summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/memory_hotplug.c27
-rw-r--r--mm/page_alloc.c2
-rw-r--r--mm/sparse.c206
3 files changed, 140 insertions, 95 deletions
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 3fbb2cfab126..aafb71594ee3 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -252,18 +252,6 @@ 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 pfn,
- unsigned long nr_pages, struct vmem_altmap *altmap)
-{
- int ret;
-
- if (pfn_valid(pfn))
- return -EEXIST;
-
- ret = sparse_add_section(nid, pfn, nr_pages, altmap);
- return ret < 0 ? ret : 0;
-}
-
static int check_pfn_span(unsigned long pfn, unsigned long nr_pages,
const char *reason)
{
@@ -327,18 +315,11 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
pfns = min(nr_pages, PAGES_PER_SECTION
- (pfn & ~PAGE_SECTION_MASK));
- err = __add_section(nid, pfn, pfns, altmap);
+ err = sparse_add_section(nid, pfn, pfns, altmap);
+ if (err)
+ break;
pfn += pfns;
nr_pages -= pfns;
-
- /*
- * EEXIST is finally dealt with by ioresource collision
- * check. see add_memory() => register_memory_resource()
- * Warning will be printed if there is collision.
- */
- if (err && (err != -EEXIST))
- break;
- err = 0;
cond_resched();
}
vmemmap_populate_print_last();
@@ -541,7 +522,7 @@ static void __remove_section(struct zone *zone, unsigned long pfn,
return;
__remove_zone(zone, pfn, nr_pages);
- sparse_remove_one_section(ms, pfn, nr_pages, map_offset, altmap);
+ sparse_remove_section(ms, pfn, nr_pages, map_offset, altmap);
}
/**
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2c74367a8eba..272c6de1bf4e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5974,7 +5974,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
* pfn out of zone.
*
* Please note that MEMMAP_HOTPLUG path doesn't clear memmap
- * because this is done early in sparse_add_one_section
+ * because this is done early in section_activate()
*/
if (!(pfn & (pageblock_nr_pages - 1))) {
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
diff --git a/mm/sparse.c b/mm/sparse.c
index 41579b66fff1..a205a2ac66a4 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -83,8 +83,15 @@ static int __meminit sparse_index_init(unsigned long section_nr, int nid)
unsigned long root = SECTION_NR_TO_ROOT(section_nr);
struct mem_section *section;
+ /*
+ * An existing section is possible in the sub-section hotplug
+ * case. First hot-add instantiates, follow-on hot-add reuses
+ * the existing section.
+ *
+ * The mem_hotplug_lock resolves the apparent race below.
+ */
if (mem_section[root])
- return -EEXIST;
+ return 0;
section = sparse_index_alloc(nid);
if (!section)
@@ -715,10 +722,120 @@ static void free_map_bootmem(struct page *memmap)
}
#endif /* CONFIG_SPARSEMEM_VMEMMAP */
+static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
+ struct vmem_altmap *altmap)
+{
+ DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
+ DECLARE_BITMAP(tmp, SUBSECTIONS_PER_SECTION) = { 0 };
+ struct mem_section *ms = __pfn_to_section(pfn);
+ bool section_is_early = early_section(ms);
+ struct page *memmap = NULL;
+ unsigned long *subsection_map = ms->usage
+ ? &ms->usage->subsection_map[0] : NULL;
+
+ subsection_mask_set(map, pfn, nr_pages);
+ if (subsection_map)
+ bitmap_and(tmp, map, subsection_map, SUBSECTIONS_PER_SECTION);
+
+ if (WARN(!subsection_map || !bitmap_equal(tmp, map, SUBSECTIONS_PER_SECTION),
+ "section already deactivated (%#lx + %ld)\n",
+ pfn, nr_pages))
+ return;
+
+ /*
+ * There are 3 cases to handle across two configurations
+ * (SPARSEMEM_VMEMMAP={y,n}):
+ *
+ * 1/ deactivation of a partial hot-added section (only possible
+ * in the SPARSEMEM_VMEMMAP=y case).
+ * a/ section was present at memory init
+ * b/ section was hot-added post memory init
+ * 2/ deactivation of a complete hot-added section
+ * 3/ deactivation of a complete section from memory init
+ *
+ * For 1/, when subsection_map does not empty we will not be
+ * freeing the usage map, but still need to free the vmemmap
+ * range.
+ *
+ * For 2/ and 3/ the SPARSEMEM_VMEMMAP={y,n} cases are unified
+ */
+ bitmap_xor(subsection_map, map, subsection_map, SUBSECTIONS_PER_SECTION);
+ if (bitmap_empty(subsection_map, SUBSECTIONS_PER_SECTION)) {
+ unsigned long section_nr = pfn_to_section_nr(pfn);
+
+ if (!section_is_early) {
+ kfree(ms->usage);
+ ms->usage = NULL;
+ }
+ memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+ ms->section_mem_map = sparse_encode_mem_map(NULL, section_nr);
+ }
+
+ if (section_is_early && memmap)
+ free_map_bootmem(memmap);
+ else
+ depopulate_section_memmap(pfn, nr_pages, altmap);
+}
+
+static struct page * __meminit section_activate(int nid, unsigned long pfn,
+ unsigned long nr_pages, struct vmem_altmap *altmap)
+{
+ DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
+ struct mem_section *ms = __pfn_to_section(pfn);
+ struct mem_section_usage *usage = NULL;
+ unsigned long *subsection_map;
+ struct page *memmap;
+ int rc = 0;
+
+ subsection_mask_set(map, pfn, nr_pages);
+
+ if (!ms->usage) {
+ usage = kzalloc(mem_section_usage_size(), GFP_KERNEL);
+ if (!usage)
+ return ERR_PTR(-ENOMEM);
+ ms->usage = usage;
+ }
+ subsection_map = &ms->usage->subsection_map[0];
+
+ if (bitmap_empty(map, SUBSECTIONS_PER_SECTION))
+ rc = -EINVAL;
+ else if (bitmap_intersects(map, subsection_map, SUBSECTIONS_PER_SECTION))
+ rc = -EEXIST;
+ else
+ bitmap_or(subsection_map, map, subsection_map,
+ SUBSECTIONS_PER_SECTION);
+
+ if (rc) {
+ if (usage)
+ ms->usage = NULL;
+ kfree(usage);
+ return ERR_PTR(rc);
+ }
+
+ /*
+ * The early init code does not consider partially populated
+ * initial sections, it simply assumes that memory will never be
+ * referenced. If we hot-add memory into such a section then we
+ * do not need to populate the memmap and can simply reuse what
+ * is already there.
+ */
+ if (nr_pages < PAGES_PER_SECTION && early_section(ms))
+ return pfn_to_page(pfn);
+
+ memmap = populate_section_memmap(pfn, nr_pages, nid, altmap);
+ if (!memmap) {
+ section_deactivate(pfn, nr_pages, altmap);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ return memmap;
+}
+
/**
- * sparse_add_one_section - add a memory section
+ * sparse_add_section - add a memory section, or populate an existing one
* @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
*
* This is only intended for hotplug.
@@ -732,51 +849,34 @@ 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;
struct mem_section *ms;
struct page *memmap;
int ret;
- /*
- * no locking for this, because it does its own
- * plus, it does a kmalloc
- */
ret = sparse_index_init(section_nr, nid);
- if (ret < 0 && ret != -EEXIST)
+ if (ret < 0)
return ret;
- ret = 0;
- memmap = populate_section_memmap(start_pfn, PAGES_PER_SECTION, nid,
- altmap);
- if (!memmap)
- return -ENOMEM;
- usage = kzalloc(mem_section_usage_size(), GFP_KERNEL);
- if (!usage) {
- depopulate_section_memmap(start_pfn, PAGES_PER_SECTION, altmap);
- return -ENOMEM;
- }
- ms = __pfn_to_section(start_pfn);
- if (ms->section_mem_map & SECTION_MARKED_PRESENT) {
- ret = -EEXIST;
- goto out;
- }
+ memmap = section_activate(nid, start_pfn, nr_pages, altmap);
+ if (IS_ERR(memmap))
+ return PTR_ERR(memmap);
/*
* Poison uninitialized struct pages in order to catch invalid flags
* combinations.
*/
- page_init_poison(memmap, sizeof(struct page) * PAGES_PER_SECTION);
+ page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
+ ms = __pfn_to_section(start_pfn);
set_section_nid(section_nr, nid);
section_mark_present(ms);
- sparse_init_one_section(ms, section_nr, memmap, usage, 0);
-out:
- if (ret < 0) {
- kfree(usage);
- depopulate_section_memmap(start_pfn, PAGES_PER_SECTION, altmap);
- }
- return ret;
+ /* Align memmap to section boundary in the subsection case */
+ if (section_nr_to_pfn(section_nr) != start_pfn)
+ memmap = pfn_to_kaddr(section_nr_to_pfn(section_nr));
+ sparse_init_one_section(ms, section_nr, memmap, ms->usage, 0);
+
+ return 0;
}
#ifdef CONFIG_MEMORY_FAILURE
@@ -809,48 +909,12 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
}
#endif
-static void free_section_usage(struct mem_section *ms, struct page *memmap,
- struct mem_section_usage *usage, unsigned long pfn,
- unsigned long nr_pages, struct vmem_altmap *altmap)
-{
- if (!usage)
- return;
-
- /*
- * Check to see if allocation came from hot-plug-add
- */
- if (!early_section(ms)) {
- kfree(usage);
- if (memmap)
- depopulate_section_memmap(pfn, nr_pages, altmap);
- return;
- }
-
- /*
- * The usemap came from bootmem. This is packed with other usemaps
- * on the section which has pgdat at boot time. Just keep it as is now.
- */
-
- if (memmap)
- free_map_bootmem(memmap);
-}
-
-void sparse_remove_one_section(struct mem_section *ms, unsigned long pfn,
+void sparse_remove_section(struct mem_section *ms, unsigned long pfn,
unsigned long nr_pages, unsigned long map_offset,
struct vmem_altmap *altmap)
{
- struct page *memmap = NULL;
- struct mem_section_usage *usage = NULL;
-
- if (ms->section_mem_map) {
- usage = ms->usage;
- memmap = sparse_decode_mem_map(ms->section_mem_map,
- __section_nr(ms));
- ms->section_mem_map = 0;
- ms->usage = NULL;
- }
-
- clear_hwpoisoned_pages(memmap + map_offset, nr_pages - map_offset);
- free_section_usage(ms, memmap, usage, pfn, nr_pages, altmap);
+ clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset,
+ nr_pages - map_offset);
+ section_deactivate(pfn, nr_pages, altmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */