Dan Williams <dan.j.willi...@intel.com> writes: > 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.
I have just a couple of questions. First, can you please add a comment above the generic implementation of memremap_compat_align describing its purpose, and why a platform might want to override it? Second, I will take it at face value that the power architecture requires a 16MB alignment, but it's not clear to me why mmu_linear_psize was chosen to represent that. What's the relationship, there, and can we please have a comment explaining it? Thanks! Jeff > > Link: > http://lore.kernel.org/r/capcyv4gbgnp95apyabcsocea50tqj9b5h__83vgngjq3oug...@mail.gmail.com > Reported-by: Aneesh Kumar K.V <aneesh.ku...@linux.ibm.com> > Reported-by: Jeff Moyer <jmo...@redhat.com> > Cc: Benjamin Herrenschmidt <b...@kernel.crashing.org> > Cc: Paul Mackerras <pau...@samba.org> > Signed-off-by: Dan Williams <dan.j.willi...@intel.com> > --- > arch/powerpc/Kconfig | 1 + > arch/powerpc/mm/ioremap.c | 12 ++++++++++++ > drivers/nvdimm/pfn_devs.c | 2 +- > include/linux/memremap.h | 8 ++++++++ > include/linux/mmzone.h | 1 + > lib/Kconfig | 3 +++ > mm/memremap.c | 13 +++++++++++++ > 7 files changed, 39 insertions(+), 1 deletion(-) > > diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig > index 497b7d0b2d7e..e6ffe905e2b9 100644 > --- a/arch/powerpc/Kconfig > +++ b/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 > diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c > index fc669643ce6a..38b5ba7d3e2d 100644 > --- a/arch/powerpc/mm/ioremap.c > +++ b/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 +98,14 @@ void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t > offset, unsigned long size, > > return NULL; > } > + > +#ifdef CONFIG_ZONE_DEVICE > +/* override of the generic version in mm/memremap.c */ > +unsigned long memremap_compat_align(void) > +{ > + if (radix_enabled()) > + return SUBSECTION_SIZE; > + return (1UL << mmu_psize_defs[mmu_linear_psize].shift); > +} > +EXPORT_SYMBOL_GPL(memremap_compat_align); > +#endif > diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c > index b94f7a7e94b8..a5c25cb87116 100644 > --- a/drivers/nvdimm/pfn_devs.c > +++ b/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) { > /* > diff --git a/include/linux/memremap.h b/include/linux/memremap.h > index 6fefb09af7c3..8af1cbd8f293 100644 > --- a/include/linux/memremap.h > +++ b/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) > @@ -165,6 +166,12 @@ 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) > @@ -172,4 +179,5 @@ static inline void put_dev_pagemap(struct dev_pagemap > *pgmap) > if (pgmap) > percpu_ref_put(pgmap->ref); > } > + > #endif /* _LINUX_MEMREMAP_H_ */ > diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h > index 462f6873905a..6b77f7239af5 100644 > --- a/include/linux/mmzone.h > +++ b/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) > diff --git a/lib/Kconfig b/lib/Kconfig > index 0cf875fd627c..17dbc7bd3895 100644 > --- a/lib/Kconfig > +++ b/lib/Kconfig > @@ -618,6 +618,9 @@ 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 > diff --git a/mm/memremap.c b/mm/memremap.c > index 09b5b7adc773..a6905d28fe91 100644 > --- a/mm/memremap.c > +++ b/mm/memremap.c > @@ -7,6 +7,7 @@ > #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> > @@ -14,6 +15,18 @@ > > static DEFINE_XARRAY(pgmap_array); > > +/* > + * Minimum compatible alignment of the resource (start, end) across > + * memremap interfaces (i.e. memremap + memremap_pages) > + */ > +#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);
