--- zzzz-none-000/linux-3.10.107/arch/s390/include/asm/pgtable.h 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/arch/s390/include/asm/pgtable.h 2021-02-04 17:41:59.000000000 +0000 @@ -12,12 +12,9 @@ #define _ASM_S390_PGTABLE_H /* - * The Linux memory management assumes a three-level page table setup. For - * s390 31 bit we "fold" the mid level into the top-level page table, so - * that we physically have the same two-level page table as the s390 mmu - * expects in 31 bit mode. For s390 64 bit we use three of the five levels - * the hardware provides (region first and region second tables are not - * used). + * The Linux memory management assumes a three-level page table setup. + * For s390 64 bit we use up to four of the five levels the hardware + * provides (region first tables are not used). * * The "pgd_xxx()" functions are trivial for a folded two-level * setup: the pgd is never bad, and a pmd always exists (as it's folded @@ -30,6 +27,7 @@ #include #include #include +#include #include #include @@ -58,9 +56,6 @@ #define __HAVE_COLOR_ZERO_PAGE /* TODO: s390 cannot support io_remap_pfn_range... */ -#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ - remap_pfn_range(vma, vaddr, pfn, size, prot) - #endif /* !__ASSEMBLY__ */ /* @@ -68,15 +63,9 @@ * table can map * PGDIR_SHIFT determines what a third-level page table entry can map */ -#ifndef CONFIG_64BIT -# define PMD_SHIFT 20 -# define PUD_SHIFT 20 -# define PGDIR_SHIFT 20 -#else /* CONFIG_64BIT */ -# define PMD_SHIFT 20 -# define PUD_SHIFT 31 -# define PGDIR_SHIFT 42 -#endif /* CONFIG_64BIT */ +#define PMD_SHIFT 20 +#define PUD_SHIFT 31 +#define PGDIR_SHIFT 42 #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) @@ -92,16 +81,11 @@ * that leads to 1024 pte per pgd */ #define PTRS_PER_PTE 256 -#ifndef CONFIG_64BIT -#define PTRS_PER_PMD 1 -#define PTRS_PER_PUD 1 -#else /* CONFIG_64BIT */ #define PTRS_PER_PMD 2048 #define PTRS_PER_PUD 2048 -#endif /* CONFIG_64BIT */ #define PTRS_PER_PGD 2048 -#define FIRST_USER_ADDRESS 0 +#define FIRST_USER_ADDRESS 0UL #define pte_ERROR(e) \ printk("%s:%d: bad pte %p.\n", __FILE__, __LINE__, (void *) pte_val(e)) @@ -114,8 +98,8 @@ #ifndef __ASSEMBLY__ /* - * The vmalloc and module area will always be on the topmost area of the kernel - * mapping. We reserve 96MB (31bit) / 128GB (64bit) for vmalloc and modules. + * The vmalloc and module area will always be on the topmost area of the + * kernel mapping. We reserve 128GB (64bit) for vmalloc and modules. * On 64 bit kernels we have a 2GB area at the top of the vmalloc area where * modules will reside. That makes sure that inter module branches always * happen without trampolines and in addition the placement within a 2GB frame @@ -127,47 +111,23 @@ #define VMEM_MAX_PHYS ((unsigned long) vmemmap) -#ifdef CONFIG_64BIT extern unsigned long MODULES_VADDR; extern unsigned long MODULES_END; #define MODULES_VADDR MODULES_VADDR #define MODULES_END MODULES_END #define MODULES_LEN (1UL << 31) -#endif + +static inline int is_module_addr(void *addr) +{ + BUILD_BUG_ON(MODULES_LEN > (1UL << 31)); + if (addr < (void *)MODULES_VADDR) + return 0; + if (addr > (void *)MODULES_END) + return 0; + return 1; +} /* - * A 31 bit pagetable entry of S390 has following format: - * | PFRA | | OS | - * 0 0IP0 - * 00000000001111111111222222222233 - * 01234567890123456789012345678901 - * - * I Page-Invalid Bit: Page is not available for address-translation - * P Page-Protection Bit: Store access not possible for page - * - * A 31 bit segmenttable entry of S390 has following format: - * | P-table origin | |PTL - * 0 IC - * 00000000001111111111222222222233 - * 01234567890123456789012345678901 - * - * I Segment-Invalid Bit: Segment is not available for address-translation - * C Common-Segment Bit: Segment is not private (PoP 3-30) - * PTL Page-Table-Length: Page-table length (PTL+1*16 entries -> up to 256) - * - * The 31 bit segmenttable origin of S390 has following format: - * - * |S-table origin | | STL | - * X **GPS - * 00000000001111111111222222222233 - * 01234567890123456789012345678901 - * - * X Space-Switch event: - * G Segment-Invalid Bit: * - * P Private-Space Bit: Segment is not private (PoP 3-30) - * S Storage-Alteration: - * STL Segment-Table-Length: Segment-table length (STL+1*16 entries -> up to 2048) - * * A 64 bit pagetable entry of S390 has following format: * | PFRA |0IPC| OS | * 0000000000111111111122222222223333333333444444444455555555556666 @@ -219,101 +179,67 @@ */ /* Hardware bits in the page table entry */ -#define _PAGE_CO 0x100 /* HW Change-bit override */ -#define _PAGE_RO 0x200 /* HW read-only bit */ +#define _PAGE_PROTECT 0x200 /* HW read-only bit */ #define _PAGE_INVALID 0x400 /* HW invalid bit */ +#define _PAGE_LARGE 0x800 /* Bit to mark a large pte */ /* Software bits in the page table entry */ -#define _PAGE_SWT 0x001 /* SW pte type bit t */ -#define _PAGE_SWX 0x002 /* SW pte type bit x */ -#define _PAGE_SWC 0x004 /* SW pte changed bit */ -#define _PAGE_SWR 0x008 /* SW pte referenced bit */ -#define _PAGE_SWW 0x010 /* SW pte write bit */ -#define _PAGE_SPECIAL 0x020 /* SW associated with special page */ +#define _PAGE_PRESENT 0x001 /* SW pte present bit */ +#define _PAGE_YOUNG 0x004 /* SW pte young bit */ +#define _PAGE_DIRTY 0x008 /* SW pte dirty bit */ +#define _PAGE_READ 0x010 /* SW pte read bit */ +#define _PAGE_WRITE 0x020 /* SW pte write bit */ +#define _PAGE_SPECIAL 0x040 /* SW associated with special page */ +#define _PAGE_UNUSED 0x080 /* SW bit for pgste usage state */ #define __HAVE_ARCH_PTE_SPECIAL +#ifdef CONFIG_MEM_SOFT_DIRTY +#define _PAGE_SOFT_DIRTY 0x002 /* SW pte soft dirty bit */ +#else +#define _PAGE_SOFT_DIRTY 0x000 +#endif + /* Set of bits not changed in pte_modify */ -#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_SPECIAL | _PAGE_CO | \ - _PAGE_SWC | _PAGE_SWR) +#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_SPECIAL | _PAGE_DIRTY | \ + _PAGE_YOUNG | _PAGE_SOFT_DIRTY) -/* Six different types of pages. */ -#define _PAGE_TYPE_EMPTY 0x400 -#define _PAGE_TYPE_NONE 0x401 -#define _PAGE_TYPE_SWAP 0x403 -#define _PAGE_TYPE_FILE 0x601 /* bit 0x002 is used for offset !! */ -#define _PAGE_TYPE_RO 0x200 -#define _PAGE_TYPE_RW 0x000 - -/* - * Only four types for huge pages, using the invalid bit and protection bit - * of a segment table entry. - */ -#define _HPAGE_TYPE_EMPTY 0x020 /* _SEGMENT_ENTRY_INV */ -#define _HPAGE_TYPE_NONE 0x220 -#define _HPAGE_TYPE_RO 0x200 /* _SEGMENT_ENTRY_RO */ -#define _HPAGE_TYPE_RW 0x000 - -/* - * PTE type bits are rather complicated. handle_pte_fault uses pte_present, - * pte_none and pte_file to find out the pte type WITHOUT holding the page - * table lock. ptep_clear_flush on the other hand uses ptep_clear_flush to - * invalidate a given pte. ipte sets the hw invalid bit and clears all tlbs - * for the page. The page table entry is set to _PAGE_TYPE_EMPTY afterwards. - * This change is done while holding the lock, but the intermediate step - * of a previously valid pte with the hw invalid bit set can be observed by - * handle_pte_fault. That makes it necessary that all valid pte types with - * the hw invalid bit set must be distinguishable from the four pte types - * empty, none, swap and file. +/* + * handle_pte_fault uses pte_present and pte_none to find out the pte type + * WITHOUT holding the page table lock. The _PAGE_PRESENT bit is used to + * distinguish present from not-present ptes. It is changed only with the page + * table lock held. + * + * The following table gives the different possible bit combinations for + * the pte hardware and software bits in the last 12 bits of a pte + * (. unassigned bit, x don't care, t swap type): * - * irxt ipte irxt - * _PAGE_TYPE_EMPTY 1000 -> 1000 - * _PAGE_TYPE_NONE 1001 -> 1001 - * _PAGE_TYPE_SWAP 1011 -> 1011 - * _PAGE_TYPE_FILE 11?1 -> 11?1 - * _PAGE_TYPE_RO 0100 -> 1100 - * _PAGE_TYPE_RW 0000 -> 1000 + * 842100000000 + * 000084210000 + * 000000008421 + * .IR.uswrdy.p + * empty .10.00000000 + * swap .11..ttttt.0 + * prot-none, clean, old .11.xx0000.1 + * prot-none, clean, young .11.xx0001.1 + * prot-none, dirty, old .10.xx0010.1 + * prot-none, dirty, young .10.xx0011.1 + * read-only, clean, old .11.xx0100.1 + * read-only, clean, young .01.xx0101.1 + * read-only, dirty, old .11.xx0110.1 + * read-only, dirty, young .01.xx0111.1 + * read-write, clean, old .11.xx1100.1 + * read-write, clean, young .01.xx1101.1 + * read-write, dirty, old .10.xx1110.1 + * read-write, dirty, young .00.xx1111.1 + * HW-bits: R read-only, I invalid + * SW-bits: p present, y young, d dirty, r read, w write, s special, + * u unused, l large * - * pte_none is true for bits combinations 1000, 1010, 1100, 1110 - * pte_present is true for bits combinations 0000, 0010, 0100, 0110, 1001 - * pte_file is true for bits combinations 1101, 1111 - * swap pte is 1011 and 0001, 0011, 0101, 0111 are invalid. + * pte_none is true for the bit pattern .10.00000000, pte == 0x400 + * pte_swap is true for the bit pattern .11..ooooo.0, (pte & 0x201) == 0x200 + * pte_present is true for the bit pattern .xx.xxxxxx.1, (pte & 0x001) == 0x001 */ -#ifndef CONFIG_64BIT - -/* Bits in the segment table address-space-control-element */ -#define _ASCE_SPACE_SWITCH 0x80000000UL /* space switch event */ -#define _ASCE_ORIGIN_MASK 0x7ffff000UL /* segment table origin */ -#define _ASCE_PRIVATE_SPACE 0x100 /* private space control */ -#define _ASCE_ALT_EVENT 0x80 /* storage alteration event control */ -#define _ASCE_TABLE_LENGTH 0x7f /* 128 x 64 entries = 8k */ - -/* Bits in the segment table entry */ -#define _SEGMENT_ENTRY_ORIGIN 0x7fffffc0UL /* page table origin */ -#define _SEGMENT_ENTRY_RO 0x200 /* page protection bit */ -#define _SEGMENT_ENTRY_INV 0x20 /* invalid segment table entry */ -#define _SEGMENT_ENTRY_COMMON 0x10 /* common segment bit */ -#define _SEGMENT_ENTRY_PTL 0x0f /* page table length */ - -#define _SEGMENT_ENTRY (_SEGMENT_ENTRY_PTL) -#define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INV) - -/* Page status table bits for virtualization */ -#define RCP_ACC_BITS 0xf0000000UL -#define RCP_FP_BIT 0x08000000UL -#define RCP_PCL_BIT 0x00800000UL -#define RCP_HR_BIT 0x00400000UL -#define RCP_HC_BIT 0x00200000UL -#define RCP_GR_BIT 0x00040000UL -#define RCP_GC_BIT 0x00020000UL -#define RCP_IN_BIT 0x00002000UL /* IPTE notify bit */ - -/* User dirty / referenced bit for KVM's migration feature */ -#define KVM_UR_BIT 0x00008000UL -#define KVM_UC_BIT 0x00004000UL - -#else /* CONFIG_64BIT */ - /* Bits in the segment/region table address-space-control-element */ #define _ASCE_ORIGIN ~0xfffUL/* segment table origin */ #define _ASCE_PRIVATE_SPACE 0x100 /* private space control */ @@ -329,8 +255,8 @@ /* Bits in the region table entry */ #define _REGION_ENTRY_ORIGIN ~0xfffUL/* region/segment table origin */ -#define _REGION_ENTRY_RO 0x200 /* region protection bit */ -#define _REGION_ENTRY_INV 0x20 /* invalid region table entry */ +#define _REGION_ENTRY_PROTECT 0x200 /* region protection bit */ +#define _REGION_ENTRY_INVALID 0x20 /* invalid region table entry */ #define _REGION_ENTRY_TYPE_MASK 0x0c /* region/segment table type mask */ #define _REGION_ENTRY_TYPE_R1 0x0c /* region first table type */ #define _REGION_ENTRY_TYPE_R2 0x08 /* region second table type */ @@ -338,49 +264,78 @@ #define _REGION_ENTRY_LENGTH 0x03 /* region third length */ #define _REGION1_ENTRY (_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_LENGTH) -#define _REGION1_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INV) +#define _REGION1_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INVALID) #define _REGION2_ENTRY (_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_LENGTH) -#define _REGION2_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INV) +#define _REGION2_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INVALID) #define _REGION3_ENTRY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_LENGTH) -#define _REGION3_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INV) +#define _REGION3_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID) #define _REGION3_ENTRY_LARGE 0x400 /* RTTE-format control, large page */ #define _REGION3_ENTRY_RO 0x200 /* page protection bit */ -#define _REGION3_ENTRY_CO 0x100 /* change-recording override */ /* Bits in the segment table entry */ +#define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL +#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff0ff33UL #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address */ #define _SEGMENT_ENTRY_ORIGIN ~0x7ffUL/* segment table origin */ -#define _SEGMENT_ENTRY_RO 0x200 /* page protection bit */ -#define _SEGMENT_ENTRY_INV 0x20 /* invalid segment table entry */ +#define _SEGMENT_ENTRY_PROTECT 0x200 /* page protection bit */ +#define _SEGMENT_ENTRY_INVALID 0x20 /* invalid segment table entry */ #define _SEGMENT_ENTRY (0) -#define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INV) +#define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INVALID) -#define _SEGMENT_ENTRY_LARGE 0x400 /* STE-format control, large page */ -#define _SEGMENT_ENTRY_CO 0x100 /* change-recording override */ -#define _SEGMENT_ENTRY_SPLIT_BIT 0 /* THP splitting bit number */ -#define _SEGMENT_ENTRY_SPLIT (1UL << _SEGMENT_ENTRY_SPLIT_BIT) - -/* Set of bits not changed in pmd_modify */ -#define _SEGMENT_CHG_MASK (_SEGMENT_ENTRY_ORIGIN | _SEGMENT_ENTRY_LARGE \ - | _SEGMENT_ENTRY_SPLIT | _SEGMENT_ENTRY_CO) +#define _SEGMENT_ENTRY_DIRTY 0x2000 /* SW segment dirty bit */ +#define _SEGMENT_ENTRY_YOUNG 0x1000 /* SW segment young bit */ +#define _SEGMENT_ENTRY_SPLIT 0x0800 /* THP splitting bit */ +#define _SEGMENT_ENTRY_LARGE 0x0400 /* STE-format control, large page */ +#define _SEGMENT_ENTRY_READ 0x0002 /* SW segment read bit */ +#define _SEGMENT_ENTRY_WRITE 0x0001 /* SW segment write bit */ -/* Page status table bits for virtualization */ -#define RCP_ACC_BITS 0xf000000000000000UL -#define RCP_FP_BIT 0x0800000000000000UL -#define RCP_PCL_BIT 0x0080000000000000UL -#define RCP_HR_BIT 0x0040000000000000UL -#define RCP_HC_BIT 0x0020000000000000UL -#define RCP_GR_BIT 0x0004000000000000UL -#define RCP_GC_BIT 0x0002000000000000UL -#define RCP_IN_BIT 0x0000200000000000UL /* IPTE notify bit */ - -/* User dirty / referenced bit for KVM's migration feature */ -#define KVM_UR_BIT 0x0000800000000000UL -#define KVM_UC_BIT 0x0000400000000000UL +#ifdef CONFIG_MEM_SOFT_DIRTY +#define _SEGMENT_ENTRY_SOFT_DIRTY 0x4000 /* SW segment soft dirty bit */ +#else +#define _SEGMENT_ENTRY_SOFT_DIRTY 0x0000 /* SW segment soft dirty bit */ +#endif -#endif /* CONFIG_64BIT */ +/* + * Segment table entry encoding (R = read-only, I = invalid, y = young bit): + * dy..R...I...wr + * prot-none, clean, old 00..1...1...00 + * prot-none, clean, young 01..1...1...00 + * prot-none, dirty, old 10..1...1...00 + * prot-none, dirty, young 11..1...1...00 + * read-only, clean, old 00..1...1...01 + * read-only, clean, young 01..1...0...01 + * read-only, dirty, old 10..1...1...01 + * read-only, dirty, young 11..1...0...01 + * read-write, clean, old 00..1...1...11 + * read-write, clean, young 01..1...0...11 + * read-write, dirty, old 10..0...1...11 + * read-write, dirty, young 11..0...0...11 + * The segment table origin is used to distinguish empty (origin==0) from + * read-write, old segment table entries (origin!