Merge commit 'v2.6.28-rc7' into tracing/core

11 files changed, 150 insertions, 51 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 6569fda5cfed..10179cfa1152 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -878,6 +878,7 @@ void invalidate_inode_buffers(struct inode *inode)
                 spin_unlock(&buffer_mapping->private_lock);
         }
 }
+EXPORT_SYMBOL(invalidate_inode_buffers);
 
 /*
  * Remove any clean buffers from the inode's buffer list.  This is called
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index b691b893a848..f0a81e631ae6 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1475,7 +1475,11 @@ static int cifs_write_end(struct file *file, struct address_space *mapping,
         cFYI(1, ("write_end for page %p from pos %lld with %d bytes",
                  page, pos, copied));
 
-        if (!PageUptodate(page) && copied == PAGE_CACHE_SIZE)
+        if (PageChecked(page)) {
+                if (copied == len)
+                        SetPageUptodate(page);
+                ClearPageChecked(page);
+        } else if (!PageUptodate(page) && copied == PAGE_CACHE_SIZE)
                 SetPageUptodate(page);
 
         if (!PageUptodate(page)) {
@@ -2062,39 +2066,70 @@ static int cifs_write_begin(struct file *file, struct address_space *mapping,
 {
         pgoff_t index = pos >> PAGE_CACHE_SHIFT;
         loff_t offset = pos & (PAGE_CACHE_SIZE - 1);
+        loff_t page_start = pos & PAGE_MASK;
+        loff_t i_size;
+        struct page *page;
+        int rc = 0;
 
         cFYI(1, ("write_begin from %lld len %d", (long long)pos, len));
 
-        *pagep = __grab_cache_page(mapping, index);
-        if (!*pagep)
-                return -ENOMEM;
-
-        if (PageUptodate(*pagep))
-                return 0;
+        page = __grab_cache_page(mapping, index);
+        if (!page) {
+                rc = -ENOMEM;
+                goto out;
+        }
 
-        /* If we are writing a full page it will be up to date,
-           no need to read from the server */
-        if (len == PAGE_CACHE_SIZE && flags & AOP_FLAG_UNINTERRUPTIBLE)
-                return 0;
+        if (PageUptodate(page))
+                goto out;
 
-        if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
-                int rc;
+        /*
+         * If we write a full page it will be up to date, no need to read from
+         * the server. If the write is short, we'll end up doing a sync write
+         * instead.
+         */
+        if (len == PAGE_CACHE_SIZE)
+                goto out;
 
-                /* might as well read a page, it is fast enough */
-                rc = cifs_readpage_worker(file, *pagep, &offset);
+        /*
+         * optimize away the read when we have an oplock, and we're not
+         * expecting to use any of the data we'd be reading in. That
+         * is, when the page lies beyond the EOF, or straddles the EOF
+         * and the write will cover all of the existing data.
+         */
+        if (CIFS_I(mapping->host)->clientCanCacheRead) {
+                i_size = i_size_read(mapping->host);
+                if (page_start >= i_size ||
+                    (offset == 0 && (pos + len) >= i_size)) {
+                        zero_user_segments(page, 0, offset,
+                                           offset + len,
+                                           PAGE_CACHE_SIZE);
+                        /*
+                         * PageChecked means that the parts of the page
+                         * to which we're not writing are considered up
+                         * to date. Once the data is copied to the
+                         * page, it can be set uptodate.
+                         */
+                        SetPageChecked(page);
+                        goto out;
+                }
+        }
 
-                /* we do not need to pass errors back
-                   e.g. if we do not have read access to the file
-                   because cifs_write_end will attempt synchronous writes
-                   -- shaggy */
+        if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
+                /*
+                 * might as well read a page, it is fast enough. If we get
+                 * an error, we don't need to return it. cifs_write_end will
+                 * do a sync write instead since PG_uptodate isn't set.
+                 */
+                cifs_readpage_worker(file, page, &page_start);
         } else {
                 /* we could try using another file handle if there is one -
                    but how would we lock it to prevent close of that handle
                    racing with this read? In any case
                    this will be written out by write_end so is fine */
         }
-
-        return 0;
+out:
+        *pagep = page;
+        return rc;
 }
 
 const struct address_space_operations cifs_addr_ops = {
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index aec5c13f6341..96355d505347 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -102,6 +102,8 @@
 
