arch/arm/include/asm/pgtable-2level.h - linux - Git at Google

 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  arch/arm/include/asm/pgtable-2level.h
  *
  *  Copyright (C) 1995-2002 Russell King
  */
 #ifndef _ASM_PGTABLE_2LEVEL_H
 #define _ASM_PGTABLE_2LEVEL_H

 #define __PAGETABLE_PMD_FOLDED 1

 /*
  * Hardware-wise, we have a two level page table structure, where the first
  * level has 4096 entries, and the second level has 256 entries.  Each entry
  * is one 32-bit word.  Most of the bits in the second level entry are used
  * by hardware, and there aren't any "accessed" and "dirty" bits.
  *
  * Linux on the other hand has a three level page table structure, which can
  * be wrapped to fit a two level page table structure easily - using the PGD
  * and PTE only.  However, Linux also expects one "PTE" table per page, and
  * at least a "dirty" bit.
  *
  * Therefore, we tweak the implementation slightly - we tell Linux that we
  * have 2048 entries in the first level, each of which is 8 bytes (iow, two
  * hardware pointers to the second level.)  The second level contains two
  * hardware PTE tables arranged contiguously, preceded by Linux versions
  * which contain the state information Linux needs.  We, therefore, end up
  * with 512 entries in the "PTE" level.
  *
  * This leads to the page tables having the following layout:
  *
  *    pgd             pte
  * |        |
  * +--------+
  * |        |       +------------+ +0
  * +- - - - +       | Linux pt 0 |
  * |        |       +------------+ +1024
  * +--------+ +0    | Linux pt 1 |
  * |        |-----> +------------+ +2048
  * +- - - - + +4    |  h/w pt 0  |
  * |        |-----> +------------+ +3072
  * +--------+ +8    |  h/w pt 1  |
  * |        |       +------------+ +4096
  *
  * See L_PTE_xxx below for definitions of bits in the "Linux pt", and
  * PTE_xxx for definitions of bits appearing in the "h/w pt".
  *
  * PMD_xxx definitions refer to bits in the first level page table.
  *
  * The "dirty" bit is emulated by only granting hardware write permission
  * iff the page is marked "writable" and "dirty" in the Linux PTE.  This
  * means that a write to a clean page will cause a permission fault, and
  * the Linux MM layer will mark the page dirty via handle_pte_fault().
  * For the hardware to notice the permission change, the TLB entry must
  * be flushed, and ptep_set_access_flags() does that for us.
  *
  * The "accessed" or "young" bit is emulated by a similar method; we only
  * allow accesses to the page if the "young" bit is set.  Accesses to the
  * page will cause a fault, and handle_pte_fault() will set the young bit
  * for us as long as the page is marked present in the corresponding Linux
  * PTE entry.  Again, ptep_set_access_flags() will ensure that the TLB is
  * up to date.
  *
  * However, when the "young" bit is cleared, we deny access to the page
  * by clearing the hardware PTE.  Currently Linux does not flush the TLB
  * for us in this case, which means the TLB will retain the transation
  * until either the TLB entry is evicted under pressure, or a context
  * switch which changes the user space mapping occurs.
  */
 #define PTRS_PER_PTE		512
 #define PTRS_PER_PMD		1
 #define PTRS_PER_PGD		2048

 #define PTE_HWTABLE_PTRS	(PTRS_PER_PTE)
 #define PTE_HWTABLE_OFF		(PTE_HWTABLE_PTRS * sizeof(pte_t))
 #define PTE_HWTABLE_SIZE	(PTRS_PER_PTE * sizeof(u32))

 #define MAX_POSSIBLE_PHYSMEM_BITS	32

 /*
  * PMD_SHIFT determines the size of the area a second-level page table can map
  * PGDIR_SHIFT determines what a third-level page table entry can map
  */
 #define PMD_SHIFT		21
 #define PGDIR_SHIFT		21

 #define PMD_SIZE		(1UL << PMD_SHIFT)
 #define PMD_MASK		(~(PMD_SIZE-1))
 #define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK		(~(PGDIR_SIZE-1))

 /*
  * section address mask and size definitions.
  */
 #define SECTION_SHIFT		20
 #define SECTION_SIZE		(1UL << SECTION_SHIFT)
 #define SECTION_MASK		(~(SECTION_SIZE-1))

