Merge nfs containerization work from Trond's tree
The nfs containerization work is a prerequisite for Jeff Layton's reboot
recovery rework.
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 164c560..689d1b1 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -32,24 +32,8 @@
DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
};
-static int ext4_readdir(struct file *, void *, filldir_t);
static int ext4_dx_readdir(struct file *filp,
void *dirent, filldir_t filldir);
-static int ext4_release_dir(struct inode *inode,
- struct file *filp);
-
-const struct file_operations ext4_dir_operations = {
- .llseek = ext4_llseek,
- .read = generic_read_dir,
- .readdir = ext4_readdir, /* we take BKL. needed?*/
- .unlocked_ioctl = ext4_ioctl,
-#ifdef CONFIG_COMPAT
- .compat_ioctl = ext4_compat_ioctl,
-#endif
- .fsync = ext4_sync_file,
- .release = ext4_release_dir,
-};
-
static unsigned char get_dtype(struct super_block *sb, int filetype)
{
@@ -60,6 +44,26 @@
return (ext4_filetype_table[filetype]);
}
+/**
+ * Check if the given dir-inode refers to an htree-indexed directory
+ * (or a directory which chould potentially get coverted to use htree
+ * indexing).
+ *
+ * Return 1 if it is a dx dir, 0 if not
+ */
+static int is_dx_dir(struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+
+ if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
+ EXT4_FEATURE_COMPAT_DIR_INDEX) &&
+ ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
+ ((inode->i_size >> sb->s_blocksize_bits) == 1)))
+ return 1;
+
+ return 0;
+}
+
/*
* Return 0 if the directory entry is OK, and 1 if there is a problem
*
@@ -115,18 +119,13 @@
unsigned int offset;
int i, stored;
struct ext4_dir_entry_2 *de;
- struct super_block *sb;
int err;
struct inode *inode = filp->f_path.dentry->d_inode;
+ struct super_block *sb = inode->i_sb;
int ret = 0;
int dir_has_error = 0;
- sb = inode->i_sb;
-
- if (EXT4_HAS_COMPAT_FEATURE(inode->i_sb,
- EXT4_FEATURE_COMPAT_DIR_INDEX) &&
- ((ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) ||
- ((inode->i_size >> sb->s_blocksize_bits) == 1))) {
+ if (is_dx_dir(inode)) {
err = ext4_dx_readdir(filp, dirent, filldir);
if (err != ERR_BAD_DX_DIR) {
ret = err;
@@ -254,22 +253,134 @@
return ret;
}
+static inline int is_32bit_api(void)
+{
+#ifdef CONFIG_COMPAT
+ return is_compat_task();
+#else
+ return (BITS_PER_LONG == 32);
+#endif
+}
+
/*
* These functions convert from the major/minor hash to an f_pos
- * value.
+ * value for dx directories
*
- * Currently we only use major hash numer. This is unfortunate, but
- * on 32-bit machines, the same VFS interface is used for lseek and
- * llseek, so if we use the 64 bit offset, then the 32-bit versions of
- * lseek/telldir/seekdir will blow out spectacularly, and from within
- * the ext2 low-level routine, we don't know if we're being called by
- * a 64-bit version of the system call or the 32-bit version of the
- * system call. Worse yet, NFSv2 only allows for a 32-bit readdir
- * cookie. Sigh.
+ * Upper layer (for example NFS) should specify FMODE_32BITHASH or
+ * FMODE_64BITHASH explicitly. On the other hand, we allow ext4 to be mounted
+ * directly on both 32-bit and 64-bit nodes, under such case, neither
+ * FMODE_32BITHASH nor FMODE_64BITHASH is specified.
*/
-#define hash2pos(major, minor) (major >> 1)
-#define pos2maj_hash(pos) ((pos << 1) & 0xffffffff)
-#define pos2min_hash(pos) (0)
+static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return major >> 1;
+ else
+ return ((__u64)(major >> 1) << 32) | (__u64)minor;
+}
+
+static inline __u32 pos2maj_hash(struct file *filp, loff_t pos)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return (pos << 1) & 0xffffffff;
+ else
+ return ((pos >> 32) << 1) & 0xffffffff;
+}
+
+static inline __u32 pos2min_hash(struct file *filp, loff_t pos)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return 0;
+ else
+ return pos & 0xffffffff;
+}
+
+/*
+ * Return 32- or 64-bit end-of-file for dx directories
+ */
+static inline loff_t ext4_get_htree_eof(struct file *filp)
+{
+ if ((filp->f_mode & FMODE_32BITHASH) ||
+ (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
+ return EXT4_HTREE_EOF_32BIT;
+ else
+ return EXT4_HTREE_EOF_64BIT;
+}
+
+
+/*
+ * ext4_dir_llseek() based on generic_file_llseek() to handle both
+ * non-htree and htree directories, where the "offset" is in terms
+ * of the filename hash value instead of the byte offset.
+ *
+ * NOTE: offsets obtained *before* ext4_set_inode_flag(dir, EXT4_INODE_INDEX)
+ * will be invalid once the directory was converted into a dx directory
+ */
+loff_t ext4_dir_llseek(struct file *file, loff_t offset, int origin)
+{
+ struct inode *inode = file->f_mapping->host;
+ loff_t ret = -EINVAL;
+ int dx_dir = is_dx_dir(inode);
+
+ mutex_lock(&inode->i_mutex);
+
+ /* NOTE: relative offsets with dx directories might not work
+ * as expected, as it is difficult to figure out the
+ * correct offset between dx hashes */
+
+ switch (origin) {
+ case SEEK_END:
+ if (unlikely(offset > 0))
+ goto out_err; /* not supported for directories */
+
+ /* so only negative offsets are left, does that have a
+ * meaning for directories at all? */
+ if (dx_dir)
+ offset += ext4_get_htree_eof(file);
+ else
+ offset += inode->i_size;
+ break;
+ case SEEK_CUR:
+ /*
+ * Here we special-case the lseek(fd, 0, SEEK_CUR)
+ * position-querying operation. Avoid rewriting the "same"
+ * f_pos value back to the file because a concurrent read(),
+ * write() or lseek() might have altered it
+ */
+ if (offset == 0) {
+ offset = file->f_pos;
+ goto out_ok;
+ }
+
+ offset += file->f_pos;
+ break;
+ }
+
+ if (unlikely(offset < 0))
+ goto out_err;
+
+ if (!dx_dir) {
+ if (offset > inode->i_sb->s_maxbytes)
+ goto out_err;
+ } else if (offset > ext4_get_htree_eof(file))
+ goto out_err;
+
+ /* Special lock needed here? */
+ if (offset != file->f_pos) {
+ file->f_pos = offset;
+ file->f_version = 0;
+ }
+
+out_ok:
+ ret = offset;
+out_err:
+ mutex_unlock(&inode->i_mutex);
+
+ return ret;
+}
/*
* This structure holds the nodes of the red-black tree used to store
@@ -330,15 +441,16 @@
}
-static struct dir_private_info *ext4_htree_create_dir_info(loff_t pos)
+static struct dir_private_info *ext4_htree_create_dir_info(struct file *filp,
+ loff_t pos)
{
struct dir_private_info *p;
p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL);
if (!p)
return NULL;
- p->curr_hash = pos2maj_hash(pos);
- p->curr_minor_hash = pos2min_hash(pos);
+ p->curr_hash = pos2maj_hash(filp, pos);
+ p->curr_minor_hash = pos2min_hash(filp, pos);
return p;
}
@@ -429,7 +541,7 @@
"null fname?!?\n");
return 0;
}
- curr_pos = hash2pos(fname->hash, fname->minor_hash);
+ curr_pos = hash2pos(filp, fname->hash, fname->minor_hash);
while (fname) {
error = filldir(dirent, fname->name,
fname->name_len, curr_pos,
@@ -454,13 +566,13 @@
int ret;
if (!info) {
- info = ext4_htree_create_dir_info(filp->f_pos);
+ info = ext4_htree_create_dir_info(filp, filp->f_pos);
if (!info)
return -ENOMEM;
filp->private_data = info;
}
- if (filp->f_pos == EXT4_HTREE_EOF)
+ if (filp->f_pos == ext4_get_htree_eof(filp))
return 0; /* EOF */
/* Some one has messed with f_pos; reset the world */
@@ -468,8 +580,8 @@
free_rb_tree_fname(&info->root);
info->curr_node = NULL;
info->extra_fname = NULL;
- info->curr_hash = pos2maj_hash(filp->f_pos);
- info->curr_minor_hash = pos2min_hash(filp->f_pos);
+ info->curr_hash = pos2maj_hash(filp, filp->f_pos);
+ info->curr_minor_hash = pos2min_hash(filp, filp->f_pos);
}
/*
@@ -501,7 +613,7 @@
if (ret < 0)
return ret;
if (ret == 0) {
- filp->f_pos = EXT4_HTREE_EOF;
+ filp->f_pos = ext4_get_htree_eof(filp);
break;
}
info->curr_node = rb_first(&info->root);
@@ -521,7 +633,7 @@
info->curr_minor_hash = fname->minor_hash;
} else {
if (info->next_hash == ~0) {
- filp->f_pos = EXT4_HTREE_EOF;
+ filp->f_pos = ext4_get_htree_eof(filp);
break;
}
info->curr_hash = info->next_hash;
@@ -540,3 +652,15 @@
