mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
8ef4227615
A recent change to the mm code in:
87744ab383
mm: fix cache mode tracking in vm_insert_mixed()
started enforcing checking the memory type against the registered list for
amixed pfn insertion mappings. It happens that the drm drivers for a number
of gpus relied on this being broken. Currently the driver only inserted
VRAM mappings into the tracking table when they came from the kernel,
and userspace mappings never landed in the table. This led to a regression
where all the mapping end up as UC instead of WC now.
I've considered a number of solutions but since this needs to be fixed
in fixes and not next, and some of the solutions were going to introduce
overhead that hadn't been there before I didn't consider them viable at
this stage. These mainly concerned hooking into the TTM io reserve APIs,
but these API have a bunch of fast paths I didn't want to unwind to add
this to.
The solution I've decided on is to add a new API like the arch_phys_wc
APIs (these would have worked but wc_del didn't take a range), and
use them from the drivers to add a WC compatible mapping to the table
for all VRAM on those GPUs. This means we can then create userspace
mapping that won't get degraded to UC.
v1.1: use CONFIG_X86_PAT + add some comments in io.h
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: x86@kernel.org
Cc: mcgrof@suse.com
Cc: Dan Williams <dan.j.williams@intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Dave Airlie <airlied@redhat.com>
167 lines
5.0 KiB
C
167 lines
5.0 KiB
C
/*
|
|
* Copyright 2006 PathScale, Inc. All Rights Reserved.
|
|
*
|
|
* 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_H
|
|
#define _LINUX_IO_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/init.h>
|
|
#include <linux/bug.h>
|
|
#include <linux/err.h>
|
|
#include <asm/io.h>
|
|
#include <asm/page.h>
|
|
|
|
struct device;
|
|
struct resource;
|
|
|
|
__visible void __iowrite32_copy(void __iomem *to, const void *from, size_t count);
|
|
void __ioread32_copy(void *to, const void __iomem *from, size_t count);
|
|
void __iowrite64_copy(void __iomem *to, const void *from, size_t count);
|
|
|
|
#ifdef CONFIG_MMU
|
|
int ioremap_page_range(unsigned long addr, unsigned long end,
|
|
phys_addr_t phys_addr, pgprot_t prot);
|
|
#else
|
|
static inline int ioremap_page_range(unsigned long addr, unsigned long end,
|
|
phys_addr_t phys_addr, pgprot_t prot)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
|
|
void __init ioremap_huge_init(void);
|
|
int arch_ioremap_pud_supported(void);
|
|
int arch_ioremap_pmd_supported(void);
|
|
#else
|
|
static inline void ioremap_huge_init(void) { }
|
|
#endif
|
|
|
|
/*
|
|
* Managed iomap interface
|
|
*/
|
|
#ifdef CONFIG_HAS_IOPORT_MAP
|
|
void __iomem * devm_ioport_map(struct device *dev, unsigned long port,
|
|
unsigned int nr);
|
|
void devm_ioport_unmap(struct device *dev, void __iomem *addr);
|
|
#else
|
|
static inline void __iomem *devm_ioport_map(struct device *dev,
|
|
unsigned long port,
|
|
unsigned int nr)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline void devm_ioport_unmap(struct device *dev, void __iomem *addr)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#define IOMEM_ERR_PTR(err) (__force void __iomem *)ERR_PTR(err)
|
|
|
|
void __iomem *devm_ioremap(struct device *dev, resource_size_t offset,
|
|
resource_size_t size);
|
|
void __iomem *devm_ioremap_nocache(struct device *dev, resource_size_t offset,
|
|
resource_size_t size);
|
|
void __iomem *devm_ioremap_wc(struct device *dev, resource_size_t offset,
|
|
resource_size_t size);
|
|
void devm_iounmap(struct device *dev, void __iomem *addr);
|
|
int check_signature(const volatile void __iomem *io_addr,
|
|
const unsigned char *signature, int length);
|
|
void devm_ioremap_release(struct device *dev, void *res);
|
|
|
|
void *devm_memremap(struct device *dev, resource_size_t offset,
|
|
size_t size, unsigned long flags);
|
|
void devm_memunmap(struct device *dev, void *addr);
|
|
|
|
void *__devm_memremap_pages(struct device *dev, struct resource *res);
|
|
|
|
/*
|
|
* Some systems do not have legacy ISA devices.
|
|
* /dev/port is not a valid interface on these systems.
|
|
* So for those archs, <asm/io.h> should define the following symbol.
|
|
*/
|
|
#ifndef arch_has_dev_port
|
|
#define arch_has_dev_port() (1)
|
|
#endif
|
|
|
|
/*
|
|
* Some systems (x86 without PAT) have a somewhat reliable way to mark a
|
|
* physical address range such that uncached mappings will actually
|
|
* end up write-combining. This facility should be used in conjunction
|
|
* with pgprot_writecombine, ioremap-wc, or set_memory_wc, since it has
|
|
* no effect if the per-page mechanisms are functional.
|
|
* (On x86 without PAT, these functions manipulate MTRRs.)
|
|
*
|
|
* arch_phys_del_wc(0) or arch_phys_del_wc(any error code) is guaranteed
|
|
* to have no effect.
|
|
*/
|
|
#ifndef arch_phys_wc_add
|
|
static inline int __must_check arch_phys_wc_add(unsigned long base,
|
|
unsigned long size)
|
|
{
|
|
return 0; /* It worked (i.e. did nothing). */
|
|
}
|
|
|
|
static inline void arch_phys_wc_del(int handle)
|
|
{
|
|
}
|
|
|
|
#define arch_phys_wc_add arch_phys_wc_add
|
|
#ifndef arch_phys_wc_index
|
|
static inline int arch_phys_wc_index(int handle)
|
|
{
|
|
return -1;
|
|
}
|
|
#define arch_phys_wc_index arch_phys_wc_index
|
|
#endif
|
|
#endif
|
|
|
|
enum {
|
|
/* See memremap() kernel-doc for usage description... */
|
|
MEMREMAP_WB = 1 << 0,
|
|
MEMREMAP_WT = 1 << 1,
|
|
MEMREMAP_WC = 1 << 2,
|
|
};
|
|
|
|
void *memremap(resource_size_t offset, size_t size, unsigned long flags);
|
|
void memunmap(void *addr);
|
|
|
|
/*
|
|
* On x86 PAT systems we have memory tracking that keeps track of
|
|
* the allowed mappings on memory ranges. This tracking works for
|
|
* all the in-kernel mapping APIs (ioremap*), but where the user
|
|
* wishes to map a range from a physical device into user memory
|
|
* the tracking won't be updated. This API is to be used by
|
|
* drivers which remap physical device pages into userspace,
|
|
* and wants to make sure they are mapped WC and not UC.
|
|
*/
|
|
#ifndef arch_io_reserve_memtype_wc
|
|
static inline int arch_io_reserve_memtype_wc(resource_size_t base,
|
|
resource_size_t size)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void arch_io_free_memtype_wc(resource_size_t base,
|
|
resource_size_t size)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#endif /* _LINUX_IO_H */
|