[PATCH v6 00/12] mm: Sub-section memory hotplug support

From: Dan Williams
Date: Wed Apr 17 2019 - 14:52:45 EST


Changes since v5 [1]:

- Rebase on next-20190416 and the new 'struct mhp_restrictions'
infrastructure.

- Extend mhp_restrictions to the 'remove' case so the sub-section policy
can be clarified with respect to the memblock-api in a symmetric
manner with the 'add' case.

- Kill is_dev_zone() since cleanups have now made it moot

[1]: https://lwn.net/Articles/783808/

---

The memory hotplug section is an arbitrary / convenient unit for memory
hotplug. 'Section-size' units have bled into the user interface
('memblock' sysfs) and can not be changed without breaking existing
userspace. The section-size constraint, while mostly benign for typical
memory hotplug, has and continues to wreak havoc with 'device-memory'
use cases, persistent memory (pmem) in particular. Recall that pmem uses
devm_memremap_pages(), and subsequently arch_add_memory(), to allocate a
'struct page' memmap for pmem. However, it does not use the 'bottom
half' of memory hotplug, i.e. never marks pmem pages online and never
exposes the userspace memblock interface for pmem. This leaves an
opening to redress the section-size constraint.

To date, the libnvdimm subsystem has attempted to inject padding to
satisfy the internal constraints of arch_add_memory(). Beyond
complicating the code, leading to bugs [2], wasting memory, and limiting
configuration flexibility, the padding hack is broken when the platform
changes this physical memory alignment of pmem from one boot to the
next. Device failure (intermittent or permanent) and physical
reconfiguration are events that can cause the platform firmware to
change the physical placement of pmem on a subsequent boot, and device
failure is an everyday event in a data-center.

It turns out that sections are only a hard requirement of the
user-facing interface for memory hotplug and with a bit more
infrastructure sub-section arch_add_memory() support can be added for
kernel internal usages like devm_memremap_pages(). Here is an analysis
of the current design assumptions in the current code and how they are
addressed in the new implementation:

Current design assumptions:

- Sections that describe boot memory (early sections) are never
unplugged / removed.

- pfn_valid(), in the CONFIG_SPARSEMEM_VMEMMAP=y, case devolves to a
valid_section() check

- __add_pages() and helper routines assume all operations occur in
PAGES_PER_SECTION units.

- The memblock sysfs interface only comprehends full sections

New design assumptions:

- Sections are instrumented with a sub-section bitmask to track (on x86)
individual 2MB sub-divisions of a 128MB section.

- Partially populated early sections can be extended with additional
sub-sections, and those sub-sections can be removed with
arch_remove_memory(). With this in place we no longer lose usable memory
capacity to padding.

- pfn_valid() is updated to look deeper than valid_section() to also check the
active-sub-section mask. This indication is in the same cacheline as
the valid_section() so the performance impact is expected to be
negligible. So far the lkp robot has not reported any regressions.

- Outside of the core vmemmap population routines which are replaced,
other helper routines like shrink_{zone,pgdat}_span() are updated to
handle the smaller granularity. Core memory hotplug routines that deal
with online memory are not touched.

- The existing memblock sysfs user api guarantees / assumptions are
not touched since this capability is limited to !online
!memblock-sysfs-accessible sections.

Meanwhile the issue reports continue to roll in from users that do not
understand when and how the 128MB constraint will bite them. The current
implementation relied on being able to support at least one misaligned
namespace, but that immediately falls over on any moderately complex
namespace creation attempt. Beyond the initial problem of 'System RAM'
colliding with pmem, and the unsolvable problem of physical alignment
changes, Linux is now being exposed to platforms that collide pmem
ranges with other pmem ranges by default [3]. In short,
devm_memremap_pages() has pushed the venerable section-size constraint
past the breaking point, and the simplicity of section-aligned
arch_add_memory() is no longer tenable.

These patches are exposed to the kbuild robot on my libnvdimm-pending
branch [4], and a preview of the unit test for this functionality is
available on the 'subsection-pending' branch of ndctl [5].

[2]: https://lore.kernel.org/r/155000671719.348031.2347363160141119237.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
[3]: https://github.com/pmem/ndctl/issues/76
[4]: https://git.kernel.org/pub/scm/linux/kernel/git/djbw/nvdimm.git/log/?h=libnvdimm-pending
[5]: https://github.com/pmem/ndctl/commit/7c59b4867e1c

---

Dan Williams (12):
mm/sparsemem: Introduce struct mem_section_usage
mm/sparsemem: Introduce common definitions for the size and mask of a section
mm/sparsemem: Add helpers track active portions of a section at boot
mm/hotplug: Prepare shrink_{zone,pgdat}_span for sub-section removal
mm/sparsemem: Convert kmalloc_section_memmap() to populate_section_memmap()
mm/hotplug: Add mem-hotplug restrictions for remove_memory()
mm: Kill is_dev_zone() helper
mm/sparsemem: Prepare for sub-section ranges
mm/sparsemem: Support sub-section hotplug
mm/devm_memremap_pages: Enable sub-section remap
libnvdimm/pfn: Fix fsdax-mode namespace info-block zero-fields
libnvdimm/pfn: Stop padding pmem namespaces to section alignment


arch/ia64/mm/init.c | 4
arch/powerpc/mm/mem.c | 5 -
arch/s390/mm/init.c | 2
arch/sh/mm/init.c | 4
arch/x86/mm/init_32.c | 4
arch/x86/mm/init_64.c | 9 +
drivers/nvdimm/dax_devs.c | 2
drivers/nvdimm/pfn.h | 12 -
drivers/nvdimm/pfn_devs.c | 93 +++-------
include/linux/memory_hotplug.h | 12 +
include/linux/mm.h | 4
include/linux/mmzone.h | 72 ++++++--
kernel/memremap.c | 70 +++-----
mm/hmm.c | 2
mm/memory_hotplug.c | 148 +++++++++-------
mm/page_alloc.c | 8 +
mm/sparse-vmemmap.c | 21 ++
mm/sparse.c | 371 +++++++++++++++++++++++++++-------------
18 files changed, 503 insertions(+), 340 deletions(-)