Re: [PATCH 5/9] powerpc/vmemmap: Add altmap support

[Balbir Singh]

On Wed, 2017-04-12 at 03:42 +1000, Oliver O'Halloran wrote:
> Adds support to powerpc for the altmap feature of ZONE_DEVICE memory. An
> altmap is a driver provided region that is used to provide the backing
> storage for the struct pages of ZONE_DEVICE memory. In situations where
> large amount of ZONE_DEVICE memory is being added to the system the
> altmap reduces pressure on main system memory by allowing the mm/
> metadata to be stored on the device itself rather in main memory.
> 
> Signed-off-by: Oliver O'Halloran 
> ---

Reviewed-by: Balbir Singh 

[PATCH 5/9] powerpc/vmemmap: Add altmap support

[Oliver O'Halloran]

Adds support to powerpc for the altmap feature of ZONE_DEVICE memory. An
altmap is a driver provided region that is used to provide the backing
storage for the struct pages of ZONE_DEVICE memory. In situations where
large amount of ZONE_DEVICE memory is being added to the system the
altmap reduces pressure on main system memory by allowing the mm/
metadata to be stored on the device itself rather in main memory.

Signed-off-by: Oliver O'Halloran 
---
 arch/powerpc/mm/init_64.c | 20 +++-
 arch/powerpc/mm/mem.c | 16 +---
 2 files changed, 28 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index f8124edb6ffa..225fbb8034e6 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -44,6 +44,7 @@
 #include 
 #include 
 #include 
+#include 
 
 #include 
 #include 
@@ -171,13 +172,17 @@ int __meminit vmemmap_populate(unsigned long start, 
unsigned long end, int node)
pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node);
 
for (; start < end; start += page_size) {
+   struct vmem_altmap *altmap;
void *p;
int rc;
 
if (vmemmap_populated(start, page_size))
continue;
 
-   p = vmemmap_alloc_block(page_size, node);
+   /* altmap lookups only work at section boundaries */
+   altmap = to_vmem_altmap(SECTION_ALIGN_DOWN(start));
+
+   p =  __vmemmap_alloc_block_buf(page_size, node, altmap);
if (!p)
return -ENOMEM;
 
@@ -241,9 +246,10 @@ void __ref vmemmap_free(unsigned long start, unsigned long 
end)
pr_debug("vmemmap_free %lx...%lx\n", start, end);
 
for (; start < end; start += page_size) {
-   struct page *page = pfn_to_page(addr >> PAGE_SHIFT);
-   unsigned int nr_pages;
-   unsigned long addr;
+   unsigned long nr_pages, addr;
+   struct vmem_altmap *altmap;
+   struct page *section_base;
+   struct page *page;
 
/*
 * the section has already be marked as invalid, so
@@ -258,9 +264,13 @@ void __ref vmemmap_free(unsigned long start, unsigned long 
end)
continue;
 
page = pfn_to_page(addr >> PAGE_SHIFT);
+   section_base = pfn_to_page(vmemmap_section_start(start));
nr_pages = 1 << page_order;
 
-   if (PageReserved(page)) {
+   altmap = to_vmem_altmap((unsigned long) section_base);
+   if (altmap) {
+   vmem_altmap_free(altmap, nr_pages);
+   } else if (PageReserved(page)) {
/* allocated from bootmem */
if (page_size < PAGE_SIZE) {
/*
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 3bbba178b464..6f7b64eaa9d8 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -36,6 +36,7 @@
 #include 
 #include 
 #include 
+#include 
 
 #include 
 #include 
@@ -176,7 +177,8 @@ int arch_remove_memory(u64 start, u64 size, enum 
memory_type type)
 {
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
-   struct zone *zone;
+   struct vmem_altmap *altmap;
+   struct page *page;
int ret;
 
/*
@@ -193,8 +195,16 @@ int arch_remove_memory(u64 start, u64 size, enum 
memory_type type)
return -EINVAL;
}
 
-   zone = page_zone(pfn_to_page(start_pfn));
-   ret = __remove_pages(zone, start_pfn, nr_pages);
+   /*
+* If we have an altmap then we need to skip over any reserved PFNs
+* when querying the zone.
+*/
+   page = pfn_to_page(start_pfn);
+   altmap = to_vmem_altmap((unsigned long) page);
+   if (altmap)
+   page += vmem_altmap_offset(altmap);
+
+   ret = __remove_pages(page_zone(page), start_pfn, nr_pages);
if (ret)
return ret;
 
-- 
2.9.3