The patch titled
Subject: mm/sparsemem: convert kmalloc_section_memmap() to populate_section_memmap()
has been added to the -mm tree. Its filename is
mm-sparsemem-convert-kmalloc_section_memmap-to-populate_section_memmap.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-sparsemem-convert-kmalloc_section_memmap-to-populate_section_memmap.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-sparsemem-convert-kmalloc_section_memmap-to-populate_section_memmap.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Dan Williams <dan.j.williams@xxxxxxxxx>
Subject: mm/sparsemem: convert kmalloc_section_memmap() to populate_section_memmap()
Allow sub-section sized ranges to be added to the memmap.
populate_section_memmap() takes an explict pfn range rather than assuming
a full section, and those parameters are plumbed all the way through to
vmmemap_populate(). There should be no sub-section usage in current
deployments. New warnings are added to clarify which memmap allocation
paths are sub-section capable.
Link: http://lkml.kernel.org/r/155977189139.2443951.460884430946346998.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Reviewed-by: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Jane Chu <jane.chu@xxxxxxxxxx>
Cc: Jeff Moyer <jmoyer@xxxxxxxxxx>
Cc: Jérôme Glisse <jglisse@xxxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Mike Rapoport <rppt@xxxxxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Toshi Kani <toshi.kani@xxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/x86/mm/init_64.c | 4 +-
include/linux/mm.h | 4 +-
mm/sparse-vmemmap.c | 21 +++++++++----
mm/sparse.c | 61 ++++++++++++++++++++++++----------------
4 files changed, 57 insertions(+), 33 deletions(-)
--- a/arch/x86/mm/init_64.c~mm-sparsemem-convert-kmalloc_section_memmap-to-populate_section_memmap
+++ a/arch/x86/mm/init_64.c
@@ -1520,7 +1520,9 @@ int __meminit vmemmap_populate(unsigned
{
int err;
- if (boot_cpu_has(X86_FEATURE_PSE))
+ if (end - start < PAGES_PER_SECTION * sizeof(struct page))
+ err = vmemmap_populate_basepages(start, end, node);
+ else if (boot_cpu_has(X86_FEATURE_PSE))
err = vmemmap_populate_hugepages(start, end, node, altmap);
else if (altmap) {
pr_err_once("%s: no cpu support for altmap allocations\n",
--- a/include/linux/mm.h~mm-sparsemem-convert-kmalloc_section_memmap-to-populate_section_memmap
+++ a/include/linux/mm.h
@@ -2741,8 +2741,8 @@ const char * arch_vma_name(struct vm_are
void print_vma_addr(char *prefix, unsigned long rip);
void *sparse_buffer_alloc(unsigned long size);
-struct page *sparse_mem_map_populate(unsigned long pnum, int nid,
- struct vmem_altmap *altmap);
+struct page * __populate_section_memmap(unsigned long pfn,
+ unsigned long nr_pages, int nid, struct vmem_altmap *altmap);
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);
--- a/mm/sparse.c~mm-sparsemem-convert-kmalloc_section_memmap-to-populate_section_memmap
+++ a/mm/sparse.c
@@ -439,8 +439,8 @@ static unsigned long __init section_map_
return PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION);
}
-struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid,
- struct vmem_altmap *altmap)
+struct page __init *__populate_section_memmap(unsigned long pfn,
+ unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
{
unsigned long size = section_map_size();
struct page *map = sparse_buffer_alloc(size);
@@ -521,10 +521,13 @@ static void __init sparse_init_nid(int n
}
sparse_buffer_init(map_count * section_map_size(), nid);
for_each_present_section_nr(pnum_begin, pnum) {
+ unsigned long pfn = section_nr_to_pfn(pnum);
+
if (pnum >= pnum_end)
break;
- map = sparse_mem_map_populate(pnum, nid, NULL);
+ map = __populate_section_memmap(pfn, PAGES_PER_SECTION,
+ nid, NULL);
if (!map) {
pr_err("%s: node[%d] memory map backing failed. Some memory will not be available.",
__func__, nid);
@@ -624,17 +627,17 @@ void offline_mem_sections(unsigned long
#endif
#ifdef CONFIG_SPARSEMEM_VMEMMAP
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
- struct vmem_altmap *altmap)
+static struct page *populate_section_memmap(unsigned long pfn,
+ unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
{
- /* This will make the necessary allocations eventually. */
- return sparse_mem_map_populate(pnum, nid, altmap);
+ return __populate_section_memmap(pfn, nr_pages, nid, altmap);
}
-static void __kfree_section_memmap(struct page *memmap,
+
+static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
struct vmem_altmap *altmap)
{
- unsigned long start = (unsigned long)memmap;
- unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
+ unsigned long start = (unsigned long) pfn_to_page(pfn);
+ unsigned long end = start + nr_pages * sizeof(struct page);
vmemmap_free(start, end, altmap);
}
@@ -646,11 +649,18 @@ static void free_map_bootmem(struct page
vmemmap_free(start, end, NULL);
