[PATCH v7 08/12] mm/sparsemem: Prepare for sub-section ranges

From: Dan Williams
Date: Thu May 02 2019 - 02:10:14 EST


Prepare the memory hot-{add,remove} paths for handling sub-section
ranges by plumbing the starting page frame and number of pages being
handled through arch_{add,remove}_memory() to
sparse_{add,remove}_one_section().

This is simply plumbing, small cleanups, and some identifier renames. No
intended functional changes.

Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
---
include/linux/memory_hotplug.h | 7 +-
mm/memory_hotplug.c | 118 +++++++++++++++++++++++++---------------
mm/sparse.c | 7 +-
3 files changed, 83 insertions(+), 49 deletions(-)

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index ae892eef8b82..835a94650ee3 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -354,9 +354,10 @@ extern int add_memory_resource(int nid, struct resource *resource);
extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
unsigned long nr_pages, struct vmem_altmap *altmap);
extern bool is_memblock_offlined(struct memory_block *mem);
-extern int sparse_add_one_section(int nid, unsigned long start_pfn,
- struct vmem_altmap *altmap);
-extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms,
+extern int sparse_add_section(int nid, unsigned long pfn,
+ unsigned long nr_pages, struct vmem_altmap *altmap);
+extern void sparse_remove_section(struct zone *zone, struct mem_section *ms,
+ unsigned long pfn, unsigned long nr_pages,
unsigned long map_offset, struct vmem_altmap *altmap);
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
unsigned long pnum);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 108380e20d8f..9f73332af910 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -251,22 +251,44 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
}
#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */

-static int __meminit __add_section(int nid, unsigned long phys_start_pfn,
- struct vmem_altmap *altmap, bool want_memblock)
+static int __meminit __add_section(int nid, unsigned long pfn,
+ unsigned long nr_pages, struct vmem_altmap *altmap,
+ bool want_memblock)
{
int ret;

- if (pfn_valid(phys_start_pfn))
+ if (pfn_valid(pfn))
return -EEXIST;

- ret = sparse_add_one_section(nid, phys_start_pfn, altmap);
+ ret = sparse_add_section(nid, pfn, nr_pages, altmap);
if (ret < 0)
return ret;

if (!want_memblock)
return 0;

- return hotplug_memory_register(nid, __pfn_to_section(phys_start_pfn));
+ return hotplug_memory_register(nid, __pfn_to_section(pfn));
+}
+
+static int subsection_check(unsigned long pfn, unsigned long nr_pages,
+ unsigned long flags, const char *reason)
+{
+ /*
+ * Only allow partial section hotplug for !memblock ranges,
+ * since register_new_memory() requires section alignment, and
+ * CONFIG_SPARSEMEM_VMEMMAP=n requires sections to be fully
+ * populated.
+ */
+ if ((!IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)
+ || (flags & MHP_MEMBLOCK_API))
+ && ((pfn & ~PAGE_SECTION_MASK)
+ || (nr_pages & ~PAGE_SECTION_MASK))) {
+ WARN(1, "Sub-section hot-%s incompatible with %s\n", reason,
+ (flags & MHP_MEMBLOCK_API)
+ ? "memblock api" : "!CONFIG_SPARSEMEM_VMEMMAP");
+ return -EINVAL;
+ }
+ return 0;
}

/*
@@ -275,34 +297,40 @@ static int __meminit __add_section(int nid, unsigned long phys_start_pfn,
* call this function after deciding the zone to which to
* add the new pages.
*/
-int __ref __add_pages(int nid, unsigned long phys_start_pfn,
- unsigned long nr_pages, struct mhp_restrictions *restrictions)
+int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
+ struct mhp_restrictions *restrictions)
{
unsigned long i;
- int err = 0;
- int start_sec, end_sec;
+ int start_sec, end_sec, err;
struct vmem_altmap *altmap = restrictions->altmap;

- /* during initialize mem_map, align hot-added range to section */
- start_sec = pfn_to_section_nr(phys_start_pfn);
- end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
-
if (altmap) {
/*
* Validate altmap is within bounds of the total request
*/
- if (altmap->base_pfn != phys_start_pfn
+ if (altmap->base_pfn != pfn
|| vmem_altmap_offset(altmap) > nr_pages) {
pr_warn_once("memory add fail, invalid altmap\n");
- err = -EINVAL;
- goto out;
+ return -EINVAL;
}
altmap->alloc = 0;
}

+ err = subsection_check(pfn, nr_pages, restrictions->flags, "add");
+ if (err)
+ return err;
+
+ start_sec = pfn_to_section_nr(pfn);
+ end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
for (i = start_sec; i <= end_sec; i++) {
- err = __add_section(nid, section_nr_to_pfn(i), altmap,
+ unsigned long pfns;
+
+ pfns = min(nr_pages, PAGES_PER_SECTION
+ - (pfn & ~PAGE_SECTION_MASK));
+ err = __add_section(nid, pfn, pfns, altmap,
restrictions->flags & MHP_MEMBLOCK_API);
+ pfn += pfns;
+ nr_pages -= pfns;

