#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, unsignedlong address,
pmd_t *pmdp, pmd_t entry, int dirty)
{ int changed; #ifdef CONFIG_DEBUG_VM
WARN_ON(!pmd_trans_huge(*pmdp));
assert_spin_locked(pmd_lockptr(vma->vm_mm, pmdp)); #endif
changed = !pmd_same(*(pmdp), entry); if (changed) { /* * We can use MMU_PAGE_2M here, because only radix * path look at the psize.
*/
__ptep_set_access_flags(vma, pmdp_ptep(pmdp),
pmd_pte(entry), address, MMU_PAGE_2M);
} return changed;
}
int pudp_set_access_flags(struct vm_area_struct *vma, unsignedlong address,
pud_t *pudp, pud_t entry, int dirty)
{ int changed; #ifdef CONFIG_DEBUG_VM
assert_spin_locked(pud_lockptr(vma->vm_mm, pudp)); #endif
changed = !pud_same(*(pudp), entry); if (changed) { /* * We can use MMU_PAGE_1G here, because only radix * path look at the psize.
*/
__ptep_set_access_flags(vma, pudp_ptep(pudp),
pud_pte(entry), address, MMU_PAGE_1G);
} return changed;
}
/* * 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, unsignedlong addr,
pmd_t *pmdp, pmd_t pmd)
{ #ifdef CONFIG_DEBUG_VM /* * Make sure hardware valid bit is not set. We don't do * tlb flush for this update.
*/
void set_pud_at(struct mm_struct *mm, unsignedlong addr,
pud_t *pudp, pud_t pud)
{ #ifdef CONFIG_DEBUG_VM /* * Make sure hardware valid bit is not set. We don't do * tlb flush for this update.
*/
staticvoid do_serialize(void *arg)
{ /* We've taken the IPI, so try to trim the mask while here */ if (radix_enabled()) { struct mm_struct *mm = arg;
exit_lazy_flush_tlb(mm, false);
}
}
/* * Serialize against __find_linux_pte() which does lock-less * lookup in page tables with local interrupts disabled. For huge pages * it casts pmd_t to pte_t. Since format of pte_t is different from * pmd_t we want to prevent transit from pmd pointing to page table * to pmd pointing to huge page (and back) while interrupts are disabled. * We clear pmd to possibly replace it with page table pointer in * different code paths. So make sure we wait for the parallel * __find_linux_pte() to finish.
*/ void serialize_against_pte_lookup(struct mm_struct *mm)
{
smp_mb();
smp_call_function_many(mm_cpumask(mm), do_serialize, mm, 1);
}
/* * We use this to invalidate a pmdp entry before switching from a * hugepte to regular pmd entry.
*/
pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsignedlong address,
pmd_t *pmdp)
{ unsignedlong old_pmd;
pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma, unsignedlong addr, pmd_t *pmdp, int full)
{
pmd_t pmd;
VM_BUG_ON(addr & ~HPAGE_PMD_MASK);
VM_BUG_ON((pmd_present(*pmdp) && !pmd_trans_huge(*pmdp)) ||
!pmd_present(*pmdp));
pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp); /* * if it not a fullmm flush, then we can possibly end up converting * this PMD pte entry to a regular level 0 PTE by a parallel page fault. * Make sure we flush the tlb in this case.
*/ if (!full)
flush_pmd_tlb_range(vma, addr, addr + HPAGE_PMD_SIZE); return pmd;
}
VM_BUG_ON(addr & ~HPAGE_PMD_MASK);
VM_BUG_ON(!pud_present(*pudp));
pud = pudp_huge_get_and_clear(vma->vm_mm, addr, pudp); /* * if it not a fullmm flush, then we can possibly end up converting * this PMD pte entry to a regular level 0 PTE by a parallel page fault. * Make sure we flush the tlb in this case.
*/ if (!full)
flush_pud_tlb_range(vma, addr, addr + HPAGE_PUD_SIZE); return pud;
}
/* * At some point we should be able to get rid of * pmd_mkhuge() and mk_huge_pmd() when we update all the * other archs to mark the pmd huge in pfn_pmd()
*/
pmd_t pfn_pmd(unsignedlong pfn, pgprot_t pgprot)
{ unsignedlong pmdv;
/* For use by kexec, called with MMU off */
notrace void mmu_cleanup_all(void)
{ if (radix_enabled())
radix__mmu_cleanup_all(); elseif (mmu_hash_ops.hpte_clear_all)
mmu_hash_ops.hpte_clear_all();
reset_sprs();
}
#ifdef CONFIG_MEMORY_HOTPLUG int __meminit create_section_mapping(unsignedlong start, unsignedlong end, int nid, pgprot_t prot)
{ if (radix_enabled()) return radix__create_section_mapping(start, end, nid, prot);
/* * When ultravisor is enabled, the partition table is stored in secure * memory and can only be accessed doing an ultravisor call. However, we * maintain a copy of the partition table in normal memory to allow Nest * MMU translations to occur (for normal VMs). * * Therefore, here we always update partition_tb, regardless of whether * we are running under an ultravisor or not.