 /*
  * ARMv6 supersection address mask and size definitions.
  */
 #define SUPERSECTION_SHIFT	24
 #define SUPERSECTION_SIZE	(1UL << SUPERSECTION_SHIFT)
 #define SUPERSECTION_MASK	(~(SUPERSECTION_SIZE-1))

 #define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)

 /*
  * "Linux" PTE definitions.
  *
  * We keep two sets of PTEs - the hardware and the linux version.
  * This allows greater flexibility in the way we map the Linux bits
  * onto the hardware tables, and allows us to have YOUNG and DIRTY
  * bits.
  *
  * The PTE table pointer refers to the hardware entries; the "Linux"
  * entries are stored 1024 bytes below.
  */
 #define L_PTE_VALID		(_AT(pteval_t, 1) << 0)		/* Valid */
 #define L_PTE_PRESENT		(_AT(pteval_t, 1) << 0)
 #define L_PTE_YOUNG		(_AT(pteval_t, 1) << 1)
 #define L_PTE_DIRTY		(_AT(pteval_t, 1) << 6)
 #define L_PTE_RDONLY		(_AT(pteval_t, 1) << 7)
 #define L_PTE_USER		(_AT(pteval_t, 1) << 8)
 #define L_PTE_XN		(_AT(pteval_t, 1) << 9)
 #define L_PTE_SHARED		(_AT(pteval_t, 1) << 10)	/* shared(v6), coherent(xsc3) */
 #define L_PTE_NONE		(_AT(pteval_t, 1) << 11)

 /* We borrow bit 7 to store the exclusive marker in swap PTEs. */
 #define L_PTE_SWP_EXCLUSIVE	L_PTE_RDONLY

 /*
  * These are the memory types, defined to be compatible with
  * pre-ARMv6 CPUs cacheable and bufferable bits: n/a,n/a,C,B
  * ARMv6+ without TEX remapping, they are a table index.
  * ARMv6+ with TEX remapping, they correspond to n/a,TEX(0),C,B
  *
  * MT type		Pre-ARMv6	ARMv6+ type / cacheable status
  * UNCACHED		Uncached	Strongly ordered
  * BUFFERABLE		Bufferable	Normal memory / non-cacheable
  * WRITETHROUGH		Writethrough	Normal memory / write through
  * WRITEBACK		Writeback	Normal memory / write back, read alloc
  * MINICACHE		Minicache	N/A
  * WRITEALLOC		Writeback	Normal memory / write back, write alloc
  * DEV_SHARED		Uncached	Device memory (shared)
  * DEV_NONSHARED	Uncached	Device memory (non-shared)
  * DEV_WC		Bufferable	Normal memory / non-cacheable
  * DEV_CACHED		Writeback	Normal memory / write back, read alloc
  * VECTORS		Variable	Normal memory / variable
  *
  * All normal memory mappings have the following properties:
  * - reads can be repeated with no side effects
  * - repeated reads return the last value written
  * - reads can fetch additional locations without side effects
  * - writes can be repeated (in certain cases) with no side effects
  * - writes can be merged before accessing the target
  * - unaligned accesses can be supported
  *
  * All device mappings have the following properties:
  * - no access speculation
  * - no repetition (eg, on return from an exception)
  * - number, order and size of accesses are maintained
  * - unaligned accesses are "unpredictable"
  */
 #define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
 #define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */
 #define L_PTE_MT_WRITETHROUGH	(_AT(pteval_t, 0x02) << 2)	/* 0010 */
 #define L_PTE_MT_WRITEBACK	(_AT(pteval_t, 0x03) << 2)	/* 0011 */
 #define L_PTE_MT_MINICACHE	(_AT(pteval_t, 0x06) << 2)	/* 0110 (sa1100, xscale) */
 #define L_PTE_MT_WRITEALLOC	(_AT(pteval_t, 0x07) << 2)	/* 0111 */
 #define L_PTE_MT_DEV_SHARED	(_AT(pteval_t, 0x04) << 2)	/* 0100 */
 #define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 0x0c) << 2)	/* 1100 */
 #define L_PTE_MT_DEV_WC		(_AT(pteval_t, 0x09) << 2)	/* 1001 */
 #define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
 #define L_PTE_MT_VECTORS	(_AT(pteval_t, 0x0f) << 2)	/* 1111 */
 #define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)

