diff options
Diffstat (limited to 'arch/parisc/include')
| -rw-r--r-- | arch/parisc/include/asm/pgtable.h | 55 | ||||
| -rw-r--r-- | arch/parisc/include/asm/tlbflush.h | 53 |
2 files changed, 66 insertions, 42 deletions
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index 0a183756d6ec..f93c4a4e6580 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -16,7 +16,7 @@ #include <asm/processor.h> #include <asm/cache.h> -extern spinlock_t pa_dbit_lock; +extern spinlock_t pa_tlb_lock; /* * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel @@ -33,6 +33,19 @@ extern spinlock_t pa_dbit_lock; */ #define kern_addr_valid(addr) (1) +/* Purge data and instruction TLB entries. Must be called holding + * the pa_tlb_lock. The TLB purge instructions are slow on SMP + * machines since the purge must be broadcast to all CPUs. + */ + +static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) +{ + mtsp(mm->context, 1); + pdtlb(addr); + if (unlikely(split_tlb)) + pitlb(addr); +} + /* Certain architectures need to do special things when PTEs * within a page table are directly modified. Thus, the following * hook is made available. @@ -42,15 +55,20 @@ extern spinlock_t pa_dbit_lock; *(pteptr) = (pteval); \ } while(0) -extern void purge_tlb_entries(struct mm_struct *, unsigned long); +#define pte_inserted(x) \ + ((pte_val(x) & (_PAGE_PRESENT|_PAGE_ACCESSED)) \ + == (_PAGE_PRESENT|_PAGE_ACCESSED)) -#define set_pte_at(mm, addr, ptep, pteval) \ - do { \ +#define set_pte_at(mm, addr, ptep, pteval) \ + do { \ + pte_t old_pte; \ unsigned long flags; \ - spin_lock_irqsave(&pa_dbit_lock, flags); \ - set_pte(ptep, pteval); \ - purge_tlb_entries(mm, addr); \ - spin_unlock_irqrestore(&pa_dbit_lock, flags); \ + spin_lock_irqsave(&pa_tlb_lock, flags); \ + old_pte = *ptep; \ + set_pte(ptep, pteval); \ + if (pte_inserted(old_pte)) \ + purge_tlb_entries(mm, addr); \ + spin_unlock_irqrestore(&pa_tlb_lock, flags); \ } while (0) #endif /* !__ASSEMBLY__ */ @@ -268,7 +286,7 @@ extern unsigned long *empty_zero_page; #define pte_none(x) (pte_val(x) == 0) #define pte_present(x) (pte_val(x) & _PAGE_PRESENT) -#define pte_clear(mm,addr,xp) do { pte_val(*(xp)) = 0; } while (0) +#define pte_clear(mm, addr, xp) set_pte_at(mm, addr, xp, __pte(0)) #define pmd_flag(x) (pmd_val(x) & PxD_FLAG_MASK) #define pmd_address(x) ((unsigned long)(pmd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT) @@ -435,15 +453,15 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned if (!pte_young(*ptep)) return 0; - spin_lock_irqsave(&pa_dbit_lock, flags); + spin_lock_irqsave(&pa_tlb_lock, flags); pte = *ptep; if (!pte_young(pte)) { - spin_unlock_irqrestore(&pa_dbit_lock, flags); + spin_unlock_irqrestore(&pa_tlb_lock, flags); return 0; } set_pte(ptep, pte_mkold(pte)); purge_tlb_entries(vma->vm_mm, addr); - spin_unlock_irqrestore(&pa_dbit_lock, flags); + spin_unlock_irqrestore(&pa_tlb_lock, flags); return 1; } @@ -453,11 +471,12 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t old_pte; unsigned long flags; - spin_lock_irqsave(&pa_dbit_lock, flags); + spin_lock_irqsave(&pa_tlb_lock, flags); old_pte = *ptep; - pte_clear(mm,addr,ptep); - purge_tlb_entries(mm, addr); - spin_unlock_irqrestore(&pa_dbit_lock, flags); + set_pte(ptep, __pte(0)); + if (pte_inserted(old_pte)) + purge_tlb_entries(mm, addr); + spin_unlock_irqrestore(&pa_tlb_lock, flags); return old_pte; } @@ -465,10 +484,10 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { unsigned long