linux_old1/arch/x86/include/asm/pgtable.h

614 lines
18 KiB
C
Raw Normal View History

#ifndef _ASM_X86_PGTABLE_H
#define _ASM_X86_PGTABLE_H
#define FIRST_USER_ADDRESS 0
#define _PAGE_BIT_PRESENT 0 /* is present */
#define _PAGE_BIT_RW 1 /* writeable */
#define _PAGE_BIT_USER 2 /* userspace addressable */
#define _PAGE_BIT_PWT 3 /* page write through */
#define _PAGE_BIT_PCD 4 /* page cache disabled */
#define _PAGE_BIT_ACCESSED 5 /* was accessed (raised by CPU) */
#define _PAGE_BIT_DIRTY 6 /* was written to (raised by CPU) */
#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */
#define _PAGE_BIT_PAT 7 /* on 4KB pages */
#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
#define _PAGE_BIT_UNUSED1 9 /* available for programmer */
#define _PAGE_BIT_IOMAP 10 /* flag used to indicate IO mapping */
#define _PAGE_BIT_UNUSED3 11
#define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */
#define _PAGE_BIT_SPECIAL _PAGE_BIT_UNUSED1
#define _PAGE_BIT_CPA_TEST _PAGE_BIT_UNUSED1
#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */
/* If _PAGE_BIT_PRESENT is clear, we use these: */
/* - if the user mapped it with PROT_NONE; pte_present gives true */
#define _PAGE_BIT_PROTNONE _PAGE_BIT_GLOBAL
/* - set: nonlinear file mapping, saved PTE; unset:swap */
#define _PAGE_BIT_FILE _PAGE_BIT_DIRTY
#define _PAGE_PRESENT (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
#define _PAGE_RW (_AT(pteval_t, 1) << _PAGE_BIT_RW)
#define _PAGE_USER (_AT(pteval_t, 1) << _PAGE_BIT_USER)
#define _PAGE_PWT (_AT(pteval_t, 1) << _PAGE_BIT_PWT)
#define _PAGE_PCD (_AT(pteval_t, 1) << _PAGE_BIT_PCD)
#define _PAGE_ACCESSED (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
#define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
#define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE)
#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
#define _PAGE_UNUSED1 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
#define _PAGE_IOMAP (_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
#define _PAGE_UNUSED3 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3)
#define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT)
#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
#define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
#define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
#define __HAVE_ARCH_PTE_SPECIAL
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
#define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX)
#else
#define _PAGE_NX (_AT(pteval_t, 0))
#endif
#define _PAGE_FILE (_AT(pteval_t, 1) << _PAGE_BIT_FILE)
#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \
_PAGE_ACCESSED | _PAGE_DIRTY)
#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \
_PAGE_DIRTY)
/* Set of bits not changed in pte_modify */
#define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \
_PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY)
#define _PAGE_CACHE_MASK (_PAGE_PCD | _PAGE_PWT)
#define _PAGE_CACHE_WB (0)
#define _PAGE_CACHE_WC (_PAGE_PWT)
#define _PAGE_CACHE_UC_MINUS (_PAGE_PCD)
#define _PAGE_CACHE_UC (_PAGE_PCD | _PAGE_PWT)
#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \
_PAGE_ACCESSED | _PAGE_NX)
#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT | _PAGE_RW | \
_PAGE_USER | _PAGE_ACCESSED)
#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | \
_PAGE_ACCESSED | _PAGE_NX)
#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | \
_PAGE_ACCESSED)
#define PAGE_COPY PAGE_COPY_NOEXEC
#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | \
_PAGE_ACCESSED | _PAGE_NX)
#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | \
_PAGE_ACCESSED)
