diff options
Diffstat (limited to 'arch/s390')
| -rw-r--r-- | arch/s390/include/asm/page.h | 22 | ||||
| -rw-r--r-- | arch/s390/include/asm/pgtable.h | 131 | ||||
| -rw-r--r-- | arch/s390/include/asm/sclp.h | 1 | ||||
| -rw-r--r-- | arch/s390/include/asm/setup.h | 16 | ||||
| -rw-r--r-- | arch/s390/kvm/kvm-s390.c | 2 | ||||
| -rw-r--r-- | arch/s390/lib/uaccess_pt.c | 2 | ||||
| -rw-r--r-- | arch/s390/mm/pageattr.c | 2 | ||||
| -rw-r--r-- | arch/s390/mm/vmem.c | 24 |
8 files changed, 110 insertions, 90 deletions
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index a86ad408407..75ce9b065f9 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -155,28 +155,6 @@ static inline int page_reset_referenced(unsigned long addr) #define _PAGE_ACC_BITS 0xf0 /* HW access control bits */ /* - * Test and clear dirty bit in storage key. - * We can't clear the changed bit atomically. This is a potential - * race against modification of the referenced bit. This function - * should therefore only be called if it is not mapped in any - * address space. - * - * Note that the bit gets set whenever page content is changed. That means - * also when the page is modified by DMA or from inside the kernel. - */ -#define __HAVE_ARCH_PAGE_TEST_AND_CLEAR_DIRTY -static inline int page_test_and_clear_dirty(unsigned long pfn, int mapped) -{ - unsigned char skey; - - skey = page_get_storage_key(pfn << PAGE_SHIFT); - if (!(skey & _PAGE_CHANGED)) - return 0; - page_set_storage_key(pfn << PAGE_SHIFT, skey & ~_PAGE_CHANGED, mapped); - return 1; -} - -/* * Test and clear referenced bit in storage key. */ #define __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index a009d4dd70c..97de1200c84 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -29,6 +29,7 @@ #ifndef __ASSEMBLY__ #include <linux/sched.h> #include <linux/mm_types.h> +#include <linux/page-flags.h> #include <asm/bug.h> #include <asm/page.h> @@ -221,13 +222,15 @@ extern unsigned long MODULES_END; /* 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 (for KVM) */ -#define _PAGE_SWR 0x008 /* SW pte referenced bit (for KVM) */ -#define _PAGE_SPECIAL 0x010 /* SW associated with special page */ +#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 __HAVE_ARCH_PTE_SPECIAL /* Set of bits not changed in pte_modify */ -#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_SPECIAL | _PAGE_SWC | _PAGE_SWR) +#define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_SPECIAL | _PAGE_CO | \ + _PAGE_SWC | _PAGE_SWR) /* Six different types of pages. */ #define _PAGE_TYPE_EMPTY 0x400 @@ -321,6 +324,7 @@ extern unsigned long MODULES_END; /* 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_TYPE_MASK 0x0c /* region/segment table type mask */ #define _REGION_ENTRY_TYPE_R1 0x0c /* region first table type */ @@ -382,9 +386,10 @@ extern unsigned long MODULES_END; */ #define PAGE_NONE __pgprot(_PAGE_TYPE_NONE) #define PAGE_RO __pgprot(_PAGE_TYPE_RO) -#define PAGE_RW __pgprot(_PAGE_TYPE_RW) +#define PAGE_RW __pgprot(_PAGE_TYPE_RO | _PAGE_SWW) +#define PAGE_RWC __pgprot(_PAGE_TYPE_RW | _PAGE_SWW | _PAGE_SWC) -#define PAGE_KERNEL PAGE_RW +#define PAGE_KERNEL PAGE_RWC #define PAGE_SHARED PAGE_KERNEL #define PAGE_COPY PAGE_RO @@ -632,23 +637,23 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste) 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, 1); + 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; - /* Clear host bits in pgste. */ + /* 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); /* Copy page access key and fetch protection bit to pgste */ pgste_val(pgste) |= (unsigned