flags; - spin_lock_irqsave(&pa_dbit_lock, flags); + spin_lock_irqsave(&pa_tlb_lock, flags); set_pte(ptep, pte_wrprotect(*ptep)); purge_tlb_entries(mm, addr); - spin_unlock_irqrestore(&pa_dbit_lock, flags); + spin_unlock_irqrestore(&pa_tlb_lock, flags); } #define pte_same(A,B) (pte_val(A) == pte_val(B)) diff --git a/arch/parisc/include/asm/tlbflush.h b/arch/parisc/include/asm/tlbflush.h index 9d086a599fa0..e84b96478193 100644 --- a/arch/parisc/include/asm/tlbflush.h +++ b/arch/parisc/include/asm/tlbflush.h @@ -13,6 +13,9 @@ * active at any one time on the Merced bus. This tlb purge * synchronisation is fairly lightweight and harmless so we activate * it on all systems not just the N class. + + * It is also used to ensure PTE updates are atomic and consistent + * with the TLB. */ extern spinlock_t pa_tlb_lock; @@ -24,20 +27,24 @@ extern void flush_tlb_all_local(void *); #define smp_flush_tlb_all() flush_tlb_all() +int __flush_tlb_range(unsigned long sid, + unsigned long start, unsigned long end); + +#define flush_tlb_range(vma, start, end) \ + __flush_tlb_range((vma)->vm_mm->context, start, end) + +#define flush_tlb_kernel_range(start, end) \ + __flush_tlb_range(0, start, end) + /* * flush_tlb_mm() * - * XXX This code is NOT valid for HP-UX compatibility processes, - * (although it will probably work 99% of the time). HP-UX - * processes are free to play with the space id's and save them - * over long periods of time, etc. so we have to preserve the - * space and just flush the entire tlb. We need to check the - * personality in order to do that, but the personality is not - * currently being set correctly. - * - * Of course, Linux processes could do the same thing, but - * we don't support that (and the compilers, dynamic linker, - * etc. do not do that). + * The code to switch to a new context is NOT valid for processes + * which play with the space id's. Thus, we have to preserve the + * space and just flush the entire tlb. However, the compilers, + * dynamic linker, etc, do not manipulate space id's, so there + * could be a significant performance benefit in switching contexts + * and not flushing the whole tlb. */ static inline void flush_tlb_mm(struct mm_struct *mm) @@ -45,10 +52,18 @@ static inline void flush_tlb_mm(struct mm_struct *mm) BUG_ON(mm == &init_mm); /* Should never happen */ #if 1 || defined(CONFIG_SMP) + /* Except for very small threads, flushing the whole TLB is + * faster than using __flush_tlb_range. The pdtlb and pitlb + * instructions are very slow because of the TLB broadcast. + * It might be faster to do local range flushes on all CPUs + * on PA 2.0 systems. + */ flush_tlb_all(); #else /* FIXME: currently broken, causing space id and protection ids - * to go out of sync, resulting in faults on userspace accesses. + * to go out of sync, resulting in faults on userspace accesses. + * This approach needs further investigation since running many + * small applications (e.g., GCC testsuite) is faster on HP-UX. */ if (mm) { if (mm->context != 0) @@ -65,22 +80,12 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, { unsigned long flags, sid; - /* For one page, it's not worth testing the split_tlb variable */ - - mb(); sid = vma->vm_mm->context; purge_tlb_start(flags); mtsp(sid, 1); pdtlb(addr); - pitlb(addr); + if (unlikely(split_tlb)) + pitlb(addr); purge_tlb_end(flags); } - -void __flush_tlb_range(unsigned long sid, - unsigned long start, unsigned long end); - -#define flush_tlb_range(vma,start,end) __flush_tlb_range((vma)->vm_mm->context,start,end) - -#define flush_tlb_kernel_range(start, end) __flush_tlb_range(0,start,end) - #endif |