fuse: auxiliary gfid mount support

* files can be accessed directly through their gfid and not just
  through their paths. For eg., if the gfid of a file is
  f3142503-c75e-45b1-b92a-463cf4c01f99, that file can be accessed
  using <gluster-mount>/.gfid/f3142503-c75e-45b1-b92a-463cf4c01f99

  .gfid is a virtual directory used to seperate out the namespace
  for accessing files through gfid. This way, we do not conflict with
  filenames which can be qualified as uuids.

* A new file/directory/symlink can be created with a pre-specified
  gfid. A setxattr done on parent directory with fuse_auxgfid_newfile_args_t
  initialized with appropriate fields as value to key "glusterfs.gfid.newfile"
  results in the entry <parent>/bname whose gfid is set to args.gfid. The
  contents of the structure should be in network byte order.

  struct auxfuse_symlink_in {
        char     linkpath[]; /* linkpath is a null terminated string */
  } __attribute__ ((__packed__));

  struct auxfuse_mknod_in {
        unsigned int   mode;
        unsigned int   rdev;
        unsigned int   umask;
  } __attribute__ ((__packed__));

  struct auxfuse_mkdir_in {
        unsigned int   mode;
        unsigned int   umask;
  } __attribute__ ((__packed__));

  typedef struct {
        unsigned int  uid;
        unsigned int  gid;
        char          gfid[UUID_CANONICAL_FORM_LEN + 1]; /* a null terminated gfid string
                                                      * in canonical form.
                                                      */
        unsigned int  st_mode;
        char          bname[];     /* bname is a null terminated string */

        union {
                struct auxfuse_mkdir_in   mkdir;
                struct auxfuse_mknod_in   mknod;
                struct auxfuse_symlink_in symlink;
        } __attribute__ ((__packed__)) args;
  } __attribute__ ((__packed__)) fuse_auxgfid_newfile_args_t;

  An initial consumer of this feature would be geo-replication to
  create files on slave mount with same gfids as that on master.
  It will also help gsyncd to access files directly through their
  gfids. gsyncd in its newer version will be consuming a changelog
  (of master) containing operations on gfids and sync corresponding
  files to slave.

* Also, bring in support to heal gfids with a specific value.
  fuse-bridge sends across a gfid during a lookup, which storage
  translators assign to an inode (file/directory etc) if there is
  no gfid associated it. This patch brings in support
  to specify that gfid value from an application, instead of relying
  on random gfid generated by fuse-bridge.

  gfids can be healed through setxattr interface. setxattr should be
  done on parent directory. The key used is "glusterfs.gfid.heal"
  and the value should be the following structure whose contents
  should be in network byte order.

  typedef struct {
        char      gfid[UUID_CANONICAL_FORM_LEN + 1]; /* a null terminated gfid
                                                      * string in canonical form
                                                      */
        char      bname[]; /* a null terminated basename */
  } __attribute__((__packed__)) fuse_auxgfid_heal_args_t;

  This feature can be used for upgrading older geo-rep setups where gfids
  of files are different on master and slave to newer setups where they
  should be same. One can delete gfids on slave using setxattr -x and
  .glusterfs and issue stat on all the files with gfids from master.

Thanks to "Amar Tumballi" <amarts@redhat.com> and "Csaba Henk"
<csaba@redhat.com> for their inputs.

Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
Change-Id: Ie8ddc0fb3732732315c7ec49eab850c16d905e4e
BUG: 952029
Reviewed-on: http://review.gluster.com/#/c/4702
Reviewed-by: Amar Tumballi <amarts@redhat.com>
Tested-by: Amar Tumballi <amarts@redhat.com>
Reviewed-on: http://review.gluster.org/4702
Reviewed-by: Xavier Hernandez <xhernandez@datalab.es>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>

3 files changed, 18 insertions, 12 deletions

diff --git a/libglusterfs/src/glusterfs.h b/libglusterfs/src/glusterfs.h
index 8643d7565a6..6c09e89b2eb 100644
--- a/libglusterfs/src/glusterfs.h
+++ b/libglusterfs/src/glusterfs.h
@@ -102,6 +102,7 @@
 #define UUID_CANONICAL_FORM_LEN 36
 
 #define GLUSTERFS_INTERNAL_FOP_KEY  "glusterfs-internal-fop"
+#define GLUSTERFS_CREATE_MODE_KEY "glusterfs-create-mode"
 
 #define ZR_FILE_CONTENT_STR     "glusterfs.file."
 #define ZR_FILE_CONTENT_STRLEN 15
@@ -320,6 +321,7 @@ struct _cmd_args {
         int              mac_compat;
 	int		 fopen_keep_cache;
 	int		 gid_timeout;
+        int              aux_gfid_mount;
 	struct list_head xlator_options;  /* list of xlator_option_t */
 
 	/* fuse options */
@@ -348,6 +350,7 @@ struct _cmd_args {
         int             brick_port;
         char           *brick_name;
         int             brick_port2;
+
 };
 typedef struct _cmd_args cmd_args_t;
 
diff --git a/libglusterfs/src/inode.c b/libglusterfs/src/inode.c
index 6f1c8ec3f25..add686fd208 100644
--- a/libglusterfs/src/inode.c
+++ b/libglusterfs/src/inode.c
@@ -310,7 +310,7 @@ __inode_destroy (inode_t *inode)
                 goto noctx;
         }
 
