diff options
Diffstat (limited to 'arch/s390/mm/pgtable.c')
| -rw-r--r-- | arch/s390/mm/pgtable.c | 364 |
1 files changed, 204 insertions, 160 deletions
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index f2cc7da473e4..666adcd681ab 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -4,6 +4,8 @@ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> */ +#include <linux/cpufeature.h> +#include <linux/export.h> #include <linux/sched.h> #include <linux/kernel.h> #include <linux/errno.h> @@ -14,24 +16,33 @@ #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/slab.h> -#include <linux/swapops.h> +#include <linux/leafops.h> #include <linux/sysctl.h> #include <linux/ksm.h> #include <linux/mman.h> -#include <asm/pgtable.h> -#include <asm/pgalloc.h> -#include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> #include <asm/page-states.h> +#include <asm/pgtable.h> +#include <asm/machine.h> + +pgprot_t pgprot_writecombine(pgprot_t prot) +{ + /* + * mio_wb_bit_mask may be set on a different CPU, but it is only set + * once at init and only read afterwards. + */ + return __pgprot(pgprot_val(prot) | mio_wb_bit_mask); +} +EXPORT_SYMBOL_GPL(pgprot_writecombine); static inline void ptep_ipte_local(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int nodat) { unsigned long opt, asce; - if (MACHINE_HAS_TLB_GUEST) { + if (machine_has_tlb_guest()) { opt = 0; asce = READ_ONCE(mm->context.gmap_asce); if (asce == 0UL || nodat) @@ -51,7 +62,7 @@ static inline void ptep_ipte_global(struct mm_struct *mm, unsigned long addr, { unsigned long opt, asce; - if (MACHINE_HAS_TLB_GUEST) { + if (machine_has_tlb_guest()) { opt = 0; asce = READ_ONCE(mm->context.gmap_asce); if (asce == 0UL || nodat) @@ -76,7 +87,7 @@ static inline pte_t ptep_flush_direct(struct mm_struct *mm, if (unlikely(pte_val(old) & _PAGE_INVALID)) return old; atomic_inc(&mm->context.flush_count); - if (MACHINE_HAS_TLB_LC && + if (cpu_has_tlb_lc() && cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) ptep_ipte_local(mm, addr, ptep, nodat); else @@ -97,7 +108,7 @@ static inline pte_t ptep_flush_lazy(struct mm_struct *mm, atomic_inc(&mm->context.flush_count); if (cpumask_equal(&mm->context.cpu_attach_mask, cpumask_of(smp_processor_id()))) { - pte_val(*ptep) |= _PAGE_INVALID; + set_pte(ptep, set_pte_bit(*ptep, __pgprot(_PAGE_INVALID))); mm->context.flush_mm = 1; } else ptep_ipte_global(mm, addr, ptep, nodat); @@ -105,37 +116,6 @@ static inline pte_t ptep_flush_lazy(struct mm_struct *mm, return old; } -static inline pgste_t pgste_get_lock(pte_t *ptep) -{ - unsigned long new = 0; -#ifdef CONFIG_PGSTE - unsigned long old; - - asm( - " lg %0,%2\n" - "0: lgr %1,%0\n" - " 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]) - : "Q" (ptep[PTRS_PER_PTE]) : "cc", "memory"); -#endif - return __pgste(new); -} - -static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste) -{ -#ifdef CONFIG_PGSTE - asm( - " 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]) - : "cc", "memory"); -#endif -} - static inline pgste_t pgste_get(pte_t *ptep) { unsigned long pgste = 0; @@ -164,10 +144,10 @@ static inline pgste_t pgste_update_all(pte_t pte, pgste_t pgste, skey = (unsigned long) page_get_storage_key(address); bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED); /* Transfer page changed & referenced bit to guest bits in pgste */ - pgste_val(pgste) |= bits << 48; /* GR bit & GC bit */ + pgste = set_pgste_bit(pgste, bits << 48); /* GR bit & GC bit */ /* Copy page