ceph: ioctls

A few Ceph ioctls for getting and setting file layout (striping)
parameters, and learning the identity and network address of the OSD a
given region of a file is stored on.

Signed-off-by: Sage Weil <sage@newdream.net>

diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 9473749..91cfdd7 100644 (file)
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -182,6 +182,7 @@ Code        Seq#    Include File            Comments
                                        <http://www.proximity.com.au/~brian/winradio/>
 0x90   00      drivers/cdrom/sbpcd.h
 0x93   60-7F   linux/auto_fs.h
+0x97    00-7F   fs/ceph/ioctl.h         Ceph file system
 0x99   00-0F                           537-Addinboard driver
                                        <mailto:buk@buks.ipn.de>
 0xA0   all     linux/sdp/sdp.h         Industrial Device Project

diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
new file mode 100644 (file)
index 0000000..e4f99ef
--- /dev/null
+++ b/fs/ceph/ioctl.c
@@ -0,0 +1,157 @@
+#include <linux/in.h>
+
+#include "ioctl.h"
+#include "super.h"
+#include "ceph_debug.h"
+
+
+/*
+ * ioctls
+ */
+
+/*
+ * get and set the file layout
+ */
+static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
+{
+       struct ceph_inode_info *ci = ceph_inode(file->f_dentry->d_inode);
+       struct ceph_ioctl_layout l;
+       int err;
+
+       err = ceph_do_getattr(file->f_dentry->d_inode, CEPH_STAT_CAP_LAYOUT);
+       if (!err) {
+               l.stripe_unit = ceph_file_layout_su(ci->i_layout);
+               l.stripe_count = ceph_file_layout_stripe_count(ci->i_layout);
+               l.object_size = ceph_file_layout_object_size(ci->i_layout);
+               l.data_pool = le32_to_cpu(ci->i_layout.fl_pg_pool);
+               if (copy_to_user(arg, &l, sizeof(l)))
+                       return -EFAULT;
+       }
+
+       return err;
+}
+
+static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
+{
+       struct inode *inode = file->f_dentry->d_inode;
+       struct inode *parent_inode = file->f_dentry->d_parent->d_inode;
+       struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+       struct ceph_mds_request *req;
+       struct ceph_ioctl_layout l;
+       int err, i;
+
+       /* copy and validate */
+       if (copy_from_user(&l, arg, sizeof(l)))
+               return -EFAULT;
+
+       if ((l.object_size & ~PAGE_MASK) ||
+           (l.stripe_unit & ~PAGE_MASK) ||
+           !l.stripe_unit ||
+           (l.object_size &&
+            (unsigned)l.object_size % (unsigned)l.stripe_unit))
+               return -EINVAL;
+
+       /* make sure it's a valid data pool */
+       if (l.data_pool > 0) {
+               mutex_lock(&mdsc->mutex);
+               err = -EINVAL;
+               for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
+                       if (mdsc->mdsmap->m_data_pg_pools[i] == l.data_pool) {
+                               err = 0;
+                               break;
+                       }
+               mutex_unlock(&mdsc->mutex);
+               if (err)
+                       return err;
+       }
+
+       req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETLAYOUT,
+                                      USE_AUTH_MDS);
+       if (IS_ERR(req))
+               return PTR_ERR(req);
+       req->r_inode = igrab(inode);
+       req->r_inode_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL;
+
+       req->r_args.setlayout.layout.fl_stripe_unit =
+               cpu_to_le32(l.stripe_unit);
+       req->r_args.setlayout.layout.fl_stripe_count =
+               cpu_to_le32(l.stripe_count);
+       req->r_args.setlayout.layout.fl_object_size =
+               cpu_to_le32(l.object_size);
+       req->r_args.setlayout.layout.fl_pg_pool = cpu_to_le32(l.data_pool);
+       req->r_args.setlayout.layout.fl_pg_preferred = cpu_to_le32((s32)-1);
+
+       err = ceph_mdsc_do_request(mdsc, parent_inode, req);
+       ceph_mdsc_put_request(req);
+       return err;
+}
+
+/*
+ * Return object name, size/offset information, and location (OSD
+ * number, network address) for a given file offset.
+ */
+static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
+{
+       struct ceph_ioctl_dataloc dl;
+       struct inode *inode = file->f_dentry->d_inode;
+       struct ceph_inode_info *ci = ceph_inode(inode);
+       struct ceph_osd_client *osdc = &ceph_client(inode->i_sb)->osdc;
+       u64 len = 1, olen;
+       u64 tmp;
+       struct ceph_object_layout ol;
+       union ceph_pg pgid;
+
+       /* copy and validate */
+       if (copy_from_user(&dl, arg, sizeof(dl)))
+               return -EFAULT;
+
+       down_read(&osdc->map_sem);
+       ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, &len,
+                                     &dl.object_no, &dl.object_offset, &olen);
+       dl.file_offset -= dl.object_offset;
+       dl.object_size = ceph_file_layout_object_size(ci->i_layout);
+       dl.block_size = ceph_file_layout_su(ci->i_layout);
+
+       /* block_offset = object_offset % block_size */
+       tmp = dl.object_offset;
+       dl.block_offset = do_div(tmp, dl.block_size);
+
+       snprintf(dl.object_name, sizeof(dl.object_name), "%llx.%08llx",
+                ceph_ino(inode), dl.object_no);
+       ceph_calc_object_layout(&ol, dl.object_name, &ci->i_layout,
+                               osdc->osdmap);
+
+       pgid.pg64 = le64_to_cpu(ol.ol_pgid);
+       dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid);
+       if (dl.osd >= 0) {
+               struct ceph_entity_addr *a =
+                       ceph_osd_addr(osdc->osdmap, dl.osd);
+               if (a)
+                       memcpy(&dl.osd_addr, &a->in_addr, sizeof(dl.osd_addr));
+       } else {
+               memset(&dl.osd_addr, 0, sizeof(dl.osd_addr));
+       }
+       up_read(&osdc->map_sem);
+
+       /* send result back to user */
+       if (copy_to_user(arg, &dl, sizeof(dl)))
+               return -EFAULT;
+
+       return 0;
+}
+
+long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+       dout("ioctl file %p cmd %u arg %lu\n", file, cmd, arg);
+       switch (cmd) {
+       case CEPH_IOC_GET_LAYOUT:
+               return ceph_ioctl_get_layout(file, (void __user *)arg);
+
+       case CEPH_IOC_SET_LAYOUT:
+               return ceph_ioctl_set_layout(file, (void __user *)arg);
+
+       case CEPH_IOC_GET_DATALOC:
+               return ceph_ioctl_get_dataloc(file, (void __user *)arg);
+       }
+       return -ENOTTY;
+}