return 0;
}
+
+const struct file_operations ext4_dir_operations = {
+ .llseek = ext4_dir_llseek,
+ .read = generic_read_dir,
+ .readdir = ext4_readdir,
+ .unlocked_ioctl = ext4_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = ext4_compat_ioctl,
+#endif
+ .fsync = ext4_sync_file,
+ .release = ext4_release_dir,
+};
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 513004f..8b64a00 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1612,7 +1612,11 @@
u32 *seed;
};
-#define EXT4_HTREE_EOF 0x7fffffff
+
+/* 32 and 64 bit signed EOF for dx directories */
+#define EXT4_HTREE_EOF_32BIT ((1UL << (32 - 1)) - 1)
+#define EXT4_HTREE_EOF_64BIT ((1ULL << (64 - 1)) - 1)
+
/*
* Control parameters used by ext4_htree_next_block
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index ac8f168..fa8e491 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -200,8 +200,8 @@
return -1;
}
hash = hash & ~1;
- if (hash == (EXT4_HTREE_EOF << 1))
- hash = (EXT4_HTREE_EOF-1) << 1;
+ if (hash == (EXT4_HTREE_EOF_32BIT << 1))
+ hash = (EXT4_HTREE_EOF_32BIT - 1) << 1;
hinfo->hash = hash;
hinfo->minor_hash = minor_hash;
return 0;
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 2774e10..f49b9af 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -496,7 +496,7 @@
__typeof__(type) num = which_strtol(val, &endp, 0); \
if (endp == val || *endp || num < (min) || num > (max)) \
return -EINVAL; \
- *((int *) kp->arg) = num; \
+ *((type *) kp->arg) = num; \
return 0; \
}
diff --git a/fs/nfsd/current_stateid.h b/fs/nfsd/current_stateid.h
new file mode 100644
index 0000000..4123551
--- /dev/null
+++ b/fs/nfsd/current_stateid.h
@@ -0,0 +1,28 @@
+#ifndef _NFSD4_CURRENT_STATE_H
+#define _NFSD4_CURRENT_STATE_H
+
+#include "state.h"
+#include "xdr4.h"
+
+extern void clear_current_stateid(struct nfsd4_compound_state *cstate);
+/*
+ * functions to set current state id
+ */
+extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *);
+extern void nfsd4_set_openstateid(struct nfsd4_compound_state *, struct nfsd4_open *);
+extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *, struct nfsd4_lock *);
+extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *);
+
+/*
+ * functions to consume current state id
+ */
+extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *);
+extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *, struct nfsd4_delegreturn *);
+extern void nfsd4_get_freestateid(struct nfsd4_compound_state *, struct nfsd4_free_stateid *);
+extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *, struct nfsd4_setattr *);
+extern void nfsd4_get_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *);
+extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *, struct nfsd4_locku *);
+extern void nfsd4_get_readstateid(struct nfsd4_compound_state *, struct nfsd4_read *);
+extern void nfsd4_get_writestateid(struct nfsd4_compound_state *, struct nfsd4_write *);
+
+#endif /* _NFSD4_CURRENT_STATE_H */
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index cf8a6bd..8e9689a 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -87,7 +87,7 @@
struct svc_expkey key;
struct svc_expkey *ek = NULL;
- if (mlen < 1 || mesg[mlen-1] != '\n')
+ if (mesg[mlen - 1] != '\n')
return -EINVAL;
mesg[mlen-1] = 0;
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 0e262f3..cf6e419 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -986,7 +986,7 @@
err = setup_callback_client(clp, &conn, ses);
if (err) {
- warn_no_callback_path(clp, err);
+ nfsd4_mark_cb_down(clp, err);
return;
}
/* Yay, the callback channel's back! Restart any callbacks: */
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 896da74..2a90366 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -39,6 +39,7 @@
#include "cache.h"
#include "xdr4.h"
#include "vfs.h"
+#include "current_stateid.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
@@ -192,10 +193,13 @@
static __be32
do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
{
- struct svc_fh resfh;
+ struct svc_fh *resfh;
__be32 status;
- fh_init(&resfh, NFS4_FHSIZE);
+ resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
+ if (!resfh)
+ return nfserr_jukebox;
+ fh_init(resfh, NFS4_FHSIZE);
open->op_truncate = 0;
if (open->op_create) {
@@ -220,7 +224,7 @@
*/
status = do_nfsd_create(rqstp, current_fh, open->op_fname.data,
open->op_fname.len, &open->op_iattr,
- &resfh, open->op_createmode,
+ resfh, open->op_createmode,
(u32 *)open->op_verf.data,
&open->op_truncate, &open->op_created);
@@ -234,30 +238,29 @@
FATTR4_WORD1_TIME_MODIFY);
} else {
status = nfsd_lookup(rqstp, current_fh,
- open->op_fname.data, open->op_fname.len, &resfh);
+ open->op_fname.data, open->op_fname.len, resfh);
fh_unlock(current_fh);
if (status)
goto out;
- status = nfsd_check_obj_isreg(&resfh);
+ status = nfsd_check_obj_isreg(resfh);
}
if (status)
goto out;
if (is_create_with_attrs(open) && open->op_acl != NULL)
- do_set_nfs4_acl(rqstp, &resfh, open->op_acl, open->op_bmval);
-
- set_change_info(&open->op_cinfo, current_fh);
- fh_dup2(current_fh, &resfh);
+ do_set_nfs4_acl(rqstp, resfh, open->op_acl, open->op_bmval);
/* set reply cache */
fh_copy_shallow(&open->op_openowner->oo_owner.so_replay.rp_openfh,
- &resfh.fh_handle);
+ &resfh->fh_handle);
if (!open->op_created)
- status = do_open_permission(rqstp, current_fh, open,
+ status = do_open_permission(rqstp, resfh, open,
NFSD_MAY_NOP);
-
+ set_change_info(&open->op_cinfo, current_fh);
+ fh_dup2(current_fh, resfh);
out:
- fh_put(&resfh);
+ fh_put(resfh);
+ kfree(resfh);
return status;
}
@@ -310,9 +313,6 @@
if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
return nfserr_inval;
- /* We don't yet support WANT bits: */
- open->op_share_access &= NFS4_SHARE_ACCESS_MASK;
-
open->op_created = 0;
/*
* RFC5661 18.51.3
@@ -452,6 +452,10 @@
return nfserr_restorefh;
fh_dup2(&cstate->current_fh, &cstate->save_fh);
+ if (HAS_STATE_ID(cstate, SAVED_STATE_ID_FLAG)) {
+ memcpy(&cstate->current_stateid, &cstate->save_stateid, sizeof(stateid_t));
+ SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+ }
return nfs_ok;
}
@@ -463,6 +467,10 @@
return nfserr_nofilehandle;
fh_dup2(&cstate->save_fh, &cstate->current_fh);
+ if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG)) {
+ memcpy(&cstate->save_stateid, &cstate->current_stateid, sizeof(stateid_t));
+ SET_STATE_ID(cstate, SAVED_STATE_ID_FLAG);
+ }
return nfs_ok;
}
@@ -481,14 +489,20 @@
&access->ac_supported);
}
+static void gen_boot_verifier(nfs4_verifier *verifier)
+{
+ __be32 verf[2];
+
+ verf[0] = (__be32)nfssvc_boot.tv_sec;
+ verf[1] = (__be32)nfssvc_boot.tv_usec;
+ memcpy(verifier->data, verf, sizeof(verifier->data));
+}
+
static __be32
nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_commit *commit)
{
- u32 *p = (u32 *)commit->co_verf.data;
- *p++ = nfssvc_boot.tv_sec;
- *p++ = nfssvc_boot.tv_usec;
-
+ gen_boot_verifier(&commit->co_verf);
return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset,
commit->co_count);
}
@@ -865,7 +879,6 @@
{
stateid_t *stateid = &write->wr_stateid;
struct file *filp = NULL;
- u32 *p;
__be32 status = nfs_ok;
unsigned long cnt;
@@ -887,9 +900,7 @@
cnt = write->wr_buflen;
write->wr_how_written = write->wr_stable_how;
- p = (u32 *)write->wr_verifier.data;
- *p++ = nfssvc_boot.tv_sec;
- *p++ = nfssvc_boot.tv_usec;
+ gen_boot_verifier(&write->wr_verifier);
status = nfsd_write(rqstp, &cstate->current_fh, filp,
write->wr_offset, rqstp->rq_vec, write->wr_vlen,
@@ -1000,6 +1011,8 @@
typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *,
void *);
typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op);
+typedef void(*stateid_setter)(struct nfsd4_compound_state *, void *);
+typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *);
enum nfsd4_op_flags {
ALLOWED_WITHOUT_FH = 1 << 0, /* No current filehandle required */
@@ -1025,6 +1038,10 @@
* the v4.0 case).
*/
OP_CACHEME = 1 << 6,
+ /*
+ * These are ops which clear current state id.
