From 8f4e91dee2a245e4be6942f4a8d83a769e13a47d Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Tue, 6 Oct 2009 11:31:14 -0700 Subject: 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 --- fs/ceph/ioctl.c | 157 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 157 insertions(+) create mode 100644 fs/ceph/ioctl.c (limited to 'fs/ceph/ioctl.c') diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c new file mode 100644 index 000000000000..e4f99eff5d93 --- /dev/null +++ b/fs/ceph/ioctl.c @@ -0,0 +1,157 @@ +#include + +#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; +} -- cgit From 51042122d4f85e0f8ee577a4230f172fcc57c456 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Wed, 4 Nov 2009 11:39:12 -0800 Subject: ceph: fix endian conversions for ceph_pg The endian conversions don't quite work with the old union ceph_pg. Just make it a regular struct, and make each field __le. This is simpler and it has the added bonus of actually working. Signed-off-by: Sage Weil --- fs/ceph/ioctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/ceph/ioctl.c') diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index e4f99eff5d93..4c33e19fc241 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -99,7 +99,7 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg) u64 len = 1, olen; u64 tmp; struct ceph_object_layout ol; - union ceph_pg pgid; + struct ceph_pg pgid; /* copy and validate */ if (copy_from_user(&dl, arg, sizeof(dl))) @@ -121,7 +121,7 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg) ceph_calc_object_layout(&ol, dl.object_name, &ci->i_layout, osdc->osdmap); - pgid.pg64 = le64_to_cpu(ol.ol_pgid); + pgid = ol.ol_pgid; dl.osd = ceph_calc_pg_primary(osdc->osdmap, pgid); if (dl.osd >= 0) { struct ceph_entity_addr *a = -- cgit From 33d4909ccc094b8262667bccdd52e01458bee0df Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Wed, 2 Dec 2009 14:42:39 -0800 Subject: ceph: allow preferred osd to be get/set via layout ioctl There is certainly no reason not to report this. The only real downside to allowing the user to set it is that you don't get default values by zeroing the layout struct (the default is -1). Signed-off-by: Sage Weil --- fs/ceph/ioctl.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'fs/ceph/ioctl.c') diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index 4c33e19fc241..8a5bcae62846 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -24,6 +24,8 @@ static long ceph_ioctl_get_layout(struct file *file, void __user *arg) 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); + l.preferred_osd = + (s32)le32_to_cpu(ci->i_layout.fl_pg_preferred); if (copy_to_user(arg, &l, sizeof(l))) return -EFAULT; } @@ -79,7 +81,8 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg) 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); + req->r_args.setlayout.layout.fl_pg_preferred = + cpu_to_le32(l.preferred_osd); err = ceph_mdsc_do_request(mdsc, parent_inode, req); ceph_mdsc_put_request(req); -- cgit