10 files changed, 152 insertions, 35 deletions

diff --git a/Documentation/filesystems/caching/fscache.txt b/Documentation/filesystems/caching/fscache.txt
index 057a3c71d524..7097fd29fb3d 100644
--- a/Documentation/filesystems/caching/fscache.txt
+++ b/Documentation/filesystems/caching/fscache.txt
@@ -272,6 +272,10 @@ proc files.
                 pgs=N   Number of pages given store req processing time
                 rxd=N   Number of store reqs deleted from tracking tree
                 olm=N   Number of store reqs over store limit
+        VmScan  nos=N   Number of release reqs against pages with no pending store
+                gon=N   Number of release reqs against pages stored by time lock granted
+                bsy=N   Number of release reqs ignored due to in-progress store
+                can=N   Number of page stores cancelled due to release req
         Ops     pend=N  Number of times async ops added to pending queues
                 run=N   Number of times async ops given CPU time
                 enq=N   Number of times async ops queued for processing
diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.txt
index 2666b1ed5e9e..1902c57b72ef 100644
--- a/Documentation/filesystems/caching/netfs-api.txt
+++ b/Documentation/filesystems/caching/netfs-api.txt
@@ -641,7 +641,7 @@ data file must be retired (see the relinquish cookie function below).
 
 Furthermore, note that this does not cancel the asynchronous read or write
 operation started by the read/alloc and write functions, so the page
-invalidation and release functions must use:
+invalidation functions must use:
 
         bool fscache_check_page_write(struct fscache_cookie *cookie,
                                       struct page *page);
@@ -654,6 +654,25 @@ to see if a page is being written to the cache, and:
 to wait for it to finish if it is.
 
 
+When releasepage() is being implemented, a special FS-Cache function exists to
+manage the heuristics of coping with vmscan trying to eject pages, which may
+conflict with the cache trying to write pages to the cache (which may itself
+need to allocate memory):
+
+        bool fscache_maybe_release_page(struct fscache_cookie *cookie,
+                                        struct page *page,
+                                        gfp_t gfp);
+
+This takes the netfs cookie, and the page and gfp arguments as supplied to
+releasepage().  It will return false if the page cannot be released yet for
+some reason and if it returns true, the page has been uncached and can now be
+released.
+
+To make a page available for release, this function may wait for an outstanding
+storage request to complete, or it may attempt to cancel the storage request -
+in which case the page will not be stored in the cache this time.
+
+
 ==========================
 INDEX AND DATA FILE UPDATE
 ==========================
diff --git a/fs/9p/cache.c b/fs/9p/cache.c
index 51c94e26a346..bcc5357a9069 100644
--- a/fs/9p/cache.c
+++ b/fs/9p/cache.c
@@ -343,18 +343,7 @@ int __v9fs_fscache_release_page(struct page *page, gfp_t gfp)
 
         BUG_ON(!vcookie->fscache);
 
-        if (PageFsCache(page)) {
-                if (fscache_check_page_write(vcookie->fscache, page)) {
-                        if (!(gfp & __GFP_WAIT))
-                                return 0;
-                        fscache_wait_on_page_write(vcookie->fscache, page);
-                }
-
-                fscache_uncache_page(vcookie->fscache, page);
-                ClearPageFsCache(page);
-        }
-
-        return 1;
+        return fscache_maybe_release_page(vnode->cache, page, gfp);
 }
 
 void __v9fs_fscache_invalidate_page(struct page *page)
@@ -368,7 +357,6 @@ void __v9fs_fscache_invalidate_page(struct page *page)
                 fscache_wait_on_page_write(vcookie->fscache, page);
                 BUG_ON(!PageLocked(page));
                 fscache_uncache_page(vcookie->fscache, page);
-                ClearPageFsCache(page);
         }
 }
 
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 681c2a7b013f..39b301662f22 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -315,7 +315,6 @@ static void afs_invalidatepage(struct page *page, unsigned long offset)
                         struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
                         fscache_wait_on_page_write(vnode->cache, page);
                         fscache_uncache_page(vnode->cache, page);
-                        ClearPageFsCache(page);
                 }
 #endif
 
@@ -349,17 +348,9 @@ static int afs_releasepage(struct page *page, gfp_t gfp_flags)
         /* deny if page is being written to the cache and the caller hasn't
          * elected to wait */
 #ifdef CONFIG_AFS_FSCACHE
-        if (PageFsCache(page)) {
-                if (fscache_check_page_write(vnode->cache, page)) {
-                        if (!(gfp_flags & __GFP_WAIT)) {
-                                _leave(" = F [cache busy]");
-                                return 0;
-                        }
-                        fscache_wait_on_page_write(vnode->cache, page);
-                }
-
-                fscache_uncache_page(vnode->cache, page);
-                ClearPageFsCache(page);
+        if (!fscache_maybe_release_page(vnode->cache, page, gfp_flags)) {
+                _leave(" = F [cache busy]");
+                return 0;
         }
 #endif
 
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index a0769872b19c..e5046519b153 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -180,6 +180,11 @@ extern atomic_t fscache_n_store_pages;
 extern atomic_t fscache_n_store_radix_deletes;
 extern atomic_t fscache_n_store_pages_over_limit;
 
+extern atomic_t fscache_n_store_vmscan_not_storing;
+extern atomic_t fscache_n_store_vmscan_gone;
+extern atomic_t fscache_n_store_vmscan_busy;
+extern atomic_t fscache_n_store_vmscan_cancelled;
+
 extern atomic_t fscache_n_marks;
 extern atomic_t fscache_n_uncaches;
 
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 022a5da8e130..fc76798bd968 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -43,6 +43,75 @@ void __fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *pa
 EXPORT_SYMBOL(__fscache_wait_on_page_write);
 
 /*
+ * decide whether a page can be released, possibly by cancelling a store to it
+ * - we're allowed to sleep if __GFP_WAIT is flagged
+ */
+bool __fscache_maybe_release_page(struct fscache_cookie *cookie,
+                                  struct page *page,
+                                  gfp_t gfp)
+{
+        struct page *xpage;
+        void *val;
+
+        _enter("%p,%p,%x", cookie, page, gfp);
+
+        rcu_read_lock();
+        val = radix_tree_lookup(&cookie->stores, page->index);
+        if (!val) {
+                rcu_read_unlock();
+                fscache_stat(&fscache_n_store_vmscan_not_storing);
+                __fscache_uncache_page(cookie, page);
+                return true;
+        }
+
+        /* see if the page is actually undergoing storage - if so we can't get
+         * rid of it till the cache has finished with it */
+        if (radix_tree_tag_get(&cookie->stores, page->index,
+                               FSCACHE_COOKIE_STORING_TAG)) {
+                rcu_read_unlock();
+                goto page_busy;
+        }
+
+        /* the page is pending storage, so we attempt to cancel the store and
+         * discard the store request so that the page can be reclaimed */
+        spin_lock(&cookie->stores_lock);
+        rcu_read_unlock();
+
+        if (radix_tree_tag_get(&cookie->stores, page->index,
+                               FSCACHE_COOKIE_STORING_TAG)) {
+                /* the page started to undergo storage whilst we were looking,
+                 * so now we can only wait or return */
+                spin_unlock(&cookie->stores_lock);
+                goto page_busy;
+        }
+
+        xpage = radix_tree_delete(&cookie->stores, page->index);
+        spin_unlock(&cookie->stores_lock);
+
+        if (xpage) {
+                fscache_stat(&fscache_n_store_vmscan_cancelled);
+                fscache_stat(&fscache_n_store_radix_deletes);
+                ASSERTCMP(xpage, ==, page);
+        } else {
+                fscache_stat(&fscache_n_store_vmscan_gone);
+        }
+
+        wake_up_bit(&cookie->flags, 0);
+        if (xpage)
+                page_cache_release(xpage);
+        __fscache_uncache_page(cookie, page);
+        return true;
+
+page_busy:
+        /* we might want to wait here, but that could deadlock the allocator as
+         * the slow-work threads writing to the cache may all end up sleeping
+         * on memory allocation */
+        fscache_stat(&fscache_n_store_vmscan_busy);
+        return false;
+}
+EXPORT_SYMBOL(__fscache_maybe_release_page);
+
+/*
  * note that a page has finished being written to the cache
  */
 static void fscache_end_page_write(struct fscache_object *object,
@@ -57,6 +126,8 @@ static void fscache_end_page_write(struct fscache_object *object,
                 /* delete the page from the tree if it is now no longer
                  * pending */
                 spin_lock(&cookie->stores_lock);
+                radix_tree_tag_clear(&cookie->stores, page->index,
+                                     FSCACHE_COOKIE_STORING_TAG);
                 if (!radix_tree_tag_get(&cookie->stores, page->index,
                                         FSCACHE_COOKIE_PENDING_TAG)) {
                         fscache_stat(&fscache_n_store_radix_deletes);
@@ -640,8 +711,12 @@ static void fscache_write_op(struct fscache_operation *_op)
                 goto superseded;
         }
 
