linux-stable/include/linux/memremap.h
Dan Williams b7b3c01b19 mm/memremap_pages: support multiple ranges per invocation
In support of device-dax growing the ability to front physically
dis-contiguous ranges of memory, update devm_memremap_pages() to track
multiple ranges with a single reference counter and devm instance.

Convert all [devm_]memremap_pages() users to specify the number of ranges
they are mapping in their 'struct dev_pagemap' instance.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: "Jérôme Glisse" <jglisse@redhat.co
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brice Goglin <Brice.Goglin@inria.fr>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Hulk Robot <hulkci@huawei.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Jason Yan <yanaijie@huawei.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: "Jérôme Glisse" <jglisse@redhat.com>
Cc: Jia He <justin.he@arm.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: kernel test robot <lkp@intel.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Wei Yang <richard.weiyang@linux.alibaba.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lkml.kernel.org/r/159643103789.4062302.18426128170217903785.stgit@dwillia2-desk3.amr.corp.intel.com
Link: https://lkml.kernel.org/r/160106116293.30709.13350662794915396198.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-10-13 18:38:28 -07:00

191 lines
5.8 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);
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_ */