cregit-Linux how code gets into the kernel

Release 4.8 mm/rmap.c

Directory: mm
 * mm/rmap.c - physical to virtual reverse mappings
 * Copyright 2001, Rik van Riel <>
 * Released under the General Public License (GPL).
 * Simple, low overhead reverse mapping scheme.
 * Please try to keep this thing as modular as possible.
 * Provides methods for unmapping each kind of mapped page:
 * the anon methods track anonymous pages, and
 * the file methods track pages belonging to an inode.
 * Original design by Rik van Riel <> 2001
 * File methods by Dave McCracken <> 2003, 2004
 * Anonymous methods by Andrea Arcangeli <> 2004
 * Contributions by Hugh Dickins 2003, 2004

 * Lock ordering in mm:
 * inode->i_mutex       (while writing or truncating, not reading or faulting)
 *   mm->mmap_sem
 *     page->flags PG_locked (lock_page)
 *       hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share)
 *         mapping->i_mmap_rwsem
 *           anon_vma->rwsem
 *             mm->page_table_lock or pte_lock
 *               zone_lru_lock (in mark_page_accessed, isolate_lru_page)
 *               swap_lock (in swap_duplicate, swap_info_get)
 *                 mmlist_lock (in mmput, drain_mmlist and others)
 *                 mapping->private_lock (in __set_page_dirty_buffers)
 *                   mem_cgroup_{begin,end}_page_stat (memcg->move_lock)
 *                     mapping->tree_lock (widely used)
 *                 inode->i_lock (in set_page_dirty's __mark_inode_dirty)
 *                 bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
 *                   sb_lock (within inode_lock in fs/fs-writeback.c)
 *                   mapping->tree_lock (widely used, in set_page_dirty,
 *                             in arch-dependent flush_dcache_mmap_lock,
 *                             within bdi.wb->list_lock in __sync_single_inode)
 * anon_vma->rwsem,mapping->i_mutex      (memory_failure, collect_procs_anon)
 *   ->tasklist_lock
 *     pte map lock

#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/rcupdate.h>
#include <linux/export.h>
#include <linux/memcontrol.h>
#include <linux/mmu_notifier.h>
#include <linux/migrate.h>
#include <linux/hugetlb.h>
#include <linux/backing-dev.h>
#include <linux/page_idle.h>

#include <asm/tlbflush.h>

#include <trace/events/tlb.h>

#include "internal.h"

static struct kmem_cache *anon_vma_cachep;

static struct kmem_cache *anon_vma_chain_cachep;

static inline struct anon_vma *anon_vma_alloc(void) { struct anon_vma *anon_vma; anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); anon_vma->degree = 1; /* Reference for first vma */ anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. */ anon_vma->root = anon_vma; } return anon_vma; }


peter zijlstrapeter zijlstra3351.56%133.33%
adrian bunkadrian bunk1828.12%133.33%
konstantin khlebnikovkonstantin khlebnikov1320.31%133.33%

static inline void anon_vma_free(struct anon_vma *anon_vma) { VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* * Synchronize against page_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by * down_read_trylock() from page_lock_anon_vma_read(). This orders: * * page_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() * * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); }


peter zijlstrapeter zijlstra3356.90%228.57%
adrian bunkadrian bunk1729.31%114.29%
ingo molnaringo molnar46.90%228.57%
hugh dickinshugh dickins35.17%114.29%
konstantin khlebnikovkonstantin khlebnikov11.72%114.29%

static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); }


rik van rielrik van riel1785.00%150.00%
linus torvaldslinus torvalds315.00%150.00%

static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); }


rik van rielrik van riel1794.44%150.00%
namhyung kimnamhyung kim15.56%150.00%

static void anon_vma_chain_link(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { avc->vma = vma; avc->anon_vma = anon_vma; list_add(&avc->same_vma, &vma->anon_vma_chain); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); }


kautuk consulkautuk consul5496.43%150.00%
michel lespinassemichel lespinasse23.57%150.00%

/** * anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, but if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in page_lock_anon_vma_read() * and that may actually touch the spinlock even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. * * This must be called with the mmap_sem held for reading. */
int anon_vma_prepare(struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; might_sleep(); if (unlikely(!anon_vma)) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *allocated; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; allocated = anon_vma; } anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); /* vma reference or self-parent link for new root */ anon_vma->degree++; allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); } return 0; out_enomem_free_avc: anon_vma_chain_free(avc); out_enomem: return -ENOMEM; }


andrew mortonandrew morton12759.91%216.67%
rik van rielrik van riel4018.87%18.33%
linus torvaldslinus torvalds125.66%216.67%
oleg nesterovoleg nesterov115.19%18.33%
hugh dickinshugh dickins115.19%18.33%
konstantin khlebnikovkonstantin khlebnikov73.30%216.67%
kautuk consulkautuk consul20.94%18.33%
peter zijlstrapeter zijlstra10.47%18.33%
ingo molnaringo molnar10.47%18.33%

/* * This is a useful helper function for locking the anon_vma root as * we traverse the vma->anon_vma_chain, looping over anon_vma's that * have the same vma. * * Such anon_vma's should have the same root, so you'd expect to see * just a single mutex_lock for the whole traversal. */
static inline struct anon_vma *lock_anon_vma_root(struct anon_vma *root, struct anon_vma *anon_vma) { struct anon_vma *new_root = anon_vma->root; if (new_root != root) { if (WARN_ON_ONCE(root)) up_write(&root->rwsem); root = new_root; down_write(&root->rwsem); } return root; }


linus torvaldslinus torvalds6293.94%150.00%
ingo molnaringo molnar46.06%150.00%

static inline void unlock_anon_vma_root(struct anon_vma *root) { if (root) up_write(&root->rwsem); }


linus torvaldslinus torvalds2291.67%150.00%
ingo molnaringo molnar28.33%150.00%

/* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. * * If dst->anon_vma is NULL this function tries to find and reuse existing * anon_vma which has no vmas and only one child anon_vma. This prevents * degradation of anon_vma hierarchy to endless linear chain in case of * constantly forking task. On the other hand, an anon_vma with more than one * child isn't reused even if there was no alive vma, thus rmap walker has a * good chance of avoiding scanning the whole hierarchy when it searches where * page is mapped. */
int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { struct anon_vma_chain *avc, *pavc; struct anon_vma *root = NULL; list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { struct anon_vma *anon_vma; avc = anon_vma_chain_alloc(GFP_NOWAIT | __GFP_NOWARN); if (unlikely(!avc)) { unlock_anon_vma_root(root); root = NULL; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto enomem_failure; } anon_vma = pavc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_chain_link(dst, avc, anon_vma); /* * Reuse existing anon_vma if its degree lower than two, * that means it has no vma and only one anon_vma child. * * Do not chose parent anon_vma, otherwise first child * will always reuse it. Root anon_vma is never reused: * it has self-parent reference and at least one child. */ if (!dst->anon_vma && anon_vma != src->anon_vma && anon_vma->degree < 2) dst->anon_vma = anon_vma; } if (dst->anon_vma) dst->anon_vma->degree++; unlock_anon_vma_root(root); return 0; enomem_failure: /* * dst->anon_vma is dropped here otherwise its degree can be incorrectly * decremented in unlink_anon_vmas(). * We can safely do this because callers of anon_vma_clone() don't care * about dst->anon_vma if anon_vma_clone() failed. */ dst->anon_vma = NULL; unlink_anon_vmas(dst); return -ENOMEM; }


linus torvaldslinus torvalds6436.16%342.86%
rik van rielrik van riel5028.25%114.29%
konstantin khlebnikovkonstantin khlebnikov3922.03%114.29%
andrew mortonandrew morton179.60%114.29%
leon yuleon yu73.95%114.29%

/* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */
int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; int error; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ vma->anon_vma = NULL; /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ error = anon_vma_clone(vma, pvma); if (error) return error; /* An existing anon_vma has been reused, all done then. */ if (vma->anon_vma) return 0; /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; /* * The root anon_vma's spinlock is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); anon_vma->parent->degree++; anon_vma_unlock_write(anon_vma); return 0; out_error_free_anon_vma: put_anon_vma(anon_vma); out_error: unlink_anon_vmas(vma); return -ENOMEM; }


rik van rielrik van riel10054.64%433.33%
konstantin khlebnikovkonstantin khlebnikov3318.03%216.67%
andrew mortonandrew morton2614.21%18.33%
linus torvaldslinus torvalds116.01%216.67%
daniel forrestdaniel forrest105.46%18.33%
peter zijlstrapeter zijlstra21.09%18.33%
ingo molnaringo molnar10.55%18.33%

void unlink_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; struct anon_vma *root = NULL; /* * Unlink each anon_vma chained to the VMA. This list is ordered * from newest to oldest, ensuring the root anon_vma gets freed last. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; root = lock_anon_vma_root(root, anon_vma); anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); /* * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root)) { anon_vma->parent->degree--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } if (vma->anon_vma) vma->anon_vma->degree--; unlock_anon_vma_root(root); /* * Iterate the list once more, it now only contains empty and unlinked * anon_vmas, destroy them. Could not do before due to __put_anon_vma() * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; VM_WARN_ON(anon_vma->degree); put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } }


peter zijlstrapeter zijlstra6539.39%112.50%
andrew mortonandrew morton3320.00%112.50%
rik van rielrik van riel3018.18%225.00%
konstantin khlebnikovkonstantin khlebnikov2917.58%225.00%
michel lespinassemichel lespinasse74.24%112.50%
ingo molnaringo molnar10.61%112.50%

static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); anon_vma->rb_root = RB_ROOT; }


andrew mortonandrew morton2356.10%116.67%
peter zijlstrapeter zijlstra614.63%116.67%
mel gormanmel gorman49.76%116.67%
michel lespinassemichel lespinasse37.32%116.67%
christoph lameterchristoph lameter37.32%116.67%
ingo molnaringo molnar24.88%116.67%

void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_DESTROY_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC|SLAB_ACCOUNT); }


andrew mortonandrew morton2764.29%125.00%
rik van rielrik van riel921.43%125.00%
vladimir davydovvladimir davydov49.52%125.00%
hugh dickinshugh dickins24.76%125.00%

/* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against page_remove_rmap() * the best this function can do is return a locked anon_vma that might * have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe page_mapped() [ hence all those page_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is DESTROY_BY_RCU and we know from page_remove_rmap() * that the anon_vma pointer from page->mapping is valid if there is a * mapcount, we can dereference the anon_vma after observing those. */
struct anon_vma *page_get_anon_vma(struct page *page) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } /* * If this page is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: * SLAB_DESTROY_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!page_mapped(page)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; }


hugh dickinshugh dickins9776.98%571.43%
peter zijlstrapeter zijlstra2822.22%114.29%
jason lowjason low10.79%114.29%

/* * Similar to page_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with page_get_anon_vma() and then block on the mutex. */
struct anon_vma *page_lock_anon_vma_read(struct page *page) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(page->mapping); if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) goto out; if (!page_mapped(page)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * If the page is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ if (!page_mapped(page)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!page_mapped(page)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); anon_vma_lock_read(anon_vma); if (atomic_dec_and_test(&anon_vma->refcount)) { /* * Oops, we held the last refcount, release the lock * and bail -- can't simply use put_anon_vma() because * we'll deadlock on the anon_vma_lock_write() recursion. */ anon_vma_unlock_read(anon_vma); __put_anon_vma(anon_vma); anon_vma = NULL; } return anon_vma; out: rcu_read_unlock(); return anon_vma; }


peter zijlstrapeter zijlstra18183.41%333.33%
hugh dickinshugh dickins2611.98%333.33%
ingo molnaringo molnar83.69%222.22%
jason lowjason low20.92%111.11%

void page_unlock_anon_vma_read(struct anon_vma *anon_vma) { anon_vma_unlock_read(anon_vma); }


oleg nesterovoleg nesterov1280.00%133.33%
ingo molnaringo molnar213.33%133.33%
peter zijlstrapeter zijlstra16.67%133.33%

#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */
void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc; int cpu; if (!tlb_ubc->flush_required) return; cpu = get_cpu(); if (cpumask_test_cpu(cpu, &tlb_ubc->cpumask)) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); local_flush_tlb(); trace_tlb_flush(TLB_LOCAL_SHOOTDOWN, TLB_FLUSH_ALL); } if (cpumask_any_but(&tlb_ubc->cpumask, cpu) < nr_cpu_ids) flush_tlb_others(&tlb_ubc->cpumask, NULL, 0, TLB_FLUSH_ALL); cpumask_clear(&tlb_ubc->cpumask); tlb_ubc->flush_required = false; tlb_ubc->writable = false; put_cpu(); }


mel gormanmel gorman9584.07%266.67%
nadav amitnadav amit1815.93%133.33%

/* Flush iff there are potentially writable TLB entries that can race with IO */
void try_to_unmap_flush_dirty(void) { struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); }


mel gormanmel gorman26100.00%1100.00%

static void set_tlb_ubc_flush_pending(struct mm_struct *mm, struct page *page, bool writable) { struct tlbflush_unmap_batch *tlb_ubc = &current->tlb_ubc; cpumask_or(&tlb_ubc->cpumask, &tlb_ubc->cpumask, mm_cpumask(mm)); tlb_ubc->flush_required = true; /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() * before the page is queued for IO. */ if (writable) tlb_ubc->writable = true; }


mel gormanmel gorman64100.00%2100.00%

/* * Returns true if the TLB flush should be deferred to the end of a batch of * unmap operations to reduce IPIs. */
static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { bool should_defer = false; if (!(flags & TTU_BATCH_FLUSH)) return false; /* If remote CPUs need to be flushed then defer batch the flush */ if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids) should_defer = true; put_cpu(); return should_defer; }


mel gormanmel gorman58100.00%1100.00%

static void set_tlb_ubc_flush_pending(struct mm_struct *mm, struct page *page, bool writable) { }


mel gormanmel gorman18100.00%2100.00%

static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; }


mel gormanmel gorman18100.00%1100.00%

#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /* * At what user virtual address is page expected in vma? * Caller should check the page is actually part of the vma. */
unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { unsigned long address; if (PageAnon(page)) { struct anon_vma *page__anon_vma = page_anon_vma(page); /* * Note: swapoff's unuse_vma() is more efficient with this * check, and needs it to match anon_vma when KSM is active. */ if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; } else if (page->mapping) { if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) return -EFAULT; } else return -EFAULT; address = __vma_address(page, vma); if (unlikely(address < vma->vm_start || address >= vma->vm_end)) return -EFAULT; return address; }


hugh dickinshugh dickins8463.64%360.00%
michel lespinassemichel lespinasse3123.48%120.00%
andrea arcangeliandrea arcangeli1712.88%120.00%

pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; pud_t *pud; pmd_t *pmd = NULL; pmd_t pmde; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; pud = pud_offset(pgd, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); /* * Some THP functions use the sequence pmdp_huge_clear_flush(), set_pmd_at() * without holding anon_vma lock for write. So when looking for a * genuine pmde (in which to find pte), test present and !THP together. */ pmde = *pmd; barrier(); if (!pmd_present(pmde) || pmd_trans_huge(pmde)) pmd = NULL; out: return pmd; }


bob liubob liu9684.21%125.00%
hugh dickinshugh dickins1412.28%125.00%
christian borntraegerchristian borntraeger32.63%125.00%
aneesh kumaraneesh kumar10.88%125.00%

/* * Check that @page is mapped at @address into @mm. * * If @sync is false, page_check_address may perform a racy check to avoid * the page table lock when the pte is not present (helpful when reclaiming * highly shared pages). * * On success returns with pte mapped and locked. */
pte_t *__page_check_address(struct page *page, struct mm_struct *mm, unsigned long address, spinlock_t **ptlp, int sync) { pmd_t *pmd; pte_t *pte; spinlock_t *ptl; if (unlikely(PageHuge(page))) { /* when pud is not present, pte will be NULL */ pte = huge_pte_offset(mm, address); if (!pte) return NULL; ptl = huge_pte_lockptr(page_hstate(page), mm, pte); goto check; } pmd = mm_find_pmd(mm, address); if (!pmd) return NULL; pte = pte_offset_map(pmd, address); /* Make a quick check before getting the lock */ if (!sync && !pte_present(*pte)) { pte_unmap(pte); return NULL; } ptl = pte_lockptr(mm, pmd); check: spin_lock(ptl); if (pte_present(*pte) && page_to_pfn(page) == pte_pfn(*pte)) { *ptlp = ptl; return pte; } pte_unmap_unlock(pte, ptl); return NULL; }


