mm/memremap_pages: Introduce memremap_compat_align()

The "sub-section memory hotplug" facility allows memremap_pages() users
like libnvdimm to compensate for hardware platforms like x86 that have a
section size larger than their hardware memory mapping granularity.  The
compensation that sub-section support affords is being tolerant of
physical memory resources shifting by units smaller (64MiB on x86) than
the memory-hotplug section size (128 MiB). Where the platform
physical-memory mapping granularity is limited by the number and
capability of address-decode-registers in the memory controller.

While the sub-section support allows memremap_pages() to operate on
sub-section (2MiB) granularity, the Power architecture may still
require 16MiB alignment on "!radix_enabled()" platforms.

In order for libnvdimm to be able to detect and manage this per-arch
limitation, introduce memremap_compat_align() as a common minimum
alignment across all driver-facing memory-mapping interfaces, and let
Power override it to 16MiB in the "!radix_enabled()" case.

The assumption / requirement for 16MiB to be a viable
memremap_compat_align() value is that Power does not have platforms
where its equivalent of address-decode-registers never hardware remaps a
persistent memory resource on smaller than 16MiB boundaries. Note that I
tried my best to not add a new Kconfig symbol, but header include
entanglements defeated the #ifndef memremap_compat_align design pattern
and the need to export it defeats the __weak design pattern for arch
overrides.

Based on an initial patch by Aneesh.

Link: http://lore.kernel.org/r/CAPcyv4gBGNP95APYaBcsocEa50tQj9b5h__83vgngjq3ouGX_Q@mail.gmail.com
Reported-by: Aneesh Kumar K.V <[email protected]>
Reported-by: Jeff Moyer <[email protected]>
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Paul Mackerras <[email protected]>
Reviewed-by: Aneesh Kumar K.V <[email protected]>
Acked-by: Michael Ellerman <[email protected]> (powerpc)
Signed-off-by: Dan Williams <[email protected]>

arch/powerpc/Kconfig

@@ -122,6 +122,7 @@ config PPC
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV
 	select ARCH_HAS_HUGEPD			if HUGETLB_PAGE
+	select ARCH_HAS_MEMREMAP_COMPAT_ALIGN
 	select ARCH_HAS_MMIOWB			if PPC64
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API

arch/powerpc/mm/ioremap.c

@@ -2,6 +2,7 @@
 
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/mmzone.h>
 #include <linux/vmalloc.h>
 #include <asm/io-workarounds.h>
 
@@ -97,3 +98,23 @@ void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
 
 	return NULL;
 }
+
+#ifdef CONFIG_ZONE_DEVICE
+/*
+ * Override the generic version in mm/memremap.c.
+ *
+ * With hash translation, the direct-map range is mapped with just one
+ * page size selected by htab_init_page_sizes(). Consult
+ * mmu_psize_defs[] to determine the minimum page size alignment.
+*/
+unsigned long memremap_compat_align(void)
+{
+	unsigned int shift = mmu_psize_defs[mmu_linear_psize].shift;
+
+	if (radix_enabled())
+		return SUBSECTION_SIZE;
+	return max(SUBSECTION_SIZE, 1UL << shift);
+
+}
+EXPORT_SYMBOL_GPL(memremap_compat_align);
+#endif

drivers/nvdimm/pfn_devs.c

@@ -750,7 +750,7 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	start = nsio->res.start;
 	size = resource_size(&nsio->res);
 	npfns = PHYS_PFN(size - SZ_8K);
-	align = max(nd_pfn->align, (1UL << SUBSECTION_SHIFT));
+	align = max(nd_pfn->align, SUBSECTION_SIZE);
 	end_trunc = start + size - ALIGN_DOWN(start + size, align);
 	if (nd_pfn->mode == PFN_MODE_PMEM) {
 		/*

include/linux/memremap.h

@@ -132,6 +132,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
 void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
+unsigned long memremap_compat_align(void);
 #else
 static inline void *devm_memremap_pages(struct device *dev,
 		struct dev_pagemap *pgmap)
@@ -165,11 +166,18 @@ static inline void vmem_altmap_free(struct vmem_altmap *altmap,
 		unsigned long nr_pfns)
 {
 }
+
+/* when memremap_pages() is disabled all archs can remap a single page */
+static inline unsigned long memremap_compat_align(void)
+{
+	return PAGE_SIZE;
+}
 #endif /* CONFIG_ZONE_DEVICE */
 
 static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
 {
 	if (pgmap)
 		percpu_ref_put(pgmap->ref);
 }
+
 #endif /* _LINUX_MEMREMAP_H_ */

include/linux/mmzone.h

@@ -1170,6 +1170,7 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec)
 #define SECTION_ALIGN_DOWN(pfn)	((pfn) & PAGE_SECTION_MASK)
 
 #define SUBSECTION_SHIFT 21
+#define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT)
 
 #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT)
 #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT)

lib/Kconfig

@@ -615,6 +615,9 @@ config ARCH_HAS_PMEM_API
 config MEMREGION
 	bool
 
+config ARCH_HAS_MEMREMAP_COMPAT_ALIGN
+	bool
+
 # use memcpy to implement user copies for nommu architectures
 config UACCESS_MEMCPY
 	bool

mm/memremap.c

@@ -7,13 +7,36 @@
 #include <linux/mm.h>
 #include <linux/pfn_t.h>
 #include <linux/swap.h>
+#include <linux/mmzone.h>
 #include <linux/swapops.h>
 #include <linux/types.h>
 #include <linux/wait_bit.h>
 #include <linux/xarray.h>
 
 static DEFINE_XARRAY(pgmap_array);
 
+/*
+ * The memremap() and memremap_pages() interfaces are alternately used
+ * to map persistent memory namespaces. These interfaces place different
+ * constraints on the alignment and size of the mapping (namespace).
+ * memremap() can map individual PAGE_SIZE pages. memremap_pages() can
+ * only map subsections (2MB), and at least one architecture (PowerPC)
+ * the minimum mapping granularity of memremap_pages() is 16MB.
+ *
+ * The role of memremap_compat_align() is to communicate the minimum
+ * arch supported alignment of a namespace such that it can freely
+ * switch modes without violating the arch constraint. Namely, do not
+ * allow a namespace to be PAGE_SIZE aligned since that namespace may be
+ * reconfigured into a mode that requires SUBSECTION_SIZE alignment.
+ */
+#ifndef CONFIG_ARCH_HAS_MEMREMAP_COMPAT_ALIGN
+unsigned long memremap_compat_align(void)
+{
+	return SUBSECTION_SIZE;
+}
+EXPORT_SYMBOL_GPL(memremap_compat_align);
+#endif
+
 #ifdef CONFIG_DEV_PAGEMAP_OPS
 DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
 EXPORT_SYMBOL(devmap_managed_key);