=0) + * HW-bits: R read-only, I invalid + * SW-bits: y young, d dirty, r read, w write + */ + +#define _SEGMENT_ENTRY_SPLIT_BIT 11 /* THP splitting bit number */ + +/* Page status table bits for virtualization */ +#define PGSTE_ACC_BITS 0xf000000000000000UL +#define PGSTE_FP_BIT 0x0800000000000000UL +#define PGSTE_PCL_BIT 0x0080000000000000UL +#define PGSTE_HR_BIT 0x0040000000000000UL +#define PGSTE_HC_BIT 0x0020000000000000UL +#define PGSTE_GR_BIT 0x0004000000000000UL +#define PGSTE_GC_BIT 0x0002000000000000UL +#define PGSTE_UC_BIT 0x0000800000000000UL /* user dirty (migration) */ +#define PGSTE_IN_BIT 0x0000400000000000UL /* IPTE notify bit */ + +/* Guest Page State used for virtualization */ +#define _PGSTE_GPS_ZERO 0x0000000080000000UL +#define _PGSTE_GPS_USAGE_MASK 0x0000000003000000UL +#define _PGSTE_GPS_USAGE_STABLE 0x0000000000000000UL +#define _PGSTE_GPS_USAGE_UNUSED 0x0000000001000000UL /* * A user page table pointer has the space-switch-event bit, the @@ -393,14 +348,18 @@ /* * Page protection definitions. */ -#define PAGE_NONE __pgprot(_PAGE_TYPE_NONE) -#define PAGE_RO __pgprot(_PAGE_TYPE_RO) -#define PAGE_RW __pgprot(_PAGE_TYPE_RO | _PAGE_SWW) -#define PAGE_RWC __pgprot(_PAGE_TYPE_RW | _PAGE_SWW | _PAGE_SWC) - -#define PAGE_KERNEL PAGE_RWC -#define PAGE_SHARED PAGE_KERNEL -#define PAGE_COPY PAGE_RO +#define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_INVALID) +#define PAGE_READ __pgprot(_PAGE_PRESENT | _PAGE_READ | \ + _PAGE_INVALID | _PAGE_PROTECT) +#define PAGE_WRITE __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ + _PAGE_INVALID | _PAGE_PROTECT) + +#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ + _PAGE_YOUNG | _PAGE_DIRTY) +#define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ + _PAGE_YOUNG | _PAGE_DIRTY) +#define PAGE_KERNEL_RO __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_YOUNG | \ + _PAGE_PROTECT) /* * On s390 the page table entry has an invalid bit and a read-only bit. @@ -409,60 +368,68 @@ */ /*xwr*/ #define __P000 PAGE_NONE -#define __P001 PAGE_RO -#define __P010 PAGE_RO -#define __P011 PAGE_RO -#define __P100 PAGE_RO -#define __P101 PAGE_RO -#define __P110 PAGE_RO -#define __P111 PAGE_RO +#define __P001 PAGE_READ +#define __P010 PAGE_READ +#define __P011 PAGE_READ +#define __P100 PAGE_READ +#define __P101 PAGE_READ +#define __P110 PAGE_READ +#define __P111 PAGE_READ #define __S000 PAGE_NONE -#define __S001 PAGE_RO -#define __S010 PAGE_RW -#define __S011 PAGE_RW -#define __S100 PAGE_RO -#define __S101 PAGE_RO -#define __S110 PAGE_RW -#define __S111 PAGE_RW +#define __S001 PAGE_READ +#define __S010 PAGE_WRITE +#define __S011 PAGE_WRITE +#define __S100 PAGE_READ +#define __S101 PAGE_READ +#define __S110 PAGE_WRITE +#define __S111 PAGE_WRITE /* * Segment entry (large page) protection definitions. */ -#define SEGMENT_NONE __pgprot(_HPAGE_TYPE_NONE) -#define SEGMENT_RO __pgprot(_HPAGE_TYPE_RO) -#define SEGMENT_RW __pgprot(_HPAGE_TYPE_RW) +#define SEGMENT_NONE __pgprot(_SEGMENT_ENTRY_INVALID | \ + _SEGMENT_ENTRY_PROTECT) +#define SEGMENT_READ __pgprot(_SEGMENT_ENTRY_PROTECT | \ + _SEGMENT_ENTRY_READ) +#define SEGMENT_WRITE __pgprot(_SEGMENT_ENTRY_READ | \ + _SEGMENT_ENTRY_WRITE) + +static inline int mm_has_pgste(struct mm_struct *mm) +{ +#ifdef CONFIG_PGSTE + if (unlikely(mm->context.has_pgste)) + return 1; +#endif + return 0; +} -static inline int mm_exclusive(struct mm_struct *mm) +static inline int mm_alloc_pgste(struct mm_struct *mm) { - return likely(mm == current->active_mm && - atomic_read(&mm->context.attach_count) <= 1); +#ifdef CONFIG_PGSTE + if (unlikely(mm->context.alloc_pgste)) + return 1; +#endif + return 0; } -static inline int mm_has_pgste(struct mm_struct *mm) +/* + * In the case that a guest uses storage keys + * faults should no longer be backed by zero pages + */ +#define mm_forbids_zeropage mm_use_skey +static inline int mm_use_skey(struct mm_struct *mm) { #ifdef CONFIG_PGSTE - if (unlikely(mm->context.has_pgste)) + if (mm->context.use_skey) return 1; #endif return 0; } + /* * pgd/pmd/pte query functions */ -#ifndef CONFIG_64BIT - -static inline int pgd_present(pgd_t pgd) { return 1; } -static inline int pgd_none(pgd_t pgd) { return 0; } -static inline int pgd_bad(pgd_t pgd) { return 0; } - -static inline int pud_present(pud_t pud) { return 1; } -static inline int pud_none(pud_t pud) { return 0; } -static inline int pud_large(pud_t pud) { return 0; } -static inline int pud_bad(pud_t pud) { return 0; } - -#else /* CONFIG_64BIT */ - static inline int pgd_present(pgd_t pgd) { if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2) @@ -474,7 +441,7 @@ { if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2) return 0; - return (pgd_val(pgd) & _REGION_ENTRY_INV) != 0UL; + return (pgd_val(pgd) & _REGION_ENTRY_INVALID) != 0UL; } static inline int pgd_bad(pgd_t pgd) @@ -485,7 +452,7 @@ * invalid for either table entry. */ unsigned long mask = - ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV & + ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID & ~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH; return (pgd_val(pgd) & mask) != 0; } @@ -501,7 +468,7 @@ { if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3) return 0; - return (pud_val(pud) & _REGION_ENTRY_INV) != 0UL; + return (pud_val(pud) & _REGION_ENTRY_INVALID) != 0UL; } static inline int pud_large(pud_t pud) @@ -519,39 +486,41 @@ * invalid for either table entry. */ unsigned long mask = - ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV & + ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID & ~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH; return (pud_val(pud) & mask) != 0; } -#endif /* CONFIG_64BIT */ - static inline int pmd_present(pmd_t pmd) { - unsigned long mask = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO; - return (pmd_val(pmd) & mask) == _HPAGE_TYPE_NONE || - !(pmd_val(pmd) & _SEGMENT_ENTRY_INV); + return pmd_val(pmd) != _SEGMENT_ENTRY_INVALID; } static inline int pmd_none(pmd_t pmd) { - return (pmd_val(pmd) & _SEGMENT_ENTRY_INV) && - !(pmd_val(pmd) & _SEGMENT_ENTRY_RO); + return pmd_val(pmd) == _SEGMENT_ENTRY_INVALID; } static inline int pmd_large(pmd_t pmd) { -#ifdef CONFIG_64BIT - return !!(pmd_val(pmd) & _SEGMENT_ENTRY_LARGE); -#else - return 0; -#endif + return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0; +} + +static inline unsigned long pmd_pfn(pmd_t pmd) +{ + unsigned long origin_mask; + + origin_mask = _SEGMENT_ENTRY_ORIGIN; + if (pmd_large(pmd)) + origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE; + return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT; } static inline int pmd_bad(pmd_t pmd) { - unsigned long mask = ~_SEGMENT_ENTRY_ORIGIN & ~_SEGMENT_ENTRY_INV; - return (pmd_val(pmd) & mask) != _SEGMENT_ENTRY; + if (pmd_large(pmd)) + return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0; + return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0; } #define __HAVE_ARCH_PMDP_SPLITTING_FLUSH @@ -570,31 +539,42 @@ #define __HAVE_ARCH_PMD_WRITE static inline int pmd_write(pmd_t pmd) { - return (pmd_val(pmd) & _SEGMENT_ENTRY_RO) == 0; + return (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) != 0; } -static inline int pmd_young(pmd_t pmd) +static inline int pmd_dirty(pmd_t pmd) { - return 0; + int dirty = 1; + if (pmd_large(pmd)) + dirty = (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) != 0; + return dirty; } -static inline int pte_none(pte_t pte) +static inline int pmd_young(pmd_t pmd) { - return (pte_val(pte) & _PAGE_INVALID) && !(pte_val(pte) & _PAGE_SWT); + int young = 1; + if (pmd_large(pmd)) + young = (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0; + return young; } static inline int pte_present(pte_t pte) { - unsigned long mask = _PAGE_RO | _PAGE_INVALID | _PAGE_SWT | _PAGE_SWX; - return (pte_val(pte) & mask) == _PAGE_TYPE_NONE || - (!(pte_val(pte) & _PAGE_INVALID) && - !