diff options
Diffstat (limited to 'arch/powerpc/mm/pgtable_64.c')
| -rw-r--r-- | arch/powerpc/mm/pgtable_64.c | 598 |
1 files changed, 590 insertions, 8 deletions
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 853d5565eed..f6ce1f111f5 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -26,15 +26,16 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/string.h> +#include <linux/export.h> #include <linux/types.h> #include <linux/mman.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/stddef.h> #include <linux/vmalloc.h> -#include <linux/init.h> #include <linux/bootmem.h> -#include <linux/lmb.h> +#include <linux/memblock.h> +#include <linux/slab.h> #include <asm/pgalloc.h> #include <asm/page.h> @@ -49,14 +50,22 @@ #include <asm/processor.h> #include <asm/cputable.h> #include <asm/sections.h> -#include <asm/system.h> -#include <asm/abs_addr.h> #include <asm/firmware.h> #include "mmu_decl.h" -unsigned long ioremap_bot = IOREMAP_BASE; +/* Some sanity checking */ +#if TASK_SIZE_USER64 > PGTABLE_RANGE +#error TASK_SIZE_USER64 exceeds pagetable range +#endif + +#ifdef CONFIG_PPC_STD_MMU_64 +#if TASK_SIZE_USER64 > (1UL << (ESID_BITS + SID_SHIFT)) +#error TASK_SIZE_USER64 exceeds user VSID range +#endif +#endif +unsigned long ioremap_bot = IOREMAP_BASE; #ifdef CONFIG_PPC_MMU_NOHASH static void *early_alloc_pgtable(unsigned long size) @@ -66,7 +75,7 @@ static void *early_alloc_pgtable(unsigned long size) if (init_bootmem_done) pt = __alloc_bootmem(size, size, __pa(MAX_DMA_ADDRESS)); else - pt = __va(lmb_alloc_base(size, size, + pt = __va(memblock_alloc_base(size, size, __pa(MAX_DMA_ADDRESS))); memset(pt, 0, size); @@ -143,6 +152,18 @@ int map_kernel_page(unsigned long ea, unsigned long pa, int flags) } #endif /* !CONFIG_PPC_MMU_NOHASH */ } + +#ifdef CONFIG_PPC_BOOK3E_64 + /* + * With hardware tablewalk, a sync is needed to ensure that + * subsequent accesses see the PTE we just wrote. Unlike userspace + * mappings, we can't tolerate spurious faults, so make sure + * the new PTE will be seen the first time. + */ + mb(); +#else + smp_wmb(); +#endif return 0; } @@ -222,6 +243,8 @@ void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size, caller); if (area == NULL) return NULL; + + area->phys_addr = paligned; ret = __ioremap_at(paligned, area->addr, size, flags); if (!ret) vunmap(area->addr); @@ -252,7 +275,17 @@ void __iomem * ioremap(phys_addr_t addr, unsigned long size) return __ioremap_caller(addr, size, flags, caller); } -void __iomem * ioremap_flags(phys_addr_t addr, unsigned long size, +void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size) +{ + unsigned long flags = _PAGE_NO_CACHE; + void *caller = __builtin_return_address(0); + + if (ppc_md.ioremap) + return ppc_md.ioremap(addr, size, flags, caller); + return __ioremap_caller(addr, size, flags, caller); +} + +void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags) { void *caller = __builtin_return_address(0); @@ -264,6 +297,14 @@ void __iomem * ioremap_flags(phys_addr_t addr, unsigned long size, /* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */ flags &= ~(_PAGE_USER | _PAGE_EXEC); +#ifdef _PAGE_BAP_SR + /* _PAGE_USER contains _PAGE_BAP_SR on BookE using the new PTE format + * which means that we just cleared supervisor access... oops ;-) This + * restores it + */ + flags |= _PAGE_BAP_SR; +#endif + if (ppc_md.ioremap) return ppc_md.ioremap(addr, size, flags, caller); return __ioremap_caller(addr, size, flags, caller); @@ -300,9 +341,550 @@ void iounmap(volatile void __iomem *token) } EXPORT_SYMBOL(ioremap); -EXPORT_SYMBOL(ioremap_flags); +EXPORT_SYMBOL(ioremap_wc); +EXPORT_SYMBOL(ioremap_prot); EXPORT_SYMBOL(__ioremap); EXPORT_SYMBOL(__ioremap_at); EXPORT_SYMBOL(iounmap); EXPORT_SYMBOL(__iounmap); EXPORT_SYMBOL(__iounmap_at); + +/* + * For hugepage we have pfn in the pmd, we use PTE_RPN_SHIFT bits for flags + * For PTE page, we have a PTE_FRAG_SIZE (4K) aligned virtual address. + */ +struct page *pmd_page(pmd_t pmd) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_trans_huge(pmd)) + return pfn_to_page(pmd_pfn(pmd)); +#endif + return virt_to_page(pmd_page_vaddr(pmd)); +} + +#ifdef CONFIG_PPC_64K_PAGES +static pte_t *get_from_cache(struct mm_struct *mm) +{ + void *pte_frag, *ret; + + spin_lock(&mm->page_table_lock); + ret = mm->context.pte_frag; + if (ret) { + pte_frag = ret + PTE_FRAG_SIZE; + /* + * If we have taken up all the fragments mark PTE page