+ */
+ OP_CLEAR_STATEID = 1 << 7,
};
struct nfsd4_operation {
@@ -1033,11 +1050,15 @@
char *op_name;
/* Try to get response size before operation */
nfsd4op_rsize op_rsize_bop;
+ stateid_setter op_get_currentstateid;
+ stateid_getter op_set_currentstateid;
};
static struct nfsd4_operation nfsd4_ops[];
+#ifdef NFSD_DEBUG
static const char *nfsd4_op_name(unsigned opnum);
+#endif
/*
* Enforce NFSv4.1 COMPOUND ordering rules:
@@ -1215,13 +1236,23 @@
if (op->status)
goto encode_op;
- if (opdesc->op_func)
+ if (opdesc->op_func) {
+ if (opdesc->op_get_currentstateid)
+ opdesc->op_get_currentstateid(cstate, &op->u);
op->status = opdesc->op_func(rqstp, cstate, &op->u);
- else
+ } else
BUG_ON(op->status == nfs_ok);
- if (!op->status && need_wrongsec_check(rqstp))
- op->status = check_nfsd_access(cstate->current_fh.fh_export, rqstp);
+ if (!op->status) {
+ if (opdesc->op_set_currentstateid)
+ opdesc->op_set_currentstateid(cstate, &op->u);
+
+ if (opdesc->op_flags & OP_CLEAR_STATEID)
+ clear_current_stateid(cstate);
+
+ if (need_wrongsec_check(rqstp))
+ op->status = check_nfsd_access(cstate->current_fh.fh_export, rqstp);
+ }
encode_op:
/* Only from SEQUENCE */
@@ -1413,6 +1444,8 @@
.op_flags = OP_MODIFIES_SOMETHING,
.op_name = "OP_CLOSE",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
+ .op_get_currentstateid = (stateid_getter)nfsd4_get_closestateid,
+ .op_set_currentstateid = (stateid_setter)nfsd4_set_closestateid,
},
[OP_COMMIT] = {
.op_func = (nfsd4op_func)nfsd4_commit,
@@ -1422,7 +1455,7 @@
},
[OP_CREATE] = {
.op_func = (nfsd4op_func)nfsd4_create,
- .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
+ .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME | OP_CLEAR_STATEID,
.op_name = "OP_CREATE",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_create_rsize,
},
@@ -1431,6 +1464,7 @@
.op_flags = OP_MODIFIES_SOMETHING,
.op_name = "OP_DELEGRETURN",
.op_rsize_bop = nfsd4_only_status_rsize,
+ .op_get_currentstateid = (stateid_getter)nfsd4_get_delegreturnstateid,
},
[OP_GETATTR] = {
.op_func = (nfsd4op_func)nfsd4_getattr,
@@ -1453,6 +1487,7 @@
.op_flags = OP_MODIFIES_SOMETHING,
.op_name = "OP_LOCK",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_lock_rsize,
+ .op_set_currentstateid = (stateid_setter)nfsd4_set_lockstateid,
},
[OP_LOCKT] = {
.op_func = (nfsd4op_func)nfsd4_lockt,
@@ -1463,15 +1498,16 @@
.op_flags = OP_MODIFIES_SOMETHING,
.op_name = "OP_LOCKU",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
+ .op_get_currentstateid = (stateid_getter)nfsd4_get_lockustateid,
},
[OP_LOOKUP] = {
.op_func = (nfsd4op_func)nfsd4_lookup,
- .op_flags = OP_HANDLES_WRONGSEC,
+ .op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID,
.op_name = "OP_LOOKUP",
},
[OP_LOOKUPP] = {
.op_func = (nfsd4op_func)nfsd4_lookupp,
- .op_flags = OP_HANDLES_WRONGSEC,
+ .op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID,
.op_name = "OP_LOOKUPP",
},
[OP_NVERIFY] = {
@@ -1483,6 +1519,7 @@
.op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING,
.op_name = "OP_OPEN",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_open_rsize,
+ .op_set_currentstateid = (stateid_setter)nfsd4_set_openstateid,
},
[OP_OPEN_CONFIRM] = {
.op_func = (nfsd4op_func)nfsd4_open_confirm,
@@ -1495,25 +1532,30 @@
.op_flags = OP_MODIFIES_SOMETHING,
.op_name = "OP_OPEN_DOWNGRADE",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
+ .op_get_currentstateid = (stateid_getter)nfsd4_get_opendowngradestateid,
+ .op_set_currentstateid = (stateid_setter)nfsd4_set_opendowngradestateid,
},
[OP_PUTFH] = {
.op_func = (nfsd4op_func)nfsd4_putfh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
- | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING,
+ | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
+ | OP_CLEAR_STATEID,
.op_name = "OP_PUTFH",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
},
[OP_PUTPUBFH] = {
.op_func = (nfsd4op_func)nfsd4_putrootfh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
- | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING,
+ | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
+ | OP_CLEAR_STATEID,
.op_name = "OP_PUTPUBFH",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
},
[OP_PUTROOTFH] = {
.op_func = (nfsd4op_func)nfsd4_putrootfh,
.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
- | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING,
+ | OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING
+ | OP_CLEAR_STATEID,
.op_name = "OP_PUTROOTFH",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
},
@@ -1522,6 +1564,7 @@
.op_flags = OP_MODIFIES_SOMETHING,
.op_name = "OP_READ",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize,
+ .op_get_currentstateid = (stateid_getter)nfsd4_get_readstateid,
},
[OP_READDIR] = {
.op_func = (nfsd4op_func)nfsd4_readdir,
@@ -1576,6 +1619,7 @@
.op_name = "OP_SETATTR",
.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
.op_rsize_bop = (nfsd4op_rsize)nfsd4_setattr_rsize,
+ .op_get_currentstateid = (stateid_getter)nfsd4_get_setattrstateid,
},
[OP_SETCLIENTID] = {
.op_func = (nfsd4op_func)nfsd4_setclientid,
@@ -1600,6 +1644,7 @@
.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
.op_name = "OP_WRITE",
.op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize,
+ .op_get_currentstateid = (stateid_getter)nfsd4_get_writestateid,
},
[OP_RELEASE_LOCKOWNER] = {
.op_func = (nfsd4op_func)nfsd4_release_lockowner,
@@ -1674,12 +1719,14 @@
},
};
+#ifdef NFSD_DEBUG
static const char *nfsd4_op_name(unsigned opnum)
{
if (opnum < ARRAY_SIZE(nfsd4_ops))
return nfsd4_ops[opnum].op_name;
return "unknown_operation";
}
+#endif
#define nfsd4_voidres nfsd4_voidargs
struct nfsd4_voidargs { int dummy; };
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c5cddd6..a0a2b53 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -58,11 +58,15 @@
static const stateid_t zero_stateid = {
/* all fields zero */
};
+static const stateid_t currentstateid = {
+ .si_generation = 1,
+};
static u64 current_sessionid = 1;
#define ZERO_STATEID(stateid) (!memcmp((stateid), &zero_stateid, sizeof(stateid_t)))
#define ONE_STATEID(stateid) (!memcmp((stateid), &one_stateid, sizeof(stateid_t)))
+#define CURRENT_STATEID(stateid) (!memcmp((stateid), ¤tstateid, sizeof(stateid_t)))
/* forward declarations */
static int check_for_locks(struct nfs4_file *filp, struct nfs4_lockowner *lowner);
@@ -91,6 +95,19 @@
mutex_lock(&client_mutex);
}
+static void free_session(struct kref *);
+
+/* Must be called under the client_lock */
+static void nfsd4_put_session_locked(struct nfsd4_session *ses)
+{
+ kref_put(&ses->se_ref, free_session);
+}
+
+static void nfsd4_get_session(struct nfsd4_session *ses)
+{
+ kref_get(&ses->se_ref);
+}
+
void
nfs4_unlock_state(void)
{
@@ -605,12 +622,20 @@
return sid->sequence % SESSION_HASH_SIZE;
}
+#ifdef NFSD_DEBUG
static inline void
dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid)
{
u32 *ptr = (u32 *)(&sessionid->data[0]);
dprintk("%s: %u:%u:%u:%u\n", fn, ptr[0], ptr[1], ptr[2], ptr[3]);
}
+#else
+static inline void
+dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid)
+{
+}
+#endif
+
static void
gen_sessionid(struct nfsd4_session *ses)
@@ -832,11 +857,12 @@
spin_unlock(&clp->cl_lock);
}
-void free_session(struct kref *kref)
+static void free_session(struct kref *kref)
{
struct nfsd4_session *ses;
int mem;
+ BUG_ON(!spin_is_locked(&client_lock));
ses = container_of(kref, struct nfsd4_session, se_ref);
nfsd4_del_conns(ses);
spin_lock(&nfsd_drc_lock);
@@ -847,6 +873,13 @@
kfree(ses);
}
+void nfsd4_put_session(struct nfsd4_session *ses)
+{
+ spin_lock(&client_lock);
+ nfsd4_put_session_locked(ses);
+ spin_unlock(&client_lock);
+}
+
static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp, struct nfsd4_create_session *cses)
{
struct nfsd4_session *new;
@@ -894,7 +927,9 @@
status = nfsd4_new_conn_from_crses(rqstp, new);
/* whoops: benny points out, status is ignored! (err, or bogus) */
if (status) {
+ spin_lock(&client_lock);