long) (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; - /* Transfer changed and referenced to kvm user bits */ - pgste_val(pgste) |= bits << 45; /* KVM_UR_BIT & KVM_UC_BIT */ - /* Transfer changed & referenced to pte sofware bits */ - pte_val(*ptep) |= bits << 1; /* _PAGE_SWR & _PAGE_SWC */ + /* Transfer referenced bit to pte */ + pte_val(*ptep) |= (bits & _PAGE_REFERENCED) << 1; #endif return pgste; @@ -661,20 +666,25 @@ static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste) if (!pte_present(*ptep)) return pgste; + /* Get referenced bit from storage key */ young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK); - /* Transfer page referenced bit to pte software bit (host view) */ - if (young || (pgste_val(pgste) & RCP_HR_BIT)) + 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; - /* Clear host referenced bit in pgste. */ - pgste_val(pgste) &= ~RCP_HR_BIT; - /* Transfer page referenced bit to guest bit in pgste */ - pgste_val(pgste) |= (unsigned long) young << 50; /* set RCP_GR_BIT */ + } #endif return pgste; - } -static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry) +static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry) { #ifdef CONFIG_PGSTE unsigned long address; @@ -688,10 +698,23 @@ static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry) /* Set page access key and fetch protection bit from pgste */ nkey |= (pgste_val(pgste) & (RCP_ACC_BITS | RCP_FP_BIT)) >> 56; if (okey != nkey) - page_set_storage_key(address, nkey, 1); + page_set_storage_key(address, nkey, 0); #endif } +static inline void pgste_set_pte(pte_t *ptep, 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; + } + *ptep = entry; +} + /** * struct gmap_struct - guest address space * @mm: pointer to the parent mm_struct @@ -750,11 +773,14 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); - pgste_set_pte(ptep, pgste, entry); - *ptep = entry; + pgste_set_key(ptep, pgste, entry); + pgste_set_pte(ptep, entry); pgste_set_unlock(ptep, pgste); - } else + } else { + if (!(pte_val(entry) & _PAGE_INVALID) && MACHINE_HAS_EDAT1) + pte_val(entry) |= _PAGE_CO; *ptep = entry; + } } /* @@ -763,16 +789,12 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, */ static inline int pte_write(pte_t pte) { - return (pte_val(pte) & _PAGE_RO) == 0; + return (pte_val(pte) & _PAGE_SWW) != 0; } static inline int pte_dirty(pte_t pte) { -#ifdef CONFIG_PGSTE - if (pte_val(pte) & _PAGE_SWC) - return 1; -#endif - return 0; + return (pte_val(pte) & _PAGE_SWC) != 0; } static inline int pte_young(pte_t pte) @@ -822,11 +844,14 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { 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; 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; @@ -835,20 +860,26 @@ static inline pte_t pte_wrprotect(pte_t pte) static inline pte_t pte_mkwrite(pte_t pte) { - pte_val(pte) &= ~_PAGE_RO; + pte_val(pte) |= _PAGE_SWW; + if (pte_val(pte) & _PAGE_SWC) + pte_val(pte) &= ~_PAGE_RO; return pte; } static inline pte_t pte_mkclean(pte_t pte) { -#ifdef CONFIG_PGSTE pte_val(pte) &= ~_PAGE_SWC; -#endif + /* Do not clobber _PAGE_TYPE_NONE pages! */ + if (!