diff --git a/fs/ceph/ioctl.h b/fs/ceph/ioctl.h
new file mode 100644 (file)
index 0000000..3c511da
--- /dev/null
+++ b/fs/ceph/ioctl.h
@@ -0,0 +1,39 @@
+#ifndef FS_CEPH_IOCTL_H
+#define FS_CEPH_IOCTL_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+#define CEPH_IOCTL_MAGIC 0x97
+
+/* just use u64 to align sanely on all archs */
+struct ceph_ioctl_layout {
+       __u64 stripe_unit, stripe_count, object_size;
+       __u64 data_pool;
+};
+
+#define CEPH_IOC_GET_LAYOUT _IOR(CEPH_IOCTL_MAGIC, 1,          \
+                                  struct ceph_ioctl_layout)
+#define CEPH_IOC_SET_LAYOUT _IOW(CEPH_IOCTL_MAGIC, 2,          \
+                                  struct ceph_ioctl_layout)
+
+/*
+ * Extract identity, address of the OSD and object storing a given
+ * file offset.
+ */
+struct ceph_ioctl_dataloc {
+       __u64 file_offset;           /* in+out: file offset */
+       __u64 object_offset;         /* out: offset in object */
+       __u64 object_no;             /* out: object # */
+       __u64 object_size;           /* out: object size */
+       char object_name[64];        /* out: object name */
+       __u64 block_offset;          /* out: offset in block */
+       __u64 block_size;            /* out: block length */
+       __s64 osd;                   /* out: osd # */
+       struct sockaddr_storage osd_addr; /* out: osd address */
+};
+
+#define CEPH_IOC_GET_DATALOC _IOWR(CEPH_IOCTL_MAGIC, 3,        \
+                                  struct ceph_ioctl_dataloc)
+
+#endif