From: Dan Williams <dan.j.williams@xxxxxxxxx> Subject: mm: document ZONE_DEVICE memory-model implications Explain the general mechanisms of 'ZONE_DEVICE' pages and list the users of 'devm_memremap_pages()'. [dan.j.williams@xxxxxxxxx: update ZONE_DEVICE memory model documentation] Link: http://lkml.kernel.org/r/156109575458.1409767.1885676287099277666.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Link: http://lkml.kernel.org/r/156092354985.979959.15763234410543451710.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx> Reported-by: Mike Rapoport <rppt@xxxxxxxxxxxxx> Reviewed-by: Mike Rapoport <rppt@xxxxxxxxxxxxx> Tested-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx> [ppc64] Cc: Jonathan Corbet <corbet@xxxxxxx> Cc: David Hildenbrand <david@xxxxxxxxxx> Cc: Jane Chu <jane.chu@xxxxxxxxxx> Cc: Jeff Moyer <jmoyer@xxxxxxxxxx> Cc: Jérôme Glisse <jglisse@xxxxxxxxxx> Cc: Logan Gunthorpe <logang@xxxxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxx> Cc: Oscar Salvador <osalvador@xxxxxxx> Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx> Cc: Toshi Kani <toshi.kani@xxxxxxx> Cc: Vlastimil Babka <vbabka@xxxxxxx> Cc: Wei Yang <richardw.yang@xxxxxxxxxxxxxxx> Cc: Jason Gunthorpe <jgg@xxxxxxxxxxxx> Cc: Christoph Hellwig <hch@xxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- Documentation/vm/memory-model.rst | 40 ++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) --- a/Documentation/vm/memory-model.rst~mm-document-zone_device-memory-model-implications +++ a/Documentation/vm/memory-model.rst @@ -181,3 +181,43 @@ that is eventually passed to vmemmap_pop of function calls. The vmemmap_populate() implementation may use the `vmem_altmap` along with :c:func:`altmap_alloc_block_buf` helper to allocate memory map on the persistent memory device. + +ZONE_DEVICE +=========== +The `ZONE_DEVICE` facility builds upon `SPARSEMEM_VMEMMAP` to offer +`struct page` `mem_map` services for device driver identified physical +address ranges. The "device" aspect of `ZONE_DEVICE` relates to the fact +that the page objects for these address ranges are never marked online, +and that a reference must be taken against the device, not just the page +to keep the memory pinned for active use. `ZONE_DEVICE`, via +:c:func:`devm_memremap_pages`, performs just enough memory hotplug to +turn on :c:func:`pfn_to_page`, :c:func:`page_to_pfn`, and +:c:func:`get_user_pages` service for the given range of pfns. Since the +page reference count never drops below 1 the page is never tracked as +free memory and the page's `struct list_head lru` space is repurposed +for back referencing to the host device / driver that mapped the memory. + +While `SPARSEMEM` presents memory as a collection of sections, +optionally collected into memory blocks, `ZONE_DEVICE` users have a need +for smaller granularity of populating the `mem_map`. Given that +`ZONE_DEVICE` memory is never marked online it is subsequently never +subject to its memory ranges being exposed through the sysfs memory +hotplug api on memory block boundaries. The implementation relies on +this lack of user-api constraint to allow sub-section sized memory +ranges to be specified to :c:func:`arch_add_memory`, the top-half of +memory hotplug. Sub-section support allows for 2MB as the cross-arch +common alignment granularity for :c:func:`devm_memremap_pages`. + +The users of `ZONE_DEVICE` are: + +* pmem: Map platform persistent memory to be used as a direct-I/O target + via DAX mappings. + +* hmm: Extend `ZONE_DEVICE` with `->page_fault()` and `->page_free()` + event callbacks to allow a device-driver to coordinate memory management + events related to device-memory, typically GPU memory. See + Documentation/vm/hmm.rst. + +* p2pdma: Create `struct page` objects to allow peer devices in a + PCI/-E topology to coordinate direct-DMA operations between themselves, + i.e. bypass host memory. _
