linux/arch/x86/mm/pat.c

841 lines
20 KiB
C
Raw Normal View History

/*
* Handle caching attributes in page tables (PAT)
*
* Authors: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
* Suresh B Siddha <suresh.b.siddha@intel.com>
*
* Loosely based on earlier PAT patchset from Eric Biederman and Andi Kleen.
*/
#include <linux/seq_file.h>
#include <linux/bootmem.h>
#include <linux/debugfs.h>
#include <linux/kernel.h>
#include <linux/module.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/rbtree.h>
#include <asm/cacheflush.h>
#include <asm/processor.h>
#include <asm/tlbflush.h>
#include <asm/x86_init.h>
#include <asm/pgtable.h>
#include <asm/fcntl.h>
#include <asm/e820.h>
#include <asm/mtrr.h>
#include <asm/page.h>
#include <asm/msr.h>
#include <asm/pat.h>
#include <asm/io.h>
#include "pat_internal.h"
#ifdef CONFIG_X86_PAT
int __read_mostly pat_enabled = 1;
static inline void pat_disable(const char *reason)
{
pat_enabled = 0;
printk(KERN_INFO "%s\n", reason);
}
static int __init nopat(char *str)
{
pat_disable("PAT support disabled.");
return 0;
}
early_param("nopat", nopat);
#else
static inline void pat_disable(const char *reason)
{
(void)reason;
}
#endif
int pat_debug_enable;
static int __init pat_debug_setup(char *str)
{
pat_debug_enable = 1;
return 0;
}
__setup("debugpat", pat_debug_setup);
static u64 __read_mostly boot_pat_state;
enum {
PAT_UC = 0, /* uncached */
PAT_WC = 1, /* Write combining */
PAT_WT = 4, /* Write Through */
PAT_WP = 5, /* Write Protected */
PAT_WB = 6, /* Write Back (default) */
PAT_UC_MINUS = 7, /* UC, but can be overriden by MTRR */
};
#define PAT(x, y) ((u64)PAT_ ## y << ((x)*8))
void pat_init(void)
{
u64 pat;
bool boot_cpu = !boot_pat_state;
if (!pat_enabled)
return;
if (!cpu_has_pat) {
if (!boot_pat_state) {
pat_disable("PAT not supported by CPU.");
return;
} else {
/*
* If this happens we are on a secondary CPU, but
* switched to PAT on the boot CPU. We have no way to
* undo PAT.
*/
printk(KERN_ERR "PAT enabled, "
"but not supported by secondary CPU\n");
BUG();
}
}
/* Set PWT to Write-Combining. All other bits stay the same */
/*
* PTE encoding used in Linux:
* PAT
* |PCD
* ||PWT
* |||
* 000 WB _PAGE_CACHE_WB
* 001 WC _PAGE_CACHE_WC
* 010 UC- _PAGE_CACHE_UC_MINUS
* 011 UC _PAGE_CACHE_UC
* PAT bit unused
*/
pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) |
PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
/* Boot CPU check */
if (!boot_pat_state)
rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);
wrmsrl(MSR_IA32_CR_PAT, pat);
if (boot_cpu)
printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n",
smp_processor_id(), boot_pat_state, pat);
}
#undef PAT
static DEFINE_SPINLOCK(memtype_lock); /* protects memtype accesses */
/*
* Does intersection of PAT memory type and MTRR memory type and returns
* the resulting memory type as PAT understands it.
