[PATCH v5 1/5] mm/sparse-vmemmap: add a pgmap argument to section activation

[Joao Martins <joao.m.martins@oracle.com>]

In support of using compound pages for devmap mappings, plumb the pgmap
down to the vmemmap_populate implementation. Note that while altmap is
retrievable from pgmap the memory hotplug code passes altmap without
pgmap[*], so both need to be independently plumbed.

So in addition to @altmap, pass @pgmap to sparse section populate
functions namely:

	sparse_add_section
	  section_activate
	    populate_section_memmap
   	      __populate_section_memmap

Passing @pgmap allows __populate_section_memmap() to both fetch the
vmemmap_shift in which memmap metadata is created for and also to let
sparse-vmemmap fetch pgmap ranges to co-relate to a given section and pick
whether to just reuse tail pages from past onlined sections.

While at it, fix the kdoc for @altmap for sparse_add_section().

[*] https://lore.kernel.org/linux-mm/20210319092635.6214-1-osalvador@suse.de/

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
---
 include/linux/memory_hotplug.h |  5 ++++-
 include/linux/mm.h             |  3 ++-
 mm/memory_hotplug.c            |  3 ++-
 mm/sparse-vmemmap.c            |  3 ++-
 mm/sparse.c                    | 26 ++++++++++++++++----------
 5 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 76bf2de86def..405aa2b4ae4f 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -15,6 +15,7 @@ struct memory_block;
 struct memory_group;
 struct resource;
 struct vmem_altmap;
+struct dev_pagemap;
 
 #ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION
 /*
@@ -122,6 +123,7 @@ typedef int __bitwise mhp_t;
 struct mhp_params {
 	struct vmem_altmap *altmap;
 	pgprot_t pgprot;
+	struct dev_pagemap *pgmap;
 };
 
 bool mhp_range_allowed(u64 start, u64 size, bool need_mapping);
@@ -335,7 +337,8 @@ extern void remove_pfn_range_from_zone(struct zone *zone,
 				       unsigned long nr_pages);
 extern bool is_memblock_offlined(struct memory_block *mem);
 extern int sparse_add_section(int nid, unsigned long pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap);
+		unsigned long nr_pages, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap);
 extern void sparse_remove_section(struct mem_section *ms,
 		unsigned long pfn, unsigned long nr_pages,
 		unsigned long map_offset, struct vmem_altmap *altmap);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bf60d947503e..f6a439582f63 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3165,7 +3165,8 @@ int vmemmap_remap_alloc(unsigned long start, unsigned long end,
 
 void *sparse_buffer_alloc(unsigned long size);
 struct page * __populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap);
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
 p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
 pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ce68098832aa..79e96b6a9036 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -328,7 +328,8 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
 		/* Select all remaining pages up to the next section boundary */
 		cur_nr_pages = min(end_pfn - pfn,
 				   SECTION_ALIGN_UP(pfn + 1) - pfn);
-		err = sparse_add_section(nid, pfn, cur_nr_pages, altmap);
+		err = sparse_add_section(nid, pfn, cur_nr_pages, altmap,
+					 params->pgmap);
 		if (err)
 			break;
 		cond_resched();
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 8aecd6b3896c..c506f77cff23 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -641,7 +641,8 @@ int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
 }
 
 struct page * __meminit __populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	unsigned long start = (unsigned long) pfn_to_page(pfn);
 	unsigned long end = start + nr_pages * sizeof(struct page);
diff --git a/mm/sparse.c b/mm/sparse.c
index 952f06d8f373..d2d76d158b39 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -427,7 +427,8 @@ static unsigned long __init section_map_size(void)
 }
 
 struct page __init *__populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	unsigned long size = section_map_size();
 	struct page *map = sparse_buffer_alloc(size);
@@ -524,7 +525,7 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin,
 			break;
 
 		map = __populate_section_memmap(pfn, PAGES_PER_SECTION,
-				nid, NULL);
+				nid, NULL, NULL);
 		if (!map) {
 			pr_err("%s: node[%d] memory map backing failed. Some memory will not be available.",
 			       __func__, nid);
@@ -629,9 +630,10 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 static struct page * __meminit populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
-	return __populate_section_memmap(pfn, nr_pages, nid, altmap);
+	return __populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
 }
 
 static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
@@ -700,7 +702,8 @@ static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages)
 }
 #else
 struct page * __meminit populate_section_memmap(unsigned long pfn,
-		unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	return kvmalloc_node(array_size(sizeof(struct page),
 					PAGES_PER_SECTION), GFP_KERNEL, nid);
@@ -823,7 +826,8 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
 }
 
 static struct page * __meminit section_activate(int nid, unsigned long pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap)
+		unsigned long nr_pages, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	struct mem_section *ms = __pfn_to_section(pfn);
 	struct mem_section_usage *usage = NULL;
@@ -855,7 +859,7 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
 	if (nr_pages < PAGES_PER_SECTION && early_section(ms))
 		return pfn_to_page(pfn);
 
-	memmap = populate_section_memmap(pfn, nr_pages, nid, altmap);
+	memmap = populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
 	if (!memmap) {
 		section_deactivate(pfn, nr_pages, altmap);
 		return ERR_PTR(-ENOMEM);
@@ -869,7 +873,8 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
  * @nid: The node to add section on
  * @start_pfn: start pfn of the memory range
  * @nr_pages: number of pfns to add in the section
- * @altmap: device page map
+ * @altmap: alternate pfns to allocate the memmap backing store
+ * @pgmap: alternate compound page geometry for devmap mappings
  *
  * This is only intended for hotplug.
  *
@@ -883,7 +888,8 @@ static struct page * __meminit section_activate(int nid, unsigned long pfn,
  * * -ENOMEM	- Out of memory.
  */
 int __meminit sparse_add_section(int nid, unsigned long start_pfn,
-		unsigned long nr_pages, struct vmem_altmap *altmap)
+		unsigned long nr_pages, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
 {
 	unsigned long section_nr = pfn_to_section_nr(start_pfn);
 	struct mem_section *ms;
@@ -894,7 +900,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
 	if (ret < 0)
 		return ret;
 
-	memmap = section_activate(nid, start_pfn, nr_pages, altmap);
+	memmap = section_activate(nid, start_pfn, nr_pages, altmap, pgmap);
 	if (IS_ERR(memmap))
 		return PTR_ERR(memmap);
 
-- 
2.17.2