(pte_val(pte) & _PAGE_SWT)); + /* Bit pattern: (pte & 0x001) == 0x001 */ + return (pte_val(pte) & _PAGE_PRESENT) != 0; } -static inline int pte_file(pte_t pte) +static inline int pte_none(pte_t pte) { - unsigned long mask = _PAGE_RO | _PAGE_INVALID | _PAGE_SWT; - return (pte_val(pte) & mask) == _PAGE_TYPE_FILE; + /* Bit pattern: pte == 0x400 */ + return pte_val(pte) == _PAGE_INVALID; +} + +static inline int pte_swap(pte_t pte) +{ + /* Bit pattern: (pte & 0x201) == 0x200 */ + return (pte_val(pte) & (_PAGE_PROTECT | _PAGE_PRESENT)) + == _PAGE_PROTECT; } static inline int pte_special(pte_t pte) @@ -608,6 +588,56 @@ return pte_val(a) == pte_val(b); } +#ifdef CONFIG_NUMA_BALANCING +static inline int pte_protnone(pte_t pte) +{ + return pte_present(pte) && !(pte_val(pte) & _PAGE_READ); +} + +static inline int pmd_protnone(pmd_t pmd) +{ + /* pmd_large(pmd) implies pmd_present(pmd) */ + return pmd_large(pmd) && !(pmd_val(pmd) & _SEGMENT_ENTRY_READ); +} +#endif + +static inline int pte_soft_dirty(pte_t pte) +{ + return pte_val(pte) & _PAGE_SOFT_DIRTY; +} +#define pte_swp_soft_dirty pte_soft_dirty + +static inline pte_t pte_mksoft_dirty(pte_t pte) +{ + pte_val(pte) |= _PAGE_SOFT_DIRTY; + return pte; +} +#define pte_swp_mksoft_dirty pte_mksoft_dirty + +static inline pte_t pte_clear_soft_dirty(pte_t pte) +{ + pte_val(pte) &= ~_PAGE_SOFT_DIRTY; + return pte; +} +#define pte_swp_clear_soft_dirty pte_clear_soft_dirty + +static inline int pmd_soft_dirty(pmd_t pmd) +{ + return pmd_val(pmd) & _SEGMENT_ENTRY_SOFT_DIRTY; +} + +static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) +{ + pmd_val(pmd) |= _SEGMENT_ENTRY_SOFT_DIRTY; + return pmd; +} + +static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) +{ + pmd_val(pmd) &= ~_SEGMENT_ENTRY_SOFT_DIRTY; + return pmd; +} + static inline pgste_t pgste_get_lock(pte_t *ptep) { unsigned long new = 0; @@ -618,8 +648,8 @@ asm( " lg %0,%2\n" "0: lgr %1,%0\n" - " nihh %0,0xff7f\n" /* clear RCP_PCL_BIT in old */ - " oihh %1,0x0080\n" /* set RCP_PCL_BIT in new */ + " nihh %0,0xff7f\n" /* clear PCL bit in old */ + " oihh %1,0x0080\n" /* set PCL bit in new */ " csg %0,%1,%2\n" " jl 0b\n" : "=&d" (old), "=&d" (new), "=Q" (ptep[PTRS_PER_PTE]) @@ -632,7 +662,7 @@ { #ifdef CONFIG_PGSTE asm( - " nihh %1,0xff7f\n" /* clear RCP_PCL_BIT */ + " nihh %1,0xff7f\n" /* clear PCL bit */ " stg %1,%0\n" : "=Q" (ptep[PTRS_PER_PTE]) : "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE]) @@ -641,6 +671,15 @@ #endif } +static inline pgste_t pgste_get(pte_t *ptep) +{ + unsigned long pgste = 0; +#ifdef CONFIG_PGSTE + pgste = *(unsigned long *)(ptep + PTRS_PER_PTE); +#endif + return __pgste(pgste); +} + static inline void pgste_set(pte_t *ptep, pgste_t pgste) { #ifdef CONFIG_PGSTE @@ -648,73 +687,35 @@ #endif } -static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste) +static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste, + struct mm_struct *mm) { #ifdef CONFIG_PGSTE - unsigned long address, bits; - unsigned char skey; + unsigned long address, bits, skey; - if (pte_val(*ptep) & _PAGE_INVALID) + if (!mm_use_skey(mm) || pte_val(*ptep) & _PAGE_INVALID) return pgste; address = pte_val(*ptep) & PAGE_MASK; - skey = page_get_storage_key(address); + skey = (unsigned long) page_get_storage_key(address); bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED); - /* Clear page changed & referenced bit in the storage key */ - if (bits & _PAGE_CHANGED) - page_set_storage_key(address, skey ^ bits, 0); - else if (bits) - page_reset_referenced(address); /* Transfer page changed & referenced bit to guest bits in pgste */ - pgste_val(pgste) |= bits << 48; /* RCP_GR_BIT & RCP_GC_BIT */ - /* Get host changed & referenced bits from pgste */ - bits |= (pgste_val(pgste) & (RCP_HR_BIT | RCP_HC_BIT)) >> 52; - /* Transfer page changed & referenced bit to kvm user bits */ - pgste_val(pgste) |= bits << 45; /* KVM_UR_BIT & KVM_UC_BIT */ - /* Clear relevant host bits in pgste. */ - pgste_val(pgste) &= ~(RCP_HR_BIT | RCP_HC_BIT); - pgste_val(pgste) &= ~(RCP_ACC_BITS | RCP_FP_BIT); + pgste_val(pgste) |= bits << 48; /* GR bit & GC bit */ /* Copy page access key and fetch protection bit to pgste */ - pgste_val(pgste) |= - (unsigned long) (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; - /* Transfer referenced bit to pte */ - pte_val(*ptep) |= (bits & _PAGE_REFERENCED) << 1; + pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT); + pgste_val(pgste) |= (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; #endif return pgste; } -static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste) -{ -#ifdef CONFIG_PGSTE - int young; - - if (pte_val(*ptep) & _PAGE_INVALID) - return pgste; - /* Get referenced bit from storage key */ - young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK); - if (young) - pgste_val(pgste) |= RCP_GR_BIT; - /* Get host referenced bit from pgste */ - if (pgste_val(pgste) & RCP_HR_BIT) { - pgste_val(pgste) &= ~RCP_HR_BIT; - young = 1; - } - /* Transfer referenced bit to kvm user bits and pte */ - if (young) { - pgste_val(pgste) |= KVM_UR_BIT; - pte_val(*ptep) |= _PAGE_SWR; - } -#endif - return pgste; -} - -static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry) +static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry, + struct mm_struct *mm) { #ifdef CONFIG_PGSTE unsigned long address; unsigned long nkey; - if (pte_val(entry) & _PAGE_INVALID) + if (!mm_use_skey(mm) || pte_val(entry) & _PAGE_INVALID) return; VM_BUG_ON(!(pte_val(*ptep) & _PAGE_INVALID)); address = pte_val(entry) & PAGE_MASK; @@ -723,60 +724,56 @@ * The guest C/R information is still in the PGSTE, set real * key C/R to 0. */ - nkey = (pgste_val(pgste) & (RCP_ACC_BITS | RCP_FP_BIT)) >> 56; + nkey = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56; + nkey |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48; page_set_storage_key(address, nkey, 0); #endif } -static inline void pgste_set_pte(pte_t *ptep, pte_t entry) +static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry) { - if (!MACHINE_HAS_ESOP && (pte_val(entry) & _PAGE_SWW)) { - /* - * Without enhanced suppression-on-protection force - * the dirty bit on for all writable ptes. - */ - pte_val(entry) |= _PAGE_SWC; - pte_val(entry) &= ~_PAGE_RO; + if ((pte_val(entry) & _PAGE_PRESENT) && + (pte_val(entry) & _PAGE_WRITE) && + !(pte_val(entry) & _PAGE_INVALID)) { + if (!MACHINE_HAS_ESOP) { + /* + * Without enhanced suppression-on-protection force + * the dirty bit on for all writable ptes. + */ + pte_val(entry) |= _PAGE_DIRTY; + pte_val(entry) &= ~_PAGE_PROTECT; + } + if (!(pte_val(entry) & _PAGE_PROTECT)) + /* This pte allows write access, set user-dirty */ + pgste_val(pgste) |= PGSTE_UC_BIT; } *ptep = entry; + return pgste; } /** * struct gmap_struct - guest address space + * @crst_list: list of all crst tables used in the guest address space * @mm: pointer to the parent mm_struct + * @guest_to_host: radix tree with guest to host address translation + * @host_to_guest: radix tree with pointer to segment table entries + * @guest_table_lock: spinlock to protect all entries in the guest page table * @table: pointer to the page directory * @asce: address space control element for gmap page table - * @crst_list: list of all crst tables used in the guest address space + * @pfault_enabled: defines if pfaults are applicable for the guest */ struct gmap { struct list_head list; + struct list_head crst_list; struct mm_struct *mm; + struct radix_tree_root guest_to_host; + struct radix_tree_root host_to_guest; + spinlock_t guest_table_lock; unsigned long *table; unsigned long asce; - struct list_head crst_list; -}; - -/** - * struct gmap_rmap - reverse mapping for segment table entries - * @gmap: pointer to the gmap_struct - * @entry: pointer to a segment table entry - * @vmaddr: virtual address in the guest address space - */ -struct gmap_rmap { - struct list_head list; - struct gmap *gmap; - unsigned