* (Type in pat and mtrr will not have same value)
* The intersection is based on "Effective Memory Type" tables in IA-32
* SDM vol 3a
*/
static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
{
x86: fix Xorg crash with xf86MapVidMem error Clarify the usage of mtrr_lookup() in PAT code, and to make PAT code resilient to mtrr lookup problems. Specifically, pat_x_mtrr_type() is restructured to highlight, under what conditions we look for mtrr hint. pat_x_mtrr_type() uses a default type when there are any errors in mtrr lookup (still maintaining the pat consistency). And, reserve_memtype() highlights its usage ot mtrr_lookup for request type of '-1' and also defaults in a sane way on any mtrr lookup failure. pat.c looks at mtrr type of a range to get a hint on what mapping type to request when user/API: (1) hasn't specified any type (/dev/mem mapping) and we do not want to take performance hit by always mapping UC_MINUS. This will be the case for /dev/mem mappings used to map BIOS area or ACPI region which are WB'able. In this case, as long as MTRR is not WB, PAT will request UC_MINUS for such mappings. (2) user/API requests WB mapping while in reality MTRR may have UC or WC. In this case, PAT can map as WB (without checking MTRR) and still effective type will be UC or WC. But, a subsequent request to map same region as UC or WC may fail, as the region will get trackked as WB in PAT list. Looking at MTRR hint helps us to track based on effective type rather than what user requested. Again, here mtrr_lookup is only used as hint and we fallback to WB mapping (as requested by user) as default. In both cases, after using the mtrr hint, we still go through the memtype list to make sure there are no inconsistencies among multiple users. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Tested-by: Rufus & Azrael <rufus-azrael@numericable.fr> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-29 19:01:44 +00:00
/*
* Look for MTRR hint to get the effective type in case where PAT
* request is for WB.
*/
if (req_type == _PAGE_CACHE_WB) {
u8 mtrr_type;
mtrr_type = mtrr_type_lookup(start, end);
if (mtrr_type != MTRR_TYPE_WRBACK)
return _PAGE_CACHE_UC_MINUS;
return _PAGE_CACHE_WB;
}
return req_type;
}
struct pagerange_state {
unsigned long cur_pfn;
int ram;
int not_ram;
};
static int
pagerange_is_ram_callback(unsigned long initial_pfn, unsigned long total_nr_pages, void *arg)
{
struct pagerange_state *state = arg;
state->not_ram |= initial_pfn > state->cur_pfn;
state->ram |= total_nr_pages > 0;
state->cur_pfn = initial_pfn + total_nr_pages;
return state->ram && state->not_ram;
}
static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end)
{
int ret = 0;
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long end_pfn = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
struct pagerange_state state = {start_pfn, 0, 0};
/*
* For legacy reasons, physical address range in the legacy ISA
* region is tracked as non-RAM. This will allow users of
* /dev/mem to map portions of legacy ISA region, even when
* some of those portions are listed(or not even listed) with
* different e820 types(RAM/reserved/..)
*/
if (start_pfn < ISA_END_ADDRESS >> PAGE_SHIFT)
start_pfn = ISA_END_ADDRESS >> PAGE_SHIFT;
if (start_pfn < end_pfn) {
ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn,
&state, pagerange_is_ram_callback);
}
return (ret > 0) ? -1 : (state.ram ? 1 : 0);
}
/*
* For RAM pages, we use page flags to mark the pages with appropriate type.
* Here we do two pass:
* - Find the memtype of all the pages in the range, look for any conflicts
* - In case of no conflicts, set the new memtype for pages in the range
*/
static int reserve_ram_pages_type(u64 start, u64 end, unsigned long req_type,
unsigned long *new_type)
{
struct page *page;
u64 pfn;
if (req_type == _PAGE_CACHE_UC) {
/* We do not support strong UC */
WARN_ON_ONCE(1);
req_type = _PAGE_CACHE_UC_MINUS;
}
for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
unsigned long type;
page = pfn_to_page(pfn);
type = get_page_memtype(page);
if (type != -1) {
printk(KERN_INFO "reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%lx, req 0x%lx\n",
start, end - 1, type, req_type);
if (new_type)
*new_type = type;
return -EBUSY;
}
}
if (new_type)
*new_type = req_type;
for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
page = pfn_to_page(pfn);
set_page_memtype(page, req_type);
}
return 0;
}
static int free_ram_pages_type(u64 start, u64 end)
{
struct page *page;
u64 pfn;
for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
page = pfn_to_page(pfn);
set_page_memtype(page, -1);
}
return 0;
}
/*
* req_type typically has one of the:
* - _PAGE_CACHE_WB
* - _PAGE_CACHE_WC
* - _PAGE_CACHE_UC_MINUS
* - _PAGE_CACHE_UC
*
* If new_type is NULL, function will return an error if it cannot reserve the
* region with req_type. If new_type is non-NULL, function will return
* available type in new_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 *new_type)
{
struct memtype *new;
unsigned long actual_type;
int is_range_ram;
int err = 0;
BUG_ON(start >= end); /* end is exclusive */
if (!pat_enabled) {
/* This is identical to page table setting without PAT */
if (new_type) {
if (req_type == _PAGE_CACHE_WC)
*new_type = _PAGE_CACHE_UC_MINUS;
else
*new_type = req_type & _PAGE_CACHE_MASK;
}
return 0;
}
/* Low ISA region is always mapped WB in page table. No need to track */
if (x86_platform.is_untracked_pat_range(start, end)) {
if (new_type)
*new_type = _PAGE_CACHE_WB;
return 0;
}
/*
* Call mtrr_lookup to get the type hint. This is an
* optimization for /dev/mem mmap'ers into WB memory (BIOS
* tools and ACPI tools). Use WB request for WB memory and use
* UC_MINUS otherwise.
*/
actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK);
if (new_type)
*new_type = actual_type;
is_range_ram = pat_pagerange_is_ram(start, end);
if (is_range_ram == 1) {
err = reserve_ram_pages_type(start, end, req_type, new_type);
return err;
} else if (is_range_ram < 0) {
return -EINVAL;
}
new = kzalloc(sizeof(struct memtype), GFP_KERNEL);
if (!new)
return -ENOMEM;
new->start = start;
new->end = end;
new->type = actual_type;
spin_lock(&memtype_lock);
err = rbt_memtype_check_insert(new, new_type);
if (err) {
printk(KERN_INFO "reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
start, end - 1,
cattr_name(new->type), cattr_name(req_type));
kfree(new);
spin_unlock(&memtype_lock);
return err;
}
spin_unlock(&memtype_lock);
dprintk("reserve_memtype added [mem %#010Lx-%#010Lx], track %s, req %s, ret %s\n",
start, end - 1, cattr_name(new->type), cattr_name(req_type),
new_type ? cattr_name(*new_type) : "-");
return err;
}
int free_memtype(u64 start, u64 end)
{
int err = -EINVAL;
int is_range_ram;
struct memtype *entry;
if (!pat_enabled)
return 0;
/* Low ISA region is always mapped WB. No need to track */
if (x86_platform.is_untracked_pat_range(start, end))
return 0;
is_range_ram = pat_pagerange_is_ram(start, end);
if (is_range_ram == 1) {
err = free_ram_pages_type(start, end);
return err;
} else if (is_range_ram < 0) {
return -EINVAL;
}
spin_lock(&memtype_lock);
entry = rbt_memtype_erase(start, end);
spin_unlock(&memtype_lock);
if (!entry) {
printk(KERN_INFO "%s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
current->comm, current->pid, start, end - 1);
return -EINVAL;
}
kfree(entry);
dprintk("free_memtype request [mem %#010Lx-%#010Lx]\n", start, end - 1);
return 0;
}
/**
* lookup_memtype - Looksup the memory type for a physical address
* @paddr: physical address of which memory type needs to be looked up
*
* Only to be called when PAT is enabled
*
* Returns _PAGE_CACHE_WB, _PAGE_CACHE_WC, _PAGE_CACHE_UC_MINUS or
* _PAGE_CACHE_UC
*/
static unsigned long lookup_memtype(u64 paddr)
{
int rettype = _PAGE_CACHE_WB;
struct memtype *entry;
if (x86_platform.is_untracked_pat_range(paddr, paddr + PAGE_SIZE))
return rettype;
if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) {
struct page *page;
page = pfn_to_page(paddr >> PAGE_SHIFT);
rettype = get_page_memtype(page);
/*
* -1 from get_page_memtype() implies RAM page is in its
* default state and not reserved, and hence of type WB
*/
if (rettype == -1)
rettype = _PAGE_CACHE_WB;
return rettype;
}
spin_lock(&memtype_lock);
entry = rbt_memtype_lookup(paddr);
if (entry != NULL)
rettype = entry->type;
else
rettype = _PAGE_CACHE_UC_MINUS;
spin_unlock(&memtype_lock);
return rettype;
}
/**
* io_reserve_memtype - Request a memory type mapping for a region of memory
* @start: start (physical address) of the region
* @end: end (physical address) of the region
* @type: A pointer to memtype, with requested type. On success, requested
* or any other compatible type that was available for the region is returned
*
* On success, returns 0
* On failure, returns non-zero
*/
int io_reserve_memtype(resource_size_t start, resource_size_t end,
unsigned long *type)
{
resource_size_t size = end - start;
unsigned long req_type = *type;
unsigned long new_type;
int ret;
WARN_ON_ONCE(iomem_map_sanity_check(start, size));
ret = reserve_memtype(start, end, req_type, &new_type);
if (ret)
goto out_err;
if (!is_new_memtype_allowed(start, size, req_type, new_type))
goto out_free;
if (kernel_map_sync_memtype(start, size, new_type) < 0)
goto out_free;
*type = new_type;
return 0;
out_free:
free_memtype(start, end);
ret = -EBUSY;
out_err:
