litmus-rt.git - The LITMUS^RT kernel.

diff options

author	Tom Tucker <tom@opengridcomputing.com>	2007-12-30 22:07:34 -0500
committer	J. Bruce Fields <bfields@citi.umich.edu>	2008-02-01 16:42:08 -0500
commit	d7979ae4a050a45b78af51832475001b68263d2a (patch)
tree	f76bf9dea36d03a1141824202015d26002000589 /net
parent	323bee32e9bef14c6dd943ecc8e8cd373a9c94d9 (diff)

svc: Move close processing to a single place

Close handling was duplicated in the UDP and TCP recvfrom methods. This code has been moved to the transport independent svc_recv function. Signed-off-by: Tom Tucker <tom@opengridcomputing.com> Acked-by: Neil Brown <neilb@suse.de> Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Greg Banks <gnb@sgi.com> Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>

Diffstat (limited to 'net')

-rw-r--r--

net/sunrpc/svcsock.c

1 files changed, 11 insertions, 15 deletions

                 return svc_deferred_recv(rqstp);
         }
-        if (test_bit(SK_CLOSE, &svsk->sk_flags)) {
-                svc_delete_socket(svsk);
-                return 0;
-        }
         clear_bit(SK_DATA, &svsk->sk_flags);
         skb = NULL;
         err = kernel_recvmsg(svsk->sk_sock, &msg, NULL,
                 return svc_deferred_recv(rqstp);
         }
-        if (test_bit(SK_CLOSE, &svsk->sk_flags)) {
-                svc_delete_socket(svsk);
-                return 0;
-        }
         if (svsk->sk_sk->sk_state == TCP_LISTEN) {
                 svc_tcp_accept(svsk);
                 svc_sock_received(svsk);
         return len;
  err_delete:
-        svc_delete_socket(svsk);
+        set_bit(SK_CLOSE, &svsk->sk_flags);
         return -EAGAIN;
  error:
         }
         spin_unlock_bh(&pool->sp_lock);
-        dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n",
+        len = 0;
-                 rqstp, pool->sp_id, svsk, atomic_read(&svsk->sk_inuse));
+        if (test_bit(SK_CLOSE, &svsk->sk_flags)) {
-        len = svsk->sk_xprt.xpt_ops->xpo_recvfrom(rqstp);
+                dprintk("svc_recv: found SK_CLOSE\n");
-        dprintk("svc: got len=%d\n", len);
+                svc_delete_socket(svsk);
+        } else {
+                dprintk("svc: server %p, pool %u, socket %p, inuse=%d\n",
+                        rqstp, pool->sp_id, svsk, atomic_read(&svsk->sk_inuse));
+                len = svsk->sk_xprt.xpt_ops->xpo_recvfrom(rqstp);
+                dprintk("svc: got len=%d\n", len);
+        }
         /* No data, incomplete (TCP) read, or accept() */
         if (len == 0 || len == -EAGAIN) {

/* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel <riel@conectiva.com.br> * 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 <riel@conectiva.com.br> 2001 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 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) * mapping->i_mmap_mutex * 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) * 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 <asm/tlbflush.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); /* * 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; } 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. */ 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); } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } 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); } /** * 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); 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; } /* * 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; } static inline void unlock_anon_vma_root(struct anon_vma *root) { if (root) up_write(&root->rwsem); } /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. */ 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); } unlock_anon_vma_root(root); return 0; enomem_failure: unlink_anon_vmas(dst); return -ENOMEM; } /* * 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; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ if (anon_vma_clone(vma, pvma)) return -ENOMEM; /* 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; /* * 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_unlock_write(anon_vma); return 0; out_error_free_anon_vma: put_anon_vma(anon_vma); out_error: unlink_anon_vmas(vma); return -ENOMEM; } 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)) continue; list_del(&avc->same_vma); anon_vma_chain_free(avc); } 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; put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } } 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; } 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, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC); } /* * 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) ACCESS_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)) { put_anon_vma(anon_vma); anon_vma = NULL; } out: rcu_read_unlock(); return anon_vma; } /* * 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) ACCESS_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 = ACCESS_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)) { put_anon_vma(anon_vma); anon_vma = NULL; goto out; } /* 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; } void page_unlock_anon_vma_read(struct anon_vma *anon_vma) { anon_vma_unlock_read(anon_vma); } /* * At what user virtual address is page expected in @vma? */ static inline unsigned long __vma_address(struct page *page, struct vm_area_struct *vma) { pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); if (unlikely(is_vm_hugetlb_page(vma))) pgoff = page->index << huge_page_order(page_hstate(page)); return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); } inline unsigned long vma_address(struct page *page, struct vm_area_struct *vma) { unsigned long address = __vma_address(page, vma); /* page should be within @vma mapping range */ VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end); return address; } /* * 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 && !(vma->vm_flags & VM_NONLINEAR)) { 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; } pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; pud_t *pud; pmd_t *pmd = NULL; 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); if (!pmd_present(*pmd)) pmd = NULL; out: return pmd; } /* * 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))) { pte = huge_pte_offset(mm, address); ptl = &mm->page_table_lock; goto check; } pmd = mm_find_pmd(mm, address); if (!pmd) return NULL; if (pmd_trans_huge(*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; } /** * 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; } /* * Subfunctions of page_referenced: page_referenced_one called * repeatedly from either page_referenced_anon or page_referenced_file. */ int page_referenced_one(struct page *page, struct vm_area_struct *vma, unsigned long address, unsigned int *mapcount, unsigned long *vm_flags) { struct mm_struct *mm = vma->vm_mm; int referenced = 0; if (unlikely(PageTransHuge(page))) { pmd_t *pmd; spin_lock(&mm->page_table_lock); /* * rmap might return false positives; we must filter * these out using page_check_address_pmd(). */ pmd = page_check_address_pmd(page, mm, address, PAGE_CHECK_ADDRESS_PMD_FLAG); if (!pmd) { spin_unlock(&mm->page_table_lock); goto out; } if (vma->vm_flags & VM_LOCKED) { spin_unlock(&mm->page_table_lock); *mapcount = 0; /* break early from loop */ *vm_flags |= VM_LOCKED; goto out; } /* go ahead even if the pmd is pmd_trans_splitting() */ if (pmdp_clear_flush_young_notify(vma, address, pmd)) referenced++; spin_unlock(&mm->page_table_lock); } else { pte_t *pte; spinlock_t *ptl; /* * rmap might return false positives; we must filter * these out using page_check_address(). */ pte = page_check_address(page, mm, address, &ptl, 0); if (!pte) goto out; if (vma->vm_flags & VM_LOCKED) { pte_unmap_unlock(pte, ptl); *mapcount = 0; /* break early from loop */ *vm_flags |= VM_LOCKED; goto out; } if (ptep_clear_flush_young_notify(vma, address, pte)) { /* * Don't treat a reference through a sequentially read * mapping as such. If the page has been used in * another mapping, we will catch it; if this other * mapping is already gone, the unmap path will have * set PG_referenced or activated the page. */ if (likely(!