 #define EP_UNACTIVE_PTR ((void *) -1L)
 
+#define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry))
+
 struct epoll_filefd {
         struct file *file;
         int fd;
@@ -200,6 +202,9 @@ struct eventpoll {
          * holding ->lock.
          */
         struct epitem *ovflist;
+
+        /* The user that created the eventpoll descriptor */
+        struct user_struct *user;
 };
 
 /* Wait structure used by the poll hooks */
@@ -227,9 +232,17 @@ struct ep_pqueue {
 };
 
 /*
+ * Configuration options available inside /proc/sys/fs/epoll/
+ */
+/* Maximum number of epoll devices, per user */
+static int max_user_instances __read_mostly;
+/* Maximum number of epoll watched descriptors, per user */
+static int max_user_watches __read_mostly;
+
+/*
  * This mutex is used to serialize ep_free() and eventpoll_release_file().
  */
-static struct mutex epmutex;
+static DEFINE_MUTEX(epmutex);
 
 /* Safe wake up implementation */
 static struct poll_safewake psw;
@@ -240,6 +253,33 @@ static struct kmem_cache *epi_cache __read_mostly;
 /* Slab cache used to allocate "struct eppoll_entry" */
 static struct kmem_cache *pwq_cache __read_mostly;
 
+#ifdef CONFIG_SYSCTL
+
+#include <linux/sysctl.h>
+
+static int zero;
+
+ctl_table epoll_table[] = {
+        {
+                .procname       = "max_user_instances",
+                .data           = &max_user_instances,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec_minmax,
+                .extra1         = &zero,
+        },
+        {
+                .procname       = "max_user_watches",
+                .data           = &max_user_watches,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec_minmax,
+                .extra1         = &zero,
+        },
+        { .ctl_name = 0 }
+};
+#endif /* CONFIG_SYSCTL */
+
 
 /* Setup the structure that is used as key for the RB tree */
 static inline void ep_set_ffd(struct epoll_filefd *ffd,
@@ -402,6 +442,8 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi)
         /* At this point it is safe to free the eventpoll item */
         kmem_cache_free(epi_cache, epi);
 
+        atomic_dec(&ep->user->epoll_watches);
+
         DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_remove(%p, %p)\n",
                      current, ep, file));
 
@@ -449,6 +491,8 @@ static void ep_free(struct eventpoll *ep)
 
         mutex_unlock(&epmutex);
         mutex_destroy(&ep->mtx);
+        atomic_dec(&ep->user->epoll_devs);
+        free_uid(ep->user);
         kfree(ep);
 }
 
@@ -532,10 +576,19 @@ void eventpoll_release_file(struct file *file)
 
 static int ep_alloc(struct eventpoll **pep)
 {
-        struct eventpoll *ep = kzalloc(sizeof(*ep), GFP_KERNEL);
+        int error;
+        struct user_struct *user;
+        struct eventpoll *ep;
 
-        if (!ep)
-                return -ENOMEM;
+        user = get_current_user();
+        error = -EMFILE;
+        if (unlikely(atomic_read(&user->epoll_devs) >=
+                        max_user_instances))
+                goto free_uid;
+        error = -ENOMEM;
+        ep = kzalloc(sizeof(*ep), GFP_KERNEL);
+        if (unlikely(!ep))
+                goto free_uid;
 
         spin_lock_init(&ep->lock);
         mutex_init(&ep->mtx);
@@ -544,12 +597,17 @@ static int ep_alloc(struct eventpoll **pep)
         INIT_LIST_HEAD(&ep->rdllist);
         ep->rbr = RB_ROOT;
         ep->ovflist = EP_UNACTIVE_PTR;
+        ep->user = user;
 
         *pep = ep;
 
         DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_alloc() ep=%p\n",
                      current, ep));
         return 0;
+
+free_uid:
+        free_uid(user);
+        return error;
 }
 