return ret;
}
/**
* io_free_memtype - Release a memory type mapping for a region of memory
* @start: start (physical address) of the region
* @end: end (physical address) of the region
*/
void io_free_memtype(resource_size_t start, resource_size_t end)
{
free_memtype(start, end);
}
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
{
return vma_prot;
}
#ifdef CONFIG_STRICT_DEVMEM
/* This check is done in drivers/char/mem.c in case of STRICT_DEVMEM*/
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
return 1;
}
#else
/* This check is needed to avoid cache aliasing when PAT is enabled */
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
u64 from = ((u64)pfn) << PAGE_SHIFT;
u64 to = from + size;
u64 cursor = from;
if (!pat_enabled)
return 1;
while (cursor < to) {
if (!devmem_is_allowed(pfn)) {
printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx]\n",
current->comm, from, to - 1);
return 0;
}
cursor += PAGE_SIZE;
pfn++;
}
return 1;
}
#endif /* CONFIG_STRICT_DEVMEM */
int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t *vma_prot)
{
unsigned long flags = _PAGE_CACHE_WB;
if (!range_is_allowed(pfn, size))
return 0;
vfs: Implement proper O_SYNC semantics While Linux provided an O_SYNC flag basically since day 1, it took until Linux 2.4.0-test12pre2 to actually get it implemented for filesystems, since that day we had generic_osync_around with only minor changes and the great "For now, when the user asks for O_SYNC, we'll actually give O_DSYNC" comment. This patch intends to actually give us real O_SYNC semantics in addition to the O_DSYNC semantics. After Jan's O_SYNC patches which are required before this patch it's actually surprisingly simple, we just need to figure out when to set the datasync flag to vfs_fsync_range and when not. This patch renames the existing O_SYNC flag to O_DSYNC while keeping it's numerical value to keep binary compatibility, and adds a new real O_SYNC flag. To guarantee backwards compatiblity it is defined as expanding to both the O_DSYNC and the new additional binary flag (__O_SYNC) to make sure we are backwards-compatible when compiled against the new headers. This also means that all places that don't care about the differences can just check O_DSYNC and get the right behaviour for O_SYNC, too - only places that actuall care need to check __O_SYNC in addition. Drivers and network filesystems have been updated in a fail safe way to always do the full sync magic if O_DSYNC is set. The few places setting O_SYNC for lower layers are kept that way for now to stay failsafe. We enforce that O_DSYNC is set when __O_SYNC is set early in the open path to make sure we always get these sane options. Note that parisc really screwed up their headers as they already define a O_DSYNC that has always been a no-op. We try to repair it by using it for the new O_DSYNC and redefinining O_SYNC to send both the traditional O_SYNC numerical value _and_ the O_DSYNC one. Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Grant Grundler <grundler@parisc-linux.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Andreas Dilger <adilger@sun.com> Acked-by: Trond Myklebust <Trond.Myklebust@netapp.com> Acked-by: Kyle McMartin <kyle@mcmartin.ca> Acked-by: Ulrich Drepper <drepper@redhat.com> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jan Kara <jack@suse.cz>
2009-10-27 10:05:28 +00:00
if (file->f_flags & O_DSYNC)
flags = _PAGE_CACHE_UC_MINUS;
#ifdef CONFIG_X86_32
/*
* On the PPro and successors, the MTRRs are used to set
* memory types for physical addresses outside main memory,
* so blindly setting UC or PWT on those pages is wrong.
