Update from upstream with manual merge of Yasunori Goto's

changes to swiotlb.c made in commit 281dd25cdc0d6903929b79183816d151ea626341
since this file has been moved from arch/ia64/lib/swiotlb.c to
lib/swiotlb.c

Signed-off-by: Tony Luck <tony.luck@intel.com>

3 files changed, 95 insertions, 7 deletions

diff --git a/fs/proc/array.c b/fs/proc/array.c
index d88d518d30f6..d84eecacbeaf 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -74,6 +74,7 @@
 #include <linux/file.h>
 #include <linux/times.h>
 #include <linux/cpuset.h>
+#include <linux/rcupdate.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -180,12 +181,14 @@ static inline char * task_state(struct task_struct *p, char *buffer)
                 p->gid, p->egid, p->sgid, p->fsgid);
         read_unlock(&tasklist_lock);
         task_lock(p);
+        rcu_read_lock();
         if (p->files)
                 fdt = files_fdtable(p->files);
         buffer += sprintf(buffer,
                 "FDSize:\t%d\n"
                 "Groups:\t",
                 fdt ? fdt->max_fds : 0);
+        rcu_read_unlock();
 
         group_info = p->group_info;
         get_group_info(group_info);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 23db452ab428..a170450aadb1 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -103,7 +103,9 @@ enum pid_directory_inos {
         PROC_TGID_NUMA_MAPS,
         PROC_TGID_MOUNTS,
         PROC_TGID_WCHAN,
+#ifdef CONFIG_MMU
         PROC_TGID_SMAPS,
+#endif
 #ifdef CONFIG_SCHEDSTATS
         PROC_TGID_SCHEDSTAT,
 #endif
@@ -141,7 +143,9 @@ enum pid_directory_inos {
         PROC_TID_NUMA_MAPS,
         PROC_TID_MOUNTS,
         PROC_TID_WCHAN,
+#ifdef CONFIG_MMU
         PROC_TID_SMAPS,
+#endif
 #ifdef CONFIG_SCHEDSTATS
         PROC_TID_SCHEDSTAT,
 #endif
@@ -195,7 +199,9 @@ static struct pid_entry tgid_base_stuff[] = {
         E(PROC_TGID_ROOT,      "root",    S_IFLNK|S_IRWXUGO),
         E(PROC_TGID_EXE,       "exe",     S_IFLNK|S_IRWXUGO),
         E(PROC_TGID_MOUNTS,    "mounts",  S_IFREG|S_IRUGO),
+#ifdef CONFIG_MMU
         E(PROC_TGID_SMAPS,     "smaps",   S_IFREG|S_IRUGO),
+#endif
 #ifdef CONFIG_SECURITY
         E(PROC_TGID_ATTR,      "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
 #endif
@@ -235,7 +241,9 @@ static struct pid_entry tid_base_stuff[] = {
         E(PROC_TID_ROOT,       "root",    S_IFLNK|S_IRWXUGO),
         E(PROC_TID_EXE,        "exe",     S_IFLNK|S_IRWXUGO),
         E(PROC_TID_MOUNTS,     "mounts",  S_IFREG|S_IRUGO),
+#ifdef CONFIG_MMU
         E(PROC_TID_SMAPS,      "smaps",   S_IFREG|S_IRUGO),
+#endif
 #ifdef CONFIG_SECURITY
         E(PROC_TID_ATTR,       "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
 #endif
@@ -340,6 +348,54 @@ static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vf
         return result;
 }
 
+
+/* Same as proc_root_link, but this addionally tries to get fs from other
+ * threads in the group */
+static int proc_task_root_link(struct inode *inode, struct dentry **dentry,
+                                struct vfsmount **mnt)
+{
+        struct fs_struct *fs;
+        int result = -ENOENT;
+        struct task_struct *leader = proc_task(inode);
+
+        task_lock(leader);
+        fs = leader->fs;
+        if (fs) {
+                atomic_inc(&fs->count);
+                task_unlock(leader);
+        } else {
+                /* Try to get fs from other threads */
+                task_unlock(leader);
+                read_lock(&tasklist_lock);
+                if (pid_alive(leader)) {
+                        struct task_struct *task = leader;
+
+                        while ((task = next_thread(task)) != leader) {
+                                task_lock(task);
+                                fs = task->fs;
+                                if (fs) {
+                                        atomic_inc(&fs->count);
+                                        task_unlock(task);
+                                        break;
+                                }
+                                task_unlock(task);
+                        }
+                }
+                read_unlock(&tasklist_lock);
+        }
+
+        if (fs) {
+                read_lock(&fs->lock);
+                *mnt = mntget(fs->rootmnt);
+                *dentry = dget(fs->root);
+                read_unlock(&fs->lock);
+                result = 0;
+                put_fs_struct(fs);
+        }
+        return result;
+}
+
+
 #define MAY_PTRACE(task) \
         (task == current || \
         (task->parent == current && \
@@ -471,14 +527,14 @@ static int proc_oom_score(struct task_struct *task, char *buffer)
 