}
#else
-static struct page *__kmalloc_section_memmap(void)
+struct page *populate_section_memmap(unsigned long pfn,
+ unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
{
struct page *page, *ret;
unsigned long memmap_size = sizeof(struct page) * PAGES_PER_SECTION;
+ if ((pfn & ~PAGE_SECTION_MASK) || nr_pages != PAGES_PER_SECTION) {
+ WARN(1, "%s: called with section unaligned parameters\n",
+ __func__);
+ return NULL;
+ }
+
page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
if (page)
goto got_map_page;
@@ -667,15 +677,17 @@ got_map_ptr:
return ret;
}
-static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
+static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
struct vmem_altmap *altmap)
{
- return __kmalloc_section_memmap();
-}
+ struct page *memmap = pfn_to_page(pfn);
+
+ if ((pfn & ~PAGE_SECTION_MASK) || nr_pages != PAGES_PER_SECTION) {
+ WARN(1, "%s: called with section unaligned parameters\n",
+ __func__);
+ return;
+ }
-static void __kfree_section_memmap(struct page *memmap,
- struct vmem_altmap *altmap)
-{
if (is_vmalloc_addr(memmap))
vfree(memmap);
else
@@ -744,12 +756,13 @@ int __meminit sparse_add_one_section(int
if (ret < 0 && ret != -EEXIST)
return ret;
ret = 0;
- memmap = kmalloc_section_memmap(section_nr, nid, altmap);
+ 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) {
- __kfree_section_memmap(memmap, altmap);
+ depopulate_section_memmap(start_pfn, PAGES_PER_SECTION, altmap);
return -ENOMEM;
}
@@ -771,7 +784,7 @@ int __meminit sparse_add_one_section(int
out:
if (ret < 0) {
kfree(usage);
- __kfree_section_memmap(memmap, altmap);
+ depopulate_section_memmap(start_pfn, PAGES_PER_SECTION, altmap);
}
return ret;
}
@@ -807,7 +820,8 @@ static inline void clear_hwpoisoned_page
#endif
static void free_section_usage(struct page *memmap,
- struct mem_section_usage *usage, struct vmem_altmap *altmap)
+ struct mem_section_usage *usage, unsigned long pfn,
+ unsigned long nr_pages, struct vmem_altmap *altmap)
{
struct page *usage_page;
@@ -821,7 +835,7 @@ static void free_section_usage(struct pa
if (PageSlab(usage_page) || PageCompound(usage_page)) {
kfree(usage);
if (memmap)
- __kfree_section_memmap(memmap, altmap);
+ depopulate_section_memmap(pfn, nr_pages, altmap);
return;
}
@@ -850,6 +864,7 @@ void sparse_remove_one_section(struct me
clear_hwpoisoned_pages(memmap + map_offset,
PAGES_PER_SECTION - map_offset);
- free_section_usage(memmap, usage, altmap);
+ free_section_usage(memmap, usage, section_nr_to_pfn(__section_nr(ms)),
+ PAGES_PER_SECTION, altmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
--- a/mm/sparse-vmemmap.c~mm-sparsemem-convert-kmalloc_section_memmap-to-populate_section_memmap
+++ a/mm/sparse-vmemmap.c
@@ -245,19 +245,26 @@ int __meminit vmemmap_populate_basepages
return 0;
}
-struct page * __meminit sparse_mem_map_populate(unsigned long pnum, int nid,
- struct vmem_altmap *altmap)
+struct page * __meminit __populate_section_memmap(unsigned long pfn,
+ unsigned long nr_pages, int nid, struct vmem_altmap *altmap)
{
unsigned long start;
unsigned long end;
- struct page *map;
- map = pfn_to_page(pnum * PAGES_PER_SECTION);
- start = (unsigned long)map;
- end = (unsigned long)(map + PAGES_PER_SECTION);
+ /*
+ * The minimum granularity of memmap extensions is
+ * PAGES_PER_SUBSECTION as allocations are tracked in the
+ * 'subsection_map' bitmap of the section.
+ */
+ end = ALIGN(pfn + nr_pages, PAGES_PER_SUBSECTION);
+ pfn &= PAGE_SUBSECTION_MASK;
+ nr_pages = end - pfn;
+
+ start = (unsigned long) pfn_to_page(pfn);
+ end = start + nr_pages * sizeof(struct page);
if (vmemmap_populate(start, end, nid, altmap))
return NULL;
- return map;
+ return pfn_to_page(pfn);
}
_
Patches currently in -mm which might be from dan.j.williams@xxxxxxxxx are
mm-sparsemem-introduce-struct-mem_section_usage.patch
mm-sparsemem-add-helpers-track-active-portions-of-a-section-at-boot.patch
mm-hotplug-prepare-shrink_zone-pgdat_span-for-sub-section-removal.patch
mm-sparsemem-convert-kmalloc_section_memmap-to-populate_section_memmap.patch
mm-hotplug-kill-is_dev_zone-usage-in-__remove_pages.patch
mm-kill-is_dev_zone-helper.patch
mm-sparsemem-prepare-for-sub-section-ranges.patch
mm-sparsemem-support-sub-section-hotplug.patch
mm-document-zone_device-memory-model-implications.patch
mm-devm_memremap_pages-enable-sub-section-remap.patch
libnvdimm-pfn-fix-fsdax-mode-namespace-info-block-zero-fields.patch
libnvdimm-pfn-stop-padding-pmem-namespaces-to-section-alignment.patch
drivers-base-devres-introduce-devm_release_action.patch
mm-devm_memremap_pages-introduce-devm_memunmap_pages.patch
pci-p2pdma-fix-the-gen_pool_add_virt-failure-path.patch
lib-genalloc-introduce-chunk-owners.patch
pci-p2pdma-track-pgmap-references-per-resource-not-globally.patch
mm-devm_memremap_pages-fix-final-page-put-race.patch