#define __PAGE_KERNEL_EXEC \
(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL)
#define __PAGE_KERNEL (__PAGE_KERNEL_EXEC | _PAGE_NX)
#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
#define __PAGE_KERNEL_EXEC_NOCACHE (__PAGE_KERNEL_EXEC | _PAGE_PCD | _PAGE_PWT)
#define __PAGE_KERNEL_WC (__PAGE_KERNEL | _PAGE_CACHE_WC)
#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
#define __PAGE_KERNEL_UC_MINUS (__PAGE_KERNEL | _PAGE_PCD)
#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX | _PAGE_USER)
#define __PAGE_KERNEL_VSYSCALL_NOCACHE (__PAGE_KERNEL_VSYSCALL | _PAGE_PCD | _PAGE_PWT)
#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE)
#define __PAGE_KERNEL_LARGE_NOCACHE (__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE)
#define __PAGE_KERNEL_IO (__PAGE_KERNEL | _PAGE_IOMAP)
#define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE | _PAGE_IOMAP)
#define __PAGE_KERNEL_IO_UC_MINUS (__PAGE_KERNEL_UC_MINUS | _PAGE_IOMAP)
#define __PAGE_KERNEL_IO_WC (__PAGE_KERNEL_WC | _PAGE_IOMAP)
#define PAGE_KERNEL __pgprot(__PAGE_KERNEL)
#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO)
#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC)
#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX)
#define PAGE_KERNEL_WC __pgprot(__PAGE_KERNEL_WC)
#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE)
#define PAGE_KERNEL_UC_MINUS __pgprot(__PAGE_KERNEL_UC_MINUS)
#define PAGE_KERNEL_EXEC_NOCACHE __pgprot(__PAGE_KERNEL_EXEC_NOCACHE)
#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE)
#define PAGE_KERNEL_LARGE_NOCACHE __pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC)
#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL)
#define PAGE_KERNEL_VSYSCALL_NOCACHE __pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)
#define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO)
#define PAGE_KERNEL_IO_NOCACHE __pgprot(__PAGE_KERNEL_IO_NOCACHE)
#define PAGE_KERNEL_IO_UC_MINUS __pgprot(__PAGE_KERNEL_IO_UC_MINUS)
#define PAGE_KERNEL_IO_WC __pgprot(__PAGE_KERNEL_IO_WC)
/* xwr */
#define __P000 PAGE_NONE
#define __P001 PAGE_READONLY
#define __P010 PAGE_COPY
#define __P011 PAGE_COPY
#define __P100 PAGE_READONLY_EXEC
#define __P101 PAGE_READONLY_EXEC
#define __P110 PAGE_COPY_EXEC
#define __P111 PAGE_COPY_EXEC
#define __S000 PAGE_NONE
#define __S001 PAGE_READONLY
#define __S010 PAGE_SHARED
#define __S011 PAGE_SHARED
#define __S100 PAGE_READONLY_EXEC
#define __S101 PAGE_READONLY_EXEC
#define __S110 PAGE_SHARED_EXEC
#define __S111 PAGE_SHARED_EXEC
/*
* early identity mapping pte attrib macros.
*/
#ifdef CONFIG_X86_64
#define __PAGE_KERNEL_IDENT_LARGE_EXEC __PAGE_KERNEL_LARGE_EXEC
#else
/*
* For PDE_IDENT_ATTR include USER bit. As the PDE and PTE protection
* bits are combined, this will alow user to access the high address mapped
* VDSO in the presence of CONFIG_COMPAT_VDSO
*/
#define PTE_IDENT_ATTR 0x003 /* PRESENT+RW */
#define PDE_IDENT_ATTR 0x067 /* PRESENT+RW+USER+DIRTY+ACCESSED */
#define PGD_IDENT_ATTR 0x001 /* PRESENT (no other attributes) */
#endif
/*
* Macro to mark a page protection value as UC-
*/
#define pgprot_noncached(prot) \
((boot_cpu_data.x86 > 3) \
? (__pgprot(pgprot_val(prot) | _PAGE_CACHE_UC_MINUS)) \
: (prot))
#ifndef __ASSEMBLY__
#define pgprot_writecombine pgprot_writecombine
extern pgprot_t pgprot_writecombine(pgprot_t prot);
/*
* ZERO_PAGE is a global shared page that is always zero: used
* for zero-mapped memory areas etc..
*/
extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
extern spinlock_t pgd_lock;
extern struct list_head pgd_list;
/*
* The following only work if pte_present() is true.
* Undefined behaviour if not..