 #ifndef __ASSEMBLY__

 /*
  * The "pud_xxx()" functions here are trivial when the pmd is folded into
  * the pud: the pud entry is never bad, always exists, and can't be set or
  * cleared.
  */
 static inline int pud_none(pud_t pud)
 {
 	return 0;
 }

 static inline int pud_bad(pud_t pud)
 {
 	return 0;
 }

 static inline int pud_present(pud_t pud)
 {
 	return 1;
 }

 static inline void pud_clear(pud_t *pudp)
 {
 }

 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
 }

 static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 {
 	return (pmd_t *)pud;
 }
 #define pmd_offset pmd_offset

 #define pmd_pfn(pmd)		(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))

 #define pmd_leaf(pmd)		(pmd_val(pmd) & PMD_TYPE_SECT)
 #define pmd_bad(pmd)		pmd_leaf(pmd)
 #define pmd_present(pmd)	(pmd_val(pmd))

 #define copy_pmd(pmdpd,pmdps)		\
 	do {				\
 		pmdpd[0] = pmdps[0];	\
 		pmdpd[1] = pmdps[1];	\
 		flush_pmd_entry(pmdpd);	\
 	} while (0)

 #define pmd_clear(pmdp)			\
 	do {				\
 		pmdp[0] = __pmd(0);	\
 		pmdp[1] = __pmd(0);	\
 		clean_pmd_entry(pmdp);	\
 	} while (0)

 /* we don't need complex calculations here as the pmd is folded into the pgd */
 #define pmd_addr_end(addr,end) (end)

 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)

 /*
  * We don't have huge page support for short descriptors, for the moment
  * define empty stubs for use by pin_page_for_write.
  */
 #define pmd_hugewillfault(pmd)	(0)

 #endif /* __ASSEMBLY__ */

 #endif /* _ASM_PGTABLE_2LEVEL_H */
	/* SPDX-License-Identifier: GPL-2.0-only */
	/*
	* arch/arm/include/asm/pgtable-2level.h
	*
	* Copyright (C) 1995-2002 Russell King
	*/
	#ifndef _ASM_PGTABLE_2LEVEL_H
	#define _ASM_PGTABLE_2LEVEL_H

	#define __PAGETABLE_PMD_FOLDED 1

	/*
	* Hardware-wise, we have a two level page table structure, where the first
	* level has 4096 entries, and the second level has 256 entries. Each entry
	* is one 32-bit word. Most of the bits in the second level entry are used
	* by hardware, and there aren't any "accessed" and "dirty" bits.
	*
	* Linux on the other hand has a three level page table structure, which can
	* be wrapped to fit a two level page table structure easily - using the PGD
	* and PTE only. However, Linux also expects one "PTE" table per page, and
	* at least a "dirty" bit.
	*
	* Therefore, we tweak the implementation slightly - we tell Linux that we
	* have 2048 entries in the first level, each of which is 8 bytes (iow, two
	* hardware pointers to the second level.) The second level contains two
	* hardware PTE tables arranged contiguously, preceded by Linux versions
	* which contain the state information Linux needs. We, therefore, end up
	* with 512 entries in the "PTE" level.
	*
	* This leads to the page tables having the following layout:
	*
	* pgd pte
	* \| \|
	* +--------+
	* \| \| +------------+ +0
	* +- - - - + \| Linux pt 0 \|
	* \| \| +------------+ +1024
	* +--------+ +0 \| Linux pt 1 \|
	* \| \|-----> +------------+ +2048
	* +- - - - + +4 \| h/w pt 0 \|
	* \| \|-----> +------------+ +3072
	* +--------+ +8 \| h/w pt 1 \|
	* \| \| +------------+ +4096
	*
	* See L_PTE_xxx below for definitions of bits in the "Linux pt", and
	* PTE_xxx for definitions of bits appearing in the "h/w pt".
	*
	* PMD_xxx definitions refer to bits in the first level page table.
	*
	* The "dirty" bit is emulated by only granting hardware write permission
	* iff the page is marked "writable" and "dirty" in the Linux PTE. This
	* means that a write to a clean page will cause a permission fault, and
	* the Linux MM layer will mark the page dirty via handle_pte_fault().
	* For the hardware to notice the permission change, the TLB entry must
	* be flushed, and ptep_set_access_flags() does that for us.
	*
	* The "accessed" or "young" bit is emulated by a similar method; we only
	* allow accesses to the page if the "young" bit is set. Accesses to the
	* page will cause a fault, and handle_pte_fault() will set the young bit
	* for us as long as the page is marked present in the corresponding Linux
	* PTE entry. Again, ptep_set_access_flags() will ensure that the TLB is
	* up to date.
	*
	* However, when the "young" bit is cleared, we deny access to the page
	* by clearing the hardware PTE. Currently Linux does not flush the TLB
	* for us in this case, which means the TLB will retain the transation
	* until either the TLB entry is evicted under pressure, or a context
	* switch which changes the user space mapping occurs.
	*/
	#define PTRS_PER_PTE 512
	#define PTRS_PER_PMD 1
	#define PTRS_PER_PGD 2048