/*
* EEXIST is finally dealt with by ioresource collision
@@ -315,7 +343,6 @@ int __ref __add_pages(int nid, unsigned long phys_start_pfn,
cond_resched();
}
vmemmap_populate_print_last();
-out:
return err;
}

@@ -494,10 +521,10 @@ static void shrink_pgdat_span(struct pglist_data *pgdat,
pgdat->node_spanned_pages = 0;
}

-static void __remove_zone(struct zone *zone, unsigned long start_pfn)
+static void __remove_zone(struct zone *zone, unsigned long start_pfn,
+ unsigned long nr_pages)
{
struct pglist_data *pgdat = zone->zone_pgdat;
- int nr_pages = PAGES_PER_SECTION;
unsigned long flags;

pgdat_resize_lock(zone->zone_pgdat, &flags);
@@ -506,29 +533,26 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn)
pgdat_resize_unlock(zone->zone_pgdat, &flags);
}

-static void __remove_section(struct zone *zone, struct mem_section *ms,
- unsigned long map_offset,
- struct vmem_altmap *altmap)
+static void __remove_section(struct zone *zone, unsigned long pfn,
+ unsigned long nr_pages, unsigned long map_offset,
+ struct vmem_altmap *altmap)
{
- unsigned long start_pfn;
- int scn_nr;
+ struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn));

if (WARN_ON_ONCE(!valid_section(ms)))
return;

unregister_memory_section(ms);

- scn_nr = __section_nr(ms);
- start_pfn = section_nr_to_pfn((unsigned long)scn_nr);
- __remove_zone(zone, start_pfn);
+ __remove_zone(zone, pfn, nr_pages);

- sparse_remove_one_section(zone, ms, map_offset, altmap);
+ sparse_remove_section(zone, ms, pfn, nr_pages, map_offset, altmap);
}

/**
* __remove_pages() - remove sections of pages from a zone
* @zone: zone from which pages need to be removed
- * @phys_start_pfn: starting pageframe (must be aligned to start of a section)
+ * @pfn: starting pageframe (must be aligned to start of a section)
* @nr_pages: number of pages to remove (must be multiple of section size)
* @altmap: alternative device page map or %NULL if default memmap is used
*
@@ -537,31 +561,39 @@ static void __remove_section(struct zone *zone, struct mem_section *ms,
* sure that pages are marked reserved and zones are adjust properly by
* calling offline_pages().
*/
-void __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
+void __remove_pages(struct zone *zone, unsigned long pfn,
unsigned long nr_pages, struct vmem_altmap *altmap)
{
- unsigned long i;
unsigned long map_offset = 0;
- int sections_to_remove;
+ int i, start_sec, end_sec;
+ struct memory_block *mem;
+ unsigned long flags = 0;

if (altmap)
map_offset = vmem_altmap_offset(altmap);

clear_zone_contiguous(zone);

- /*
- * We can only remove entire sections
- */
- BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
- BUG_ON(nr_pages % PAGES_PER_SECTION);
+ mem = find_memory_block(__pfn_to_section(pfn));
+ if (mem) {
+ flags |= MHP_MEMBLOCK_API;
+ put_device(&mem->dev);
+ }

- sections_to_remove = nr_pages / PAGES_PER_SECTION;
- for (i = 0; i < sections_to_remove; i++) {
- unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
+ if (subsection_check(pfn, nr_pages, flags, "remove"))
+ return;
+
+ start_sec = pfn_to_section_nr(pfn);
+ end_sec = pfn_to_section_nr(pfn + nr_pages - 1);
+ for (i = start_sec; i <= end_sec; i++) {
+ unsigned long pfns;

cond_resched();
- __remove_section(zone, __pfn_to_section(pfn), map_offset,
- altmap);
+ pfns = min(nr_pages, PAGES_PER_SECTION
+ - (pfn & ~PAGE_SECTION_MASK));
+ __remove_section(zone, pfn, pfns, map_offset, altmap);
+ pfn += pfns;
+ nr_pages -= pfns;
map_offset = 0;
}

diff --git a/mm/sparse.c b/mm/sparse.c
index ed26761327bf..198371e5fc87 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -756,8 +756,8 @@ static void free_map_bootmem(struct page *memmap)
* * -EEXIST - Section has been present.
* * -ENOMEM - Out of memory.
*/
-int __meminit sparse_add_one_section(int nid, unsigned long start_pfn,
- struct vmem_altmap *altmap)
+int __meminit sparse_add_section(int nid, unsigned long start_pfn,
+ unsigned long nr_pages, struct vmem_altmap *altmap)
{
unsigned long section_nr = pfn_to_section_nr(start_pfn);
struct mem_section_usage *usage;
@@ -866,7 +866,8 @@ static void free_section_usage(struct page *memmap,
free_map_bootmem(memmap);
}

-void sparse_remove_one_section(struct zone *zone, struct mem_section *ms,
+void sparse_remove_section(struct zone *zone, struct mem_section *ms,
+ unsigned long pfn, unsigned long nr_pages,
unsigned long map_offset, struct vmem_altmap *altmap)
{
struct page *memmap = NULL;