*/
static inline int pte_dirty(pte_t pte)
{
return pte_flags(pte) & _PAGE_DIRTY;
}
static inline int pte_young(pte_t pte)
{
return pte_flags(pte) & _PAGE_ACCESSED;
}
static inline int pte_write(pte_t pte)
{
return pte_flags(pte) & _PAGE_RW;
}
static inline int pte_file(pte_t pte)
{
return pte_flags(pte) & _PAGE_FILE;
}
static inline int pte_huge(pte_t pte)
{
return pte_flags(pte) & _PAGE_PSE;
}
static inline int pte_global(pte_t pte)
{
return pte_flags(pte) & _PAGE_GLOBAL;
}
static inline int pte_exec(pte_t pte)
{
return !(pte_flags(pte) & _PAGE_NX);
}
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:13:00 +08:00
static inline int pte_special(pte_t pte)
{
return pte_flags(pte) & _PAGE_SPECIAL;
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:13:00 +08:00
}
static inline unsigned long pte_pfn(pte_t pte)
{
return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
}
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
static inline int pmd_large(pmd_t pte)
{
return (pmd_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
(_PAGE_PSE | _PAGE_PRESENT);
}
static inline pte_t pte_mkclean(pte_t pte)
{
return __pte(pte_val(pte) & ~_PAGE_DIRTY);
}
static inline pte_t pte_mkold(pte_t pte)
{
return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
}
static inline pte_t pte_wrprotect(pte_t pte)
{
return __pte(pte_val(pte) & ~_PAGE_RW);
}
static inline pte_t pte_mkexec(pte_t pte)
{
return __pte(pte_val(pte) & ~_PAGE_NX);
}
static inline pte_t pte_mkdirty(pte_t pte)
{
return __pte(pte_val(pte) | _PAGE_DIRTY);
}
static inline pte_t pte_mkyoung(pte_t pte)
{
return __pte(pte_val(pte) | _PAGE_ACCESSED);
}
static inline pte_t pte_mkwrite(pte_t pte)
{
return __pte(pte_val(pte) | _PAGE_RW);
}
static inline pte_t pte_mkhuge(pte_t pte)
{
return __pte(pte_val(pte) | _PAGE_PSE);
}
static inline pte_t pte_clrhuge(pte_t pte)
{
return __pte(pte_val(pte) & ~_PAGE_PSE);
}
static inline pte_t pte_mkglobal(pte_t pte)
{
return __pte(pte_val(pte) | _PAGE_GLOBAL);
}
static inline pte_t pte_clrglobal(pte_t pte)
{
return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
}
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:13:00 +08:00
static inline pte_t pte_mkspecial(pte_t pte)
{
return __pte(pte_val(pte) | _PAGE_SPECIAL);
mm: introduce pte_special pte bit s390 for one, cannot implement VM_MIXEDMAP with pfn_valid, due to their memory model (which is more dynamic than most). Instead, they had proposed to implement it with an additional path through vm_normal_page(), using a bit in the pte to determine whether or not the page should be refcounted: vm_normal_page() { ... if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { if (vma->vm_flags & VM_MIXEDMAP) { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; #else if (!pfn_valid(pfn)) return NULL; #endif goto out; } ... } This is fine, however if we are allowed to use a bit in the pte to determine refcountedness, we can use that to _completely_ replace all the vma based schemes. So instead of adding more cases to the already complex vma-based scheme, we can have a clearly seperate and simple pte-based scheme (and get slightly better code generation in the process): vm_normal_page() { #ifdef s390 if (!mixedmap_refcount_pte(pte)) return NULL; return pte_page(pte); #else ... #endif } And finally, we may rather make this concept usable by any architecture rather than making it s390 only, so implement a new type of pte state for this. Unfortunately the old vma based code must stay, because some architectures may not be able to spare pte bits. This makes vm_normal_page a little bit more ugly than we would like, but the 2 cases are clearly seperate. So introduce a pte_special pte state, and use it in mm/memory.c. It is currently a noop for all architectures, so this doesn't actually result in any compiled code changes to mm/memory.o. BTW: I haven't put vm_normal_page() into arch code as-per an earlier suggestion. The reason is that, regardless of where vm_normal_page is actually implemented, the *abstraction* is still exactly the same. Also, while it depends on whether the architecture has pte_special or not, that is the only two possible cases, and it really isn't an arch specific function -- the role of the arch code should be to provide primitive functions and accessors with which to build the core code; pte_special does that. We do not want architectures to know or care about vm_normal_page itself, and we definitely don't want them being able to invent something new there out of sight of mm/ code. If we made vm_normal_page an arch function, then we have to make vm_insert_mixed (next patch) an arch function too. So I don't think moving it to arch code fundamentally improves any abstractions, while it does practically make the code more difficult to follow, for both mm and arch developers, and easier to misuse. [akpm@linux-foundation.org: build fix] Signed-off-by: Nick Piggin <npiggin@suse.de> Acked-by: Carsten Otte <cotte@de.ibm.com> Cc: Jared Hulbert <jaredeh@gmail.