*/
partition_tb[lpid].patb0 = cpu_to_be64(dw0);
partition_tb[lpid].patb1 = cpu_to_be64(dw1);
/* * If ultravisor is enabled, we do an ultravisor call to register the * partition table entry (PATE), which also do a global flush of TLBs * and partition table caches for the lpid. Otherwise, just do the * flush. The type of flush (hash or radix) depends on what the previous * use of the partition ID was, not the new use.
*/ if (firmware_has_feature(FW_FEATURE_ULTRAVISOR)) {
uv_register_pate(lpid, dw0, dw1);
pr_info("PATE registered by ultravisor: dw0 = 0x%lx, dw1 = 0x%lx\n",
dw0, dw1);
} elseif (flush) { /* * Boot does not need to flush, because MMU is off and each * CPU does a tlbiel_all() before switching them on, which * flushes everything.
*/
flush_partition(lpid, (old & PATB_HR));
}
}
EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);
spin_lock(&mm->page_table_lock);
ret = mm->context.pmd_frag; if (ret) {
pmd_frag = ret + PMD_FRAG_SIZE; /* * If we have taken up all the fragments mark PTE page NULL
*/ if (((unsignedlong)pmd_frag & ~PAGE_MASK) == 0)
pmd_frag = NULL;
mm->context.pmd_frag = pmd_frag;
}
spin_unlock(&mm->page_table_lock); return (pmd_t *)ret;
}
if (mm == &init_mm)
gfp &= ~__GFP_ACCOUNT;
ptdesc = pagetable_alloc(gfp, 0); if (!ptdesc) return NULL; if (!pagetable_pmd_ctor(mm, ptdesc)) {
pagetable_free(ptdesc); return NULL;
}
atomic_set(&ptdesc->pt_frag_refcount, 1);
ret = ptdesc_address(ptdesc); /* * if we support only one fragment just return the * allocated page.
*/ if (PMD_FRAG_NR == 1) return ret;
spin_lock(&mm->page_table_lock); /* * If we find ptdesc_page set, we return * the allocated page with single fragment * count.
*/ if (likely(!mm->context.pmd_frag)) {
atomic_set(&ptdesc->pt_frag_refcount, PMD_FRAG_NR);
mm->context.pmd_frag = ret + PMD_FRAG_SIZE;
}
spin_unlock(&mm->page_table_lock);
/* * Clear the _PAGE_PRESENT so that no hardware parallel update is * possible. Also keep the pte_present true so that we don't take * wrong fault.
*/
pte_val = pte_update(vma->vm_mm, addr, ptep, _PAGE_PRESENT, _PAGE_INVALID, 0);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * For hash translation mode, we use the deposited table to store hash slot * information and they are stored at PTRS_PER_PMD offset from related pmd * location. Hence a pmd move requires deposit and withdraw. * * For radix translation with split pmd ptl, we store the deposited table in the * pmd page. Hence if we have different pmd page we need to withdraw during pmd * move. * * With hash we use deposited table always irrespective of anon or not. * With radix we use deposited table only for anonymous mapping.
*/ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, struct spinlock *old_pmd_ptl, struct vm_area_struct *vma)
{ if (radix_enabled()) return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma);
returntrue;
} #endif
/* * Does the CPU support tlbie?
*/ bool tlbie_capable __read_mostly = IS_ENABLED(CONFIG_PPC_RADIX_BROADCAST_TLBIE);
EXPORT_SYMBOL(tlbie_capable);
/* * Should tlbie be used for management of CPU TLBs, for kernel and process * address spaces? tlbie may still be used for nMMU accelerators, and for KVM * guest address spaces.
*/ bool tlbie_enabled __read_mostly = IS_ENABLED(CONFIG_PPC_RADIX_BROADCAST_TLBIE);
staticint __init setup_disable_tlbie(char *str)
{ if (!radix_enabled()) {
pr_err("disable_tlbie: Unable to disable TLBIE with Hash MMU.\n"); return 1;
}
staticint __init pgtable_debugfs_setup(void)
{ if (!tlbie_capable) return 0;
/* * There is no locking vs tlb flushing when changing this value. * The tlb flushers will see one value or another, and use either * tlbie or tlbiel with IPIs. In both cases the TLBs will be * invalidated as expected.
*/
debugfs_create_bool("tlbie_enabled", 0600,
arch_debugfs_dir,
&tlbie_enabled);
return 0;
}
arch_initcall(pgtable_debugfs_setup);
#ifdefined(CONFIG_ZONE_DEVICE) && defined(CONFIG_ARCH_HAS_MEMREMAP_COMPAT_ALIGN) /* * Override the generic version in mm/memremap.c. * * With hash translation, the direct-map range is mapped with just one * page size selected by htab_init_page_sizes(). Consult * mmu_psize_defs[] to determine the minimum page size alignment.
*/ unsignedlong memremap_compat_align(void)
{ if (!radix_enabled()) { unsignedint shift = mmu_psize_defs[mmu_linear_psize].shift; return max(SUBSECTION_SIZE, 1UL << shift);
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.