libnvdimm/dax: Pick the right alignment default when creating dax devices

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"
  }
]

Cc: linux-mm@kvack.org
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Link: https://lore.kernel.org/r/20190905154603.10349-8-aneesh.kumar@linux.ibm.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

1 files changed, 54 insertions, 21 deletions

diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index ce9ef18282dd..934cdcaaae97 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/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;
+
+	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)
+{
 
-	return data;
+	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