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:13:00 +08:00
}
extern pteval_t __supported_pte_mask;
static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
{
return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) |
pgprot_val(pgprot)) & __supported_pte_mask);
}
static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
{
return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) |
pgprot_val(pgprot)) & __supported_pte_mask);
}
static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
pteval_t val = pte_val(pte);
/*
* Chop off the NX bit (if present), and add the NX portion of
* the newprot (if present):
*/
val &= _PAGE_CHG_MASK;
val |= pgprot_val(newprot) & (~_PAGE_CHG_MASK) & __supported_pte_mask;
return __pte(val);
}
/* mprotect needs to preserve PAT bits when updating vm_page_prot */
#define pgprot_modify pgprot_modify
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
{
pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK;
pgprotval_t addbits = pgprot_val(newprot);
return __pgprot(preservebits | addbits);
}
#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK)
#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
static inline int is_new_memtype_allowed(unsigned long flags,
unsigned long new_flags)
{
/*
* Certain new memtypes are not allowed with certain
* requested memtype:
* - request is uncached, return cannot be write-back
* - request is write-combine, return cannot be write-back
*/
if ((flags == _PAGE_CACHE_UC_MINUS &&
new_flags == _PAGE_CACHE_WB) ||
(flags == _PAGE_CACHE_WC &&
new_flags == _PAGE_CACHE_WB)) {
return 0;
}
return 1;
}
#ifndef __ASSEMBLY__
/* Indicate that x86 has its own track and untrack pfn vma functions */
#define __HAVE_PFNMAP_TRACKING
#define __HAVE_PHYS_MEM_ACCESS_PROT
struct file;
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot);
int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t *vma_prot);
#endif
/* Install a pte for a particular vaddr in kernel space. */
void set_pte_vaddr(unsigned long vaddr, pte_t pte);
#ifdef CONFIG_X86_32
extern void native_pagetable_setup_start(pgd_t *base);
extern void native_pagetable_setup_done(pgd_t *base);
#else
static inline void native_pagetable_setup_start(pgd_t *base) {}
static inline void native_pagetable_setup_done(pgd_t *base) {}
#endif
struct seq_file;
extern void arch_report_meminfo(struct seq_file *m);
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else /* !CONFIG_PARAVIRT */
#define set_pte(ptep, pte) native_set_pte(ptep, pte)
#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
#define set_pte_present(mm, addr, ptep, pte) \
native_set_pte_present(mm, addr, ptep, pte)
#define set_pte_atomic(ptep, pte) \
native_set_pte_atomic(ptep, pte)
#define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd)
#ifndef __PAGETABLE_PUD_FOLDED
#define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd)
#define pgd_clear(pgd) native_pgd_clear(pgd)
#endif
#ifndef set_pud
# define set_pud(pudp, pud) native_set_pud(pudp, pud)
#endif
#ifndef __PAGETABLE_PMD_FOLDED
#define pud_clear(pud) native_pud_clear(pud)
#endif
#define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep)
#define pmd_clear(pmd) native_pmd_clear(pmd)
#define pte_update(mm, addr, ptep) do { } while (0)
#define pte_update_defer(mm, addr, ptep) do { } while (0)
static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
{
native_pagetable_setup_start(base);
}
static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
{
native_pagetable_setup_done(base);
}
#endif /* CONFIG_PARAVIRT */
static inline int pte_none(pte_t pte)
{
return !pte.pte;
}
#define __HAVE_ARCH_PTE_SAME
static inline int pte_same(pte_t a, pte_t b)
{
return a.pte == b.pte;
}
static inline int pte_present(pte_t a)
{
return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
