x86: PAT use reserve free memtype in mmap of /dev/mem

Use reserve_memtype and free_memtype wrappers for /dev/mem mmaps. The memtype
is slightly complicated here, given that we have to support existing X mappings.
We fallback on UC_MINUS for that.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
venkatesh.pallipadi@intel.com 2008-03-18 17:00:21 -07:00 committed by Ingo Molnar
parent f0970c13b6
commit e7f260a276
2 changed files with 152 additions and 11 deletions

View File

@ -11,6 +11,7 @@
#include <linux/kernel.h>
#include <linux/gfp.h>
#include <linux/fs.h>
#include <linux/bootmem.h>
#include <asm/msr.h>
#include <asm/tlbflush.h>
@ -21,6 +22,7 @@
#include <asm/cacheflush.h>
#include <asm/fcntl.h>
#include <asm/mtrr.h>
#include <asm/io.h>
int pat_wc_enabled = 1;
@ -190,6 +192,21 @@ static int pat_x_mtrr_type(u64 start, u64 end, unsigned long prot,
return 0;
}
/*
* req_type typically has one of the:
* - _PAGE_CACHE_WB
* - _PAGE_CACHE_WC
* - _PAGE_CACHE_UC_MINUS
* - _PAGE_CACHE_UC
*
* req_type will have a special case value '-1', when requester want to inherit
* the memory type from mtrr (if WB), existing PAT, defaulting to UC_MINUS.
*
* If ret_type is NULL, function will return an error if it cannot reserve the
* region with req_type. If ret_type is non-null, function will return
* available type in ret_type in case of no error. In case of any error
* it will return a negative return value.
*/
int reserve_memtype(u64 start, u64 end, unsigned long req_type,
unsigned long *ret_type)
{
@ -200,9 +217,14 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
/* Only track when pat_wc_enabled */
if (!pat_wc_enabled) {
if (ret_type)
*ret_type = req_type;
/* This is identical to page table setting without PAT */
if (ret_type) {
if (req_type == -1) {
*ret_type = _PAGE_CACHE_WB;
} else {
*ret_type = req_type;
}
}
return 0;
}
@ -214,8 +236,29 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
return 0;
}
req_type &= _PAGE_CACHE_MASK;
err = pat_x_mtrr_type(start, end, req_type, &actual_type);
if (req_type == -1) {
/*
* Special case where caller wants to inherit from mtrr or
* existing pat mapping, defaulting to UC_MINUS in case of
* no match.
*/
u8 mtrr_type = mtrr_type_lookup(start, end);
if (mtrr_type == 0xFE) { /* MTRR match error */
err = -1;
}
if (mtrr_type == MTRR_TYPE_WRBACK) {
req_type = _PAGE_CACHE_WB;
actual_type = _PAGE_CACHE_WB;
} else {
req_type = _PAGE_CACHE_UC_MINUS;
actual_type = _PAGE_CACHE_UC_MINUS;
}
} else {
req_type &= _PAGE_CACHE_MASK;
err = pat_x_mtrr_type(start, end, req_type, &actual_type);
}
if (err) {
if (ret_type)
*ret_type = actual_type;
@ -420,7 +463,14 @@ int free_memtype(u64 start, u64 end)
}
/* /dev/mem interface. Use the previous mapping */
/*
* /dev/mem mmap interface. The memtype used for mapping varies:
* - Use UC for mappings with O_SYNC flag
* - Without O_SYNC flag, if there is any conflict in reserve_memtype,
* inherit the memtype from existing mapping.
* - Else use UC_MINUS memtype (for backward compatibility with existing
* X drivers.
*/
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
{
@ -430,10 +480,13 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t *vma_prot)
{
u64 offset = ((u64) pfn) << PAGE_SHIFT;
unsigned long flags = _PAGE_CACHE_UC_MINUS;
unsigned long ret_flags;
int retval;
if (file->f_flags & O_SYNC) {
*vma_prot = pgprot_noncached(*vma_prot);
return 1;
flags = _PAGE_CACHE_UC;
}
#ifdef CONFIG_X86_32
@ -451,10 +504,65 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
test_bit(X86_FEATURE_CYRIX_ARR, boot_cpu_data.x86_capability) ||
test_bit(X86_FEATURE_CENTAUR_MCR, boot_cpu_data.x86_capability)) &&
(pfn << PAGE_SHIFT) >= __pa(high_memory)) {
*vma_prot = pgprot_noncached(*vma_prot);
return 1;
flags = _PAGE_CACHE_UC;
}
#endif
/*
* With O_SYNC, we can only take UC mapping. Fail if we cannot.
* Without O_SYNC, we want to get
* - WB for WB-able memory and no other conflicting mappings
* - UC_MINUS for non-WB-able memory with no other conflicting mappings
* - Inherit from confliting mappings otherwise
*/
if (flags != _PAGE_CACHE_UC_MINUS) {
retval = reserve_memtype(offset, offset + size, flags, NULL);
} else {
retval = reserve_memtype(offset, offset + size, -1, &ret_flags);
}
if (retval < 0)
return 0;
flags = ret_flags;
if (pfn <= max_pfn_mapped &&
ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) {
free_memtype(offset, offset + size);
printk(KERN_DEBUG
"%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n",
current->comm, current->pid,
cattr_name(flags),
offset, offset + size);
return 0;
}
*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
flags);
return 1;
}
void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
{
u64 addr = (u64)pfn << PAGE_SHIFT;
unsigned long flags;
unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
reserve_memtype(addr, addr + size, want_flags, &flags);
if (flags != want_flags) {
printk(KERN_DEBUG
"%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n",
current->comm, current->pid,
cattr_name(want_flags),
addr, addr + size,
cattr_name(flags));
}
}
void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
{
u64 addr = (u64)pfn << PAGE_SHIFT;
free_memtype(addr, addr + size);
}

View File

@ -300,6 +300,35 @@ static inline int private_mapping_ok(struct vm_area_struct *vma)
}
#endif
void __attribute__((weak))
map_devmem(unsigned long pfn, unsigned long len, pgprot_t prot)
{
/* nothing. architectures can override. */
}
void __attribute__((weak))
unmap_devmem(unsigned long pfn, unsigned long len, pgprot_t prot)
{
/* nothing. architectures can override. */
}
static void mmap_mem_open(struct vm_area_struct *vma)
{
map_devmem(vma->vm_pgoff, vma->vm_end - vma->vm_start,
vma->vm_page_prot);
}
static void mmap_mem_close(struct vm_area_struct *vma)
{
unmap_devmem(vma->vm_pgoff, vma->vm_end - vma->vm_start,
vma->vm_page_prot);
}
static struct vm_operations_struct mmap_mem_ops = {
.open = mmap_mem_open,
.close = mmap_mem_close
};
static int mmap_mem(struct file * file, struct vm_area_struct * vma)
{
size_t size = vma->vm_end - vma->vm_start;
@ -321,13 +350,17 @@ static int mmap_mem(struct file * file, struct vm_area_struct * vma)
size,
vma->vm_page_prot);
vma->vm_ops = &mmap_mem_ops;
/* Remap-pfn-range will mark the range VM_IO and VM_RESERVED */
if (remap_pfn_range(vma,
vma->vm_start,
vma->vm_pgoff,
size,
vma->vm_page_prot))
vma->vm_page_prot)) {
unmap_devmem(vma->vm_pgoff, size, vma->vm_page_prot);
return -EAGAIN;
}
return 0;
}