mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
9b06860d7c
- Add support for region alignment configuration and enforcement to fix compatibility across architectures and PowerPC page size configurations. - Introduce 'zero_page_range' as a dax operation. This facilitates filesystem-dax operation without a block-device. - Introduce phys_to_target_node() to facilitate drivers that want to know resulting numa node if a given reserved address range was onlined. - Advertise a persistence-domain for of_pmem and papr_scm. The persistence domain indicates where cpu-store cycles need to reach in the platform-memory subsystem before the platform will consider them power-fail protected. - Promote numa_map_to_online_node() to a cross-kernel generic facility. - Save x86 numa information to allow for node-id lookups for reserved memory ranges, deploy that capability for the e820-pmem driver. - Pick up some miscellaneous minor fixes, that missed v5.6-final, including a some smatch reports in the ioctl path and some unit test compilation fixups. - Fixup some flexible-array declarations. -----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEEf41QbsdZzFdA8EfZHtKRamZ9iAIFAl6LtIAACgkQHtKRamZ9 iAIwRA/8CLVVuQpgHQ1tqK4h8CZPrISFXh7wy7uhocEU2xrDh6iGVnLztmoLRr2k 5f8T9lRzreSAwIVL5DbGqP1pFncqIt9VMnKsFlaPMBGCBNR+hURY0iBCNjIT+jiq BOzLd52MR2rqJxeXGTMUbWrBrbmuj4mZPdmGVuFFe7GFRpoaVpCgOo+296eWa/ot gIOFUTonZY7STYjNvDok0TXCmiCFuJb+P+y5ldfCPShHvZhTiaF53jircja8vAjO G5dt8ixBKUK0rXRc4SEQsQhAZNcAFHb6Gy5lg4C2QzhTF374xTc9usJZNWbIE9iM 5mipBYvjVuoY+XaCNZDkaRcJIy/jqB15O6l3QIWbZLGaK9m95YPp9LmkPFwd3JpO e3rO24ML471DxqB9iWIiJCNcBBocLOlnd6qAQTpppWDpGNbudwXvfsmKHmKIScSE x+IDCdscLmmm+WG2dLmLraWOVPu42xZFccoQCi4M3TTqfeB9pZ9XckFQ37zX62zG 5t+7Ek+t1W4QVt/JQYVKH03XT15sqUpVknvx0Hl4Y5TtbDOkFLkO8RN0/HyExDef 7iegS35kqTsM4EfZQ+9juKbI2JBAjHANcbj0V4dogqaRj6vr3akumBzUtuYqAofv qU3s9skmLsEemOJC+ns2PT8vl5dyIoeDfH0r2XvGWxYqolMqJpA= =sY4N -----END PGP SIGNATURE----- Merge tag 'libnvdimm-for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm Pull libnvdimm and dax updates from Dan Williams: "There were multiple touches outside of drivers/nvdimm/ this round to add cross arch compatibility to the devm_memremap_pages() interface, enhance numa information for persistent memory ranges, and add a zero_page_range() dax operation. This cycle I switched from the patchwork api to Konstantin's b4 script for collecting tags (from x86, PowerPC, filesystem, and device-mapper folks), and everything looks to have gone ok there. This has all appeared in -next with no reported issues. Summary: - Add support for region alignment configuration and enforcement to fix compatibility across architectures and PowerPC page size configurations. - Introduce 'zero_page_range' as a dax operation. This facilitates filesystem-dax operation without a block-device. - Introduce phys_to_target_node() to facilitate drivers that want to know resulting numa node if a given reserved address range was onlined. - Advertise a persistence-domain for of_pmem and papr_scm. The persistence domain indicates where cpu-store cycles need to reach in the platform-memory subsystem before the platform will consider them power-fail protected. - Promote numa_map_to_online_node() to a cross-kernel generic facility. - Save x86 numa information to allow for node-id lookups for reserved memory ranges, deploy that capability for the e820-pmem driver. - Pick up some miscellaneous minor fixes, that missed v5.6-final, including a some smatch reports in the ioctl path and some unit test compilation fixups. - Fixup some flexible-array declarations" * tag 'libnvdimm-for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (29 commits) dax: Move mandatory ->zero_page_range() check in alloc_dax() dax,iomap: Add helper dax_iomap_zero() to zero a range dax: Use new dax zero page method for zeroing a page dm,dax: Add dax zero_page_range operation s390,dcssblk,dax: Add dax zero_page_range operation to dcssblk driver dax, pmem: Add a dax operation zero_page_range pmem: Add functions for reading/writing page to/from pmem libnvdimm: Update persistence domain value for of_pmem and papr_scm device tools/test/nvdimm: Fix out of tree build libnvdimm/region: Fix build error libnvdimm/region: Replace zero-length array with flexible-array member libnvdimm/label: Replace zero-length array with flexible-array member ACPI: NFIT: Replace zero-length array with flexible-array member libnvdimm/region: Introduce an 'align' attribute libnvdimm/region: Introduce NDD_LABELING libnvdimm/namespace: Enforce memremap_compat_align() libnvdimm/pfn: Prevent raw mode fallback if pfn-infoblock valid libnvdimm: Out of bounds read in __nd_ioctl() acpi/nfit: improve bounds checking for 'func' mm/memremap_pages: Introduce memremap_compat_align() ...
186 lines
5.6 KiB
C
186 lines
5.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_MEMREMAP_H_
|
|
#define _LINUX_MEMREMAP_H_
|
|
#include <linux/ioport.h>
|
|
#include <linux/percpu-refcount.h>
|
|
|
|
struct resource;
|
|
struct device;
|
|
|
|
/**
|
|
* struct vmem_altmap - pre-allocated storage for vmemmap_populate
|
|
* @base_pfn: base of the entire dev_pagemap mapping
|
|
* @reserve: pages mapped, but reserved for driver use (relative to @base)
|
|
* @free: free pages set aside in the mapping for memmap storage
|
|
* @align: pages reserved to meet allocation alignments
|
|
* @alloc: track pages consumed, private to vmemmap_populate()
|
|
*/
|
|
struct vmem_altmap {
|
|
const unsigned long base_pfn;
|
|
const unsigned long end_pfn;
|
|
const unsigned long reserve;
|
|
unsigned long free;
|
|
unsigned long align;
|
|
unsigned long alloc;
|
|
};
|
|
|
|
/*
|
|
* Specialize ZONE_DEVICE memory into multiple types each having differents
|
|
* usage.
|
|
*
|
|
* MEMORY_DEVICE_PRIVATE:
|
|
* Device memory that is not directly addressable by the CPU: CPU can neither
|
|
* read nor write private memory. In this case, we do still have struct pages
|
|
* backing the device memory. Doing so simplifies the implementation, but it is
|
|
* important to remember that there are certain points at which the struct page
|
|
* must be treated as an opaque object, rather than a "normal" struct page.
|
|
*
|
|
* A more complete discussion of unaddressable memory may be found in
|
|
* include/linux/hmm.h and Documentation/vm/hmm.rst.
|
|
*
|
|
* MEMORY_DEVICE_FS_DAX:
|
|
* Host memory that has similar access semantics as System RAM i.e. DMA
|
|
* coherent and supports page pinning. In support of coordinating page
|
|
* pinning vs other operations MEMORY_DEVICE_FS_DAX arranges for a
|
|
* wakeup event whenever a page is unpinned and becomes idle. This
|
|
* wakeup is used to coordinate physical address space management (ex:
|
|
* fs truncate/hole punch) vs pinned pages (ex: device dma).
|
|
*
|
|
* MEMORY_DEVICE_DEVDAX:
|
|
* Host memory that has similar access semantics as System RAM i.e. DMA
|
|
* coherent and supports page pinning. In contrast to
|
|
* MEMORY_DEVICE_FS_DAX, this memory is access via a device-dax
|
|
* character device.
|
|
*
|
|
* MEMORY_DEVICE_PCI_P2PDMA:
|
|
* Device memory residing in a PCI BAR intended for use with Peer-to-Peer
|
|
* transactions.
|
|
*/
|
|
enum memory_type {
|
|
/* 0 is reserved to catch uninitialized type fields */
|
|
MEMORY_DEVICE_PRIVATE = 1,
|
|
MEMORY_DEVICE_FS_DAX,
|
|
MEMORY_DEVICE_DEVDAX,
|
|
MEMORY_DEVICE_PCI_P2PDMA,
|
|
};
|
|
|
|
struct dev_pagemap_ops {
|
|
/*
|
|
* Called once the page refcount reaches 1. (ZONE_DEVICE pages never
|
|
* reach 0 refcount unless there is a refcount bug. This allows the
|
|
* device driver to implement its own memory management.)