* For Pentiums and earlier, the surround logic should disable
* caching for the high addresses through the KEN pin, but
* we maintain the tradition of paranoia in this code.
*/
if (!pat_enabled &&
!(boot_cpu_has(X86_FEATURE_MTRR) ||
boot_cpu_has(X86_FEATURE_K6_MTRR) ||
boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
(pfn << PAGE_SHIFT) >= __pa(high_memory)) {
flags = _PAGE_CACHE_UC;
}
#endif
*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
flags);
return 1;
}
/*
* Change the memory type for the physial address range in kernel identity
* mapping space if that range is a part of identity map.
*/
int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
{
unsigned long id_sz;
if (base >= __pa(high_memory))
return 0;
id_sz = (__pa(high_memory) < base + size) ?
__pa(high_memory) - base :
size;
if (ioremap_change_attr((unsigned long)__va(base), id_sz, flags) < 0) {
printk(KERN_INFO "%s:%d ioremap_change_attr failed %s "
"for [mem %#010Lx-%#010Lx]\n",
current->comm, current->pid,
cattr_name(flags),
base, (unsigned long long)(base + size-1));
return -EINVAL;
}
return 0;
}
/*
* Internal interface to reserve a range of physical memory with prot.
* Reserved non RAM regions only and after successful reserve_memtype,
* this func also keeps identity mapping (if any) in sync with this new prot.
*/
static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
int strict_prot)
{
int is_ram = 0;
int ret;
unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
unsigned long flags = want_flags;
is_ram = pat_pagerange_is_ram(paddr, paddr + size);
/*
* reserve_pfn_range() for RAM pages. We do not refcount to keep
* track of number of mappings of RAM pages. We can assert that
* the type requested matches the type of first page in the range.
*/
if (is_ram) {
if (!pat_enabled)
return 0;
flags = lookup_memtype(paddr);
if (want_flags != flags) {
printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
current->comm, current->pid,
cattr_name(want_flags),
(unsigned long long)paddr,
(unsigned long long)(paddr + size - 1),
cattr_name(flags));
*vma_prot = __pgprot((pgprot_val(*vma_prot) &
(~_PAGE_CACHE_MASK)) |
flags);
}
return 0;
}
ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
if (ret)
return ret;
if (flags != want_flags) {
if (strict_prot ||
!is_new_memtype_allowed(paddr, size, want_flags, flags)) {
free_memtype(paddr, paddr + size);
printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
" for [mem %#010Lx-%#010Lx], got %s\n",
current->comm, current->pid,
cattr_name(want_flags),
(unsigned long long)paddr,
(unsigned long long)(paddr + size - 1),
cattr_name(flags));
return -EINVAL;
}
/*
* We allow returning different type than the one requested in
* non strict case.
*/
*vma_prot = __pgprot((pgprot_val(*vma_prot) &
(~_PAGE_CACHE_MASK)) |
flags);
}
if (kernel_map_sync_memtype(paddr, size, flags) < 0) {
free_memtype(paddr, paddr + size);
return -EINVAL;
}
return 0;
}
/*
* Internal interface to free a range of physical memory.
* Frees non RAM regions only.
*/
static void free_pfn_range(u64 paddr, unsigned long size)
{
int is_ram;
is_ram = pat_pagerange_is_ram(paddr, paddr + size);
if (is_ram == 0)
free_memtype(paddr, paddr + size);
}
/*
* track_pfn_vma_copy is called when vma that is covering the pfnmap gets
* copied through copy_page_range().
*
* If the vma has a linear pfn mapping for the entire range, we get the prot
* from pte and reserve the entire vma range with single reserve_pfn_range call.
