xref: /linux/arch/alpha/include/asm/pgtable.h (revision 742f62b63904cdc20a364a49d2861e32464a0af7)

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ALPHA_PGTABLE_H
#define _ALPHA_PGTABLE_H

#include <asm-generic/pgtable-nopud.h>

/*
 * This file contains the functions and defines necessary to modify and use
 * the Alpha page table tree.
 *
 * This hopefully works with any standard Alpha page-size, as defined
 * in <asm/page.h> (currently 8192).
 */
#include <linux/mmzone.h>

#include <asm/page.h>
#include <asm/processor.h>	/* For TASK_SIZE */
#include <asm/machvec.h>
#include <asm/setup.h>
#include <linux/page_table_check.h>

struct mm_struct;
struct vm_area_struct;

/* Certain architectures need to do special things when PTEs
 * within a page table are directly modified.  Thus, the following
 * hook is made available.
 */
#define set_pte(pteptr, pteval) ((*(pteptr)) = (pteval))

/* PMD_SHIFT determines the size of the area a second-level page table can map */
#define PMD_SHIFT	(PAGE_SHIFT + (PAGE_SHIFT-3))
#define PMD_SIZE	(1UL << PMD_SHIFT)
#define PMD_MASK	(~(PMD_SIZE-1))

/* PGDIR_SHIFT determines what a third-level page table entry can map */
#define PGDIR_SHIFT	(PAGE_SHIFT + 2*(PAGE_SHIFT-3))
#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
#define PGDIR_MASK	(~(PGDIR_SIZE-1))

/*
 * Entries per page directory level:  the Alpha is three-level, with
 * all levels having a one-page page table.
 */
#define PTRS_PER_PTE	(1UL << (PAGE_SHIFT-3))
#define PTRS_PER_PMD	(1UL << (PAGE_SHIFT-3))
#define PTRS_PER_PGD	(1UL << (PAGE_SHIFT-3))
#define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)

/* Number of pointers that fit on a page:  this will go away. */
#define PTRS_PER_PAGE	(1UL << (PAGE_SHIFT-3))

#ifdef CONFIG_ALPHA_LARGE_VMALLOC
#define VMALLOC_START		0xfffffe0000000000
#else
#define VMALLOC_START		(-2*PGDIR_SIZE)
#endif
#define VMALLOC_END		(-PGDIR_SIZE)

/*
 * OSF/1 PAL-code-imposed page table bits
 */
#define _PAGE_VALID	0x0001
#define _PAGE_FOR	0x0002	/* used for page protection (fault on read) */
#define _PAGE_FOW	0x0004	/* used for page protection (fault on write) */
#define _PAGE_FOE	0x0008	/* used for page protection (fault on exec) */
#define _PAGE_ASM	0x0010
#define _PAGE_GH_MASK	0x0060	/* granularity hint, PTE<6:5> */
#define _PAGE_GH_SHIFT	5
#define _PAGE_KRE	0x0100	/* kernel read enable, in __ACCESS_BITS */
#define _PAGE_URE	0x0200	/* user read enable, in __ACCESS_BITS */
#define _PAGE_KWE	0x1000	/* kernel write enable, in __DIRTY_BITS */
#define _PAGE_UWE	0x2000	/* user write enable, in __DIRTY_BITS */

/* .. and these are ours ... */
#define _PAGE_DIRTY	0x20000
#define _PAGE_ACCESSED	0x40000
#define _PAGE_SPECIAL	0x80000

/* We borrow bit 39 to store the exclusive marker in swap PTEs. */
#define _PAGE_SWP_EXCLUSIVE	0x8000000000UL

/*
 * NOTE! The "accessed" bit isn't necessarily exact:  it can be kept exactly
 * by software (use the KRE/URE/KWE/UWE bits appropriately), but I'll fake it.
 * Under Linux/AXP, the "accessed" bit just means "read", and I'll just use
 * the KRE/URE bits to watch for it. That way we don't need to overload the
 * KWE/UWE bits with both handling dirty and accessed.
 *
 * Note that the kernel uses the accessed bit just to check whether to page
 * out a page or not, so it doesn't have to be exact anyway.
 */

#define __DIRTY_BITS	(_PAGE_DIRTY | _PAGE_KWE | _PAGE_UWE)
#define __ACCESS_BITS	(_PAGE_ACCESSED | _PAGE_KRE | _PAGE_URE)

#define _PFN_MASK	0xFFFFFFFF00000000UL

#define _PAGE_TABLE	(_PAGE_VALID | __DIRTY_BITS | __ACCESS_BITS)
/*
 * pte_modify() must preserve the granularity hint, or
 * hugetlb_change_protection() would turn a block into single-page PTEs.
 */
#define _PAGE_CHG_MASK	(_PFN_MASK | __DIRTY_BITS | __ACCESS_BITS | \
			 _PAGE_GH_MASK | _PAGE_SPECIAL)

