powerpc/mm: Fallback to RAM if the altmap is unusable

oohal · mpe · commit 9ef34630a461 · 2018-12-09T21:33:21.000+11:00
The "altmap" is used to provide a pool of memory that is reserved for the vmemmap backing of hot-plugged memory. This is useful when adding large amount of ZONE_DEVICE memory to a system with a limited amount of normal memory. On ppc64 we use huge pages to map the vmemmap which requires the backing storage to be contigious and aligned to the hugepage size. The altmap implementation allows for the altmap provider to reserve a few PFNs at the start of the range for it's own uses and when this occurs the first chunk of the altmap is not usable for hugepage mappings. On hash there is no sane way to fall back to a normal sized page mapping so we fail the allocation. This results in memory hotplug failing with ENOMEM when the new range doesn't fall into an existing vmemmap block. This patch handles this case by falling back to using system memory rather than failing if we cannot allocate from the altmap. This fallback should only ever be used for the first vmemmap block so it should not cause excess memory consumption. Fixes: 7b73d97 ("mm: pass the vmem_altmap to vmemmap_populate") Signed-off-by: Oliver O'Halloran <oohall@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
@@ -188,15 +188,20 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 	pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node);
 
 	for (; start < end; start += page_size) {
-		void *p;
+		void *p = NULL;
 		int rc;
 
 		if (vmemmap_populated(start, page_size))
 			continue;
 
+		/*
+		 * Allocate from the altmap first if we have one. This may
+		 * fail due to alignment issues when using 16MB hugepages, so
+		 * fall back to system memory if the altmap allocation fail.
+		 */
 		if (altmap)
 			p = altmap_alloc_block_buf(page_size, altmap);
-		else
+		if (!p)
 			p = vmemmap_alloc_block_buf(page_size, node);
 		if (!p)
 			return -ENOMEM;
@@ -255,8 +260,15 @@ void __ref vmemmap_free(unsigned long start, unsigned long end,
 {
 	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
 	unsigned long page_order = get_order(page_size);
+	unsigned long alt_start = ~0, alt_end = ~0;
+	unsigned long base_pfn;
 
 	start = _ALIGN_DOWN(start, page_size);
+	if (altmap) {
+		alt_start = altmap->base_pfn;
+		alt_end = altmap->base_pfn + altmap->reserve +
+			  altmap->free + altmap->alloc + altmap->align;
+	}
 
 	pr_debug("vmemmap_free %lx...%lx\n", start, end);
 
@@ -280,8 +292,9 @@ void __ref vmemmap_free(unsigned long start, unsigned long end,
 		page = pfn_to_page(addr >> PAGE_SHIFT);
 		section_base = pfn_to_page(vmemmap_section_start(start));
 		nr_pages = 1 << page_order;
+		base_pfn = PHYS_PFN(addr);
 
-		if (altmap) {
+		if (base_pfn >= alt_start && base_pfn < alt_end) {
 			vmem_altmap_free(altmap, nr_pages);
 		} else if (PageReserved(page)) {
 			/* allocated from bootmem */
