mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-27 19:29:37 +00:00
![Dan Williams](/assets/img/avatar_default.png)
Given 'struct dev_pagemap' spans both data pages and metadata pages be
careful to consult the altmap if present to delineate metadata. In fact
the pfn_first() helper already identifies the first valid data pfn, so
export that helper for other code paths via pgmap_pfn_valid().
Other usage of get_dev_pagemap() are not a concern because those are
operating on known data pfns having been looked up by get_user_pages().
I.e. metadata pfns are never user mapped.
Link: https://lkml.kernel.org/r/161058501758.1840162.4239831989762604527.stgit@dwillia2-desk3.amr.corp.intel.com
Fixes: 6100e34b25
("mm, memory_failure: Teach memory_failure() about dev_pagemap pages")
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reported-by: David Hildenbrand <david@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Qian Cai <cai@lca.pw>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
197 lines
6 KiB
C
197 lines
6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_MEMREMAP_H_
|
|
#define _LINUX_MEMREMAP_H_
|
|
#include <linux/range.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_GENERIC:
|
|
* Host memory that has similar access semantics as System RAM i.e. DMA
|
|
* coherent and supports page pinning. This is for example used by DAX devices
|
|
* that expose memory using a 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_GENERIC,
|
|
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
|
|
* @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.
|
|
* @nr_range: number of ranges to be mapped
|
|
* @range: range to be mapped when nr_range == 1
|
|
* @ranges: array of ranges to be mapped when nr_range > 1
|
|
*/
|
|
struct dev_pagemap {
|
|
struct vmem_altmap altmap;
|
|
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;
|
|
int nr_range;
|
|
union {
|
|
struct range range;
|
|
struct range ranges[0];
|
|
};
|
|
};
|
|
|
|
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);
|
|
bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn);
|
|
|
|
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 bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
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_ */
|