(vma->vm_flags & VM_SEQ_READ))) referenced++; } pte_unmap_unlock(pte, ptl); } (*mapcount)--; if (referenced) *vm_flags |= vma->vm_flags; out: return referenced; } static int page_referenced_anon(struct page *page, struct mem_cgroup *memcg, unsigned long *vm_flags) { unsigned int mapcount; struct anon_vma *anon_vma; pgoff_t pgoff; struct anon_vma_chain *avc; int referenced = 0; anon_vma = page_lock_anon_vma_read(page); if (!anon_vma) return referenced; mapcount = page_mapcount(page); pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); /* * If we are reclaiming on behalf of a cgroup, skip * counting on behalf of references from different * cgroups */ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) continue; referenced += page_referenced_one(page, vma, address, &mapcount, vm_flags); if (!mapcount) break; } page_unlock_anon_vma_read(anon_vma); return referenced; } /** * page_referenced_file - referenced check for object-based rmap * @page: the page we're checking references on. * @memcg: target memory control group * @vm_flags: collect encountered vma->vm_flags who actually referenced the page * * For an object-based mapped page, find all the places it is mapped and * check/clear the referenced flag. This is done by following the page->mapping * pointer, then walking the chain of vmas it holds. It returns the number * of references it found. * * This function is only called from page_referenced for object-based pages. */ static int page_referenced_file(struct page *page, struct mem_cgroup *memcg, unsigned long *vm_flags) { unsigned int mapcount; struct address_space *mapping = page->mapping; pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); struct vm_area_struct *vma; int referenced = 0; /* * The caller's checks on page->mapping and !PageAnon have made * sure that this is a file page: the check for page->mapping * excludes the case just before it gets set on an anon page. */ BUG_ON(PageAnon(page)); /* * The page lock not only makes sure that page->mapping cannot * suddenly be NULLified by truncation, it makes sure that the * structure at mapping cannot be freed and reused yet, * so we can safely take mapping->i_mmap_mutex. */ BUG_ON(!PageLocked(page)); mutex_lock(&mapping->i_mmap_mutex); /* * i_mmap_mutex does not stabilize mapcount at all, but mapcount * is more likely to be accurate if we note it after spinning. */ mapcount = page_mapcount(page); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); /* * If we are reclaiming on behalf of a cgroup, skip * counting on behalf of references from different * cgroups */ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) continue; referenced += page_referenced_one(page, vma, address, &mapcount, vm_flags); if (!mapcount) break; } mutex_unlock(&mapping->i_mmap_mutex); return referenced; } /** * page_referenced - test if the page was referenced * @page: the page to test * @is_locked: caller holds lock on the page * @memcg: target memory cgroup * @vm_flags: collect encountered vma->vm_flags who actually referenced the page * * Quick test_and_clear_referenced for all mappings to a page, * returns the number of ptes which referenced the page. */ int page_referenced(struct page *page, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags) { int referenced = 0; int we_locked = 0; *vm_flags = 0; if (page_mapped(page) && page_rmapping(page)) { if (!is_locked && (!PageAnon(page) || PageKsm(page))) { we_locked = trylock_page(page); if (!we_locked) { referenced++; goto out; } } if (unlikely(PageKsm(page))) referenced += page_referenced_ksm(page, memcg, vm_flags); else if (PageAnon(page)) referenced += page_referenced_anon(page, memcg, vm_flags); else if (page->mapping) referenced += page_referenced_file(page, memcg, vm_flags); if (we_locked) unlock_page(page); } out: return referenced; } static int page_mkclean_one(struct page *page, struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; pte_t *pte; spinlock_t *ptl; int ret = 0; pte = page_check_address(page, mm, address, &ptl, 1); if (!pte) goto out; if (pte_dirty(*pte) || pte_write(*pte)) { pte_t entry; flush_cache_page(vma, address, pte_pfn(*pte)); entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(mm, address, pte, entry); ret = 1; } pte_unmap_unlock(pte, ptl); if (ret) mmu_notifier_invalidate_page(mm, address); out: return ret; } static int page_mkclean_file(struct address_space *mapping, struct page *page) { pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); struct vm_area_struct *vma; int ret = 0; BUG_ON(PageAnon(page)); mutex_lock(&mapping->i_mmap_mutex); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { if (vma->vm_flags & VM_SHARED) { unsigned long address = vma_address(page, vma); ret += page_mkclean_one(page, vma, address); } } mutex_unlock(&mapping->i_mmap_mutex); return ret; } int page_mkclean(struct page *page) { int ret = 0; BUG_ON(!PageLocked(page));


context:
space:
mode: