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

Aneesh Kumar K.V aneesh.kumar at linux.ibm.com
Tue May 14 12:54:49 AEST 2019


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.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar at 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 a5ac3b240293..44fe923b2ee3 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -292,12 +292,6 @@ 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 01f40672507f..347cab166376 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;
@@ -474,6 +492,18 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 		align = 1UL << ilog2(offset);
 	mode = le32_to_cpu(pfn_sb->mode);
 
+	/*
+	 * 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, settings mismatch\n");
+		dev_dbg(&nd_pfn->dev, "align: %lx:%lx\n", nd_pfn->align, align);
+		return -EINVAL;
+	}
+
 	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 381e872bfde0..d5cfea3d8b86 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -110,7 +110,12 @@ 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



More information about the Linuxppc-dev mailing list