xfs: add O_TMPFILE support
v2 cover xfs: add O_TMPFILE support
From: Zhi Yong Wu <[email protected]>
HI, folks
It's time to post the latest revision out, welcome to any constructive comment, thanks.
If anyone is interested in playing with it, you can get this patchset from my dev git on github:
git://github.com/wuzhy/kernel.git xfs_tmpfile
The patchset was tested against the code snippet from Andy Lutomirski and other test cases:
http://lwn.net/Articles/562296/
If you have any other better test cases, please let me know, thanks.
#include <stdio.h>
#include <err.h>
#include <fcntl.h>
#include <unistd.h>
#include <string.h>
#define __O_TMPFILE 020000000
#define O_DIRECTORY 0200000
#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
#define AT_EMPTY_PATH 0x1000
int main(int argc, char **argv)
{
char buf[128];
if (argc != 3)
errx(1, "Usage: flinktest PATH linkat|proc");
int fd = open(".", O_TMPFILE | O_RDWR, 0600);
if (fd == -1)
err(1, "O_TMPFILE");
else
printf("fd #: %d\n", fd);
write(fd, "test", 4);
if (!strcmp(argv[2], "linkat")) {
if (linkat(fd, "", AT_FDCWD, argv[1], AT_EMPTY_PATH) != 0)
err(1, "linkat");
} else if (!strcmp(argv[2], "proc")) {
sprintf(buf, "/proc/self/fd/%d", fd);
if (linkat(AT_FDCWD, buf, AT_FDCWD, argv[1], AT_SYMLINK_FOLLOW) != 0)
err(1, "linkat");
} else {
errx(1, "invalid mode");
} return 0;
}
Changelog from v1:
- Fixed one chunk of the comments from Christoph Hellwig and Jeff Liu.
v1:
- Addressed the comments from Dave Chinner and Christoph Hellwig.
Zhi Yong Wu (3):
xfs: factor prid related codes into xfs_get_initial_prid()
xfs: add O_TMPFILE support
xfs: allow linkat() on O_TMPFILE files
fs/xfs/xfs_inode.c | 123 ++++++++++++++++++++++++++++++++++++++++++++-- fs/xfs/xfs_inode.h | 12 +++++ fs/xfs/xfs_iops.c | 16 ++++++ fs/xfs/xfs_shared.h | 4 +- fs/xfs/xfs_symlink.c | 5 +-- fs/xfs/xfs_trans_resv.c | 55 +++++++++++++++++++-- fs/xfs/xfs_trans_resv.h | 3 + 7 files changed, 203 insertions(+), 15 deletions(-)
Signature · 6 lines
1.7.6.5 _______________________________________________ xfs mailing list [email protected] http://oss.sgi.com/mailman/listinfo/xfs
PATCH v2 1/3 xfs: factor prid related codes into xfs_get_initial_prid()
From: Zhi Yong Wu <[email protected]>
It will be reused by the O_TMPFILE creation function.
--- fs/xfs/xfs_inode.c | 6 +----- fs/xfs/xfs_inode.h | 10 ++++++++++ fs/xfs/xfs_symlink.c | 5 +---- 3 files changed, 12 insertions(+), 9 deletions(-)
fs/xfs/xfs_inode.c +1 -5
@@ -42,7 +42,6 @@#include "xfs_bmap_util.h" #include "xfs_error.h" #include "xfs_quota.h" -#include "xfs_dinode.h" #include "xfs_filestream.h" #include "xfs_cksum.h" #include "xfs_trace.h"
@@ -1169,10 +1168,7 @@ xfs_create(if (XFS_FORCED_SHUTDOWN (mp))return XFS_ERROR (EIO ); -if (dp->i_d.di_flags &XFS_DIFLAG_PROJINHERIT ) - prid =xfs_get_projid (dp); -else - prid =XFS_PROJID_DEFAULT ; + prid =xfs_get_initial_prid (dp);/* * Make sure that we have allocated dquot(s) on disk.