|
|
*/
|
|
void (*page_free)(struct page *page);
|
|
|
|
/*
|
|
* Transition the refcount in struct dev_pagemap to the dead state.
|
|
*/
|
|
void (*kill)(struct dev_pagemap *pgmap);
|
|
|
|
/*
|
|
* Wait for refcount in struct dev_pagemap to be idle and reap it.
|
|
*/
|
|
void (*cleanup)(struct dev_pagemap *pgmap);
|
|
|
|
/*
|
|
* Used for private (un-addressable) device memory only. Must migrate
|
|
* the page back to a CPU accessible page.
|
|
*/
|
|
vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf);
|
|
};
|
|
|
|
#define PGMAP_ALTMAP_VALID (1 << 0)
|
|
|
|
/**
|
|
* struct dev_pagemap - metadata for ZONE_DEVICE mappings
|
|
* @altmap: pre-allocated/reserved memory for vmemmap allocations
|
|
* @res: physical address range covered by @ref
|
|
* @ref: reference count that pins the devm_memremap_pages() mapping
|
|
* @internal_ref: internal reference if @ref is not provided by the caller
|
|
* @done: completion for @internal_ref
|
|
* @type: memory type: see MEMORY_* in memory_hotplug.h
|
|
* @flags: PGMAP_* flags to specify defailed behavior
|
|
* @ops: method table
|
|
* @owner: an opaque pointer identifying the entity that manages this
|
|
* instance. Used by various helpers to make sure that no
|
|
* foreign ZONE_DEVICE memory is accessed.
|
|
*/
|
|
struct dev_pagemap {
|
|
struct vmem_altmap altmap;
|
|
struct resource res;
|
|
struct percpu_ref *ref;
|
|
struct percpu_ref internal_ref;
|
|
struct completion done;
|
|
enum memory_type type;
|
|
unsigned int flags;
|
|
const struct dev_pagemap_ops *ops;
|
|
void *owner;
|
|
};
|
|
|
|
static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap)
|
|
{
|
|
if (pgmap->flags & PGMAP_ALTMAP_VALID)
|
|
return &pgmap->altmap;
|
|
return NULL;
|
|
}
|
|
|
|
#ifdef CONFIG_ZONE_DEVICE
|
|
void *memremap_pages(struct dev_pagemap *pgmap, int nid);
|
|
void memunmap_pages(struct dev_pagemap *pgmap);
|
|
void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
|
|
void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap);
|
|
struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
|
|
struct dev_pagemap *pgmap);
|
|
|
|
unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
|
|
void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
|
|
unsigned long memremap_compat_align(void);
|
|
#else
|
|
static inline void *devm_memremap_pages(struct device *dev,
|
|
struct dev_pagemap *pgmap)
|
|
{
|
|
/*
|
|
* Fail attempts to call devm_memremap_pages() without
|
|
* ZONE_DEVICE support enabled, this requires callers to fall
|
|
* back to plain devm_memremap() based on config
|
|
*/
|
|
WARN_ON_ONCE(1);
|
|
return ERR_PTR(-ENXIO);
|
|
}
|
|
|
|
static inline void devm_memunmap_pages(struct device *dev,
|
|
struct dev_pagemap *pgmap)
|
|
{
|
|
}
|
|
|
|
static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
|
|
struct dev_pagemap *pgmap)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void vmem_altmap_free(struct vmem_altmap *altmap,
|
|
unsigned long nr_pfns)
|
|
{
|
|
}
|
|
|
|
/* when memremap_pages() is disabled all archs can remap a single page */
|
|
static inline unsigned long memremap_compat_align(void)
|
|
{
|
|
return PAGE_SIZE;
|
|
}
|
|
#endif /* CONFIG_ZONE_DEVICE */
|
|
|
|
static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
|
|
{
|
|
if (pgmap)
|
|
percpu_ref_put(pgmap->ref);
|
|
}
|
|
|
|
#endif /* _LINUX_MEMREMAP_H_ */
|