summaryrefslogtreecommitdiffstats
path: root/fs/gfs2/inode.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-07-24 16:07:52 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-07-24 16:07:52 -0700
commitb403f230448ed687edcc460cd46de652bc686b12 (patch)
tree991eb7b80b62be8f68e08d70e07a283194ee0e52 /fs/gfs2/inode.c
parent523d939ef98fd712632d93a5a2b588e477a7565e (diff)
parente1cb6be9e142e6cc6246f3ab2776b4d7a2b3d9f0 (diff)
downloadop-kernel-dev-b403f230448ed687edcc460cd46de652bc686b12.zip
op-kernel-dev-b403f230448ed687edcc460cd46de652bc686b12.tar.gz
Merge tag 'gfs2-4.7.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2
Pull gfs2 updates from Bob Peterson: "We've got ten patches this time, half of which are related to a plethora of nasty outcomes when inodes are transitioned from the unlinked state to the free state. Small file systems are particularly vulnerable to these problems, and it can manifest as mainly hangs, but also file system corruption. The patches have been tested for literally many weeks, with a very gruelling test, so I have a high level of confidence. - Andreas Gruenbacher wrote a series of five patches for various lockups during the transition of inodes from unlinked to free. The main patch is titled "Fix gfs2_lookup_by_inum lock inversion" and the other four are support and cleanup patches related to that. - Ben Marzinski contributed two patches with regard to a recreatable problem when gfs2 tries to write a page to a file that is being truncated, resulting in a BUG() in gfs2_remove_from_journal. Note that Ben had to export vfs function __block_write_full_page to get this to work properly. It's been posted a long time and he talked to various VFS people about it, and nobody seemed to mind. - I contributed 3 patches: o The first one fixes a memory corruptor: a race in which one process can overwrite the gl_object pointer set by another process, causing kernel panic and other symptoms. o The second patch fixes another race that resulted in a false-positive BUG_ON. This occurred when resource group reservations were freed by one process while another process was trying to grab a new reservation in the same resource group. o The third patch fixes a problem with doing journal replay when the journals are not all the same size" * tag 'gfs2-4.7.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2: GFS2: Fix gfs2_replay_incr_blk for multiple journal sizes GFS2: Check rs_free with rd_rsspin protection gfs2: writeout truncated pages fs: export __block_write_full_page gfs2: Lock holder cleanup gfs2: Large-filesystem fix for 32-bit systems gfs2: Get rid of gfs2_ilookup gfs2: Fix gfs2_lookup_by_inum lock inversion gfs2: Initialize iopen glock holder for new inodes GFS2: don't set rgrp gl_object until it's inserted into rgrp tree
Diffstat (limited to 'fs/gfs2/inode.c')
-rw-r--r--fs/gfs2/inode.c128
1 files changed, 85 insertions, 43 deletions
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 9bad79f..e0621ca 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -37,9 +37,35 @@
#include "super.h"
#include "glops.h"
-struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr)
+static int iget_test(struct inode *inode, void *opaque)
{
- return ilookup(sb, (unsigned long)no_addr);
+ u64 no_addr = *(u64 *)opaque;
+
+ return GFS2_I(inode)->i_no_addr == no_addr;
+}
+
+static int iget_set(struct inode *inode, void *opaque)
+{
+ u64 no_addr = *(u64 *)opaque;
+
+ GFS2_I(inode)->i_no_addr = no_addr;
+ inode->i_ino = no_addr;
+ return 0;
+}
+
+static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr)
+{
+ struct inode *inode;
+
+repeat:
+ inode = iget5_locked(sb, no_addr, iget_test, iget_set, &no_addr);
+ if (!inode)
+ return inode;
+ if (is_bad_inode(inode)) {
+ iput(inode);
+ goto repeat;
+ }
+ return inode;
}
/**
@@ -78,26 +104,37 @@ static void gfs2_set_iop(struct inode *inode)
/**
* gfs2_inode_lookup - Lookup an inode
* @sb: The super block
- * @no_addr: The inode number
* @type: The type of the inode
+ * @no_addr: The inode number
+ * @no_formal_ino: The inode generation number
+ * @blktype: Requested block type (GFS2_BLKST_DINODE or GFS2_BLKST_UNLINKED;
+ * GFS2_BLKST_FREE do indicate not to verify)
+ *
+ * If @type is DT_UNKNOWN, the inode type is fetched from disk.