 /* permission checks */
 
-static int proc_check_root(struct inode *inode)
+/* If the process being read is separated by chroot from the reading process,
+ * don't let the reader access the threads.
+ */
+static int proc_check_chroot(struct dentry *root, struct vfsmount *vfsmnt)
 {
-        struct dentry *de, *base, *root;
-        struct vfsmount *our_vfsmnt, *vfsmnt, *mnt;
+        struct dentry *de, *base;
+        struct vfsmount *our_vfsmnt, *mnt;
         int res = 0;
-
-        if (proc_root_link(inode, &root, &vfsmnt)) /* Ewww... */
-                return -ENOENT;
         read_lock(&current->fs->lock);
         our_vfsmnt = mntget(current->fs->rootmnt);
         base = dget(current->fs->root);
@@ -511,6 +567,16 @@ out:
         goto exit;
 }
 
+static int proc_check_root(struct inode *inode)
+{
+        struct dentry *root;
+        struct vfsmount *vfsmnt;
+
+        if (proc_root_link(inode, &root, &vfsmnt)) /* Ewww... */
+                return -ENOENT;
+        return proc_check_chroot(root, vfsmnt);
+}
+
 static int proc_permission(struct inode *inode, int mask, struct nameidata *nd)
 {
         if (generic_permission(inode, mask, NULL) != 0)
@@ -518,6 +584,20 @@ static int proc_permission(struct inode *inode, int mask, struct nameidata *nd)
         return proc_check_root(inode);
 }
 
+static int proc_task_permission(struct inode *inode, int mask, struct nameidata *nd)
+{
+        struct dentry *root;
+        struct vfsmount *vfsmnt;
+
+        if (generic_permission(inode, mask, NULL) != 0)
+                return -EACCES;
+
+        if (proc_task_root_link(inode, &root, &vfsmnt))
+                return -ENOENT;
+
+        return proc_check_chroot(root, vfsmnt);
+}
+
 extern struct seq_operations proc_pid_maps_op;
 static int maps_open(struct inode *inode, struct file *file)
 {
@@ -558,6 +638,7 @@ static struct file_operations proc_numa_maps_operations = {
 };
 #endif
 
+#ifdef CONFIG_MMU
 extern struct seq_operations proc_pid_smaps_op;
 static int smaps_open(struct inode *inode, struct file *file)
 {
@@ -576,6 +657,7 @@ static struct file_operations proc_smaps_operations = {
         .llseek         = seq_lseek,
         .release        = seq_release,
 };
+#endif
 
 extern struct seq_operations mounts_op;
 static int mounts_open(struct inode *inode, struct file *file)
@@ -1419,7 +1501,7 @@ static struct inode_operations proc_fd_inode_operations = {
 
 static struct inode_operations proc_task_inode_operations = {
         .lookup         = proc_task_lookup,
-        .permission     = proc_permission,
+        .permission     = proc_task_permission,
 };
 
 #ifdef CONFIG_SECURITY
@@ -1609,10 +1691,12 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
                 case PROC_TGID_MOUNTS:
                         inode->i_fop = &proc_mounts_operations;
                         break;
+#ifdef CONFIG_MMU
                 case PROC_TID_SMAPS:
                 case PROC_TGID_SMAPS:
                         inode->i_fop = &proc_smaps_operations;
                         break;
+#endif
 #ifdef CONFIG_SECURITY
                 case PROC_TID_ATTR:
                         inode->i_nlink = 2;
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index f3bf016d5ee3..cff10ab1af63 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -91,6 +91,7 @@ static void *nommu_vma_list_start(struct seq_file *m, loff_t *_pos)
                         next = _rb;
                         break;
                 }
+                pos--;
         }
 
         return next;