Re: [PATCH v5 10/13] powerpc/book3s64/vmemmap: Switch radix to use a different vmemmap handling function

This is in preparation to update radix to implement vmemmap optimization
for devdax. Below are the rules w.r.t radix vmemmap mapping

1. First try to map things using PMD (2M)
2. With altmap if altmap cross-boundary check returns true, fall back to
   PAGE_SIZE
3. If we can't allocate PMD_SIZE backing memory for vmemmap, fallback to
   PAGE_SIZE

On removing vmemmap mapping, check if every subsection that is using the
vmemmap area is invalid. If found to be invalid, that implies we can safely
free the vmemmap area. We don't use the PAGE_UNUSED pattern used by x86
because with 64K page size, we need to do the above check even at the
PAGE_SIZE granularity.

Signed-off-by: Aneesh Kumar K.V <redacted>
---
 arch/powerpc/include/asm/book3s/64/radix.h |   2 +
 arch/powerpc/include/asm/pgtable.h         |   4 +
 arch/powerpc/mm/book3s64/radix_pgtable.c   | 326 +++++++++++++++++++--
 arch/powerpc/mm/init_64.c                  |  26 +-
 4 files changed, 327 insertions(+), 31 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 2ef92f36340f..f1461289643a 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h

@@ -331,6 +331,8 @@ extern int __meminit radix__vmemmap_create_mapping(unsigned long start,
 					     unsigned long phys);
 int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end,
 				      int node, struct vmem_altmap *altmap);
+void __ref radix__vmemmap_free(unsigned long start, unsigned long end,
+			       struct vmem_altmap *altmap);
 extern void radix__vmemmap_remove_mapping(unsigned long start,
 				    unsigned long page_size);
 

diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 6a88bfdaa69b..68817ea7f994 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h

@@ -165,6 +165,10 @@ static inline bool is_ioremap_addr(const void *x)
 
 	return addr >= IOREMAP_BASE && addr < IOREMAP_END;
 }
+
+int __meminit vmemmap_populated(unsigned long vmemmap_addr, int vmemmap_map_size);
+bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start,
+			   unsigned long page_size);
 #endif /* CONFIG_PPC64 */
 
 #endif /* __ASSEMBLY__ */

diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 227fea53c217..9a7f3707b6fb 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c

@@ -744,8 +744,59 @@ static void free_pud_table(pud_t *pud_start, p4d_t *p4d)
 	p4d_clear(p4d);
 }
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static bool __meminit vmemmap_pmd_is_unused(unsigned long addr, unsigned long end)
+{
+	unsigned long start = ALIGN_DOWN(addr, PMD_SIZE);
+
+	return !vmemmap_populated(start, PMD_SIZE);
+}
+
+static bool __meminit vmemmap_page_is_unused(unsigned long addr, unsigned long end)
+{
+	unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE);
+
+	return !vmemmap_populated(start, PAGE_SIZE);
+
+}
+#endif
+
+static void __meminit free_vmemmap_pages(struct page *page,
+					 struct vmem_altmap *altmap,
+					 int order)
+{
+	unsigned int nr_pages = 1 << order;
+
+	if (altmap) {
+		unsigned long alt_start, alt_end;
+		unsigned long base_pfn = page_to_pfn(page);
+
+		/*
+		 * with 2M vmemmap mmaping we can have things setup
+		 * such that even though atlmap is specified we never
+		 * used altmap.
+		 */
+		alt_start = altmap->base_pfn;
+		alt_end = altmap->base_pfn + altmap->reserve +
+			altmap->free + altmap->alloc + altmap->align;
+
+		if (base_pfn >= alt_start && base_pfn < alt_end) {
+			vmem_altmap_free(altmap, nr_pages);
+			return;
+		}
+	}
+