 /*
@@ -703,9 +761,11 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
         struct epitem *epi;
         struct ep_pqueue epq;
 
-        error = -ENOMEM;
+        if (unlikely(atomic_read(&ep->user->epoll_watches) >=
+                     max_user_watches))
+                return -ENOSPC;
         if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
-                goto error_return;
+                return -ENOMEM;
 
         /* Item initialization follow here ... */
         INIT_LIST_HEAD(&epi->rdllink);
@@ -735,6 +795,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
          * install process. Namely an allocation for a wait queue failed due
          * high memory pressure.
          */
+        error = -ENOMEM;
         if (epi->nwait < 0)
                 goto error_unregister;
 
@@ -765,6 +826,8 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 
         spin_unlock_irqrestore(&ep->lock, flags);
 
+        atomic_inc(&ep->user->epoll_watches);
+
         /* We have to call this outside the lock */
         if (pwake)
                 ep_poll_safewake(&psw, &ep->poll_wait);
@@ -789,7 +852,7 @@ error_unregister:
         spin_unlock_irqrestore(&ep->lock, flags);
 
         kmem_cache_free(epi_cache, epi);
-error_return:
+
         return error;
 }
 
@@ -1078,6 +1141,7 @@ asmlinkage long sys_epoll_create1(int flags)
                               flags & O_CLOEXEC);
         if (fd < 0)
                 ep_free(ep);
+        atomic_inc(&ep->user->epoll_devs);
 
 error_return:
         DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
@@ -1299,7 +1363,12 @@ asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
 
 static int __init eventpoll_init(void)
 {
-        mutex_init(&epmutex);
+        struct sysinfo si;
+
+        si_meminfo(&si);
+        max_user_instances = 128;
+        max_user_watches = (((si.totalram - si.totalhigh) / 32) << PAGE_SHIFT) /
+                EP_ITEM_COST;
 
         /* Initialize the structure used to perform safe poll wait head wake ups */
         ep_poll_safewake_init(&psw);
diff --git a/fs/ntfs/debug.h b/fs/ntfs/debug.h
index 5e6724c1afd1..2142b1c68b61 100644
--- a/fs/ntfs/debug.h
+++ b/fs/ntfs/debug.h
@@ -30,7 +30,8 @@
 
 extern int debug_msgs;
 
-#if 0 /* Fool kernel-doc since it doesn't do macros yet */
+extern void __ntfs_debug(const char *file, int line, const char *function,
+        const char *format, ...) __attribute__ ((format (printf, 4, 5)));
 /**
  * ntfs_debug - write a debug level message to syslog
  * @f:          a printf format string containing the message
@@ -39,11 +40,6 @@ extern int debug_msgs;
  * ntfs_debug() writes a DEBUG level message to the syslog but only if the
  * driver was compiled with -DDEBUG. Otherwise, the call turns into a NOP.
  */
-static void ntfs_debug(const char *f, ...);
-#endif
-
-extern void __ntfs_debug (const char *file, int line, const char *function,
-        const char *format, ...) __attribute__ ((format (printf, 4, 5)));
 #define ntfs_debug(f, a...)                                             \
         __ntfs_debug(__FILE__, __LINE__, __func__, f, ##a)
 
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index 7e947c672469..3a178ec48d7c 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -112,7 +112,7 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
                 bh = bhs[i];
 
                 if (buffer_jbd(bh)) {
-                        mlog(ML_ERROR,
+                        mlog(ML_BH_IO,
                              "trying to sync read a jbd "
                              "managed bh (blocknr = %llu), skipping\n",
                              (unsigned long long)bh->b_blocknr);
@@ -147,15 +147,10 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
         for (i = nr; i > 0; i--) {
                 bh = bhs[i - 1];
 
-                if (buffer_jbd(bh)) {
-                        mlog(ML_ERROR,
-                             "the journal got the buffer while it was "
-                             "locked for io! (blocknr = %llu)\n",
-                             (unsigned long long)bh->b_blocknr);
-                        BUG();
-                }
+                /* No need to wait on the buffer if it's managed by JBD. */
+                if (!buffer_jbd(bh))
+                        wait_on_buffer(bh);
 