-        radix_tree_tag_clear(&cookie->stores, page->index,
-                             FSCACHE_COOKIE_PENDING_TAG);
+        if (page) {
+                radix_tree_tag_set(&cookie->stores, page->index,
+                                   FSCACHE_COOKIE_STORING_TAG);
+                radix_tree_tag_clear(&cookie->stores, page->index,
+                                     FSCACHE_COOKIE_PENDING_TAG);
+        }
 
         spin_unlock(&cookie->stores_lock);
         spin_unlock(&object->lock);
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 045ba396dbf2..cda69994e06d 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -63,6 +63,11 @@ atomic_t fscache_n_store_pages;
 atomic_t fscache_n_store_radix_deletes;
 atomic_t fscache_n_store_pages_over_limit;
 
+atomic_t fscache_n_store_vmscan_not_storing;
+atomic_t fscache_n_store_vmscan_gone;
+atomic_t fscache_n_store_vmscan_busy;
+atomic_t fscache_n_store_vmscan_cancelled;
+
 atomic_t fscache_n_marks;
 atomic_t fscache_n_uncaches;
 
@@ -211,6 +216,12 @@ static int fscache_stats_show(struct seq_file *m, void *v)
                    atomic_read(&fscache_n_store_radix_deletes),
                    atomic_read(&fscache_n_store_pages_over_limit));
 
+        seq_printf(m, "VmScan : nos=%u gon=%u bsy=%u can=%u\n",
+                   atomic_read(&fscache_n_store_vmscan_not_storing),
+                   atomic_read(&fscache_n_store_vmscan_gone),
+                   atomic_read(&fscache_n_store_vmscan_busy),
+                   atomic_read(&fscache_n_store_vmscan_cancelled));
+
         seq_printf(m, "Ops    : pend=%u run=%u enq=%u can=%u rej=%u\n",
                    atomic_read(&fscache_n_op_pend),
                    atomic_read(&fscache_n_op_run),
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index 70fad69eb959..fa588006588d 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -359,17 +359,13 @@ int nfs_fscache_release_page(struct page *page, gfp_t gfp)
 
         BUG_ON(!cookie);
 
-        if (fscache_check_page_write(cookie, page)) {
-                if (!(gfp & __GFP_WAIT))
-                        return 0;
-                fscache_wait_on_page_write(cookie, page);
-        }
-
         if (PageFsCache(page)) {
                 dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n",
                          cookie, page, nfsi);
 
-                fscache_uncache_page(cookie, page);
+                if (!fscache_maybe_release_page(cookie, page, gfp))
+                        return 0;
+
                 nfs_add_fscache_stats(page->mapping->host,
                                       NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
         }
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index f3aa4bdafef6..4750d5fb419f 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -317,6 +317,7 @@ struct fscache_cookie {
         void                            *netfs_data;    /* back pointer to netfs */
         struct radix_tree_root          stores;         /* pages to be stored on this cookie */
 #define FSCACHE_COOKIE_PENDING_TAG      0               /* pages tag: pending write to cache */
+#define FSCACHE_COOKIE_STORING_TAG      1               /* pages tag: writing to cache */
 
         unsigned long                   flags;
 #define FSCACHE_COOKIE_LOOKING_UP       0       /* T if non-index cookie being looked up still */
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 6d8ee466e0a0..595ce49288b7 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -202,6 +202,8 @@ extern int __fscache_write_page(struct fscache_cookie *, struct page *, gfp_t);
 extern void __fscache_uncache_page(struct fscache_cookie *, struct page *);
 extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *);
 extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *);
+extern bool __fscache_maybe_release_page(struct fscache_cookie *, struct page *,
+                                         gfp_t);
 
 /**
  * fscache_register_netfs - Register a filesystem as desiring caching services
@@ -615,4 +617,29 @@ void fscache_wait_on_page_write(struct fscache_cookie *cookie,
                 __fscache_wait_on_page_write(cookie, page);
 }
 
+/**
+ * fscache_maybe_release_page - Consider releasing a page, cancelling a store
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that is being cached.
+ * @gfp: The gfp flags passed to releasepage()
+ *
+ * Consider releasing a page for the vmscan algorithm, on behalf of the netfs's
+ * releasepage() call.  A storage request on the page may cancelled if it is
+ * not currently being processed.
+ *
+ * The function returns true if the page no longer has a storage request on it,
+ * and false if a storage request is left in place.  If true is returned, the
+ * page will have been passed to fscache_uncache_page().  If false is returned
+ * the page cannot be freed yet.
+ */
+static inline
+bool fscache_maybe_release_page(struct fscache_cookie *cookie,
+                                struct page *page,
+                                gfp_t gfp)
+{
+        if (fscache_cookie_valid(cookie) && PageFsCache(page))
+                return __fscache_maybe_release_page(cookie, page, gfp);
+        return false;
+}
+
 #endif /* _LINUX_FSCACHE_H */