/*
 * Granularity hints. A PTE with hint order N is one of a block of 8^N
 * physically contiguous pages, naturally aligned both virtually and
 * physically, that the TB may map with a single entry. With 8KB pages the
 * four encodings give 8KB, 64KB, 512KB and 4MB.
 *
 * Every PTE of a block must still carry the PFN of its own page, and all of
 * them must agree in bits <15:0>: the protection, fault, hint and valid bits.
 * __ACCESS_BITS and __DIRTY_BITS reach into that range, so young and dirty
 * updates have to be applied to the whole block too.
 *
 * The hint is advisory: an implementation that ignores it still translates
 * correctly through the individual PTEs, so it is safe to set on any Alpha.
 */
#define GH_ORDER_MAX	4			/* hint orders 0..3 */

#define gh_cont_shift(order)	(PAGE_SHIFT + 3 * (order))
#define gh_cont_size(order)	(1UL << gh_cont_shift(order))
#define gh_cont_mask(order)	(~(gh_cont_size(order) - 1))
#define gh_pte_num(order)	(1UL << (3 * (order)))

#define for_each_gh_order(order) \
	for ((order) = 1; (order) < GH_ORDER_MAX; (order)++)

/*
 * All the normal masks have the "page accessed" bits on, as any time they are used,
 * the page is accessed. They are cleared only by the page-out routines
 */
#define PAGE_NONE	__pgprot(_PAGE_VALID | __ACCESS_BITS | _PAGE_FOR | _PAGE_FOW | _PAGE_FOE)
#define PAGE_SHARED	__pgprot(_PAGE_VALID | __ACCESS_BITS)
#define PAGE_COPY	__pgprot(_PAGE_VALID | __ACCESS_BITS | _PAGE_FOW)
#define PAGE_READONLY	__pgprot(_PAGE_VALID | __ACCESS_BITS | _PAGE_FOW)
#define PAGE_KERNEL	__pgprot(_PAGE_VALID | _PAGE_ASM | _PAGE_KRE | _PAGE_KWE)

#define _PAGE_NORMAL(x) __pgprot(_PAGE_VALID | __ACCESS_BITS | (x))

#define _PAGE_P(x) _PAGE_NORMAL((x) | _PAGE_FOW)
#define _PAGE_S(x) _PAGE_NORMAL(x)

/*
 * The hardware can handle write-only mappings, but as the Alpha
 * architecture does byte-wide writes with a read-modify-write
 * sequence, it's not practical to have write-without-read privs.
 * Thus the "-w- -> rw-" and "-wx -> rwx" mapping here (and in
 * arch/alpha/mm/fault.c)
 */
	/* xwr */

/*
 * pgprot_noncached() is only for infiniband pci support, and a real
 * implementation for RAM would be more complicated.
 */
#define pgprot_noncached(prot)	(prot)

/*
 * All caching attribute macros are identity on Alpha, so the generic
 * pgprot_modify() degenerates to tautological self-comparisons.
 * Override it to just return newprot directly.
 */
#define pgprot_modify pgprot_modify
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
{
	return newprot;
}

/*
 * On certain platforms whose physical address space can overlap KSEG,
 * namely EV6 and above, we must re-twiddle the physaddr to restore the
 * correct high-order bits.
 *
 * This is extremely confusing until you realize that this is actually
 * just working around a userspace bug.  The X server was intending to
 * provide the physical address but instead provided the KSEG address.
 * Or tried to, except it's not representable.
 *
 * On Tsunami there's nothing meaningful at 0x40000000000, so this is
 * a safe thing to do.  Come the first core logic that does put something
 * in this area -- memory or whathaveyou -- then this hack will have
 * to go away.  So be prepared!
 */

#if defined(CONFIG_ALPHA_GENERIC) && defined(USE_48_BIT_KSEG)
#error "EV6-only feature in a generic kernel"
#endif
#if defined(CONFIG_ALPHA_GENERIC) || \
    (defined(CONFIG_ALPHA_EV6) && !defined(USE_48_BIT_KSEG))
#define KSEG_PFN	(0xc0000000000UL >> PAGE_SHIFT)
#define PHYS_TWIDDLE(pfn) \
  ((((pfn) & KSEG_PFN) == (0x40000000000UL >> PAGE_SHIFT)) \
  ? ((pfn) ^= KSEG_PFN) : (pfn))
#else
#define PHYS_TWIDDLE(pfn) (pfn)
#endif

