Vishal Verma <vishal.l.verma@xxxxxxxxx> writes: > The MHP_MEMMAP_ON_MEMORY flag for hotplugged memory is restricted to > 'memblock_size' chunks of memory being added. Adding a larger span of > memory precludes memmap_on_memory semantics. > > For users of hotplug such as kmem, large amounts of memory might get > added from the CXL subsystem. In some cases, this amount may exceed the > available 'main memory' to store the memmap for the memory being added. > In this case, it is useful to have a way to place the memmap on the > memory being added, even if it means splitting the addition into > memblock-sized chunks. > > Change add_memory_resource() to loop over memblock-sized chunks of > memory if caller requested memmap_on_memory, and if other conditions for > it are met. Teach try_remove_memory() to also expect that a memory > range being removed might have been split up into memblock sized chunks, > and to loop through those as needed. > > This does preclude being able to use PUD mappings in the direct map; a > proposal to how this could be optimized in the future is laid out > here[1]. > > [1]: https://lore.kernel.org/linux-mm/b6753402-2de9-25b2-36e9-eacd49752b19@xxxxxxxxxx/ > > Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> > Cc: David Hildenbrand <david@xxxxxxxxxx> > Cc: Michal Hocko <mhocko@xxxxxxxx> > Cc: Oscar Salvador <osalvador@xxxxxxx> > Cc: Dan Williams <dan.j.williams@xxxxxxxxx> > Cc: Dave Jiang <dave.jiang@xxxxxxxxx> > Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx> > Cc: Huang Ying <ying.huang@xxxxxxxxx> > Suggested-by: David Hildenbrand <david@xxxxxxxxxx> > Reviewed-by: Dan Williams <dan.j.williams@xxxxxxxxx> > Signed-off-by: Vishal Verma <vishal.l.verma@xxxxxxxxx> > --- > mm/memory_hotplug.c | 214 ++++++++++++++++++++++++++++++++++++---------------- > 1 file changed, 148 insertions(+), 66 deletions(-) > > diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c > index 6be7de9efa55..83e5ec377aad 100644 > --- a/mm/memory_hotplug.c > +++ b/mm/memory_hotplug.c > @@ -1380,6 +1380,43 @@ static bool mhp_supports_memmap_on_memory(unsigned long size) > return arch_supports_memmap_on_memory(vmemmap_size); > } > > +static int add_memory_create_devices(int nid, struct memory_group *group, > + u64 start, u64 size, mhp_t mhp_flags) > +{ > + struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; > + struct vmem_altmap mhp_altmap = { > + .base_pfn = PHYS_PFN(start), > + .end_pfn = PHYS_PFN(start + size - 1), > + }; > + int ret; > + > + if ((mhp_flags & MHP_MEMMAP_ON_MEMORY)) { > + mhp_altmap.free = memory_block_memmap_on_memory_pages(); > + params.altmap = kmemdup(&mhp_altmap, sizeof(struct vmem_altmap), > + GFP_KERNEL); > + if (!params.altmap) > + return -ENOMEM; > + } > + > + /* call arch's memory hotadd */ > + ret = arch_add_memory(nid, start, size, ¶ms); > + if (ret < 0) > + goto error; > + > + /* create memory block devices after memory was added */ > + ret = create_memory_block_devices(start, size, params.altmap, group); > + if (ret) > + goto err_bdev; > + > + return 0; > + > +err_bdev: > + arch_remove_memory(start, size, NULL); > +error: > + kfree(params.altmap); > + return ret; > +} > + > /* > * NOTE: The caller must call lock_device_hotplug() to serialize hotplug > * and online/offline operations (triggered e.g. by sysfs). > @@ -1388,14 +1425,10 @@ static bool mhp_supports_memmap_on_memory(unsigned long size) > */ > int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) > { > - struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; > + unsigned long memblock_size = memory_block_size_bytes(); > enum memblock_flags memblock_flags = MEMBLOCK_NONE; > - struct vmem_altmap mhp_altmap = { > - .base_pfn = PHYS_PFN(res->start), > - .end_pfn = PHYS_PFN(res->end), > - }; > struct memory_group *group = NULL; > - u64 start, size; > + u64 start, size, cur_start; > bool new_node = false; > int ret; > > @@ -1436,28 +1469,21 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) > /* > * Self hosted memmap array > */ > - if (mhp_flags & MHP_MEMMAP_ON_MEMORY) { > - if (mhp_supports_memmap_on_memory(size)) { > - mhp_altmap.free = memory_block_memmap_on_memory_pages(); > - params.altmap = kmemdup(&mhp_altmap, > - sizeof(struct vmem_altmap), > - GFP_KERNEL); > - if (!params.altmap) > + if ((mhp_flags & MHP_MEMMAP_ON_MEMORY) && > + mhp_supports_memmap_on_memory(memblock_size)) { > + for (cur_start = start; cur_start < start + size; > + cur_start += memblock_size) { > + ret = add_memory_create_devices(nid, group, cur_start, > + memblock_size, > + mhp_flags); > + if (ret) > goto error; > } > - /* fallback to not using altmap */ > - } > - > - /* call arch's memory hotadd */ > - ret = arch_add_memory(nid, start, size, ¶ms); > - if (ret < 0) > - goto error_free; > - > - /* create memory block devices after memory was added */ > - ret = create_memory_block_devices(start, size, params.altmap, group); > - if (ret) { > - arch_remove_memory(start, size, NULL); > - goto error_free; > + } else { > + ret = add_memory_create_devices(nid, group, start, size, > + mhp_flags); IIUC, if (mhp_flags & MHP_MEMMAP_ON_MEMORY) == true and mhp_supports_memmap_on_memory(memblock_size) == false, we will go here and allocate params.altmap in add_memory_create_devices(). If so, it seems better to pass whether to create altmap instead of mhp_flags to add_memory_create_devices(). -- Best Regards, Huang, Ying > + if (ret) > + goto error; > } > > if (new_node) { [snip]