andrew mortonandrew morton5729.84%535.71%
hugh dickinshugh dickins5729.84%214.29%
naoya horiguchinaoya horiguchi3015.71%17.14%
nikita danilovnikita danilov199.95%17.14%
kirill a. shutemovkirill a. shutemov105.24%17.14%
jianguo wujianguo wu94.71%17.14%
nick pigginnick piggin63.14%17.14%
bob liubob liu21.05%17.14%
namhyung kimnamhyung kim10.52%17.14%

/** * page_mapped_in_vma - check whether a page is really mapped in a VMA * @page: the page to test * @vma: the VMA to test * * Returns 1 if the page is mapped into the page tables of the VMA, 0 * if the page is not mapped into the page tables of this VMA. Only * valid for normal file or anonymous VMAs. */
int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) { unsigned long address; pte_t *pte; spinlock_t *ptl; address = __vma_address(page, vma); if (unlikely(address < vma->vm_start || address >= vma->vm_end)) return 0; pte = page_check_address(page, vma->vm_mm, address, &ptl, 1); if (!pte) /* the page is not in this mm */ return 0; pte_unmap_unlock(pte, ptl); return 1; }


nick pigginnick piggin7984.95%150.00%
michel lespinassemichel lespinasse1415.05%150.00%

#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * Check that @page is mapped at @address into @mm. In contrast to * page_check_address(), this function can handle transparent huge pages. * * On success returns true with pte mapped and locked. For PMD-mapped * transparent huge pages *@ptep is set to NULL. */
bool page_check_address_transhuge(struct page *page, struct mm_struct *mm, unsigned long address, pmd_t **pmdp, pte_t **ptep, spinlock_t **ptlp) { pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t *pte; spinlock_t *ptl; if (unlikely(PageHuge(page))) { /* when pud is not present, pte will be NULL */ pte = huge_pte_offset(mm, address); if (!pte) return false; ptl = huge_pte_lockptr(page_hstate(page), mm, pte); pmd = NULL; goto check_pte; } pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) return false; pud = pud_offset(pgd, address); if (!pud_present(*pud)) return false; pmd = pmd_offset(pud, address); if (pmd_trans_huge(*pmd)) { ptl = pmd_lock(mm, pmd); if (!pmd_present(*pmd)) goto unlock_pmd; if (unlikely(!pmd_trans_huge(*pmd))) { spin_unlock(ptl); goto map_pte; } if (pmd_page(*pmd) != page) goto unlock_pmd; pte = NULL; goto found; unlock_pmd: spin_unlock(ptl); return false; } else { pmd_t pmde = *pmd; barrier(); if (!pmd_present(pmde) || pmd_trans_huge(pmde)) return false; } map_pte: pte = pte_offset_map(pmd, address); if (!pte_present(*pte)) { pte_unmap(pte); return false; } ptl = pte_lockptr(mm, pmd); check_pte: spin_lock(ptl); if (!pte_present(*pte)) { pte_unmap_unlock(pte, ptl); return false; } /* THP can be referenced by any subpage */ if (pte_pfn(*pte) - page_to_pfn(page) >= hpage_nr_pages(page)) { pte_unmap_unlock(pte, ptl); return false; } found: *ptep = pte; *pmdp = pmd; *ptlp = ptl; return true; }


kirill a. shutemovkirill a. shutemov26067.53%218.18%
vladimir davydovvladimir davydov5414.03%19.09%
andrea arcangeliandrea arcangeli369.35%218.18%
nikita danilovnikita danilov246.23%19.09%
joonsoo kimjoonsoo kim51.30%19.09%
hugh dickinshugh dickins41.04%218.18%
nick pigginnick piggin10.26%19.09%
fengguang wufengguang wu10.26%19.09%

#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ struct page_referenced_arg { int mapcount;