free_session(&new->se_ref);
+ spin_unlock(&client_lock);
return NULL;
}
if (cses->flags & SESSION4_BACK_CHAN) {
@@ -1006,12 +1041,13 @@
static inline void
free_client(struct nfs4_client *clp)
{
+ BUG_ON(!spin_is_locked(&client_lock));
while (!list_empty(&clp->cl_sessions)) {
struct nfsd4_session *ses;
ses = list_entry(clp->cl_sessions.next, struct nfsd4_session,
se_perclnt);
list_del(&ses->se_perclnt);
- nfsd4_put_session(ses);
+ nfsd4_put_session_locked(ses);
}
if (clp->cl_cred.cr_group_info)
put_group_info(clp->cl_cred.cr_group_info);
@@ -1138,12 +1174,12 @@
static void gen_confirm(struct nfs4_client *clp)
{
+ __be32 verf[2];
static u32 i;
- u32 *p;
- p = (u32 *)clp->cl_confirm.data;
- *p++ = get_seconds();
- *p++ = i++;
+ verf[0] = (__be32)get_seconds();
+ verf[1] = (__be32)i++;
+ memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data));
}
static struct nfs4_stid *find_stateid(struct nfs4_client *cl, stateid_t *t)
@@ -1180,7 +1216,9 @@
if (princ) {
clp->cl_principal = kstrdup(princ, GFP_KERNEL);
if (clp->cl_principal == NULL) {
+ spin_lock(&client_lock);
free_client(clp);
+ spin_unlock(&client_lock);
return NULL;
}
}
@@ -1347,6 +1385,7 @@
slot->sl_opcnt = resp->opcnt;
slot->sl_status = resp->cstate.status;
+ slot->sl_flags |= NFSD4_SLOT_INITIALIZED;
if (nfsd4_not_cached(resp)) {
slot->sl_datalen = 0;
return;
@@ -1374,15 +1413,12 @@
struct nfsd4_op *op;
struct nfsd4_slot *slot = resp->cstate.slot;
- dprintk("--> %s resp->opcnt %d cachethis %u \n", __func__,
- resp->opcnt, resp->cstate.slot->sl_cachethis);
-
/* Encode the replayed sequence operation */
op = &args->ops[resp->opcnt - 1];
nfsd4_encode_operation(resp, op);
/* Return nfserr_retry_uncached_rep in next operation. */
- if (args->opcnt > 1 && slot->sl_cachethis == 0) {
+ if (args->opcnt > 1 && !(slot->sl_flags & NFSD4_SLOT_CACHETHIS)) {
op = &args->ops[resp->opcnt++];
op->status = nfserr_retry_uncached_rep;
nfsd4_encode_operation(resp, op);
@@ -1575,16 +1611,11 @@
else
return nfserr_seq_misordered;
}
- /* Normal */
+ /* Note unsigned 32-bit arithmetic handles wraparound: */
if (likely(seqid == slot_seqid + 1))
return nfs_ok;
- /* Replay */
if (seqid == slot_seqid)
return nfserr_replay_cache;
- /* Wraparound */
- if (seqid == 1 && (slot_seqid + 1) == 0)
- return nfs_ok;
- /* Misordered replay or misordered new request */
return nfserr_seq_misordered;
}
@@ -1815,9 +1846,10 @@
nfsd4_probe_callback_sync(ses->se_client);
nfs4_unlock_state();
+ spin_lock(&client_lock);
nfsd4_del_conns(ses);
-
- nfsd4_put_session(ses);
+ nfsd4_put_session_locked(ses);
+ spin_unlock(&client_lock);
status = nfs_ok;
out:
dprintk("%s returns %d\n", __func__, ntohl(status));
@@ -1921,8 +1953,12 @@
* sr_highest_slotid and the sr_target_slot id to maxslots */
seq->maxslots = session->se_fchannel.maxreqs;
- status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_inuse);
+ status = check_slot_seqid(seq->seqid, slot->sl_seqid,
+ slot->sl_flags & NFSD4_SLOT_INUSE);
if (status == nfserr_replay_cache) {
+ status = nfserr_seq_misordered;
+ if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED))
+ goto out;
cstate->slot = slot;
cstate->session = session;
/* Return the cached reply status and set cstate->status
@@ -1938,9 +1974,12 @@
conn = NULL;
/* Success! bump slot seqid */
- slot->sl_inuse = true;
slot->sl_seqid = seq->seqid;
- slot->sl_cachethis = seq->cachethis;
+ slot->sl_flags |= NFSD4_SLOT_INUSE;
+ if (seq->cachethis)
+ slot->sl_flags |= NFSD4_SLOT_CACHETHIS;
+ else
+ slot->sl_flags &= ~NFSD4_SLOT_CACHETHIS;
cstate->slot = slot;
cstate->session = session;
@@ -2633,8 +2672,6 @@
static int share_access_to_flags(u32 share_access)
{
- share_access &= ~NFS4_SHARE_WANT_MASK;
-
return share_access == NFS4_SHARE_ACCESS_READ ? RD_STATE : WR_STATE;
}
@@ -2776,10 +2813,15 @@
static void
-nfs4_set_claim_prev(struct nfsd4_open *open)
+nfs4_set_claim_prev(struct nfsd4_open *open, bool has_session)
{
open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
- open->op_openowner->oo_owner.so_client->cl_firststate = 1;
+ /*
+ * On a 4.1+ client, we don't create a state record for a client
+ * until it performs RECLAIM_COMPLETE:
+ */
+ if (!has_session)
+ open->op_openowner->oo_owner.so_client->cl_firststate = 1;
}
/* Should we give out recallable state?: */
@@ -2855,6 +2897,27 @@
return 0;
}
+static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
+{
+ open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+ if (status == -EAGAIN)
+ open->op_why_no_deleg = WND4_CONTENTION;
+ else {
+ open->op_why_no_deleg = WND4_RESOURCE;
+ switch (open->op_deleg_want) {
+ case NFS4_SHARE_WANT_READ_DELEG:
+ case NFS4_SHARE_WANT_WRITE_DELEG:
+ case NFS4_SHARE_WANT_ANY_DELEG:
+ break;
+ case NFS4_SHARE_WANT_CANCEL:
+ open->op_why_no_deleg = WND4_CANCELLED;
+ break;
+ case NFS4_SHARE_WANT_NO_DELEG:
+ BUG(); /* not supposed to get here */
+ }
+ }
+}
+
/*
* Attempt to hand out a delegation.
*/
@@ -2864,7 +2927,7 @@
struct nfs4_delegation *dp;
struct nfs4_openowner *oo = container_of(stp->st_stateowner, struct nfs4_openowner, oo_owner);
int cb_up;
- int status, flag = 0;
+ int status = 0, flag = 0;
cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client);
flag = NFS4_OPEN_DELEGATE_NONE;
@@ -2905,11 +2968,16 @@
dprintk("NFSD: delegation stateid=" STATEID_FMT "\n",
STATEID_VAL(&dp->dl_stid.sc_stateid));
out:
- if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS
- && flag == NFS4_OPEN_DELEGATE_NONE
- && open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE)
- dprintk("NFSD: WARNING: refusing delegation reclaim\n");
open->op_delegate_type = flag;
+ if (flag == NFS4_OPEN_DELEGATE_NONE) {
+ if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS &&
+ open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE)
+ dprintk("NFSD: WARNING: refusing delegation reclaim\n");
+
+ /* 4.1 client asking for a delegation? */
+ if (open->op_deleg_want)
+ nfsd4_open_deleg_none_ext(open, status);
+ }
return;
out_free:
nfs4_put_delegation(dp);
@@ -2918,6 +2986,24 @@
goto out;
}
+static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open,
+ struct nfs4_delegation *dp)
+{
+ if (open->op_deleg_want == NFS4_SHARE_WANT_READ_DELEG &&
+ dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) {
+ open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+ open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE;
+ } else if (open->op_deleg_want == NFS4_SHARE_WANT_WRITE_DELEG &&
+ dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) {
+ open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+ open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE;
+ }
+ /* Otherwise the client must be confused wanting a delegation
+ * it already has, therefore we don't return
+ * NFS4_OPEN_DELEGATE_NONE_EXT and reason.
+ */
+}
+
/*
* called with nfs4_lock_state() held.
*/
@@ -2979,24 +3065,36 @@
update_stateid(&stp->st_stid.sc_stateid);
memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
- if (nfsd4_has_session(&resp->cstate))
+ if (nfsd4_has_session(&resp->cstate)) {
open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
+ if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
+ open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
+ open->op_why_no_deleg = WND4_NOT_WANTED;
+ goto nodeleg;
+ }
+ }
+
/*
* Attempt to hand out a delegation. No error return, because the
* OPEN succeeds even if we fail.
*/
nfs4_open_delegation(current_fh, open, stp);
-
+nodeleg:
status = nfs_ok;
dprintk("%s: stateid=" STATEID_FMT "\n", __func__,
STATEID_VAL(&stp->st_stid.sc_stateid));
out:
+ /* 4.1 client trying to upgrade/downgrade delegation? */
+ if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp &&
+ open->op_deleg_want)
+ nfsd4_deleg_xgrade_none_ext(open, dp);
+
if (fp)
put_nfs4_file(fp);
if (status == 0 && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
- nfs4_set_claim_prev(open);
+ nfs4_set_claim_prev(open, nfsd4_has_session(&resp->cstate));
/*
* To finish the open response, we just need to set the rflags.