+ *
+ * If @blktype is anything other than GFS2_BLKST_FREE (which is used as a
+ * placeholder because it doesn't otherwise make sense), the on-disk block type
+ * is verified to be @blktype.
*
* Returns: A VFS inode, or an error
*/
struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
- u64 no_addr, u64 no_formal_ino)
+ u64 no_addr, u64 no_formal_ino,
+ unsigned int blktype)
{
struct inode *inode;
struct gfs2_inode *ip;
struct gfs2_glock *io_gl = NULL;
+ struct gfs2_holder i_gh;
int error;
- inode = iget_locked(sb, (unsigned long)no_addr);
+ gfs2_holder_mark_uninitialized(&i_gh);
+ inode = gfs2_iget(sb, no_addr);
if (!inode)
return ERR_PTR(-ENOMEM);
ip = GFS2_I(inode);
- ip->i_no_addr = no_addr;
if (inode->i_state & I_NEW) {
struct gfs2_sbd *sdp = GFS2_SB(inode);
@@ -112,10 +149,29 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
if (unlikely(error))
goto fail_put;
+ if (type == DT_UNKNOWN || blktype != GFS2_BLKST_FREE) {
+ /*
+ * The GL_SKIP flag indicates to skip reading the inode
+ * block. We read the inode with gfs2_inode_refresh
+ * after possibly checking the block type.
+ */
+ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE,
+ GL_SKIP, &i_gh);
+ if (error)
+ goto fail_put;
+
+ if (blktype != GFS2_BLKST_FREE) {
+ error = gfs2_check_blk_type(sdp, no_addr,
+ blktype);
+ if (error)
+ goto fail_put;
+ }
+ }
+
set_bit(GIF_INVALID, &ip->i_flags);
error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
if (unlikely(error))
- goto fail_iopen;
+ goto fail_put;
ip->i_iopen_gh.gh_gl->gl_object = ip;
gfs2_glock_put(io_gl);
@@ -134,6 +190,8 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
unlock_new_inode(inode);
}
+ if (gfs2_holder_initialized(&i_gh))
+ gfs2_glock_dq_uninit(&i_gh);
return inode;
fail_refresh:
@@ -141,10 +199,11 @@ fail_refresh:
ip->i_iopen_gh.gh_gl->gl_object = NULL;
gfs2_glock_dq_wait(&ip->i_iopen_gh);
gfs2_holder_uninit(&ip->i_iopen_gh);
-fail_iopen:
+fail_put:
if (io_gl)
gfs2_glock_put(io_gl);
-fail_put:
+ if (gfs2_holder_initialized(&i_gh))
+ gfs2_glock_dq_uninit(&i_gh);
ip->i_gl->gl_object = NULL;
fail:
iget_failed(inode);
@@ -155,23 +214,12 @@ struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
u64 *no_formal_ino, unsigned int blktype)
{
struct super_block *sb = sdp->sd_vfs;
- struct gfs2_holder i_gh;
- struct inode *inode = NULL;
+ struct inode *inode;
int error;
- /* Must not read in block until block type is verified */
- error = gfs2_glock_nq_num(sdp, no_addr, &gfs2_inode_glops,
- LM_ST_EXCLUSIVE, GL_SKIP, &i_gh);
- if (error)
- return ERR_PTR(error);
-
- error = gfs2_check_blk_type(sdp, no_addr, blktype);
- if (error)
- goto fail;
-
- inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0);
+ inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0, blktype);
if (IS_ERR(inode))
- goto fail;
+ return inode;
/* Two extra checks for NFS only */
if (no_formal_ino) {
@@ -182,16 +230,12 @@ struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
error = -EIO;
if (GFS2_I(inode)->i_diskflags & GFS2_DIF_SYSTEM)
goto fail_iput;
-
- error = 0;
}
+ return inode;
-fail:
- gfs2_glock_dq_uninit(&i_gh);
- return error ? ERR_PTR(error) : inode;
fail_iput:
iput(inode);
- goto fail;
+ return ERR_PTR(error);
}
