summaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
authorOscar Salvador <osalvador@suse.de>2021-05-04 18:39:33 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-05-05 11:27:26 -0700
commit8736cc2d002f14e90d2b33bc5bef1740f6275ba4 (patch)
tree39fdd41bcdd872eb11b528340bc28854e7c70619 /drivers
parent8ca559132a2d9b56732d35e2b947af96acb9b80b (diff)
drivers/base/memory: introduce memory_block_{online,offline}
Patch series "Allocate memmap from hotadded memory (per device)", v10. The primary goal of this patchset is to reduce memory overhead of the hot-added memory (at least for SPARSEMEM_VMEMMAP memory model). The current way we use to populate memmap (struct page array) has two main drawbacks: a) it consumes an additional memory until the hotadded memory itself is onlined and b) memmap might end up on a different numa node which is especially true for movable_node configuration. c) due to fragmentation we might end up populating memmap with base pages One way to mitigate all these issues is to simply allocate memmap array (which is the largest memory footprint of the physical memory hotplug) from the hot-added memory itself. SPARSEMEM_VMEMMAP memory model allows us to map any pfn range so the memory doesn't need to be online to be usable for the array. See patch 4 for more details. This feature is only usable when CONFIG_SPARSEMEM_VMEMMAP is set. [Overall design]: Implementation wise we reuse vmem_altmap infrastructure to override the default allocator used by vmemap_populate. memory_block structure gains a new field called nr_vmemmap_pages, which accounts for the number of vmemmap pages used by that memory_block. E.g: On x86_64, that is 512 vmemmap pages on small memory bloks and 4096 on large memory blocks (1GB) We also introduce new two functions: memory_block_{online,offline}. These functions take care of initializing/unitializing vmemmap pages prior to calling {online,offline}_pages, so the latter functions can remain totally untouched. More details can be found in the respective changelogs. This patch (of 8): This is a preparatory patch that introduces two new functions: memory_block_online() and memory_block_offline(). For now, these functions will only call online_pages() and offline_pages() respectively, but they will be later in charge of preparing the vmemmap pages, carrying out the initialization and proper accounting of such pages. Since memory_block struct contains all the information, pass this struct down the chain till the end functions. Link: https://lkml.kernel.org/r/20210421102701.25051-1-osalvador@suse.de Link: https://lkml.kernel.org/r/20210421102701.25051-2-osalvador@suse.de Signed-off-by: Oscar Salvador <osalvador@suse.de> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'drivers')
-rw-r--r--drivers/base/memory.c33
1 files changed, 21 insertions, 12 deletions
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index f35298425575..f209925a5d4e 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -169,30 +169,41 @@ int memory_notify(unsigned long val, void *v)
return blocking_notifier_call_chain(&memory_chain, val, v);
}
+static int memory_block_online(struct memory_block *mem)
+{
+ unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
+ unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
+
+ return online_pages(start_pfn, nr_pages, mem->online_type, mem->nid);
+}
+
+static int memory_block_offline(struct memory_block *mem)
+{
+ unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
+ unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
+
+ return offline_pages(start_pfn, nr_pages);
+}
+
/*
* MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is
* OK to have direct references to sparsemem variables in here.
*/
static int
-memory_block_action(unsigned long start_section_nr, unsigned long action,
- int online_type, int nid)
+memory_block_action(struct memory_block *mem, unsigned long action)
{
- unsigned long start_pfn;
- unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
int ret;
- start_pfn = section_nr_to_pfn(start_section_nr);
-
switch (action) {
case MEM_ONLINE:
- ret = online_pages(start_pfn, nr_pages, online_type, nid);
+ ret = memory_block_online(mem);
break;
case MEM_OFFLINE:
- ret = offline_pages(start_pfn, nr_pages);
+ ret = memory_block_offline(mem);
break;
default:
WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
- "%ld\n", __func__, start_section_nr, action, action);
+ "%ld\n", __func__, mem->start_section_nr, action, action);
ret = -EINVAL;
}
@@ -210,9 +221,7 @@ static int memory_block_change_state(struct memory_block *mem,
if (to_state == MEM_OFFLINE)
mem->state = MEM_GOING_OFFLINE;
- ret = memory_block_action(mem->start_section_nr, to_state,
- mem->online_type, mem->nid);
-
+ ret = memory_block_action(mem, to_state);
mem->state = ret ? from_state_req : to_state;
return ret;