 
-#define PFN_MIN_VERSION 0
+#define PFN_MIN_VERSION 1
 
 struct nd_pfn_sb {
 	u8 signature[PFN_SIG_LEN];
@@ -43,7 +43,10 @@ struct nd_pfn_sb {
 	/* minor-version-2 record the base alignment of the mapping */
 	__le32 align;
 	__le16 min_version;
-	u8 padding[3998];
+	/* minor-version-3 record the page size and struct page size */
+	__le16 page_struct_size;
+	__le32 page_size;
+	u8 padding[3992];
 	__le64 checksum;
 };
 
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 00c57805cad3..e01eee9efafe 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -467,6 +467,15 @@ 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) < 3) {
+		/*
+		 * 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(SZ_4K);
+	}
+
 	switch (le32_to_cpu(pfn_sb->mode)) {
 	case PFN_MODE_RAM:
 	case PFN_MODE_PMEM:
@@ -482,6 +491,20 @@ 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
@@ -776,11 +799,13 @@ 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(2);
+	pfn_sb->version_minor = cpu_to_le16(3);
 	pfn_sb->min_version = cpu_to_le16(PFN_MIN_VERSION);
 	pfn_sb->start_pad = cpu_to_le32(start_pad);
 	pfn_sb->end_trunc = cpu_to_le32(end_trunc);
 	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

_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

[PATCH v3 4/6] mm/nvdimm: Use correct #defines instead of opencoding

[Aneesh Kumar K.V]

The nfpn related change is needed to fix the kernel message

"number of pfns truncated from 2617344 to 163584"

The change makes sure the nfpns stored in the superblock is right value.

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       | 6 +++---
 drivers/nvdimm/region_devs.c    | 8 ++++----
 4 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c
index edf278067e72..c5f28c48bde4 100644
--- a/drivers/nvdimm/label.c
+++ b/drivers/nvdimm/label.c
@@ -363,7 +363,7 @@ 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 d0214644e334..c4c5a191b1d6 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -1014,10 +1014,10 @@ 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 e01eee9efafe..d137f52f46ee 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -778,8 +778,8 @@ 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 + reserve + 64 * npfns,
-				max(nd_pfn->align, PMD_SIZE)) - start;
+		offset = ALIGN(start + reserve + sizeof(struct page) * npfns,
+			       max(nd_pfn->align, PMD_SIZE)) - start;
 	} else if (nd_pfn->mode == PFN_MODE_RAM)
 		offset = ALIGN(start + reserve, nd_pfn->align) - start;
 	else
@@ -791,7 +791,7 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 		return -ENXIO;
 	}
 
-	npfns = (size - offset - start_pad - end_trunc) / SZ_4K;
+	npfns = (size - offset - start_pad - end_trunc) / PAGE_SIZE;
 	pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
 	pfn_sb->dataoff = cpu_to_le64(offset);
 	pfn_sb->npfns = cpu_to_le64(npfns);
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index fcf3d8828540..139d7b45b337 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -1005,10 +1005,10 @@ 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 v3 5/6] 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 191d62af0e51..524be92c1cd0 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -296,12 +296,6 @@ 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 d137f52f46ee..9855357c9040 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -18,6 +18,7 @@
 #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"
@@ -111,6 +112,8 @@ 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)
 {
 	/*
@@ -133,6 +136,7 @@ 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)
@@ -310,7 +314,7 @@ 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)) {
@@ -420,6 +424,20 @@ 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;
+}
+
 int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 {
 	u64 checksum, offset;
@@ -505,6 +523,18 @@ 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: "
+			"%lx:%lx\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

_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

[PATCH v3 6/6] mm/nvdimm: Use correct alignment when looking at first pfn from a region

[Aneesh Kumar K.V]

We already add the start_pad to the resource->start but fails to section
align the start. This make sure with altmap we compute the right first
pfn when start_pad is zero and we are doing an align down of start address.

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 1490e63f69a9..bf488b8658e7 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -60,9 +60,11 @@ static unsigned long pfn_first(struct dev_pagemap *pgmap)
 	struct vmem_altmap *altmap = &pgmap->altmap;
 	unsigned long pfn;
 
-	pfn = res->start >> PAGE_SHIFT;
-	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

_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

Re: [PATCH v3 1/6] nvdimm: Consider probe return -EOPNOTSUPP as success

[Aneesh Kumar K.V]

Hi Dan,

Any feedback on this?

A change I would like to get done on top of this series is

+	if (__le16_to_cpu(pfn_sb->version_minor) < 3) {
+		/*
+		 * 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(SZ_4K);
+	}
+

to

+	if (__le16_to_cpu(pfn_sb->version_minor) < 3) {
+		/*
+		 * 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);
+	}
+


That would make sure we will able to access the namespace created on
powerpc with newer kernel.

Kindly let me know if you want to see further changes to this series. Do
you think this is ready for next merge window?

-aneesh

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

> With following patches we 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/region_devs.c | 19 +++++++++++++++----
>  3 files changed, 19 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
> index 2eb6a6cfe9e4..792b3e90453b 100644
> --- a/drivers/nvdimm/bus.c
> +++ b/drivers/nvdimm/bus.c
> @@ -100,8 +100,8 @@ 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 e5ffd5733540..9e67a79fb6d5 100644
> --- a/drivers/nvdimm/nd-core.h
> +++ b/drivers/nvdimm/nd-core.h
> @@ -134,7 +134,8 @@ 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/region_devs.c b/drivers/nvdimm/region_devs.c
> index b4ef7d9ff22e..fcf3d8828540 100644
> --- a/drivers/nvdimm/region_devs.c
> +++ b/drivers/nvdimm/region_devs.c
> @@ -723,7 +723,7 @@ 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;
>  
> @@ -753,6 +753,16 @@ 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);
>  
> @@ -788,14 +798,15 @@ 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

Re: [PATCH v3 3/6] mm/nvdimm: Add page size and struct page size to pfn superblock

[Jan Kara]

On Tue 04-06-19 14:43:54, Aneesh Kumar K.V wrote:
> 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.
> 
> We also increment PFN_MIN_VERSION to make sure that older kernel
> won't initialize namespace created with newer kernel.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
...
> diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
> index 00c57805cad3..e01eee9efafe 100644
> --- a/drivers/nvdimm/pfn_devs.c
> +++ b/drivers/nvdimm/pfn_devs.c
> @@ -467,6 +467,15 @@ 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) < 3) {
> +		/*
> +		 * 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(SZ_4K);
> +	}
> +
>  	switch (le32_to_cpu(pfn_sb->mode)) {
>  	case PFN_MODE_RAM:
>  	case PFN_MODE_PMEM:

As we discussed with Aneesh privately, this actually means that existing
NVDIMM namespaces on PPC64 will stop working due to these defaults for old
superblocks. I don't think that's a good thing as upgrading kernels is
going to be nightmare due to this on PPC64. So I believe we should make
defaults for old superblocks such that working setups keep working without
sysadmin having to touch anything.

								Honza
-- 
Jan Kara <jack@suse.com>
SUSE Labs, CR