fs/xfs/xfs_inode.h +10 -0
@@ -20,6 +20,7 @@#include "xfs_inode_buf.h" #include "xfs_inode_fork.h" +#include "xfs_dinode.h" /* * Kernel only inode definitions
@@ -192,6 +193,15 @@ xfs_set_projid(struct xfs_inode *ip, ip->i_d.di_projid_lo = (__uint16_t) (projid &0xffff ); } +static inline prid_t +xfs_get_initial_prid (struct xfs_inode *dp) +{ +if (dp->i_d.di_flags &XFS_DIFLAG_PROJINHERIT ) +return xfs_get_projid (dp); + +return XFS_PROJID_DEFAULT ; +} +/* * In-core inode flags. */
fs/xfs/xfs_symlink.c +1 -4
@@ -208,10 +208,7 @@ xfs_symlink(return XFS_ERROR (ENAMETOOLONG ); udqp = gdqp =NULL ; -if (dp->i_d.di_flags &XFS_DIFLAG_PROJINHERIT ) - prid =xfs_get_projid (dp); -else - prid =XFS_PROJID_DEFAULT ; + prid =xfs_get_initial_prid (dp);/* * Make sure that we have allocated dquot(s) on disk.
Signature · 6 lines
1.7.6.5 _______________________________________________ xfs mailing list [email protected] http://oss.sgi.com/mailman/listinfo/xfs
PATCH v2 2/3 xfs: add O_TMPFILE support
In reply to Zhi Yong WuFrom: Zhi Yong Wu <[email protected]>
Add two functions xfs_create_tmpfile() and xfs_vn_tmpfile() to support O_TMPFILE file creation.
In contrast to xfs_create(), xfs_create_tmpfile() has a different log reservation to the regular file creation because there is no directory modification, and doesn't check if an entry can be added to the directory, but the reservation quotas is required appropriately, and finally its inode is added to the unlinked list.
xfs_vn_tmpfile() add one O_TMPFILE method to VFS interface and directly invoke xfs_create_tmpfile().
--- fs/xfs/xfs_inode.c | 107 +++++++++++++++++++++++++++++++++++++++++++++++ fs/xfs/xfs_inode.h | 2 + fs/xfs/xfs_iops.c | 16 +++++++ fs/xfs/xfs_shared.h | 4 +- fs/xfs/xfs_trans_resv.c | 36 +++++++++++++++- fs/xfs/xfs_trans_resv.h | 2 + 6 files changed, 164 insertions(+), 3 deletions(-)
fs/xfs/xfs_inode.c +107 -0
@@ -1333,6 +1333,113 @@ xfs_create( }int +xfs_create_tmpfile ( +struct xfs_inode *dp, +struct dentry *dentry, +umode_t mode) +{ +struct xfs_mount *mp = dp->i_mount; +struct xfs_inode *ip =NULL ; +struct xfs_trans *tp =NULL ; +int error; +uint cancel_flags =XFS_TRANS_RELEASE_LOG_RES ; +prid_t prid; +struct xfs_dquot *udqp =NULL ; +struct xfs_dquot *gdqp =NULL ; +struct xfs_dquot *pdqp =NULL ; +struct xfs_trans_res *tres; +uint resblks; + +if (XFS_FORCED_SHUTDOWN (mp)) +return XFS_ERROR (EIO ); + + prid =xfs_get_initial_prid (dp); + +/* +* Make sure that we have allocated dquot(s) on disk. +*/ + error =xfs_qm_vop_dqalloc (dp,xfs_kuid_to_uid (current_fsuid ()), +xfs_kgid_to_gid (current_fsgid ()), prid, +XFS_QMOPT_QUOTALL |XFS_QMOPT_INHERIT , + &udqp, &gdqp, &pdqp); +if (error) +return error; + + resblks =XFS_IALLOC_SPACE_RES (mp); + tp =xfs_trans_alloc (mp,XFS_TRANS_CREATE_TMPFILE ); + + tres = &M_RES (mp)->tr_create_tmpfile; + error =xfs_trans_reserve (tp, tres, resblks,0 ); +if (error ==ENOSPC ) { +/* No space at all so try a "no-allocation" reservation */ + resblks =0 ; + error =xfs_trans_reserve (tp, tres,0 ,0 ); + } +if (error) { + cancel_flags =0 ; + goto out_trans_cancel; + } + + error =xfs_trans_reserve_quota (tp, mp, udqp, gdqp, + pdqp, resblks,1 ,0 ); +if (error) + goto out_trans_cancel; + + error =xfs_dir_ialloc (&tp, dp, mode,1 ,0 , + prid, resblks >0 , &ip,NULL ); +if (error) { +if (error ==ENOSPC ) + goto out_trans_cancel; + goto out_trans_abort; + } + +if (mp->m_flags &XFS_MOUNT_WSYNC ) +xfs_trans_set_sync (tp); + +/* +* Attach the dquot(s) to the inodes and modify them incore. +* These ids of the inode couldn't have changed since the new +* inode has been locked ever since it was created. +*/ +xfs_qm_vop_create_dqattach (tp, ip, udqp, gdqp, pdqp); + + ip->i_d.di_nlink--; +d_tmpfile (dentry,VFS_I (ip)); + error =xfs_iunlink (tp, ip); +if (error) + goto out_trans_abort; + + error =xfs_trans_commit (tp,XFS_TRANS_RELEASE_LOG_RES ); +if (error) + goto out_release_inode; + +xfs_qm_dqrele (udqp); +xfs_qm_dqrele (gdqp); +xfs_qm_dqrele (pdqp); + +return 0 ; + + out_trans_abort: + cancel_flags |=XFS_TRANS_ABORT ; + out_trans_cancel: +xfs_trans_cancel (tp, cancel_flags); + out_release_inode: +/* +* Wait until after the current transaction is aborted to +* release the inode. This prevents recursive transactions +* and deadlocks from xfs_inactive. +*/ +if (ip) +IRELE (ip); + +xfs_qm_dqrele (udqp); +xfs_qm_dqrele (gdqp); +xfs_qm_dqrele (pdqp); + +return error; +} + +int xfs_link( xfs_inode_t *tdp, xfs_inode_t *sip,
fs/xfs/xfs_inode.h +2 -0
@@ -333,6 +333,8 @@ int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name, struct xfs_inode **ipp, struct xfs_name *ci_name);int xfs_create (struct xfs_inode *dp,struct xfs_name *name,umode_t mode,xfs_dev_t rdev,struct xfs_inode **ipp); +int xfs_create_tmpfile (struct xfs_inode *dp,struct dentry *dentry, +umode_t mode);int xfs_remove (struct xfs_inode *dp,struct xfs_name *name,struct xfs_inode *ip); int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip,
fs/xfs/xfs_iops.c +16 -0
@@ -39,6 +39,7 @@#include "xfs_da_btree.h" #include "xfs_dir2_priv.h" #include "xfs_dinode.h" +#include "xfs_trans_space.h" #include <linux/capability.h> #include <linux/xattr.h>
@@ -1050,6 +1051,19 @@ xfs_vn_fiemap(return 0 ; } +STATIC int +xfs_vn_tmpfile ( +struct inode *dir, +struct dentry *dentry, +umode_t mode) +{ +int error; + + error =xfs_create_tmpfile (XFS_I (dir), dentry, mode); + +return -error; +} +static const struct inode_operations xfs_inode_operations = { .get_acl = xfs_get_acl, .getattr = xfs_vn_getattr,
@@ -1086,6 +1100,7 @@ static const struct inode_operations xfs_dir_inode_operations = { .removexattr = generic_removexattr, .listxattr = xfs_vn_listxattr, .update_time = xfs_vn_update_time, + .tmpfile = xfs_vn_tmpfile, };static const struct inode_operations xfs_dir_ci_inode_operations = {
@@ -1112,6 +1127,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = { .removexattr = generic_removexattr, .listxattr = xfs_vn_listxattr, .update_time = xfs_vn_update_time, + .tmpfile = xfs_vn_tmpfile, };static const struct inode_operations xfs_symlink_inode_operations = {
fs/xfs/xfs_shared.h +3 -1
@@ -104,7 +104,8 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops;#define XFS_TRANS_SB_COUNT 41#define XFS_TRANS_CHECKPOINT 42#define XFS_TRANS_ICREATE 43 -#define XFS_TRANS_TYPE_MAX 43 +#define XFS_TRANS_CREATE_TMPFILE 44 +#define XFS_TRANS_TYPE_MAX 44/* new transaction types need to be reflected in xfs_logprint(8) */ #define XFS_TRANS_TYPES \