*/
@@ -3400,7 +3498,14 @@
nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_test_stateid *test_stateid)
{
- /* real work is done during encoding */
+ struct nfsd4_test_stateid_id *stateid;
+ struct nfs4_client *cl = cstate->session->se_client;
+
+ nfs4_lock_state();
+ list_for_each_entry(stateid, &test_stateid->ts_stateid_list, ts_id_list)
+ stateid->ts_id_status = nfs4_validate_stateid(cl, &stateid->ts_id_stateid);
+ nfs4_unlock_state();
+
return nfs_ok;
}
@@ -3596,7 +3701,9 @@
cstate->current_fh.fh_dentry->d_name.name);
/* We don't yet support WANT bits: */
- od->od_share_access &= NFS4_SHARE_ACCESS_MASK;
+ if (od->od_deleg_want)
+ dprintk("NFSD: %s: od_deleg_want=0x%x ignored\n", __func__,
+ od->od_deleg_want);
nfs4_lock_state();
status = nfs4_preprocess_confirmed_seqid_op(cstate, od->od_seqid,
@@ -4353,7 +4460,9 @@
struct nfs4_client *clp;
clp = find_confirmed_client_by_str(name, strhashval);
- return clp ? 1 : 0;
+ if (!clp)
+ return 0;
+ return clp->cl_firststate;
}
/*
@@ -4613,21 +4722,26 @@
/* initialization to perform when the nfsd service is started: */
-static int
-__nfs4_state_start(void)
+int
+nfs4_state_start(void)
{
int ret;
+ nfsd4_load_reboot_recovery_data();
boot_time = get_seconds();
locks_start_grace(&nfsd4_manager);
printk(KERN_INFO "NFSD: starting %ld-second grace period\n",
nfsd4_grace);
ret = set_callback_cred();
- if (ret)
- return -ENOMEM;
+ if (ret) {
+ ret = -ENOMEM;
+ goto out_recovery;
+ }
laundry_wq = create_singlethread_workqueue("nfsd4");
- if (laundry_wq == NULL)
- return -ENOMEM;
+ if (laundry_wq == NULL) {
+ ret = -ENOMEM;
+ goto out_recovery;
+ }
ret = nfsd4_create_callback_queue();
if (ret)
goto out_free_laundry;
@@ -4636,16 +4750,12 @@
return 0;
out_free_laundry:
destroy_workqueue(laundry_wq);
+out_recovery:
+ nfs4_release_reclaim();
+ nfsd4_shutdown_recdir();
return ret;
}
-int
-nfs4_state_start(void)
-{
- nfsd4_load_reboot_recovery_data();
- return __nfs4_state_start();
-}
-
static void
__nfs4_state_shutdown(void)
{
@@ -4691,3 +4801,104 @@
nfs4_unlock_state();
nfsd4_destroy_callback_queue();
}
+
+static void
+get_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid)
+{
+ if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG) && CURRENT_STATEID(stateid))
+ memcpy(stateid, &cstate->current_stateid, sizeof(stateid_t));
+}
+
+static void
+put_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid)
+{
+ if (cstate->minorversion) {
+ memcpy(&cstate->current_stateid, stateid, sizeof(stateid_t));
+ SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+ }
+}
+
+void
+clear_current_stateid(struct nfsd4_compound_state *cstate)
+{
+ CLEAR_STATE_ID(cstate, CURRENT_STATE_ID_FLAG);
+}
+
+/*
+ * functions to set current state id
+ */
+void
+nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp)
+{
+ put_stateid(cstate, &odp->od_stateid);
+}
+
+void
+nfsd4_set_openstateid(struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
+{
+ put_stateid(cstate, &open->op_stateid);
+}
+
+void
+nfsd4_set_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close)
+{
+ put_stateid(cstate, &close->cl_stateid);
+}
+
+void
+nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, struct nfsd4_lock *lock)
+{
+ put_stateid(cstate, &lock->lk_resp_stateid);
+}
+
+/*
+ * functions to consume current state id
+ */
+
+void
+nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp)
+{
+ get_stateid(cstate, &odp->od_stateid);
+}
+
+void
+nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate, struct nfsd4_delegreturn *drp)
+{
+ get_stateid(cstate, &drp->dr_stateid);
+}
+
+void
+nfsd4_get_freestateid(struct nfsd4_compound_state *cstate, struct nfsd4_free_stateid *fsp)
+{
+ get_stateid(cstate, &fsp->fr_stateid);
+}
+
+void
+nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate, struct nfsd4_setattr *setattr)
+{
+ get_stateid(cstate, &setattr->sa_stateid);
+}
+
+void
+nfsd4_get_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close)
+{
+ get_stateid(cstate, &close->cl_stateid);
+}
+
+void
+nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate, struct nfsd4_locku *locku)
+{
+ get_stateid(cstate, &locku->lu_stateid);
+}
+
+void
+nfsd4_get_readstateid(struct nfsd4_compound_state *cstate, struct nfsd4_read *read)
+{
+ get_stateid(cstate, &read->rd_stateid);
+}
+
+void
+nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, struct nfsd4_write *write)
+{
+ get_stateid(cstate, &write->wr_stateid);
+}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 0ec5a1b..bcd8904 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -133,22 +133,6 @@
} \
} while (0)
-static void save_buf(struct nfsd4_compoundargs *argp, struct nfsd4_saved_compoundargs *savep)
-{
- savep->p = argp->p;
- savep->end = argp->end;
- savep->pagelen = argp->pagelen;
- savep->pagelist = argp->pagelist;
-}
-
-static void restore_buf(struct nfsd4_compoundargs *argp, struct nfsd4_saved_compoundargs *savep)
-{
- argp->p = savep->p;
- argp->end = savep->end;
- argp->pagelen = savep->pagelen;
- argp->pagelist = savep->pagelist;
-}
-
static __be32 *read_buf(struct nfsd4_compoundargs *argp, u32 nbytes)
{
/* We want more bytes than seem to be available.
@@ -638,14 +622,18 @@
DECODE_TAIL;
}
-static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *x)
+static __be32 nfsd4_decode_share_access(struct nfsd4_compoundargs *argp, u32 *share_access, u32 *deleg_want, u32 *deleg_when)
{
__be32 *p;
u32 w;
READ_BUF(4);
READ32(w);
- *x = w;
+ *share_access = w & NFS4_SHARE_ACCESS_MASK;
+ *deleg_want = w & NFS4_SHARE_WANT_MASK;
+ if (deleg_when)
+ *deleg_when = w & NFS4_SHARE_WHEN_MASK;
+
switch (w & NFS4_SHARE_ACCESS_MASK) {
case NFS4_SHARE_ACCESS_READ:
case NFS4_SHARE_ACCESS_WRITE:
@@ -673,6 +661,9 @@
w &= ~NFS4_SHARE_WANT_MASK;
if (!w)
return nfs_ok;
+
+ if (!deleg_when) /* open_downgrade */
+ return nfserr_inval;
switch (w) {
case NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL:
case NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED:
@@ -719,6 +710,7 @@
nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open)
{
DECODE_HEAD;
+ u32 dummy;
memset(open->op_bmval, 0, sizeof(open->op_bmval));
open->op_iattr.ia_valid = 0;
@@ -727,7 +719,9 @@
/* seqid, share_access, share_deny, clientid, ownerlen */
READ_BUF(4);
READ32(open->op_seqid);
- status = nfsd4_decode_share_access(argp, &open->op_share_access);
+ /* decode, yet ignore deleg_when until supported */
+ status = nfsd4_decode_share_access(argp, &open->op_share_access,
+ &open->op_deleg_want, &dummy);
if (status)
goto xdr_error;
status = nfsd4_decode_share_deny(argp, &open->op_share_deny);
@@ -755,14 +749,14 @@
goto out;
break;
case NFS4_CREATE_EXCLUSIVE:
- READ_BUF(8);
- COPYMEM(open->op_verf.data, 8);
+ READ_BUF(NFS4_VERIFIER_SIZE);
+ COPYMEM(open->op_verf.data, NFS4_VERIFIER_SIZE);
break;
case NFS4_CREATE_EXCLUSIVE4_1:
if (argp->minorversion < 1)
goto xdr_error;
- READ_BUF(8);
- COPYMEM(open->op_verf.data, 8);
+ READ_BUF(NFS4_VERIFIER_SIZE);
+ COPYMEM(open->op_verf.data, NFS4_VERIFIER_SIZE);
status = nfsd4_decode_fattr(argp, open->op_bmval,
&open->op_iattr, &open->op_acl);
if (status)
@@ -848,7 +842,8 @@
return status;
READ_BUF(4);
READ32(open_down->od_seqid);
- status = nfsd4_decode_share_access(argp, &open_down->od_share_access);
+ status = nfsd4_decode_share_access(argp, &open_down->od_share_access,
+ &open_down->od_deleg_want, NULL);
if (status)
return status;
status = nfsd4_decode_share_deny(argp, &open_down->od_share_deny);
@@ -994,8 +989,8 @@
{
DECODE_HEAD;
- READ_BUF(8);
- COPYMEM(setclientid->se_verf.data, 8);
+ READ_BUF(NFS4_VERIFIER_SIZE);
+ COPYMEM(setclientid->se_verf.data, NFS4_VERIFIER_SIZE);
status = nfsd4_decode_opaque(argp, &setclientid->se_name);
if (status)
@@ -1020,9 +1015,9 @@
{
DECODE_HEAD;