long *entry; - unsigned long vmaddr; -}; - -/** - * struct gmap_pgtable - gmap information attached to a page table - * @vmaddr: address of the 1MB segment in the process virtual memory - * @mapper: list of segment table entries mapping a page table - */ -struct gmap_pgtable { - unsigned long vmaddr; - struct list_head mapper; + unsigned long asce_end; + void *private; + bool pfault_enabled; }; /** @@ -785,21 +782,24 @@ */ struct gmap_notifier { struct list_head list; - void (*notifier_call)(struct gmap *gmap, unsigned long address); + void (*notifier_call)(struct gmap *gmap, unsigned long gaddr); }; -struct gmap *gmap_alloc(struct mm_struct *mm); +struct gmap *gmap_alloc(struct mm_struct *mm, unsigned long limit); void gmap_free(struct gmap *gmap); void gmap_enable(struct gmap *gmap); void gmap_disable(struct gmap *gmap); int gmap_map_segment(struct gmap *gmap, unsigned long from, unsigned long to, unsigned long len); int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len); -unsigned long __gmap_translate(unsigned long address, struct gmap *); -unsigned long gmap_translate(unsigned long address, struct gmap *); -unsigned long __gmap_fault(unsigned long address, struct gmap *); -unsigned long gmap_fault(unsigned long address, struct gmap *); -void gmap_discard(unsigned long from, unsigned long to, struct gmap *); +unsigned long __gmap_translate(struct gmap *, unsigned long gaddr); +unsigned long gmap_translate(struct gmap *, unsigned long gaddr); +int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr); +int gmap_fault(struct gmap *, unsigned long gaddr, unsigned int fault_flags); +void gmap_discard(struct gmap *, unsigned long from, unsigned long to); +void __gmap_zap(struct gmap *, unsigned long gaddr); +bool gmap_test_and_clear_dirty(unsigned long address, struct gmap *); + void gmap_register_ipte_notifier(struct gmap_notifier *); void gmap_unregister_ipte_notifier(struct gmap_notifier *); @@ -811,8 +811,8 @@ pte_t *ptep, pgste_t pgste) { #ifdef CONFIG_PGSTE - if (pgste_val(pgste) & RCP_IN_BIT) { - pgste_val(pgste) &= ~RCP_IN_BIT; + if (pgste_val(pgste) & PGSTE_IN_BIT) { + pgste_val(pgste) &= ~PGSTE_IN_BIT; gmap_do_ipte_notify(mm, addr, ptep); } #endif @@ -831,12 +831,11 @@ if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); - pgste_set_key(ptep, pgste, entry); - pgste_set_pte(ptep, entry); + pgste_val(pgste) &= ~_PGSTE_GPS_ZERO; + pgste_set_key(ptep, pgste, entry, mm); + pgste = pgste_set_pte(ptep, pgste, entry); pgste_set_unlock(ptep, pgste); } else { - if (!(pte_val(entry) & _PAGE_INVALID) && MACHINE_HAS_EDAT1) - pte_val(entry) |= _PAGE_CO; *ptep = entry; } } @@ -847,21 +846,23 @@ */ static inline int pte_write(pte_t pte) { - return (pte_val(pte) & _PAGE_SWW) != 0; + return (pte_val(pte) & _PAGE_WRITE) != 0; } static inline int pte_dirty(pte_t pte) { - return (pte_val(pte) & _PAGE_SWC) != 0; + return (pte_val(pte) & _PAGE_DIRTY) != 0; } static inline int pte_young(pte_t pte) { -#ifdef CONFIG_PGSTE - if (pte_val(pte) & _PAGE_SWR) - return 1; -#endif - return 0; + return (pte_val(pte) & _PAGE_YOUNG) != 0; +} + +#define __HAVE_ARCH_PTE_UNUSED +static inline int pte_unused(pte_t pte) +{ + return pte_val(pte) & _PAGE_UNUSED; } /* @@ -870,28 +871,24 @@ static inline void pgd_clear(pgd_t *pgd) { -#ifdef CONFIG_64BIT if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2) pgd_val(*pgd) = _REGION2_ENTRY_EMPTY; -#endif } static inline void pud_clear(pud_t *pud) { -#ifdef CONFIG_64BIT if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) pud_val(*pud) = _REGION3_ENTRY_EMPTY; -#endif } static inline void pmd_clear(pmd_t *pmdp) { - pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY; + pmd_val(*pmdp) = _SEGMENT_ENTRY_INVALID; } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + pte_val(*ptep) = _PAGE_INVALID; } /* @@ -902,55 +899,63 @@ { pte_val(pte) &= _PAGE_CHG_MASK; pte_val(pte) |= pgprot_val(newprot); - if ((pte_val(pte) & _PAGE_SWC) && (pte_val(pte) & _PAGE_SWW)) - pte_val(pte) &= ~_PAGE_RO; + /* + * newprot for PAGE_NONE, PAGE_READ and PAGE_WRITE has the + * invalid bit set, clear it again for readable, young pages + */ + if ((pte_val(pte) & _PAGE_YOUNG) && (pte_val(pte) & _PAGE_READ)) + pte_val(pte) &= ~_PAGE_INVALID; + /* + * newprot for PAGE_READ and PAGE_WRITE has the page protection + * bit set, clear it again for writable, dirty pages + */ + if ((pte_val(pte) & _PAGE_DIRTY) && (pte_val(pte) & _PAGE_WRITE)) + pte_val(pte) &= ~_PAGE_PROTECT; return pte; } static inline pte_t pte_wrprotect(pte_t pte) { - pte_val(pte) &= ~_PAGE_SWW; - /* Do not clobber _PAGE_TYPE_NONE pages! */ - if (!(pte_val(pte) & _PAGE_INVALID)) - pte_val(pte) |= _PAGE_RO; + pte_val(pte) &= ~_PAGE_WRITE; + pte_val(pte) |= _PAGE_PROTECT; return pte; } static inline pte_t pte_mkwrite(pte_t pte) { - pte_val(pte) |= _PAGE_SWW; - if (pte_val(pte) & _PAGE_SWC) - pte_val(pte) &= ~_PAGE_RO; + pte_val(pte) |= _PAGE_WRITE; + if (pte_val(pte) & _PAGE_DIRTY) + pte_val(pte) &= ~_PAGE_PROTECT; return pte; } static inline pte_t pte_mkclean(pte_t pte) { - pte_val(pte) &= ~_PAGE_SWC; - /* Do not clobber _PAGE_TYPE_NONE pages! */ - if (!(pte_val(pte) & _PAGE_INVALID)) - pte_val(pte) |= _PAGE_RO; + pte_val(pte) &= ~_PAGE_DIRTY; + pte_val(pte) |= _PAGE_PROTECT; return pte; } static inline pte_t pte_mkdirty(pte_t pte) { - pte_val(pte) |= _PAGE_SWC; - if (pte_val(pte) & _PAGE_SWW) - pte_val(pte) &= ~_PAGE_RO; + pte_val(pte) |= _PAGE_DIRTY | _PAGE_SOFT_DIRTY; + if (pte_val(pte) & _PAGE_WRITE) + pte_val(pte) &= ~_PAGE_PROTECT; return pte; } static inline pte_t pte_mkold(pte_t pte) { -#ifdef CONFIG_PGSTE - pte_val(pte) &= ~_PAGE_SWR; -#endif + pte_val(pte) &= ~_PAGE_YOUNG; + pte_val(pte) |= _PAGE_INVALID; return pte; } static inline pte_t pte_mkyoung(pte_t pte) { + pte_val(pte) |= _PAGE_YOUNG; + if (pte_val(pte) & _PAGE_READ) + pte_val(pte) &= ~_PAGE_INVALID; return pte; } @@ -963,48 +968,105 @@ #ifdef CONFIG_HUGETLB_PAGE static inline pte_t pte_mkhuge(pte_t pte) { - pte_val(pte) |= (_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO); + pte_val(pte) |= _PAGE_LARGE; return pte; } #endif -/* - * Get (and clear) the user dirty bit for a pte. - */ -static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm, - pte_t *ptep) +static inline void __ptep_ipte(unsigned long address, pte_t *ptep) { - pgste_t pgste; - int dirty = 0; + unsigned long pto = (unsigned long) ptep; - if (mm_has_pgste(mm)) { - pgste = pgste_get_lock(ptep); - pgste = pgste_update_all(ptep, pgste); - dirty = !!(pgste_val(pgste) & KVM_UC_BIT); - pgste_val(pgste) &= ~KVM_UC_BIT; - pgste_set_unlock(ptep, pgste); - return dirty; - } - return dirty; + /* Invalidation + global TLB flush for the pte */ + asm volatile( + " ipte %2,%3" + : "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address)); +} + +static inline void __ptep_ipte_local(unsigned long address, pte_t *ptep) +{ + unsigned long pto = (unsigned long) ptep; + + /* Invalidation + local TLB flush for the pte */ + asm volatile( + " .insn rrf,0xb2210000,%2,%3,0,1" + : "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address)); +} + +static inline void __ptep_ipte_range(unsigned long address, int nr, pte_t *ptep) +{ + unsigned long pto = (unsigned long) ptep; + + /* Invalidate a range of ptes + global TLB flush of the ptes */ + do { + asm volatile( + " .insn rrf,0xb2210000,%2,%0,%1,0" + : "+a" (address), "+a" (nr) : "a" (pto) : "memory"); + } while (nr != 255); +} + +static inline void ptep_flush_direct(struct mm_struct *mm, + unsigned long address, pte_t *ptep) +{ + int active, count; + + if (pte_val(*ptep) & _PAGE_INVALID) + return; + active = (mm == current->active_mm) ? 