/*
 * Conversion functions:  convert a page and protection to a page entry,
 * and a page entry and page directory to the page they refer to.
 */
#define page_to_pa(page)	(page_to_pfn(page) << PAGE_SHIFT)
#define PFN_PTE_SHIFT		32
#define pte_pfn(pte)		(pte_val(pte) >> PFN_PTE_SHIFT)

#define pte_page(pte)	pfn_to_page(pte_pfn(pte))

extern inline pte_t pfn_pte(unsigned long physpfn, pgprot_t pgprot)
{ pte_t pte; pte_val(pte) = (PHYS_TWIDDLE(physpfn) << 32) | pgprot_val(pgprot); return pte; }

extern inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{ pte_val(pte) = (pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot); return pte; }

extern inline void pmd_set(pmd_t * pmdp, pte_t * ptep)
{ pmd_val(*pmdp) = _PAGE_TABLE | ((((unsigned long) ptep) - PAGE_OFFSET) << (32-PAGE_SHIFT)); }

extern inline void pud_set(pud_t * pudp, pmd_t * pmdp)
{ pud_val(*pudp) = _PAGE_TABLE | ((((unsigned long) pmdp) - PAGE_OFFSET) << (32-PAGE_SHIFT)); }


extern void migrate_flush_tlb_page(struct vm_area_struct *vma,
					unsigned long addr);

extern inline unsigned long
pmd_page_vaddr(pmd_t pmd)
{
	return ((pmd_val(pmd) & _PFN_MASK) >> (32-PAGE_SHIFT)) + PAGE_OFFSET;
}

#define pmd_pfn(pmd)	(pmd_val(pmd) >> 32)
#define pmd_page(pmd)	(pfn_to_page(pmd_val(pmd) >> 32))
#define pud_page(pud)	(pfn_to_page(pud_val(pud) >> 32))

extern inline pmd_t *pud_pgtable(pud_t pgd)
{
	return (pmd_t *)(PAGE_OFFSET + ((pud_val(pgd) & _PFN_MASK) >> (32-PAGE_SHIFT)));
}

extern inline int pte_none(pte_t pte)		{ return !pte_val(pte); }
extern inline int pte_present(pte_t pte)	{ return pte_val(pte) & _PAGE_VALID; }
extern inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
	WRITE_ONCE(pte_val(*ptep), 0);
}

extern inline int pmd_none(pmd_t pmd)		{ return !pmd_val(pmd); }
extern inline int pmd_bad(pmd_t pmd)		{ return (pmd_val(pmd) & ~_PFN_MASK) != _PAGE_TABLE; }
extern inline int pmd_present(pmd_t pmd)	{ return pmd_val(pmd) & _PAGE_VALID; }
extern inline void pmd_clear(pmd_t * pmdp)	{ pmd_val(*pmdp) = 0; }

extern inline int pud_none(pud_t pud)		{ return !pud_val(pud); }
extern inline int pud_bad(pud_t pud)		{ return (pud_val(pud) & ~_PFN_MASK) != _PAGE_TABLE; }
extern inline int pud_present(pud_t pud)	{ return pud_val(pud) & _PAGE_VALID; }
extern inline void pud_clear(pud_t * pudp)	{ pud_val(*pudp) = 0; }

/*
 * The following only work if pte_present() is true.
 * Undefined behaviour if not..
 */
extern inline int pte_write(pte_t pte)		{ return !(pte_val(pte) & _PAGE_FOW); }
extern inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
extern inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
extern inline int pte_user(pte_t pte)		{ return pte_val(pte) & _PAGE_URE; }

static inline bool pte_user_accessible_page(struct mm_struct *mm,
					     unsigned long addr, pte_t pte)
{
	return pte_present(pte) && pte_user(pte);
}

static inline bool pmd_user_accessible_page(struct mm_struct *mm,
					     unsigned long addr, pmd_t pmd)
{
	return false;
}

static inline bool pud_user_accessible_page(struct mm_struct *mm,
					     unsigned long addr, pud_t pud)
{
	return false;
}

extern inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) |= _PAGE_FOW; return pte; }
extern inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~(__DIRTY_BITS); return pte; }
extern inline pte_t pte_mkold(pte_t pte)	{ pte_val(pte) &= ~(__ACCESS_BITS); return pte; }
extern inline pte_t pte_mkwrite_novma(pte_t pte){ pte_val(pte) &= ~_PAGE_FOW; return pte; }
extern inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= __DIRTY_BITS; return pte; }
extern inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= __ACCESS_BITS; return pte; }
extern inline int pte_special(pte_t pte)	{ return pte_val(pte) & _PAGE_SPECIAL; }
extern inline pte_t pte_mkspecial(pte_t pte)	{ pte_val(pte) |= _PAGE_SPECIAL; return pte; }

extern inline unsigned int pte_gh_order(pte_t pte)
{
	return (pte_val(pte) & _PAGE_GH_MASK) >> _PAGE_GH_SHIFT;
}

extern inline pte_t pte_mkgh(pte_t pte, unsigned int order)
{
	pte_val(pte) &= ~_PAGE_GH_MASK;
	pte_val(pte) |= (unsigned long)order << _PAGE_GH_SHIFT;
	return pte;
}