- READ_BUF(8 + sizeof(nfs4_verifier));
+ READ_BUF(8 + NFS4_VERIFIER_SIZE);
COPYMEM(&scd_c->sc_clientid, 8);
- COPYMEM(&scd_c->sc_confirm, sizeof(nfs4_verifier));
+ COPYMEM(&scd_c->sc_confirm, NFS4_VERIFIER_SIZE);
DECODE_TAIL;
}
@@ -1385,26 +1380,29 @@
static __be32
nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_stateid *test_stateid)
{
- unsigned int nbytes;
- stateid_t si;
int i;
- __be32 *p;
- __be32 status;
+ __be32 *p, status;
+ struct nfsd4_test_stateid_id *stateid;
READ_BUF(4);
test_stateid->ts_num_ids = ntohl(*p++);
- nbytes = test_stateid->ts_num_ids * sizeof(stateid_t);
- if (nbytes > (u32)((char *)argp->end - (char *)argp->p))
- goto xdr_error;
-
- test_stateid->ts_saved_args = argp;
- save_buf(argp, &test_stateid->ts_savedp);
+ INIT_LIST_HEAD(&test_stateid->ts_stateid_list);
for (i = 0; i < test_stateid->ts_num_ids; i++) {
- status = nfsd4_decode_stateid(argp, &si);
+ stateid = kmalloc(sizeof(struct nfsd4_test_stateid_id), GFP_KERNEL);
+ if (!stateid) {
+ status = PTR_ERR(stateid);
+ goto out;
+ }
+
+ defer_free(argp, kfree, stateid);
+ INIT_LIST_HEAD(&stateid->ts_id_list);
+ list_add_tail(&stateid->ts_id_list, &test_stateid->ts_stateid_list);
+
+ status = nfsd4_decode_stateid(argp, &stateid->ts_id_stateid);
if (status)
- return status;
+ goto out;
}
status = 0;
@@ -2661,8 +2659,8 @@
__be32 *p;
if (!nfserr) {
- RESERVE_SPACE(8);
- WRITEMEM(commit->co_verf.data, 8);
+ RESERVE_SPACE(NFS4_VERIFIER_SIZE);
+ WRITEMEM(commit->co_verf.data, NFS4_VERIFIER_SIZE);
ADJUST_ARGS();
}
return nfserr;
@@ -2851,6 +2849,20 @@
WRITE32(0); /* XXX: is NULL principal ok? */
ADJUST_ARGS();
break;
+ case NFS4_OPEN_DELEGATE_NONE_EXT: /* 4.1 */
+ switch (open->op_why_no_deleg) {
+ case WND4_CONTENTION:
+ case WND4_RESOURCE:
+ RESERVE_SPACE(8);
+ WRITE32(open->op_why_no_deleg);
+ WRITE32(0); /* deleg signaling not supported yet */
+ break;
+ default:
+ RESERVE_SPACE(4);
+ WRITE32(open->op_why_no_deleg);
+ }
+ ADJUST_ARGS();
+ break;
default:
BUG();
}
@@ -3008,7 +3020,7 @@
if (resp->xbuf->page_len)
return nfserr_resource;
- RESERVE_SPACE(8); /* verifier */
+ RESERVE_SPACE(NFS4_VERIFIER_SIZE);
savep = p;
/* XXX: Following NFSv3, we ignore the READDIR verifier for now. */
@@ -3209,9 +3221,9 @@
__be32 *p;
if (!nfserr) {
- RESERVE_SPACE(8 + sizeof(nfs4_verifier));
+ RESERVE_SPACE(8 + NFS4_VERIFIER_SIZE);
WRITEMEM(&scd->se_clientid, 8);
- WRITEMEM(&scd->se_confirm, sizeof(nfs4_verifier));
+ WRITEMEM(&scd->se_confirm, NFS4_VERIFIER_SIZE);
ADJUST_ARGS();
}
else if (nfserr == nfserr_clid_inuse) {
@@ -3232,7 +3244,7 @@
RESERVE_SPACE(16);
WRITE32(write->wr_bytes_written);
WRITE32(write->wr_how_written);
- WRITEMEM(write->wr_verifier.data, 8);
+ WRITEMEM(write->wr_verifier.data, NFS4_VERIFIER_SIZE);
ADJUST_ARGS();
}
return nfserr;
@@ -3391,30 +3403,17 @@
nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, int nfserr,
struct nfsd4_test_stateid *test_stateid)
{
- struct nfsd4_compoundargs *argp;
- struct nfs4_client *cl = resp->cstate.session->se_client;
- stateid_t si;
+ struct nfsd4_test_stateid_id *stateid, *next;
__be32 *p;
- int i;
- int valid;
- restore_buf(test_stateid->ts_saved_args, &test_stateid->ts_savedp);
- argp = test_stateid->ts_saved_args;
-
- RESERVE_SPACE(4);
+ RESERVE_SPACE(4 + (4 * test_stateid->ts_num_ids));
*p++ = htonl(test_stateid->ts_num_ids);
- resp->p = p;
- nfs4_lock_state();
- for (i = 0; i < test_stateid->ts_num_ids; i++) {
- nfsd4_decode_stateid(argp, &si);
- valid = nfs4_validate_stateid(cl, &si);
- RESERVE_SPACE(4);
- *p++ = htonl(valid);
- resp->p = p;
+ list_for_each_entry_safe(stateid, next, &test_stateid->ts_stateid_list, ts_id_list) {
+ *p++ = htonl(stateid->ts_id_status);
}
- nfs4_unlock_state();
+ ADJUST_ARGS();
return nfserr;
}
@@ -3532,7 +3531,7 @@
if (length > session->se_fchannel.maxresp_sz)
return nfserr_rep_too_big;
- if (slot->sl_cachethis == 1 &&
+ if ((slot->sl_flags & NFSD4_SLOT_CACHETHIS) &&
length > session->se_fchannel.maxresp_cached)
return nfserr_rep_too_big_to_cache;
@@ -3656,8 +3655,7 @@
if (nfsd4_has_session(cs)) {
if (cs->status != nfserr_replay_cache) {
nfsd4_store_cache_entry(resp);
- dprintk("%s: SET SLOT STATE TO AVAILABLE\n", __func__);
- cs->slot->sl_inuse = false;
+ cs->slot->sl_flags &= ~NFSD4_SLOT_INUSE;
}
/* Renew the clientid on success and on replay */
release_session_client(cs->session);
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index fce472f..28dfad3 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -307,33 +307,37 @@
dprintk("%s nfsd_drc_max_mem %u \n", __func__, nfsd_drc_max_mem);
}
+static int nfsd_get_default_max_blksize(void)
+{
+ struct sysinfo i;
+ unsigned long long target;
+ unsigned long ret;
+
+ si_meminfo(&i);
+ target = (i.totalram - i.totalhigh) << PAGE_SHIFT;
+ /*
+ * Aim for 1/4096 of memory per thread This gives 1MB on 4Gig
+ * machines, but only uses 32K on 128M machines. Bottom out at
+ * 8K on 32M and smaller. Of course, this is only a default.
+ */
+ target >>= 12;
+
+ ret = NFSSVC_MAXBLKSIZE;
+ while (ret > target && ret >= 8*1024*2)
+ ret /= 2;
+ return ret;
+}
+
int nfsd_create_serv(void)
{
- int err = 0;
-
WARN_ON(!mutex_is_locked(&nfsd_mutex));
if (nfsd_serv) {
svc_get(nfsd_serv);
return 0;
}
- if (nfsd_max_blksize == 0) {
- /* choose a suitable default */
- struct sysinfo i;
- si_meminfo(&i);
- /* Aim for 1/4096 of memory per thread
- * This gives 1MB on 4Gig machines
- * But only uses 32K on 128M machines.
- * Bottom out at 8K on 32M and smaller.
- * Of course, this is only a default.
- */
- nfsd_max_blksize = NFSSVC_MAXBLKSIZE;
- i.totalram <<= PAGE_SHIFT - 12;
- while (nfsd_max_blksize > i.totalram &&
- nfsd_max_blksize >= 8*1024*2)
- nfsd_max_blksize /= 2;
- }
+ if (nfsd_max_blksize == 0)
+ nfsd_max_blksize = nfsd_get_default_max_blksize();
nfsd_reset_versions();
-
nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
nfsd_last_thread, nfsd, THIS_MODULE);
if (nfsd_serv == NULL)
@@ -341,7 +345,7 @@
set_max_drc();
do_gettimeofday(&nfssvc_boot); /* record boot time */
- return err;
+ return 0;
}
int nfsd_nrpools(void)
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index ffb5df1..1e2b582 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -128,12 +128,14 @@
(NFSD_CACHE_SIZE_SLOTS_PER_SESSION * NFSD_SLOT_CACHE_SIZE)
struct nfsd4_slot {
- bool sl_inuse;
- bool sl_cachethis;
- u16 sl_opcnt;
u32 sl_seqid;
__be32 sl_status;
u32 sl_datalen;
+ u16 sl_opcnt;
+#define NFSD4_SLOT_INUSE (1 << 0)
+#define NFSD4_SLOT_CACHETHIS (1 << 1)
+#define NFSD4_SLOT_INITIALIZED (1 << 2)
+ u8 sl_flags;
char sl_data[];
};
@@ -196,18 +198,7 @@
struct nfsd4_slot *se_slots[]; /* forward channel slots */
};
-static inline void
-nfsd4_put_session(struct nfsd4_session *ses)
-{
- extern void free_session(struct kref *kref);
- kref_put(&ses->se_ref, free_session);
-}
-
-static inline void
-nfsd4_get_session(struct nfsd4_session *ses)
-{
- kref_get(&ses->se_ref);
-}
+extern void nfsd4_put_session(struct nfsd4_session *ses);
/* formatted contents of nfs4_sessionid */
struct nfsd4_sessionid {
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index edf6d3e..7423d71 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -737,12 +737,13 @@
/*
* Open an existing file or directory.
- * The access argument indicates the type of open (read/write/lock)
+ * The may_flags argument indicates the type of open (read/write/lock)
+ * and additional flags.
* N.B. After this call fhp needs an fh_put
*/
__be32
nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
- int access, struct file **filp)
+ int may_flags, struct file **filp)
{
struct dentry *dentry;
struct inode *inode;
@@ -757,7 +758,7 @@
* and (hopefully) checked permission - so allow OWNER_OVERRIDE
* in case a chmod has now revoked permission.