-        for (index = 0; index < inode->table->xl->graph->xl_count; index++) {
+        for (index = 0; index < inode->table->ctxcount; index++) {
                 if (inode->_ctx[index].xl_key) {
                         xl = (xlator_t *)(long)inode->_ctx[index].xl_key;
                         old_THIS = THIS;
@@ -528,10 +528,9 @@ __inode_create (inode_table_t *table)
         INIT_LIST_HEAD (&newi->hash);
         INIT_LIST_HEAD (&newi->dentry_list);
 
-        newi->_ctx = GF_CALLOC (1, (sizeof (struct _inode_ctx) *
-                                    table->xl->graph->xl_count),
+        newi->_ctx = GF_CALLOC (1,
+                                (sizeof (struct _inode_ctx) * table->ctxcount),
                                 gf_common_mt_inode_ctx);
-
         if (newi->_ctx == NULL) {
                 LOCK_DESTROY (&newi->lock);
                 mem_put (newi);
@@ -1316,6 +1315,7 @@ inode_table_new (size_t lru_limit, xlator_t *xl)
                 return NULL;
 
         new->xl = xl;
+        new->ctxcount = xl->graph->xl_count + 1;
 
         new->lru_limit = lru_limit;
 
@@ -1466,7 +1466,7 @@ __inode_ctx_set2 (inode_t *inode, xlator_t *xlator, uint64_t *value1_p,
         if (!inode || !xlator)
                 return -1;
 
-        for (index = 0; index < xlator->graph->xl_count; index++) {
+        for (index = 0; index < inode->table->ctxcount; index++) {
                 if (!inode->_ctx[index].xl_key) {
                         if (set_idx == -1)
                                 set_idx = index;
@@ -1523,12 +1523,12 @@ __inode_ctx_get2 (inode_t *inode, xlator_t *xlator, uint64_t *value1,
         if (!inode || !xlator)
                 return -1;
 
-        for (index = 0; index < xlator->graph->xl_count; index++) {
+        for (index = 0; index < inode->table->ctxcount; index++) {
                 if (inode->_ctx[index].xl_key == xlator)
                         break;
         }
 
-        if (index == xlator->graph->xl_count) {
+        if (index == inode->table->ctxcount) {
                 ret = -1;
                 goto out;
         }
@@ -1575,12 +1575,13 @@ inode_ctx_del2 (inode_t *inode, xlator_t *xlator, uint64_t *value1,
 
         LOCK (&inode->lock);
         {
-                for (index = 0; index < xlator->graph->xl_count; index++) {
+                for (index = 0; index < inode->table->ctxcount;
+                     index++) {
                         if (inode->_ctx[index].xl_key == xlator)
                                 break;
                 }
 
-                if (index == xlator->graph->xl_count) {
+                if (index == inode->table->ctxcount) {
                         ret = -1;
                         goto unlock;
                 }
@@ -1628,14 +1629,15 @@ inode_dump (inode_t *inode, char *prefix)
                 gf_proc_dump_write("ref", "%u", inode->ref);
                 gf_proc_dump_write("ia_type", "%d", inode->ia_type);
                 if (inode->_ctx) {
-                        inode_ctx = GF_CALLOC (inode->table->xl->graph->xl_count,
+                        inode_ctx = GF_CALLOC (inode->table->ctxcount,
                                                sizeof (*inode_ctx),
                                                gf_common_mt_inode_ctx);
                         if (inode_ctx == NULL) {
                                 goto unlock;
                         }
 
-                        for (i = 0; i < inode->table->xl->graph->xl_count; i++) {
+                        for (i = 0; i < inode->table->ctxcount;
+                             i++) {
                                 inode_ctx[i] = inode->_ctx[i];
                         }
                 }
@@ -1652,7 +1654,7 @@ unlock:
         UNLOCK(&inode->lock);
 
         if (inode_ctx && (dump_options.xl_options.dump_inodectx == _gf_true)) {
-                for (i = 0; i < inode->table->xl->graph->xl_count; i++) {
+                for (i = 0; i < inode->table->ctxcount; i++) {
                         if (inode_ctx[i].xl_key) {
                                 xl = (xlator_t *)(long)inode_ctx[i].xl_key;
                                 if (xl->dumpops && xl->dumpops->inodectx)
diff --git a/libglusterfs/src/inode.h b/libglusterfs/src/inode.h
index 199ce44849a..cf766a31bc6 100644
--- a/libglusterfs/src/inode.h
+++ b/libglusterfs/src/inode.h
@@ -56,6 +56,7 @@ struct _inode_table {
         struct mem_pool   *inode_pool;  /* memory pool for inodes */
         struct mem_pool   *dentry_pool; /* memory pool for dentrys */
         struct mem_pool   *fd_mem_pool; /* memory pool for fd_t */
+        int                ctxcount;    /* number of slots in inode->ctx */
 };