1 : 0; + count = atomic_add_return(0x10000, &mm->context.attach_count); + if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active && + cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) + __ptep_ipte_local(address, ptep); + else + __ptep_ipte(address, ptep); + atomic_sub(0x10000, &mm->context.attach_count); +} + +static inline void ptep_flush_lazy(struct mm_struct *mm, + unsigned long address, pte_t *ptep) +{ + int active, count; + + if (pte_val(*ptep) & _PAGE_INVALID) + return; + active = (mm == current->active_mm) ? 1 : 0; + count = atomic_add_return(0x10000, &mm->context.attach_count); + if ((count & 0xffff) <= active) { + pte_val(*ptep) |= _PAGE_INVALID; + mm->context.flush_mm = 1; + } else + __ptep_ipte(address, ptep); + atomic_sub(0x10000, &mm->context.attach_count); } /* - * Get (and clear) the user referenced bit for a pte. + * Get (and clear) the user dirty bit for a pte. */ -static inline int ptep_test_and_clear_user_young(struct mm_struct *mm, +static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) { pgste_t pgste; - int young = 0; + pte_t pte; + int dirty; - if (mm_has_pgste(mm)) { - pgste = pgste_get_lock(ptep); - pgste = pgste_update_young(ptep, pgste); - young = !!(pgste_val(pgste) & KVM_UR_BIT); - pgste_val(pgste) &= ~KVM_UR_BIT; - pgste_set_unlock(ptep, pgste); + if (!mm_has_pgste(mm)) + return 0; + pgste = pgste_get_lock(ptep); + dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT); + pgste_val(pgste) &= ~PGSTE_UC_BIT; + pte = *ptep; + if (dirty && (pte_val(pte) & _PAGE_PRESENT)) { + pgste = pgste_ipte_notify(mm, addr, ptep, pgste); + __ptep_ipte(addr, ptep); + if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE)) + pte_val(pte) |= _PAGE_PROTECT; + else + pte_val(pte) |= _PAGE_INVALID; + *ptep = pte; } - return young; + pgste_set_unlock(ptep, pgste); + return dirty; } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG @@ -1012,47 +1074,36 @@ unsigned long addr, pte_t *ptep) { pgste_t pgste; - pte_t pte; + pte_t pte, oldpte; + int young; if (mm_has_pgste(vma->vm_mm)) { pgste = pgste_get_lock(ptep); - pgste = pgste_update_young(ptep, pgste); - pte = *ptep; - *ptep = pte_mkold(pte); - pgste_set_unlock(ptep, pgste); - return pte_young(pte); + pgste = pgste_ipte_notify(vma->vm_mm, addr, ptep, pgste); } - return 0; + + oldpte = pte = *ptep; + ptep_flush_direct(vma->vm_mm, addr, ptep); + young = pte_young(pte); + pte = pte_mkold(pte); + + if (mm_has_pgste(vma->vm_mm)) { + pgste = pgste_update_all(&oldpte, pgste, vma->vm_mm); + pgste = pgste_set_pte(ptep, pgste, pte); + pgste_set_unlock(ptep, pgste); + } else + *ptep = pte; + + return young; } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH static inline int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - /* No need to flush TLB - * On s390 reference bits are in storage key and never in TLB - * With virtualization we handle the reference bit, without we - * we can simply return */ return ptep_test_and_clear_young(vma, address, ptep); } -static inline void __ptep_ipte(unsigned long address, pte_t *ptep) -{ - if (!(pte_val(*ptep) & _PAGE_INVALID)) { -#ifndef CONFIG_64BIT - /* pto must point to the start of the segment table */ - pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00); -#else - /* ipte in zarch mode can do the math */ - pte_t *pto = ptep; -#endif - asm volatile( - " ipte %2,%3" - : "=m" (*ptep) : "m" (*ptep), - "a" (pto), "a" (address)); - } -} - /* * This is hard to understand. ptep_get_and_clear and ptep_clear_flush * both clear the TLB for the unmapped pte. The reason is that @@ -1073,19 +1124,17 @@ pgste_t pgste; pte_t pte; - mm->context.flush_mm = 1; if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); pgste = pgste_ipte_notify(mm, address, ptep, pgste); } pte = *ptep; - if (!mm_exclusive(mm)) - __ptep_ipte(address, ptep); - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + ptep_flush_lazy(mm, address, ptep); + pte_val(*ptep) = _PAGE_INVALID; if (mm_has_pgste(mm)) { - pgste = pgste_update_all(&pte, pgste); + pgste = pgste_update_all(&pte, pgste, mm); pgste_set_unlock(ptep, pgste); } return pte; @@ -1099,18 +1148,16 @@ pgste_t pgste; pte_t pte; - mm->context.flush_mm = 1; if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); pgste_ipte_notify(mm, address, ptep, pgste); } pte = *ptep; - if (!mm_exclusive(mm)) - __ptep_ipte(address, ptep); + ptep_flush_lazy(mm, address, ptep); if (mm_has_pgste(mm)) { - pgste = pgste_update_all(&pte, pgste); + pgste = pgste_update_all(&pte, pgste, mm); pgste_set(ptep, pgste); } return pte; @@ -1123,9 +1170,9 @@ pgste_t pgste; if (mm_has_pgste(mm)) { - pgste = *(pgste_t *)(ptep + PTRS_PER_PTE); - pgste_set_key(ptep, pgste, pte); - pgste_set_pte(ptep, pte); + pgste = pgste_get(ptep); + pgste_set_key(ptep, pgste, pte, mm); + pgste = pgste_set_pte(ptep, pgste, pte); pgste_set_unlock(ptep, pgste); } else *ptep = pte; @@ -1144,11 +1191,14 @@ } pte = *ptep; - __ptep_ipte(address, ptep); - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + ptep_flush_direct(vma->vm_mm, address, ptep); + pte_val(*ptep) = _PAGE_INVALID; if (mm_has_pgste(vma->vm_mm)) { - pgste = pgste_update_all(&pte, pgste); + if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) == + _PGSTE_GPS_USAGE_UNUSED) + pte_val(pte) |= _PAGE_UNUSED; + pgste = pgste_update_all(&pte, pgste, vma->vm_mm); pgste_set_unlock(ptep, pgste); } return pte; @@ -1169,19 +1219,18 @@ pgste_t pgste; pte_t pte; - if (mm_has_pgste(mm)) { + if (!full && mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); - if (!full) - pgste = pgste_ipte_notify(mm, address, ptep, pgste); + pgste = pgste_ipte_notify(mm, address, ptep, pgste); } pte = *ptep; if (!full) - __ptep_ipte(address, ptep); - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + ptep_flush_lazy(mm, address, ptep); + pte_val(*ptep) = _PAGE_INVALID; - if (mm_has_pgste(mm)) { - pgste = pgste_update_all(&pte, pgste); + if (!full && mm_has_pgste(mm)) { + pgste = pgste_update_all(&pte, pgste, mm); pgste_set_unlock(ptep, pgste); } return pte; @@ -1195,18 +1244,16 @@ pte_t pte = *ptep; if (pte_write(pte)) { - mm->context.flush_mm = 1; if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); pgste = pgste_ipte_notify(mm, address, ptep, pgste); } - if (!mm_exclusive(mm)) - __ptep_ipte(address, ptep); + ptep_flush_lazy(mm, address, ptep); pte = pte_wrprotect(pte); if (mm_has_pgste(mm)) { - pgste_set_pte(ptep, pte); + pgste = pgste_set_pte(ptep, pgste, pte); pgste_set_unlock(ptep, pgste); } else *ptep = pte; @@ -1220,18 +1267,22 @@ pte_t entry, int dirty) { pgste_t pgste; + pte_t oldpte; - if (pte_same(*ptep, entry)) + oldpte = *ptep; + if (pte_same(oldpte, entry)) return 0; if (mm_has_pgste(vma->vm_mm)) { pgste = pgste_get_lock(ptep); pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste); } - __ptep_ipte(address, ptep); + ptep_flush_direct(vma->vm_mm, address, ptep); if (mm_has_pgste(vma->vm_mm)) { - pgste_set_pte(ptep, entry); + if (pte_val(oldpte) & _PAGE_INVALID) + pgste_set_key(ptep, pgste, entry, vma->vm_mm); + pgste = pgste_set_pte(ptep, pgste, entry); pgste_set_unlock(ptep, pgste); } else *ptep = entry; @@ -1246,7 +1297,7 @@ { pte_t __pte; pte_val(__pte) = physpage + pgprot_val(pgprot); - return __pte; + return pte_mkyoung(__pte); } static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) @@ -1254,10 +1305,8 @@ unsigned long physpage = page_to_phys(page); pte_t __pte = mk_pte_phys(physpage, pgprot); - if ((pte_val(__pte) & _PAGE_SWW) && PageDirty(page)) { - pte_val(__pte) |= _PAGE_SWC; - pte_val(__pte) &= ~_PAGE_RO; - } + if (pte_write(__pte) && PageDirty(page)) + __pte = pte_mkdirty(__pte); return __pte; } @@ -1269,17 +1318,6 @@ #define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) #define pgd_offset_k(address) pgd_offset(&init_mm, address) -#ifndef CONFIG_64BIT - -#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN) -#define pud_deref(pmd) ({ BUG(); 0UL; }) -#define pgd_deref(pmd) ({ BUG(); 0UL; }) - -#define pud_offset(pgd, address) ((pud_t *) pgd) -#define pmd_offset(pud, address) ((pmd_t *) pud + pmd_index(address)) - -#else /* CONFIG_64BIT */ - #define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN) #define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN) #define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN) @@ -1300,13 +1338,11 @@ return pmd + pmd_index(address); } -#endif /* CONFIG_64BIT */ - #define pfn_pte(pfn,pgprot) mk_pte_phys(__pa((pfn) << PAGE_SHIFT),(pgprot)) #define pte_pfn(x) (pte_val(x) >> PAGE_SHIFT) #define pte_page(x) pfn_to_page(pte_pfn(x)) -#define pmd_page(pmd) pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT) +#define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) /* Find an entry in the lowest level page table.. */ #define pte_offset(pmd, addr) ((pte_t *) pmd_deref(*(pmd)) + pte_index(addr)) @@ -1314,39 +1350,90 @@ #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address) #define pte_unmap(pte) do { } while (0) -static inline void __pmd_idte(unsigned long address, pmd_t *pmdp) -{ - unsigned long sto = (unsigned long) pmdp - - pmd_index(address) * sizeof(pmd_t); - - if (!