*/
- err = fh_verify(rqstp, fhp, type, access | NFSD_MAY_OWNER_OVERRIDE);
+ err = fh_verify(rqstp, fhp, type, may_flags | NFSD_MAY_OWNER_OVERRIDE);
if (err)
goto out;
@@ -768,7 +769,7 @@
* or any access when mandatory locking enabled
*/
err = nfserr_perm;
- if (IS_APPEND(inode) && (access & NFSD_MAY_WRITE))
+ if (IS_APPEND(inode) && (may_flags & NFSD_MAY_WRITE))
goto out;
/*
* We must ignore files (but only files) which might have mandatory
@@ -781,12 +782,12 @@
if (!inode->i_fop)
goto out;
- host_err = nfsd_open_break_lease(inode, access);
+ host_err = nfsd_open_break_lease(inode, may_flags);
if (host_err) /* NOMEM or WOULDBLOCK */
goto out_nfserr;
- if (access & NFSD_MAY_WRITE) {
- if (access & NFSD_MAY_READ)
+ if (may_flags & NFSD_MAY_WRITE) {
+ if (may_flags & NFSD_MAY_READ)
flags = O_RDWR|O_LARGEFILE;
else
flags = O_WRONLY|O_LARGEFILE;
@@ -795,8 +796,15 @@
flags, current_cred());
if (IS_ERR(*filp))
host_err = PTR_ERR(*filp);
- else
- host_err = ima_file_check(*filp, access);
+ else {
+ host_err = ima_file_check(*filp, may_flags);
+
+ if (may_flags & NFSD_MAY_64BIT_COOKIE)
+ (*filp)->f_mode |= FMODE_64BITHASH;
+ else
+ (*filp)->f_mode |= FMODE_32BITHASH;
+ }
+
out_nfserr:
err = nfserrno(host_err);
out:
@@ -2020,8 +2028,13 @@
__be32 err;
struct file *file;
loff_t offset = *offsetp;
+ int may_flags = NFSD_MAY_READ;
- err = nfsd_open(rqstp, fhp, S_IFDIR, NFSD_MAY_READ, &file);
+ /* NFSv2 only supports 32 bit cookies */
+ if (rqstp->rq_vers > 2)
+ may_flags |= NFSD_MAY_64BIT_COOKIE;
+
+ err = nfsd_open(rqstp, fhp, S_IFDIR, may_flags, &file);
if (err)
goto out;
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 1dcd238..ec0611b 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -27,6 +27,8 @@
#define NFSD_MAY_BYPASS_GSS 0x400
#define NFSD_MAY_READ_IF_EXEC 0x800
+#define NFSD_MAY_64BIT_COOKIE 0x1000 /* 64 bit readdir cookies for >= NFSv3 */
+
#define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE)
#define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 2364747..1b35015 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -43,6 +43,13 @@
#define NFSD4_MAX_TAGLEN 128
#define XDR_LEN(n) (((n) + 3) & ~3)
+#define CURRENT_STATE_ID_FLAG (1<<0)
+#define SAVED_STATE_ID_FLAG (1<<1)
+
+#define SET_STATE_ID(c, f) ((c)->sid_flags |= (f))
+#define HAS_STATE_ID(c, f) ((c)->sid_flags & (f))
+#define CLEAR_STATE_ID(c, f) ((c)->sid_flags &= ~(f))
+
struct nfsd4_compound_state {
struct svc_fh current_fh;
struct svc_fh save_fh;
@@ -54,6 +61,10 @@
size_t iovlen;
u32 minorversion;
u32 status;
+ stateid_t current_stateid;
+ stateid_t save_stateid;
+ /* to indicate current and saved state id presents */
+ u32 sid_flags;
};
static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs)
@@ -212,16 +223,19 @@
struct xdr_netobj op_fname; /* request - everything but CLAIM_PREV */
u32 op_delegate_type; /* request - CLAIM_PREV only */
stateid_t op_delegate_stateid; /* request - response */
+ u32 op_why_no_deleg; /* response - DELEG_NONE_EXT only */
u32 op_create; /* request */
u32 op_createmode; /* request */
u32 op_bmval[3]; /* request */
struct iattr iattr; /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */
- nfs4_verifier verf; /* EXCLUSIVE4 */
+ nfs4_verifier op_verf __attribute__((aligned(32)));
+ /* EXCLUSIVE4 */
clientid_t op_clientid; /* request */
struct xdr_netobj op_owner; /* request */
u32 op_seqid; /* request */
u32 op_share_access; /* request */
u32 op_share_deny; /* request */
+ u32 op_deleg_want; /* request */
stateid_t op_stateid; /* response */
u32 op_recall; /* recall */
struct nfsd4_change_info op_cinfo; /* response */
@@ -234,7 +248,6 @@
struct nfs4_acl *op_acl;
};
#define op_iattr iattr
-#define op_verf verf
struct nfsd4_open_confirm {
stateid_t oc_req_stateid /* request */;
@@ -245,8 +258,9 @@
struct nfsd4_open_downgrade {
stateid_t od_stateid;
u32 od_seqid;
- u32 od_share_access;
- u32 od_share_deny;
+ u32 od_share_access; /* request */
+ u32 od_deleg_want; /* request */
+ u32 od_share_deny; /* request */
};
@@ -343,10 +357,15 @@
struct page **pagelist;
};
+struct nfsd4_test_stateid_id {
+ __be32 ts_id_status;
+ stateid_t ts_id_stateid;
+ struct list_head ts_id_list;
+};
+
struct nfsd4_test_stateid {
__be32 ts_num_ids;
- struct nfsd4_compoundargs *ts_saved_args;
- struct nfsd4_saved_compoundargs ts_savedp;
+ struct list_head ts_stateid_list;
};
struct nfsd4_free_stateid {
@@ -503,7 +522,8 @@
static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp)
{
- return !resp->cstate.slot->sl_cachethis || nfsd4_is_solo_sequence(resp);
+ return !(resp->cstate.slot->sl_flags & NFSD4_SLOT_CACHETHIS)
+ || nfsd4_is_solo_sequence(resp);
}
#define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 386da09..8975a56 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -92,6 +92,10 @@
/* File is opened using open(.., 3, ..) and is writeable only for ioctls
(specialy hack for floppy.c) */
#define FMODE_WRITE_IOCTL ((__force fmode_t)0x100)
+/* 32bit hashes as llseek() offset (for directories) */
+#define FMODE_32BITHASH ((__force fmode_t)0x200)
+/* 64bit hashes as llseek() offset (for directories) */
+#define FMODE_64BITHASH ((__force fmode_t)0x400)
/*
* Don't update ctime and mtime.
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 834df8b..0987146 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -438,7 +438,20 @@
enum open_delegation_type4 {
NFS4_OPEN_DELEGATE_NONE = 0,
NFS4_OPEN_DELEGATE_READ = 1,
- NFS4_OPEN_DELEGATE_WRITE = 2
+ NFS4_OPEN_DELEGATE_WRITE = 2,
+ NFS4_OPEN_DELEGATE_NONE_EXT = 3, /* 4.1 */
+};
+
+enum why_no_delegation4 { /* new to v4.1 */
+ WND4_NOT_WANTED = 0,
+ WND4_CONTENTION = 1,
+ WND4_RESOURCE = 2,
+ WND4_NOT_SUPP_FTYPE = 3,
+ WND4_WRITE_DELEG_NOT_SUPP_FTYPE = 4,
+ WND4_NOT_SUPP_UPGRADE = 5,
+ WND4_NOT_SUPP_DOWNGRADE = 6,
+ WND4_CANCELLED = 7,
+ WND4_IS_DIR = 8,
};
enum lock_type4 {
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index c14fe86..0b8e3e6 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -190,7 +190,7 @@
extern void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *, int);
extern void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *, int);
extern void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *, int,
- u32, u64, u32);
+ __be32, __be64, u32);
extern void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *,
struct rpcrdma_msg *,
struct rpcrdma_msg *,
@@ -292,7 +292,7 @@
if (wr_ary) {
rp_ary = (struct rpcrdma_write_array *)
&wr_ary->
- wc_array[wr_ary->wc_nchunks].wc_target.rs_length;
+ wc_array[ntohl(wr_ary->wc_nchunks)].wc_target.rs_length;
goto found_it;
}
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index f21ece0..de0b0f3 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -830,6 +830,8 @@
{
ssize_t ret;
+ if (count == 0)
+ return -EINVAL;
if (copy_from_user(kaddr, buf, count))
return -EFAULT;
kaddr[count] = '\0';
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index bcd574f..521d8f7 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -507,7 +507,7 @@
time_t expiry;
struct unix_gid ug, *ugp;
- if (mlen <= 0 || mesg[mlen-1] != '\n')
+ if (mesg[mlen - 1] != '\n')
return -EINVAL;
mesg[mlen-1] = 0;
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 40ae884..824d32f 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1381,8 +1381,6 @@
spin_lock_bh(&serv->sv_lock);
list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list)
set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
- list_for_each_entry(svsk, &serv->sv_tempsocks, sk_xprt.xpt_list)
- set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
spin_unlock_bh(&serv->sv_lock);
}
EXPORT_SYMBOL_GPL(svc_sock_update_bufs);
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index 09af4fa..8343737 100644
--- a/net/sunrpc/xprtrdma/svc_rdma.c
+++ b/net/sunrpc/xprtrdma/svc_rdma.c
@@ -47,6 +47,7 @@
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/sched.h>
#include <linux/sunrpc/svc_rdma.h>
+#include "xprt_rdma.h"
#define RPCDBG_FACILITY RPCDBG_SVCXPRT
diff --git a/net/sunrpc/xprtrdma/svc_rdma_marshal.c b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
index 9530ef2..8d2eddd 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_marshal.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_marshal.c
@@ -60,21 +60,11 @@
struct rpcrdma_read_chunk *ch = (struct rpcrdma_read_chunk *)va;
while (ch->rc_discrim != xdr_zero) {
- u64 ch_offset;
-
if (((unsigned long)ch + sizeof(struct rpcrdma_read_chunk)) >
(unsigned long)vaend) {
dprintk("svcrdma: vaend=%p, ch=%p\n", vaend, ch);
return NULL;
}
-
- ch->rc_discrim = ntohl(ch->rc_discrim);
- ch->rc_position = ntohl(ch->rc_position);
- ch->rc_target.rs_handle = ntohl(ch->rc_target.rs_handle);
- ch->rc_target.rs_length = ntohl(ch->rc_target.rs_length);
- va = (u32 *)&ch->rc_target.rs_offset;
- xdr_decode_hyper(va, &ch_offset);
- put_unaligned(ch_offset, (u64 *)va);
ch++;
}
return (u32 *)&ch->rc_position;
@@ -91,7 +81,7 @@
*byte_count = 0;