@@ -112,6 +113,7 @@ extern const struct xfs_buf_ops xfs_symlink_buf_ops; { XFS_TRANS_SETATTR_SIZE, "SETATTR_SIZE" }, \ { XFS_TRANS_INACTIVE, "INACTIVE" }, \ { XFS_TRANS_CREATE, "CREATE" }, \ + { XFS_TRANS_CREATE_TMPFILE, "CREATE_TMPFILE" }, \ { XFS_TRANS_CREATE_TRUNC, "CREATE_TRUNC" }, \ { XFS_TRANS_TRUNCATE_FILE, "TRUNCATE_FILE" }, \ { XFS_TRANS_REMOVE, "REMOVE" }, \
fs/xfs/xfs_trans_resv.c +34 -2
@@ -229,6 +229,18 @@ xfs_calc_link_reservation( }/* +* For adding an inode to unlinked list we can modify: +* the agi hash list: sector size +* the unlinked inode: inode size +*/ +STATIC uint +xfs_calc_iunlink_add_reservation (xfs_mount_t *mp) +{ +return xfs_calc_buf_res (1 , mp->m_sb.sb_sectsize) + +xfs_calc_inode_res (mp,1 ); +} + +/* * For removing a directory entry we can modify: * the parent directory inode: inode size * the removed inode: inode size
@@ -245,10 +257,11 @@ xfs_calc_remove_reservation( struct xfs_mount *mp) {return XFS_DQUOT_LOGRES (mp) + -MAX ((xfs_calc_inode_res (mp,2 ) + +xfs_calc_iunlink_add_reservation (mp) + +MAX ((xfs_calc_inode_res (mp,1 ) +xfs_calc_buf_res (XFS_DIROP_LOG_COUNT (mp),XFS_FSB_TO_B (mp,1 ))), - (xfs_calc_buf_res (5 , mp->m_sb.sb_sectsize) + + (xfs_calc_buf_res (4 , mp->m_sb.sb_sectsize) +xfs_calc_buf_res (XFS_ALLOCFREE_LOG_COUNT (mp,2 ),XFS_FSB_TO_B (mp,1 )))); }
@@ -343,6 +356,20 @@ xfs_calc_create_reservation( } +STATIC uint +xfs_calc_create_tmpfile_reservation ( +struct xfs_mount *mp) +{ +uint res =XFS_DQUOT_LOGRES (mp); + +if (xfs_sb_version_hascrc (&mp->m_sb)) + res +=xfs_calc_icreate_resv_alloc (mp); +else + res +=xfs_calc_create_resv_alloc (mp); + +return res +xfs_calc_iunlink_add_reservation (mp); +} +/* * Making a new directory is the same as creating a new file. */
@@ -729,6 +756,11 @@ xfs_trans_resv_calc( resp->tr_create.tr_logcount =XFS_CREATE_LOG_COUNT ; resp->tr_create.tr_logflags |=XFS_TRANS_PERM_LOG_RES ; + resp->tr_create_tmpfile.tr_logres = +xfs_calc_create_tmpfile_reservation (mp); + resp->tr_create_tmpfile.tr_logcount =XFS_CREATE_TMPFILE_LOG_COUNT ; + resp->tr_create_tmpfile.tr_logflags |=XFS_TRANS_PERM_LOG_RES ; + resp->tr_mkdir.tr_logres =xfs_calc_mkdir_reservation (mp); resp->tr_mkdir.tr_logcount =XFS_MKDIR_LOG_COUNT ; resp->tr_mkdir.tr_logflags |=XFS_TRANS_PERM_LOG_RES ;
fs/xfs/xfs_trans_resv.h +2 -0
@@ -38,6 +38,7 @@ struct xfs_trans_resv {struct xfs_trans_res tr_remove;/* unlink trans */ struct xfs_trans_res tr_symlink;/* symlink trans */ struct xfs_trans_res tr_create;/* create trans */ +struct xfs_trans_res tr_create_tmpfile;/* create O_TMPFILE trans */ struct xfs_trans_res tr_mkdir;/* mkdir trans */ struct xfs_trans_res tr_ifree;/* inode free trans */ struct xfs_trans_res tr_ichange;/* inode update trans */
@@ -100,6 +101,7 @@ struct xfs_trans_resv {#define XFS_ITRUNCATE_LOG_COUNT 2#define XFS_INACTIVE_LOG_COUNT 2#define XFS_CREATE_LOG_COUNT 2 +#define XFS_CREATE_TMPFILE_LOG_COUNT 2#define XFS_MKDIR_LOG_COUNT 3#define XFS_SYMLINK_LOG_COUNT 3#define XFS_REMOVE_LOG_COUNT 2
Signature · 6 lines
1.7.6.5 _______________________________________________ xfs mailing list [email protected] http://oss.sgi.com/mailman/listinfo/xfs
PATCH v2 3/3 xfs: allow linkat() on O_TMPFILE files
In reply to Zhi Yong WuFrom: Zhi Yong Wu <[email protected]>
The VFS allows an anonymous temporary file to be named at a later time via a linkat() syscall. The inodes for O_TMPFILE files are are marked with a special flag I_LINKABLE and have a zero link count.