(pmd_val(*pmdp) & _SEGMENT_ENTRY_INV)) { - asm volatile( - " .insn rrf,0xb98e0000,%2,%3,0,0" - : "=m" (*pmdp) - : "m" (*pmdp), "a" (sto), - "a" ((address & HPAGE_MASK)) - : "cc" - ); - } -} - #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE) static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot) { /* - * pgprot is PAGE_NONE, PAGE_RO, or PAGE_RW (see __Pxxx / __Sxxx) + * pgprot is PAGE_NONE, PAGE_READ, or PAGE_WRITE (see __Pxxx / __Sxxx) * Convert to segment table entry format. */ if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE)) return pgprot_val(SEGMENT_NONE); - if (pgprot_val(pgprot) == pgprot_val(PAGE_RO)) - return pgprot_val(SEGMENT_RO); - return pgprot_val(SEGMENT_RW); + if (pgprot_val(pgprot) == pgprot_val(PAGE_READ)) + return pgprot_val(SEGMENT_READ); + return pgprot_val(SEGMENT_WRITE); +} + +static inline pmd_t pmd_wrprotect(pmd_t pmd) +{ + pmd_val(pmd) &= ~_SEGMENT_ENTRY_WRITE; + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; + return pmd; +} + +static inline pmd_t pmd_mkwrite(pmd_t pmd) +{ + pmd_val(pmd) |= _SEGMENT_ENTRY_WRITE; + if (pmd_large(pmd) && !(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) + return pmd; + pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; + return pmd; +} + +static inline pmd_t pmd_mkclean(pmd_t pmd) +{ + if (pmd_large(pmd)) { + pmd_val(pmd) &= ~_SEGMENT_ENTRY_DIRTY; + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; + } + return pmd; +} + +static inline pmd_t pmd_mkdirty(pmd_t pmd) +{ + if (pmd_large(pmd)) { + pmd_val(pmd) |= _SEGMENT_ENTRY_DIRTY | + _SEGMENT_ENTRY_SOFT_DIRTY; + if (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; + } + return pmd; +} + +static inline pmd_t pmd_mkyoung(pmd_t pmd) +{ + if (pmd_large(pmd)) { + pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG; + if (pmd_val(pmd) & _SEGMENT_ENTRY_READ) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID; + } + return pmd; +} + +static inline pmd_t pmd_mkold(pmd_t pmd) +{ + if (pmd_large(pmd)) { + pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG; + pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; + } + return pmd; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { - pmd_val(pmd) &= _SEGMENT_CHG_MASK; + if (pmd_large(pmd)) { + pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN_LARGE | + _SEGMENT_ENTRY_DIRTY | _SEGMENT_ENTRY_YOUNG | + _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_SPLIT | + _SEGMENT_ENTRY_SOFT_DIRTY; + pmd_val(pmd) |= massage_pgprot_pmd(newprot); + if (!(pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY)) + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; + if (!(pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG)) + pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; + return pmd; + } + pmd_val(pmd) &= _SEGMENT_ENTRY_ORIGIN; pmd_val(pmd) |= massage_pgprot_pmd(newprot); return pmd; } @@ -1358,123 +1445,162 @@ return __pmd; } -static inline pmd_t pmd_mkwrite(pmd_t pmd) +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLB_PAGE */ + +static inline void __pmdp_csp(pmd_t *pmdp) { - /* Do not clobber _HPAGE_TYPE_NONE pages! */ - if (!(pmd_val(pmd) & _SEGMENT_ENTRY_INV)) - pmd_val(pmd) &= ~_SEGMENT_ENTRY_RO; - return pmd; + register unsigned long reg2 asm("2") = pmd_val(*pmdp); + register unsigned long reg3 asm("3") = pmd_val(*pmdp) | + _SEGMENT_ENTRY_INVALID; + register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5; + + asm volatile( + " csp %1,%3" + : "=m" (*pmdp) + : "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc"); +} + +static inline void __pmdp_idte(unsigned long address, pmd_t *pmdp) +{ + unsigned long sto; + + sto = (unsigned long) pmdp - pmd_index(address) * sizeof(pmd_t); + asm volatile( + " .insn rrf,0xb98e0000,%2,%3,0,0" + : "=m" (*pmdp) + : "m" (*pmdp), "a" (sto), "a" ((address & HPAGE_MASK)) + : "cc" ); +} + +static inline void __pmdp_idte_local(unsigned long address, pmd_t *pmdp) +{ + unsigned long sto; + + sto = (unsigned long) pmdp - pmd_index(address) * sizeof(pmd_t); + asm volatile( + " .insn rrf,0xb98e0000,%2,%3,0,1" + : "=m" (*pmdp) + : "m" (*pmdp), "a" (sto), "a" ((address & HPAGE_MASK)) + : "cc" ); +} + +static inline void pmdp_flush_direct(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + int active, count; + + if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID) + return; + if (!MACHINE_HAS_IDTE) { + __pmdp_csp(pmdp); + return; + } + active = (mm == current->active_mm) ? 1 : 0; + count = atomic_add_return(0x10000, &mm->context.attach_count); + if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active && + cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) + __pmdp_idte_local(address, pmdp); + else + __pmdp_idte(address, pmdp); + atomic_sub(0x10000, &mm->context.attach_count); +} + +static inline void pmdp_flush_lazy(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + int active, count; + + if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID) + return; + active = (mm == current->active_mm) ? 1 : 0; + count = atomic_add_return(0x10000, &mm->context.attach_count); + if ((count & 0xffff) <= active) { + pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID; + mm->context.flush_mm = 1; + } else if (MACHINE_HAS_IDTE) + __pmdp_idte(address, pmdp); + else + __pmdp_csp(pmdp); + atomic_sub(0x10000, &mm->context.attach_count); } -#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLB_PAGE */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PGTABLE_DEPOSIT -extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable); +extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable); #define __HAVE_ARCH_PGTABLE_WITHDRAW -extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm); +extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); static inline int pmd_trans_splitting(pmd_t pmd) { - return pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT; + return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) && + (pmd_val(pmd) & _SEGMENT_ENTRY_SPLIT); } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t entry) { - if (!