	#define PTE_HWTABLE_PTRS (PTRS_PER_PTE)
	#define PTE_HWTABLE_OFF (PTE_HWTABLE_PTRS * sizeof(pte_t))
	#define PTE_HWTABLE_SIZE (PTRS_PER_PTE * sizeof(u32))

	#define MAX_POSSIBLE_PHYSMEM_BITS 32

	/*
	* PMD_SHIFT determines the size of the area a second-level page table can map
	* PGDIR_SHIFT determines what a third-level page table entry can map
	*/
	#define PMD_SHIFT 21
	#define PGDIR_SHIFT 21

	#define PMD_SIZE (1UL << PMD_SHIFT)
	#define PMD_MASK (~(PMD_SIZE-1))
	#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
	#define PGDIR_MASK (~(PGDIR_SIZE-1))

	/*
	* section address mask and size definitions.
	*/
	#define SECTION_SHIFT 20
	#define SECTION_SIZE (1UL << SECTION_SHIFT)
	#define SECTION_MASK (~(SECTION_SIZE-1))

	/*
	* ARMv6 supersection address mask and size definitions.
	*/
	#define SUPERSECTION_SHIFT 24
	#define SUPERSECTION_SIZE (1UL << SUPERSECTION_SHIFT)
	#define SUPERSECTION_MASK (~(SUPERSECTION_SIZE-1))

	#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE)

	/*
	* "Linux" PTE definitions.
	*
	* We keep two sets of PTEs - the hardware and the linux version.
	* This allows greater flexibility in the way we map the Linux bits
	* onto the hardware tables, and allows us to have YOUNG and DIRTY
	* bits.
	*
	* The PTE table pointer refers to the hardware entries; the "Linux"
	* entries are stored 1024 bytes below.
	*/
	#define L_PTE_VALID (_AT(pteval_t, 1) << 0) /* Valid */
	#define L_PTE_PRESENT (_AT(pteval_t, 1) << 0)
	#define L_PTE_YOUNG (_AT(pteval_t, 1) << 1)
	#define L_PTE_DIRTY (_AT(pteval_t, 1) << 6)
	#define L_PTE_RDONLY (_AT(pteval_t, 1) << 7)
	#define L_PTE_USER (_AT(pteval_t, 1) << 8)
	#define L_PTE_XN (_AT(pteval_t, 1) << 9)
	#define L_PTE_SHARED (_AT(pteval_t, 1) << 10) /* shared(v6), coherent(xsc3) */
	#define L_PTE_NONE (_AT(pteval_t, 1) << 11)

	/* We borrow bit 7 to store the exclusive marker in swap PTEs. */
	#define L_PTE_SWP_EXCLUSIVE L_PTE_RDONLY