@@ -236,8 +280,8 @@ struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
struct gfs2_holder d_gh;
int error = 0;
struct inode *inode = NULL;
- int unlock = 0;
+ gfs2_holder_mark_uninitialized(&d_gh);
if (!name->len || name->len > GFS2_FNAMESIZE)
return ERR_PTR(-ENAMETOOLONG);
@@ -252,7 +296,6 @@ struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh);
if (error)
return ERR_PTR(error);
- unlock = 1;
}
if (!is_root) {
@@ -265,7 +308,7 @@ struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
if (IS_ERR(inode))
error = PTR_ERR(inode);
out:
- if (unlock)
+ if (gfs2_holder_initialized(&d_gh))
gfs2_glock_dq_uninit(&d_gh);
if (error == -ENOENT)
return NULL;
@@ -1309,7 +1352,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
struct gfs2_inode *ip = GFS2_I(d_inode(odentry));
struct gfs2_inode *nip = NULL;
struct gfs2_sbd *sdp = GFS2_SB(odir);
- struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, };
+ struct gfs2_holder ghs[5], r_gh;
struct gfs2_rgrpd *nrgd;
unsigned int num_gh;
int dir_rename = 0;
@@ -1317,6 +1360,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
unsigned int x;
int error;
+ gfs2_holder_mark_uninitialized(&r_gh);
if (d_really_is_positive(ndentry)) {
nip = GFS2_I(d_inode(ndentry));
if (ip == nip)
@@ -1506,7 +1550,7 @@ out_gunlock:
gfs2_holder_uninit(ghs + x);
}
out_gunlock_r:
- if (r_gh.gh_gl)
+ if (gfs2_holder_initialized(&r_gh))
gfs2_glock_dq_uninit(&r_gh);
out:
return error;
@@ -1532,13 +1576,14 @@ static int gfs2_exchange(struct inode *odir, struct dentry *odentry,
struct gfs2_inode *oip = GFS2_I(odentry->d_inode);
struct gfs2_inode *nip = GFS2_I(ndentry->d_inode);
struct gfs2_sbd *sdp = GFS2_SB(odir);
- struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, };
+ struct gfs2_holder ghs[5], r_gh;
unsigned int num_gh;
unsigned int x;
umode_t old_mode = oip->i_inode.i_mode;
umode_t new_mode = nip->i_inode.i_mode;
int error;
+ gfs2_holder_mark_uninitialized(&r_gh);
error = gfs2_rindex_update(sdp);
if (error)
return error;
@@ -1646,7 +1691,7 @@ out_gunlock:
gfs2_holder_uninit(ghs + x);
}
out_gunlock_r:
- if (r_gh.gh_gl)
+ if (gfs2_holder_initialized(&r_gh))
gfs2_glock_dq_uninit(&r_gh);
out:
return error;
@@ -1743,9 +1788,8 @@ int gfs2_permission(struct inode *inode, int mask)
struct gfs2_inode *ip;
struct gfs2_holder i_gh;
int error;
- int unlock = 0;
-
+ gfs2_holder_mark_uninitialized(&i_gh);
ip = GFS2_I(inode);
if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
if (mask & MAY_NOT_BLOCK)
@@ -1753,14 +1797,13 @@ int gfs2_permission(struct inode *inode, int mask)
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
if (error)
return error;
- unlock = 1;
}
if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode))
error = -EACCES;
else
error = generic_permission(inode, mask);
- if (unlock)
+ if (gfs2_holder_initialized(&i_gh))
gfs2_glock_dq_uninit(&i_gh);
return error;
@@ -1932,17 +1975,16 @@ static int gfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int error;
- int unlock = 0;
+ gfs2_holder_mark_uninitialized(&gh);
if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
if (error)
return error;
- unlock = 1;
}
generic_fillattr(inode, stat);
- if (unlock)
+ if (gfs2_holder_initialized(&gh))
gfs2_glock_dq_uninit(&gh);
return 0;
OpenPOWER on IntegriCloud