/*
 * Swap PTEs leave bits <31:0> clear, so this is false for every swap,
 * migration and marker entry, not just for ordinary small pages.
 */
extern inline int pte_huge(pte_t pte)		{ return pte_val(pte) & _PAGE_GH_MASK; }

/*
 * The smp_rmb() in the following functions are required to order the load of
 * *dir (the pointer in the top level page table) with any subsequent load of
 * the returned pmd_t *ret (ret is data dependent on *dir).
 *
 * If this ordering is not enforced, the CPU might load an older value of
 * *ret, which may be uninitialized data. See mm/memory.c:__pte_alloc for
 * more details.
 *
 * Note that we never change the mm->pgd pointer after the task is running, so
 * pgd_offset does not require such a barrier.
 */

/* Find an entry in the second-level page table.. */
extern inline pmd_t * pmd_offset(pud_t * dir, unsigned long address)
{
	pmd_t *ret = pud_pgtable(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1));
	smp_rmb(); /* see above */
	return ret;
}
#define pmd_offset pmd_offset

/* Find an entry in the third-level page table.. */
extern inline pte_t * pte_offset_kernel(pmd_t * dir, unsigned long address)
{
	pte_t *ret = (pte_t *) pmd_page_vaddr(*dir)
		+ ((address >> PAGE_SHIFT) & (PTRS_PER_PAGE - 1));
	smp_rmb(); /* see above */
	return ret;
}
#define pte_offset_kernel pte_offset_kernel

extern pgd_t swapper_pg_dir[1024];

#ifdef CONFIG_COMPACTION
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR

static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
					unsigned long address,
					pte_t *ptep)
{
	pte_t pte = READ_ONCE(*ptep);

	pte_clear(mm, address, ptep);
	page_table_check_pte_clear(mm, address, pte);
	return pte;
}

#define __HAVE_ARCH_PTEP_CLEAR_FLUSH

static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
				unsigned long addr, pte_t *ptep)
{
	struct mm_struct *mm = vma->vm_mm;
	pte_t pte = ptep_get_and_clear(mm, addr, ptep);

	migrate_flush_tlb_page(vma, addr);
	return pte;
}

#endif
/*
 * The Alpha doesn't have any external MMU info:  the kernel page
 * tables contain all the necessary information.
 */
extern inline void update_mmu_cache(struct vm_area_struct * vma,
	unsigned long address, pte_t *ptep)
{
}

static inline void update_mmu_cache_range(struct vm_fault *vmf,
		struct vm_area_struct *vma, unsigned long address,
		pte_t *ptep, unsigned int nr)
{
}

/*
 * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
 * are !pte_none() && !pte_present().
 *
 * Format of swap PTEs:
 *
 *   6 6 6 6 5 5 5 5 5 5 5 5 5 5 4 4 4 4 4 4 4 4 4 4 3 3 3 3 3 3 3 3
 *   3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2
 *   <------------------- offset ------------------> E <--- type -->
 *
 *   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
 *   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
 *   <--------------------------- zeroes -------------------------->
 *
 *   E is the exclusive marker that is not stored in swap entries.
 */
extern inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
{ pte_t pte; pte_val(pte) = ((type & 0x7f) << 32) | (offset << 40); return pte; }

#define __swp_type(x)		(((x).val >> 32) & 0x7f)
#define __swp_offset(x)		((x).val >> 40)
#define __swp_entry(type, off)	((swp_entry_t) { pte_val(mk_swap_pte((type), (off))) })
#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x)	((pte_t) { (x).val })

static inline bool pte_swp_exclusive(pte_t pte)
{
	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}

static inline pte_t pte_swp_mkexclusive(pte_t pte)
{
	pte_val(pte) |= _PAGE_SWP_EXCLUSIVE;
	return pte;
}

static inline pte_t pte_swp_clear_exclusive(pte_t pte)
{
	pte_val(pte) &= ~_PAGE_SWP_EXCLUSIVE;
	return pte;
}

#define pte_ERROR(e) \
	printk("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e))
#define pmd_ERROR(e) \
	printk("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e))
#define pgd_ERROR(e) \
	printk("%s:%d: bad pgd %016lx.\n", __FILE__, __LINE__, pgd_val(e))

extern void paging_init(void);

/* We have our own get_unmapped_area */
#define HAVE_ARCH_UNMAPPED_AREA

#endif /* _ALPHA_PGTABLE_H */