(pte_val(pte) & _PAGE_INVALID)) + pte_val(pte) |= _PAGE_RO; 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; return pte; } @@ -886,10 +917,10 @@ static inline pte_t pte_mkhuge(pte_t pte) pte_val(pte) |= _SEGMENT_ENTRY_INV; } /* - * Clear SW pte bits SWT and SWX, there are no SW bits in a segment - * table entry. + * Clear SW pte bits, there are no SW bits in a segment table entry. */ - pte_val(pte) &= ~(_PAGE_SWT | _PAGE_SWX); + pte_val(pte) &= ~(_PAGE_SWT | _PAGE_SWX | _PAGE_SWC | + _PAGE_SWR | _PAGE_SWW); /* * Also set the change-override bit because we don't need dirty bit * tracking for hugetlbfs pages. @@ -1041,9 +1072,11 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long address, pte_t *ptep, pte_t pte) { - *ptep = pte; - if (mm_has_pgste(mm)) + if (mm_has_pgste(mm)) { + pgste_set_pte(ptep, pte); pgste_set_unlock(ptep, *(pgste_t *)(ptep + PTRS_PER_PTE)); + } else + *ptep = pte; } #define __HAVE_ARCH_PTEP_CLEAR_FLUSH @@ -1111,10 +1144,13 @@ static inline pte_t ptep_set_wrprotect(struct mm_struct *mm, if (!mm_exclusive(mm)) __ptep_ipte(address, ptep); - *ptep = pte_wrprotect(pte); + pte = pte_wrprotect(pte); - if (mm_has_pgste(mm)) + if (mm_has_pgste(mm)) { + pgste_set_pte(ptep, pte); pgste_set_unlock(ptep, pgste); + } else + *ptep = pte; } return pte; } @@ -1132,10 +1168,12 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma, pgste = pgste_get_lock(ptep); __ptep_ipte(address, ptep); - *ptep = entry; - if (mm_has_pgste(vma->vm_mm)) + if (mm_has_pgste(vma->vm_mm)) { + pgste_set_pte(ptep, entry); pgste_set_unlock(ptep, pgste); + } else + *ptep = entry; return 1; } @@ -1153,8 +1191,13 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) { unsigned long physpage = page_to_phys(page); + pte_t __pte = mk_pte_phys(physpage, pgprot); - return mk_pte_phys(physpage, pgprot); + if ((pte_val(__pte) & _PAGE_SWW) && PageDirty(page)) { + pte_val(__pte) |= _PAGE_SWC; + pte_val(__pte) &= ~_PAGE_RO; + } + return __pte; } #define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1)) @@ -1246,6 +1289,8 @@ static inline int pmd_trans_splitting(pmd_t pmd) 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; } diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index 833788693f0..06a13613604 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -46,7 +46,6 @@ int sclp_cpu_deconfigure(u8 cpu); void sclp_facilities_detect(void); unsigned long long sclp_get_rnmax(void); unsigned long long sclp_get_rzm(void); -u8 sclp_get_fac85(void); int sclp_sdias_blk_count(void); int sclp_sdias_copy(void *dest, int blk_num, int nr_blks); int sclp_chp_configure(struct chp_id chpid); diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h index f69f76b3447..f6857516e52 100644 --- a/arch/s390/include/asm/setup.h +++ b/arch/s390/include/asm/setup.h @@ -64,13 +64,14 @@ extern unsigned int s390_user_mode; #define MACHINE_FLAG_VM (1UL << 0) #define MACHINE_FLAG_IEEE (1UL << 1) -#define MACHINE_FLAG_CSP (1UL << 3) -#define MACHINE_FLAG_MVPG (1UL << 4) -#define MACHINE_FLAG_DIAG44 (1UL << 5) -#define MACHINE_FLAG_IDTE (1UL << 6) -#define MACHINE_FLAG_DIAG9C (1UL << 7) -#define MACHINE_FLAG_MVCOS (1UL << 8) -#define MACHINE_FLAG_KVM (1UL << 9) +#define MACHINE_FLAG_CSP (1UL << 2) +#define MACHINE_FLAG_MVPG (1UL << 3) +#define MACHINE_FLAG_DIAG44 (1UL << 4) +#define MACHINE_FLAG_IDTE (1UL << 5) +#define MACHINE_FLAG_DIAG9C (1UL << 6) +#define MACHINE_FLAG_MVCOS (1UL << 7) +#define MACHINE_FLAG_KVM (1UL << 8) +#define MACHINE_FLAG_ESOP (1UL << 9) #define MACHINE_FLAG_EDAT1 (1UL << 10) #define MACHINE_FLAG_EDAT2 (1UL << 11) #define MACHINE_FLAG_LPAR (1UL << 12) @@ -84,6 +85,7 @@ extern unsigned int s390_user_mode; #define MACHINE_IS_LPAR (S390_lowcore.machine_flags & MACHINE_FLAG_LPAR) #define MACHINE_HAS_DIAG9C (S390_lowcore.machine_flags & MACHINE_FLAG_DIAG9C) +#define MACHINE_HAS_ESOP (S390_lowcore.machine_flags & MACHINE_FLAG_ESOP) #define MACHINE_HAS_PFMF MACHINE_HAS_EDAT1 #define MACHINE_HAS_HPAGE MACHINE_HAS_EDAT1 diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f090e819bf7..2923781590a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -147,7 +147,7 @@ int kvm_dev_ioctl_check_extension(long ext) r = KVM_MAX_VCPUS; break; case KVM_CAP_S390_COW: - r = sclp_get_fac85() & 0x2; + r = MACHINE_HAS_ESOP; break; default: r = 0; diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index 9017a63dda3..a70ee84c024 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -50,7 +50,7 @@ static __always_inline unsigned long follow_table(struct mm_struct *mm, ptep = pte_offset_map(pmd, addr); if (!pte_present(*ptep)) return -0x11UL; - if (write && !pte_write(*ptep)) + if (write && (!pte_write(*ptep) || !pte_dirty(*ptep))) return -0x04UL; return (pte_val(*ptep) & PAGE_MASK) + (addr & ~PAGE_MASK); diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 29ccee3651f..d21040ed5e5 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -127,7 +127,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable) pte_val(*pte) = _PAGE_TYPE_EMPTY; continue; } - *pte = mk_pte_phys(address, __pgprot(_PAGE_TYPE_RW)); + pte_val(*pte) = __pa(address); } } diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 6ed1426d27c..79699f46a44 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -85,11 +85,9 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) pud_t *pu_dir; pmd_t *pm_dir; pte_t *pt_dir; - pte_t pte; int ret = -ENOMEM; while (address < end) { - pte = mk_pte_phys(address, __pgprot(ro ? _PAGE_RO : 0)); pg_dir = pgd_offset_k(address); if (pgd_none(*pg_dir)) { pu_dir = vmem_pud_alloc(); @@ -101,9 +99,9 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) #if defined(CONFIG_64BIT) && !defined(CONFIG_DEBUG_PAGEALLOC) if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address && !(address & ~PUD_MASK) && (address + PUD_SIZE <= end)) { - pte_val(pte) |= _REGION3_ENTRY_LARGE; - pte_val(pte) |= _REGION_ENTRY_TYPE_R3; - pud_val(*pu_dir) = pte_val(pte); + pud_val(*pu_dir) = __pa(address) | + _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE | + (ro ? _REGION_ENTRY_RO : 0); address += PUD_SIZE; continue; } @@ -118,8 +116,9 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) #if defined(CONFIG_64BIT) && !defined(CONFIG_DEBUG_PAGEALLOC) if (MACHINE_HAS_EDAT1 && pmd_none(*pm_dir) && address && !(address & ~PMD_MASK) && (address + PMD_SIZE <= end)) { - pte_val(pte) |= _SEGMENT_ENTRY_LARGE; - pmd_val(*pm_dir) = pte_val(pte); + pmd_val(*pm_dir) = __pa(address) | + _SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE | + (ro ? _SEGMENT_ENTRY_RO : 0); address += PMD_SIZE; continue; } @@ -132,7 +131,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) } pt_dir = pte_offset_kernel(pm_dir, address); - *pt_dir = pte; + pte_val(*pt_dir) = __pa(address) | (ro ? _PAGE_RO : 0); address += PAGE_SIZE; } ret = 0; @@ -199,7 +198,6 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) pud_t *pu_dir; pmd_t *pm_dir; pte_t *pt_dir; - pte_t pte; int ret = -ENOMEM; start_addr = (unsigned long) start; @@ -237,9 +235,8 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) new_page = vmemmap_alloc_block(PMD_SIZE, node); if (!new_page) goto out; - pte = mk_pte_phys(__pa(new_page), PAGE_RW); - pte_val(pte) |= _SEGMENT_ENTRY_LARGE; - pmd_val(*pm_dir) = pte_val(pte); + pmd_val(*pm_dir) = __pa(new_page) | + _SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE; address = (address + PMD_SIZE) & PMD_MASK; continue; } @@ -260,8 +257,7 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node) new_page =__pa(vmem_alloc_pages(0)); if (!new_page) goto out; - pte = pfn_pte(new_page >> PAGE_SHIFT, PAGE_KERNEL); - *pt_dir = pte; + pte_val(*pt_dir) = __pa(new_page); } address += PAGE_SIZE; } |