*ch_count = 0;
for (; ch->rc_discrim != 0; ch++) {
- *byte_count = *byte_count + ch->rc_target.rs_length;
+ *byte_count = *byte_count + ntohl(ch->rc_target.rs_length);
*ch_count = *ch_count + 1;
}
}
@@ -108,7 +98,8 @@
*/
static u32 *decode_write_list(u32 *va, u32 *vaend)
{
- int ch_no;
+ int nchunks;
+
struct rpcrdma_write_array *ary =
(struct rpcrdma_write_array *)va;
@@ -121,37 +112,24 @@
dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend);
return NULL;
}
- ary->wc_discrim = ntohl(ary->wc_discrim);
- ary->wc_nchunks = ntohl(ary->wc_nchunks);
+ nchunks = ntohl(ary->wc_nchunks);
if (((unsigned long)&ary->wc_array[0] +
- (sizeof(struct rpcrdma_write_chunk) * ary->wc_nchunks)) >
+ (sizeof(struct rpcrdma_write_chunk) * nchunks)) >
(unsigned long)vaend) {
dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n",
- ary, ary->wc_nchunks, vaend);
+ ary, nchunks, vaend);
return NULL;
}
- for (ch_no = 0; ch_no < ary->wc_nchunks; ch_no++) {
- u64 ch_offset;
-
- ary->wc_array[ch_no].wc_target.rs_handle =
- ntohl(ary->wc_array[ch_no].wc_target.rs_handle);
- ary->wc_array[ch_no].wc_target.rs_length =
- ntohl(ary->wc_array[ch_no].wc_target.rs_length);
- va = (u32 *)&ary->wc_array[ch_no].wc_target.rs_offset;
- xdr_decode_hyper(va, &ch_offset);
- put_unaligned(ch_offset, (u64 *)va);
- }
-
/*
* rs_length is the 2nd 4B field in wc_target and taking its
* address skips the list terminator
*/
- return (u32 *)&ary->wc_array[ch_no].wc_target.rs_length;
+ return (u32 *)&ary->wc_array[nchunks].wc_target.rs_length;
}
static u32 *decode_reply_array(u32 *va, u32 *vaend)
{
- int ch_no;
+ int nchunks;
struct rpcrdma_write_array *ary =
(struct rpcrdma_write_array *)va;
@@ -164,28 +142,15 @@
dprintk("svcrdma: ary=%p, vaend=%p\n", ary, vaend);
return NULL;
}
- ary->wc_discrim = ntohl(ary->wc_discrim);
- ary->wc_nchunks = ntohl(ary->wc_nchunks);
+ nchunks = ntohl(ary->wc_nchunks);
if (((unsigned long)&ary->wc_array[0] +
- (sizeof(struct rpcrdma_write_chunk) * ary->wc_nchunks)) >
+ (sizeof(struct rpcrdma_write_chunk) * nchunks)) >
(unsigned long)vaend) {
dprintk("svcrdma: ary=%p, wc_nchunks=%d, vaend=%p\n",
- ary, ary->wc_nchunks, vaend);
+ ary, nchunks, vaend);
return NULL;
}
- for (ch_no = 0; ch_no < ary->wc_nchunks; ch_no++) {
- u64 ch_offset;
-
- ary->wc_array[ch_no].wc_target.rs_handle =
- ntohl(ary->wc_array[ch_no].wc_target.rs_handle);
- ary->wc_array[ch_no].wc_target.rs_length =
- ntohl(ary->wc_array[ch_no].wc_target.rs_length);
- va = (u32 *)&ary->wc_array[ch_no].wc_target.rs_offset;
- xdr_decode_hyper(va, &ch_offset);
- put_unaligned(ch_offset, (u64 *)va);
- }
-
- return (u32 *)&ary->wc_array[ch_no];
+ return (u32 *)&ary->wc_array[nchunks];
}
int svc_rdma_xdr_decode_req(struct rpcrdma_msg **rdma_req,
@@ -386,13 +351,14 @@
void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *ary,
int chunk_no,
- u32 rs_handle, u64 rs_offset,
+ __be32 rs_handle,
+ __be64 rs_offset,
u32 write_len)
{
struct rpcrdma_segment *seg = &ary->wc_array[chunk_no].wc_target;
- seg->rs_handle = htonl(rs_handle);
+ seg->rs_handle = rs_handle;
+ seg->rs_offset = rs_offset;
seg->rs_length = htonl(write_len);
- xdr_encode_hyper((u32 *) &seg->rs_offset, rs_offset);
}
void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *xprt,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index df67211..41cb63b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -147,7 +147,7 @@
page_off = 0;
ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
ch_no = 0;
- ch_bytes = ch->rc_target.rs_length;
+ ch_bytes = ntohl(ch->rc_target.rs_length);
head->arg.head[0] = rqstp->rq_arg.head[0];
head->arg.tail[0] = rqstp->rq_arg.tail[0];
head->arg.pages = &head->pages[head->count];
@@ -183,7 +183,7 @@
ch_no++;
ch++;
chl_map->ch[ch_no].start = sge_no;
- ch_bytes = ch->rc_target.rs_length;
+ ch_bytes = ntohl(ch->rc_target.rs_length);
/* If bytes remaining account for next chunk */
if (byte_count) {
head->arg.page_len += ch_bytes;
@@ -281,11 +281,12 @@
offset = 0;
ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
for (ch_no = 0; ch_no < ch_count; ch_no++) {
+ int len = ntohl(ch->rc_target.rs_length);
rpl_map->sge[ch_no].iov_base = frmr->kva + offset;
- rpl_map->sge[ch_no].iov_len = ch->rc_target.rs_length;
+ rpl_map->sge[ch_no].iov_len = len;
chl_map->ch[ch_no].count = 1;
chl_map->ch[ch_no].start = ch_no;
- offset += ch->rc_target.rs_length;
+ offset += len;
ch++;
}
@@ -316,7 +317,7 @@
for (i = 0; i < count; i++) {
ctxt->sge[i].length = 0; /* in case map fails */
if (!frmr) {
- BUG_ON(0 == virt_to_page(vec[i].iov_base));
+ BUG_ON(!virt_to_page(vec[i].iov_base));
off = (unsigned long)vec[i].iov_base & ~PAGE_MASK;
ctxt->sge[i].addr =
ib_dma_map_page(xprt->sc_cm_id->device,
@@ -426,6 +427,7 @@
for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
ch->rc_discrim != 0; ch++, ch_no++) {
+ u64 rs_offset;
next_sge:
ctxt = svc_rdma_get_context(xprt);
ctxt->direction = DMA_FROM_DEVICE;
@@ -440,10 +442,10 @@
read_wr.opcode = IB_WR_RDMA_READ;
ctxt->wr_op = read_wr.opcode;
read_wr.send_flags = IB_SEND_SIGNALED;
- read_wr.wr.rdma.rkey = ch->rc_target.rs_handle;
- read_wr.wr.rdma.remote_addr =
- get_unaligned(&(ch->rc_target.rs_offset)) +
- sgl_offset;
+ read_wr.wr.rdma.rkey = ntohl(ch->rc_target.rs_handle);
+ xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
+ &rs_offset);
+ read_wr.wr.rdma.remote_addr = rs_offset + sgl_offset;
read_wr.sg_list = ctxt->sge;
read_wr.num_sge =
rdma_read_max_sge(xprt, chl_map->ch[ch_no].count);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 249a835..42eb7ba 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -409,21 +409,21 @@
u64 rs_offset;
arg_ch = &arg_ary->wc_array[chunk_no].wc_target;
- write_len = min(xfer_len, arg_ch->rs_length);
+ write_len = min(xfer_len, ntohl(arg_ch->rs_length));
/* Prepare the response chunk given the length actually
* written */
- rs_offset = get_unaligned(&(arg_ch->rs_offset));
+ xdr_decode_hyper((__be32 *)&arg_ch->rs_offset, &rs_offset);
svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no,
- arg_ch->rs_handle,
- rs_offset,
- write_len);
+ arg_ch->rs_handle,
+ arg_ch->rs_offset,
+ write_len);
chunk_off = 0;
while (write_len) {
int this_write;
this_write = min(write_len, max_write);
ret = send_write(xprt, rqstp,
- arg_ch->rs_handle,
+ ntohl(arg_ch->rs_handle),
rs_offset + chunk_off,
xdr_off,
this_write,
@@ -457,6 +457,7 @@
u32 xdr_off;
int chunk_no;
int chunk_off;
+ int nchunks;
struct rpcrdma_segment *ch;
struct rpcrdma_write_array *arg_ary;
struct rpcrdma_write_array *res_ary;
@@ -476,26 +477,27 @@
max_write = xprt->sc_max_sge * PAGE_SIZE;
/* xdr offset starts at RPC message */
+ nchunks = ntohl(arg_ary->wc_nchunks);
for (xdr_off = 0, chunk_no = 0;
- xfer_len && chunk_no < arg_ary->wc_nchunks;
+ xfer_len && chunk_no < nchunks;
chunk_no++) {
u64 rs_offset;
ch = &arg_ary->wc_array[chunk_no].wc_target;
- write_len = min(xfer_len, ch->rs_length);
+ write_len = min(xfer_len, htonl(ch->rs_length));
/* Prepare the reply chunk given the length actually
* written */
- rs_offset = get_unaligned(&(ch->rs_offset));
+ xdr_decode_hyper((__be32 *)&ch->rs_offset, &rs_offset);
svc_rdma_xdr_encode_array_chunk(res_ary, chunk_no,
- ch->rs_handle, rs_offset,
- write_len);
+ ch->rs_handle, ch->rs_offset,
+ write_len);
chunk_off = 0;
while (write_len) {
int this_write;
this_write = min(write_len, max_write);
ret = send_write(xprt, rqstp,
- ch->rs_handle,
+ ntohl(ch->rs_handle),
rs_offset + chunk_off,
xdr_off,
this_write,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 894cb42..73b428b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -51,6 +51,7 @@
#include <rdma/rdma_cm.h>
#include <linux/sunrpc/svc_rdma.h>
#include <linux/export.h>
+#include "xprt_rdma.h"
#define RPCDBG_FACILITY RPCDBG_SVCXPRT
@@ -90,12 +91,6 @@
.xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP,
};
-/* WR context cache. Created in svc_rdma.c */
-extern struct kmem_cache *svc_rdma_ctxt_cachep;
-
-/* Workqueue created in svc_rdma.c */
-extern struct workqueue_struct *svc_rdma_wq;
-
struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt)
{
struct svc_rdma_op_ctxt *ctxt;
@@ -150,9 +145,6 @@
atomic_dec(&xprt->sc_ctxt_used);
}
-/* Temporary NFS request map cache. Created in svc_rdma.c */
-extern struct kmem_cache *svc_rdma_map_cachep;
-
/*
* Temporary NFS req mappings are shared across all transport
* instances. These are short lived and should be bounded by the number
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 08c5d5a..9a66c95 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -343,4 +343,11 @@
*/
int rpcrdma_marshal_req(struct rpc_rqst *);
+/* Temporary NFS request map cache. Created in svc_rdma.c */
+extern struct kmem_cache *svc_rdma_map_cachep;
+/* WR context cache. Created in svc_rdma.c */
+extern struct kmem_cache *svc_rdma_ctxt_cachep;
+/* Workqueue created in svc_rdma.c */
+extern struct workqueue_struct *svc_rdma_wq;
+
#endif /* _LINUX_SUNRPC_XPRT_RDMA_H */