access key and fetch protection bit to pgste */ - pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT); - pgste_val(pgste) |= (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; + pgste = clear_pgste_bit(pgste, PGSTE_ACC_BITS | PGSTE_FP_BIT); + pgste = set_pgste_bit(pgste, (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56); #endif return pgste; @@ -201,20 +181,20 @@ static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry) if ((pte_val(entry) & _PAGE_PRESENT) && (pte_val(entry) & _PAGE_WRITE) && !(pte_val(entry) & _PAGE_INVALID)) { - if (!MACHINE_HAS_ESOP) { + 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; + entry = set_pte_bit(entry, __pgprot(_PAGE_DIRTY)); + entry = clear_pte_bit(entry, __pgprot(_PAGE_PROTECT)); } if (!(pte_val(entry) & _PAGE_PROTECT)) /* This pte allows write access, set user-dirty */ - pgste_val(pgste) |= PGSTE_UC_BIT; + pgste = set_pgste_bit(pgste, PGSTE_UC_BIT); } #endif - *ptep = entry; + set_pte(ptep, entry); return pgste; } @@ -227,7 +207,7 @@ static inline pgste_t pgste_pte_notify(struct mm_struct *mm, bits = pgste_val(pgste) & (PGSTE_IN_BIT | PGSTE_VSIE_BIT); if (bits) { - pgste_val(pgste) ^= bits; + pgste = __pgste(pgste_val(pgste) ^ bits); ptep_notify(mm, addr, ptep, bits); } #endif @@ -257,12 +237,12 @@ static inline pte_t ptep_xchg_commit(struct mm_struct *mm, pgste = pgste_update_all(old, pgste, mm); if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED) - pte_val(old) |= _PAGE_UNUSED; + old = set_pte_bit(old, __pgprot(_PAGE_UNUSED)); } pgste = pgste_set_pte(ptep, pgste, new); pgste_set_unlock(ptep, pgste); } else { - *ptep = new; + set_pte(ptep, new); } return old; } @@ -284,6 +264,31 @@ pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr, } EXPORT_SYMBOL(ptep_xchg_direct); +/* + * Caller must check that new PTE only differs in _PAGE_PROTECT HW bit, so that + * RDP can be used instead of IPTE. See also comments at pte_allow_rdp(). + */ +void ptep_reset_dat_prot(struct mm_struct *mm, unsigned long addr, pte_t *ptep, + pte_t new) +{ + preempt_disable(); + atomic_inc(&mm->context.flush_count); + if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) + __ptep_rdp(addr, ptep, 1); + else + __ptep_rdp(addr, ptep, 0); + /* + * PTE is not invalidated by RDP, only _PAGE_PROTECT is cleared. That + * means it is still valid and active, and must not be changed according + * to the architecture. But writing a new value that only differs in SW + * bits is allowed. + */ + set_pte(ptep, new); + atomic_dec(&mm->context.flush_count); + preempt_enable(); +} +EXPORT_SYMBOL(ptep_reset_dat_prot); + pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t new) { @@ -301,14 +306,14 @@ pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr, } EXPORT_SYMBOL(ptep_xchg_lazy); -pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, +pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pgste_t pgste; pte_t old; int nodat; + struct mm_struct *mm = vma->vm_mm; - preempt_disable(); pgste = ptep_xchg_start(mm, addr, ptep); nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT); old = ptep_flush_lazy(mm, addr, ptep, nodat); @@ -318,31 +323,27 @@ pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, } return old; } -EXPORT_SYMBOL(ptep_modify_prot_start); -void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) +void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep, pte_t old_pte, pte_t pte) { pgste_t pgste; + struct mm_struct *mm = vma->vm_mm; - if (!MACHINE_HAS_NX) - pte_val(pte) &= ~_PAGE_NOEXEC; if (mm_has_pgste(mm)) { 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; + set_pte(ptep, pte); } - preempt_enable(); } -EXPORT_SYMBOL(ptep_modify_prot_commit); static inline void pmdp_idte_local(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { - if (MACHINE_HAS_TLB_GUEST) + if (machine_has_tlb_guest()) __pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE, mm->context.asce, IDTE_LOCAL); else @@ -354,19 +355,15 @@ static inline void pmdp_idte_local(struct mm_struct *mm, static inline void pmdp_idte_global(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { - if (MACHINE_HAS_TLB_GUEST) { + if (machine_has_tlb_guest()) { __pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE, mm->context.asce, IDTE_GLOBAL); if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m) gmap_pmdp_idte_global(mm, addr); - } else if (MACHINE_HAS_IDTE) { + } else { __pmdp_idte(addr, pmdp, 0, 0, IDTE_GLOBAL); if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m) gmap_pmdp_idte_global(mm, addr); - } else { - __pmdp_csp(pmdp); - if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m) - gmap_pmdp_csp(mm, addr); } } @@ -379,7 +376,7 @@ static inline pmd_t pmdp_flush_direct(struct mm_struct *mm, if (pmd_val(old) & _SEGMENT_ENTRY_INVALID) return old; atomic_inc(&mm->context.flush_count); - if (MACHINE_HAS_TLB_LC && + if (cpu_has_tlb_lc() && cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) pmdp_idte_local(mm, addr, pmdp); else @@ -399,7 +396,7 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm, atomic_inc(&mm->context.flush_count); if (cpumask_equal(&mm->context.cpu_attach_mask, cpumask_of(smp_processor_id()))) { - pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID; + set_pmd(pmdp, set_pmd_bit(*pmdp, __pgprot(_SEGMENT_ENTRY_INVALID))); mm->context.flush_mm = 1; if (mm_has_pgste(mm)) gmap_pmdp_invalidate(mm, addr); @@ -410,23 +407,39 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm, return old; } -static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr) +#ifdef CONFIG_PGSTE +static int pmd_lookup(struct mm_struct *mm, unsigned long addr, pmd_t **pmdp) { + struct vm_area_struct *vma; pgd_t *pgd; p4d_t *p4d; pud_t *pud; - pmd_t *pmd; + + /* We need a valid VMA, otherwise this is clearly a fault. */ + vma = vma_lookup(mm, addr); + if (!vma) + return -EFAULT; pgd = pgd_offset(mm, addr); - p4d = p4d_alloc(mm, pgd, addr); - if (!p4d) - return NULL; - pud = pud_alloc(mm, p4d, addr); - if (!pud) - return NULL; - pmd = pmd_alloc(mm, pud, addr); - return pmd; + if (!pgd_present(*pgd)) + return -ENOENT; + + p4d = p4d_offset(pgd, addr); + if (!p4d_present(*p4d)) + return -ENOENT; + + pud = pud_offset(p4d, addr); + if (!pud_present(*pud)) + return -ENOENT; + + /* Large PUDs are not supported yet. */ + if (pud_leaf(*pud)) + return -EFAULT; + + *pmdp = pmd_offset(pud, addr); + return 0; } +#endif pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t new) @@ -435,7 +448,7 @@ pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr, preempt_disable(); old = pmdp_flush_direct(mm, addr, pmdp); - *pmdp = new; + set_pmd(pmdp, new); preempt_enable(); return old; } @@ -448,7 +461,7 @@ pmd_t pmdp_xchg_lazy(struct mm_struct *mm, unsigned long addr, preempt_disable(); old = pmdp_flush_lazy(mm, addr, pmdp); - *pmdp = new; + set_pmd(pmdp, new); preempt_enable(); return old; } @@ -457,7 +470,7 @@ EXPORT_SYMBOL(pmdp_xchg_lazy); static inline void pudp_idte_local(struct