NULL + */ + if (((unsigned long)pte_frag & ~PAGE_MASK) == 0) + pte_frag = NULL; + mm->context.pte_frag = pte_frag; + } + spin_unlock(&mm->page_table_lock); + return (pte_t *)ret; +} + +static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel) +{ + void *ret = NULL; + struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK | + __GFP_REPEAT | __GFP_ZERO); + if (!page) + return NULL; + if (!kernel && !pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } + + ret = page_address(page); + spin_lock(&mm->page_table_lock); + /* + * If we find pgtable_page set, we return + * the allocated page with single fragement + * count. + */ + if (likely(!mm->context.pte_frag)) { + atomic_set(&page->_count, PTE_FRAG_NR); + mm->context.pte_frag = ret + PTE_FRAG_SIZE; + } + spin_unlock(&mm->page_table_lock); + + return (pte_t *)ret; +} + +pte_t *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel) +{ + pte_t *pte; + + pte = get_from_cache(mm); + if (pte) + return pte; + + return __alloc_for_cache(mm, kernel); +} + +void page_table_free(struct mm_struct *mm, unsigned long *table, int kernel) +{ + struct page *page = virt_to_page(table); + if (put_page_testzero(page)) { + if (!kernel) + pgtable_page_dtor(page); + free_hot_cold_page(page, 0); + } +} + +#ifdef CONFIG_SMP +static void page_table_free_rcu(void *table) +{ + struct page *page = virt_to_page(table); + if (put_page_testzero(page)) { + pgtable_page_dtor(page); + free_hot_cold_page(page, 0); + } +} + +void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) +{ + unsigned long pgf = (unsigned long)table; + + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); + pgf |= shift; + tlb_remove_table(tlb, (void *)pgf); +} + +void __tlb_remove_table(void *_table) +{ + void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE); + unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE; + + if (!shift) + /* PTE page needs special handling */ + page_table_free_rcu(table); + else { + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); + kmem_cache_free(PGT_CACHE(shift), table); + } +} +#else +void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift) +{ + if (!shift) { + /* PTE page needs special handling */ + struct page *page = virt_to_page(table); + if (put_page_testzero(page)) { + pgtable_page_dtor(page); + free_hot_cold_page(page, 0); + } + } else { + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); + kmem_cache_free(PGT_CACHE(shift), table); + } +} +#endif +#endif /* CONFIG_PPC_64K_PAGES */ + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + +/* + * This is called when relaxing access to a hugepage. It's also called in the page + * fault path when we don't hit any of the major fault cases, ie, a minor + * update of _PAGE_ACCESSED, _PAGE_DIRTY, etc... The generic code will have + * handled those two for us, we additionally deal with missing execute + * permission here on some processors + */ +int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp, pmd_t entry, int dirty) +{ + int changed; +#ifdef CONFIG_DEBUG_VM + WARN_ON(!pmd_trans_huge(*pmdp)); + assert_spin_locked(&vma->vm_mm->page_table_lock); +#endif + changed = !pmd_same(*(pmdp), entry); + if (changed) { + __ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry)); + /* + * Since we are not supporting SW TLB systems, we don't + * have any thing similar to flush_tlb_page_nohash() + */ + } + return changed; +} + +unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, unsigned long clr, + unsigned long set) +{ + + unsigned long old, tmp; + +#ifdef CONFIG_DEBUG_VM + WARN_ON(!pmd_trans_huge(*pmdp)); + assert_spin_locked(&mm->page_table_lock); +#endif + +#ifdef PTE_ATOMIC_UPDATES + __asm__ __volatile__( + "1: ldarx %0,0,%3\n\ + andi. %1,%0,%6\n\ + bne- 1b \n\ + andc %1,%0,%4 \n\ + or %1,%1,%7\n\ + stdcx. %1,0,%3 \n\ + bne- 1b" + : "=&r" (old), "=&r" (tmp), "=m" (*pmdp) + : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY), "r" (set) + : "cc" ); +#else + old = pmd_val(*pmdp); + *pmdp = __pmd((old & ~clr) | set); +#endif + if (old & _PAGE_HASHPTE) + hpte_do_hugepage_flush(mm, addr, pmdp); + return old; +} + +pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + pmd_t pmd; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + if (pmd_trans_huge(*pmdp)) { + pmd = pmdp_get_and_clear(vma->vm_mm, address, pmdp); + } else { + /* + * khugepaged calls this for normal pmd + */ + pmd = *pmdp; + pmd_clear(pmdp); + /* + * Wait