On Tue, May 07, 2019 at 08:38:00PM +0200, David Hildenbrand wrote:
>Only memory to be added to the buddy and to be onlined/offlined by
>user space using memory block devices needs (and should have!) memory
>block devices.
>
>Factor out creation of memory block devices Create all devices after
>arch_add_memory() succeeded. We can later drop the want_memblock parameter,
>because it is now effectively stale.
>
>Only after memory block devices have been added, memory can be onlined
>by user space. This implies, that memory is not visible to user space at
>all before arch_add_memory() succeeded.
>
>Cc: Greg Kroah-Hartman <gre...@linuxfoundation.org>
>Cc: "Rafael J. Wysocki" <raf...@kernel.org>
>Cc: David Hildenbrand <da...@redhat.com>
>Cc: "mike.tra...@hpe.com" <mike.tra...@hpe.com>
>Cc: Andrew Morton <a...@linux-foundation.org>
>Cc: Ingo Molnar <mi...@kernel.org>
>Cc: Andrew Banman <andrew.ban...@hpe.com>
>Cc: Oscar Salvador <osalva...@suse.de>
>Cc: Michal Hocko <mho...@suse.com>
>Cc: Pavel Tatashin <pasha.tatas...@soleen.com>
>Cc: Qian Cai <c...@lca.pw>
>Cc: Wei Yang <richard.weiy...@gmail.com>
>Cc: Arun KS <aru...@codeaurora.org>
>Cc: Mathieu Malaterre <ma...@debian.org>
>Signed-off-by: David Hildenbrand <da...@redhat.com>
>---
> drivers/base/memory.c | 70 ++++++++++++++++++++++++++----------------
> include/linux/memory.h | 2 +-
> mm/memory_hotplug.c | 15 ++++-----
> 3 files changed, 53 insertions(+), 34 deletions(-)
>
>diff --git a/drivers/base/memory.c b/drivers/base/memory.c
>index 6e0cb4fda179..862c202a18ca 100644
>--- a/drivers/base/memory.c
>+++ b/drivers/base/memory.c
>@@ -701,44 +701,62 @@ static int add_memory_block(int base_section_nr)
> return 0;
> }
>
>+static void unregister_memory(struct memory_block *memory)
>+{
>+ BUG_ON(memory->dev.bus != &memory_subsys);
>+
>+ /* drop the ref. we got via find_memory_block() */
>+ put_device(&memory->dev);
>+ device_unregister(&memory->dev);
>+}
>+
> /*
>- * need an interface for the VM to add new memory regions,
>- * but without onlining it.
>+ * Create memory block devices for the given memory area. Start and size
>+ * have to be aligned to memory block granularity. Memory block devices
>+ * will be initialized as offline.
> */
>-int hotplug_memory_register(int nid, struct mem_section *section)
>+int hotplug_memory_register(unsigned long start, unsigned long size)
> {
>- int ret = 0;
>+ unsigned long block_nr_pages = memory_block_size_bytes() >> PAGE_SHIFT;
>+ unsigned long start_pfn = PFN_DOWN(start);
>+ unsigned long end_pfn = start_pfn + (size >> PAGE_SHIFT);
>+ unsigned long pfn;
> struct memory_block *mem;
>+ int ret = 0;
>
>- mutex_lock(&mem_sysfs_mutex);
>+ BUG_ON(!IS_ALIGNED(start, memory_block_size_bytes()));
>+ BUG_ON(!IS_ALIGNED(size, memory_block_size_bytes()));
>
>- mem = find_memory_block(section);
>- if (mem) {
>- mem->section_count++;
>- put_device(&mem->dev);
>- } else {
>- ret = init_memory_block(&mem, section, MEM_OFFLINE);
>+ mutex_lock(&mem_sysfs_mutex);
>+ for (pfn = start_pfn; pfn != end_pfn; pfn += block_nr_pages) {
>+ mem = find_memory_block(__pfn_to_section(pfn));
>+ if (mem) {
>+ WARN_ON_ONCE(false);
One question here, the purpose of WARN_ON_ONCE(false) is? Would we trigger
this?
>+ put_device(&mem->dev);
>+ continue;
>+ }
>+ ret = init_memory_block(&mem, __pfn_to_section(pfn),
>+ MEM_OFFLINE);
> if (ret)
>- goto out;
>- mem->section_count++;
>+ break;
>+ mem->section_count = memory_block_size_bytes() /
>+ MIN_MEMORY_BLOCK_SIZE;
Maybe we can leverage sections_per_block variable.
mem->section_count = sections_per_block;
>+ }
>+ if (ret) {
>+ end_pfn = pfn;
>+ for (pfn = start_pfn; pfn != end_pfn; pfn += block_nr_pages) {
>+ mem = find_memory_block(__pfn_to_section(pfn));
>+ if (!mem)
>+ continue;
>+ mem->section_count = 0;
>+ unregister_memory(mem);
>+ }
> }
--
Wei Yang
Help you, Help me