mm_struct *mm, unsigned long addr, pud_t *pudp) { - if (MACHINE_HAS_TLB_GUEST) + if (machine_has_tlb_guest()) __pudp_idte(addr, pudp, IDTE_NODAT | IDTE_GUEST_ASCE, mm->context.asce, IDTE_LOCAL); else @@ -467,17 +480,11 @@ static inline void pudp_idte_local(struct mm_struct *mm, static inline void pudp_idte_global(struct mm_struct *mm, unsigned long addr, pud_t *pudp) { - if (MACHINE_HAS_TLB_GUEST) + if (machine_has_tlb_guest()) __pudp_idte(addr, pudp, IDTE_NODAT | IDTE_GUEST_ASCE, mm->context.asce, IDTE_GLOBAL); - else if (MACHINE_HAS_IDTE) - __pudp_idte(addr, pudp, 0, 0, IDTE_GLOBAL); else - /* - * Invalid bit position is the same for pmd and pud, so we can - * re-use _pmd_csp() here - */ - __pmdp_csp((pmd_t *) pudp); + __pudp_idte(addr, pudp, 0, 0, IDTE_GLOBAL); } static inline pud_t pudp_flush_direct(struct mm_struct *mm, @@ -489,7 +496,7 @@ static inline pud_t pudp_flush_direct(struct mm_struct *mm, if (pud_val(old) & _REGION_ENTRY_INVALID) return old; atomic_inc(&mm->context.flush_count); - if (MACHINE_HAS_TLB_LC && + if (cpu_has_tlb_lc() && cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) pudp_idte_local(mm, addr, pudp); else @@ -505,7 +512,7 @@ pud_t pudp_xchg_direct(struct mm_struct *mm, unsigned long addr, preempt_disable(); old = pudp_flush_direct(mm, addr, pudp); - *pudp = new; + set_pud(pudp, new); preempt_enable(); return old; } @@ -545,9 +552,9 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) list_del(lh); } ptep = (pte_t *) pgtable; - pte_val(*ptep) = _PAGE_INVALID; + set_pte(ptep, __pte(_PAGE_INVALID)); ptep++; - pte_val(*ptep) = _PAGE_INVALID; + set_pte(ptep, __pte(_PAGE_INVALID)); return pgtable; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -561,7 +568,7 @@ void ptep_set_pte_at(struct mm_struct *mm, unsigned long addr, /* the mm_has_pgste() check is done in set_pte_at() */ preempt_disable(); pgste = pgste_get_lock(ptep); - pgste_val(pgste) &= ~_PGSTE_GPS_ZERO; + pgste = clear_pgste_bit(pgste, _PGSTE_GPS_ZERO); pgste_set_key(ptep, pgste, entry, mm); pgste = pgste_set_pte(ptep, pgste, entry); pgste_set_unlock(ptep, pgste); @@ -574,7 +581,7 @@ void ptep_set_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep) preempt_disable(); pgste = pgste_get_lock(ptep); - pgste_val(pgste) |= PGSTE_IN_BIT; + pgste = set_pgste_bit(pgste, PGSTE_IN_BIT); pgste_set_unlock(ptep, pgste); preempt_enable(); } @@ -612,14 +619,14 @@ int ptep_force_prot(struct mm_struct *mm, unsigned long addr, if (prot == PROT_NONE && !pte_i) { ptep_flush_direct(mm, addr, ptep, nodat); pgste = pgste_update_all(entry, pgste, mm); - pte_val(entry) |= _PAGE_INVALID; + entry = set_pte_bit(entry, __pgprot(_PAGE_INVALID)); } if (prot == PROT_READ && !pte_p) { ptep_flush_direct(mm, addr, ptep, nodat); - pte_val(entry) &= ~_PAGE_INVALID; - pte_val(entry) |= _PAGE_PROTECT; + entry = clear_pte_bit(entry, __pgprot(_PAGE_INVALID)); + entry = set_pte_bit(entry, __pgprot(_PAGE_PROTECT)); } - pgste_val(pgste) |= bit; + pgste = set_pgste_bit(pgste, bit); pgste = pgste_set_pte(ptep, pgste, entry); pgste_set_unlock(ptep, pgste); return 0; @@ -639,10 +646,10 @@ int ptep_shadow_pte(struct mm_struct *mm, unsigned long saddr, if (!(pte_val(spte) & _PAGE_INVALID) && !((pte_val(spte) & _PAGE_PROTECT) && !(pte_val(pte) & _PAGE_PROTECT))) { - pgste_val(spgste) |= PGSTE_VSIE_BIT; + spgste = set_pgste_bit(spgste, PGSTE_VSIE_BIT); tpgste = pgste_get_lock(tptep); - pte_val(tpte) = (pte_val(spte) & PAGE_MASK) | - (pte_val(pte) & _PAGE_PROTECT); + tpte = __pte((pte_val(spte) & PAGE_MASK) | + (pte_val(pte) & _PAGE_PROTECT)); /* don't touch the storage key - it belongs to parent pgste */ tpgste = pgste_set_pte(tptep, tpgste, tpte); pgste_set_unlock(tptep, tpgste); @@ -666,14 +673,14 @@ void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep) pgste_set_unlock(ptep, pgste); } -static void ptep_zap_swap_entry(struct mm_struct *mm, swp_entry_t entry) +static void ptep_zap_softleaf_entry(struct mm_struct *mm, softleaf_t entry) { - if (!non_swap_entry(entry)) + if (softleaf_is_swap(entry)) dec_mm_counter(mm, MM_SWAPENTS); - else if (is_migration_entry(entry)) { - struct page *page = migration_entry_to_page(entry); + else if (softleaf_is_migration(entry)) { + struct folio *folio = softleaf_to_folio(entry); - dec_mm_counter(mm, mm_counter(page)); + dec_mm_counter(mm, mm_counter(folio)); } free_swap_and_cache(entry); } @@ -693,11 +700,11 @@ void ptep_zap_unused(struct mm_struct *mm, unsigned long addr, if (!reset && pte_swap(pte) && ((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED || (pgstev & _PGSTE_GPS_ZERO))) { - ptep_zap_swap_entry(mm, pte_to_swp_entry(pte)); + ptep_zap_softleaf_entry(mm, softleaf_from_pte(pte)); pte_clear(mm, addr, ptep); } if (reset) - pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK; + pgste = clear_pgste_bit(pgste, _PGSTE_GPS_USAGE_MASK | _PGSTE_GPS_NODAT); pgste_set_unlock(ptep, pgste); preempt_enable(); } @@ -710,11 +717,11 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep) /* Clear storage key ACC and F, but set R/C */ preempt_disable(); pgste = pgste_get_lock(ptep); - pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT); - pgste_val(pgste) |= PGSTE_GR_BIT | PGSTE_GC_BIT; + pgste = clear_pgste_bit(pgste, PGSTE_ACC_BITS | PGSTE_FP_BIT); + pgste = set_pgste_bit(pgste, PGSTE_GR_BIT | PGSTE_GC_BIT); ptev = pte_val(*ptep); if (!(ptev & _PAGE_INVALID) && (ptev & _PAGE_WRITE)) - page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 1); + page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 0); pgste_set_unlock(ptep, pgste); preempt_enable(); } @@ -732,17 +739,17 @@ bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long addr, pgste = pgste_get_lock(ptep); dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT); - pgste_val(pgste) &= ~PGSTE_UC_BIT; + pgste = clear_pgste_bit(pgste, PGSTE_UC_BIT); pte = *ptep; if (dirty && (pte_val(pte) & _PAGE_PRESENT)) { pgste = pgste_pte_notify(mm, addr, ptep, pgste); nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT); ptep_ipte_global(mm, addr, ptep, nodat); - if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE)) - pte_val(pte) |= _PAGE_PROTECT; + if (machine_has_esop() || !(pte_val(pte) & _PAGE_WRITE)) + pte = set_pte_bit(pte, __pgprot(_PAGE_PROTECT)); else - pte_val(pte) |= _PAGE_INVALID; - *ptep = pte; + pte = set_pte_bit(pte, __pgprot(_PAGE_INVALID)); + set_pte(ptep, pte); } pgste_set_unlock(ptep, pgste); return dirty; @@ -758,17 +765,26 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp; pte_t *ptep; - pmdp = pmd_alloc_map(mm, addr); - if (unlikely(!pmdp)) + /* + * If we don't have a PTE table and if there is no huge page mapped, + * we can ignore attempts to set the key to 0, because it already is 0. + */ + switch (pmd_lookup(mm, addr, &pmdp)) { + case -ENOENT: + return key ? -EFAULT : 0; + case 0: + break; + default: return -EFAULT; - + } +again: ptl = pmd_lock(mm, pmdp); if (!pmd_present(*pmdp)) { spin_unlock(ptl); - return -EFAULT; + return key ? -EFAULT : 0; } - if (pmd_large(*pmdp)) { + if (pmd_leaf(*pmdp)) { paddr = pmd_val(*pmdp) & HPAGE_MASK; paddr |= addr & ~HPAGE_MASK; /* @@ -781,16 +797,15 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, } spin_unlock(ptl); - ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl); - if (unlikely(!ptep)) - return -EFAULT; - + ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); + if (!ptep) + goto again; new = old = pgste_get_lock(ptep); - pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT | - PGSTE_ACC_BITS | PGSTE_FP_BIT); + new = clear_pgste_bit(new, PGSTE_GR_BIT | PGSTE_GC_BIT | + PGSTE_ACC_BITS | PGSTE_FP_BIT); keyul = (unsigned long) key; - pgste_val(new) |= (keyul & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48; - pgste_val(new) |= (keyul & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; + new = set_pgste_bit(new, (keyul & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48); + new = set_pgste_bit(new, (keyul & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56); if (!(pte_val(*ptep) & _PAGE_INVALID)) { unsigned long bits, skey; @@ -801,12 +816,12 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, /* Set storage key ACC and FP */ page_set_storage_key(paddr, skey, !nq); /* Merge host changed & referenced into pgste */ - pgste_val(new) |= bits << 52; + new = set_pgste_bit(new, bits << 52); } /* changing the guest storage key is considered a change of the page */ if ((pgste_val(new) ^ pgste_val(old)) & (PGSTE_ACC_BITS | PGSTE_FP_BIT | PGSTE_GR_BIT | PGSTE_GC_BIT)) - pgste_val(new) |= PGSTE_UC_BIT; + new = set_pgste_bit(new, PGSTE_UC_BIT); pgste_set_unlock(ptep, new); pte_unmap_unlock(ptep, ptl); @@ -814,7 +829,7 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, } EXPORT_SYMBOL(set_guest_storage_key); -/** +/* * Conditionally set a guest storage key (handling csske). * oldkey will be updated when either mr or mc is set and a pointer is given. * @@ -847,7 +862,7 @@ int cond_set_guest_storage_key(struct mm_struct *mm, unsigned long addr, } EXPORT_SYMBOL(cond_set_guest_storage_key); -/** +/* * Reset a guest reference bit (rrbe), returning the reference and changed bit. * * Returns < 0 in case of error, otherwise the cc to be reported to the guest. @@ -861,17 +876,26 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr) pte_t *ptep; int cc = 0; - pmdp = pmd_alloc_map(mm, addr); - if (unlikely(!pmdp)) + /* + * If we don't have a PTE table and if there is no huge page mapped, + * the storage key is 0 and there is nothing for us to do. + */ + switch (pmd_lookup(mm, addr, &pmdp)) { + case -ENOENT: + return 0; + case 0: + break; + default: return -EFAULT; - + } +again: ptl = pmd_lock(mm, pmdp); if (!pmd_present(*pmdp)) { spin_unlock(ptl); - return -EFAULT; + return 0; } - if (pmd_large(*pmdp)) { + if (pmd_leaf(*pmdp)) { paddr = pmd_val(*pmdp) & HPAGE_MASK; paddr |= addr & ~HPAGE_MASK; cc = page_reset_referenced(paddr); @@ -880,25 +904,24 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr) } spin_unlock(ptl); - ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl); - if (unlikely(!ptep)) - return -EFAULT; - + ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); + if (!ptep) + goto again; new = old = pgste_get_lock(ptep); /* Reset guest reference bit only */ - pgste_val(new) &= ~PGSTE_GR_BIT; + new = clear_pgste_bit(new, PGSTE_GR_BIT); if (!