To support this in XFS, xfs_link() detects if this flag I_LINKABLE is set and behaves appropriately when detected. So in this case, its transaciton reservation takes into account the additional overhead of removing the inode from the unlinked list. Then the inode is removed from the unlinked list and the directory entry is added. Finally its link count is bumped accordingly.
--- fs/xfs/xfs_inode.c | 10 +++++++++- fs/xfs/xfs_trans_resv.c | 19 +++++++++++++++++-- fs/xfs/xfs_trans_resv.h | 1 + 3 files changed, 27 insertions(+), 3 deletions(-)
fs/xfs/xfs_inode.c +9 -1
@@ -61,6 +61,8 @@ kmem_zone_t *xfs_inode_zone; STATIC int xfs_iflush_int(xfs_inode_t *, xfs_buf_t *); +STATIC int xfs_iunlink_remove(xfs_trans_t *, xfs_inode_t *); +/* * helper function to extract extent size hint from inode */
@@ -1118,7 +1120,7 @@ xfs_bumplink( {xfs_trans_ichgtime (tp, ip,XFS_ICHGTIME_CHG ); -ASSERT (ip->i_d.di_nlink >0 ); +ASSERT (ip->i_d.di_nlink >0 || (VFS_I (ip)->i_state &I_LINKABLE )); ip->i_d.di_nlink++;inc_nlink (VFS_I (ip)); if ((ip->i_d.di_version == 1) &&
@@ -1504,6 +1506,12 @@ xfs_link(xfs_bmap_init (&free_list, &first_block); +if (sip->i_d.di_nlink ==0 ) { + error =xfs_iunlink_remove (tp, sip); +if (error) + goto abort_return; + } + error =xfs_dir_createname (tp, tdp, target_name, sip->i_ino, &first_block, &free_list, resblks);if (error)
fs/xfs/xfs_trans_resv.c +17 -2
@@ -204,6 +204,20 @@ xfs_calc_rename_reservation( }/* +* For removing an inode from unlinked list at first, we can modify: +* the agi hash list and counters: sector size +* the on disk inode before ours in the agi hash list: inode cluster size +*/ +STATIC uint +xfs_calc_iunlink_remove_reservation ( +struct xfs_mount *mp) +{ +return xfs_calc_buf_res (1 , mp->m_sb.sb_sectsize) + +MAX ((__uint16_t )XFS_FSB_TO_B (mp,1 ), + (__uint16_t )XFS_INODE_CLUSTER_SIZE (mp)); +} + +/* * For creating a link to an inode: * the parent directory inode: inode size * the linked inode: inode size
@@ -220,6 +234,7 @@ xfs_calc_link_reservation( struct xfs_mount *mp) {return XFS_DQUOT_LOGRES (mp) + +xfs_calc_iunlink_remove_reservation (mp) + MAX((xfs_calc_inode_res(mp, 2) + xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1))),
@@ -410,9 +425,9 @@ xfs_calc_ifree_reservation( {return XFS_DQUOT_LOGRES (mp) +xfs_calc_inode_res (mp,1 ) + -xfs_calc_buf_res (2 , mp->m_sb.sb_sectsize) + +xfs_calc_buf_res (1 , mp->m_sb.sb_sectsize) +xfs_calc_buf_res (1 ,XFS_FSB_TO_B (mp,1 )) + -max_t (uint,XFS_FSB_TO_B (mp,1 ),XFS_INODE_CLUSTER_SIZE (mp)) + +xfs_calc_iunlink_remove_reservation (mp) +xfs_calc_buf_res (1 ,0 ) +xfs_calc_buf_res (2 +XFS_IALLOC_BLOCKS (mp) + mp->m_in_maxlevels, 0) +
fs/xfs/xfs_trans_resv.h +1 -0
@@ -106,6 +106,7 @@ struct xfs_trans_resv {#define XFS_SYMLINK_LOG_COUNT 3#define XFS_REMOVE_LOG_COUNT 2#define XFS_LINK_LOG_COUNT 2 +#define XFS_LINK_TMPFILE_LOG_COUNT 2#define XFS_RENAME_LOG_COUNT 2#define XFS_WRITE_LOG_COUNT 2#define XFS_ADDAFORK_LOG_COUNT 2
Signature · 6 lines
1.7.6.5 _______________________________________________ xfs mailing list [email protected] http://oss.sgi.com/mailman/listinfo/xfs