resources: add io-mapping functions to dynamically map large device apertures
Impact: add new generic io_map_*() APIs Graphics devices have large PCI apertures which would consume a significant fraction of a 32-bit address space if mapped during driver initialization. Using ioremap at runtime is impractical as it is too slow. This new set of interfaces uses atomic mappings on 32-bit processors and a large static mapping on 64-bit processors to provide reasonable 32-bit performance and optimal 64-bit performance. The current implementation sits atop the io_map_atomic fixmap-based mechanism for 32-bit processors. This includes some editorial suggestions from Randy Dunlap for Documentation/io-mapping.txt Signed-off-by: Keith Packard <keithp@keithp.com> Signed-off-by: Eric Anholt <eric@anholt.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
parent
fd94093435
commit
9663f2e6a6
2 changed files with 194 additions and 0 deletions
76
Documentation/io-mapping.txt
Normal file
76
Documentation/io-mapping.txt
Normal file
|
@ -0,0 +1,76 @@
|
|||
The io_mapping functions in linux/io-mapping.h provide an abstraction for
|
||||
efficiently mapping small regions of an I/O device to the CPU. The initial
|
||||
usage is to support the large graphics aperture on 32-bit processors where
|
||||
ioremap_wc cannot be used to statically map the entire aperture to the CPU
|
||||
as it would consume too much of the kernel address space.
|
||||
|
||||
A mapping object is created during driver initialization using
|
||||
|
||||
struct io_mapping *io_mapping_create_wc(unsigned long base,
|
||||
unsigned long size)
|
||||
|
||||
'base' is the bus address of the region to be made
|
||||
mappable, while 'size' indicates how large a mapping region to
|
||||
enable. Both are in bytes.
|
||||
|
||||
This _wc variant provides a mapping which may only be used
|
||||
with the io_mapping_map_atomic_wc or io_mapping_map_wc.
|
||||
|
||||
With this mapping object, individual pages can be mapped either atomically
|
||||
or not, depending on the necessary scheduling environment. Of course, atomic
|
||||
maps are more efficient:
|
||||
|
||||
void *io_mapping_map_atomic_wc(struct io_mapping *mapping,
|
||||
unsigned long offset)
|
||||
|
||||
'offset' is the offset within the defined mapping region.
|
||||
Accessing addresses beyond the region specified in the
|
||||
creation function yields undefined results. Using an offset
|
||||
which is not page aligned yields an undefined result. The
|
||||
return value points to a single page in CPU address space.
|
||||
|
||||
This _wc variant returns a write-combining map to the
|
||||
page and may only be used with mappings created by
|
||||
io_mapping_create_wc
|
||||
|
||||
Note that the task may not sleep while holding this page
|
||||
mapped.
|
||||
|
||||
void io_mapping_unmap_atomic(void *vaddr)
|
||||
|
||||
'vaddr' must be the the value returned by the last
|
||||
io_mapping_map_atomic_wc call. This unmaps the specified
|
||||
page and allows the task to sleep once again.
|
||||
|
||||
If you need to sleep while holding the lock, you can use the non-atomic
|
||||
variant, although they may be significantly slower.
|
||||
|
||||
void *io_mapping_map_wc(struct io_mapping *mapping,
|
||||
unsigned long offset)
|
||||
|
||||
This works like io_mapping_map_atomic_wc except it allows
|
||||
the task to sleep while holding the page mapped.
|
||||
|
||||
void io_mapping_unmap(void *vaddr)
|
||||
|
||||
This works like io_mapping_unmap_atomic, except it is used
|
||||
for pages mapped with io_mapping_map_wc.
|
||||
|
||||
At driver close time, the io_mapping object must be freed:
|
||||
|
||||
void io_mapping_free(struct io_mapping *mapping)
|
||||
|
||||
Current Implementation:
|
||||
|
||||
The initial implementation of these functions uses existing mapping
|
||||
mechanisms and so provides only an abstraction layer and no new
|
||||
functionality.
|
||||
|
||||
On 64-bit processors, io_mapping_create_wc calls ioremap_wc for the whole
|
||||
range, creating a permanent kernel-visible mapping to the resource. The
|
||||
map_atomic and map functions add the requested offset to the base of the
|
||||
virtual address returned by ioremap_wc.
|
||||
|
||||
On 32-bit processors, io_mapping_map_atomic_wc uses io_map_atomic_prot_pfn,
|
||||
which uses the fixmaps to get us a mapping to a page using an atomic fashion.