-                wait_on_buffer(bh);
                 if (!buffer_uptodate(bh)) {
                         /* Status won't be cleared from here on out,
                          * so we can safely record this and loop back
@@ -251,8 +246,6 @@ int ocfs2_read_blocks(struct inode *inode, u64 block, int nr,
                         ignore_cache = 1;
                 }
 
-                /* XXX: Can we ever get this and *not* have the cached
-                 * flag set? */
                 if (buffer_jbd(bh)) {
                         if (ignore_cache)
                                 mlog(ML_BH_IO, "trying to sync read a jbd "
diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c
index 533a789c3ef8..ba962d71b34d 100644
--- a/fs/ocfs2/dlm/dlmfs.c
+++ b/fs/ocfs2/dlm/dlmfs.c
@@ -608,8 +608,10 @@ static int __init init_dlmfs_fs(void)
                                 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
                                         SLAB_MEM_SPREAD),
                                 dlmfs_init_once);
-        if (!dlmfs_inode_cache)
+        if (!dlmfs_inode_cache) {
+                status = -ENOMEM;
                 goto bail;
+        }
         cleanup_inode = 1;
 
         user_dlm_worker = create_singlethread_workqueue("user_dlm");
diff --git a/fs/ocfs2/dlm/userdlm.h b/fs/ocfs2/dlm/userdlm.h
index 39ec27738499..0c3cc03c61fa 100644
--- a/fs/ocfs2/dlm/userdlm.h
+++ b/fs/ocfs2/dlm/userdlm.h
@@ -33,7 +33,7 @@
 #include <linux/workqueue.h>
 
 /* user_lock_res->l_flags flags. */
-#define USER_LOCK_ATTACHED      (0x00000001) /* have we initialized
+#define USER_LOCK_ATTACHED      (0x00000001) /* we have initialized
                                                * the lvb */
 #define USER_LOCK_BUSY          (0x00000002) /* we are currently in
                                                * dlm_lock */
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index ec684426034b..6e6cc0a2e5f7 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2841,9 +2841,8 @@ static void ocfs2_unlock_ast(void *opaque, int error)
 
         lockres_clear_flags(lockres, OCFS2_LOCK_BUSY);
         lockres->l_unlock_action = OCFS2_UNLOCK_INVALID;
-        spin_unlock_irqrestore(&lockres->l_lock, flags);
-
         wake_up(&lockres->l_event);
+        spin_unlock_irqrestore(&lockres->l_lock, flags);
 
         mlog_exit_void();
 }
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index fef7ece32376..3fed9e3d8992 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -85,7 +85,7 @@ enum ocfs2_unlock_action {
 };
 
 /* ocfs2_lock_res->l_flags flags. */
-#define OCFS2_LOCK_ATTACHED      (0x00000001) /* have we initialized
+#define OCFS2_LOCK_ATTACHED      (0x00000001) /* we have initialized
                                                * the lvb */
 #define OCFS2_LOCK_BUSY          (0x00000002) /* we are currently in
                                                * dlm_lock */
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index faec2d879357..9b76d41a8ac6 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -740,6 +740,9 @@ static int user_dlm_lock_status(union ocfs2_dlm_lksb *lksb)
 
 static void *user_dlm_lvb(union ocfs2_dlm_lksb *lksb)
 {
+        if (!lksb->lksb_fsdlm.sb_lvbptr)
+                lksb->lksb_fsdlm.sb_lvbptr = (char *)lksb +
+                                             sizeof(struct dlm_lksb);
         return (void *)(lksb->lksb_fsdlm.sb_lvbptr);
 }
 
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 6e74b117aaf0..30ebde490f7f 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -106,6 +106,7 @@ void udf_clear_inode(struct inode *inode)
                 udf_truncate_tail_extent(inode);
                 unlock_kernel();
                 write_inode_now(inode, 0);
+                invalidate_inode_buffers(inode);
         }
         iinfo = UDF_I(inode);
         kfree(iinfo->i_ext.i_data);