Re: [PATCH v7 05/12] mm/sparsemem: Convert kmalloc_section_memmap() to populate_section_memmap()
On Wed, May 01, 2019 at 10:55:48PM -0700, Dan Williams wrote:
> 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.
>
> Cc: Michal Hocko
> Cc: David Hildenbrand
> Cc: Logan Gunthorpe
> Signed-off-by: Dan Williams
> ---
> 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(-)
>
> diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
> index 20d14254b686..bb018d09d2dc 100644
> --- a/arch/x86/mm/init_64.c
> +++ b/arch/x86/mm/init_64.c
> @@ -1457,7 +1457,9 @@ int __meminit vmemmap_populate(unsigned long start,
> unsigned long end, int node,
> {
> int err;
>
> - if (boot_cpu_has(X86_FEATURE_PSE))
> + if (end - start < PAGES_PER_SECTION * sizeof(struct page))
maybe just:
if (PHYS_PFN(end) - PHYS_PFN(start) < PAGES_PER_SECTION) ?
> + 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",
Although the following looks more clear to me:
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap)
{
int err;
bool partial_section = (PHYS_PFN(end) - PFN_PHYS(start)) <
PAGES_PER_SECTION;
if (partial_section || !boot_cpu_has(X86_FEATURE_PSE))
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",
__func__);
err = -ENOMEM;
}
if (!err)
sync_global_pgds(start, end - 1);
return err;
}
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 0e8834ac32b7..5360a0e4051d 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -2748,8 +2748,8 @@ const char * arch_vma_name(struct vm_area_struct *vma);
> 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);
> diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
> index 7fec05796796..dcb023aa23d1 100644
> --- a/mm/sparse-vmemmap.c
> +++ b/mm/sparse-vmemmap.c
> @@ -245,19 +245,26 @@ int __meminit vmemmap_populate_basepages(unsigned long
> start,
> 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
> + * SECTION_ACTIVE_SIZE as allocations are tracked in the
> + * 'map_active' bitmap of the section.
> + */
> + end = ALIGN(pfn + nr_pages, PHYS_PFN(SECTION_ACTIVE_SIZE));
I would use PAGES_PER_SUB_SECTION directly:
end = ALIGN(pfn + nr_pages, PAGES_PER_SUB_SECTION);
> + pfn &= PHYS_PFN(SECTION_ACTIVE_MASK);
pfn &= PAGE_SUB_SECTION_MASK ?
[...]
> -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;
> +
[PATCH v7 05/12] 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.
Cc: Michal Hocko
Cc: David Hildenbrand
Cc: Logan Gunthorpe
Signed-off-by: Dan Williams
---
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(-)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 20d14254b686..bb018d09d2dc 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1457,7 +1457,9 @@ int __meminit vmemmap_populate(unsigned long start,
unsigned long end, int node,
{
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",
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0e8834ac32b7..5360a0e4051d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2748,8 +2748,8 @@ const char * arch_vma_name(struct vm_area_struct *vma);
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);
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 7fec05796796..dcb023aa23d1 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -245,19 +245,26 @@ int __meminit vmemmap_populate_basepages(unsigned long
start,
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
+* SECTION_ACTIVE_SIZE as allocations are tracked in the
+* 'map_active' bitmap of the section.
+*/
+ end = ALIGN(pfn + nr_pages, PHYS_PFN(SECTION_ACTIVE_SIZE));
+ pfn &= PHYS_PFN(SECTION_ACTIVE_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);
}
diff --git a/mm/sparse.c b/mm/sparse.c
index 8d4f28e2c25e..ed26761327bf 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -452,8 +452,8 @@ static unsigned long __init section_map_size(void)
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);
@@ -534,10 +534,13 @@ static void __init sparse_init_nid(int nid, unsigned long
pnum_begin,
}
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);
@@ -637,17 +640,17 @@ void offline_mem_sections(unsigned long start_pfn,
unsigned long end_pfn)
#endif
#ifdef CONFIG_