|
||||
For io_mapping_map_wc, ioremap_wc() is used to get a mapping of the region.
|
118
include/linux/io-mapping.h
Normal file
118
include/linux/io-mapping.h
Normal file
|
@ -0,0 +1,118 @@
|
|||
/*
|
||||
* Copyright © 2008 Keith Packard <keithp@keithp.com>
|
||||
*
|
||||
* This file is free software; you can redistribute it and/or modify
|
||||
* it under the terms of version 2 of the GNU General Public License
|
||||
* as published by the Free Software Foundation.
|
||||
*
|
||||
* This program is distributed in the hope that it will be useful,
|
||||
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
* GNU General Public License for more details.
|
||||
*
|
||||
* You should have received a copy of the GNU General Public License
|
||||
* along with this program; if not, write to the Free Software Foundation,
|
||||
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
|
||||
*/
|
||||
|
||||
#ifndef _LINUX_IO_MAPPING_H
|
||||
#define _LINUX_IO_MAPPING_H
|
||||
|
||||
#include <linux/types.h>
|
||||
#include <asm/io.h>
|
||||
#include <asm/page.h>
|
||||
#include <asm/iomap.h>
|
||||
|
||||
/*
|
||||
* The io_mapping mechanism provides an abstraction for mapping
|
||||
* individual pages from an io device to the CPU in an efficient fashion.
|
||||
*
|
||||
* See Documentation/io_mapping.txt
|
||||
*/
|
||||
|
||||
/* this struct isn't actually defined anywhere */
|
||||
struct io_mapping;
|
||||
|
||||
#ifdef CONFIG_X86_64
|
||||
|
||||
/* Create the io_mapping object*/
|
||||
static inline struct io_mapping *
|
||||
io_mapping_create_wc(unsigned long base, unsigned long size)
|
||||
{
|
||||
return (struct io_mapping *) ioremap_wc(base, size);
|
||||
}
|
||||
|
||||
static inline void
|
||||
io_mapping_free(struct io_mapping *mapping)
|
||||
{
|
||||
iounmap(mapping);
|
||||
}
|
||||
|
||||
/* Atomic map/unmap */
|
||||
static inline void *
|
||||
io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset)
|
||||
{
|
||||
return ((char *) mapping) + offset;
|
||||
}
|
||||
|
||||
static inline void
|
||||
io_mapping_unmap_atomic(void *vaddr)
|
||||
{
|
||||
}
|
||||
|
||||
/* Non-atomic map/unmap */
|
||||
static inline void *
|
||||
io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset)
|
||||
{
|
||||
return ((char *) mapping) + offset;
|
||||
}
|
||||
|
||||
static inline void
|
||||
io_mapping_unmap(void *vaddr)
|
||||
{
|
||||
}
|
||||
|
||||
#endif /* CONFIG_X86_64 */
|
||||
|
||||
#ifdef CONFIG_X86_32
|
||||
static inline struct io_mapping *
|
||||
io_mapping_create_wc(unsigned long base, unsigned long size)
|
||||
{
|
||||
return (struct io_mapping *) base;
|
||||
}
|
||||
|
||||
static inline void
|
||||
io_mapping_free(struct io_mapping *mapping)
|
||||
{
|
||||
}
|
||||
|
||||
/* Atomic map/unmap */
|
||||
static inline void *
|
||||
io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset)
|
||||
{
|
||||
offset += (unsigned long) mapping;
|
||||
return iomap_atomic_prot_pfn(offset >> PAGE_SHIFT, KM_USER0,
|
||||
__pgprot(__PAGE_KERNEL_WC));
|
||||
}
|
||||
|
||||
static inline void
|
||||
io_mapping_unmap_atomic(void *vaddr)
|
||||
{
|
||||
iounmap_atomic(vaddr, KM_USER0);
|
||||
}
|
||||
|
||||
static inline void *
|
||||
io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset)
|
||||
{
|
||||
offset += (unsigned long) mapping;
|
||||
return ioremap_wc(offset, PAGE_SIZE);
|
||||
}
|
||||
|
||||
static inline void
|
||||
io_mapping_unmap(void *vaddr)
|
||||
{
|
||||
iounmap(vaddr);
|
||||
}
|
||||
#endif /* CONFIG_X86_32 */
|
||||
|
||||
#endif /* _LINUX_IO_MAPPING_H */
|
Loading…
Reference in a new issue