*/
int track_pfn_vma_copy(struct vm_area_struct *vma)
{
resource_size_t paddr;
unsigned long prot;
unsigned long vma_size = vma->vm_end - vma->vm_start;
pgprot_t pgprot;
if (is_linear_pfn_mapping(vma)) {
/*
* reserve the whole chunk covered by vma. We need the
* starting address and protection from pte.
*/
if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
WARN_ON_ONCE(1);
return -EINVAL;
}
pgprot = __pgprot(prot);
return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
}
return 0;
}
/*
* track_pfn_vma_new is called when a _new_ pfn mapping is being established
* for physical range indicated by pfn and size.
*
* prot is passed in as a parameter for the new mapping. If the vma has a
* linear pfn mapping for the entire range reserve the entire vma range with
* single reserve_pfn_range call.
*/
int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long size)
{
unsigned long flags;
resource_size_t paddr;
unsigned long vma_size = vma->vm_end - vma->vm_start;
if (is_linear_pfn_mapping(vma)) {
/* reserve the whole chunk starting from vm_pgoff */
paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
return reserve_pfn_range(paddr, vma_size, prot, 0);
}
if (!pat_enabled)
return 0;
/* for vm_insert_pfn and friends, we set prot based on lookup */
flags = lookup_memtype(pfn << PAGE_SHIFT);
*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
flags);
return 0;
}
/*
* untrack_pfn_vma is called while unmapping a pfnmap for a region.
* untrack can be called for a specific region indicated by pfn and size or
* can be for the entire vma (in which case size can be zero).
*/
void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
unsigned long size)
{
resource_size_t paddr;
unsigned long vma_size = vma->vm_end - vma->vm_start;
if (is_linear_pfn_mapping(vma)) {
/* free the whole chunk starting from vm_pgoff */
paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
free_pfn_range(paddr, vma_size);
return;
}
}
pgprot_t pgprot_writecombine(pgprot_t prot)
{
if (pat_enabled)
return __pgprot(pgprot_val(prot) | _PAGE_CACHE_WC);
else
return pgprot_noncached(prot);
}
EXPORT_SYMBOL_GPL(pgprot_writecombine);
#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
static struct memtype *memtype_get_idx(loff_t pos)
{
struct memtype *print_entry;
int ret;
print_entry = kzalloc(sizeof(struct memtype), GFP_KERNEL);
if (!print_entry)
return NULL;
spin_lock(&memtype_lock);
ret = rbt_memtype_copy_nth_element(print_entry, pos);
spin_unlock(&memtype_lock);
if (!ret) {
return print_entry;
} else {
kfree(print_entry);
return NULL;
}
}
static void *memtype_seq_start(struct seq_file *seq, loff_t *pos)
{
if (*pos == 0) {
++*pos;
seq_printf(seq, "PAT memtype list:\n");
}
return memtype_get_idx(*pos);
}
static void *memtype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
++*pos;
return memtype_get_idx(*pos);
}
static void memtype_seq_stop(struct seq_file *seq, void *v)
{
}
static int memtype_seq_show(struct seq_file *seq, void *v)
{
struct memtype *print_entry = (struct memtype *)v;
seq_printf(seq, "%s @ 0x%Lx-0x%Lx\n", cattr_name(print_entry->type),
print_entry->start, print_entry->end);
kfree(print_entry);
return 0;
}
static const struct seq_operations memtype_seq_ops = {
.start = memtype_seq_start,
.next = memtype_seq_next,
.stop = memtype_seq_stop,
.show = memtype_seq_show,
};
static int memtype_seq_open(struct inode *inode, struct file *file)
{
return seq_open(file, &memtype_seq_ops);
}
static const struct file_operations memtype_fops = {
.open = memtype_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static int __init pat_memtype_list_init(void)
{
if (pat_enabled) {
debugfs_create_file("pat_memtype_list", S_IRUSR,
arch_debugfs_dir, NULL, &memtype_fops);
}
return 0;
}
late_initcall(pat_memtype_list_init);
#endif /* CONFIG_DEBUG_FS && CONFIG_X86_PAT */