	/*
	* These are the memory types, defined to be compatible with
	* pre-ARMv6 CPUs cacheable and bufferable bits: n/a,n/a,C,B
	* ARMv6+ without TEX remapping, they are a table index.
	* ARMv6+ with TEX remapping, they correspond to n/a,TEX(0),C,B
	*
	* MT type Pre-ARMv6 ARMv6+ type / cacheable status
	* UNCACHED Uncached Strongly ordered
	* BUFFERABLE Bufferable Normal memory / non-cacheable
	* WRITETHROUGH Writethrough Normal memory / write through
	* WRITEBACK Writeback Normal memory / write back, read alloc
	* MINICACHE Minicache N/A
	* WRITEALLOC Writeback Normal memory / write back, write alloc
	* DEV_SHARED Uncached Device memory (shared)
	* DEV_NONSHARED Uncached Device memory (non-shared)
	* DEV_WC Bufferable Normal memory / non-cacheable
	* DEV_CACHED Writeback Normal memory / write back, read alloc
	* VECTORS Variable Normal memory / variable
	*
	* All normal memory mappings have the following properties:
	* - reads can be repeated with no side effects
	* - repeated reads return the last value written
	* - reads can fetch additional locations without side effects
	* - writes can be repeated (in certain cases) with no side effects
	* - writes can be merged before accessing the target
	* - unaligned accesses can be supported
	*
	* All device mappings have the following properties:
	* - no access speculation
	* - no repetition (eg, on return from an exception)
	* - number, order and size of accesses are maintained
	* - unaligned accesses are "unpredictable"
	*/
	#define L_PTE_MT_UNCACHED (_AT(pteval_t, 0x00) << 2) /* 0000 */
	#define L_PTE_MT_BUFFERABLE (_AT(pteval_t, 0x01) << 2) /* 0001 */
	#define L_PTE_MT_WRITETHROUGH (_AT(pteval_t, 0x02) << 2) /* 0010 */
	#define L_PTE_MT_WRITEBACK (_AT(pteval_t, 0x03) << 2) /* 0011 */
	#define L_PTE_MT_MINICACHE (_AT(pteval_t, 0x06) << 2) /* 0110 (sa1100, xscale) */
	#define L_PTE_MT_WRITEALLOC (_AT(pteval_t, 0x07) << 2) /* 0111 */
	#define L_PTE_MT_DEV_SHARED (_AT(pteval_t, 0x04) << 2) /* 0100 */
	#define L_PTE_MT_DEV_NONSHARED (_AT(pteval_t, 0x0c) << 2) /* 1100 */
	#define L_PTE_MT_DEV_WC (_AT(pteval_t, 0x09) << 2) /* 1001 */
	#define L_PTE_MT_DEV_CACHED (_AT(pteval_t, 0x0b) << 2) /* 1011 */
	#define L_PTE_MT_VECTORS (_AT(pteval_t, 0x0f) << 2) /* 1111 */
	#define L_PTE_MT_MASK (_AT(pteval_t, 0x0f) << 2)

	#ifndef __ASSEMBLY__

	/*
	* The "pud_xxx()" functions here are trivial when the pmd is folded into
	* the pud: the pud entry is never bad, always exists, and can't be set or
	* cleared.
	*/
	static inline int pud_none(pud_t pud)
	{
	return 0;
	}

	static inline int pud_bad(pud_t pud)
	{
	return 0;
	}

	static inline int pud_present(pud_t pud)
	{
	return 1;
	}

	static inline void pud_clear(pud_t *pudp)
	{
	}

	static inline void set_pud(pud_t *pudp, pud_t pud)
	{
	}

	static inline pmd_t pmd_offset(pud_t pud, unsigned long addr)
	{
	return (pmd_t *)pud;
	}
	#define pmd_offset pmd_offset

	#define pmd_pfn(pmd) (__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))

	#define pmd_leaf(pmd) (pmd_val(pmd) & PMD_TYPE_SECT)
	#define pmd_bad(pmd) pmd_leaf(pmd)
	#define pmd_present(pmd) (pmd_val(pmd))

	#define copy_pmd(pmdpd,pmdps) \
	do { \
	pmdpd[0] = pmdps[0]; \
	pmdpd[1] = pmdps[1]; \
	flush_pmd_entry(pmdpd); \
	} while (0)

	#define pmd_clear(pmdp) \
	do { \
	pmdp[0] = __pmd(0); \
	pmdp[1] = __pmd(0); \
	clean_pmd_entry(pmdp); \
	} while (0)

	/* we don't need complex calculations here as the pmd is folded into the pgd */
	#define pmd_addr_end(addr,end) (end)

	#define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)

	/*
	* We don't have huge page support for short descriptors, for the moment
	* define empty stubs for use by pin_page_for_write.
	*/
	#define pmd_hugewillfault(pmd) (0)

	#endif /* __ASSEMBLY__ */

	#endif /* _ASM_PGTABLE_2LEVEL_H */