(pmd_val(entry) & _SEGMENT_ENTRY_INV) && MACHINE_HAS_EDAT1) - pmd_val(entry) |= _SEGMENT_ENTRY_CO; *pmdp = entry; } static inline pmd_t pmd_mkhuge(pmd_t pmd) { pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE; + pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG; + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; return pmd; } -static inline pmd_t pmd_wrprotect(pmd_t pmd) +#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) { - pmd_val(pmd) |= _SEGMENT_ENTRY_RO; - return pmd; -} + pmd_t pmd; -static inline pmd_t pmd_mkdirty(pmd_t pmd) -{ - /* No dirty bit in the segment table entry. */ - return pmd; + pmd = *pmdp; + pmdp_flush_direct(vma->vm_mm, address, pmdp); + *pmdp = pmd_mkold(pmd); + return pmd_young(pmd); } -static inline pmd_t pmd_mkold(pmd_t pmd) +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) { - /* No referenced bit in the segment table entry. */ - return pmd; -} + pmd_t pmd = *pmdp; -static inline pmd_t pmd_mkyoung(pmd_t pmd) -{ - /* No referenced bit in the segment table entry. */ + pmdp_flush_direct(mm, address, pmdp); + pmd_clear(pmdp); return pmd; } -#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG -static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) -{ - unsigned long pmd_addr = pmd_val(*pmdp) & HPAGE_MASK; - long tmp, rc; - int counter; - - rc = 0; - if (MACHINE_HAS_RRBM) { - counter = PTRS_PER_PTE >> 6; - asm volatile( - "0: .insn rre,0xb9ae0000,%0,%3\n" /* rrbm */ - " ogr %1,%0\n" - " la %3,0(%4,%3)\n" - " brct %2,0b\n" - : "=&d" (tmp), "+&d" (rc), "+d" (counter), - "+a" (pmd_addr) - : "a" (64 * 4096UL) : "cc"); - rc = !!rc; - } else { - counter = PTRS_PER_PTE; - asm volatile( - "0: rrbe 0,%2\n" - " la %2,0(%3,%2)\n" - " brc 12,1f\n" - " lhi %0,1\n" - "1: brct %1,0b\n" - : "+d" (rc), "+d" (counter), "+a" (pmd_addr) - : "a" (4096UL) : "cc"); - } - return rc; -} - -#define __HAVE_ARCH_PMDP_GET_AND_CLEAR -static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm, - unsigned long address, pmd_t *pmdp) +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL +static inline pmd_t pmdp_huge_get_and_clear_full(struct mm_struct *mm, + unsigned long address, + pmd_t *pmdp, int full) { pmd_t pmd = *pmdp; - __pmd_idte(address, pmdp); + if (!full) + pmdp_flush_lazy(mm, address, pmdp); pmd_clear(pmdp); return pmd; } -#define __HAVE_ARCH_PMDP_CLEAR_FLUSH -static inline pmd_t pmdp_clear_flush(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmdp) +#define __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH +static inline pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) { - return pmdp_get_and_clear(vma->vm_mm, address, pmdp); + return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); } #define __HAVE_ARCH_PMDP_INVALIDATE static inline void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { - __pmd_idte(address, pmdp); + pmdp_flush_direct(vma->vm_mm, address, pmdp); } #define __HAVE_ARCH_PMDP_SET_WRPROTECT @@ -1484,11 +1610,19 @@ pmd_t pmd = *pmdp; if (pmd_write(pmd)) { - __pmd_idte(address, pmdp); + pmdp_flush_direct(mm, address, pmdp); set_pmd_at(mm, address, pmdp, pmd_wrprotect(pmd)); } } +static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, + pmd_t *pmdp) +{ + return pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); +} +#define pmdp_collapse_flush pmdp_collapse_flush + #define pfn_pmd(pfn, pgprot) mk_pmd_phys(__pa((pfn) << PAGE_SHIFT), (pgprot)) #define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot)) @@ -1501,82 +1635,58 @@ { return MACHINE_HAS_HPAGE ? 1 : 0; } - -static inline unsigned long pmd_pfn(pmd_t pmd) -{ - return pmd_val(pmd) >> PAGE_SHIFT; -} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* - * 31 bit swap entry format: - * A page-table entry has some bits we have to treat in a special way. - * Bits 0, 20 and bit 23 have to be zero, otherwise an specification - * exception will occur instead of a page translation exception. The - * specifiation exception has the bad habit not to store necessary - * information in the lowcore. - * Bit 21 and bit 22 are the page invalid bit and the page protection - * bit. We set both to indicate a swapped page. - * Bit 30 and 31 are used to distinguish the different page types. For - * a swapped page these bits need to be zero. - * This leaves the bits 1-19 and bits 24-29 to store type and offset. - * We use the 5 bits from 25-29 for the type and the 20 bits from 1-19 - * plus 24 for the offset. - * 0| offset |0110|o|type |00| - * 0 0000000001111111111 2222 2 22222 33 - * 0 1234567890123456789 0123 4 56789 01 - * * 64 bit swap entry format: * A page-table entry has some bits we have to treat in a special way. - * Bits 52 and bit 55 have to be zero, otherwise an specification + * Bits 52 and bit 55 have to be zero, otherwise a specification * exception will occur instead of a page translation exception. The - * specifiation exception has the bad habit not to store necessary + * specification exception has the bad habit not to store necessary * information in the lowcore. - * Bit 53 and bit 54 are the page invalid bit and the page protection - * bit. We set both to indicate a swapped page. - * Bit 62 and 63 are used to distinguish the different page types. For - * a swapped page these bits need to be zero. - * This leaves the bits 0-51 and bits 56-61 to store type and offset. - * We use the 5 bits from 57-61 for the type and the 53 bits from 0-51 - * plus 56 for the offset. - * | offset |0110|o|type |00| - * 0000000000111111111122222222223333333333444444444455 5555 5 55566 66 - * 0123456789012345678901234567890123456789012345678901 2345 6 78901 23 + * Bits 54 and 63 are used to indicate the page type. + * A swap pte is indicated by bit pattern (pte & 0x201) == 0x200 + * This leaves the bits 0-51 and bits 56-62 to store type and offset. + * We use the 5 bits from 57-61 for the type and the 52 bits from 0-51 + * for the offset. + * | offset |01100|type |00| + * |0000000000111111111122222222223333333333444444444455|55555|55566|66| + * |0123456789012345678901234567890123456789012345678901|23456|78901|23| */ -#ifndef CONFIG_64BIT -#define __SWP_OFFSET_MASK (~0UL >> 12) -#else -#define __SWP_OFFSET_MASK (~0UL >> 11) -#endif + +#define __SWP_OFFSET_MASK ((1UL << 52) - 1) +#define __SWP_OFFSET_SHIFT 12 +#define __SWP_TYPE_MASK ((1UL << 5) - 1) +#define __SWP_TYPE_SHIFT 2 + static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) { pte_t pte; - offset &= __SWP_OFFSET_MASK; - pte_val(pte) = _PAGE_TYPE_SWAP | ((type & 0x1f) << 2) | - ((offset & 1UL) << 7) | ((offset & ~1UL) << 11); + + pte_val(pte) = _PAGE_INVALID | _PAGE_PROTECT; + pte_val(pte) |= (offset & __SWP_OFFSET_MASK) << __SWP_OFFSET_SHIFT; + pte_val(pte) |= (type & __SWP_TYPE_MASK) << __SWP_TYPE_SHIFT; return pte; } -#define __swp_type(entry) (((entry).val >> 2) & 0x1f) -#define __swp_offset(entry) (((entry).val >> 11) | (((entry).val >> 7) & 1)) -#define __swp_entry(type,offset) ((swp_entry_t) { pte_val(mk_swap_pte((type),(offset))) }) +static inline unsigned long __swp_type(swp_entry_t entry) +{ + return (entry.val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK; +} + +static inline unsigned long __swp_offset(swp_entry_t entry) +{ + return (entry.val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK; +} + +static inline swp_entry_t __swp_entry(unsigned long type, unsigned long offset) +{ + return (swp_entry_t) { pte_val(mk_swap_pte(type, offset)) }; +} #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) -#ifndef CONFIG_64BIT -# define PTE_FILE_MAX_BITS 26 -#else /* CONFIG_64BIT */ -# define PTE_FILE_MAX_BITS 59 -#endif /* CONFIG_64BIT */ - -#define pte_to_pgoff(__pte) \ - ((((__pte).pte >> 12) << 7) + (((__pte).pte >> 1) & 0x7f)) - -#define pgoff_to_pte(__off) \ - ((pte_t) { ((((__off) & 0x7f) << 1) + (((__off) >> 7) << 12)) \ - | _PAGE_TYPE_FILE }) - #endif /* !__ASSEMBLY__ */ #define kern_addr_valid(addr) (1) @@ -1584,6 +1694,12 @@ extern int vmem_add_mapping(unsigned long start, unsigned long size); extern int vmem_remove_mapping(unsigned long start, unsigned long size); extern int s390_enable_sie(void); +extern int s390_enable_skey(void); +extern void s390_reset_cmma(struct mm_struct *mm); + +/* s390 has a private copy of get unmapped area to deal with cache synonyms */ +#define HAVE_ARCH_UNMAPPED_AREA +#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN /* * No page table caches to initialise