arm64/mm: enable vmem_altmap support for vmemmap mappings

Device memory ranges when getting hot added into ZONE_DEVICE, might
require their vmemmap mapping's backing memory to be allocated from their
own range instead of consuming system memory.  This prevents large system
memory usage for potentially large device memory ranges.  Device driver
communicates this request via vmem_altmap structure.  Architecture needs
to take this request into account while creating and tearing down vemmmap
mappings.

This enables vmem_altmap support in vmemmap_populate() and vmemmap_free()
which includes vmemmap_populate_basepages() used for ARM64_16K_PAGES and
ARM64_64K_PAGES configs.

Signed-off-by: Anshuman Khandual <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Tested-by: Jia He <[email protected]>
Reviewed-by: Catalin Marinas <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Steve Capper <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Yu Zhao <[email protected]>
Cc: Hsin-Yi Wang <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Fenghua Yu <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Cc: "Matthew Wilcox (Oracle)" <[email protected]>
Cc: Michael Ellerman <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mike Rapoport <[email protected]>
Cc: Palmer Dabbelt <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Paul Walmsley <[email protected]>
Cc: Pavel Tatashin <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Robin Murphy <[email protected]>
Cc: Tony Luck <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Linus Torvalds <[email protected]>

Author: Anshuman Khandual

arch/arm64/mm/mmu.c

@@ -761,15 +761,20 @@ int kern_addr_valid(unsigned long addr)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
-static void free_hotplug_page_range(struct page *page, size_t size)
+static void free_hotplug_page_range(struct page *page, size_t size,
+				    struct vmem_altmap *altmap)
 {
-	WARN_ON(PageReserved(page));
-	free_pages((unsigned long)page_address(page), get_order(size));
+	if (altmap) {
+		vmem_altmap_free(altmap, size >> PAGE_SHIFT);
+	} else {
+		WARN_ON(PageReserved(page));
+		free_pages((unsigned long)page_address(page), get_order(size));
+	}
 }
 
 static void free_hotplug_pgtable_page(struct page *page)
 {
-	free_hotplug_page_range(page, PAGE_SIZE);
+	free_hotplug_page_range(page, PAGE_SIZE, NULL);
 }
 
 static bool pgtable_range_aligned(unsigned long start, unsigned long end,
@@ -792,7 +797,8 @@ static bool pgtable_range_aligned(unsigned long start, unsigned long end,
 }
 
 static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr,
-				    unsigned long end, bool free_mapped)
+				    unsigned long end, bool free_mapped,
+				    struct vmem_altmap *altmap)
 {
 	pte_t *ptep, pte;
 
@@ -806,12 +812,14 @@ static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr,
 		pte_clear(&init_mm, addr, ptep);
 		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 		if (free_mapped)
-			free_hotplug_page_range(pte_page(pte), PAGE_SIZE);
+			free_hotplug_page_range(pte_page(pte),
+						PAGE_SIZE, altmap);
 	} while (addr += PAGE_SIZE, addr < end);
 }
 
 static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr,
-				    unsigned long end, bool free_mapped)
+				    unsigned long end, bool free_mapped,
+				    struct vmem_altmap *altmap)
 {
 	unsigned long next;
 	pmd_t *pmdp, pmd;
@@ -834,16 +842,17 @@ static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr,
 			flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 			if (free_mapped)
 				free_hotplug_page_range(pmd_page(pmd),
-							PMD_SIZE);
+							PMD_SIZE, altmap);
 			continue;
 		}
 		WARN_ON(!pmd_table(pmd));
-		unmap_hotplug_pte_range(pmdp, addr, next, free_mapped);
+		unmap_hotplug_pte_range(pmdp, addr, next, free_mapped, altmap);
 	} while (addr = next, addr < end);
 }
 
 static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr,
-				    unsigned long end, bool free_mapped)
+				    unsigned long end, bool free_mapped,
+				    struct vmem_altmap *altmap)
 {
 	unsigned long next;
 	pud_t *pudp, pud;
@@ -866,16 +875,17 @@ static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr,
 			flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 			if (free_mapped)
 				free_hotplug_page_range(pud_page(pud),
-							PUD_SIZE);
+							PUD_SIZE, altmap);
 			continue;
 		}
 		WARN_ON(!pud_table(pud));
-		unmap_hotplug_pmd_range(pudp, addr, next, free_mapped);
+		unmap_hotplug_pmd_range(pudp, addr, next, free_mapped, altmap);
 	} while (addr = next, addr < end);
 }
 
 static void unmap_hotplug_p4d_range(pgd_t *pgdp, unsigned long addr,
-				    unsigned long end, bool free_mapped)
+				    unsigned long end, bool free_mapped,
+				    struct vmem_altmap *altmap)
 {
 	unsigned long next;
 	p4d_t *p4dp, p4d;
@@ -888,16 +898,24 @@ static void unmap_hotplug_p4d_range(pgd_t *pgdp, unsigned long addr,
 			continue;
 
 		WARN_ON(!p4d_present(p4d));
-		unmap_hotplug_pud_range(p4dp, addr, next, free_mapped);
+		unmap_hotplug_pud_range(p4dp, addr, next, free_mapped, altmap);
 	} while (addr = next, addr < end);
 }
 
 static void unmap_hotplug_range(unsigned long addr, unsigned long end,
-				bool free_mapped)
+				bool free_mapped, struct vmem_altmap *altmap)
 {
 	unsigned long next;
 	pgd_t *pgdp, pgd;
 
+	/*
+	 * altmap can only be used as vmemmap mapping backing memory.
+	 * In case the backing memory itself is not being freed, then
+	 * altmap is irrelevant. Warn about this inconsistency when
+	 * encountered.
+	 */
+	WARN_ON(!free_mapped && altmap);
+
 	do {
 		next = pgd_addr_end(addr, end);
 		pgdp = pgd_offset_k(addr);
@@ -906,7 +924,7 @@ static void unmap_hotplug_range(unsigned long addr, unsigned long end,
 			continue;
 
 		WARN_ON(!pgd_present(pgd));
-		unmap_hotplug_p4d_range(pgdp, addr, next, free_mapped);
+		unmap_hotplug_p4d_range(pgdp, addr, next, free_mapped, altmap);
 	} while (addr = next, addr < end);
 }
 
@@ -1070,7 +1088,7 @@ static void free_empty_tables(unsigned long addr, unsigned long end,
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
-	return vmemmap_populate_basepages(start, end, node, NULL);
+	return vmemmap_populate_basepages(start, end, node, altmap);
 }
 #else	/* !ARM64_SWAPPER_USES_SECTION_MAPS */
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
@@ -1102,7 +1120,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		if (pmd_none(READ_ONCE(*pmdp))) {
 			void *p = NULL;
 
-			p = vmemmap_alloc_block_buf(PMD_SIZE, node, NULL);
+			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
 			if (!p)
 				return -ENOMEM;
 
@@ -1120,7 +1138,7 @@ void vmemmap_free(unsigned long start, unsigned long end,
 #ifdef CONFIG_MEMORY_HOTPLUG
 	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
 
-	unmap_hotplug_range(start, end, true);
+	unmap_hotplug_range(start, end, true, altmap);
 	free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END);
 #endif
 }
@@ -1411,7 +1429,7 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
 	WARN_ON(pgdir != init_mm.pgd);
 	WARN_ON((start < PAGE_OFFSET) || (end > PAGE_END));
 
-	unmap_hotplug_range(start, end, false);
+	unmap_hotplug_range(start, end, false, NULL);
 	free_empty_tables(start, end, PAGE_OFFSET, PAGE_END);
 }