x86, mm: introduce vmem_altmap to augment vmemmap_populate()

In support of providing struct page for large persistent memory
capacities, use struct vmem_altmap to change the default policy for
allocating memory for the memmap array.  The default vmemmap_populate()
allocates page table storage area from the page allocator.  Given
persistent memory capacities relative to DRAM it may not be feasible to
store the memmap in 'System Memory'.  Instead vmem_altmap represents
pre-allocated "device pages" to satisfy vmemmap_alloc_block_buf()
requests.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reported-by: kbuild test robot <lkp@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 45 insertions, 6 deletions

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 2ea574ff9714..43405992d027 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -275,7 +275,8 @@ extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
 extern bool is_memblock_offlined(struct memory_block *mem);
 extern void remove_memory(int nid, u64 start, u64 size);
 extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn);
-extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms);
+extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms,
+		unsigned long map_offset);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
 
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index d90721c178bb..aa3e82a80d7b 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -4,21 +4,53 @@
 
 struct resource;
 struct device;
+
+/**
+ * struct vmem_altmap - pre-allocated storage for vmemmap_populate
+ * @base_pfn: base of the entire dev_pagemap mapping
+ * @reserve: pages mapped, but reserved for driver use (relative to @base)
+ * @free: free pages set aside in the mapping for memmap storage
+ * @align: pages reserved to meet allocation alignments
+ * @alloc: track pages consumed, private to vmemmap_populate()
+ */
+struct vmem_altmap {
+	const unsigned long base_pfn;
+	const unsigned long reserve;
+	unsigned long free;
+	unsigned long align;
+	unsigned long alloc;
+};
+
+unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
+void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
+
+#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_ZONE_DEVICE)
+struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start);
+#else
+static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
+{
+	return NULL;
+}
+#endif
+
 /**
  * struct dev_pagemap - metadata for ZONE_DEVICE mappings
+ * @altmap: pre-allocated/reserved memory for vmemmap allocations
  * @dev: host device of the mapping for debug
  */
 struct dev_pagemap {
-	/* TODO: vmem_altmap and percpu_ref count */
+	struct vmem_altmap *altmap;
+	const struct resource *res;
 	struct device *dev;
 };
 
 #ifdef CONFIG_ZONE_DEVICE
-void *devm_memremap_pages(struct device *dev, struct resource *res);
+void *devm_memremap_pages(struct device *dev, struct resource *res,
+		struct vmem_altmap *altmap);
 struct dev_pagemap *find_dev_pagemap(resource_size_t phys);
 #else
 static inline void *devm_memremap_pages(struct device *dev,
-		struct resource *res)
+		struct resource *res, struct vmem_altmap *altmap)
 {
 	/*
 	 * Fail attempts to call devm_memremap_pages() without
@@ -34,5 +66,4 @@ static inline struct dev_pagemap *find_dev_pagemap(resource_size_t phys)
 	return NULL;
 }
 #endif
-
 #endif /* _LINUX_MEMREMAP_H_ */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index d9fe12d45c21..8bb0907a3603 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2217,7 +2217,14 @@ pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node);
 pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
 pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
 void *vmemmap_alloc_block(unsigned long size, int node);
-void *vmemmap_alloc_block_buf(unsigned long size, int node);
+struct vmem_altmap;
+void *__vmemmap_alloc_block_buf(unsigned long size, int node,
+		struct vmem_altmap *altmap);
+static inline void *vmemmap_alloc_block_buf(unsigned long size, int node)
+{
+	return __vmemmap_alloc_block_buf(size, node, NULL);
+}
+
 void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
 int vmemmap_populate_basepages(unsigned long start, unsigned long end,
 			       int node);