(pte_val(*ptep) & _PAGE_INVALID)) { paddr = pte_val(*ptep) & PAGE_MASK; cc = page_reset_referenced(paddr); /* Merge real referenced bit into host-set */ - pgste_val(new) |= ((unsigned long) cc << 53) & PGSTE_HR_BIT; + new = set_pgste_bit(new, ((unsigned long)cc << 53) & PGSTE_HR_BIT); } /* Reflect guest's logical view, not physical */ cc |= (pgste_val(old) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 49; /* Changing the guest storage key is considered a change of the page */ if ((pgste_val(new) ^ pgste_val(old)) & PGSTE_GR_BIT) - pgste_val(new) |= PGSTE_UC_BIT; + new = set_pgste_bit(new, PGSTE_UC_BIT); pgste_set_unlock(ptep, new); pte_unmap_unlock(ptep, ptl); @@ -915,19 +938,28 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp; pte_t *ptep; - pmdp = pmd_alloc_map(mm, addr); - if (unlikely(!pmdp)) - return -EFAULT; + /* + * If we don't have a PTE table and if there is no huge page mapped, + * the storage key is 0. + */ + *key = 0; + switch (pmd_lookup(mm, addr, &pmdp)) { + case -ENOENT: + return 0; + case 0: + break; + default: + return -EFAULT; + } +again: ptl = pmd_lock(mm, pmdp); if (!pmd_present(*pmdp)) { - /* Not yet mapped memory has a zero key */ spin_unlock(ptl); - *key = 0; return 0; } - if (pmd_large(*pmdp)) { + if (pmd_leaf(*pmdp)) { paddr = pmd_val(*pmdp) & HPAGE_MASK; paddr |= addr & ~HPAGE_MASK; *key = page_get_storage_key(paddr); @@ -936,10 +968,9 @@ int get_guest_storage_key(struct mm_struct *mm, unsigned long addr, } spin_unlock(ptl); - ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl); - if (unlikely(!ptep)) - return -EFAULT; - + ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); + if (!ptep) + goto again; pgste = pgste_get_lock(ptep); *key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56; paddr = pte_val(*ptep) & PAGE_MASK; @@ -968,6 +999,7 @@ EXPORT_SYMBOL(get_guest_storage_key); int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, unsigned long *oldpte, unsigned long *oldpgste) { + struct vm_area_struct *vma; unsigned long pgstev; spinlock_t *ptl; pgste_t pgste; @@ -977,6 +1009,10 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, WARN_ON_ONCE(orc > ESSA_MAX); if (unlikely(orc > ESSA_MAX)) return -EINVAL; + + vma = vma_lookup(mm, hva); + if (!vma || is_vm_hugetlb_page(vma)) + return -EFAULT; ptep = get_locked_pte(mm, hva, &ptl); if (unlikely(!ptep)) return -EFAULT; @@ -1049,7 +1085,7 @@ int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc, if (res) pgstev |= _PGSTE_GPS_ZERO; - pgste_val(pgste) = pgstev; + pgste = __pgste(pgstev); pgste_set_unlock(ptep, pgste); pte_unmap_unlock(ptep, ptl); return res; @@ -1069,17 +1105,21 @@ EXPORT_SYMBOL(pgste_perform_essa); int set_pgste_bits(struct mm_struct *mm, unsigned long hva, unsigned long bits, unsigned long value) { + struct vm_area_struct *vma; spinlock_t *ptl; pgste_t new; pte_t *ptep; + vma = vma_lookup(mm, hva); + if (!vma || is_vm_hugetlb_page(vma)) + return -EFAULT; ptep = get_locked_pte(mm, hva, &ptl); if (unlikely(!ptep)) return -EFAULT; new = pgste_get_lock(ptep); - pgste_val(new) &= ~bits; - pgste_val(new) |= value & bits; + new = clear_pgste_bit(new, bits); + new = set_pgste_bit(new, value & bits); pgste_set_unlock(ptep, new); pte_unmap_unlock(ptep, ptl); @@ -1097,9 +1137,13 @@ EXPORT_SYMBOL(set_pgste_bits); */ int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep) { + struct vm_area_struct *vma; spinlock_t *ptl; pte_t *ptep; + vma = vma_lookup(mm, hva); + if (!vma || is_vm_hugetlb_page(vma)) + return -EFAULT; ptep = get_locked_pte(mm, hva, &ptl); if (unlikely(!ptep)) return -EFAULT; |