On 01.05.19 21:18, Pavel Tatashin wrote:
> It is now allowed to use persistent memory like a regular RAM, but
> currently there is no way to remove this memory until machine is
> rebooted.
>
> This work expands the functionality to also allows hotremoving
> previously hotplugged persistent memory, and recover the device for use
> for other purposes.
>
> To hotremove persistent memory, the management software must first
> offline all memory blocks of dax region, and than unbind it from
> device-dax/kmem driver. So, operations should look like this:
>
> echo offline > echo offline > /sys/devices/system/memory/memoryN/state
> ...
> echo dax0.0 > /sys/bus/dax/drivers/kmem/unbind
>
> Note: if unbind is done without offlining memory beforehand, it won't be
> possible to do dax0.0 hotremove, and dax's memory is going to be part of
> System RAM until reboot.
>
> Signed-off-by: Pavel Tatashin <pasha.tatas...@soleen.com>
> ---
> drivers/dax/dax-private.h | 2 +
> drivers/dax/kmem.c | 99 +++++++++++++++++++++++++++++++++++++--
> 2 files changed, 97 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
> index a45612148ca0..999aaf3a29b3 100644
> --- a/drivers/dax/dax-private.h
> +++ b/drivers/dax/dax-private.h
> @@ -53,6 +53,7 @@ struct dax_region {
> * @pgmap - pgmap for memmap setup / lifetime (driver owned)
> * @ref: pgmap reference count (driver owned)
> * @cmp: @ref final put completion (driver owned)
> + * @dax_mem_res: physical address range of hotadded DAX memory
> */
> struct dev_dax {
> struct dax_region *region;
> @@ -62,6 +63,7 @@ struct dev_dax {
> struct dev_pagemap pgmap;
> struct percpu_ref ref;
> struct completion cmp;
> + struct resource *dax_kmem_res;
> };
>
> static inline struct dev_dax *to_dev_dax(struct device *dev)
> diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
> index 4c0131857133..72b868066026 100644
> --- a/drivers/dax/kmem.c
> +++ b/drivers/dax/kmem.c
> @@ -71,21 +71,112 @@ int dev_dax_kmem_probe(struct device *dev)
> kfree(new_res);
> return rc;
> }
> + dev_dax->dax_kmem_res = new_res;
>
> return 0;
> }
>
> +#ifdef CONFIG_MEMORY_HOTREMOVE
> +static int
> +check_devdax_mem_offlined_cb(struct memory_block *mem, void *arg)
> +{
> + /* Memory block device */
> + struct device *mem_dev = &mem->dev;
> + bool is_offline;
> +
> + device_lock(mem_dev);
> + is_offline = mem_dev->offline;
> + device_unlock(mem_dev);
> +
> + /*
> + * Check that device-dax's memory_blocks are offline. If a memory_block
> + * is not offline a warning is printed and an error is returned.
> + */
> + if (!is_offline) {
> + /* Dax device device */
> + struct device *dev = (struct device *)arg;
> + struct dev_dax *dev_dax = to_dev_dax(dev);
> + struct resource *res = &dev_dax->region->res;
> + unsigned long spfn = section_nr_to_pfn(mem->start_section_nr);
> + unsigned long epfn = section_nr_to_pfn(mem->end_section_nr) +
> + PAGES_PER_SECTION - 1;
> + phys_addr_t spa = spfn << PAGE_SHIFT;
> + phys_addr_t epa = epfn << PAGE_SHIFT;
> +
> + dev_err(dev,
> + "DAX region %pR cannot be hotremoved until the next
> reboot. Memory block [%pa-%pa] is not offline.\n",
> + res, &spa, &epa);
> +
> + return -EBUSY;
> + }
> +
> + return 0;
> +}
> +
> +static int dev_dax_kmem_remove(struct device *dev)
> +{
> + struct dev_dax *dev_dax = to_dev_dax(dev);
> + struct resource *res = dev_dax->dax_kmem_res;
> + resource_size_t kmem_start;
> + resource_size_t kmem_size;
> + unsigned long start_pfn;
> + unsigned long end_pfn;
> + int rc;
> +
> + kmem_start = res->start;
> + kmem_size = resource_size(res);
> + start_pfn = kmem_start >> PAGE_SHIFT;
> + end_pfn = start_pfn + (kmem_size >> PAGE_SHIFT) - 1;
> +
> + /*
> + * Keep hotplug lock while checking memory state, and also required
> + * during __remove_memory() call. Admin can't change memory state via
> + * sysfs while this lock is kept.
> + */
> + lock_device_hotplug();
> +
> + /*
> + * Walk and check that every singe memory_block of dax region is
> + * offline. Hotremove can succeed only when every memory_block is
> + * offlined beforehand.
> + */
> + rc = walk_memory_range(start_pfn, end_pfn, dev,
> + check_devdax_mem_offlined_cb);
> +
> + /*
> + * If admin has not offlined memory beforehand, we cannot hotremove dax.
> + * Unfortunately, because unbind will still succeed there is no way for
> + * user to hotremove dax after this.
> + */
> + if (rc) {
> + unlock_device_hotplug();
> + return rc;
> + }
> +
> + /* Hotremove memory, cannot fail because memory is already offlined */
> + __remove_memory(dev_dax->target_node, kmem_start, kmem_size);
> + unlock_device_hotplug();
> +
> + /* Release and free dax resources */
> + release_resource(res);
> + kfree(res);
> + dev_dax->dax_kmem_res = NULL;
> +
> + return 0;
> +}
> +#else
> static int dev_dax_kmem_remove(struct device *dev)
> {
> /*
> - * Purposely leak the request_mem_region() for the device-dax
> - * range and return '0' to ->remove() attempts. The removal of
> - * the device from the driver always succeeds, but the region
> - * is permanently pinned as reserved by the unreleased
> + * Without hotremove purposely leak the request_mem_region() for the
> + * device-dax range and return '0' to ->remove() attempts. The removal
> + * of the device from the driver always succeeds, but the region is
> + * permanently pinned as reserved by the unreleased
> * request_mem_region().
> */
> return 0;
> }
> +#endif /* CONFIG_MEMORY_HOTREMOVE */
>
> static struct dax_device_driver device_dax_kmem_driver = {
> .drv = {
>
Memory unplug bits
Reviewed-by: David Hildenbrand <da...@redhat.com>
--
Thanks,
David / dhildenb
_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm
