The patch titled Subject: mm/sparsemem: add helpers track active portions of a section at boot has been removed from the -mm tree. Its filename was mm-sparsemem-add-helpers-track-active-portions-of-a-section-at-boot.patch This patch was dropped because it was withdrawn ------------------------------------------------------ From: Dan Williams <dan.j.williams@xxxxxxxxx> Subject: mm/sparsemem: add helpers track active portions of a section at boot Prepare for hot{plug,remove} of sub-ranges of a section by tracking a section active bitmask, each bit representing 2MB (SECTION_SIZE (128M) / map_active bitmask length (64)). If it turns out that 2MB is too large of an active tracking granularity it is trivial to increase the size of the map_active bitmap. The implications of a partially populated section is that pfn_valid() needs to go beyond a valid_section() check and read the sub-section active ranges from the bitmask. Link: http://lkml.kernel.org/r/155552635098.2015392.5460028594173939000.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxx> Cc: Vlastimil Babka <vbabka@xxxxxxx> Cc: Logan Gunthorpe <logang@xxxxxxxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: Jeff Moyer <jmoyer@xxxxxxxxxx> Cc: Jérôme Glisse <jglisse@xxxxxxxxxx> Cc: Toshi Kani <toshi.kani@xxxxxxx> Cc: Oscar Salvador <osalvador@xxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/mmzone.h | 29 ++++++++++++++++++++++- mm/page_alloc.c | 4 ++- mm/sparse.c | 48 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 79 insertions(+), 2 deletions(-) --- a/include/linux/mmzone.h~mm-sparsemem-add-helpers-track-active-portions-of-a-section-at-boot +++ a/include/linux/mmzone.h @@ -1117,6 +1117,8 @@ struct mem_section_usage { unsigned long pageblock_flags[0]; }; +void section_active_init(unsigned long pfn, unsigned long nr_pages); + struct page; struct page_ext; struct mem_section { @@ -1254,12 +1256,36 @@ static inline struct mem_section *__pfn_ extern int __highest_present_section_nr; +static inline int section_active_index(phys_addr_t phys) +{ + return (phys & ~(PA_SECTION_MASK)) / SECTION_ACTIVE_SIZE; +} + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) +{ + int idx = section_active_index(PFN_PHYS(pfn)); + + return !!(ms->usage->map_active & (1UL << idx)); +} +#else +static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) +{ + return 1; +} +#endif + #ifndef CONFIG_HAVE_ARCH_PFN_VALID static inline int pfn_valid(unsigned long pfn) { + struct mem_section *ms; + if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; - return valid_section(__nr_to_section(pfn_to_section_nr(pfn))); + ms = __nr_to_section(pfn_to_section_nr(pfn)); + if (!valid_section(ms)) + return 0; + return pfn_section_valid(ms, pfn); } #endif @@ -1290,6 +1316,7 @@ void sparse_init(void); #else #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) +#define section_active_init(_pfn, _nr_pages) do {} while (0) #endif /* CONFIG_SPARSEMEM */ /* --- a/mm/page_alloc.c~mm-sparsemem-add-helpers-track-active-portions-of-a-section-at-boot +++ a/mm/page_alloc.c @@ -7287,10 +7287,12 @@ void __init free_area_init_nodes(unsigne /* Print out the early node map */ pr_info("Early memory node ranges\n"); - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { pr_info(" node %3d: [mem %#018Lx-%#018Lx]\n", nid, (u64)start_pfn << PAGE_SHIFT, ((u64)end_pfn << PAGE_SHIFT) - 1); + section_active_init(start_pfn, end_pfn - start_pfn); + } /* Initialise every node */ mminit_verify_pageflags_layout(); --- a/mm/sparse.c~mm-sparsemem-add-helpers-track-active-portions-of-a-section-at-boot +++ a/mm/sparse.c @@ -210,6 +210,54 @@ static inline unsigned long first_presen return next_present_section_nr(-1); } +static unsigned long section_active_mask(unsigned long pfn, + unsigned long nr_pages) +{ + int idx_start, idx_size; + phys_addr_t start, size; + + if (!nr_pages) + return 0; + + start = PFN_PHYS(pfn); + size = PFN_PHYS(min(nr_pages, PAGES_PER_SECTION + - (pfn & ~PAGE_SECTION_MASK))); + size = ALIGN(size, SECTION_ACTIVE_SIZE); + + idx_start = section_active_index(start); + idx_size = section_active_index(size); + + if (idx_size == 0) + return -1; + return ((1UL << idx_size) - 1) << idx_start; +} + +void section_active_init(unsigned long pfn, unsigned long nr_pages) +{ + int end_sec = pfn_to_section_nr(pfn + nr_pages - 1); + int i, start_sec = pfn_to_section_nr(pfn); + + if (!nr_pages) + return; + + for (i = start_sec; i <= end_sec; i++) { + struct mem_section *ms; + unsigned long mask; + unsigned long pfns; + + pfns = min(nr_pages, PAGES_PER_SECTION + - (pfn & ~PAGE_SECTION_MASK)); + mask = section_active_mask(pfn, pfns); + + ms = __nr_to_section(i); + pr_debug("%s: sec: %d mask: %#018lx\n", __func__, i, mask); + ms->usage->map_active = mask; + + pfn += pfns; + nr_pages -= pfns; + } +} + /* Record a memory area against a node. */ void __init memory_present(int nid, unsigned long start, unsigned long end) { _ Patches currently in -mm which might be from dan.j.williams@xxxxxxxxx are mm-hotplug-prepare-shrink_zone-pgdat_span-for-sub-section-removal.patch mm-sparsemem-convert-kmalloc_section_memmap-to-populate_section_memmap.patch mm-hotplug-add-mem-hotplug-restrictions-for-remove_memory.patch mm-kill-is_dev_zone-helper.patch mm-sparsemem-prepare-for-sub-section-ranges.patch mm-sparsemem-support-sub-section-hotplug.patch mm-devm_memremap_pages-enable-sub-section-remap.patch libnvdimm-pfn-fix-fsdax-mode-namespace-info-block-zero-fields.patch libnvdimm-pfn-stop-padding-pmem-namespaces-to-section-alignment.patch mm-shuffle-initial-free-memory-to-improve-memory-side-cache-utilization.patch mm-shuffle-initial-free-memory-to-improve-memory-side-cache-utilization-fix.patch mm-move-buddy-list-manipulations-into-helpers.patch mm-move-buddy-list-manipulations-into-helpers-fix.patch mm-maintain-randomization-of-page-free-lists.patch