}
#endif /* __ASSEMBLY__ */
#ifdef CONFIG_X86_32
# include "pgtable_32.h"
#else
# include "pgtable_64.h"
#endif
/*
* the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
*
* this macro returns the index of the entry in the pgd page which would
* control the given virtual address
*/
#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
/*
* pgd_offset() returns a (pgd_t *)
* pgd_index() is used get the offset into the pgd page's array of pgd_t's;
*/
#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
/*
* a shortcut which implies the use of the kernel's pgd, instead
* of a process's
*/
#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
#define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET)
#define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
#ifndef __ASSEMBLY__
enum {
PG_LEVEL_NONE,
PG_LEVEL_4K,
PG_LEVEL_2M,
PG_LEVEL_1G,
PG_LEVEL_NUM
};
#ifdef CONFIG_PROC_FS
extern void update_page_count(int level, unsigned long pages);
#else
static inline void update_page_count(int level, unsigned long pages) { }
#endif
/*
* Helper function that returns the kernel pagetable entry controlling
* the virtual address 'address'. NULL means no pagetable entry present.
* NOTE: the return type is pte_t but if the pmd is PSE then we return it
* as a pte too.
*/
extern pte_t *lookup_address(unsigned long address, unsigned int *level);
/* local pte updates need not use xchg for locking */
static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
{
pte_t res = *ptep;
/* Pure native function needs no input for mm, addr */
native_pte_clear(NULL, 0, ptep);
return res;
}
static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep , pte_t pte)
{
native_set_pte(ptep, pte);
}
#ifndef CONFIG_PARAVIRT
/*
* Rules for using pte_update - it must be called after any PTE update which
* has not been done using the set_pte / clear_pte interfaces. It is used by
* shadow mode hypervisors to resynchronize the shadow page tables. Kernel PTE
* updates should either be sets, clears, or set_pte_atomic for P->P
* transitions, which means this hook should only be called for user PTEs.
* This hook implies a P->P protection or access change has taken place, which
* requires a subsequent TLB flush. The notification can optionally be delayed
* until the TLB flush event by using the pte_update_defer form of the
* interface, but care must be taken to assure that the flush happens while
* still holding the same page table lock so that the shadow and primary pages
* do not become out of sync on SMP.
*/
#define pte_update(mm, addr, ptep) do { } while (0)
#define pte_update_defer(mm, addr, ptep) do { } while (0)
#endif
/*
* We only update the dirty/accessed state if we set
* the dirty bit by hand in the kernel, since the hardware
* will do the accessed bit for us, and we don't want to
* race with other CPU's that might be updating the dirty
* bit at the same time.
*/
struct vm_area_struct;
#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
extern int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
pte_t entry, int dirty);
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
extern int ptep_test_and_clear_young(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep);
#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
extern int ptep_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep);
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
pte_t pte = native_ptep_get_and_clear(ptep);
pte_update(mm, addr, ptep);
return pte;
}
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
unsigned long addr, pte_t *ptep,
int full)
{
pte_t pte;
if (full) {
/*
* Full address destruction in progress; paravirt does not
* care about updates and native needs no locking
*/
pte = native_local_ptep_get_and_clear(ptep);
} else {
pte = ptep_get_and_clear(mm, addr, ptep);
}
return pte;
}
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
pte_update(mm, addr, ptep);
}
/*
* clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
*
* dst - pointer to pgd range anwhere on a pgd page
* src - ""
* count - the number of pgds to copy.
*
* dst and src can be on the same page, but the range must not overlap,
* and must not cross a page boundary.
*/
static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
{
memcpy(dst, src, count * sizeof(pgd_t));
}
#include <asm-generic/pgtable.h>
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PGTABLE_H */