for all pending hash_page to finish. This is needed + * in case of subpage collapse. When we collapse normal pages + * to hugepage, we first clear the pmd, then invalidate all + * the PTE entries. The assumption here is that any low level + * page fault will see a none pmd and take the slow path that + * will wait on mmap_sem. But we could very well be in a + * hash_page with local ptep pointer value. Such a hash page + * can result in adding new HPTE entries for normal subpages. + * That means we could be modifying the page content as we + * copy them to a huge page. So wait for parallel hash_page + * to finish before invalidating HPTE entries. We can do this + * by sending an IPI to all the cpus and executing a dummy + * function there. + */ + kick_all_cpus_sync(); + /* + * Now invalidate the hpte entries in the range + * covered by pmd. This make sure we take a + * fault and will find the pmd as none, which will + * result in a major fault which takes mmap_sem and + * hence wait for collapse to complete. Without this + * the __collapse_huge_page_copy can result in copying + * the old content. + */ + flush_tlb_pmd_range(vma->vm_mm, &pmd, address); + } + return pmd; +} + +int pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp); +} + +/* + * We currently remove entries from the hashtable regardless of whether + * the entry was young or dirty. The generic routines only flush if the + * entry was young or dirty which is not good enough. + * + * We should be more intelligent about this but for the moment we override + * these functions and force a tlb flush unconditionally + */ +int pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp); +} + +/* + * We mark the pmd splitting and invalidate all the hpte + * entries for this hugepage. + */ +void pmdp_splitting_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + unsigned long old, tmp; + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + +#ifdef CONFIG_DEBUG_VM + WARN_ON(!pmd_trans_huge(*pmdp)); + assert_spin_locked(&vma->vm_mm->page_table_lock); +#endif + +#ifdef PTE_ATOMIC_UPDATES + + __asm__ __volatile__( + "1: ldarx %0,0,%3\n\ + andi. %1,%0,%6\n\ + bne- 1b \n\ + ori %1,%0,%4 \n\ + stdcx. %1,0,%3 \n\ + bne- 1b" + : "=&r" (old), "=&r" (tmp), "=m" (*pmdp) + : "r" (pmdp), "i" (_PAGE_SPLITTING), "m" (*pmdp), "i" (_PAGE_BUSY) + : "cc" ); +#else + old = pmd_val(*pmdp); + *pmdp = __pmd(old | _PAGE_SPLITTING); +#endif + /* + * If we didn't had the splitting flag set, go and flush the + * HPTE entries. + */ + if (!(old & _PAGE_SPLITTING)) { + /* We need to flush the hpte */ + if (old & _PAGE_HASHPTE) + hpte_do_hugepage_flush(vma->vm_mm, address, pmdp); + } + /* + * This ensures that generic code that rely on IRQ disabling + * to prevent a parallel THP split work as expected. + */ + kick_all_cpus_sync(); +} + +/* + * We want to put the pgtable in pmd and use pgtable for tracking + * the base page size hptes + */ +void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp, + pgtable_t pgtable) +{ + pgtable_t *pgtable_slot; + assert_spin_locked(&mm->page_table_lock); + /* + * we store the pgtable in the second half of PMD + */ + pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD; + *pgtable_slot = pgtable; + /* + * expose the deposited pgtable to other cpus. + * before we set the hugepage PTE at pmd level + * hash fault code looks at the deposted pgtable + * to store hash index values. + */ + smp_wmb(); +} + +pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) +{ + pgtable_t pgtable; + pgtable_t *pgtable_slot; + + assert_spin_locked(&mm->page_table_lock); + pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD; + pgtable = *pgtable_slot; + /* + * Once we withdraw, mark the entry NULL. + */ + *pgtable_slot = NULL; + /* + * We store HPTE information in the deposited PTE fragment. + * zero out the content on withdraw. + */ + memset(pgtable, 0, PTE_FRAG_SIZE); + return pgtable; +} + +/* + * set a new huge pmd. We should not be called for updating + * an existing pmd entry. That should go via pmd_hugepage_update. + */ +void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd) +{ +#ifdef CONFIG_DEBUG_VM + WARN_ON(pmd_val(*pmdp) & _PAGE_PRESENT); + assert_spin_locked(&mm->page_table_lock); + WARN_ON(!pmd_trans_huge(pmd)); +#endif + return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd)); +} + +void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmdp) +{ + pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0); +} + +/* + * A linux hugepage PMD was changed and the corresponding hash table entries + * neesd to be flushed. + */ +void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp) +{ + int ssize, i; + unsigned long s_addr; + int max_hpte_count; + unsigned int psize, valid; + unsigned char *hpte_slot_array; + unsigned long hidx, vpn, vsid, hash, shift, slot; + + /* + * Flush all the hptes mapping this hugepage + */ + s_addr = addr & HPAGE_PMD_MASK; + hpte_slot_array = get_hpte_slot_array(pmdp); + /* + * IF we try to do a HUGE PTE update after a withdraw is done. + * we will find the below NULL. This happens when we do + * split_huge_page_pmd + */ + if (!hpte_slot_array) + return; + + /* get the base page size */ + psize = get_slice_psize(mm, s_addr); + + if (ppc_md.hugepage_invalidate) + return ppc_md.hugepage_invalidate(mm, hpte_slot_array, + s_addr, psize); + /* + * No bluk hpte removal support, invalidate each entry + */ + shift = mmu_psize_defs[psize].shift; + max_hpte_count = HPAGE_PMD_SIZE >> shift; + for (i = 0; i < max_hpte_count; i++) { + /* + * 8 bits per each hpte entries + * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit] + */ + valid = hpte_valid(hpte_slot_array, i); + if (!valid) + continue; + hidx = hpte_hash_index(hpte_slot_array, i); + + /* get the vpn */ + addr = s_addr + (i * (1ul << shift)); + if (!is_kernel_addr(addr)) { + ssize = user_segment_size(addr); + vsid = get_vsid(mm->context.id, addr, ssize); + WARN_ON(vsid == 0); + } else { + vsid = get_kernel_vsid(addr, mmu_kernel_ssize); + ssize = mmu_kernel_ssize; + } + + vpn = hpt_vpn(addr, vsid, ssize); + hash = hpt_hash(vpn, shift, ssize); + if (hidx & _PTEIDX_SECONDARY) + hash = ~hash; + + slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; + slot += hidx & _PTEIDX_GROUP_IX; + ppc_md.hpte_invalidate(slot, vpn, psize, + MMU_PAGE_16M, ssize, 0); + } +} + +static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot) +{ + pmd_val(pmd) |= pgprot_val(pgprot); + return pmd; +} + +pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot) +{ + pmd_t pmd; + /* + * For a valid pte, we would have _PAGE_PRESENT or _PAGE_FILE always + * set. We use this to check THP page at pmd level. + * leaf pte for huge page, bottom two bits != 00 + */ + pmd_val(pmd) = pfn << PTE_RPN_SHIFT; + pmd_val(pmd) |= _PAGE_THP_HUGE; + pmd = pmd_set_protbits(pmd, pgprot); + return pmd; +} + +pmd_t mk_pmd(struct page *page, pgprot_t pgprot) +{ + return pfn_pmd(page_to_pfn(page), pgprot); +} + +pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) +{ + + pmd_val(pmd) &= _HPAGE_CHG_MASK; + pmd = pmd_set_protbits(pmd, newprot); + return pmd; +} + +/* + * This is called at the end of handling a user page fault, when the + * fault has been handled by updating a HUGE PMD entry in the linux page tables. + * We use it to preload an HPTE into the hash table corresponding to + * the updated linux HUGE PMD entry. + */ +void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd) +{ + return; +} + +pmd_t pmdp_get_and_clear(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp) +{ + pmd_t old_pmd; + pgtable_t pgtable; + unsigned long old; + pgtable_t *pgtable_slot; + + old = pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0); + old_pmd = __pmd(old); + /* + * We have pmd == none and we are holding page_table_lock. + * So we can safely go and clear the pgtable hash + * index info. + */ + pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD; + pgtable = *pgtable_slot; + /* + * Let's zero out old valid and hash index details + * hash fault look at them. + */ + memset(pgtable, 0, PTE_FRAG_SIZE); + return old_pmd; +} + +int has_transparent_hugepage(void) +{ + if (!mmu_has_feature(MMU_FTR_16M_PAGE)) + return 0; + /* + * We support THP only if PMD_SIZE is 16MB. + */ + if (mmu_psize_defs[MMU_PAGE_16M].shift != PMD_SHIFT) + return 0; + /* + * We need to make sure that we support 16MB hugepage in a segement + * with base page size 64K or 4K. We only enable THP with a PAGE_SIZE + * of 64K. + */ + /* + * If we have 64K HPTE, we will be using that by default + */ + if (mmu_psize_defs[MMU_PAGE_64K].shift && + (mmu_psize_defs[MMU_PAGE_64K].penc[MMU_PAGE_16M] == -1)) + return 0; + /* + * Ok we only have 4K HPTE + */ + if (mmu_psize_defs[MMU_PAGE_4K].penc[MMU_PAGE_16M] == -1) + return 0; + + return 1; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ |