summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/cifs/cifs_debug.c58
-rw-r--r--fs/cifs/cifs_dfs_ref.c14
-rw-r--r--fs/cifs/cifs_fs_sb.h4
-rw-r--r--fs/cifs/cifs_swn.h27
-rw-r--r--fs/cifs/cifsacl.c4
-rw-r--r--fs/cifs/cifsfs.c47
-rw-r--r--fs/cifs/cifsfs.h2
-rw-r--r--fs/cifs/cifsglob.h32
-rw-r--r--fs/cifs/cifspdu.h2
-rw-r--r--fs/cifs/cifsproto.h30
-rw-r--r--fs/cifs/cifssmb.c52
-rw-r--r--fs/cifs/connect.c34
-rw-r--r--fs/cifs/dfs_cache.c41
-rw-r--r--fs/cifs/dir.c150
-rw-r--r--fs/cifs/file.c79
-rw-r--r--fs/cifs/fs_context.c143
-rw-r--r--fs/cifs/fs_context.h13
-rw-r--r--fs/cifs/inode.c140
-rw-r--r--fs/cifs/ioctl.c13
-rw-r--r--fs/cifs/link.c46
-rw-r--r--fs/cifs/misc.c2
-rw-r--r--fs/cifs/readdir.c15
-rw-r--r--fs/cifs/smb1ops.c6
-rw-r--r--fs/cifs/smb2inode.c10
-rw-r--r--fs/cifs/smb2misc.c1
-rw-r--r--fs/cifs/smb2ops.c195
-rw-r--r--fs/cifs/smb2pdu.c2
-rw-r--r--fs/cifs/smb2pdu.h49
-rw-r--r--fs/cifs/smb2proto.h16
-rw-r--r--fs/cifs/unc.c4
-rw-r--r--fs/cifs/xattr.c40
-rw-r--r--fs/coda/file.c6
-rw-r--r--fs/crypto/Kconfig30
-rw-r--r--fs/debugfs/file.c3
-rw-r--r--fs/debugfs/inode.c2
-rw-r--r--fs/erofs/Kconfig14
-rw-r--r--fs/erofs/Makefile2
-rw-r--r--fs/erofs/data.c19
-rw-r--r--fs/erofs/decompressor.c272
-rw-r--r--fs/erofs/erofs_fs.h54
-rw-r--r--fs/erofs/inode.c7
-rw-r--r--fs/erofs/internal.h86
-rw-r--r--fs/erofs/pcpubuf.c148
-rw-r--r--fs/erofs/super.c148
-rw-r--r--fs/erofs/utils.c12
-rw-r--r--fs/erofs/zdata.c254
-rw-r--r--fs/erofs/zdata.h14
-rw-r--r--fs/erofs/zmap.c164
-rw-r--r--fs/eventpoll.c52
-rw-r--r--fs/locks.c66
-rw-r--r--fs/namespace.c14
-rw-r--r--fs/nfs_common/nfsacl.c71
-rw-r--r--fs/nfsd/Kconfig6
-rw-r--r--fs/nfsd/netns.h6
-rw-r--r--fs/nfsd/nfs2acl.c87
-rw-r--r--fs/nfsd/nfs3acl.c39
-rw-r--r--fs/nfsd/nfs3proc.c97
-rw-r--r--fs/nfsd/nfs3xdr.c1043
-rw-r--r--fs/nfsd/nfs4proc.c40
-rw-r--r--fs/nfsd/nfs4recover.c8
-rw-r--r--fs/nfsd/nfs4state.c82
-rw-r--r--fs/nfsd/nfs4xdr.c110
-rw-r--r--fs/nfsd/nfsctl.c28
-rw-r--r--fs/nfsd/nfsd.h7
-rw-r--r--fs/nfsd/nfsfh.c2
-rw-r--r--fs/nfsd/nfsfh.h2
-rw-r--r--fs/nfsd/nfsproc.c53
-rw-r--r--fs/nfsd/nfssvc.c42
-rw-r--r--fs/nfsd/nfsxdr.c413
-rw-r--r--fs/nfsd/state.h4
-rw-r--r--fs/nfsd/trace.h24
-rw-r--r--fs/nfsd/vfs.c9
-rw-r--r--fs/nfsd/vfs.h2
-rw-r--r--fs/nfsd/xdr.h23
-rw-r--r--fs/nfsd/xdr3.h37
-rw-r--r--fs/nfsd/xdr4.h2
-rw-r--r--fs/overlayfs/file.c11
-rw-r--r--fs/verity/Kconfig8
78 files changed, 3060 insertions, 1834 deletions
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 88a7958170ee..68e8e5b27841 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -17,15 +17,14 @@
#include "cifsproto.h"
#include "cifs_debug.h"
#include "cifsfs.h"
+#include "fs_context.h"
#ifdef CONFIG_CIFS_DFS_UPCALL
#include "dfs_cache.h"
#endif
#ifdef CONFIG_CIFS_SMB_DIRECT
#include "smbdirect.h"
#endif
-#ifdef CONFIG_CIFS_SWN_UPCALL
#include "cifs_swn.h"
-#endif
void
cifs_dump_mem(char *label, void *data, int length)
@@ -118,10 +117,8 @@ static void cifs_debug_tcon(struct seq_file *m, struct cifs_tcon *tcon)
seq_printf(m, " POSIX Extensions");
if (tcon->ses->server->ops->dump_share_caps)
tcon->ses->server->ops->dump_share_caps(m, tcon);
-#ifdef CONFIG_CIFS_SWN_UPCALL
if (tcon->use_witness)
seq_puts(m, " Witness");
-#endif
if (tcon->need_reconnect)
seq_puts(m, "\tDISCONNECTED ");
@@ -490,10 +487,8 @@ skip_rdma:
spin_unlock(&cifs_tcp_ses_lock);
seq_putc(m, '\n');
-
-#ifdef CONFIG_CIFS_SWN_UPCALL
cifs_swn_dump(m);
-#endif
+
/* BB add code to dump additional info such as TCP session info now */
return 0;
}
@@ -702,6 +697,7 @@ static const struct proc_ops cifs_lookup_cache_proc_ops;
static const struct proc_ops traceSMB_proc_ops;
static const struct proc_ops cifs_security_flags_proc_ops;
static const struct proc_ops cifs_linux_ext_proc_ops;
+static const struct proc_ops cifs_mount_params_proc_ops;
void
cifs_proc_init(void)
@@ -726,6 +722,8 @@ cifs_proc_init(void)
proc_create("LookupCacheEnabled", 0644, proc_fs_cifs,
&cifs_lookup_cache_proc_ops);
+ proc_create("mount_params", 0444, proc_fs_cifs, &cifs_mount_params_proc_ops);
+
#ifdef CONFIG_CIFS_DFS_UPCALL
proc_create("dfscache", 0644, proc_fs_cifs, &dfscache_proc_ops);
#endif
@@ -764,6 +762,7 @@ cifs_proc_clean(void)
remove_proc_entry("SecurityFlags", proc_fs_cifs);
remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs);
remove_proc_entry("LookupCacheEnabled", proc_fs_cifs);
+ remove_proc_entry("mount_params", proc_fs_cifs);
#ifdef CONFIG_CIFS_DFS_UPCALL
remove_proc_entry("dfscache", proc_fs_cifs);
@@ -1023,6 +1022,51 @@ static const struct proc_ops cifs_security_flags_proc_ops = {
.proc_release = single_release,
.proc_write = cifs_security_flags_proc_write,
};
+
+/* To make it easier to debug, can help to show mount params */
+static int cifs_mount_params_proc_show(struct seq_file *m, void *v)
+{
+ const struct fs_parameter_spec *p;
+ const char *type;
+
+ for (p = smb3_fs_parameters; p->name; p++) {
+ /* cannot use switch with pointers... */
+ if (!p->type) {
+ if (p->flags == fs_param_neg_with_no)
+ type = "noflag";
+ else
+ type = "flag";
+ } else if (p->type == fs_param_is_bool)
+ type = "bool";
+ else if (p->type == fs_param_is_u32)
+ type = "u32";
+ else if (p->type == fs_param_is_u64)
+ type = "u64";
+ else if (p->type == fs_param_is_string)
+ type = "string";
+ else
+ type = "unknown";
+
+ seq_printf(m, "%s:%s\n", p->name, type);
+ }
+
+ return 0;
+}
+
+static int cifs_mount_params_proc_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, cifs_mount_params_proc_show, NULL);
+}
+
+static const struct proc_ops cifs_mount_params_proc_ops = {
+ .proc_open = cifs_mount_params_proc_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_release = single_release,
+ /* No need for write for now */
+ /* .proc_write = cifs_mount_params_proc_write, */
+};
+
#else
inline void cifs_proc_init(void)
{
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 6b1ce4efb591..c87c37cf2914 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -270,7 +270,7 @@ static struct vfsmount *cifs_dfs_do_mount(struct dentry *mntpt,
char *mountdata;
char *devname;
- devname = kstrndup(fullpath, strlen(fullpath), GFP_KERNEL);
+ devname = kstrdup(fullpath, GFP_KERNEL);
if (!devname)
return ERR_PTR(-ENOMEM);
@@ -302,6 +302,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
struct cifs_sb_info *cifs_sb;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
+ void *page;
char *full_path, *root_path;
unsigned int xid;
int rc;
@@ -324,10 +325,13 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
goto cdda_exit;
}
+ page = alloc_dentry_path();
/* always use tree name prefix */
- full_path = build_path_from_dentry_optional_prefix(mntpt, true);
- if (full_path == NULL)
- goto cdda_exit;
+ full_path = build_path_from_dentry_optional_prefix(mntpt, page, true);
+ if (IS_ERR(full_path)) {
+ mnt = ERR_CAST(full_path);
+ goto free_full_path;
+ }
convert_delimiter(full_path, '\\');
@@ -385,7 +389,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
free_root_path:
kfree(root_path);
free_full_path:
- kfree(full_path);
+ free_dentry_path(page);
cdda_exit:
cifs_dbg(FYI, "leaving %s\n" , __func__);
return mnt;
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index aa77edc12212..2a5325a7ae49 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -81,5 +81,9 @@ struct cifs_sb_info {
* (cifs_autodisable_serverino) in order to match new mounts.
*/
bool mnt_cifs_serverino_autodisabled;
+ /*
+ * Available once the mount has completed.
+ */
+ struct dentry *root;
};
#endif /* _CIFS_FS_SB_H */
diff --git a/fs/cifs/cifs_swn.h b/fs/cifs/cifs_swn.h
index 236ecd4959d5..8a9d2a5c9077 100644
--- a/fs/cifs/cifs_swn.h
+++ b/fs/cifs/cifs_swn.h
@@ -7,11 +7,13 @@
#ifndef _CIFS_SWN_H
#define _CIFS_SWN_H
+#include "cifsglob.h"
struct cifs_tcon;
struct sk_buff;
struct genl_info;
+#ifdef CONFIG_CIFS_SWN_UPCALL
extern int cifs_swn_register(struct cifs_tcon *tcon);
extern int cifs_swn_unregister(struct cifs_tcon *tcon);
@@ -22,4 +24,29 @@ extern void cifs_swn_dump(struct seq_file *m);
extern void cifs_swn_check(void);
+static inline bool cifs_swn_set_server_dstaddr(struct TCP_Server_Info *server)
+{
+ if (server->use_swn_dstaddr) {
+ server->dstaddr = server->swn_dstaddr;
+ return true;
+ }
+ return false;
+}
+
+static inline void cifs_swn_reset_server_dstaddr(struct TCP_Server_Info *server)
+{
+ server->use_swn_dstaddr = false;
+}
+
+#else
+
+static inline int cifs_swn_register(struct cifs_tcon *tcon) { return 0; }
+static inline int cifs_swn_unregister(struct cifs_tcon *tcon) { return 0; }
+static inline int cifs_swn_notify(struct sk_buff *s, struct genl_info *i) { return 0; }
+static inline void cifs_swn_dump(struct seq_file *m) {}
+static inline void cifs_swn_check(void) {}
+static inline bool cifs_swn_set_server_dstaddr(struct TCP_Server_Info *server) { return false; }
+static inline void cifs_swn_reset_server_dstaddr(struct TCP_Server_Info *server) {}
+
+#endif /* CONFIG_CIFS_SWN_UPCALL */
#endif /* _CIFS_SWN_H */
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index d178cf85e926..784407f9280f 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -1094,11 +1094,9 @@ static int set_chmod_dacl(struct cifs_acl *pdacl, struct cifs_acl *pndacl,
struct cifs_ace *pnntace = NULL;
char *nacl_base = NULL;
u32 num_aces = 0;
- __u64 nmode;
bool new_aces_set = false;
/* Assuming that pndacl and pnmode are never NULL */
- nmode = *pnmode;
nacl_base = (char *)pndacl;
nsize = sizeof(struct cifs_acl);
@@ -1651,7 +1649,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
* Add three ACEs for owner, group, everyone getting rid of other ACEs
* as chmod disables ACEs and set the security descriptor. Allocate
* memory for the smb header, set security descriptor request security
- * descriptor parameters, and secuirty descriptor itself
+ * descriptor parameters, and security descriptor itself
*/
nsecdesclen = max_t(u32, nsecdesclen, DEFAULT_SEC_DESC_LEN);
pnntsd = kmalloc(nsecdesclen, GFP_KERNEL);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 5ddd20b62484..5f2c139143a7 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -217,8 +217,11 @@ cifs_read_super(struct super_block *sb)
rc = super_setup_bdi(sb);
if (rc)
goto out_no_root;
- /* tune readahead according to rsize */
- sb->s_bdi->ra_pages = cifs_sb->ctx->rsize / PAGE_SIZE;
+ /* tune readahead according to rsize if readahead size not set on mount */
+ if (cifs_sb->ctx->rasize)
+ sb->s_bdi->ra_pages = cifs_sb->ctx->rasize / PAGE_SIZE;
+ else
+ sb->s_bdi->ra_pages = cifs_sb->ctx->rsize / PAGE_SIZE;
sb->s_blocksize = CIFS_MAX_MSGSIZE;
sb->s_blocksize_bits = 14; /* default 2**14 = CIFS_MAX_MSGSIZE */
@@ -257,6 +260,29 @@ out_no_root:
static void cifs_kill_sb(struct super_block *sb)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
+ struct cifs_tcon *tcon;
+ struct cached_fid *cfid;
+
+ /*
+ * We ned to release all dentries for the cached directories
+ * before we kill the sb.
+ */
+ if (cifs_sb->root) {
+ dput(cifs_sb->root);
+ cifs_sb->root = NULL;
+ }
+ tcon = cifs_sb_master_tcon(cifs_sb);
+ if (tcon) {
+ cfid = &tcon->crfid;
+ mutex_lock(&cfid->fid_mutex);
+ if (cfid->dentry) {
+
+ dput(cfid->dentry);
+ cfid->dentry = NULL;
+ }
+ mutex_unlock(&cfid->fid_mutex);
+ }
+
kill_anon_super(sb);
cifs_umount(cifs_sb);
}
@@ -626,6 +652,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
seq_printf(s, ",rsize=%u", cifs_sb->ctx->rsize);
seq_printf(s, ",wsize=%u", cifs_sb->ctx->wsize);
seq_printf(s, ",bsize=%u", cifs_sb->ctx->bsize);
+ if (cifs_sb->ctx->rasize)
+ seq_printf(s, ",rasize=%u", cifs_sb->ctx->rasize);
if (tcon->ses->server->min_offload)
seq_printf(s, ",esize=%u", tcon->ses->server->min_offload);
seq_printf(s, ",echo_interval=%lu",
@@ -656,10 +684,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
seq_printf(s, ",multichannel,max_channels=%zu",
tcon->ses->chan_max);
-#ifdef CONFIG_CIFS_SWN_UPCALL
if (tcon->use_witness)
seq_puts(s, ",witness");
-#endif
return 0;
}
@@ -834,6 +860,12 @@ cifs_smb3_do_mount(struct file_system_type *fs_type,
goto out;
}
+ /* cifs_setup_volume_info->smb3_parse_devname() redups UNC & prepath */
+ kfree(cifs_sb->ctx->UNC);
+ cifs_sb->ctx->UNC = NULL;
+ kfree(cifs_sb->ctx->prepath);
+ cifs_sb->ctx->prepath = NULL;
+
rc = cifs_setup_volume_info(cifs_sb->ctx, NULL, old_ctx->UNC);
if (rc) {
root = ERR_PTR(rc);
@@ -888,6 +920,9 @@ cifs_smb3_do_mount(struct file_system_type *fs_type,
if (IS_ERR(root))
goto out_super;
+ if (cifs_sb)
+ cifs_sb->root = dget(root);
+
cifs_dbg(FYI, "dentry root is: %p\n", root);
return root;
@@ -1528,10 +1563,6 @@ init_cifs(void)
int rc = 0;
cifs_proc_init();
INIT_LIST_HEAD(&cifs_tcp_ses_list);
-#ifdef CONFIG_CIFS_DNOTIFY_EXPERIMENTAL /* unused temporarily */
- INIT_LIST_HEAD(&GlobalDnotifyReqList);
- INIT_LIST_HEAD(&GlobalDnotifyRsp_Q);
-#endif /* was needed for dnotify, and will be needed for inotify when VFS fix */
/*
* Initialize Global counters
*/
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 0d7ef150dbb2..6beddb108ba0 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -165,5 +165,5 @@ extern struct dentry *cifs_smb3_do_mount(struct file_system_type *fs_type,
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.31"
+#define CIFS_VERSION "2.32"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index ec824ab8c5ca..b23a0ee8c6f8 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -495,7 +495,7 @@ struct smb_version_operations {
struct inode *inode,
struct dentry *dentry,
struct cifs_tcon *tcon,
- char *full_path,
+ const char *full_path,
umode_t mode,
dev_t device_number);
/* version specific fiemap implementation */
@@ -988,10 +988,12 @@ struct cached_fid {
bool is_valid:1; /* Do we have a useable root fid */
bool file_all_info_is_valid:1;
bool has_lease:1;
+ unsigned long time; /* jiffies of when lease was taken */
struct kref refcount;
struct cifs_fid *fid;
struct mutex fid_mutex;
struct cifs_tcon *tcon;
+ struct dentry *dentry;
struct work_struct lease_break;
struct smb2_file_all_info file_all_info;
};
@@ -1070,6 +1072,7 @@ struct cifs_tcon {
bool use_resilient:1; /* use resilient instead of durable handles */
bool use_persistent:1; /* use persistent instead of durable handles */
bool no_lease:1; /* Do not request leases on files or directories */
+ bool use_witness:1; /* use witness protocol */
__le32 capabilities;
__u32 share_flags;
__u32 maximal_access;
@@ -1094,9 +1097,6 @@ struct cifs_tcon {
int remap:2;
struct list_head ulist; /* cache update list */
#endif
-#ifdef CONFIG_CIFS_SWN_UPCALL
- bool use_witness:1; /* use witness protocol */
-#endif
};
/*
@@ -1316,8 +1316,6 @@ struct cifs_readdata {
struct page **pages;
};
-struct cifs_writedata;
-
/* asynchronous write support */
struct cifs_writedata {
struct kref refcount;
@@ -1796,9 +1794,8 @@ require use of the stronger protocol */
*
* Semaphores
* ----------
- * sesSem operations on smb session
- * tconSem operations on tree connection
- * fh_sem file handle reconnection operations
+ * cifsInodeInfo->lock_sem protects:
+ * the list of locks held by the inode
*
****************************************************************************/
@@ -1829,13 +1826,6 @@ GLOBAL_EXTERN struct list_head cifs_tcp_ses_list;
*/
GLOBAL_EXTERN spinlock_t cifs_tcp_ses_lock;
-#ifdef CONFIG_CIFS_DNOTIFY_EXPERIMENTAL /* unused temporarily */
-/* Outstanding dir notify requests */
-GLOBAL_EXTERN struct list_head GlobalDnotifyReqList;
-/* DirNotify response queue */
-GLOBAL_EXTERN struct list_head GlobalDnotifyRsp_Q;
-#endif /* was needed for dnotify, and will be needed for inotify when VFS fix */
-
/*
* Global transaction id (XID) information
*/
@@ -1879,19 +1869,9 @@ extern unsigned int cifs_min_small; /* min size of small buf pool */
extern unsigned int cifs_max_pending; /* MAX requests at once to server*/
extern bool disable_legacy_dialects; /* forbid vers=1.0 and vers=2.0 mounts */
-GLOBAL_EXTERN struct rb_root uidtree;
-GLOBAL_EXTERN struct rb_root gidtree;
-GLOBAL_EXTERN spinlock_t siduidlock;
-GLOBAL_EXTERN spinlock_t sidgidlock;
-GLOBAL_EXTERN struct rb_root siduidtree;
-GLOBAL_EXTERN struct rb_root sidgidtree;
-GLOBAL_EXTERN spinlock_t uidsidlock;
-GLOBAL_EXTERN spinlock_t gidsidlock;
-
void cifs_oplock_break(struct work_struct *work);
void cifs_queue_oplock_break(struct cifsFileInfo *cfile);
-extern const struct slow_work_ops cifs_oplock_break_ops;
extern struct workqueue_struct *cifsiod_wq;
extern struct workqueue_struct *decrypt_wq;
extern struct workqueue_struct *fileinfo_put_wq;
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index 9adc74bd9f8f..b53a87db282f 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -1903,7 +1903,7 @@ typedef struct smb_com_transaction2_fnext_req {
__le16 InformationLevel;
__u32 ResumeKey;
__le16 SearchFlags;
- char ResumeFileName[1];
+ char ResumeFileName[];
} __attribute__((packed)) TRANSACTION2_FNEXT_REQ;
typedef struct smb_com_transaction2_fnext_rsp {
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 75ce6f742b8d..c8faa3e82fe7 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -69,9 +69,20 @@ extern int init_cifs_idmap(void);
extern void exit_cifs_idmap(void);
extern int init_cifs_spnego(void);
extern void exit_cifs_spnego(void);
-extern char *build_path_from_dentry(struct dentry *);
+extern const char *build_path_from_dentry(struct dentry *, void *);
extern char *build_path_from_dentry_optional_prefix(struct dentry *direntry,
- bool prefix);
+ void *page, bool prefix);
+static inline void *alloc_dentry_path(void)
+{
+ return __getname();
+}
+
+static inline void free_dentry_path(void *page)
+{
+ if (page)
+ __putname(page);
+}
+
extern char *cifs_build_path_to_root(struct smb3_fs_context *ctx,
struct cifs_sb_info *cifs_sb,
struct cifs_tcon *tcon,
@@ -184,7 +195,7 @@ extern struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid,
struct file *file,
struct tcon_link *tlink,
__u32 oplock);
-extern int cifs_posix_open(char *full_path, struct inode **inode,
+extern int cifs_posix_open(const char *full_path, struct inode **inode,
struct super_block *sb, int mode,
unsigned int f_flags, __u32 *oplock, __u16 *netfid,
unsigned int xid);
@@ -207,7 +218,7 @@ extern int cifs_get_inode_info_unix(struct inode **pinode,
const unsigned char *search_path,
struct super_block *sb, unsigned int xid);
extern int cifs_set_file_info(struct inode *inode, struct iattr *attrs,
- unsigned int xid, char *full_path, __u32 dosattr);
+ unsigned int xid, const char *full_path, __u32 dosattr);
extern int cifs_rename_pending_delete(const char *full_path,
struct dentry *dentry,
const unsigned int xid);
@@ -358,11 +369,6 @@ extern int CIFSSMBSetFileDisposition(const unsigned int xid,
struct cifs_tcon *tcon,
bool delete_file, __u16 fid,
__u32 pid_of_opener);
-#if 0
-extern int CIFSSMBSetAttrLegacy(unsigned int xid, struct cifs_tcon *tcon,
- char *fileName, __u16 dos_attributes,
- const struct nls_table *nls_codepage);
-#endif /* possibly unneeded function */
extern int CIFSSMBSetEOF(const unsigned int xid, struct cifs_tcon *tcon,
const char *file_name, __u64 size,
struct cifs_sb_info *cifs_sb, bool set_allocation);
@@ -504,12 +510,6 @@ extern int generate_smb311signingkey(struct cifs_ses *);
extern int calc_lanman_hash(const char *password, const char *cryptkey,
bool encrypt, char *lnm_session_key);
#endif /* CIFS_WEAK_PW_HASH */
-#ifdef CONFIG_CIFS_DNOTIFY_EXPERIMENTAL /* unused temporarily */
-extern int CIFSSMBNotify(const unsigned int xid, struct cifs_tcon *tcon,
- const int notify_subdirs, const __u16 netfid,
- __u32 filter, struct file *file, int multishot,
- const struct nls_table *nls_codepage);
-#endif /* was needed for dnotify, and will be needed for inotify when VFS fix */
extern int CIFSSMBCopy(unsigned int xid,
struct cifs_tcon *source_tcon,
const char *fromName,
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index c279527aae92..41f74163cc1c 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -114,7 +114,7 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
mutex_lock(&tcon->crfid.fid_mutex);
tcon->crfid.is_valid = false;
/* cached handle is not valid, so SMB2_CLOSE won't be sent below */
- close_shroot_lease_locked(&tcon->crfid);
+ close_cached_dir_lease_locked(&tcon->crfid);
memset(tcon->crfid.fid, 0, sizeof(struct cifs_fid));
mutex_unlock(&tcon->crfid.fid_mutex);
@@ -5917,56 +5917,6 @@ SetTimesRetry:
return rc;
}
-/* Can not be used to set time stamps yet (due to old DOS time format) */
-/* Can be used to set attributes */
-#if 0 /* Possibly not needed - since it turns out that strangely NT4 has a bug
- handling it anyway and NT4 was what we thought it would be needed for
- Do not delete it until we prove whether needed for Win9x though */
-int
-CIFSSMBSetAttrLegacy(unsigned int xid, struct cifs_tcon *tcon, char *fileName,
- __u16 dos_attrs, const struct nls_table *nls_codepage)
-{
- SETATTR_REQ *pSMB = NULL;
- SETATTR_RSP *pSMBr = NULL;
- int rc = 0;
- int bytes_returned;
- int name_len;
-
- cifs_dbg(FYI, "In SetAttrLegacy\n");
-
-SetAttrLgcyRetry:
- rc = smb_init(SMB_COM_SETATTR, 8, tcon, (void **) &pSMB,
- (void **) &pSMBr);
- if (rc)
- return rc;
-
- if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
- name_len =
- ConvertToUTF16((__le16 *) pSMB->fileName, fileName,
- PATH_MAX, nls_codepage);
- name_len++; /* trailing null */
- name_len *= 2;
- } else {
- name_len = copy_path_name(pSMB->fileName, fileName);
- }
- pSMB->attr = cpu_to_le16(dos_attrs);
- pSMB->BufferFormat = 0x04;
- inc_rfc1001_len(pSMB, name_len + 1);
- pSMB->ByteCount = cpu_to_le16(name_len + 1);
- rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
- (struct smb_hdr *) pSMBr, &bytes_returned, 0);
- if (rc)
- cifs_dbg(FYI, "Error in LegacySetAttr = %d\n", rc);
-
- cifs_buf_release(pSMB);
-
- if (rc == -EAGAIN)
- goto SetAttrLgcyRetry;
-
- return rc;
-}
-#endif /* temporarily unneeded SetAttr legacy function */
-
static void
cifs_fill_unix_set_info(FILE_UNIX_BASIC_INFO *data_offset,
const struct cifs_unix_set_info_args *args)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 24668eb006c6..121d8b4535b0 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -62,9 +62,7 @@
#include "dfs_cache.h"
#endif
#include "fs_context.h"
-#ifdef CONFIG_CIFS_SWN_UPCALL
#include "cifs_swn.h"
-#endif
extern mempool_t *cifs_req_poolp;
extern bool disable_legacy_dialects;
@@ -314,12 +312,8 @@ cifs_reconnect(struct TCP_Server_Info *server)
mutex_lock(&server->srv_mutex);
-#ifdef CONFIG_CIFS_SWN_UPCALL
- if (server->use_swn_dstaddr) {
- server->dstaddr = server->swn_dstaddr;
- } else {
-#endif
+ if (!cifs_swn_set_server_dstaddr(server)) {
#ifdef CONFIG_CIFS_DFS_UPCALL
if (cifs_sb && cifs_sb->origin_fullpath)
/*
@@ -344,9 +338,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
#endif
-#ifdef CONFIG_CIFS_SWN_UPCALL
}
-#endif
if (cifs_rdma_enabled(server))
rc = smbd_reconnect(server);
@@ -363,9 +355,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
if (server->tcpStatus != CifsExiting)
server->tcpStatus = CifsNeedNegotiate;
spin_unlock(&GlobalMid_Lock);
-#ifdef CONFIG_CIFS_SWN_UPCALL
- server->use_swn_dstaddr = false;
-#endif
+ cifs_swn_reset_server_dstaddr(server);
mutex_unlock(&server->srv_mutex);
}
} while (server->tcpStatus == CifsNeedReconnect);
@@ -430,10 +420,8 @@ cifs_echo_request(struct work_struct *work)
cifs_dbg(FYI, "Unable to send echo request to server: %s\n",
server->hostname);
-#ifdef CONFIG_CIFS_SWN_UPCALL
/* Check witness registrations */
cifs_swn_check();
-#endif
requeue_echo:
queue_delayed_work(cifsiod_wq, &server->echo, server->echo_interval);
@@ -1790,9 +1778,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses)
* for the request.
*/
if (is_domain && ses->domainName) {
- ctx->domainname = kstrndup(ses->domainName,
- strlen(ses->domainName),
- GFP_KERNEL);
+ ctx->domainname = kstrdup(ses->domainName, GFP_KERNEL);
if (!ctx->domainname) {
cifs_dbg(FYI, "Unable to allocate %zd bytes for domain\n",
len);
@@ -2009,7 +1995,6 @@ cifs_put_tcon(struct cifs_tcon *tcon)
return;
}
-#ifdef CONFIG_CIFS_SWN_UPCALL
if (tcon->use_witness) {
int rc;
@@ -2019,7 +2004,6 @@ cifs_put_tcon(struct cifs_tcon *tcon)
__func__, rc);
}
}
-#endif
list_del_init(&tcon->tcon_list);
spin_unlock(&cifs_tcp_ses_lock);
@@ -2181,9 +2165,9 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
}
tcon->use_resilient = true;
}
-#ifdef CONFIG_CIFS_SWN_UPCALL
+
tcon->use_witness = false;
- if (ctx->witness) {
+ if (IS_ENABLED(CONFIG_CIFS_SWN_UPCALL) && ctx->witness) {
if (ses->server->vals->protocol_id >= SMB30_PROT_ID) {
if (tcon->capabilities & SMB2_SHARE_CAP_CLUSTER) {
/*
@@ -2209,7 +2193,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
goto out_fail;
}
}
-#endif
/* If the user really knows what they are doing they can override */
if (tcon->share_flags & SMB2_SHAREFLAG_NO_CACHING) {
@@ -3426,8 +3409,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
goto error;
}
/* Save mount options */
- mntdata = kstrndup(cifs_sb->ctx->mount_options,
- strlen(cifs_sb->ctx->mount_options), GFP_KERNEL);
+ mntdata = kstrdup(cifs_sb->ctx->mount_options, GFP_KERNEL);
if (!mntdata) {
rc = -ENOMEM;
goto error;
@@ -3500,7 +3482,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
* links, the prefix path is included in both and may be changed during reconnect. See
* cifs_tree_connect().
*/
- cifs_sb->origin_fullpath = kstrndup(full_path, strlen(full_path), GFP_KERNEL);
+ cifs_sb->origin_fullpath = kstrdup(full_path, GFP_KERNEL);
if (!cifs_sb->origin_fullpath) {
rc = -ENOMEM;
goto error;
@@ -3877,9 +3859,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
ctx->sectype = master_tcon->ses->sectype;
ctx->sign = master_tcon->ses->sign;
ctx->seal = master_tcon->seal;
-#ifdef CONFIG_CIFS_SWN_UPCALL
ctx->witness = master_tcon->use_witness;
-#endif
rc = cifs_set_vol_auth(ctx, master_tcon->ses);
if (rc) {
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 098b4bc8da59..b1fa30fefe1f 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -81,23 +81,24 @@ static void refresh_cache_worker(struct work_struct *work);
static DECLARE_DELAYED_WORK(refresh_task, refresh_cache_worker);
-static int get_normalized_path(const char *path, char **npath)
+static int get_normalized_path(const char *path, const char **npath)
{
if (!path || strlen(path) < 3 || (*path != '\\' && *path != '/'))
return -EINVAL;
if (*path == '\\') {
- *npath = (char *)path;
+ *npath = path;
} else {
- *npath = kstrndup(path, strlen(path), GFP_KERNEL);
- if (!*npath)
+ char *s = kstrdup(path, GFP_KERNEL);
+ if (!s)
return -ENOMEM;
- convert_delimiter(*npath, '\\');
+ convert_delimiter(s, '\\');
+ *npath = s;
}
return 0;
}
-static inline void free_normalized_path(const char *path, char *npath)
+static inline void free_normalized_path(const char *path, const char *npath)
{
if (path != npath)
kfree(npath);
@@ -358,7 +359,7 @@ static struct cache_dfs_tgt *alloc_target(const char *name, int path_consumed)
t = kmalloc(sizeof(*t), GFP_ATOMIC);
if (!t)
return ERR_PTR(-ENOMEM);
- t->name = kstrndup(name, strlen(name), GFP_ATOMIC);
+ t->name = kstrdup(name, GFP_ATOMIC);
if (!t->name) {
kfree(t);
return ERR_PTR(-ENOMEM);
@@ -419,7 +420,7 @@ static struct cache_entry *alloc_cache_entry(const char *path,
if (!ce)
return ERR_PTR(-ENOMEM);
- ce->path = kstrndup(path, strlen(path), GFP_KERNEL);
+ ce->path = kstrdup(path, GFP_KERNEL);
if (!ce->path) {
kmem_cache_free(cache_slab, ce);
return ERR_PTR(-ENOMEM);
@@ -531,7 +532,7 @@ static struct cache_entry *lookup_cache_entry(const char *path, unsigned int *ha
char *s, *e;
char sep;
- npath = kstrndup(path, strlen(path), GFP_KERNEL);
+ npath = kstrdup(path, GFP_KERNEL);
if (!npath)
return ERR_PTR(-ENOMEM);
@@ -641,7 +642,7 @@ static int __update_cache_entry(const char *path,
if (ce->tgthint) {
s = ce->tgthint->name;
- th = kstrndup(s, strlen(s), GFP_ATOMIC);
+ th = kstrdup(s, GFP_ATOMIC);
if (!th)
return -ENOMEM;
}
@@ -786,11 +787,11 @@ static int setup_referral(const char *path, struct cache_entry *ce,
memset(ref, 0, sizeof(*ref));
- ref->path_name = kstrndup(path, strlen(path), GFP_ATOMIC);
+ ref->path_name = kstrdup(path, GFP_ATOMIC);
if (!ref->path_name)
return -ENOMEM;
- ref->node_name = kstrndup(target, strlen(target), GFP_ATOMIC);
+ ref->node_name = kstrdup(target, GFP_ATOMIC);
if (!ref->node_name) {
rc = -ENOMEM;
goto err_free_path;
@@ -828,7 +829,7 @@ static int get_targets(struct cache_entry *ce, struct dfs_cache_tgt_list *tl)
goto err_free_it;
}
- it->it_name = kstrndup(t->name, strlen(t->name), GFP_ATOMIC);
+ it->it_name = kstrdup(t->name, GFP_ATOMIC);
if (!it->it_name) {
kfree(it);
rc = -ENOMEM;
@@ -882,7 +883,7 @@ int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses,
struct dfs_cache_tgt_list *tgt_list)
{
int rc;
- char *npath;
+ const char *npath;
struct cache_entry *ce;
rc = get_normalized_path(path, &npath);
@@ -936,7 +937,7 @@ int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref,
struct dfs_cache_tgt_list *tgt_list)
{
int rc;
- char *npath;
+ const char *npath;
struct cache_entry *ce;
rc = get_normalized_path(path, &npath);
@@ -991,7 +992,7 @@ int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses,
const struct dfs_cache_tgt_iterator *it)
{
int rc;
- char *npath;
+ const char *npath;
struct cache_entry *ce;
struct cache_dfs_tgt *t;
@@ -1053,7 +1054,7 @@ int dfs_cache_noreq_update_tgthint(const char *path,
const struct dfs_cache_tgt_iterator *it)
{
int rc;
- char *npath;
+ const char *npath;
struct cache_entry *ce;
struct cache_dfs_tgt *t;
@@ -1111,7 +1112,7 @@ int dfs_cache_get_tgt_referral(const char *path,
struct dfs_info3_param *ref)
{
int rc;
- char *npath;
+ const char *npath;
struct cache_entry *ce;
if (!it || !ref)
@@ -1166,7 +1167,7 @@ int dfs_cache_add_vol(char *mntdata, struct smb3_fs_context *ctx, const char *fu
if (!vi)
return -ENOMEM;
- vi->fullpath = kstrndup(fullpath, strlen(fullpath), GFP_KERNEL);
+ vi->fullpath = kstrdup(fullpath, GFP_KERNEL);
if (!vi->fullpath) {
rc = -ENOMEM;
goto err_free_vi;
@@ -1484,7 +1485,7 @@ static int refresh_tcon(struct vol_info *vi, struct cifs_tcon *tcon)
{
int rc = 0;
unsigned int xid;
- char *path, *npath;
+ const char *path, *npath;
struct cache_entry *ce;
struct cifs_ses *root_ses = NULL, *ses;
struct dfs_info3_param *refs = NULL;
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index a3fb81e0ba17..03afad8b24af 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -78,31 +78,31 @@ cifs_build_path_to_root(struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_s
}
/* Note: caller must free return buffer */
-char *
-build_path_from_dentry(struct dentry *direntry)
+const char *
+build_path_from_dentry(struct dentry *direntry, void *page)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
bool prefix = tcon->Flags & SMB_SHARE_IS_IN_DFS;
- return build_path_from_dentry_optional_prefix(direntry,
+ return build_path_from_dentry_optional_prefix(direntry, page,
prefix);
}
char *
-build_path_from_dentry_optional_prefix(struct dentry *direntry, bool prefix)
+build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page,
+ bool prefix)
{
- struct dentry *temp;
- int namelen;
int dfsplen;
int pplen = 0;
- char *full_path;
- char dirsep;
struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
- unsigned seq;
+ char dirsep = CIFS_DIR_SEP(cifs_sb);
+ char *s;
+
+ if (unlikely(!page))
+ return ERR_PTR(-ENOMEM);
- dirsep = CIFS_DIR_SEP(cifs_sb);
if (prefix)
dfsplen = strnlen(tcon->treeName, MAX_TREE_SIZE + 1);
else
@@ -111,86 +111,39 @@ build_path_from_dentry_optional_prefix(struct dentry *direntry, bool prefix)
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
pplen = cifs_sb->prepath ? strlen(cifs_sb->prepath) + 1 : 0;
-cifs_bp_rename_retry:
- namelen = dfsplen + pplen;
- seq = read_seqbegin(&rename_lock);
- rcu_read_lock();
- for (temp = direntry; !IS_ROOT(temp);) {
- namelen += (1 + temp->d_name.len);
- temp = temp->d_parent;
- if (temp == NULL) {
- cifs_dbg(VFS, "corrupt dentry\n");
- rcu_read_unlock();
- return NULL;
- }
- }
- rcu_read_unlock();
-
- full_path = kmalloc(namelen+1, GFP_ATOMIC);
- if (full_path == NULL)
- return full_path;
- full_path[namelen] = 0; /* trailing null */
- rcu_read_lock();
- for (temp = direntry; !IS_ROOT(temp);) {
- spin_lock(&temp->d_lock);
- namelen -= 1 + temp->d_name.len;
- if (namelen < 0) {
- spin_unlock(&temp->d_lock);
- break;
- } else {
- full_path[namelen] = dirsep;
- strncpy(full_path + namelen + 1, temp->d_name.name,
- temp->d_name.len);
- cifs_dbg(FYI, "name: %s\n", full_path + namelen);
- }
- spin_unlock(&temp->d_lock);
- temp = temp->d_parent;
- if (temp == NULL) {
- cifs_dbg(VFS, "corrupt dentry\n");
- rcu_read_unlock();
- kfree(full_path);
- return NULL;
- }
- }
- rcu_read_unlock();
- if (namelen != dfsplen + pplen || read_seqretry(&rename_lock, seq)) {
- cifs_dbg(FYI, "did not end path lookup where expected. namelen=%ddfsplen=%d\n",
- namelen, dfsplen);
- /* presumably this is only possible if racing with a rename
- of one of the parent directories (we can not lock the dentries
- above us to prevent this, but retrying should be harmless) */
- kfree(full_path);
- goto cifs_bp_rename_retry;
- }
- /* DIR_SEP already set for byte 0 / vs \ but not for
- subsequent slashes in prepath which currently must
- be entered the right way - not sure if there is an alternative
- since the '\' is a valid posix character so we can not switch
- those safely to '/' if any are found in the middle of the prepath */
- /* BB test paths to Windows with '/' in the midst of prepath */
-
+ s = dentry_path_raw(direntry, page, PAGE_SIZE);
+ if (IS_ERR(s))
+ return s;
+ if (!s[1]) // for root we want "", not "/"
+ s++;
+ if (s < (char *)page + pplen + dfsplen)
+ return ERR_PTR(-ENAMETOOLONG);
if (pplen) {
- int i;
-
cifs_dbg(FYI, "using cifs_sb prepath <%s>\n", cifs_sb->prepath);
- memcpy(full_path+dfsplen+1, cifs_sb->prepath, pplen-1);
- full_path[dfsplen] = dirsep;
- for (i = 0; i < pplen-1; i++)
- if (full_path[dfsplen+1+i] == '/')
- full_path[dfsplen+1+i] = CIFS_DIR_SEP(cifs_sb);
+ s -= pplen;
+ memcpy(s + 1, cifs_sb->prepath, pplen - 1);
+ *s = '/';
}
+ if (dirsep != '/') {
+ /* BB test paths to Windows with '/' in the midst of prepath */
+ char *p;
+ for (p = s; *p; p++)
+ if (*p == '/')
+ *p = dirsep;
+ }
if (dfsplen) {
- strncpy(full_path, tcon->treeName, dfsplen);
+ s -= dfsplen;
+ memcpy(s, tcon->treeName, dfsplen);
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) {
int i;
for (i = 0; i < dfsplen; i++) {
- if (full_path[i] == '\\')
- full_path[i] = '/';
+ if (s[i] == '\\')
+ s[i] = '/';
}
}
}
- return full_path;
+ return s;
}
/*
@@ -233,7 +186,8 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
int desired_access;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifs_tcon *tcon = tlink_tcon(tlink);
- char *full_path = NULL;
+ const char *full_path;
+ void *page = alloc_dentry_path();
FILE_ALL_INFO *buf = NULL;
struct inode *newinode = NULL;
int disposition;
@@ -244,9 +198,11 @@ cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int xid,
if (tcon->ses->server->oplocks)
*oplock = REQ_OPLOCK;
- full_path = build_path_from_dentry(direntry);
- if (!full_path)
- return -ENOMEM;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ free_dentry_path(page);
+ return PTR_ERR(full_path);
+ }
if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open &&
(CIFS_UNIX_POSIX_PATH_OPS_CAP &
@@ -448,7 +404,7 @@ cifs_create_set_dentry:
out:
kfree(buf);
- kfree(full_path);
+ free_dentry_path(page);
return rc;
out_err:
@@ -619,7 +575,8 @@ int cifs_mknod(struct user_namespace *mnt_userns, struct inode *inode,
struct cifs_sb_info *cifs_sb;
struct tcon_link *tlink;
struct cifs_tcon *tcon;
- char *full_path = NULL;
+ const char *full_path;
+ void *page;
if (!old_valid_dev(device_number))
return -EINVAL;
@@ -629,13 +586,13 @@ int cifs_mknod(struct user_namespace *mnt_userns, struct inode *inode,
if (IS_ERR(tlink))
return PTR_ERR(tlink);
+ page = alloc_dentry_path();
tcon = tlink_tcon(tlink);
-
xid = get_xid();
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto mknod_out;
}
@@ -644,7 +601,7 @@ int cifs_mknod(struct user_namespace *mnt_userns, struct inode *inode,
device_number);
mknod_out:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
@@ -660,7 +617,8 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
struct inode *newInode = NULL;
- char *full_path = NULL;
+ const char *full_path;
+ void *page;
xid = get_xid();
@@ -687,11 +645,13 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
/* can not grab the rename sem here since it would
deadlock in the cases (beginning of sys_rename itself)
in which we already have the sb rename sem */
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
+ page = alloc_dentry_path();
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
cifs_put_tlink(tlink);
free_xid(xid);
- return ERR_PTR(-ENOMEM);
+ free_dentry_path(page);
+ return ERR_CAST(full_path);
}
if (d_really_is_positive(direntry)) {
@@ -727,7 +687,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
}
newInode = ERR_PTR(rc);
}
- kfree(full_path);
+ free_dentry_path(page);
cifs_put_tlink(tlink);
free_xid(xid);
return d_splice_alias(newInode, direntry);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 042e24aad410..3d4e6e7dac1d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -112,7 +112,7 @@ static inline int cifs_get_disposition(unsigned int flags)
return FILE_OPEN;
}
-int cifs_posix_open(char *full_path, struct inode **pinode,
+int cifs_posix_open(const char *full_path, struct inode **pinode,
struct super_block *sb, int mode, unsigned int f_flags,
__u32 *poplock, __u16 *pnetfid, unsigned int xid)
{
@@ -175,7 +175,7 @@ posix_open_ret:
}
static int
-cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb,
+cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb,
struct cifs_tcon *tcon, unsigned int f_flags, __u32 *oplock,
struct cifs_fid *fid, unsigned int xid)
{
@@ -530,7 +530,8 @@ int cifs_open(struct inode *inode, struct file *file)
struct cifs_tcon *tcon;
struct tcon_link *tlink;
struct cifsFileInfo *cfile = NULL;
- char *full_path = NULL;
+ void *page;
+ const char *full_path;
bool posix_open_ok = false;
struct cifs_fid fid;
struct cifs_pending_open open;
@@ -546,9 +547,10 @@ int cifs_open(struct inode *inode, struct file *file)
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
- full_path = build_path_from_dentry(file_dentry(file));
- if (full_path == NULL) {
- rc = -ENOMEM;
+ page = alloc_dentry_path();
+ full_path = build_path_from_dentry(file_dentry(file), page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto out;
}
@@ -640,7 +642,7 @@ int cifs_open(struct inode *inode, struct file *file)
}
out:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
@@ -689,7 +691,8 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
struct TCP_Server_Info *server;
struct cifsInodeInfo *cinode;
struct inode *inode;
- char *full_path = NULL;
+ void *page;
+ const char *full_path;
int desired_access;
int disposition = FILE_OPEN;
int create_options = CREATE_NOT_DIR;
@@ -699,9 +702,8 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
mutex_lock(&cfile->fh_mutex);
if (!cfile->invalidHandle) {
mutex_unlock(&cfile->fh_mutex);
- rc = 0;
free_xid(xid);
- return rc;
+ return 0;
}
inode = d_inode(cfile->dentry);
@@ -715,12 +717,13 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
* called and if the server was down that means we end up here, and we
* can never tell if the caller already has the rename_sem.
*/
- full_path = build_path_from_dentry(cfile->dentry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ page = alloc_dentry_path();
+ full_path = build_path_from_dentry(cfile->dentry, page);
+ if (IS_ERR(full_path)) {
mutex_unlock(&cfile->fh_mutex);
+ free_dentry_path(page);
free_xid(xid);
- return rc;
+ return PTR_ERR(full_path);
}
cifs_dbg(FYI, "inode = 0x%p file flags 0x%x for %s\n",
@@ -838,7 +841,7 @@ reopen_success:
cifs_relock_file(cfile);
reopen_error_exit:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
return rc;
}
@@ -2069,34 +2072,31 @@ cifs_get_writable_path(struct cifs_tcon *tcon, const char *name,
int flags,
struct cifsFileInfo **ret_file)
{
- struct list_head *tmp;
struct cifsFileInfo *cfile;
- struct cifsInodeInfo *cinode;
- char *full_path;
+ void *page = alloc_dentry_path();
*ret_file = NULL;
spin_lock(&tcon->open_file_lock);
- list_for_each(tmp, &tcon->openFileList) {
- cfile = list_entry(tmp, struct cifsFileInfo,
- tlist);
- full_path = build_path_from_dentry(cfile->dentry);
- if (full_path == NULL) {
+ list_for_each_entry(cfile, &tcon->openFileList, tlist) {
+ struct cifsInodeInfo *cinode;
+ const char *full_path = build_path_from_dentry(cfile->dentry, page);
+ if (IS_ERR(full_path)) {
spin_unlock(&tcon->open_file_lock);
- return -ENOMEM;
+ free_dentry_path(page);
+ return PTR_ERR(full_path);
}
- if (strcmp(full_path, name)) {
- kfree(full_path);
+ if (strcmp(full_path, name))
continue;
- }
- kfree(full_path);
cinode = CIFS_I(d_inode(cfile->dentry));
spin_unlock(&tcon->open_file_lock);
+ free_dentry_path(page);
return cifs_get_writable_file(cinode, flags, ret_file);
}
spin_unlock(&tcon->open_file_lock);
+ free_dentry_path(page);
return -ENOENT;
}
@@ -2104,35 +2104,32 @@ int
cifs_get_readable_path(struct cifs_tcon *tcon, const char *name,
struct cifsFileInfo **ret_file)
{
- struct list_head *tmp;
struct cifsFileInfo *cfile;
- struct cifsInodeInfo *cinode;
- char *full_path;
+ void *page = alloc_dentry_path();
*ret_file = NULL;
spin_lock(&tcon->open_file_lock);
- list_for_each(tmp, &tcon->openFileList) {
- cfile = list_entry(tmp, struct cifsFileInfo,
- tlist);
- full_path = build_path_from_dentry(cfile->dentry);
- if (full_path == NULL) {
+ list_for_each_entry(cfile, &tcon->openFileList, tlist) {
+ struct cifsInodeInfo *cinode;
+ const char *full_path = build_path_from_dentry(cfile->dentry, page);
+ if (IS_ERR(full_path)) {
spin_unlock(&tcon->open_file_lock);
- return -ENOMEM;
+ free_dentry_path(page);
+ return PTR_ERR(full_path);
}
- if (strcmp(full_path, name)) {
- kfree(full_path);
+ if (strcmp(full_path, name))
continue;
- }
- kfree(full_path);
cinode = CIFS_I(d_inode(cfile->dentry));
spin_unlock(&tcon->open_file_lock);
+ free_dentry_path(page);
*ret_file = find_readable_file(cinode, 0);
return *ret_file ? 0 : -ENOENT;
}
spin_unlock(&tcon->open_file_lock);
+ free_dentry_path(page);
return -ENOENT;
}
diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c
index 78889024a7ed..3e0d016849e3 100644
--- a/fs/cifs/fs_context.c
+++ b/fs/cifs/fs_context.c
@@ -137,6 +137,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
fsparam_u32("min_enc_offload", Opt_min_enc_offload),
fsparam_u32("esize", Opt_min_enc_offload),
fsparam_u32("bsize", Opt_blocksize),
+ fsparam_u32("rasize", Opt_rasize),
fsparam_u32("rsize", Opt_rsize),
fsparam_u32("wsize", Opt_wsize),
fsparam_u32("actimeo", Opt_actimeo),
@@ -188,8 +189,8 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
{}
};
-int
-cifs_parse_security_flavors(char *value, struct smb3_fs_context *ctx)
+static int
+cifs_parse_security_flavors(struct fs_context *fc, char *value, struct smb3_fs_context *ctx)
{
substring_t args[MAX_OPT_ARGS];
@@ -203,7 +204,7 @@ cifs_parse_security_flavors(char *value, struct smb3_fs_context *ctx)
switch (match_token(value, cifs_secflavor_tokens, args)) {
case Opt_sec_krb5p:
- cifs_dbg(VFS, "sec=krb5p is not supported!\n");
+ cifs_errorf(fc, "sec=krb5p is not supported!\n");
return 1;
case Opt_sec_krb5i:
ctx->sign = true;
@@ -238,7 +239,7 @@ cifs_parse_security_flavors(char *value, struct smb3_fs_context *ctx)
ctx->nullauth = 1;
break;
default:
- cifs_dbg(VFS, "bad security option: %s\n", value);
+ cifs_errorf(fc, "bad security option: %s\n", value);
return 1;
}
@@ -254,8 +255,8 @@ static const match_table_t cifs_cacheflavor_tokens = {
{ Opt_cache_err, NULL }
};
-int
-cifs_parse_cache_flavor(char *value, struct smb3_fs_context *ctx)
+static int
+cifs_parse_cache_flavor(struct fs_context *fc, char *value, struct smb3_fs_context *ctx)
{
substring_t args[MAX_OPT_ARGS];
@@ -291,7 +292,7 @@ cifs_parse_cache_flavor(char *value, struct smb3_fs_context *ctx)
ctx->cache_rw = true;
break;
default:
- cifs_dbg(VFS, "bad cache= option: %s\n", value);
+ cifs_errorf(fc, "bad cache= option: %s\n", value);
return 1;
}
return 0;
@@ -339,7 +340,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx
}
static int
-cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3)
+cifs_parse_smb_version(struct fs_context *fc, char *value, struct smb3_fs_context *ctx, bool is_smb3)
{
substring_t args[MAX_OPT_ARGS];
@@ -347,24 +348,24 @@ cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3)
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
case Smb_1:
if (disable_legacy_dialects) {
- cifs_dbg(VFS, "mount with legacy dialect disabled\n");
+ cifs_errorf(fc, "mount with legacy dialect disabled\n");
return 1;
}
if (is_smb3) {
- cifs_dbg(VFS, "vers=1.0 (cifs) not permitted when mounting with smb3\n");
+ cifs_errorf(fc, "vers=1.0 (cifs) not permitted when mounting with smb3\n");
return 1;
}
- cifs_dbg(VFS, "Use of the less secure dialect vers=1.0 is not recommended unless required for access to very old servers\n");
+ cifs_errorf(fc, "Use of the less secure dialect vers=1.0 is not recommended unless required for access to very old servers\n");
ctx->ops = &smb1_operations;
ctx->vals = &smb1_values;
break;
case Smb_20:
if (disable_legacy_dialects) {
- cifs_dbg(VFS, "mount with legacy dialect disabled\n");
+ cifs_errorf(fc, "mount with legacy dialect disabled\n");
return 1;
}
if (is_smb3) {
- cifs_dbg(VFS, "vers=2.0 not permitted when mounting with smb3\n");
+ cifs_errorf(fc, "vers=2.0 not permitted when mounting with smb3\n");
return 1;
}
ctx->ops = &smb20_operations;
@@ -372,10 +373,10 @@ cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3)
break;
#else
case Smb_1:
- cifs_dbg(VFS, "vers=1.0 (cifs) mount not permitted when legacy dialects disabled\n");
+ cifs_errorf(fc, "vers=1.0 (cifs) mount not permitted when legacy dialects disabled\n");
return 1;
case Smb_20:
- cifs_dbg(VFS, "vers=2.0 mount not permitted when legacy dialects disabled\n");
+ cifs_errorf(fc, "vers=2.0 mount not permitted when legacy dialects disabled\n");
return 1;
#endif /* CIFS_ALLOW_INSECURE_LEGACY */
case Smb_21:
@@ -403,7 +404,7 @@ cifs_parse_smb_version(char *value, struct smb3_fs_context *ctx, bool is_smb3)
ctx->vals = &smbdefault_values;
break;
default:
- cifs_dbg(VFS, "Unknown vers= option specified: %s\n", value);
+ cifs_errorf(fc, "Unknown vers= option specified: %s\n", value);
return 1;
}
return 0;
@@ -430,7 +431,7 @@ int smb3_parse_opt(const char *options, const char *key, char **val)
if (nval == p)
continue;
*nval++ = 0;
- *val = kstrndup(nval, strlen(nval), GFP_KERNEL);
+ *val = kstrdup(nval, GFP_KERNEL);
rc = !*val ? -ENOMEM : 0;
goto out;
}
@@ -588,14 +589,14 @@ static int smb3_fs_context_validate(struct fs_context *fc)
struct smb3_fs_context *ctx = smb3_fc2context(fc);
if (ctx->rdma && ctx->vals->protocol_id < SMB30_PROT_ID) {
- cifs_dbg(VFS, "SMB Direct requires Version >=3.0\n");
+ cifs_errorf(fc, "SMB Direct requires Version >=3.0\n");
return -EOPNOTSUPP;
}
#ifndef CONFIG_KEYS
/* Muliuser mounts require CONFIG_KEYS support */
if (ctx->multiuser) {
- cifs_dbg(VFS, "Multiuser mounts require kernels with CONFIG_KEYS enabled\n");
+ cifs_errorf(fc, "Multiuser mounts require kernels with CONFIG_KEYS enabled\n");
return -1;
}
#endif
@@ -605,13 +606,13 @@ static int smb3_fs_context_validate(struct fs_context *fc)
if (!ctx->UNC) {
- cifs_dbg(VFS, "CIFS mount error: No usable UNC path provided in device string!\n");
+ cifs_errorf(fc, "CIFS mount error: No usable UNC path provided in device string!\n");
return -1;
}
/* make sure UNC has a share name */
if (strlen(ctx->UNC) < 3 || !strchr(ctx->UNC + 3, '\\')) {
- cifs_dbg(VFS, "Malformed UNC. Unable to find share name.\n");
+ cifs_errorf(fc, "Malformed UNC. Unable to find share name.\n");
return -ENOENT;
}
@@ -684,49 +685,50 @@ static void smb3_fs_context_free(struct fs_context *fc)
* Compare the old and new proposed context during reconfigure
* and check if the changes are compatible.
*/
-static int smb3_verify_reconfigure_ctx(struct smb3_fs_context *new_ctx,
+static int smb3_verify_reconfigure_ctx(struct fs_context *fc,
+ struct smb3_fs_context *new_ctx,
struct smb3_fs_context *old_ctx)
{
if (new_ctx->posix_paths != old_ctx->posix_paths) {
- cifs_dbg(VFS, "can not change posixpaths during remount\n");
+ cifs_errorf(fc, "can not change posixpaths during remount\n");
return -EINVAL;
}
if (new_ctx->sectype != old_ctx->sectype) {
- cifs_dbg(VFS, "can not change sec during remount\n");
+ cifs_errorf(fc, "can not change sec during remount\n");
return -EINVAL;
}
if (new_ctx->multiuser != old_ctx->multiuser) {
- cifs_dbg(VFS, "can not change multiuser during remount\n");
+ cifs_errorf(fc, "can not change multiuser during remount\n");
return -EINVAL;
}
if (new_ctx->UNC &&
(!old_ctx->UNC || strcmp(new_ctx->UNC, old_ctx->UNC))) {
- cifs_dbg(VFS, "can not change UNC during remount\n");
+ cifs_errorf(fc, "can not change UNC during remount\n");
return -EINVAL;
}
if (new_ctx->username &&
(!old_ctx->username || strcmp(new_ctx->username, old_ctx->username))) {
- cifs_dbg(VFS, "can not change username during remount\n");
+ cifs_errorf(fc, "can not change username during remount\n");
return -EINVAL;
}
if (new_ctx->password &&
(!old_ctx->password || strcmp(new_ctx->password, old_ctx->password))) {
- cifs_dbg(VFS, "can not change password during remount\n");
+ cifs_errorf(fc, "can not change password during remount\n");
return -EINVAL;
}
if (new_ctx->domainname &&
(!old_ctx->domainname || strcmp(new_ctx->domainname, old_ctx->domainname))) {
- cifs_dbg(VFS, "can not change domainname during remount\n");
+ cifs_errorf(fc, "can not change domainname during remount\n");
return -EINVAL;
}
if (new_ctx->nodename &&
(!old_ctx->nodename || strcmp(new_ctx->nodename, old_ctx->nodename))) {
- cifs_dbg(VFS, "can not change nodename during remount\n");
+ cifs_errorf(fc, "can not change nodename during remount\n");
return -EINVAL;
}
if (new_ctx->iocharset &&
(!old_ctx->iocharset || strcmp(new_ctx->iocharset, old_ctx->iocharset))) {
- cifs_dbg(VFS, "can not change iocharset during remount\n");
+ cifs_errorf(fc, "can not change iocharset during remount\n");
return -EINVAL;
}
@@ -747,7 +749,7 @@ static int smb3_reconfigure(struct fs_context *fc)
struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb);
int rc;
- rc = smb3_verify_reconfigure_ctx(ctx, cifs_sb->ctx);
+ rc = smb3_verify_reconfigure_ctx(fc, ctx, cifs_sb->ctx);
if (rc)
return rc;
@@ -933,13 +935,33 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
*/
if ((result.uint_32 < CIFS_MAX_MSGSIZE) ||
(result.uint_32 > (4 * SMB3_DEFAULT_IOSIZE))) {
- cifs_dbg(VFS, "%s: Invalid blocksize\n",
+ cifs_errorf(fc, "%s: Invalid blocksize\n",
__func__);
goto cifs_parse_mount_err;
}
ctx->bsize = result.uint_32;
ctx->got_bsize = true;
break;
+ case Opt_rasize:
+ /*
+ * readahead size realistically should never need to be
+ * less than 1M (CIFS_DEFAULT_IOSIZE) or greater than 32M
+ * (perhaps an exception should be considered in the
+ * for the case of a large number of channels
+ * when multichannel is negotiated) since that would lead
+ * to plenty of parallel I/O in flight to the server.
+ * Note that smaller read ahead sizes would
+ * hurt performance of common tools like cp and scp
+ * which often trigger sequential i/o with read ahead
+ */
+ if ((result.uint_32 > (8 * SMB3_DEFAULT_IOSIZE)) ||
+ (result.uint_32 < CIFS_DEFAULT_IOSIZE)) {
+ cifs_errorf(fc, "%s: Invalid rasize %d vs. %d\n",
+ __func__, result.uint_32, SMB3_DEFAULT_IOSIZE);
+ goto cifs_parse_mount_err;
+ }
+ ctx->rasize = result.uint_32;
+ break;
case Opt_rsize:
ctx->rsize = result.uint_32;
ctx->got_rsize = true;
@@ -951,25 +973,25 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
case Opt_acregmax:
ctx->acregmax = HZ * result.uint_32;
if (ctx->acregmax > CIFS_MAX_ACTIMEO) {
- cifs_dbg(VFS, "acregmax too large\n");
+ cifs_errorf(fc, "acregmax too large\n");
goto cifs_parse_mount_err;
}
break;
case Opt_acdirmax:
ctx->acdirmax = HZ * result.uint_32;
if (ctx->acdirmax > CIFS_MAX_ACTIMEO) {
- cifs_dbg(VFS, "acdirmax too large\n");
+ cifs_errorf(fc, "acdirmax too large\n");
goto cifs_parse_mount_err;
}
break;
case Opt_actimeo:
if (HZ * result.uint_32 > CIFS_MAX_ACTIMEO) {
- cifs_dbg(VFS, "timeout too large\n");
+ cifs_errorf(fc, "timeout too large\n");
goto cifs_parse_mount_err;
}
if ((ctx->acdirmax != CIFS_DEF_ACTIMEO) ||
(ctx->acregmax != CIFS_DEF_ACTIMEO)) {
- cifs_dbg(VFS, "actimeo ignored since acregmax or acdirmax specified\n");
+ cifs_errorf(fc, "actimeo ignored since acregmax or acdirmax specified\n");
break;
}
ctx->acdirmax = ctx->acregmax = HZ * result.uint_32;
@@ -982,7 +1004,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
break;
case Opt_max_credits:
if (result.uint_32 < 20 || result.uint_32 > 60000) {
- cifs_dbg(VFS, "%s: Invalid max_credits value\n",
+ cifs_errorf(fc, "%s: Invalid max_credits value\n",
__func__);
goto cifs_parse_mount_err;
}
@@ -990,7 +1012,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
break;
case Opt_max_channels:
if (result.uint_32 < 1 || result.uint_32 > CIFS_MAX_CHANNELS) {
- cifs_dbg(VFS, "%s: Invalid max_channels value, needs to be 1-%d\n",
+ cifs_errorf(fc, "%s: Invalid max_channels value, needs to be 1-%d\n",
__func__, CIFS_MAX_CHANNELS);
goto cifs_parse_mount_err;
}
@@ -999,7 +1021,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
case Opt_handletimeout:
ctx->handle_timeout = result.uint_32;
if (ctx->handle_timeout > SMB3_MAX_HANDLE_TIMEOUT) {
- cifs_dbg(VFS, "Invalid handle cache timeout, longer than 16 minutes\n");
+ cifs_errorf(fc, "Invalid handle cache timeout, longer than 16 minutes\n");
goto cifs_parse_mount_err;
}
break;
@@ -1010,23 +1032,23 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
case 0:
break;
case -ENOMEM:
- cifs_dbg(VFS, "Unable to allocate memory for devname\n");
+ cifs_errorf(fc, "Unable to allocate memory for devname\n");
goto cifs_parse_mount_err;
case -EINVAL:
- cifs_dbg(VFS, "Malformed UNC in devname\n");
+ cifs_errorf(fc, "Malformed UNC in devname\n");
goto cifs_parse_mount_err;
default:
- cifs_dbg(VFS, "Unknown error parsing devname\n");
+ cifs_errorf(fc, "Unknown error parsing devname\n");
goto cifs_parse_mount_err;
}
ctx->source = kstrdup(param->string, GFP_KERNEL);
if (ctx->source == NULL) {
- cifs_dbg(VFS, "OOM when copying UNC string\n");
+ cifs_errorf(fc, "OOM when copying UNC string\n");
goto cifs_parse_mount_err;
}
fc->source = kstrdup(param->string, GFP_KERNEL);
if (fc->source == NULL) {
- cifs_dbg(VFS, "OOM when copying UNC string\n");
+ cifs_errorf(fc, "OOM when copying UNC string\n");
goto cifs_parse_mount_err;
}
break;
@@ -1046,7 +1068,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
}
ctx->username = kstrdup(param->string, GFP_KERNEL);
if (ctx->username == NULL) {
- cifs_dbg(VFS, "OOM when copying username string\n");
+ cifs_errorf(fc, "OOM when copying username string\n");
goto cifs_parse_mount_err;
}
break;
@@ -1058,7 +1080,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
ctx->password = kstrdup(param->string, GFP_KERNEL);
if (ctx->password == NULL) {
- cifs_dbg(VFS, "OOM when copying password string\n");
+ cifs_errorf(fc, "OOM when copying password string\n");
goto cifs_parse_mount_err;
}
break;
@@ -1085,7 +1107,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
kfree(ctx->domainname);
ctx->domainname = kstrdup(param->string, GFP_KERNEL);
if (ctx->domainname == NULL) {
- cifs_dbg(VFS, "OOM when copying domainname string\n");
+ cifs_errorf(fc, "OOM when copying domainname string\n");
goto cifs_parse_mount_err;
}
cifs_dbg(FYI, "Domain name set\n");
@@ -1109,7 +1131,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
kfree(ctx->iocharset);
ctx->iocharset = kstrdup(param->string, GFP_KERNEL);
if (ctx->iocharset == NULL) {
- cifs_dbg(VFS, "OOM when copying iocharset string\n");
+ cifs_errorf(fc, "OOM when copying iocharset string\n");
goto cifs_parse_mount_err;
}
}
@@ -1175,21 +1197,21 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
goto cifs_parse_mount_err;
case Opt_vers:
/* protocol version (dialect) */
- if (cifs_parse_smb_version(param->string, ctx, is_smb3) != 0)
+ if (cifs_parse_smb_version(fc, param->string, ctx, is_smb3) != 0)
goto cifs_parse_mount_err;
ctx->got_version = true;
break;
case Opt_sec:
- if (cifs_parse_security_flavors(param->string, ctx) != 0)
+ if (cifs_parse_security_flavors(fc, param->string, ctx) != 0)
goto cifs_parse_mount_err;
break;
case Opt_cache:
- if (cifs_parse_cache_flavor(param->string, ctx) != 0)
+ if (cifs_parse_cache_flavor(fc, param->string, ctx) != 0)
goto cifs_parse_mount_err;
break;
case Opt_witness:
#ifndef CONFIG_CIFS_SWN_UPCALL
- cifs_dbg(VFS, "Witness support needs CONFIG_CIFS_SWN_UPCALL config option\n");
+ cifs_errorf(fc, "Witness support needs CONFIG_CIFS_SWN_UPCALL config option\n");
goto cifs_parse_mount_err;
#endif
ctx->witness = true;
@@ -1290,7 +1312,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
break;
case Opt_fsc:
#ifndef CONFIG_CIFS_FSCACHE
- cifs_dbg(VFS, "FS-Cache support needs CONFIG_CIFS_FSCACHE kernel config option set\n");
+ cifs_errorf(fc, "FS-Cache support needs CONFIG_CIFS_FSCACHE kernel config option set\n");
goto cifs_parse_mount_err;
#endif
ctx->fsc = true;
@@ -1311,15 +1333,13 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
if (result.negated) {
ctx->nopersistent = true;
if (ctx->persistent) {
- cifs_dbg(VFS,
- "persistenthandles mount options conflict\n");
+ cifs_errorf(fc, "persistenthandles mount options conflict\n");
goto cifs_parse_mount_err;
}
} else {
ctx->persistent = true;
if ((ctx->nopersistent) || (ctx->resilient)) {
- cifs_dbg(VFS,
- "persistenthandles mount options conflict\n");
+ cifs_errorf(fc, "persistenthandles mount options conflict\n");
goto cifs_parse_mount_err;
}
}
@@ -1330,8 +1350,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
} else {
ctx->resilient = true;
if (ctx->persistent) {
- cifs_dbg(VFS,
- "persistenthandles mount options conflict\n");
+ cifs_errorf(fc, "persistenthandles mount options conflict\n");
goto cifs_parse_mount_err;
}
}
@@ -1379,7 +1398,9 @@ int smb3_init_fs_context(struct fs_context *fc)
ctx->cred_uid = current_uid();
ctx->linux_uid = current_uid();
ctx->linux_gid = current_gid();
- ctx->bsize = 1024 * 1024; /* can improve cp performance significantly */
+ /* By default 4MB read ahead size, 1MB block size */
+ ctx->bsize = CIFS_DEFAULT_IOSIZE; /* can improve cp performance significantly */
+ ctx->rasize = 0; /* 0 = use default (ie negotiated rsize) for read ahead pages */
/*
* default to SFM style remapping of seven reserved characters
diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h
index 87dd1f7168f2..2a71c8e411ac 100644
--- a/fs/cifs/fs_context.h
+++ b/fs/cifs/fs_context.h
@@ -13,7 +13,12 @@
#include <linux/parser.h>
#include <linux/fs_parser.h>
-#define cifs_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__)
+/* Log errors in fs_context (new mount api) but also in dmesg (old style) */
+#define cifs_errorf(fc, fmt, ...) \
+ do { \
+ errorf(fc, fmt, ## __VA_ARGS__); \
+ cifs_dbg(VFS, fmt, ## __VA_ARGS__); \
+ } while (0)
enum smb_version {
Smb_1 = 1,
@@ -115,6 +120,7 @@ enum cifs_param {
Opt_dirmode,
Opt_min_enc_offload,
Opt_blocksize,
+ Opt_rasize,
Opt_rsize,
Opt_wsize,
Opt_actimeo,
@@ -230,6 +236,7 @@ struct smb3_fs_context {
/* reuse existing guid for multichannel */
u8 client_guid[SMB2_CLIENT_GUID_SIZE];
unsigned int bsize;
+ unsigned int rasize;
unsigned int rsize;
unsigned int wsize;
unsigned int min_offload;
@@ -257,10 +264,6 @@ struct smb3_fs_context {
extern const struct fs_parameter_spec smb3_fs_parameters[];
-extern int cifs_parse_cache_flavor(char *value,
- struct smb3_fs_context *ctx);
-extern int cifs_parse_security_flavors(char *value,
- struct smb3_fs_context *ctx);
extern int smb3_init_fs_context(struct fs_context *fc);
extern void smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx);
extern void smb3_cleanup_fs_context(struct smb3_fs_context *ctx);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index f2df4422e54a..a0846f788436 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1408,7 +1408,7 @@ out:
int
cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid,
- char *full_path, __u32 dosattr)
+ const char *full_path, __u32 dosattr)
{
bool set_time = false;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
@@ -1609,7 +1609,8 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry)
{
int rc = 0;
unsigned int xid;
- char *full_path = NULL;
+ const char *full_path;
+ void *page;
struct inode *inode = d_inode(dentry);
struct cifsInodeInfo *cifs_inode;
struct super_block *sb = dir->i_sb;
@@ -1629,6 +1630,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry)
server = tcon->ses->server;
xid = get_xid();
+ page = alloc_dentry_path();
if (tcon->nodelete) {
rc = -EACCES;
@@ -1637,9 +1639,9 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry)
/* Unlink can be called from rename so we can not take the
* sb->s_vfs_rename_mutex here */
- full_path = build_path_from_dentry(dentry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto unlink_out;
}
@@ -1713,7 +1715,7 @@ out_reval:
cifs_inode = CIFS_I(dir);
CIFS_I(dir)->time = 0; /* force revalidate of dir as well */
unlink_out:
- kfree(full_path);
+ free_dentry_path(page);
kfree(attrs);
free_xid(xid);
cifs_put_tlink(tlink);
@@ -1866,7 +1868,8 @@ int cifs_mkdir(struct user_namespace *mnt_userns, struct inode *inode,
struct tcon_link *tlink;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
- char *full_path;
+ const char *full_path;
+ void *page;
cifs_dbg(FYI, "In cifs_mkdir, mode = %04ho inode = 0x%p\n",
mode, inode);
@@ -1879,9 +1882,10 @@ int cifs_mkdir(struct user_namespace *mnt_userns, struct inode *inode,
xid = get_xid();
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ page = alloc_dentry_path();
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto mkdir_out;
}
@@ -1924,7 +1928,7 @@ mkdir_out:
* attributes are invalid now.
*/
CIFS_I(inode)->time = 0;
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
@@ -1938,16 +1942,17 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
struct tcon_link *tlink;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
- char *full_path = NULL;
+ const char *full_path;
+ void *page = alloc_dentry_path();
struct cifsInodeInfo *cifsInode;
cifs_dbg(FYI, "cifs_rmdir, inode = 0x%p\n", inode);
xid = get_xid();
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto rmdir_exit;
}
@@ -1997,7 +2002,7 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
current_time(inode);
rmdir_exit:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
return rc;
}
@@ -2072,8 +2077,8 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir,
struct dentry *source_dentry, struct inode *target_dir,
struct dentry *target_dentry, unsigned int flags)
{
- char *from_name = NULL;
- char *to_name = NULL;
+ const char *from_name, *to_name;
+ void *page1, *page2;
struct cifs_sb_info *cifs_sb;
struct tcon_link *tlink;
struct cifs_tcon *tcon;
@@ -2091,21 +2096,19 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir,
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
+ page1 = alloc_dentry_path();
+ page2 = alloc_dentry_path();
xid = get_xid();
- /*
- * we already have the rename sem so we do not need to
- * grab it again here to protect the path integrity
- */
- from_name = build_path_from_dentry(source_dentry);
- if (from_name == NULL) {
- rc = -ENOMEM;
+ from_name = build_path_from_dentry(source_dentry, page1);
+ if (IS_ERR(from_name)) {
+ rc = PTR_ERR(from_name);
goto cifs_rename_exit;
}
- to_name = build_path_from_dentry(target_dentry);
- if (to_name == NULL) {
- rc = -ENOMEM;
+ to_name = build_path_from_dentry(target_dentry, page2);
+ if (IS_ERR(to_name)) {
+ rc = PTR_ERR(to_name);
goto cifs_rename_exit;
}
@@ -2177,18 +2180,21 @@ unlink_target:
cifs_rename_exit:
kfree(info_buf_source);
- kfree(from_name);
- kfree(to_name);
+ free_dentry_path(page2);
+ free_dentry_path(page1);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
}
static bool
-cifs_inode_needs_reval(struct inode *inode)
+cifs_dentry_needs_reval(struct dentry *dentry)
{
+ struct inode *inode = d_inode(dentry);
struct cifsInodeInfo *cifs_i = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+ struct cached_fid *cfid = NULL;
if (cifs_i->time == 0)
return true;
@@ -2199,6 +2205,16 @@ cifs_inode_needs_reval(struct inode *inode)
if (!lookupCacheEnabled)
return true;
+ if (!open_cached_dir_by_dentry(tcon, dentry->d_parent, &cfid)) {
+ mutex_lock(&cfid->fid_mutex);
+ if (cfid->time && cifs_i->time > cfid->time) {
+ mutex_unlock(&cfid->fid_mutex);
+ close_cached_dir(cfid);
+ return false;
+ }
+ mutex_unlock(&cfid->fid_mutex);
+ close_cached_dir(cfid);
+ }
/*
* depending on inode type, check if attribute caching disabled for
* files or directories
@@ -2297,10 +2313,10 @@ cifs_zap_mapping(struct inode *inode)
int cifs_revalidate_file_attr(struct file *filp)
{
int rc = 0;
- struct inode *inode = file_inode(filp);
+ struct dentry *dentry = file_dentry(filp);
struct cifsFileInfo *cfile = (struct cifsFileInfo *) filp->private_data;
- if (!cifs_inode_needs_reval(inode))
+ if (!cifs_dentry_needs_reval(dentry))
return rc;
if (tlink_tcon(cfile->tlink)->unix_ext)
@@ -2317,22 +2333,22 @@ int cifs_revalidate_dentry_attr(struct dentry *dentry)
int rc = 0;
struct inode *inode = d_inode(dentry);
struct super_block *sb = dentry->d_sb;
- char *full_path = NULL;
+ const char *full_path;
+ void *page;
int count = 0;
if (inode == NULL)
return -ENOENT;
- if (!cifs_inode_needs_reval(inode))
+ if (!cifs_dentry_needs_reval(dentry))
return rc;
xid = get_xid();
- /* can not safely grab the rename sem here if rename calls revalidate
- since that would deadlock */
- full_path = build_path_from_dentry(dentry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ page = alloc_dentry_path();
+ full_path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto out;
}
@@ -2351,7 +2367,7 @@ again:
if (rc == -EAGAIN && count++ < 10)
goto again;
out:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
return rc;
@@ -2522,7 +2538,7 @@ void cifs_setsize(struct inode *inode, loff_t offset)
static int
cifs_set_file_size(struct inode *inode, struct iattr *attrs,
- unsigned int xid, char *full_path)
+ unsigned int xid, const char *full_path)
{
int rc;
struct cifsFileInfo *open_file;
@@ -2613,7 +2629,8 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
{
int rc;
unsigned int xid;
- char *full_path = NULL;
+ const char *full_path;
+ void *page = alloc_dentry_path();
struct inode *inode = d_inode(direntry);
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
@@ -2634,9 +2651,9 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
if (rc < 0)
goto out;
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto out;
}
@@ -2748,7 +2765,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
cifsInode->time = 0;
out:
kfree(args);
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
return rc;
}
@@ -2764,7 +2781,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
struct cifsFileInfo *wfile;
struct cifs_tcon *tcon;
- char *full_path = NULL;
+ const char *full_path;
+ void *page = alloc_dentry_path();
int rc = -EACCES;
__u32 dosattr = 0;
__u64 mode = NO_CHANGE_64;
@@ -2778,16 +2796,13 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
attrs->ia_valid |= ATTR_FORCE;
rc = setattr_prepare(&init_user_ns, direntry, attrs);
- if (rc < 0) {
- free_xid(xid);
- return rc;
- }
+ if (rc < 0)
+ goto cifs_setattr_exit;
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
- free_xid(xid);
- return rc;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
+ goto cifs_setattr_exit;
}
/*
@@ -2937,8 +2952,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
mark_inode_dirty(inode);
cifs_setattr_exit:
- kfree(full_path);
free_xid(xid);
+ free_dentry_path(page);
return rc;
}
@@ -2961,12 +2976,3 @@ cifs_setattr(struct user_namespace *mnt_userns, struct dentry *direntry,
/* BB: add cifs_setattr_legacy for really old servers */
return rc;
}
-
-#if 0
-void cifs_delete_inode(struct inode *inode)
-{
- cifs_dbg(FYI, "In cifs_delete_inode, inode = 0x%p\n", inode);
- /* may have to add back in if and when safe distributed caching of
- directories added e.g. via FindNotify */
-}
-#endif
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index dcde44ff6cf9..08d99fec593e 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -42,13 +42,16 @@ static long cifs_ioctl_query_info(unsigned int xid, struct file *filep,
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
struct dentry *dentry = filep->f_path.dentry;
- unsigned char *path;
+ const unsigned char *path;
+ void *page = alloc_dentry_path();
__le16 *utf16_path = NULL, root_path;
int rc = 0;
- path = build_path_from_dentry(dentry);
- if (path == NULL)
- return -ENOMEM;
+ path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(path)) {
+ free_dentry_path(page);
+ return PTR_ERR(path);
+ }
cifs_dbg(FYI, "%s %s\n", __func__, path);
@@ -73,7 +76,7 @@ static long cifs_ioctl_query_info(unsigned int xid, struct file *filep,
ici_exit:
if (utf16_path != &root_path)
kfree(utf16_path);
- kfree(path);
+ free_dentry_path(page);
return rc;
}
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 7c5878a645d9..616e1bc0cc0a 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -510,8 +510,8 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
{
int rc = -EACCES;
unsigned int xid;
- char *from_name = NULL;
- char *to_name = NULL;
+ const char *from_name, *to_name;
+ void *page1, *page2;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink;
struct cifs_tcon *tcon;
@@ -524,11 +524,17 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
tcon = tlink_tcon(tlink);
xid = get_xid();
+ page1 = alloc_dentry_path();
+ page2 = alloc_dentry_path();
- from_name = build_path_from_dentry(old_file);
- to_name = build_path_from_dentry(direntry);
- if ((from_name == NULL) || (to_name == NULL)) {
- rc = -ENOMEM;
+ from_name = build_path_from_dentry(old_file, page1);
+ if (IS_ERR(from_name)) {
+ rc = PTR_ERR(from_name);
+ goto cifs_hl_exit;
+ }
+ to_name = build_path_from_dentry(direntry, page2);
+ if (IS_ERR(to_name)) {
+ rc = PTR_ERR(to_name);
goto cifs_hl_exit;
}
@@ -587,8 +593,8 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
}
cifs_hl_exit:
- kfree(from_name);
- kfree(to_name);
+ free_dentry_path(page1);
+ free_dentry_path(page2);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
@@ -600,7 +606,8 @@ cifs_get_link(struct dentry *direntry, struct inode *inode,
{
int rc = -ENOMEM;
unsigned int xid;
- char *full_path = NULL;
+ const char *full_path;
+ void *page;
char *target_path = NULL;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink = NULL;
@@ -620,11 +627,13 @@ cifs_get_link(struct dentry *direntry, struct inode *inode,
tcon = tlink_tcon(tlink);
server = tcon->ses->server;
- full_path = build_path_from_dentry(direntry);
- if (!full_path) {
+ page = alloc_dentry_path();
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
free_xid(xid);
cifs_put_tlink(tlink);
- return ERR_PTR(-ENOMEM);
+ free_dentry_path(page);
+ return ERR_CAST(full_path);
}
cifs_dbg(FYI, "Full path: %s inode = 0x%p\n", full_path, inode);
@@ -649,7 +658,7 @@ cifs_get_link(struct dentry *direntry, struct inode *inode,
&target_path, reparse_point);
}
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
if (rc != 0) {
@@ -669,7 +678,8 @@ cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode,
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- char *full_path = NULL;
+ const char *full_path;
+ void *page = alloc_dentry_path();
struct inode *newinode = NULL;
xid = get_xid();
@@ -681,9 +691,9 @@ cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode,
}
pTcon = tlink_tcon(tlink);
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto symlink_exit;
}
@@ -719,7 +729,7 @@ cifs_symlink(struct user_namespace *mnt_userns, struct inode *inode,
}
}
symlink_exit:
- kfree(full_path);
+ free_dentry_path(page);
cifs_put_tlink(tlink);
free_xid(xid);
return rc;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 82e176720ca6..c15a90e422be 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -1180,7 +1180,7 @@ int update_super_prepath(struct cifs_tcon *tcon, char *prefix)
kfree(cifs_sb->prepath);
if (prefix && *prefix) {
- cifs_sb->prepath = kstrndup(prefix, strlen(prefix), GFP_ATOMIC);
+ cifs_sb->prepath = kstrdup(prefix, GFP_ATOMIC);
if (!cifs_sb->prepath) {
rc = -ENOMEM;
goto out;
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 80bf4c6f4c7b..7531e8905881 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -384,7 +384,7 @@ int get_symlink_reparse_path(char *full_path, struct cifs_sb_info *cifs_sb,
static int
initiate_cifs_search(const unsigned int xid, struct file *file,
- char *full_path)
+ const char *full_path)
{
__u16 search_flags;
int rc = 0;
@@ -704,7 +704,7 @@ static int cifs_save_resume_key(const char *current_entry,
*/
static int
find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos,
- struct file *file, char *full_path,
+ struct file *file, const char *full_path,
char **current_entry, int *num_to_ret)
{
__u16 search_flags;
@@ -942,13 +942,14 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
char *tmp_buf = NULL;
char *end_of_smb;
unsigned int max_len;
- char *full_path = NULL;
+ const char *full_path;
+ void *page = alloc_dentry_path();
xid = get_xid();
- full_path = build_path_from_dentry(file_dentry(file));
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(file_dentry(file), page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto rddir2_exit;
}
@@ -1043,7 +1044,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
kfree(tmp_buf);
rddir2_exit:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
return rc;
}
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index e31b939e628c..3b83839fc2c2 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -926,9 +926,7 @@ cifs_unix_dfs_readlink(const unsigned int xid, struct cifs_tcon *tcon,
0);
if (!rc) {
- *symlinkinfo = kstrndup(referral.node_name,
- strlen(referral.node_name),
- GFP_KERNEL);
+ *symlinkinfo = kstrdup(referral.node_name, GFP_KERNEL);
free_dfs_info_param(&referral);
if (!*symlinkinfo)
rc = -ENOMEM;
@@ -1027,7 +1025,7 @@ cifs_can_echo(struct TCP_Server_Info *server)
static int
cifs_make_node(unsigned int xid, struct inode *inode,
struct dentry *dentry, struct cifs_tcon *tcon,
- char *full_path, umode_t mode, dev_t dev)
+ const char *full_path, umode_t mode, dev_t dev)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct inode *newinode = NULL;
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index a718dc77e604..9a61209a283e 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -512,7 +512,6 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
int rc;
struct smb2_file_all_info *smb2_data;
__u32 create_options = 0;
- bool no_cached_open = tcon->nohandlecache;
struct cifsFileInfo *cfile;
struct cached_fid *cfid = NULL;
@@ -525,11 +524,8 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
return -ENOMEM;
/* If it is a root and its handle is cached then use it */
- if (!strlen(full_path) && !no_cached_open) {
- rc = open_shroot(xid, tcon, cifs_sb, &cfid);
- if (rc)
- goto out;
-
+ rc = open_cached_dir(xid, tcon, full_path, cifs_sb, &cfid);
+ if (!rc) {
if (tcon->crfid.file_all_info_is_valid) {
move_smb2_info_to_cifs(data,
&tcon->crfid.file_all_info);
@@ -540,7 +536,7 @@ smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
if (!rc)
move_smb2_info_to_cifs(data, smb2_data);
}
- close_shroot(cfid);
+ close_cached_dir(cfid);
goto out;
}
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index aac384f69f74..06d555d4da9a 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -667,6 +667,7 @@ smb2_is_valid_lease_break(char *buffer)
!memcmp(rsp->LeaseKey,
tcon->crfid.fid->lease_key,
SMB2_LEASE_KEY_SIZE)) {
+ tcon->crfid.time = 0;
INIT_WORK(&tcon->crfid.lease_break,
smb2_cached_lease_break);
queue_work(cifsiod_wq,
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index f703204fb185..dd0eb665b680 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -690,17 +690,21 @@ smb2_close_cached_fid(struct kref *ref)
cfid->is_valid = false;
cfid->file_all_info_is_valid = false;
cfid->has_lease = false;
+ if (cfid->dentry) {
+ dput(cfid->dentry);
+ cfid->dentry = NULL;
+ }
}
}
-void close_shroot(struct cached_fid *cfid)
+void close_cached_dir(struct cached_fid *cfid)
{
mutex_lock(&cfid->fid_mutex);
kref_put(&cfid->refcount, smb2_close_cached_fid);
mutex_unlock(&cfid->fid_mutex);
}
-void close_shroot_lease_locked(struct cached_fid *cfid)
+void close_cached_dir_lease_locked(struct cached_fid *cfid)
{
if (cfid->has_lease) {
cfid->has_lease = false;
@@ -708,10 +712,10 @@ void close_shroot_lease_locked(struct cached_fid *cfid)
}
}
-void close_shroot_lease(struct cached_fid *cfid)
+void close_cached_dir_lease(struct cached_fid *cfid)
{
mutex_lock(&cfid->fid_mutex);
- close_shroot_lease_locked(cfid);
+ close_cached_dir_lease_locked(cfid);
mutex_unlock(&cfid->fid_mutex);
}
@@ -721,13 +725,15 @@ smb2_cached_lease_break(struct work_struct *work)
struct cached_fid *cfid = container_of(work,
struct cached_fid, lease_break);
- close_shroot_lease(cfid);
+ close_cached_dir_lease(cfid);
}
/*
- * Open the directory at the root of a share
+ * Open the and cache a directory handle.
+ * Only supported for the root handle.
*/
-int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
+int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
+ const char *path,
struct cifs_sb_info *cifs_sb,
struct cached_fid **cfid)
{
@@ -745,6 +751,18 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
__le16 utf16_path = 0; /* Null - since an open of top of share */
u8 oplock = SMB2_OPLOCK_LEVEL_II;
struct cifs_fid *pfid;
+ struct dentry *dentry;
+
+ if (tcon->nohandlecache)
+ return -ENOTSUPP;
+
+ if (cifs_sb->root == NULL)
+ return -ENOENT;
+
+ if (strlen(path))
+ return -ENOENT;
+
+ dentry = cifs_sb->root;
mutex_lock(&tcon->crfid.fid_mutex);
if (tcon->crfid.is_valid) {
@@ -830,11 +848,9 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
};
/*
- * caller expects this func to set pfid to a valid
- * cached root, so we copy the existing one and get a
- * reference.
+ * caller expects this func to set the fid in crfid to valid
+ * cached root, so increment the refcount.
*/
- memcpy(pfid, tcon->crfid.fid, sizeof(*pfid));
kref_get(&tcon->crfid.refcount);
mutex_unlock(&tcon->crfid.fid_mutex);
@@ -867,13 +883,18 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
oparms.fid->mid = le64_to_cpu(o_rsp->sync_hdr.MessageId);
#endif /* CIFS_DEBUG2 */
- memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid));
tcon->crfid.tcon = tcon;
tcon->crfid.is_valid = true;
+ tcon->crfid.dentry = dentry;
+ dget(dentry);
kref_init(&tcon->crfid.refcount);
/* BB TBD check to see if oplock level check can be removed below */
if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) {
+ /*
+ * See commit 2f94a3125b87. Increment the refcount when we
+ * get a lease for root, release it if lease break occurs
+ */
kref_get(&tcon->crfid.refcount);
tcon->crfid.has_lease = true;
smb2_parse_contexts(server, o_rsp,
@@ -892,6 +913,8 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
&rsp_iov[1], sizeof(struct smb2_file_all_info),
(char *)&tcon->crfid.file_all_info))
tcon->crfid.file_all_info_is_valid = true;
+ tcon->crfid.time = jiffies;
+
oshr_exit:
mutex_unlock(&tcon->crfid.fid_mutex);
@@ -905,6 +928,22 @@ oshr_free:
return rc;
}
+int open_cached_dir_by_dentry(struct cifs_tcon *tcon,
+ struct dentry *dentry,
+ struct cached_fid **cfid)
+{
+ mutex_lock(&tcon->crfid.fid_mutex);
+ if (tcon->crfid.dentry == dentry) {
+ cifs_dbg(FYI, "found a cached root file handle by dentry\n");
+ *cfid = &tcon->crfid;
+ kref_get(&tcon->crfid.refcount);
+ mutex_unlock(&tcon->crfid.fid_mutex);
+ return 0;
+ }
+ mutex_unlock(&tcon->crfid.fid_mutex);
+ return -ENOENT;
+}
+
static void
smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon,
struct cifs_sb_info *cifs_sb)
@@ -914,7 +953,6 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon,
u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
struct cifs_open_parms oparms;
struct cifs_fid fid;
- bool no_cached_open = tcon->nohandlecache;
struct cached_fid *cfid = NULL;
oparms.tcon = tcon;
@@ -924,14 +962,12 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon,
oparms.fid = &fid;
oparms.reconnect = false;
- if (no_cached_open) {
+ rc = open_cached_dir(xid, tcon, "", cifs_sb, &cfid);
+ if (rc == 0)
+ memcpy(&fid, cfid->fid, sizeof(struct cifs_fid));
+ else
rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL,
NULL, NULL);
- } else {
- rc = open_shroot(xid, tcon, cifs_sb, &cfid);
- if (rc == 0)
- memcpy(&fid, cfid->fid, sizeof(struct cifs_fid));
- }
if (rc)
return;
@@ -945,10 +981,10 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon,
FS_VOLUME_INFORMATION);
SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
FS_SECTOR_SIZE_INFORMATION); /* SMB3 specific */
- if (no_cached_open)
+ if (cfid == NULL)
SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
else
- close_shroot(cfid);
+ close_cached_dir(cfid);
}
static void
@@ -1531,7 +1567,10 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon,
NULL, 0 /* no input */, CIFSMaxBufSize,
(char **)&res_key, &ret_data_len);
- if (rc) {
+ if (rc == -EOPNOTSUPP) {
+ pr_warn_once("Server share %s does not support copy range\n", tcon->treeName);
+ goto req_res_key_exit;
+ } else if (rc) {
cifs_tcon_dbg(VFS, "refcpy ioctl error %d getting resume key\n", rc);
goto req_res_key_exit;
}
@@ -1763,18 +1802,14 @@ smb2_ioctl_query_info(const unsigned int xid,
}
iqinf_exit:
- kfree(vars);
- kfree(buffer);
- SMB2_open_free(&rqst[0]);
- if (qi.flags & PASSTHRU_FSCTL)
- SMB2_ioctl_free(&rqst[1]);
- else
- SMB2_query_info_free(&rqst[1]);
-
- SMB2_close_free(&rqst[2]);
+ cifs_small_buf_release(rqst[0].rq_iov[0].iov_base);
+ cifs_small_buf_release(rqst[1].rq_iov[0].iov_base);
+ cifs_small_buf_release(rqst[2].rq_iov[0].iov_base);
free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base);
free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base);
+ kfree(vars);
+ kfree(buffer);
return rc;
e_fault:
@@ -2217,22 +2252,23 @@ smb3_notify(const unsigned int xid, struct file *pfile,
struct smb3_notify notify;
struct dentry *dentry = pfile->f_path.dentry;
struct inode *inode = file_inode(pfile);
- struct cifs_sb_info *cifs_sb;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct cifs_open_parms oparms;
struct cifs_fid fid;
struct cifs_tcon *tcon;
- unsigned char *path = NULL;
+ const unsigned char *path;
+ void *page = alloc_dentry_path();
__le16 *utf16_path = NULL;
u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
int rc = 0;
- path = build_path_from_dentry(dentry);
- if (path == NULL)
- return -ENOMEM;
-
- cifs_sb = CIFS_SB(inode->i_sb);
+ path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(path)) {
+ rc = PTR_ERR(path);
+ goto notify_exit;
+ }
- utf16_path = cifs_convert_path_to_utf16(path + 1, cifs_sb);
+ utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
if (utf16_path == NULL) {
rc = -ENOMEM;
goto notify_exit;
@@ -2264,7 +2300,7 @@ smb3_notify(const unsigned int xid, struct file *pfile,
cifs_dbg(FYI, "change notify for path %s rc %d\n", path, rc);
notify_exit:
- kfree(path);
+ free_dentry_path(page);
kfree(utf16_path);
return rc;
}
@@ -3652,6 +3688,77 @@ out:
return rc;
}
+static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon,
+ loff_t off, loff_t len)
+{
+ int rc;
+ unsigned int xid;
+ struct cifsFileInfo *cfile = file->private_data;
+ __le64 eof;
+
+ xid = get_xid();
+
+ if (off >= i_size_read(file->f_inode) ||
+ off + len >= i_size_read(file->f_inode)) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ rc = smb2_copychunk_range(xid, cfile, cfile, off + len,
+ i_size_read(file->f_inode) - off - len, off);
+ if (rc < 0)
+ goto out;
+
+ eof = cpu_to_le64(i_size_read(file->f_inode) - len);
+ rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
+ cfile->fid.volatile_fid, cfile->pid, &eof);
+ if (rc < 0)
+ goto out;
+
+ rc = 0;
+ out:
+ free_xid(xid);
+ return rc;
+}
+
+static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon,
+ loff_t off, loff_t len)
+{
+ int rc;
+ unsigned int xid;
+ struct cifsFileInfo *cfile = file->private_data;
+ __le64 eof;
+ __u64 count;
+
+ xid = get_xid();
+
+ if (off >= i_size_read(file->f_inode)) {
+ rc = -EINVAL;
+ goto out;
+ }
+
+ count = i_size_read(file->f_inode) - off;
+ eof = cpu_to_le64(i_size_read(file->f_inode) + len);
+
+ rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
+ cfile->fid.volatile_fid, cfile->pid, &eof);
+ if (rc < 0)
+ goto out;
+
+ rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len);
+ if (rc < 0)
+ goto out;
+
+ rc = smb3_zero_range(file, tcon, off, len, 1);
+ if (rc < 0)
+ goto out;
+
+ rc = 0;
+ out:
+ free_xid(xid);
+ return rc;
+}
+
static loff_t smb3_llseek(struct file *file, struct cifs_tcon *tcon, loff_t offset, int whence)
{
struct cifsFileInfo *wrcfile, *cfile = file->private_data;
@@ -3823,6 +3930,10 @@ static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode,
return smb3_zero_range(file, tcon, off, len, false);
} else if (mode == FALLOC_FL_KEEP_SIZE)
return smb3_simple_falloc(file, tcon, off, len, true);
+ else if (mode == FALLOC_FL_COLLAPSE_RANGE)
+ return smb3_collapse_range(file, tcon, off, len);
+ else if (mode == FALLOC_FL_INSERT_RANGE)
+ return smb3_insert_range(file, tcon, off, len);
else if (mode == 0)
return smb3_simple_falloc(file, tcon, off, len, false);
@@ -4178,7 +4289,7 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
}
spin_unlock(&cifs_tcp_ses_lock);
- return 1;
+ return -EAGAIN;
}
/*
* Encrypt or decrypt @rqst message. @rqst[0] has the following format:
@@ -4968,7 +5079,7 @@ smb2_next_header(char *buf)
static int
smb2_make_node(unsigned int xid, struct inode *inode,
struct dentry *dentry, struct cifs_tcon *tcon,
- char *full_path, umode_t mode, dev_t dev)
+ const char *full_path, umode_t mode, dev_t dev)
{
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
int rc = -EPERM;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 2199a9bfae8f..e36c2a867783 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1857,7 +1857,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
if ((tcon->need_reconnect) || (tcon->ses->need_reconnect))
return 0;
- close_shroot_lease(&tcon->crfid);
+ close_cached_dir_lease(&tcon->crfid);
rc = smb2_plain_req_init(SMB2_TREE_DISCONNECT, tcon, ses->server,
(void **) &req,
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index a5a9e33c0d73..6442dc1c292b 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -144,7 +144,7 @@ struct smb2_transform_hdr {
} __packed;
/* See MS-SMB2 2.2.42 */
-struct smb2_compression_transform_hdr {
+struct smb2_compression_transform_hdr_unchained {
__le32 ProtocolId; /* 0xFC 'S' 'M' 'B' */
__le32 OriginalCompressedSegmentSize;
__le16 CompressionAlgorithm;
@@ -160,10 +160,17 @@ struct compression_payload_header {
__le16 CompressionAlgorithm;
__le16 Flags;
__le32 Length; /* length of compressed playload including field below if present */
- /* __le32 OriginalPayloadSize; */ /* optional */
+ /* __le32 OriginalPayloadSize; */ /* optional, present when LZNT1, LZ77, LZ77+Huffman */
} __packed;
/* See MS-SMB2 2.2.42.2 */
+struct smb2_compression_transform_hdr_chained {
+ __le32 ProtocolId; /* 0xFC 'S' 'M' 'B' */
+ __le32 OriginalCompressedSegmentSize;
+ /* struct compression_payload_header[] */
+} __packed;
+
+/* See MS-SMB2 2.2.42.2.2 */
struct compression_pattern_payload_v1 {
__le16 Pattern;
__le16 Reserved1;
@@ -181,7 +188,11 @@ struct smb2_rdma_transform {
__le32 Reserved2;
} __packed;
-struct smb2_rdma_encryption_transform {
+/* TransformType */
+#define SMB2_RDMA_TRANSFORM_TYPE_ENCRYPTION 0x0001
+#define SMB2_RDMA_TRANSFORM_TYPE_SIGNING 0x0002
+
+struct smb2_rdma_crypto_transform {
__le16 TransformType;
__le16 SignatureLength;
__le16 NonceLength;
@@ -409,13 +420,29 @@ struct smb2_netname_neg_context {
} __packed;
/*
- * For rdma transform capabilities context see MS-SMB2 2.2.3.1.6
+ * For smb2_transport_capabilities context see MS-SMB2 2.2.3.1.5
* and 2.2.4.1.5
*/
+/* Flags */
+#define SMB2_ACCEPT_TRANSFORM_LEVEL_SECURITY 0x00000001
+
+struct smb2_transport_capabilities_context {
+ __le16 ContextType; /* 6 */
+ __le16 DataLength;
+ __u32 Reserved;
+ __le32 Flags;
+} __packed;
+
+/*
+ * For rdma transform capabilities context see MS-SMB2 2.2.3.1.6
+ * and 2.2.4.1.6
+ */
+
/* RDMA Transform IDs */
#define SMB2_RDMA_TRANSFORM_NONE 0x0000
#define SMB2_RDMA_TRANSFORM_ENCRYPTION 0x0001
+#define SMB2_RDMA_TRANSFORM_SIGNING 0x0002
struct smb2_rdma_transform_capabilities_context {
__le16 ContextType; /* 7 */
@@ -427,6 +454,11 @@ struct smb2_rdma_transform_capabilities_context {
__le16 RDMATransformIds[];
} __packed;
+/*
+ * For signing capabilities context see MS-SMB2 2.2.3.1.7
+ * and 2.2.4.1.7
+ */
+
/* Signing algorithms */
#define SIGNING_ALG_HMAC_SHA256 0
#define SIGNING_ALG_AES_CMAC 1
@@ -634,7 +666,8 @@ struct smb2_tree_connect_rsp {
#define SHI1005_FLAGS_ENABLE_HASH_V2 0x00004000
#define SHI1005_FLAGS_ENCRYPT_DATA 0x00008000
#define SMB2_SHAREFLAG_IDENTITY_REMOTING 0x00040000 /* 3.1.1 */
-#define SHI1005_FLAGS_ALL 0x0004FF33
+#define SMB2_SHAREFLAG_COMPRESS_DATA 0x00100000 /* 3.1.1 */
+#define SHI1005_FLAGS_ALL 0x0014FF33
/* Possible share capabilities */
#define SMB2_SHARE_CAP_DFS cpu_to_le32(0x00000008) /* all dialects */
@@ -1390,7 +1423,11 @@ struct smb2_lock_req {
struct smb2_sync_hdr sync_hdr;
__le16 StructureSize; /* Must be 48 */
__le16 LockCount;
- __le32 Reserved;
+ /*
+ * The least significant four bits are the index, the other 28 bits are
+ * the lock sequence number (0 to 64). See MS-SMB2 2.2.26
+ */
+ __le32 LockSequenceNumber;
__u64 PersistentFileId; /* opaque endianness */
__u64 VolatileFileId; /* opaque endianness */
/* Followed by at least one */
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index a2eb34a8d9c9..a5f87b02cfaf 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -69,12 +69,16 @@ extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
extern int smb3_handle_read_data(struct TCP_Server_Info *server,
struct mid_q_entry *mid);
-extern int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
- struct cifs_sb_info *cifs_sb,
- struct cached_fid **cfid);
-extern void close_shroot(struct cached_fid *cfid);
-extern void close_shroot_lease(struct cached_fid *cfid);
-extern void close_shroot_lease_locked(struct cached_fid *cfid);
+extern int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
+ const char *path,
+ struct cifs_sb_info *cifs_sb,
+ struct cached_fid **cfid);
+extern int open_cached_dir_by_dentry(struct cifs_tcon *tcon,
+ struct dentry *dentry,
+ struct cached_fid **cfid);
+extern void close_cached_dir(struct cached_fid *cfid);
+extern void close_cached_dir_lease(struct cached_fid *cfid);
+extern void close_cached_dir_lease_locked(struct cached_fid *cfid);
extern void move_smb2_info_to_cifs(FILE_ALL_INFO *dst,
struct smb2_file_all_info *src);
extern int smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon,
diff --git a/fs/cifs/unc.c b/fs/cifs/unc.c
index 394aa00cea40..f6fc5e343ea4 100644
--- a/fs/cifs/unc.c
+++ b/fs/cifs/unc.c
@@ -50,7 +50,6 @@ char *extract_sharename(const char *unc)
{
const char *src;
char *delim, *dst;
- int len;
/* skip double chars at the beginning */
src = unc + 2;
@@ -60,10 +59,9 @@ char *extract_sharename(const char *unc)
if (!delim)
return ERR_PTR(-EINVAL);
delim++;
- len = strlen(delim);
/* caller has to free the memory */
- dst = kstrndup(delim, len, GFP_KERNEL);
+ dst = kstrdup(delim, GFP_KERNEL);
if (!dst)
return ERR_PTR(-ENOMEM);
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 41a611e76bb7..e351b945135b 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -53,7 +53,7 @@ enum { XATTR_USER, XATTR_CIFS_ACL, XATTR_ACL_ACCESS, XATTR_ACL_DEFAULT,
XATTR_CIFS_NTSD, XATTR_CIFS_NTSD_FULL };
static int cifs_attrib_set(unsigned int xid, struct cifs_tcon *pTcon,
- struct inode *inode, char *full_path,
+ struct inode *inode, const char *full_path,
const void *value, size_t size)
{
ssize_t rc = -EOPNOTSUPP;
@@ -77,7 +77,7 @@ static int cifs_attrib_set(unsigned int xid, struct cifs_tcon *pTcon,
}
static int cifs_creation_time_set(unsigned int xid, struct cifs_tcon *pTcon,
- struct inode *inode, char *full_path,
+ struct inode *inode, const char *full_path,
const void *value, size_t size)
{
ssize_t rc = -EOPNOTSUPP;
@@ -112,7 +112,8 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- char *full_path;
+ const char *full_path;
+ void *page;
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
@@ -120,10 +121,11 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
pTcon = tlink_tcon(tlink);
xid = get_xid();
+ page = alloc_dentry_path();
- full_path = build_path_from_dentry(dentry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto out;
}
/* return dos attributes as pseudo xattr */
@@ -235,7 +237,7 @@ static int cifs_xattr_set(const struct xattr_handler *handler,
}
out:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
@@ -297,7 +299,8 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- char *full_path;
+ const char *full_path;
+ void *page;
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
@@ -305,10 +308,11 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
pTcon = tlink_tcon(tlink);
xid = get_xid();
+ page = alloc_dentry_path();
- full_path = build_path_from_dentry(dentry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(dentry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto out;
}
@@ -401,7 +405,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
rc = -EOPNOTSUPP;
out:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
@@ -414,7 +418,8 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- char *full_path;
+ const char *full_path;
+ void *page;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
return -EOPNOTSUPP;
@@ -425,10 +430,11 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
pTcon = tlink_tcon(tlink);
xid = get_xid();
+ page = alloc_dentry_path();
- full_path = build_path_from_dentry(direntry);
- if (full_path == NULL) {
- rc = -ENOMEM;
+ full_path = build_path_from_dentry(direntry, page);
+ if (IS_ERR(full_path)) {
+ rc = PTR_ERR(full_path);
goto list_ea_exit;
}
/* return dos attributes as pseudo xattr */
@@ -442,7 +448,7 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
full_path, NULL, data, buf_size, cifs_sb);
list_ea_exit:
- kfree(full_path);
+ free_dentry_path(page);
free_xid(xid);
cifs_put_tlink(tlink);
return rc;
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 128d63df5bfb..ef5ca22bfb3e 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -175,10 +175,10 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
ret = call_mmap(vma->vm_file, vma);
if (ret) {
- /* if call_mmap fails, our caller will put coda_file so we
- * should drop the reference to the host_file that we got.
+ /* if call_mmap fails, our caller will put host_file so we
+ * should drop the reference to the coda_file that we got.
*/
- fput(host_file);
+ fput(coda_file);
kfree(cvm_ops);
} else {
/* here we add redirects for the open/close vm_operations */
diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig
index a5f5c30368a2..2d0c8922f635 100644
--- a/fs/crypto/Kconfig
+++ b/fs/crypto/Kconfig
@@ -14,16 +14,30 @@ config FS_ENCRYPTION
F2FS and UBIFS make use of this feature.
# Filesystems supporting encryption must select this if FS_ENCRYPTION. This
-# allows the algorithms to be built as modules when all the filesystems are.
+# allows the algorithms to be built as modules when all the filesystems are,
+# whereas selecting them from FS_ENCRYPTION would force them to be built-in.
+#
+# Note: this option only pulls in the algorithms that filesystem encryption
+# needs "by default". If userspace will use "non-default" encryption modes such
+# as Adiantum encryption, then those other modes need to be explicitly enabled
+# in the crypto API; see Documentation/filesystems/fscrypt.rst for details.
+#
+# Also note that this option only pulls in the generic implementations of the
+# algorithms, not any per-architecture optimized implementations. It is
+# strongly recommended to enable optimized implementations too. It is safe to
+# disable these generic implementations if corresponding optimized
+# implementations will always be available too; for this reason, these are soft
+# dependencies ('imply' rather than 'select'). Only disable these generic
+# implementations if you're sure they will never be needed, though.
config FS_ENCRYPTION_ALGS
tristate
- select CRYPTO_AES
- select CRYPTO_CBC
- select CRYPTO_CTS
- select CRYPTO_ECB
- select CRYPTO_HMAC
- select CRYPTO_SHA512
- select CRYPTO_XTS
+ imply CRYPTO_AES
+ imply CRYPTO_CBC
+ imply CRYPTO_CTS
+ imply CRYPTO_ECB
+ imply CRYPTO_HMAC
+ imply CRYPTO_SHA512
+ imply CRYPTO_XTS
config FS_ENCRYPTION_INLINE_CRYPT
bool "Enable fscrypt to use inline crypto"
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 686e0ad28788..9979d981e9be 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -773,7 +773,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_atomic_t);
ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf,
size_t count, loff_t *ppos)
{
- char buf[3];
+ char buf[2];
bool val;
int r;
struct dentry *dentry = F_DENTRY(file);
@@ -789,7 +789,6 @@ ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf,
else
buf[0] = 'N';
buf[1] = '\n';
- buf[2] = 0x00;
return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
}
EXPORT_SYMBOL_GPL(debugfs_read_file_bool);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 22e86ae4dd5a..1d252164d97b 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -35,7 +35,7 @@
static struct vfsmount *debugfs_mount;
static int debugfs_mount_count;
static bool debugfs_registered;
-static unsigned int debugfs_allow = DEFAULT_DEBUGFS_ALLOW_BITS;
+static unsigned int debugfs_allow __ro_after_init = DEFAULT_DEBUGFS_ALLOW_BITS;
/*
* Don't allow access attributes to be changed whilst the kernel is locked down
diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
index 74b0aaa7114c..858b3339f381 100644
--- a/fs/erofs/Kconfig
+++ b/fs/erofs/Kconfig
@@ -76,17 +76,3 @@ config EROFS_FS_ZIP
If you don't want to enable compression feature, say N.
-config EROFS_FS_CLUSTER_PAGE_LIMIT
- int "EROFS Cluster Pages Hard Limit"
- depends on EROFS_FS_ZIP
- range 1 256
- default "1"
- help
- Indicates maximum # of pages of a compressed
- physical cluster.
-
- For example, if files in a image were compressed
- into 8k-unit, hard limit should not be configured
- less than 2. Otherwise, the image will be refused
- to mount on this kernel.
-
diff --git a/fs/erofs/Makefile b/fs/erofs/Makefile
index af159539fc1b..1f9aced49070 100644
--- a/fs/erofs/Makefile
+++ b/fs/erofs/Makefile
@@ -1,6 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-$(CONFIG_EROFS_FS) += erofs.o
-erofs-objs := super.o inode.o data.o namei.o dir.o utils.o
+erofs-objs := super.o inode.o data.o namei.o dir.o utils.o pcpubuf.o
erofs-$(CONFIG_EROFS_FS_XATTR) += xattr.o
erofs-$(CONFIG_EROFS_FS_ZIP) += decompressor.o zmap.o zdata.o
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 1249e74b3bf0..ebac756cb2a3 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -109,21 +109,6 @@ err_out:
return err;
}
-int erofs_map_blocks(struct inode *inode,
- struct erofs_map_blocks *map, int flags)
-{
- if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout)) {
- int err = z_erofs_map_blocks_iter(inode, map, flags);
-
- if (map->mpage) {
- put_page(map->mpage);
- map->mpage = NULL;
- }
- return err;
- }
- return erofs_map_blocks_flatmode(inode, map, flags);
-}
-
static inline struct bio *erofs_read_raw_page(struct bio *bio,
struct address_space *mapping,
struct page *page,
@@ -159,7 +144,7 @@ submit_bio_retry:
erofs_blk_t blknr;
unsigned int blkoff;
- err = erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW);
+ err = erofs_map_blocks_flatmode(inode, &map, EROFS_GET_BLOCKS_RAW);
if (err)
goto err_out;
@@ -318,7 +303,7 @@ static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
return 0;
}
- if (!erofs_map_blocks(inode, &map, EROFS_GET_BLOCKS_RAW))
+ if (!erofs_map_blocks_flatmode(inode, &map, EROFS_GET_BLOCKS_RAW))
return erofs_blknr(map.m_pa);
return 0;
diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c
index 1cb1ffd10569..88e33addf229 100644
--- a/fs/erofs/decompressor.c
+++ b/fs/erofs/decompressor.c
@@ -28,6 +28,42 @@ struct z_erofs_decompressor {
char *name;
};
+int z_erofs_load_lz4_config(struct super_block *sb,
+ struct erofs_super_block *dsb,
+ struct z_erofs_lz4_cfgs *lz4, int size)
+{
+ struct erofs_sb_info *sbi = EROFS_SB(sb);
+ u16 distance;
+
+ if (lz4) {
+ if (size < sizeof(struct z_erofs_lz4_cfgs)) {
+ erofs_err(sb, "invalid lz4 cfgs, size=%u", size);
+ return -EINVAL;
+ }
+ distance = le16_to_cpu(lz4->max_distance);
+
+ sbi->lz4.max_pclusterblks = le16_to_cpu(lz4->max_pclusterblks);
+ if (!sbi->lz4.max_pclusterblks) {
+ sbi->lz4.max_pclusterblks = 1; /* reserved case */
+ } else if (sbi->lz4.max_pclusterblks >
+ Z_EROFS_PCLUSTER_MAX_SIZE / EROFS_BLKSIZ) {
+ erofs_err(sb, "too large lz4 pclusterblks %u",
+ sbi->lz4.max_pclusterblks);
+ return -EINVAL;
+ } else if (sbi->lz4.max_pclusterblks >= 2) {
+ erofs_info(sb, "EXPERIMENTAL big pcluster feature in use. Use at your own risk!");
+ }
+ } else {
+ distance = le16_to_cpu(dsb->u1.lz4_max_distance);
+ sbi->lz4.max_pclusterblks = 1;
+ }
+
+ sbi->lz4.max_distance_pages = distance ?
+ DIV_ROUND_UP(distance, PAGE_SIZE) + 1 :
+ LZ4_MAX_DISTANCE_PAGES;
+ return erofs_pcpubuf_growsize(sbi->lz4.max_pclusterblks);
+}
+
static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
struct list_head *pagepool)
{
@@ -36,6 +72,8 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
struct page *availables[LZ4_MAX_DISTANCE_PAGES] = { NULL };
unsigned long bounced[DIV_ROUND_UP(LZ4_MAX_DISTANCE_PAGES,
BITS_PER_LONG)] = { 0 };
+ unsigned int lz4_max_distance_pages =
+ EROFS_SB(rq->sb)->lz4.max_distance_pages;
void *kaddr = NULL;
unsigned int i, j, top;
@@ -44,14 +82,14 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
struct page *const page = rq->out[i];
struct page *victim;
- if (j >= LZ4_MAX_DISTANCE_PAGES)
+ if (j >= lz4_max_distance_pages)
j = 0;
/* 'valid' bounced can only be tested after a complete round */
if (test_bit(j, bounced)) {
- DBG_BUGON(i < LZ4_MAX_DISTANCE_PAGES);
- DBG_BUGON(top >= LZ4_MAX_DISTANCE_PAGES);
- availables[top++] = rq->out[i - LZ4_MAX_DISTANCE_PAGES];
+ DBG_BUGON(i < lz4_max_distance_pages);
+ DBG_BUGON(top >= lz4_max_distance_pages);
+ availables[top++] = rq->out[i - lz4_max_distance_pages];
}
if (page) {
@@ -73,9 +111,8 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
victim = availables[--top];
get_page(victim);
} else {
- victim = erofs_allocpage(pagepool, GFP_KERNEL);
- if (!victim)
- return -ENOMEM;
+ victim = erofs_allocpage(pagepool,
+ GFP_KERNEL | __GFP_NOFAIL);
set_page_private(victim, Z_EROFS_SHORTLIVED_PAGE);
}
rq->out[i] = victim;
@@ -83,96 +120,123 @@ static int z_erofs_lz4_prepare_destpages(struct z_erofs_decompress_req *rq,
return kaddr ? 1 : 0;
}
-static void *generic_copy_inplace_data(struct z_erofs_decompress_req *rq,
- u8 *src, unsigned int pageofs_in)
+static void *z_erofs_handle_inplace_io(struct z_erofs_decompress_req *rq,
+ void *inpage, unsigned int *inputmargin, int *maptype,
+ bool support_0padding)
{
- /*
- * if in-place decompression is ongoing, those decompressed
- * pages should be copied in order to avoid being overlapped.
- */
- struct page **in = rq->in;
- u8 *const tmp = erofs_get_pcpubuf(0);
- u8 *tmpp = tmp;
- unsigned int inlen = rq->inputsize - pageofs_in;
- unsigned int count = min_t(uint, inlen, PAGE_SIZE - pageofs_in);
-
- while (tmpp < tmp + inlen) {
- if (!src)
- src = kmap_atomic(*in);
- memcpy(tmpp, src + pageofs_in, count);
- kunmap_atomic(src);
- src = NULL;
- tmpp += count;
- pageofs_in = 0;
- count = PAGE_SIZE;
+ unsigned int nrpages_in, nrpages_out;
+ unsigned int ofull, oend, inputsize, total, i, j;
+ struct page **in;
+ void *src, *tmp;
+
+ inputsize = rq->inputsize;
+ nrpages_in = PAGE_ALIGN(inputsize) >> PAGE_SHIFT;
+ oend = rq->pageofs_out + rq->outputsize;
+ ofull = PAGE_ALIGN(oend);
+ nrpages_out = ofull >> PAGE_SHIFT;
+
+ if (rq->inplace_io) {
+ if (rq->partial_decoding || !support_0padding ||
+ ofull - oend < LZ4_DECOMPRESS_INPLACE_MARGIN(inputsize))
+ goto docopy;
+
+ for (i = 0; i < nrpages_in; ++i) {
+ DBG_BUGON(rq->in[i] == NULL);
+ for (j = 0; j < nrpages_out - nrpages_in + i; ++j)
+ if (rq->out[j] == rq->in[i])
+ goto docopy;
+ }
+ }
+
+ if (nrpages_in <= 1) {
+ *maptype = 0;
+ return inpage;
+ }
+ kunmap_atomic(inpage);
+ might_sleep();
+ src = erofs_vm_map_ram(rq->in, nrpages_in);
+ if (!src)
+ return ERR_PTR(-ENOMEM);
+ *maptype = 1;
+ return src;
+
+docopy:
+ /* Or copy compressed data which can be overlapped to per-CPU buffer */
+ in = rq->in;
+ src = erofs_get_pcpubuf(nrpages_in);
+ if (!src) {
+ DBG_BUGON(1);
+ kunmap_atomic(inpage);
+ return ERR_PTR(-EFAULT);
+ }
+
+ tmp = src;
+ total = rq->inputsize;
+ while (total) {
+ unsigned int page_copycnt =
+ min_t(unsigned int, total, PAGE_SIZE - *inputmargin);
+
+ if (!inpage)
+ inpage = kmap_atomic(*in);
+ memcpy(tmp, inpage + *inputmargin, page_copycnt);
+ kunmap_atomic(inpage);
+ inpage = NULL;
+ tmp += page_copycnt;
+ total -= page_copycnt;
++in;
+ *inputmargin = 0;
}
- return tmp;
+ *maptype = 2;
+ return src;
}
static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
{
- unsigned int inputmargin, inlen;
- u8 *src;
- bool copied, support_0padding;
- int ret;
-
- if (rq->inputsize > PAGE_SIZE)
- return -EOPNOTSUPP;
+ unsigned int inputmargin;
+ u8 *headpage, *src;
+ bool support_0padding;
+ int ret, maptype;
- src = kmap_atomic(*rq->in);
+ DBG_BUGON(*rq->in == NULL);
+ headpage = kmap_atomic(*rq->in);
inputmargin = 0;
support_0padding = false;
/* decompression inplace is only safe when 0padding is enabled */
- if (EROFS_SB(rq->sb)->feature_incompat &
- EROFS_FEATURE_INCOMPAT_LZ4_0PADDING) {
+ if (erofs_sb_has_lz4_0padding(EROFS_SB(rq->sb))) {
support_0padding = true;
- while (!src[inputmargin & ~PAGE_MASK])
+ while (!headpage[inputmargin & ~PAGE_MASK])
if (!(++inputmargin & ~PAGE_MASK))
break;
if (inputmargin >= rq->inputsize) {
- kunmap_atomic(src);
+ kunmap_atomic(headpage);
return -EIO;
}
}
- copied = false;
- inlen = rq->inputsize - inputmargin;
- if (rq->inplace_io) {
- const uint oend = (rq->pageofs_out +
- rq->outputsize) & ~PAGE_MASK;
- const uint nr = PAGE_ALIGN(rq->pageofs_out +
- rq->outputsize) >> PAGE_SHIFT;
-
- if (rq->partial_decoding || !support_0padding ||
- rq->out[nr - 1] != rq->in[0] ||
- rq->inputsize - oend <
- LZ4_DECOMPRESS_INPLACE_MARGIN(inlen)) {
- src = generic_copy_inplace_data(rq, src, inputmargin);
- inputmargin = 0;
- copied = true;
- }
- }
+ rq->inputsize -= inputmargin;
+ src = z_erofs_handle_inplace_io(rq, headpage, &inputmargin, &maptype,
+ support_0padding);
+ if (IS_ERR(src))
+ return PTR_ERR(src);
/* legacy format could compress extra data in a pcluster. */
if (rq->partial_decoding || !support_0padding)
ret = LZ4_decompress_safe_partial(src + inputmargin, out,
- inlen, rq->outputsize,
- rq->outputsize);
+ rq->inputsize, rq->outputsize, rq->outputsize);
else
ret = LZ4_decompress_safe(src + inputmargin, out,
- inlen, rq->outputsize);
+ rq->inputsize, rq->outputsize);
if (ret != rq->outputsize) {
erofs_err(rq->sb, "failed to decompress %d in[%u, %u] out[%u]",
- ret, inlen, inputmargin, rq->outputsize);
+ ret, rq->inputsize, inputmargin, rq->outputsize);
WARN_ON(1);
print_hex_dump(KERN_DEBUG, "[ in]: ", DUMP_PREFIX_OFFSET,
- 16, 1, src + inputmargin, inlen, true);
+ 16, 1, src + inputmargin, rq->inputsize, true);
print_hex_dump(KERN_DEBUG, "[out]: ", DUMP_PREFIX_OFFSET,
16, 1, out, rq->outputsize, true);
@@ -181,10 +245,16 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, u8 *out)
ret = -EIO;
}
- if (copied)
- erofs_put_pcpubuf(src);
- else
+ if (maptype == 0) {
kunmap_atomic(src);
+ } else if (maptype == 1) {
+ vm_unmap_ram(src, PAGE_ALIGN(rq->inputsize) >> PAGE_SHIFT);
+ } else if (maptype == 2) {
+ erofs_put_pcpubuf(src);
+ } else {
+ DBG_BUGON(1);
+ return -EFAULT;
+ }
return ret;
}
@@ -234,57 +304,51 @@ static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq,
const struct z_erofs_decompressor *alg = decompressors + rq->alg;
unsigned int dst_maptype;
void *dst;
- int ret, i;
+ int ret;
- if (nrpages_out == 1 && !rq->inplace_io) {
- DBG_BUGON(!*rq->out);
- dst = kmap_atomic(*rq->out);
- dst_maptype = 0;
- goto dstmap_out;
- }
+ /* two optimized fast paths only for non bigpcluster cases yet */
+ if (rq->inputsize <= PAGE_SIZE) {
+ if (nrpages_out == 1 && !rq->inplace_io) {
+ DBG_BUGON(!*rq->out);
+ dst = kmap_atomic(*rq->out);
+ dst_maptype = 0;
+ goto dstmap_out;
+ }
- /*
- * For the case of small output size (especially much less
- * than PAGE_SIZE), memcpy the decompressed data rather than
- * compressed data is preferred.
- */
- if (rq->outputsize <= PAGE_SIZE * 7 / 8) {
- dst = erofs_get_pcpubuf(0);
- if (IS_ERR(dst))
- return PTR_ERR(dst);
-
- rq->inplace_io = false;
- ret = alg->decompress(rq, dst);
- if (!ret)
- copy_from_pcpubuf(rq->out, dst, rq->pageofs_out,
- rq->outputsize);
-
- erofs_put_pcpubuf(dst);
- return ret;
+ /*
+ * For the case of small output size (especially much less
+ * than PAGE_SIZE), memcpy the decompressed data rather than
+ * compressed data is preferred.
+ */
+ if (rq->outputsize <= PAGE_SIZE * 7 / 8) {
+ dst = erofs_get_pcpubuf(1);
+ if (IS_ERR(dst))
+ return PTR_ERR(dst);
+
+ rq->inplace_io = false;
+ ret = alg->decompress(rq, dst);
+ if (!ret)
+ copy_from_pcpubuf(rq->out, dst, rq->pageofs_out,
+ rq->outputsize);
+
+ erofs_put_pcpubuf(dst);
+ return ret;
+ }
}
+ /* general decoding path which can be used for all cases */
ret = alg->prepare_destpages(rq, pagepool);
- if (ret < 0) {
+ if (ret < 0)
return ret;
- } else if (ret) {
+ if (ret) {
dst = page_address(*rq->out);
dst_maptype = 1;
goto dstmap_out;
}
- i = 0;
- while (1) {
- dst = vm_map_ram(rq->out, nrpages_out, -1);
-
- /* retry two more times (totally 3 times) */
- if (dst || ++i >= 3)
- break;
- vm_unmap_aliases();
- }
-
+ dst = erofs_vm_map_ram(rq->out, nrpages_out);
if (!dst)
return -ENOMEM;
-
dst_maptype = 2;
dstmap_out:
diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 9ad1615f4474..8739d3adf51f 100644
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -18,15 +18,22 @@
* be incompatible with this kernel version.
*/
#define EROFS_FEATURE_INCOMPAT_LZ4_0PADDING 0x00000001
-#define EROFS_ALL_FEATURE_INCOMPAT EROFS_FEATURE_INCOMPAT_LZ4_0PADDING
+#define EROFS_FEATURE_INCOMPAT_COMPR_CFGS 0x00000002
+#define EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER 0x00000002
+#define EROFS_ALL_FEATURE_INCOMPAT \
+ (EROFS_FEATURE_INCOMPAT_LZ4_0PADDING | \
+ EROFS_FEATURE_INCOMPAT_COMPR_CFGS | \
+ EROFS_FEATURE_INCOMPAT_BIG_PCLUSTER)
-/* 128-byte erofs on-disk super block */
+#define EROFS_SB_EXTSLOT_SIZE 16
+
+/* erofs on-disk super block (currently 128 bytes) */
struct erofs_super_block {
__le32 magic; /* file system magic number */
__le32 checksum; /* crc32c(super_block) */
__le32 feature_compat;
__u8 blkszbits; /* support block_size == PAGE_SIZE only */
- __u8 reserved;
+ __u8 sb_extslots; /* superblock size = 128 + sb_extslots * 16 */
__le16 root_nid; /* nid of root directory */
__le64 inos; /* total valid ino # (== f_files - f_favail) */
@@ -39,7 +46,13 @@ struct erofs_super_block {
__u8 uuid[16]; /* 128-bit uuid for volume */
__u8 volume_name[16]; /* volume name */
__le32 feature_incompat;
- __u8 reserved2[44];
+ union {
+ /* bitmap for available compression algorithms */
+ __le16 available_compr_algs;
+ /* customized sliding window size instead of 64k by default */
+ __le16 lz4_max_distance;
+ } __packed u1;
+ __u8 reserved2[42];
};
/*
@@ -75,6 +88,9 @@ static inline bool erofs_inode_is_data_compressed(unsigned int datamode)
#define EROFS_I_VERSION_BIT 0
#define EROFS_I_DATALAYOUT_BIT 1
+#define EROFS_I_ALL \
+ ((1 << (EROFS_I_DATALAYOUT_BIT + EROFS_I_DATALAYOUT_BITS)) - 1)
+
/* 32-byte reduced form of an ondisk inode */
struct erofs_inode_compact {
__le16 i_format; /* inode format hints */
@@ -189,20 +205,33 @@ static inline unsigned int erofs_xattr_entry_size(struct erofs_xattr_entry *e)
e->e_name_len + le16_to_cpu(e->e_value_size));
}
+/* maximum supported size of a physical compression cluster */
+#define Z_EROFS_PCLUSTER_MAX_SIZE (1024 * 1024)
+
/* available compression algorithm types (for h_algorithmtype) */
enum {
Z_EROFS_COMPRESSION_LZ4 = 0,
Z_EROFS_COMPRESSION_MAX
};
+#define Z_EROFS_ALL_COMPR_ALGS (1 << (Z_EROFS_COMPRESSION_MAX - 1))
+
+/* 14 bytes (+ length field = 16 bytes) */
+struct z_erofs_lz4_cfgs {
+ __le16 max_distance;
+ __le16 max_pclusterblks;
+ u8 reserved[10];
+} __packed;
/*
* bit 0 : COMPACTED_2B indexes (0 - off; 1 - on)
* e.g. for 4k logical cluster size, 4B if compacted 2B is off;
* (4B) + 2B + (4B) if compacted 2B is on.
+ * bit 1 : HEAD1 big pcluster (0 - off; 1 - on)
+ * bit 2 : HEAD2 big pcluster (0 - off; 1 - on)
*/
-#define Z_EROFS_ADVISE_COMPACTED_2B_BIT 0
-
-#define Z_EROFS_ADVISE_COMPACTED_2B (1 << Z_EROFS_ADVISE_COMPACTED_2B_BIT)
+#define Z_EROFS_ADVISE_COMPACTED_2B 0x0001
+#define Z_EROFS_ADVISE_BIG_PCLUSTER_1 0x0002
+#define Z_EROFS_ADVISE_BIG_PCLUSTER_2 0x0004
struct z_erofs_map_header {
__le32 h_reserved1;
@@ -214,9 +243,7 @@ struct z_erofs_map_header {
__u8 h_algorithmtype;
/*
* bit 0-2 : logical cluster bits - 12, e.g. 0 for 4096;
- * bit 3-4 : (physical - logical) cluster bits of head 1:
- * For example, if logical clustersize = 4096, 1 for 8192.
- * bit 5-7 : (physical - logical) cluster bits of head 2.
+ * bit 3-7 : reserved.
*/
__u8 h_clusterbits;
};
@@ -259,6 +286,13 @@ enum {
#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS 2
#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT 0
+/*
+ * D0_CBLKCNT will be marked _only_ at the 1st non-head lcluster to store the
+ * compressed block count of a compressed extent (in logical clusters, aka.
+ * block count of a pcluster).
+ */
+#define Z_EROFS_VLE_DI_D0_CBLKCNT (1 << 11)
+
struct z_erofs_vle_decompressed_index {
__le16 di_advise;
/* where to decompress in the head cluster */
diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 119fdce1b520..7ed2d7391692 100644
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -44,6 +44,13 @@ static struct page *erofs_read_inode(struct inode *inode,
dic = page_address(page) + *ofs;
ifmt = le16_to_cpu(dic->i_format);
+ if (ifmt & ~EROFS_I_ALL) {
+ erofs_err(inode->i_sb, "unsupported i_format %u of nid %llu",
+ ifmt, vi->nid);
+ err = -EOPNOTSUPP;
+ goto err_out;
+ }
+
vi->datalayout = erofs_inode_datalayout(ifmt);
if (vi->datalayout >= EROFS_INODE_DATALAYOUT_MAX) {
erofs_err(inode->i_sb, "unsupported datalayout %u of nid %llu",
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 351dae524a0c..f92e3e32b9f4 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -50,6 +50,8 @@ struct erofs_fs_context {
#ifdef CONFIG_EROFS_FS_ZIP
/* current strategy of how to use managed cache */
unsigned char cache_strategy;
+ /* strategy of sync decompression (false - auto, true - force on) */
+ bool readahead_sync_decompress;
/* threshold for decompression synchronously */
unsigned int max_sync_decompress_pages;
@@ -57,6 +59,14 @@ struct erofs_fs_context {
unsigned int mount_opt;
};
+/* all filesystem-wide lz4 configurations */
+struct erofs_sb_lz4_info {
+ /* # of pages needed for EROFS lz4 rolling decompression */
+ u16 max_distance_pages;
+ /* maximum possible blocks for pclusters in the filesystem */
+ u16 max_pclusterblks;
+};
+
struct erofs_sb_info {
#ifdef CONFIG_EROFS_FS_ZIP
/* list for all registered superblocks, mainly for shrinker */
@@ -67,9 +77,12 @@ struct erofs_sb_info {
struct xarray managed_pslots;
unsigned int shrinker_run_no;
+ u16 available_compr_algs;
/* pseudo inode to manage cached pages */
struct inode *managed_cache;
+
+ struct erofs_sb_lz4_info lz4;
#endif /* CONFIG_EROFS_FS_ZIP */
u32 blocks;
u32 meta_blkaddr;
@@ -80,6 +93,7 @@ struct erofs_sb_info {
/* inode slot unit size in bit shift */
unsigned char islotbits;
+ u32 sb_size; /* total superblock size */
u32 build_time_nsec;
u64 build_time;
@@ -182,12 +196,6 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
return v;
}
#endif /* !CONFIG_SMP */
-
-/* hard limit of pages per compressed cluster */
-#define Z_EROFS_CLUSTER_MAX_PAGES (CONFIG_EROFS_FS_CLUSTER_PAGE_LIMIT)
-#define EROFS_PCPUBUF_NR_PAGES Z_EROFS_CLUSTER_MAX_PAGES
-#else
-#define EROFS_PCPUBUF_NR_PAGES 0
#endif /* !CONFIG_EROFS_FS_ZIP */
/* we strictly follow PAGE_SIZE and no buffer head yet */
@@ -216,6 +224,17 @@ static inline erofs_off_t iloc(struct erofs_sb_info *sbi, erofs_nid_t nid)
return blknr_to_addr(sbi->meta_blkaddr) + (nid << sbi->islotbits);
}
+#define EROFS_FEATURE_FUNCS(name, compat, feature) \
+static inline bool erofs_sb_has_##name(struct erofs_sb_info *sbi) \
+{ \
+ return sbi->feature_##compat & EROFS_FEATURE_##feature; \
+}
+
+EROFS_FEATURE_FUNCS(lz4_0padding, incompat, INCOMPAT_LZ4_0PADDING)
+EROFS_FEATURE_FUNCS(compr_cfgs, incompat, INCOMPAT_COMPR_CFGS)
+EROFS_FEATURE_FUNCS(big_pcluster, incompat, INCOMPAT_BIG_PCLUSTER)
+EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM)
+
/* atomic flag definitions */
#define EROFS_I_EA_INITED_BIT 0
#define EROFS_I_Z_INITED_BIT 1
@@ -244,7 +263,6 @@ struct erofs_inode {
unsigned short z_advise;
unsigned char z_algorithmtype[2];
unsigned char z_logical_clusterbits;
- unsigned char z_physical_clusterbits[2];
};
#endif /* CONFIG_EROFS_FS_ZIP */
};
@@ -287,7 +305,7 @@ extern const struct address_space_operations erofs_raw_access_aops;
extern const struct address_space_operations z_erofs_aops;
/*
- * Logical to physical block mapping, used by erofs_map_blocks()
+ * Logical to physical block mapping
*
* Different with other file systems, it is used for 2 access modes:
*
@@ -334,7 +352,7 @@ struct erofs_map_blocks {
struct page *mpage;
};
-/* Flags used by erofs_map_blocks() */
+/* Flags used by erofs_map_blocks_flatmode() */
#define EROFS_GET_BLOCKS_RAW 0x0001
/* zmap.c */
@@ -356,8 +374,6 @@ static inline int z_erofs_map_blocks_iter(struct inode *inode,
/* data.c */
struct page *erofs_get_meta_page(struct super_block *sb, erofs_blk_t blkaddr);
-int erofs_map_blocks(struct inode *, struct erofs_map_blocks *, int);
-
/* inode.c */
static inline unsigned long erofs_inode_hash(erofs_nid_t nid)
{
@@ -386,23 +402,30 @@ int erofs_namei(struct inode *dir, struct qstr *name,
/* dir.c */
extern const struct file_operations erofs_dir_fops;
-/* utils.c / zdata.c */
-struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp);
-
-#if (EROFS_PCPUBUF_NR_PAGES > 0)
-void *erofs_get_pcpubuf(unsigned int pagenr);
-#define erofs_put_pcpubuf(buf) do { \
- (void)&(buf); \
- preempt_enable(); \
-} while (0)
-#else
-static inline void *erofs_get_pcpubuf(unsigned int pagenr)
+static inline void *erofs_vm_map_ram(struct page **pages, unsigned int count)
{
- return ERR_PTR(-EOPNOTSUPP);
+ int retried = 0;
+
+ while (1) {
+ void *p = vm_map_ram(pages, count, -1);
+
+ /* retry two more times (totally 3 times) */
+ if (p || ++retried >= 3)
+ return p;
+ vm_unmap_aliases();
+ }
+ return NULL;
}
-#define erofs_put_pcpubuf(buf) do {} while (0)
-#endif
+/* pcpubuf.c */
+void *erofs_get_pcpubuf(unsigned int requiredpages);
+void erofs_put_pcpubuf(void *ptr);
+int erofs_pcpubuf_growsize(unsigned int nrpages);
+void erofs_pcpubuf_init(void);
+void erofs_pcpubuf_exit(void);
+
+/* utils.c / zdata.c */
+struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp);
#ifdef CONFIG_EROFS_FS_ZIP
int erofs_workgroup_put(struct erofs_workgroup *grp);
@@ -421,6 +444,9 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
struct erofs_workgroup *egrp);
int erofs_try_to_free_cached_page(struct address_space *mapping,
struct page *page);
+int z_erofs_load_lz4_config(struct super_block *sb,
+ struct erofs_super_block *dsb,
+ struct z_erofs_lz4_cfgs *lz4, int len);
#else
static inline void erofs_shrinker_register(struct super_block *sb) {}
static inline void erofs_shrinker_unregister(struct super_block *sb) {}
@@ -428,6 +454,16 @@ static inline int erofs_init_shrinker(void) { return 0; }
static inline void erofs_exit_shrinker(void) {}
static inline int z_erofs_init_zip_subsystem(void) { return 0; }
static inline void z_erofs_exit_zip_subsystem(void) {}
+static inline int z_erofs_load_lz4_config(struct super_block *sb,
+ struct erofs_super_block *dsb,
+ struct z_erofs_lz4_cfgs *lz4, int len)
+{
+ if (lz4 || dsb->u1.lz4_max_distance) {
+ erofs_err(sb, "lz4 algorithm isn't enabled");
+ return -EINVAL;
+ }
+ return 0;
+}
#endif /* !CONFIG_EROFS_FS_ZIP */
#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
diff --git a/fs/erofs/pcpubuf.c b/fs/erofs/pcpubuf.c
new file mode 100644
index 000000000000..6c885575128a
--- /dev/null
+++ b/fs/erofs/pcpubuf.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) Gao Xiang <xiang@kernel.org>
+ *
+ * For low-latency decompression algorithms (e.g. lz4), reserve consecutive
+ * per-CPU virtual memory (in pages) in advance to store such inplace I/O
+ * data if inplace decompression is failed (due to unmet inplace margin for
+ * example).
+ */
+#include "internal.h"
+
+struct erofs_pcpubuf {
+ raw_spinlock_t lock;
+ void *ptr;
+ struct page **pages;
+ unsigned int nrpages;
+};
+
+static DEFINE_PER_CPU(struct erofs_pcpubuf, erofs_pcb);
+
+void *erofs_get_pcpubuf(unsigned int requiredpages)
+ __acquires(pcb->lock)
+{
+ struct erofs_pcpubuf *pcb = &get_cpu_var(erofs_pcb);
+
+ raw_spin_lock(&pcb->lock);
+ /* check if the per-CPU buffer is too small */
+ if (requiredpages > pcb->nrpages) {
+ raw_spin_unlock(&pcb->lock);
+ put_cpu_var(erofs_pcb);
+ /* (for sparse checker) pretend pcb->lock is still taken */
+ __acquire(pcb->lock);
+ return NULL;
+ }
+ return pcb->ptr;
+}
+
+void erofs_put_pcpubuf(void *ptr) __releases(pcb->lock)
+{
+ struct erofs_pcpubuf *pcb = &per_cpu(erofs_pcb, smp_processor_id());
+
+ DBG_BUGON(pcb->ptr != ptr);
+ raw_spin_unlock(&pcb->lock);
+ put_cpu_var(erofs_pcb);
+}
+
+/* the next step: support per-CPU page buffers hotplug */
+int erofs_pcpubuf_growsize(unsigned int nrpages)
+{
+ static DEFINE_MUTEX(pcb_resize_mutex);
+ static unsigned int pcb_nrpages;
+ LIST_HEAD(pagepool);
+ int delta, cpu, ret, i;
+
+ mutex_lock(&pcb_resize_mutex);
+ delta = nrpages - pcb_nrpages;
+ ret = 0;
+ /* avoid shrinking pcpubuf, since no idea how many fses rely on */
+ if (delta <= 0)
+ goto out;
+
+ for_each_possible_cpu(cpu) {
+ struct erofs_pcpubuf *pcb = &per_cpu(erofs_pcb, cpu);
+ struct page **pages, **oldpages;
+ void *ptr, *old_ptr;
+
+ pages = kmalloc_array(nrpages, sizeof(*pages), GFP_KERNEL);
+ if (!pages) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ for (i = 0; i < nrpages; ++i) {
+ pages[i] = erofs_allocpage(&pagepool, GFP_KERNEL);
+ if (!pages[i]) {
+ ret = -ENOMEM;
+ oldpages = pages;
+ goto free_pagearray;
+ }
+ }
+ ptr = vmap(pages, nrpages, VM_MAP, PAGE_KERNEL);
+ if (!ptr) {
+ ret = -ENOMEM;
+ oldpages = pages;
+ goto free_pagearray;
+ }
+ raw_spin_lock(&pcb->lock);
+ old_ptr = pcb->ptr;
+ pcb->ptr = ptr;
+ oldpages = pcb->pages;
+ pcb->pages = pages;
+ i = pcb->nrpages;
+ pcb->nrpages = nrpages;
+ raw_spin_unlock(&pcb->lock);
+
+ if (!oldpages) {
+ DBG_BUGON(old_ptr);
+ continue;
+ }
+
+ if (old_ptr)
+ vunmap(old_ptr);
+free_pagearray:
+ while (i)
+ list_add(&oldpages[--i]->lru, &pagepool);
+ kfree(oldpages);
+ if (ret)
+ break;
+ }
+ pcb_nrpages = nrpages;
+ put_pages_list(&pagepool);
+out:
+ mutex_unlock(&pcb_resize_mutex);
+ return ret;
+}
+
+void erofs_pcpubuf_init(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct erofs_pcpubuf *pcb = &per_cpu(erofs_pcb, cpu);
+
+ raw_spin_lock_init(&pcb->lock);
+ }
+}
+
+void erofs_pcpubuf_exit(void)
+{
+ int cpu, i;
+
+ for_each_possible_cpu(cpu) {
+ struct erofs_pcpubuf *pcb = &per_cpu(erofs_pcb, cpu);
+
+ if (pcb->ptr) {
+ vunmap(pcb->ptr);
+ pcb->ptr = NULL;
+ }
+ if (!pcb->pages)
+ continue;
+
+ for (i = 0; i < pcb->nrpages; ++i)
+ if (pcb->pages[i])
+ put_page(pcb->pages[i]);
+ kfree(pcb->pages);
+ pcb->pages = NULL;
+ }
+}
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index d5a6b9b888a5..bbf3bbd908e0 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -122,6 +122,136 @@ static bool check_layout_compatibility(struct super_block *sb,
return true;
}
+#ifdef CONFIG_EROFS_FS_ZIP
+/* read variable-sized metadata, offset will be aligned by 4-byte */
+static void *erofs_read_metadata(struct super_block *sb, struct page **pagep,
+ erofs_off_t *offset, int *lengthp)
+{
+ struct page *page = *pagep;
+ u8 *buffer, *ptr;
+ int len, i, cnt;
+ erofs_blk_t blk;
+
+ *offset = round_up(*offset, 4);
+ blk = erofs_blknr(*offset);
+
+ if (!page || page->index != blk) {
+ if (page) {
+ unlock_page(page);
+ put_page(page);
+ }
+ page = erofs_get_meta_page(sb, blk);
+ if (IS_ERR(page))
+ goto err_nullpage;
+ }
+
+ ptr = kmap(page);
+ len = le16_to_cpu(*(__le16 *)&ptr[erofs_blkoff(*offset)]);
+ if (!len)
+ len = U16_MAX + 1;
+ buffer = kmalloc(len, GFP_KERNEL);
+ if (!buffer) {
+ buffer = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+ *offset += sizeof(__le16);
+ *lengthp = len;
+
+ for (i = 0; i < len; i += cnt) {
+ cnt = min(EROFS_BLKSIZ - (int)erofs_blkoff(*offset), len - i);
+ blk = erofs_blknr(*offset);
+
+ if (!page || page->index != blk) {
+ if (page) {
+ kunmap(page);
+ unlock_page(page);
+ put_page(page);
+ }
+ page = erofs_get_meta_page(sb, blk);
+ if (IS_ERR(page)) {
+ kfree(buffer);
+ goto err_nullpage;
+ }
+ ptr = kmap(page);
+ }
+ memcpy(buffer + i, ptr + erofs_blkoff(*offset), cnt);
+ *offset += cnt;
+ }
+out:
+ kunmap(page);
+ *pagep = page;
+ return buffer;
+err_nullpage:
+ *pagep = NULL;
+ return page;
+}
+
+static int erofs_load_compr_cfgs(struct super_block *sb,
+ struct erofs_super_block *dsb)
+{
+ struct erofs_sb_info *sbi;
+ struct page *page;
+ unsigned int algs, alg;
+ erofs_off_t offset;
+ int size, ret;
+
+ sbi = EROFS_SB(sb);
+ sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs);
+
+ if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) {
+ erofs_err(sb, "try to load compressed fs with unsupported algorithms %x",
+ sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS);
+ return -EINVAL;
+ }
+
+ offset = EROFS_SUPER_OFFSET + sbi->sb_size;
+ page = NULL;
+ alg = 0;
+ ret = 0;
+
+ for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) {
+ void *data;
+
+ if (!(algs & 1))
+ continue;
+
+ data = erofs_read_metadata(sb, &page, &offset, &size);
+ if (IS_ERR(data)) {
+ ret = PTR_ERR(data);
+ goto err;
+ }
+
+ switch (alg) {
+ case Z_EROFS_COMPRESSION_LZ4:
+ ret = z_erofs_load_lz4_config(sb, dsb, data, size);
+ break;
+ default:
+ DBG_BUGON(1);
+ ret = -EFAULT;
+ }
+ kfree(data);
+ if (ret)
+ goto err;
+ }
+err:
+ if (page) {
+ unlock_page(page);
+ put_page(page);
+ }
+ return ret;
+}
+#else
+static int erofs_load_compr_cfgs(struct super_block *sb,
+ struct erofs_super_block *dsb)
+{
+ if (dsb->u1.available_compr_algs) {
+ erofs_err(sb, "try to load compressed fs when compression is disabled");
+ return -EINVAL;
+ }
+ return 0;
+}
+#endif
+
static int erofs_read_superblock(struct super_block *sb)
{
struct erofs_sb_info *sbi;
@@ -149,7 +279,7 @@ static int erofs_read_superblock(struct super_block *sb)
}
sbi->feature_compat = le32_to_cpu(dsb->feature_compat);
- if (sbi->feature_compat & EROFS_FEATURE_COMPAT_SB_CHKSUM) {
+ if (erofs_sb_has_sb_chksum(sbi)) {
ret = erofs_superblock_csum_verify(sb, data);
if (ret)
goto out;
@@ -166,6 +296,12 @@ static int erofs_read_superblock(struct super_block *sb)
if (!check_layout_compatibility(sb, dsb))
goto out;
+ sbi->sb_size = 128 + dsb->sb_extslots * EROFS_SB_EXTSLOT_SIZE;
+ if (sbi->sb_size > EROFS_BLKSIZ) {
+ erofs_err(sb, "invalid sb_extslots %u (more than a fs block)",
+ sbi->sb_size);
+ goto out;
+ }
sbi->blocks = le32_to_cpu(dsb->blocks);
sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr);
#ifdef CONFIG_EROFS_FS_XATTR
@@ -187,7 +323,12 @@ static int erofs_read_superblock(struct super_block *sb)
ret = -EFSCORRUPTED;
goto out;
}
- ret = 0;
+
+ /* parse on-disk compression configurations */
+ if (erofs_sb_has_compr_cfgs(sbi))
+ ret = erofs_load_compr_cfgs(sb, dsb);
+ else
+ ret = z_erofs_load_lz4_config(sb, dsb, NULL, 0);
out:
kunmap(page);
put_page(page);
@@ -200,6 +341,7 @@ static void erofs_default_options(struct erofs_fs_context *ctx)
#ifdef CONFIG_EROFS_FS_ZIP
ctx->cache_strategy = EROFS_ZIP_CACHE_READAROUND;
ctx->max_sync_decompress_pages = 3;
+ ctx->readahead_sync_decompress = false;
#endif
#ifdef CONFIG_EROFS_FS_XATTR
set_opt(ctx, XATTR_USER);
@@ -513,6 +655,7 @@ static int __init erofs_module_init(void)
if (err)
goto shrinker_err;
+ erofs_pcpubuf_init();
err = z_erofs_init_zip_subsystem();
if (err)
goto zip_err;
@@ -542,6 +685,7 @@ static void __exit erofs_module_exit(void)
/* Ensure all RCU free inodes are safe before cache is destroyed. */
rcu_barrier();
kmem_cache_destroy(erofs_inode_cachep);
+ erofs_pcpubuf_exit();
}
/* get filesystem statistics */
diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c
index de9986d2f82f..6758c5b19f7c 100644
--- a/fs/erofs/utils.c
+++ b/fs/erofs/utils.c
@@ -21,18 +21,6 @@ struct page *erofs_allocpage(struct list_head *pool, gfp_t gfp)
return page;
}
-#if (EROFS_PCPUBUF_NR_PAGES > 0)
-static struct {
- u8 data[PAGE_SIZE * EROFS_PCPUBUF_NR_PAGES];
-} ____cacheline_aligned_in_smp erofs_pcpubuf[NR_CPUS];
-
-void *erofs_get_pcpubuf(unsigned int pagenr)
-{
- preempt_disable();
- return &erofs_pcpubuf[smp_processor_id()].data[pagenr * PAGE_SIZE];
-}
-#endif
-
#ifdef CONFIG_EROFS_FS_ZIP
/* global shrink count (for all mounted EROFS instances) */
static atomic_long_t erofs_global_shrink_cnt;
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index 3851e1a64f73..78e4b598ecca 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -11,6 +11,93 @@
#include <trace/events/erofs.h>
/*
+ * since pclustersize is variable for big pcluster feature, introduce slab
+ * pools implementation for different pcluster sizes.
+ */
+struct z_erofs_pcluster_slab {
+ struct kmem_cache *slab;
+ unsigned int maxpages;
+ char name[48];
+};
+
+#define _PCLP(n) { .maxpages = n }
+
+static struct z_erofs_pcluster_slab pcluster_pool[] __read_mostly = {
+ _PCLP(1), _PCLP(4), _PCLP(16), _PCLP(64), _PCLP(128),
+ _PCLP(Z_EROFS_PCLUSTER_MAX_PAGES)
+};
+
+static void z_erofs_destroy_pcluster_pool(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
+ if (!pcluster_pool[i].slab)
+ continue;
+ kmem_cache_destroy(pcluster_pool[i].slab);
+ pcluster_pool[i].slab = NULL;
+ }
+}
+
+static int z_erofs_create_pcluster_pool(void)
+{
+ struct z_erofs_pcluster_slab *pcs;
+ struct z_erofs_pcluster *a;
+ unsigned int size;
+
+ for (pcs = pcluster_pool;
+ pcs < pcluster_pool + ARRAY_SIZE(pcluster_pool); ++pcs) {
+ size = struct_size(a, compressed_pages, pcs->maxpages);
+
+ sprintf(pcs->name, "erofs_pcluster-%u", pcs->maxpages);
+ pcs->slab = kmem_cache_create(pcs->name, size, 0,
+ SLAB_RECLAIM_ACCOUNT, NULL);
+ if (pcs->slab)
+ continue;
+
+ z_erofs_destroy_pcluster_pool();
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+static struct z_erofs_pcluster *z_erofs_alloc_pcluster(unsigned int nrpages)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
+ struct z_erofs_pcluster_slab *pcs = pcluster_pool + i;
+ struct z_erofs_pcluster *pcl;
+
+ if (nrpages > pcs->maxpages)
+ continue;
+
+ pcl = kmem_cache_zalloc(pcs->slab, GFP_NOFS);
+ if (!pcl)
+ return ERR_PTR(-ENOMEM);
+ pcl->pclusterpages = nrpages;
+ return pcl;
+ }
+ return ERR_PTR(-EINVAL);
+}
+
+static void z_erofs_free_pcluster(struct z_erofs_pcluster *pcl)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(pcluster_pool); ++i) {
+ struct z_erofs_pcluster_slab *pcs = pcluster_pool + i;
+
+ if (pcl->pclusterpages > pcs->maxpages)
+ continue;
+
+ kmem_cache_free(pcs->slab, pcl);
+ return;
+ }
+ DBG_BUGON(1);
+}
+
+/*
* a compressed_pages[] placeholder in order to avoid
* being filled with file pages for in-place decompression.
*/
@@ -37,12 +124,11 @@ typedef tagptr1_t compressed_page_t;
tagptr_fold(compressed_page_t, page, 1)
static struct workqueue_struct *z_erofs_workqueue __read_mostly;
-static struct kmem_cache *pcluster_cachep __read_mostly;
void z_erofs_exit_zip_subsystem(void)
{
destroy_workqueue(z_erofs_workqueue);
- kmem_cache_destroy(pcluster_cachep);
+ z_erofs_destroy_pcluster_pool();
}
static inline int z_erofs_init_workqueue(void)
@@ -59,32 +145,16 @@ static inline int z_erofs_init_workqueue(void)
return z_erofs_workqueue ? 0 : -ENOMEM;
}
-static void z_erofs_pcluster_init_once(void *ptr)
-{
- struct z_erofs_pcluster *pcl = ptr;
- struct z_erofs_collection *cl = z_erofs_primarycollection(pcl);
- unsigned int i;
-
- mutex_init(&cl->lock);
- cl->nr_pages = 0;
- cl->vcnt = 0;
- for (i = 0; i < Z_EROFS_CLUSTER_MAX_PAGES; ++i)
- pcl->compressed_pages[i] = NULL;
-}
-
int __init z_erofs_init_zip_subsystem(void)
{
- pcluster_cachep = kmem_cache_create("erofs_compress",
- Z_EROFS_WORKGROUP_SIZE, 0,
- SLAB_RECLAIM_ACCOUNT,
- z_erofs_pcluster_init_once);
- if (pcluster_cachep) {
- if (!z_erofs_init_workqueue())
- return 0;
-
- kmem_cache_destroy(pcluster_cachep);
- }
- return -ENOMEM;
+ int err = z_erofs_create_pcluster_pool();
+
+ if (err)
+ return err;
+ err = z_erofs_init_workqueue();
+ if (err)
+ z_erofs_destroy_pcluster_pool();
+ return err;
}
enum z_erofs_collectmode {
@@ -104,6 +174,12 @@ enum z_erofs_collectmode {
* |_______PRIMARY_FOLLOWED_______|________PRIMARY_HOOKED___________|
*/
COLLECT_PRIMARY_HOOKED,
+ /*
+ * a weak form of COLLECT_PRIMARY_FOLLOWED, the difference is that it
+ * could be dispatched into bypass queue later due to uptodated managed
+ * pages. All related online pages cannot be reused for inplace I/O (or
+ * pagevec) since it can be directly decoded without I/O submission.
+ */
COLLECT_PRIMARY_FOLLOWED_NOINPLACE,
/*
* The current collection has been linked with the owned chain, and
@@ -128,7 +204,8 @@ struct z_erofs_collector {
struct z_erofs_pcluster *pcl, *tailpcl;
struct z_erofs_collection *cl;
- struct page **compressedpages;
+ /* a pointer used to pick up inplace I/O pages */
+ struct page **icpage_ptr;
z_erofs_next_pcluster_t owned_head;
enum z_erofs_collectmode mode;
@@ -162,18 +239,19 @@ static void preload_compressed_pages(struct z_erofs_collector *clt,
enum z_erofs_cache_alloctype type,
struct list_head *pagepool)
{
- const struct z_erofs_pcluster *pcl = clt->pcl;
- const unsigned int clusterpages = BIT(pcl->clusterbits);
- struct page **pages = clt->compressedpages;
- pgoff_t index = pcl->obj.index + (pages - pcl->compressed_pages);
+ struct z_erofs_pcluster *pcl = clt->pcl;
bool standalone = true;
gfp_t gfp = (mapping_gfp_mask(mc) & ~__GFP_DIRECT_RECLAIM) |
__GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;
+ struct page **pages;
+ pgoff_t index;
if (clt->mode < COLLECT_PRIMARY_FOLLOWED)
return;
- for (; pages < pcl->compressed_pages + clusterpages; ++pages) {
+ pages = pcl->compressed_pages;
+ index = pcl->obj.index;
+ for (; index < pcl->obj.index + pcl->pclusterpages; ++index, ++pages) {
struct page *page;
compressed_page_t t;
struct page *newpage = NULL;
@@ -186,21 +264,25 @@ static void preload_compressed_pages(struct z_erofs_collector *clt,
if (page) {
t = tag_compressed_page_justfound(page);
- } else if (type == DELAYEDALLOC) {
- t = tagptr_init(compressed_page_t, PAGE_UNALLOCATED);
- } else if (type == TRYALLOC) {
- newpage = erofs_allocpage(pagepool, gfp);
- if (!newpage)
- goto dontalloc;
-
- set_page_private(newpage, Z_EROFS_PREALLOCATED_PAGE);
- t = tag_compressed_page_justfound(newpage);
- } else { /* DONTALLOC */
-dontalloc:
- if (standalone)
- clt->compressedpages = pages;
+ } else {
+ /* I/O is needed, no possible to decompress directly */
standalone = false;
- continue;
+ switch (type) {
+ case DELAYEDALLOC:
+ t = tagptr_init(compressed_page_t,
+ PAGE_UNALLOCATED);
+ break;
+ case TRYALLOC:
+ newpage = erofs_allocpage(pagepool, gfp);
+ if (!newpage)
+ continue;
+ set_page_private(newpage,
+ Z_EROFS_PREALLOCATED_PAGE);
+ t = tag_compressed_page_justfound(newpage);
+ break;
+ default: /* DONTALLOC */
+ continue;
+ }
}
if (!cmpxchg_relaxed(pages, NULL, tagptr_cast_ptr(t)))
@@ -214,7 +296,11 @@ dontalloc:
}
}
- if (standalone) /* downgrade to PRIMARY_FOLLOWED_NOINPLACE */
+ /*
+ * don't do inplace I/O if all compressed pages are available in
+ * managed cache since it can be moved to the bypass queue instead.
+ */
+ if (standalone)
clt->mode = COLLECT_PRIMARY_FOLLOWED_NOINPLACE;
}
@@ -225,14 +311,13 @@ int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi,
struct z_erofs_pcluster *const pcl =
container_of(grp, struct z_erofs_pcluster, obj);
struct address_space *const mapping = MNGD_MAPPING(sbi);
- const unsigned int clusterpages = BIT(pcl->clusterbits);
int i;
/*
* refcount of workgroup is now freezed as 1,
* therefore no need to worry about available decompression users.
*/
- for (i = 0; i < clusterpages; ++i) {
+ for (i = 0; i < pcl->pclusterpages; ++i) {
struct page *page = pcl->compressed_pages[i];
if (!page)
@@ -257,13 +342,12 @@ int erofs_try_to_free_cached_page(struct address_space *mapping,
struct page *page)
{
struct z_erofs_pcluster *const pcl = (void *)page_private(page);
- const unsigned int clusterpages = BIT(pcl->clusterbits);
int ret = 0; /* 0 - busy */
if (erofs_workgroup_try_to_freeze(&pcl->obj, 1)) {
unsigned int i;
- for (i = 0; i < clusterpages; ++i) {
+ for (i = 0; i < pcl->pclusterpages; ++i) {
if (pcl->compressed_pages[i] == page) {
WRITE_ONCE(pcl->compressed_pages[i], NULL);
ret = 1;
@@ -279,16 +363,14 @@ int erofs_try_to_free_cached_page(struct address_space *mapping,
}
/* page_type must be Z_EROFS_PAGE_TYPE_EXCLUSIVE */
-static inline bool z_erofs_try_inplace_io(struct z_erofs_collector *clt,
- struct page *page)
+static bool z_erofs_try_inplace_io(struct z_erofs_collector *clt,
+ struct page *page)
{
struct z_erofs_pcluster *const pcl = clt->pcl;
- const unsigned int clusterpages = BIT(pcl->clusterbits);
- while (clt->compressedpages < pcl->compressed_pages + clusterpages) {
- if (!cmpxchg(clt->compressedpages++, NULL, page))
+ while (clt->icpage_ptr > pcl->compressed_pages)
+ if (!cmpxchg(--clt->icpage_ptr, NULL, page))
return true;
- }
return false;
}
@@ -399,10 +481,10 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
struct erofs_workgroup *grp;
int err;
- /* no available workgroup, let's allocate one */
- pcl = kmem_cache_alloc(pcluster_cachep, GFP_NOFS);
- if (!pcl)
- return -ENOMEM;
+ /* no available pcluster, let's allocate one */
+ pcl = z_erofs_alloc_pcluster(map->m_plen >> PAGE_SHIFT);
+ if (IS_ERR(pcl))
+ return PTR_ERR(pcl);
atomic_set(&pcl->obj.refcount, 1);
pcl->obj.index = map->m_pa >> PAGE_SHIFT;
@@ -416,25 +498,18 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
else
pcl->algorithmformat = Z_EROFS_COMPRESSION_SHIFTED;
- pcl->clusterbits = EROFS_I(inode)->z_physical_clusterbits[0];
- pcl->clusterbits -= PAGE_SHIFT;
-
/* new pclusters should be claimed as type 1, primary and followed */
pcl->next = clt->owned_head;
clt->mode = COLLECT_PRIMARY_FOLLOWED;
cl = z_erofs_primarycollection(pcl);
-
- /* must be cleaned before freeing to slab */
- DBG_BUGON(cl->nr_pages);
- DBG_BUGON(cl->vcnt);
-
cl->pageofs = map->m_la & ~PAGE_MASK;
/*
* lock all primary followed works before visible to others
* and mutex_trylock *never* fails for a new pcluster.
*/
+ mutex_init(&cl->lock);
DBG_BUGON(!mutex_trylock(&cl->lock));
grp = erofs_insert_workgroup(inode->i_sb, &pcl->obj);
@@ -458,7 +533,7 @@ static int z_erofs_register_collection(struct z_erofs_collector *clt,
err_out:
mutex_unlock(&cl->lock);
- kmem_cache_free(pcluster_cachep, pcl);
+ z_erofs_free_pcluster(pcl);
return err;
}
@@ -502,9 +577,8 @@ out:
z_erofs_pagevec_ctor_init(&clt->vector, Z_EROFS_NR_INLINE_PAGEVECS,
clt->cl->pagevec, clt->cl->vcnt);
- clt->compressedpages = clt->pcl->compressed_pages;
- if (clt->mode <= COLLECT_PRIMARY) /* cannot do in-place I/O */
- clt->compressedpages += Z_EROFS_CLUSTER_MAX_PAGES;
+ /* since file-backed online pages are traversed in reverse order */
+ clt->icpage_ptr = clt->pcl->compressed_pages + clt->pcl->pclusterpages;
return 0;
}
@@ -517,9 +591,8 @@ static void z_erofs_rcu_callback(struct rcu_head *head)
struct z_erofs_collection *const cl =
container_of(head, struct z_erofs_collection, rcu);
- kmem_cache_free(pcluster_cachep,
- container_of(cl, struct z_erofs_pcluster,
- primary_collection));
+ z_erofs_free_pcluster(container_of(cl, struct z_erofs_pcluster,
+ primary_collection));
}
void erofs_workgroup_free_rcu(struct erofs_workgroup *grp)
@@ -706,9 +779,12 @@ err_out:
goto out;
}
+static void z_erofs_decompressqueue_work(struct work_struct *work);
static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
bool sync, int bios)
{
+ struct erofs_sb_info *const sbi = EROFS_SB(io->sb);
+
/* wake up the caller thread for sync decompression */
if (sync) {
unsigned long flags;
@@ -720,8 +796,15 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io,
return;
}
- if (!atomic_add_return(bios, &io->pending_bios))
+ if (atomic_add_return(bios, &io->pending_bios))
+ return;
+ /* Use workqueue and sync decompression for atomic contexts only */
+ if (in_atomic() || irqs_disabled()) {
queue_work(z_erofs_workqueue, &io->u.work);
+ sbi->ctx.readahead_sync_decompress = true;
+ return;
+ }
+ z_erofs_decompressqueue_work(&io->u.work);
}
static bool z_erofs_page_is_invalidated(struct page *page)
@@ -761,9 +844,8 @@ static int z_erofs_decompress_pcluster(struct super_block *sb,
struct list_head *pagepool)
{
struct erofs_sb_info *const sbi = EROFS_SB(sb);
- const unsigned int clusterpages = BIT(pcl->clusterbits);
struct z_erofs_pagevec_ctor ctor;
- unsigned int i, outputsize, llen, nr_pages;
+ unsigned int i, inputsize, outputsize, llen, nr_pages;
struct page *pages_onstack[Z_EROFS_VMAP_ONSTACK_PAGES];
struct page **pages, **compressed_pages, *page;
@@ -843,7 +925,7 @@ static int z_erofs_decompress_pcluster(struct super_block *sb,
overlapped = false;
compressed_pages = pcl->compressed_pages;
- for (i = 0; i < clusterpages; ++i) {
+ for (i = 0; i < pcl->pclusterpages; ++i) {
unsigned int pagenr;
page = compressed_pages[i];
@@ -896,12 +978,13 @@ static int z_erofs_decompress_pcluster(struct super_block *sb,
partial = true;
}
+ inputsize = pcl->pclusterpages * PAGE_SIZE;
err = z_erofs_decompress(&(struct z_erofs_decompress_req) {
.sb = sb,
.in = compressed_pages,
.out = pages,
.pageofs_out = cl->pageofs,
- .inputsize = PAGE_SIZE,
+ .inputsize = inputsize,
.outputsize = outputsize,
.alg = pcl->algorithmformat,
.inplace_io = overlapped,
@@ -909,8 +992,8 @@ static int z_erofs_decompress_pcluster(struct super_block *sb,
}, pagepool);
out:
- /* must handle all compressed pages before endding pages */
- for (i = 0; i < clusterpages; ++i) {
+ /* must handle all compressed pages before ending pages */
+ for (i = 0; i < pcl->pclusterpages; ++i) {
page = compressed_pages[i];
if (erofs_page_is_managed(sbi, page))
@@ -1213,7 +1296,7 @@ static void z_erofs_submit_queue(struct super_block *sb,
pcl = container_of(owned_head, struct z_erofs_pcluster, next);
cur = pcl->obj.index;
- end = cur + BIT(pcl->clusterbits);
+ end = cur + pcl->pclusterpages;
/* close the main owned chain at first */
owned_head = cmpxchg(&pcl->next, Z_EROFS_PCLUSTER_TAIL,
@@ -1333,7 +1416,8 @@ static void z_erofs_readahead(struct readahead_control *rac)
struct erofs_sb_info *const sbi = EROFS_I_SB(inode);
unsigned int nr_pages = readahead_count(rac);
- bool sync = (nr_pages <= sbi->ctx.max_sync_decompress_pages);
+ bool sync = (sbi->ctx.readahead_sync_decompress &&
+ nr_pages <= sbi->ctx.max_sync_decompress_pages);
struct z_erofs_decompress_frontend f = DECOMPRESS_FRONTEND_INIT(inode);
struct page *page, *head = NULL;
LIST_HEAD(pagepool);
diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h
index b503b353d4ab..942ee69dff6a 100644
--- a/fs/erofs/zdata.h
+++ b/fs/erofs/zdata.h
@@ -10,6 +10,7 @@
#include "internal.h"
#include "zpvec.h"
+#define Z_EROFS_PCLUSTER_MAX_PAGES (Z_EROFS_PCLUSTER_MAX_SIZE / PAGE_SIZE)
#define Z_EROFS_NR_INLINE_PAGEVECS 3
/*
@@ -59,16 +60,17 @@ struct z_erofs_pcluster {
/* A: point to next chained pcluster or TAILs */
z_erofs_next_pcluster_t next;
- /* A: compressed pages (including multi-usage pages) */
- struct page *compressed_pages[Z_EROFS_CLUSTER_MAX_PAGES];
-
/* A: lower limit of decompressed length and if full length or not */
unsigned int length;
+ /* I: physical cluster size in pages */
+ unsigned short pclusterpages;
+
/* I: compression algorithm format */
unsigned char algorithmformat;
- /* I: bit shift of physical cluster size */
- unsigned char clusterbits;
+
+ /* A: compressed pages (can be cached or inplaced pages) */
+ struct page *compressed_pages[];
};
#define z_erofs_primarycollection(pcluster) (&(pcluster)->primary_collection)
@@ -82,8 +84,6 @@ struct z_erofs_pcluster {
#define Z_EROFS_PCLUSTER_NIL (NULL)
-#define Z_EROFS_WORKGROUP_SIZE sizeof(struct z_erofs_pcluster)
-
struct z_erofs_decompressqueue {
struct super_block *sb;
atomic_t pending_bios;
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 14d2de35110c..e62d813756f2 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -11,17 +11,16 @@
int z_erofs_fill_inode(struct inode *inode)
{
struct erofs_inode *const vi = EROFS_I(inode);
+ struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
- if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) {
+ if (!erofs_sb_has_big_pcluster(sbi) &&
+ vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) {
vi->z_advise = 0;
vi->z_algorithmtype[0] = 0;
vi->z_algorithmtype[1] = 0;
vi->z_logical_clusterbits = LOG_BLOCK_SIZE;
- vi->z_physical_clusterbits[0] = vi->z_logical_clusterbits;
- vi->z_physical_clusterbits[1] = vi->z_logical_clusterbits;
set_bit(EROFS_I_Z_INITED_BIT, &vi->flags);
}
-
inode->i_mapping->a_ops = &z_erofs_aops;
return 0;
}
@@ -52,7 +51,8 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags))
goto out_unlock;
- DBG_BUGON(vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY);
+ DBG_BUGON(!erofs_sb_has_big_pcluster(EROFS_SB(sb)) &&
+ vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY);
pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize +
vi->xattr_isize, 8);
@@ -77,18 +77,22 @@ static int z_erofs_fill_inode_lazy(struct inode *inode)
}
vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7);
- vi->z_physical_clusterbits[0] = vi->z_logical_clusterbits +
- ((h->h_clusterbits >> 3) & 3);
-
- if (vi->z_physical_clusterbits[0] != LOG_BLOCK_SIZE) {
- erofs_err(sb, "unsupported physical clusterbits %u for nid %llu, please upgrade kernel",
- vi->z_physical_clusterbits[0], vi->nid);
- err = -EOPNOTSUPP;
+ if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) &&
+ vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 |
+ Z_EROFS_ADVISE_BIG_PCLUSTER_2)) {
+ erofs_err(sb, "per-inode big pcluster without sb feature for nid %llu",
+ vi->nid);
+ err = -EFSCORRUPTED;
+ goto unmap_done;
+ }
+ if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION &&
+ !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^
+ !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2)) {
+ erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu",
+ vi->nid);
+ err = -EFSCORRUPTED;
goto unmap_done;
}
-
- vi->z_physical_clusterbits[1] = vi->z_logical_clusterbits +
- ((h->h_clusterbits >> 5) & 7);
/* paired with smp_mb() at the beginning of the function */
smp_mb();
set_bit(EROFS_I_Z_INITED_BIT, &vi->flags);
@@ -111,7 +115,7 @@ struct z_erofs_maprecorder {
u8 type;
u16 clusterofs;
u16 delta[2];
- erofs_blk_t pblk;
+ erofs_blk_t pblk, compressedlcs;
};
static int z_erofs_reload_indexes(struct z_erofs_maprecorder *m,
@@ -174,6 +178,15 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m,
case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
m->clusterofs = 1 << vi->z_logical_clusterbits;
m->delta[0] = le16_to_cpu(di->di_u.delta[0]);
+ if (m->delta[0] & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+ if (!(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) {
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
+ }
+ m->compressedlcs = m->delta[0] &
+ ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+ m->delta[0] = 1;
+ }
m->delta[1] = le16_to_cpu(di->di_u.delta[1]);
break;
case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN:
@@ -210,6 +223,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
unsigned int vcnt, base, lo, encodebits, nblk;
int i;
u8 *in, type;
+ bool big_pcluster;
if (1 << amortizedshift == 4)
vcnt = 2;
@@ -218,6 +232,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
else
return -EOPNOTSUPP;
+ big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1;
encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt;
base = round_down(eofs, vcnt << amortizedshift);
in = m->kaddr + base;
@@ -229,7 +244,15 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
m->type = type;
if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
m->clusterofs = 1 << lclusterbits;
- if (i + 1 != vcnt) {
+ if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+ if (!big_pcluster) {
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
+ }
+ m->compressedlcs = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+ m->delta[0] = 1;
+ return 0;
+ } else if (i + 1 != (int)vcnt) {
m->delta[0] = lo;
return 0;
}
@@ -242,22 +265,48 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m,
in, encodebits * (i - 1), &type);
if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
lo = 0;
+ else if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT)
+ lo = 1;
m->delta[0] = lo + 1;
return 0;
}
m->clusterofs = lo;
m->delta[0] = 0;
/* figout out blkaddr (pblk) for HEAD lclusters */
- nblk = 1;
- while (i > 0) {
- --i;
- lo = decode_compactedbits(lclusterbits, lomask,
- in, encodebits * i, &type);
- if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
- i -= lo;
-
- if (i >= 0)
+ if (!big_pcluster) {
+ nblk = 1;
+ while (i > 0) {
+ --i;
+ lo = decode_compactedbits(lclusterbits, lomask,
+ in, encodebits * i, &type);
+ if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD)
+ i -= lo;
+
+ if (i >= 0)
+ ++nblk;
+ }
+ } else {
+ nblk = 0;
+ while (i > 0) {
+ --i;
+ lo = decode_compactedbits(lclusterbits, lomask,
+ in, encodebits * i, &type);
+ if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) {
+ if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) {
+ --i;
+ nblk += lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT;
+ continue;
+ }
+ /* bigpcluster shouldn't have plain d0 == 1 */
+ if (lo <= 1) {
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
+ }
+ i -= lo - 2;
+ continue;
+ }
++nblk;
+ }
}
in += (vcnt << amortizedshift) - sizeof(__le32);
m->pblk = le32_to_cpu(*(__le32 *)in) + nblk;
@@ -381,6 +430,58 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m,
return 0;
}
+static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m,
+ unsigned int initial_lcn)
+{
+ struct erofs_inode *const vi = EROFS_I(m->inode);
+ struct erofs_map_blocks *const map = m->map;
+ const unsigned int lclusterbits = vi->z_logical_clusterbits;
+ unsigned long lcn;
+ int err;
+
+ DBG_BUGON(m->type != Z_EROFS_VLE_CLUSTER_TYPE_PLAIN &&
+ m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD);
+ if (!(map->m_flags & EROFS_MAP_ZIPPED) ||
+ !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) {
+ map->m_plen = 1 << lclusterbits;
+ return 0;
+ }
+
+ lcn = m->lcn + 1;
+ if (m->compressedlcs)
+ goto out;
+ if (lcn == initial_lcn)
+ goto err_bonus_cblkcnt;
+
+ err = z_erofs_load_cluster_from_disk(m, lcn);
+ if (err)
+ return err;
+
+ switch (m->type) {
+ case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
+ if (m->delta[0] != 1)
+ goto err_bonus_cblkcnt;
+ if (m->compressedlcs)
+ break;
+ fallthrough;
+ default:
+ erofs_err(m->inode->i_sb,
+ "cannot found CBLKCNT @ lcn %lu of nid %llu",
+ lcn, vi->nid);
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
+ }
+out:
+ map->m_plen = m->compressedlcs << lclusterbits;
+ return 0;
+err_bonus_cblkcnt:
+ erofs_err(m->inode->i_sb,
+ "bogus CBLKCNT @ lcn %lu of nid %llu",
+ lcn, vi->nid);
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
+}
+
int z_erofs_map_blocks_iter(struct inode *inode,
struct erofs_map_blocks *map,
int flags)
@@ -392,6 +493,7 @@ int z_erofs_map_blocks_iter(struct inode *inode,
};
int err = 0;
unsigned int lclusterbits, endoff;
+ unsigned long initial_lcn;
unsigned long long ofs, end;
trace_z_erofs_map_blocks_iter_enter(inode, map, flags);
@@ -410,10 +512,10 @@ int z_erofs_map_blocks_iter(struct inode *inode,
lclusterbits = vi->z_logical_clusterbits;
ofs = map->m_la;
- m.lcn = ofs >> lclusterbits;
+ initial_lcn = ofs >> lclusterbits;
endoff = ofs & ((1 << lclusterbits) - 1);
- err = z_erofs_load_cluster_from_disk(&m, m.lcn);
+ err = z_erofs_load_cluster_from_disk(&m, initial_lcn);
if (err)
goto unmap_out;
@@ -443,7 +545,7 @@ int z_erofs_map_blocks_iter(struct inode *inode,
m.delta[0] = 1;
fallthrough;
case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD:
- /* get the correspoinding first chunk */
+ /* get the corresponding first chunk */
err = z_erofs_extent_lookback(&m, m.delta[0]);
if (err)
goto unmap_out;
@@ -457,10 +559,12 @@ int z_erofs_map_blocks_iter(struct inode *inode,
}
map->m_llen = end - map->m_la;
- map->m_plen = 1 << lclusterbits;
map->m_pa = blknr_to_addr(m.pblk);
map->m_flags |= EROFS_MAP_MAPPED;
+ err = z_erofs_get_extent_compressedlen(&m, initial_lcn);
+ if (err)
+ goto out;
unmap_out:
if (m.kaddr)
kunmap_atomic(m.kaddr);
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 3196474cbe24..73138ea68342 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -366,8 +366,8 @@ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p)
*
* @ep: Pointer to the eventpoll context.
*
- * Returns: Returns a value different than zero if ready events are available,
- * or zero otherwise.
+ * Return: a value different than %zero if ready events are available,
+ * or %zero otherwise.
*/
static inline int ep_events_available(struct eventpoll *ep)
{
@@ -1023,7 +1023,7 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
}
#endif /* CONFIG_KCMP */
-/**
+/*
* Adds a new entry to the tail of the list in a lockless way, i.e.
* multiple CPUs are allowed to call this function concurrently.
*
@@ -1035,10 +1035,10 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
* completed.
*
* Also an element can be locklessly added to the list only in one
- * direction i.e. either to the tail either to the head, otherwise
+ * direction i.e. either to the tail or to the head, otherwise
* concurrent access will corrupt the list.
*
- * Returns %false if element has been already added to the list, %true
+ * Return: %false if element has been already added to the list, %true
* otherwise.
*/
static inline bool list_add_tail_lockless(struct list_head *new,
@@ -1076,11 +1076,11 @@ static inline bool list_add_tail_lockless(struct list_head *new,
return true;
}
-/**
+/*
* Chains a new epi entry to the tail of the ep->ovflist in a lockless way,
* i.e. multiple CPUs are allowed to call this function concurrently.
*
- * Returns %false if epi element has been already chained, %true otherwise.
+ * Return: %false if epi element has been already chained, %true otherwise.
*/
static inline bool chain_epi_lockless(struct epitem *epi)
{
@@ -1105,8 +1105,8 @@ static inline bool chain_epi_lockless(struct epitem *epi)
* mechanism. It is called by the stored file descriptors when they
* have events to report.
*
- * This callback takes a read lock in order not to content with concurrent
- * events from another file descriptors, thus all modifications to ->rdllist
+ * This callback takes a read lock in order not to contend with concurrent
+ * events from another file descriptor, thus all modifications to ->rdllist
* or ->ovflist are lockless. Read lock is paired with the write lock from
* ep_scan_ready_list(), which stops all list modifications and guarantees
* that lists state is seen correctly.
@@ -1335,8 +1335,8 @@ static int reverse_path_check_proc(struct hlist_head *refs, int depth)
* paths such that we will spend all our time waking up
* eventpoll objects.
*
- * Returns: Returns zero if the proposed links don't create too many paths,
- * -1 otherwise.
+ * Return: %zero if the proposed links don't create too many paths,
+ * %-1 otherwise.
*/
static int reverse_path_check(void)
{
@@ -1734,7 +1734,7 @@ static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms)
}
/**
- * ep_poll - Retrieves ready events, and delivers them to the caller supplied
+ * ep_poll - Retrieves ready events, and delivers them to the caller-supplied
* event buffer.
*
* @ep: Pointer to the eventpoll context.
@@ -1747,7 +1747,7 @@ static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms)
* until at least one event has been retrieved (or an error
* occurred).
*
- * Returns: Returns the number of ready events which have been fetched, or an
+ * Return: the number of ready events which have been fetched, or an
* error code, in case of error.
*/
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
@@ -1774,9 +1774,9 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
/*
* This call is racy: We may or may not see events that are being added
- * to the ready list under the lock (e.g., in IRQ callbacks). For, cases
+ * to the ready list under the lock (e.g., in IRQ callbacks). For cases
* with a non-zero timeout, this thread will check the ready list under
- * lock and will added to the wait queue. For, cases with a zero
+ * lock and will add to the wait queue. For cases with a zero
* timeout, the user by definition should not care and will have to
* recheck again.
*/
@@ -1869,15 +1869,15 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
/**
* ep_loop_check_proc - verify that adding an epoll file inside another
- * epoll structure, does not violate the constraints, in
+ * epoll structure does not violate the constraints, in
* terms of closed loops, or too deep chains (which can
* result in excessive stack usage).
*
- * @priv: Pointer to the epoll file to be currently checked.
+ * @ep: the &struct eventpoll to be currently checked.
* @depth: Current depth of the path being checked.
*
- * Returns: Returns zero if adding the epoll @file inside current epoll
- * structure @ep does not violate the constraints, or -1 otherwise.
+ * Return: %zero if adding the epoll @file inside current epoll
+ * structure @ep does not violate the constraints, or %-1 otherwise.
*/
static int ep_loop_check_proc(struct eventpoll *ep, int depth)
{
@@ -1919,14 +1919,14 @@ static int ep_loop_check_proc(struct eventpoll *ep, int depth)
/**
* ep_loop_check - Performs a check to verify that adding an epoll file (@to)
- * into another epoll file (represented by @from) does not create
+ * into another epoll file (represented by @ep) does not create
* closed loops or too deep chains.
*
- * @from: Pointer to the epoll we are inserting into.
+ * @ep: Pointer to the epoll we are inserting into.
* @to: Pointer to the epoll to be inserted.
*
- * Returns: Returns zero if adding the epoll @to inside the epoll @from
- * does not violate the constraints, or -1 otherwise.
+ * Return: %zero if adding the epoll @to inside the epoll @from
+ * does not violate the constraints, or %-1 otherwise.
*/
static int ep_loop_check(struct eventpoll *ep, struct eventpoll *to)
{
@@ -2074,8 +2074,8 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
ep = f.file->private_data;
/*
- * When we insert an epoll file descriptor, inside another epoll file
- * descriptor, there is the change of creating closed loops, which are
+ * When we insert an epoll file descriptor inside another epoll file
+ * descriptor, there is the chance of creating closed loops, which are
* better be handled here, than in more critical paths. While we are
* checking for loops we also determine the list of files reachable
* and hang them on the tfile_check_list, so we can check that we
@@ -2113,7 +2113,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds,
}
/*
- * Try to lookup the file inside our RB tree, Since we grabbed "mtx"
+ * Try to lookup the file inside our RB tree. Since we grabbed "mtx"
* above, we can be sure to be able to use the item looked up by
* ep_find() till we release the mutex.
*/
diff --git a/fs/locks.c b/fs/locks.c
index 6125d2de39b8..5c42363aa811 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2369,7 +2369,6 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock)
if (flock->l_pid != 0)
goto out;
- cmd = F_GETLK;
fl->fl_flags |= FL_OFDLCK;
fl->fl_owner = filp;
}
@@ -2825,7 +2824,7 @@ struct locks_iterator {
};
static void lock_get_status(struct seq_file *f, struct file_lock *fl,
- loff_t id, char *pfx)
+ loff_t id, char *pfx, int repeat)
{
struct inode *inode = NULL;
unsigned int fl_pid;
@@ -2841,7 +2840,11 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
if (fl->fl_file != NULL)
inode = locks_inode(fl->fl_file);
- seq_printf(f, "%lld:%s ", id, pfx);
+ seq_printf(f, "%lld: ", id);
+
+ if (repeat)
+ seq_printf(f, "%*s", repeat - 1 + (int)strlen(pfx), pfx);
+
if (IS_POSIX(fl)) {
if (fl->fl_flags & FL_ACCESS)
seq_puts(f, "ACCESS");
@@ -2903,21 +2906,64 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
}
}
+static struct file_lock *get_next_blocked_member(struct file_lock *node)
+{
+ struct file_lock *tmp;
+
+ /* NULL node or root node */
+ if (node == NULL || node->fl_blocker == NULL)
+ return NULL;
+
+ /* Next member in the linked list could be itself */
+ tmp = list_next_entry(node, fl_blocked_member);
+ if (list_entry_is_head(tmp, &node->fl_blocker->fl_blocked_requests, fl_blocked_member)
+ || tmp == node) {
+ return NULL;
+ }
+
+ return tmp;
+}
+
static int locks_show(struct seq_file *f, void *v)
{
struct locks_iterator *iter = f->private;
- struct file_lock *fl, *bfl;
+ struct file_lock *cur, *tmp;
struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
+ int level = 0;
- fl = hlist_entry(v, struct file_lock, fl_link);
+ cur = hlist_entry(v, struct file_lock, fl_link);
- if (locks_translate_pid(fl, proc_pidns) == 0)
+ if (locks_translate_pid(cur, proc_pidns) == 0)
return 0;
- lock_get_status(f, fl, iter->li_pos, "");
+ /* View this crossed linked list as a binary tree, the first member of fl_blocked_requests
+ * is the left child of current node, the next silibing in fl_blocked_member is the
+ * right child, we can alse get the parent of current node from fl_blocker, so this
+ * question becomes traversal of a binary tree
+ */
+ while (cur != NULL) {
+ if (level)
+ lock_get_status(f, cur, iter->li_pos, "-> ", level);
+ else
+ lock_get_status(f, cur, iter->li_pos, "", level);
- list_for_each_entry(bfl, &fl->fl_blocked_requests, fl_blocked_member)
- lock_get_status(f, bfl, iter->li_pos, " ->");
+ if (!list_empty(&cur->fl_blocked_requests)) {
+ /* Turn left */
+ cur = list_first_entry_or_null(&cur->fl_blocked_requests,
+ struct file_lock, fl_blocked_member);
+ level++;
+ } else {
+ /* Turn right */
+ tmp = get_next_blocked_member(cur);
+ /* Fall back to parent node */
+ while (tmp == NULL && cur->fl_blocker != NULL) {
+ cur = cur->fl_blocker;
+ level--;
+ tmp = get_next_blocked_member(cur);
+ }
+ cur = tmp;
+ }
+ }
return 0;
}
@@ -2938,7 +2984,7 @@ static void __show_fd_locks(struct seq_file *f,
(*id)++;
seq_puts(f, "lock:\t");
- lock_get_status(f, fl, *id, "");
+ lock_get_status(f, fl, *id, "", 0);
}
}
diff --git a/fs/namespace.c b/fs/namespace.c
index 56bb5a5fdc0d..f63337828e1c 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1242,8 +1242,9 @@ struct vfsmount *mntget(struct vfsmount *mnt)
}
EXPORT_SYMBOL(mntget);
-/* path_is_mountpoint() - Check if path is a mount in the current
- * namespace.
+/**
+ * path_is_mountpoint() - Check if path is a mount in the current namespace.
+ * @path: path to check
*
* d_mountpoint() can only be used reliably to establish if a dentry is
* not mounted in any namespace and that common case is handled inline.
@@ -1369,7 +1370,7 @@ void mnt_cursor_del(struct mnt_namespace *ns, struct mount *cursor)
/**
* may_umount_tree - check if a mount tree is busy
- * @mnt: root of mount tree
+ * @m: root of mount tree
*
* This is called to check if a tree of mounts has any
* open files, pwds, chroots or sub mounts that are
@@ -1939,10 +1940,11 @@ void drop_collected_mounts(struct vfsmount *mnt)
/**
* clone_private_mount - create a private clone of a path
+ * @path: path to clone
*
- * This creates a new vfsmount, which will be the clone of @path. The new will
- * not be attached anywhere in the namespace and will be private (i.e. changes
- * to the originating mount won't be propagated into this).
+ * This creates a new vfsmount, which will be the clone of @path. The new mount
+ * will not be attached anywhere in the namespace and will be private (i.e.
+ * changes to the originating mount won't be propagated into this).
*
* Release with mntput().
*/
diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c
index 79c563c1a5e8..5a5bd85d08f8 100644
--- a/fs/nfs_common/nfsacl.c
+++ b/fs/nfs_common/nfsacl.c
@@ -136,6 +136,77 @@ int nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
}
EXPORT_SYMBOL_GPL(nfsacl_encode);
+/**
+ * nfs_stream_encode_acl - Encode an NFSv3 ACL
+ *
+ * @xdr: an xdr_stream positioned to receive an encoded ACL
+ * @inode: inode of file whose ACL this is
+ * @acl: posix_acl to encode
+ * @encode_entries: whether to encode ACEs as well
+ * @typeflag: ACL type: NFS_ACL_DEFAULT or zero
+ *
+ * Return values:
+ * %false: The ACL could not be encoded
+ * %true: @xdr is advanced to the next available position
+ */
+bool nfs_stream_encode_acl(struct xdr_stream *xdr, struct inode *inode,
+ struct posix_acl *acl, int encode_entries,
+ int typeflag)
+{
+ const size_t elem_size = XDR_UNIT * 3;
+ u32 entries = (acl && acl->a_count) ? max_t(int, acl->a_count, 4) : 0;
+ struct nfsacl_encode_desc nfsacl_desc = {
+ .desc = {
+ .elem_size = elem_size,
+ .array_len = encode_entries ? entries : 0,
+ .xcode = xdr_nfsace_encode,
+ },
+ .acl = acl,
+ .typeflag = typeflag,
+ .uid = inode->i_uid,
+ .gid = inode->i_gid,
+ };
+ struct nfsacl_simple_acl aclbuf;
+ unsigned int base;
+ int err;
+
+ if (entries > NFS_ACL_MAX_ENTRIES)
+ return false;
+ if (xdr_stream_encode_u32(xdr, entries) < 0)
+ return false;
+
+ if (encode_entries && acl && acl->a_count == 3) {
+ struct posix_acl *acl2 = &aclbuf.acl;
+
+ /* Avoid the use of posix_acl_alloc(). nfsacl_encode() is
+ * invoked in contexts where a memory allocation failure is
+ * fatal. Fortunately this fake ACL is small enough to
+ * construct on the stack. */
+ posix_acl_init(acl2, 4);
+
+ /* Insert entries in canonical order: other orders seem
+ to confuse Solaris VxFS. */
+ acl2->a_entries[0] = acl->a_entries[0]; /* ACL_USER_OBJ */
+ acl2->a_entries[1] = acl->a_entries[1]; /* ACL_GROUP_OBJ */
+ acl2->a_entries[2] = acl->a_entries[1]; /* ACL_MASK */
+ acl2->a_entries[2].e_tag = ACL_MASK;
+ acl2->a_entries[3] = acl->a_entries[2]; /* ACL_OTHER */
+ nfsacl_desc.acl = acl2;
+ }
+
+ base = xdr_stream_pos(xdr);
+ if (!xdr_reserve_space(xdr, XDR_UNIT +
+ elem_size * nfsacl_desc.desc.array_len))
+ return false;
+ err = xdr_encode_array2(xdr->buf, base, &nfsacl_desc.desc);
+ if (err)
+ return false;
+
+ return true;
+}
+EXPORT_SYMBOL_GPL(nfs_stream_encode_acl);
+
+
struct nfsacl_decode_desc {
struct xdr_array2_desc desc;
unsigned int count;
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index d6cff5fbe705..5fa38ad9e7e3 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -99,7 +99,7 @@ config NFSD_BLOCKLAYOUT
help
This option enables support for the exporting pNFS block layouts
in the kernel's NFS server. The pNFS block layout enables NFS
- clients to directly perform I/O to block devices accesible to both
+ clients to directly perform I/O to block devices accessible to both
the server and the clients. See RFC 5663 for more details.
If unsure, say N.
@@ -113,7 +113,7 @@ config NFSD_SCSILAYOUT
help
This option enables support for the exporting pNFS SCSI layouts
in the kernel's NFS server. The pNFS SCSI layout enables NFS
- clients to directly perform I/O to SCSI devices accesible to both
+ clients to directly perform I/O to SCSI devices accessible to both
the server and the clients. See draft-ietf-nfsv4-scsi-layout for
more details.
@@ -127,7 +127,7 @@ config NFSD_FLEXFILELAYOUT
This option enables support for the exporting pNFS Flex File
layouts in the kernel's NFS server. The pNFS Flex File layout
enables NFS clients to directly perform I/O to NFSv3 devices
- accesible to both the server and the clients. See
+ accessible to both the server and the clients. See
draft-ietf-nfsv4-flex-files for more details.
Warning, this server implements the bare minimum functionality
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index c330f5bd0cf3..a75abeb1e698 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -51,9 +51,6 @@ struct nfsd_net {
bool grace_ended;
time64_t boot_time;
- /* internal mount of the "nfsd" pseudofilesystem: */
- struct vfsmount *nfsd_mnt;
-
struct dentry *nfsd_client_dir;
/*
@@ -130,6 +127,9 @@ struct nfsd_net {
wait_queue_head_t ntf_wq;
atomic_t ntf_refcnt;
+ /* Allow umount to wait for nfsd state cleanup */
+ struct completion nfsd_shutdown_complete;
+
/*
* clientid and stateid data for construction of net unique COPY
* stateids.
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 855e17772eba..4b43929c1f25 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -242,79 +242,61 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
/* GETACL */
static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_getaclres *resp = rqstp->rq_resp;
struct dentry *dentry = resp->fh.fh_dentry;
struct inode *inode;
- struct kvec *head = rqstp->rq_res.head;
- unsigned int base;
- int n;
int w;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- return xdr_ressize_check(rqstp, p);
+ if (!svcxdr_encode_stat(xdr, resp->status))
+ return 0;
- /*
- * Since this is version 2, the check for nfserr in
- * nfsd_dispatch actually ensures the following cannot happen.
- * However, it seems fragile to depend on that.
- */
if (dentry == NULL || d_really_is_negative(dentry))
- return 0;
+ return 1;
inode = d_inode(dentry);
- p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
- *p++ = htonl(resp->mask);
- if (!xdr_ressize_check(rqstp, p))
+ if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->mask) < 0)
return 0;
- base = (char *)p - (char *)head->iov_base;
rqstp->rq_res.page_len = w = nfsacl_size(
(resp->mask & NFS_ACL) ? resp->acl_access : NULL,
(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
while (w > 0) {
if (!*(rqstp->rq_next_page++))
- return 0;
+ return 1;
w -= PAGE_SIZE;
}
- n = nfsacl_encode(&rqstp->rq_res, base, inode,
- resp->acl_access,
- resp->mask & NFS_ACL, 0);
- if (n > 0)
- n = nfsacl_encode(&rqstp->rq_res, base + n, inode,
- resp->acl_default,
- resp->mask & NFS_DFACL,
- NFS_ACL_DEFAULT);
- return (n > 0);
-}
-
-static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p)
-{
- struct nfsd_attrstat *resp = rqstp->rq_resp;
-
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- goto out;
+ if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access,
+ resp->mask & NFS_ACL, 0))
+ return 0;
+ if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default,
+ resp->mask & NFS_DFACL, NFS_ACL_DEFAULT))
+ return 0;
- p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
-out:
- return xdr_ressize_check(rqstp, p);
+ return 1;
}
/* ACCESS */
static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_accessres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- goto out;
+ if (!svcxdr_encode_stat(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->access) < 0)
+ return 0;
+ break;
+ }
- p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
- *p++ = htonl(resp->access);
-out:
- return xdr_ressize_check(rqstp, p);
+ return 1;
}
/*
@@ -329,13 +311,6 @@ static void nfsaclsvc_release_getacl(struct svc_rqst *rqstp)
posix_acl_release(resp->acl_default);
}
-static void nfsaclsvc_release_attrstat(struct svc_rqst *rqstp)
-{
- struct nfsd_attrstat *resp = rqstp->rq_resp;
-
- fh_put(&resp->fh);
-}
-
static void nfsaclsvc_release_access(struct svc_rqst *rqstp)
{
struct nfsd3_accessres *resp = rqstp->rq_resp;
@@ -375,8 +350,8 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
[ACLPROC2_SETACL] = {
.pc_func = nfsacld_proc_setacl,
.pc_decode = nfsaclsvc_decode_setaclargs,
- .pc_encode = nfsaclsvc_encode_attrstatres,
- .pc_release = nfsaclsvc_release_attrstat,
+ .pc_encode = nfssvc_encode_attrstatres,
+ .pc_release = nfssvc_release_attrstat,
.pc_argsize = sizeof(struct nfsd3_setaclargs),
.pc_ressize = sizeof(struct nfsd_attrstat),
.pc_cachetype = RC_NOCACHE,
@@ -386,8 +361,8 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = {
[ACLPROC2_GETATTR] = {
.pc_func = nfsacld_proc_getattr,
.pc_decode = nfssvc_decode_fhandleargs,
- .pc_encode = nfsaclsvc_encode_attrstatres,
- .pc_release = nfsaclsvc_release_attrstat,
+ .pc_encode = nfssvc_encode_attrstatres,
+ .pc_release = nfssvc_release_attrstat,
.pc_argsize = sizeof(struct nfsd_fhandle),
.pc_ressize = sizeof(struct nfsd_attrstat),
.pc_cachetype = RC_NOCACHE,
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 9a6f18d74d14..a1591feeea22 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -168,22 +168,25 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
/* GETACL */
static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_getaclres *resp = rqstp->rq_resp;
struct dentry *dentry = resp->fh.fh_dentry;
+ struct kvec *head = rqstp->rq_res.head;
+ struct inode *inode = d_inode(dentry);
+ unsigned int base;
+ int n;
+ int w;
- *p++ = resp->status;
- p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
- if (resp->status == 0 && dentry && d_really_is_positive(dentry)) {
- struct inode *inode = d_inode(dentry);
- struct kvec *head = rqstp->rq_res.head;
- unsigned int base;
- int n;
- int w;
-
- *p++ = htonl(resp->mask);
- if (!xdr_ressize_check(rqstp, p))
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->mask) < 0)
return 0;
- base = (char *)p - (char *)head->iov_base;
+
+ base = (char *)xdr->p - (char *)head->iov_base;
rqstp->rq_res.page_len = w = nfsacl_size(
(resp->mask & NFS_ACL) ? resp->acl_access : NULL,
@@ -204,9 +207,11 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
NFS_ACL_DEFAULT);
if (n <= 0)
return 0;
- } else
- if (!xdr_ressize_check(rqstp, p))
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
+ }
return 1;
}
@@ -214,11 +219,11 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
/* SETACL */
static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
- return xdr_ressize_check(rqstp, p);
+ return svcxdr_encode_nfsstat3(xdr, resp->status) &&
+ svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh);
}
/*
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 8675851199f8..17715a6c7a40 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -126,14 +126,15 @@ nfsd3_proc_readlink(struct svc_rqst *rqstp)
{
struct nfsd_fhandle *argp = rqstp->rq_argp;
struct nfsd3_readlinkres *resp = rqstp->rq_resp;
- char *buffer = page_address(*(rqstp->rq_next_page++));
dprintk("nfsd: READLINK(3) %s\n", SVCFH_fmt(&argp->fh));
/* Read the symlink. */
fh_copy(&resp->fh, &argp->fh);
resp->len = NFS3_MAXPATHLEN;
- resp->status = nfsd_readlink(rqstp, &resp->fh, buffer, &resp->len);
+ resp->pages = rqstp->rq_next_page++;
+ resp->status = nfsd_readlink(rqstp, &resp->fh,
+ page_address(*resp->pages), &resp->len);
return rpc_success;
}
@@ -158,6 +159,7 @@ nfsd3_proc_read(struct svc_rqst *rqstp)
v = 0;
len = argp->count;
+ resp->pages = rqstp->rq_next_page;
while (len > 0) {
struct page *page = *(rqstp->rq_next_page++);
@@ -439,17 +441,30 @@ static void nfsd3_init_dirlist_pages(struct svc_rqst *rqstp,
struct nfsd3_readdirres *resp,
int count)
{
+ struct xdr_buf *buf = &resp->dirlist;
+ struct xdr_stream *xdr = &resp->xdr;
+
count = min_t(u32, count, svc_max_payload(rqstp));
- /* Convert byte count to number of words (i.e. >> 2),
- * and reserve room for the NULL ptr & eof flag (-2 words) */
- resp->buflen = (count >> 2) - 2;
+ memset(buf, 0, sizeof(*buf));
- resp->buffer = page_address(*rqstp->rq_next_page);
+ /* Reserve room for the NULL ptr & eof flag (-2 words) */
+ buf->buflen = count - XDR_UNIT * 2;
+ buf->pages = rqstp->rq_next_page;
while (count > 0) {
rqstp->rq_next_page++;
count -= PAGE_SIZE;
}
+
+ /* This is xdr_init_encode(), but it assumes that
+ * the head kvec has already been consumed. */
+ xdr_set_scratch_buffer(xdr, NULL, 0);
+ xdr->buf = buf;
+ xdr->page_ptr = buf->pages;
+ xdr->iov = NULL;
+ xdr->p = page_address(*buf->pages);
+ xdr->end = xdr->p + (PAGE_SIZE >> 2);
+ xdr->rqst = NULL;
}
/*
@@ -460,10 +475,7 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp)
{
struct nfsd3_readdirargs *argp = rqstp->rq_argp;
struct nfsd3_readdirres *resp = rqstp->rq_resp;
- int count = 0;
loff_t offset;
- struct page **p;
- caddr_t page_addr = NULL;
dprintk("nfsd: READDIR(3) %s %d bytes at %d\n",
SVCFH_fmt(&argp->fh),
@@ -471,39 +483,18 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp)
nfsd3_init_dirlist_pages(rqstp, resp, argp->count);
- /* Read directory and encode entries on the fly */
fh_copy(&resp->fh, &argp->fh);
-
resp->common.err = nfs_ok;
+ resp->cookie_offset = 0;
resp->rqstp = rqstp;
offset = argp->cookie;
-
resp->status = nfsd_readdir(rqstp, &resp->fh, &offset,
- &resp->common, nfs3svc_encode_entry);
+ &resp->common, nfs3svc_encode_entry3);
memcpy(resp->verf, argp->verf, 8);
- count = 0;
- for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) {
- page_addr = page_address(*p);
+ nfs3svc_encode_cookie3(resp, offset);
- if (((caddr_t)resp->buffer >= page_addr) &&
- ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) {
- count += (caddr_t)resp->buffer - page_addr;
- break;
- }
- count += PAGE_SIZE;
- }
- resp->count = count >> 2;
- if (resp->offset) {
- if (unlikely(resp->offset1)) {
- /* we ended up with offset on a page boundary */
- *resp->offset = htonl(offset >> 32);
- *resp->offset1 = htonl(offset & 0xffffffff);
- resp->offset1 = NULL;
- } else {
- xdr_encode_hyper(resp->offset, offset);
- }
- resp->offset = NULL;
- }
+ /* Recycle only pages that were part of the reply */
+ rqstp->rq_next_page = resp->xdr.page_ptr + 1;
return rpc_success;
}
@@ -517,10 +508,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp)
{
struct nfsd3_readdirargs *argp = rqstp->rq_argp;
struct nfsd3_readdirres *resp = rqstp->rq_resp;
- int count = 0;
loff_t offset;
- struct page **p;
- caddr_t page_addr = NULL;
dprintk("nfsd: READDIR+(3) %s %d bytes at %d\n",
SVCFH_fmt(&argp->fh),
@@ -528,10 +516,9 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp)
nfsd3_init_dirlist_pages(rqstp, resp, argp->count);
- /* Read directory and encode entries on the fly */
fh_copy(&resp->fh, &argp->fh);
-
resp->common.err = nfs_ok;
+ resp->cookie_offset = 0;
resp->rqstp = rqstp;
offset = argp->cookie;
@@ -545,30 +532,12 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp)
}
resp->status = nfsd_readdir(rqstp, &resp->fh, &offset,
- &resp->common, nfs3svc_encode_entry_plus);
+ &resp->common, nfs3svc_encode_entryplus3);
memcpy(resp->verf, argp->verf, 8);
- for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) {
- page_addr = page_address(*p);
+ nfs3svc_encode_cookie3(resp, offset);
- if (((caddr_t)resp->buffer >= page_addr) &&
- ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) {
- count += (caddr_t)resp->buffer - page_addr;
- break;
- }
- count += PAGE_SIZE;
- }
- resp->count = count >> 2;
- if (resp->offset) {
- if (unlikely(resp->offset1)) {
- /* we ended up with offset on a page boundary */
- *resp->offset = htonl(offset >> 32);
- *resp->offset1 = htonl(offset & 0xffffffff);
- resp->offset1 = NULL;
- } else {
- xdr_encode_hyper(resp->offset, offset);
- }
- resp->offset = NULL;
- }
+ /* Recycle only pages that were part of the reply */
+ rqstp->rq_next_page = resp->xdr.page_ptr + 1;
out:
return rpc_success;
@@ -736,7 +705,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
[NFS3PROC_GETATTR] = {
.pc_func = nfsd3_proc_getattr,
.pc_decode = nfs3svc_decode_fhandleargs,
- .pc_encode = nfs3svc_encode_attrstatres,
+ .pc_encode = nfs3svc_encode_getattrres,
.pc_release = nfs3svc_release_fhandle,
.pc_argsize = sizeof(struct nfsd_fhandle),
.pc_ressize = sizeof(struct nfsd3_attrstatres),
@@ -758,7 +727,7 @@ static const struct svc_procedure nfsd_procedures3[22] = {
[NFS3PROC_LOOKUP] = {
.pc_func = nfsd3_proc_lookup,
.pc_decode = nfs3svc_decode_diropargs,
- .pc_encode = nfs3svc_encode_diropres,
+ .pc_encode = nfs3svc_encode_lookupres,
.pc_release = nfs3svc_release_fhandle2,
.pc_argsize = sizeof(struct nfsd3_diropargs),
.pc_ressize = sizeof(struct nfsd3_diropres),
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 9d9a01ce0b27..0a5ebc52e6a9 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -14,13 +14,26 @@
#include "netns.h"
#include "vfs.h"
-#define NFSDDBG_FACILITY NFSDDBG_XDR
+/*
+ * Force construction of an empty post-op attr
+ */
+static const struct svc_fh nfs3svc_null_fh = {
+ .fh_no_wcc = true,
+};
+/*
+ * time_delta. {1, 0} means the server is accurate only
+ * to the nearest second.
+ */
+static const struct timespec64 nfs3svc_time_delta = {
+ .tv_sec = 1,
+ .tv_nsec = 0,
+};
/*
* Mapping of S_IF* types to NFS file types
*/
-static u32 nfs3_ftypes[] = {
+static const u32 nfs3_ftypes[] = {
NF3NON, NF3FIFO, NF3CHR, NF3BAD,
NF3DIR, NF3BAD, NF3BLK, NF3BAD,
NF3REG, NF3BAD, NF3LNK, NF3BAD,
@@ -33,9 +46,11 @@ static u32 nfs3_ftypes[] = {
*/
static __be32 *
-encode_time3(__be32 *p, struct timespec64 *time)
+encode_nfstime3(__be32 *p, const struct timespec64 *time)
{
- *p++ = htonl((u32) time->tv_sec); *p++ = htonl(time->tv_nsec);
+ *p++ = cpu_to_be32((u32)time->tv_sec);
+ *p++ = cpu_to_be32(time->tv_nsec);
+
return p;
}
@@ -82,14 +97,80 @@ svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp)
return true;
}
-static __be32 *
-encode_fh(__be32 *p, struct svc_fh *fhp)
+/**
+ * svcxdr_encode_nfsstat3 - Encode an NFSv3 status code
+ * @xdr: XDR stream
+ * @status: status value to encode
+ *
+ * Return values:
+ * %false: Send buffer space was exhausted
+ * %true: Success
+ */
+bool
+svcxdr_encode_nfsstat3(struct xdr_stream *xdr, __be32 status)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, sizeof(status));
+ if (!p)
+ return false;
+ *p = status;
+
+ return true;
+}
+
+static bool
+svcxdr_encode_nfs_fh3(struct xdr_stream *xdr, const struct svc_fh *fhp)
{
- unsigned int size = fhp->fh_handle.fh_size;
- *p++ = htonl(size);
- if (size) p[XDR_QUADLEN(size)-1]=0;
+ u32 size = fhp->fh_handle.fh_size;
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, XDR_UNIT + size);
+ if (!p)
+ return false;
+ *p++ = cpu_to_be32(size);
+ if (size)
+ p[XDR_QUADLEN(size) - 1] = 0;
memcpy(p, &fhp->fh_handle.fh_base, size);
- return p + XDR_QUADLEN(size);
+
+ return true;
+}
+
+static bool
+svcxdr_encode_post_op_fh3(struct xdr_stream *xdr, const struct svc_fh *fhp)
+{
+ if (xdr_stream_encode_item_present(xdr) < 0)
+ return false;
+ if (!svcxdr_encode_nfs_fh3(xdr, fhp))
+ return false;
+
+ return true;
+}
+
+static bool
+svcxdr_encode_cookieverf3(struct xdr_stream *xdr, const __be32 *verf)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, NFS3_COOKIEVERFSIZE);
+ if (!p)
+ return false;
+ memcpy(p, verf, NFS3_COOKIEVERFSIZE);
+
+ return true;
+}
+
+static bool
+svcxdr_encode_writeverf3(struct xdr_stream *xdr, const __be32 *verf)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, NFS3_WRITEVERFSIZE);
+ if (!p)
+ return false;
+ memcpy(p, verf, NFS3_WRITEVERFSIZE);
+
+ return true;
}
static bool
@@ -253,115 +334,157 @@ svcxdr_decode_devicedata3(struct svc_rqst *rqstp, struct xdr_stream *xdr,
svcxdr_decode_specdata3(xdr, args);
}
-static __be32 *encode_fsid(__be32 *p, struct svc_fh *fhp)
+static bool
+svcxdr_encode_fattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ const struct svc_fh *fhp, const struct kstat *stat)
{
- u64 f;
+ struct user_namespace *userns = nfsd_user_namespace(rqstp);
+ __be32 *p;
+ u64 fsid;
+
+ p = xdr_reserve_space(xdr, XDR_UNIT * 21);
+ if (!p)
+ return false;
+
+ *p++ = cpu_to_be32(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]);
+ *p++ = cpu_to_be32((u32)(stat->mode & S_IALLUGO));
+ *p++ = cpu_to_be32((u32)stat->nlink);
+ *p++ = cpu_to_be32((u32)from_kuid_munged(userns, stat->uid));
+ *p++ = cpu_to_be32((u32)from_kgid_munged(userns, stat->gid));
+ if (S_ISLNK(stat->mode) && stat->size > NFS3_MAXPATHLEN)
+ p = xdr_encode_hyper(p, (u64)NFS3_MAXPATHLEN);
+ else
+ p = xdr_encode_hyper(p, (u64)stat->size);
+
+ /* used */
+ p = xdr_encode_hyper(p, ((u64)stat->blocks) << 9);
+
+ /* rdev */
+ *p++ = cpu_to_be32((u32)MAJOR(stat->rdev));
+ *p++ = cpu_to_be32((u32)MINOR(stat->rdev));
+
switch(fsid_source(fhp)) {
- default:
- case FSIDSOURCE_DEV:
- p = xdr_encode_hyper(p, (u64)huge_encode_dev
- (fhp->fh_dentry->d_sb->s_dev));
- break;
case FSIDSOURCE_FSID:
- p = xdr_encode_hyper(p, (u64) fhp->fh_export->ex_fsid);
+ fsid = (u64)fhp->fh_export->ex_fsid;
break;
case FSIDSOURCE_UUID:
- f = ((u64*)fhp->fh_export->ex_uuid)[0];
- f ^= ((u64*)fhp->fh_export->ex_uuid)[1];
- p = xdr_encode_hyper(p, f);
+ fsid = ((u64 *)fhp->fh_export->ex_uuid)[0];
+ fsid ^= ((u64 *)fhp->fh_export->ex_uuid)[1];
break;
+ default:
+ fsid = (u64)huge_encode_dev(fhp->fh_dentry->d_sb->s_dev);
}
- return p;
-}
+ p = xdr_encode_hyper(p, fsid);
-static __be32 *
-encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
- struct kstat *stat)
-{
- struct user_namespace *userns = nfsd_user_namespace(rqstp);
- *p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]);
- *p++ = htonl((u32) (stat->mode & S_IALLUGO));
- *p++ = htonl((u32) stat->nlink);
- *p++ = htonl((u32) from_kuid_munged(userns, stat->uid));
- *p++ = htonl((u32) from_kgid_munged(userns, stat->gid));
- if (S_ISLNK(stat->mode) && stat->size > NFS3_MAXPATHLEN) {
- p = xdr_encode_hyper(p, (u64) NFS3_MAXPATHLEN);
- } else {
- p = xdr_encode_hyper(p, (u64) stat->size);
- }
- p = xdr_encode_hyper(p, ((u64)stat->blocks) << 9);
- *p++ = htonl((u32) MAJOR(stat->rdev));
- *p++ = htonl((u32) MINOR(stat->rdev));
- p = encode_fsid(p, fhp);
+ /* fileid */
p = xdr_encode_hyper(p, stat->ino);
- p = encode_time3(p, &stat->atime);
- p = encode_time3(p, &stat->mtime);
- p = encode_time3(p, &stat->ctime);
- return p;
+ p = encode_nfstime3(p, &stat->atime);
+ p = encode_nfstime3(p, &stat->mtime);
+ encode_nfstime3(p, &stat->ctime);
+
+ return true;
}
-static __be32 *
-encode_saved_post_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
+static bool
+svcxdr_encode_wcc_attr(struct xdr_stream *xdr, const struct svc_fh *fhp)
{
- /* Attributes to follow */
- *p++ = xdr_one;
- return encode_fattr3(rqstp, p, fhp, &fhp->fh_post_attr);
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, XDR_UNIT * 6);
+ if (!p)
+ return false;
+ p = xdr_encode_hyper(p, (u64)fhp->fh_pre_size);
+ p = encode_nfstime3(p, &fhp->fh_pre_mtime);
+ encode_nfstime3(p, &fhp->fh_pre_ctime);
+
+ return true;
}
-/*
- * Encode post-operation attributes.
- * The inode may be NULL if the call failed because of a stale file
- * handle. In this case, no attributes are returned.
- */
-static __be32 *
-encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
+static bool
+svcxdr_encode_pre_op_attr(struct xdr_stream *xdr, const struct svc_fh *fhp)
{
- struct dentry *dentry = fhp->fh_dentry;
- if (!fhp->fh_no_wcc && dentry && d_really_is_positive(dentry)) {
- __be32 err;
- struct kstat stat;
-
- err = fh_getattr(fhp, &stat);
- if (!err) {
- *p++ = xdr_one; /* attributes follow */
- lease_get_mtime(d_inode(dentry), &stat.mtime);
- return encode_fattr3(rqstp, p, fhp, &stat);
- }
+ if (!fhp->fh_pre_saved) {
+ if (xdr_stream_encode_item_absent(xdr) < 0)
+ return false;
+ return true;
}
- *p++ = xdr_zero;
- return p;
+
+ if (xdr_stream_encode_item_present(xdr) < 0)
+ return false;
+ return svcxdr_encode_wcc_attr(xdr, fhp);
}
-/* Helper for NFSv3 ACLs */
-__be32 *
-nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
+/**
+ * svcxdr_encode_post_op_attr - Encode NFSv3 post-op attributes
+ * @rqstp: Context of a completed RPC transaction
+ * @xdr: XDR stream
+ * @fhp: File handle to encode
+ *
+ * Return values:
+ * %false: Send buffer space was exhausted
+ * %true: Success
+ */
+bool
+svcxdr_encode_post_op_attr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ const struct svc_fh *fhp)
{
- return encode_post_op_attr(rqstp, p, fhp);
+ struct dentry *dentry = fhp->fh_dentry;
+ struct kstat stat;
+
+ /*
+ * The inode may be NULL if the call failed because of a
+ * stale file handle. In this case, no attributes are
+ * returned.
+ */
+ if (fhp->fh_no_wcc || !dentry || !d_really_is_positive(dentry))
+ goto no_post_op_attrs;
+ if (fh_getattr(fhp, &stat) != nfs_ok)
+ goto no_post_op_attrs;
+
+ if (xdr_stream_encode_item_present(xdr) < 0)
+ return false;
+ lease_get_mtime(d_inode(dentry), &stat.mtime);
+ if (!svcxdr_encode_fattr3(rqstp, xdr, fhp, &stat))
+ return false;
+
+ return true;
+
+no_post_op_attrs:
+ return xdr_stream_encode_item_absent(xdr) > 0;
}
/*
- * Enocde weak cache consistency data
+ * Encode weak cache consistency data
*/
-static __be32 *
-encode_wcc_data(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp)
+static bool
+svcxdr_encode_wcc_data(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ const struct svc_fh *fhp)
{
- struct dentry *dentry = fhp->fh_dentry;
-
- if (dentry && d_really_is_positive(dentry) && fhp->fh_post_saved) {
- if (fhp->fh_pre_saved) {
- *p++ = xdr_one;
- p = xdr_encode_hyper(p, (u64) fhp->fh_pre_size);
- p = encode_time3(p, &fhp->fh_pre_mtime);
- p = encode_time3(p, &fhp->fh_pre_ctime);
- } else {
- *p++ = xdr_zero;
- }
- return encode_saved_post_attr(rqstp, p, fhp);
- }
- /* no pre- or post-attrs */
- *p++ = xdr_zero;
- return encode_post_op_attr(rqstp, p, fhp);
+ struct dentry *dentry = fhp->fh_dentry;
+
+ if (!dentry || !d_really_is_positive(dentry) || !fhp->fh_post_saved)
+ goto neither;
+
+ /* before */
+ if (!svcxdr_encode_pre_op_attr(xdr, fhp))
+ return false;
+
+ /* after */
+ if (xdr_stream_encode_item_present(xdr) < 0)
+ return false;
+ if (!svcxdr_encode_fattr3(rqstp, xdr, fhp, &fhp->fh_post_attr))
+ return false;
+
+ return true;
+
+neither:
+ if (xdr_stream_encode_item_absent(xdr) < 0)
+ return false;
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, fhp))
+ return false;
+
+ return true;
}
static bool fs_supports_change_attribute(struct super_block *sb)
@@ -713,210 +836,252 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p)
/* GETATTR */
int
-nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p)
+nfs3svc_encode_getattrres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
- *p++ = resp->status;
- if (resp->status == 0) {
- lease_get_mtime(d_inode(resp->fh.fh_dentry),
- &resp->stat.mtime);
- p = encode_fattr3(rqstp, p, &resp->fh, &resp->stat);
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ lease_get_mtime(d_inode(resp->fh.fh_dentry), &resp->stat.mtime);
+ if (!svcxdr_encode_fattr3(rqstp, xdr, &resp->fh, &resp->stat))
+ return 0;
+ break;
}
- return xdr_ressize_check(rqstp, p);
+
+ return 1;
}
/* SETATTR, REMOVE, RMDIR */
int
nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_attrstat *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = encode_wcc_data(rqstp, p, &resp->fh);
- return xdr_ressize_check(rqstp, p);
+ return svcxdr_encode_nfsstat3(xdr, resp->status) &&
+ svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh);
}
/* LOOKUP */
-int
-nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p)
+int nfs3svc_encode_lookupres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_diropres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- if (resp->status == 0) {
- p = encode_fh(p, &resp->fh);
- p = encode_post_op_attr(rqstp, p, &resp->fh);
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_nfs_fh3(xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh))
+ return 0;
}
- p = encode_post_op_attr(rqstp, p, &resp->dirfh);
- return xdr_ressize_check(rqstp, p);
+
+ return 1;
}
/* ACCESS */
int
nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_accessres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = encode_post_op_attr(rqstp, p, &resp->fh);
- if (resp->status == 0)
- *p++ = htonl(resp->access);
- return xdr_ressize_check(rqstp, p);
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->access) < 0)
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ }
+
+ return 1;
}
/* READLINK */
int
nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_readlinkres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
- *p++ = resp->status;
- p = encode_post_op_attr(rqstp, p, &resp->fh);
- if (resp->status == 0) {
- *p++ = htonl(resp->len);
- xdr_ressize_check(rqstp, p);
- rqstp->rq_res.page_len = resp->len;
- if (resp->len & 3) {
- /* need to pad the tail */
- rqstp->rq_res.tail[0].iov_base = p;
- *p = 0;
- rqstp->rq_res.tail[0].iov_len = 4 - (resp->len&3);
- }
- if (svc_encode_result_payload(rqstp, head->iov_len, resp->len))
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
- return 1;
- } else
- return xdr_ressize_check(rqstp, p);
+ if (xdr_stream_encode_u32(xdr, resp->len) < 0)
+ return 0;
+ xdr_write_pages(xdr, resp->pages, 0, resp->len);
+ if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0)
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ }
+
+ return 1;
}
/* READ */
int
nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_readres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
- *p++ = resp->status;
- p = encode_post_op_attr(rqstp, p, &resp->fh);
- if (resp->status == 0) {
- *p++ = htonl(resp->count);
- *p++ = htonl(resp->eof);
- *p++ = htonl(resp->count); /* xdr opaque count */
- xdr_ressize_check(rqstp, p);
- /* now update rqstp->rq_res to reflect data as well */
- rqstp->rq_res.page_len = resp->count;
- if (resp->count & 3) {
- /* need to pad the tail */
- rqstp->rq_res.tail[0].iov_base = p;
- *p = 0;
- rqstp->rq_res.tail[0].iov_len = 4 - (resp->count & 3);
- }
- if (svc_encode_result_payload(rqstp, head->iov_len,
- resp->count))
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
return 0;
- return 1;
- } else
- return xdr_ressize_check(rqstp, p);
+ if (xdr_stream_encode_u32(xdr, resp->count) < 0)
+ return 0;
+ if (xdr_stream_encode_bool(xdr, resp->eof) < 0)
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->count) < 0)
+ return 0;
+ xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base,
+ resp->count);
+ if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0)
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ }
+
+ return 1;
}
/* WRITE */
int
nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_writeres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = encode_wcc_data(rqstp, p, &resp->fh);
- if (resp->status == 0) {
- *p++ = htonl(resp->count);
- *p++ = htonl(resp->committed);
- *p++ = resp->verf[0];
- *p++ = resp->verf[1];
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->count) < 0)
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->committed) < 0)
+ return 0;
+ if (!svcxdr_encode_writeverf3(xdr, resp->verf))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
+ return 0;
}
- return xdr_ressize_check(rqstp, p);
+
+ return 1;
}
/* CREATE, MKDIR, SYMLINK, MKNOD */
int
nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_diropres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- if (resp->status == 0) {
- *p++ = xdr_one;
- p = encode_fh(p, &resp->fh);
- p = encode_post_op_attr(rqstp, p, &resp->fh);
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_fh3(xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh))
+ return 0;
}
- p = encode_wcc_data(rqstp, p, &resp->dirfh);
- return xdr_ressize_check(rqstp, p);
+
+ return 1;
}
/* RENAME */
int
nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_renameres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = encode_wcc_data(rqstp, p, &resp->ffh);
- p = encode_wcc_data(rqstp, p, &resp->tfh);
- return xdr_ressize_check(rqstp, p);
+ return svcxdr_encode_nfsstat3(xdr, resp->status) &&
+ svcxdr_encode_wcc_data(rqstp, xdr, &resp->ffh) &&
+ svcxdr_encode_wcc_data(rqstp, xdr, &resp->tfh);
}
/* LINK */
int
nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_linkres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = encode_post_op_attr(rqstp, p, &resp->fh);
- p = encode_wcc_data(rqstp, p, &resp->tfh);
- return xdr_ressize_check(rqstp, p);
+ return svcxdr_encode_nfsstat3(xdr, resp->status) &&
+ svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh) &&
+ svcxdr_encode_wcc_data(rqstp, xdr, &resp->tfh);
}
/* READDIR */
int
nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_readdirres *resp = rqstp->rq_resp;
+ struct xdr_buf *dirlist = &resp->dirlist;
- *p++ = resp->status;
- p = encode_post_op_attr(rqstp, p, &resp->fh);
-
- if (resp->status == 0) {
- /* stupid readdir cookie */
- memcpy(p, resp->verf, 8); p += 2;
- xdr_ressize_check(rqstp, p);
- if (rqstp->rq_res.head[0].iov_len + (2<<2) > PAGE_SIZE)
- return 1; /*No room for trailer */
- rqstp->rq_res.page_len = (resp->count) << 2;
-
- /* add the 'tail' to the end of the 'head' page - page 0. */
- rqstp->rq_res.tail[0].iov_base = p;
- *p++ = 0; /* no more entries */
- *p++ = htonl(resp->common.err == nfserr_eof);
- rqstp->rq_res.tail[0].iov_len = 2<<2;
- return 1;
- } else
- return xdr_ressize_check(rqstp, p);
-}
-
-static __be32 *
-encode_entry_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name,
- int namlen, u64 ino)
-{
- *p++ = xdr_one; /* mark entry present */
- p = xdr_encode_hyper(p, ino); /* file id */
- p = xdr_encode_array(p, name, namlen);/* name length & name */
-
- cd->offset = p; /* remember pointer */
- p = xdr_encode_hyper(p, NFS_OFFSET_MAX);/* offset of next entry */
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_cookieverf3(xdr, resp->verf))
+ return 0;
+ xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len);
+ /* no more entries */
+ if (xdr_stream_encode_item_absent(xdr) < 0)
+ return 0;
+ if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0)
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh))
+ return 0;
+ }
- return p;
+ return 1;
}
static __be32
@@ -957,267 +1122,327 @@ out:
return rv;
}
-static __be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen, u64 ino)
+/**
+ * nfs3svc_encode_cookie3 - Encode a directory offset cookie
+ * @resp: readdir result context
+ * @offset: offset cookie to encode
+ *
+ * The buffer space for the offset cookie has already been reserved
+ * by svcxdr_encode_entry3_common().
+ */
+void nfs3svc_encode_cookie3(struct nfsd3_readdirres *resp, u64 offset)
{
- struct svc_fh *fh = &cd->scratch;
- __be32 err;
-
- fh_init(fh, NFS3_FHSIZE);
- err = compose_entry_fh(cd, fh, name, namlen, ino);
- if (err) {
- *p++ = 0;
- *p++ = 0;
- goto out;
- }
- p = encode_post_op_attr(cd->rqstp, p, fh);
- *p++ = xdr_one; /* yes, a file handle follows */
- p = encode_fh(p, fh);
-out:
- fh_put(fh);
- return p;
-}
+ __be64 cookie = cpu_to_be64(offset);
-/*
- * Encode a directory entry. This one works for both normal readdir
- * and readdirplus.
- * The normal readdir reply requires 2 (fileid) + 1 (stringlen)
- * + string + 2 (cookie) + 1 (next) words, i.e. 6 + strlen.
- *
- * The readdirplus baggage is 1+21 words for post_op_attr, plus the
- * file handle.
- */
+ if (!resp->cookie_offset)
+ return;
+ write_bytes_to_xdr_buf(&resp->dirlist, resp->cookie_offset, &cookie,
+ sizeof(cookie));
+ resp->cookie_offset = 0;
+}
-#define NFS3_ENTRY_BAGGAGE (2 + 1 + 2 + 1)
-#define NFS3_ENTRYPLUS_BAGGAGE (1 + 21 + 1 + (NFS3_FHSIZE >> 2))
-static int
-encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
- loff_t offset, u64 ino, unsigned int d_type, int plus)
+static bool
+svcxdr_encode_entry3_common(struct nfsd3_readdirres *resp, const char *name,
+ int namlen, loff_t offset, u64 ino)
{
- struct nfsd3_readdirres *cd = container_of(ccd, struct nfsd3_readdirres,
- common);
- __be32 *p = cd->buffer;
- caddr_t curr_page_addr = NULL;
- struct page ** page;
- int slen; /* string (name) length */
- int elen; /* estimated entry length in words */
- int num_entry_words = 0; /* actual number of words */
-
- if (cd->offset) {
- u64 offset64 = offset;
-
- if (unlikely(cd->offset1)) {
- /* we ended up with offset on a page boundary */
- *cd->offset = htonl(offset64 >> 32);
- *cd->offset1 = htonl(offset64 & 0xffffffff);
- cd->offset1 = NULL;
- } else {
- xdr_encode_hyper(cd->offset, offset64);
- }
- cd->offset = NULL;
- }
+ struct xdr_buf *dirlist = &resp->dirlist;
+ struct xdr_stream *xdr = &resp->xdr;
- /*
- dprintk("encode_entry(%.*s @%ld%s)\n",
- namlen, name, (long) offset, plus? " plus" : "");
- */
-
- /* truncate filename if too long */
- namlen = min(namlen, NFS3_MAXNAMLEN);
+ if (xdr_stream_encode_item_present(xdr) < 0)
+ return false;
+ /* fileid */
+ if (xdr_stream_encode_u64(xdr, ino) < 0)
+ return false;
+ /* name */
+ if (xdr_stream_encode_opaque(xdr, name, min(namlen, NFS3_MAXNAMLEN)) < 0)
+ return false;
+ /* cookie */
+ resp->cookie_offset = dirlist->len;
+ if (xdr_stream_encode_u64(xdr, NFS_OFFSET_MAX) < 0)
+ return false;
- slen = XDR_QUADLEN(namlen);
- elen = slen + NFS3_ENTRY_BAGGAGE
- + (plus? NFS3_ENTRYPLUS_BAGGAGE : 0);
+ return true;
+}
- if (cd->buflen < elen) {
- cd->common.err = nfserr_toosmall;
- return -EINVAL;
- }
+/**
+ * nfs3svc_encode_entry3 - encode one NFSv3 READDIR entry
+ * @data: directory context
+ * @name: name of the object to be encoded
+ * @namlen: length of that name, in bytes
+ * @offset: the offset of the previous entry
+ * @ino: the fileid of this entry
+ * @d_type: unused
+ *
+ * Return values:
+ * %0: Entry was successfully encoded.
+ * %-EINVAL: An encoding problem occured, secondary status code in resp->common.err
+ *
+ * On exit, the following fields are updated:
+ * - resp->xdr
+ * - resp->common.err
+ * - resp->cookie_offset
+ */
+int nfs3svc_encode_entry3(void *data, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type)
+{
+ struct readdir_cd *ccd = data;
+ struct nfsd3_readdirres *resp = container_of(ccd,
+ struct nfsd3_readdirres,
+ common);
+ unsigned int starting_length = resp->dirlist.len;
- /* determine which page in rq_respages[] we are currently filling */
- for (page = cd->rqstp->rq_respages + 1;
- page < cd->rqstp->rq_next_page; page++) {
- curr_page_addr = page_address(*page);
+ /* The offset cookie for the previous entry */
+ nfs3svc_encode_cookie3(resp, offset);
- if (((caddr_t)cd->buffer >= curr_page_addr) &&
- ((caddr_t)cd->buffer < curr_page_addr + PAGE_SIZE))
- break;
- }
+ if (!svcxdr_encode_entry3_common(resp, name, namlen, offset, ino))
+ goto out_toosmall;
- if ((caddr_t)(cd->buffer + elen) < (curr_page_addr + PAGE_SIZE)) {
- /* encode entry in current page */
+ xdr_commit_encode(&resp->xdr);
+ resp->common.err = nfs_ok;
+ return 0;
- p = encode_entry_baggage(cd, p, name, namlen, ino);
+out_toosmall:
+ resp->cookie_offset = 0;
+ resp->common.err = nfserr_toosmall;
+ resp->dirlist.len = starting_length;
+ return -EINVAL;
+}
- if (plus)
- p = encode_entryplus_baggage(cd, p, name, namlen, ino);
- num_entry_words = p - cd->buffer;
- } else if (*(page+1) != NULL) {
- /* temporarily encode entry into next page, then move back to
- * current and next page in rq_respages[] */
- __be32 *p1, *tmp;
- int len1, len2;
+static bool
+svcxdr_encode_entry3_plus(struct nfsd3_readdirres *resp, const char *name,
+ int namlen, u64 ino)
+{
+ struct xdr_stream *xdr = &resp->xdr;
+ struct svc_fh *fhp = &resp->scratch;
+ bool result;
- /* grab next page for temporary storage of entry */
- p1 = tmp = page_address(*(page+1));
+ result = false;
+ fh_init(fhp, NFS3_FHSIZE);
+ if (compose_entry_fh(resp, fhp, name, namlen, ino) != nfs_ok)
+ goto out_noattrs;
- p1 = encode_entry_baggage(cd, p1, name, namlen, ino);
+ if (!svcxdr_encode_post_op_attr(resp->rqstp, xdr, fhp))
+ goto out;
+ if (!svcxdr_encode_post_op_fh3(xdr, fhp))
+ goto out;
+ result = true;
- if (plus)
- p1 = encode_entryplus_baggage(cd, p1, name, namlen, ino);
+out:
+ fh_put(fhp);
+ return result;
- /* determine entry word length and lengths to go in pages */
- num_entry_words = p1 - tmp;
- len1 = curr_page_addr + PAGE_SIZE - (caddr_t)cd->buffer;
- if ((num_entry_words << 2) < len1) {
- /* the actual number of words in the entry is less
- * than elen and can still fit in the current page
- */
- memmove(p, tmp, num_entry_words << 2);
- p += num_entry_words;
-
- /* update offset */
- cd->offset = cd->buffer + (cd->offset - tmp);
- } else {
- unsigned int offset_r = (cd->offset - tmp) << 2;
-
- /* update pointer to offset location.
- * This is a 64bit quantity, so we need to
- * deal with 3 cases:
- * - entirely in first page
- * - entirely in second page
- * - 4 bytes in each page
- */
- if (offset_r + 8 <= len1) {
- cd->offset = p + (cd->offset - tmp);
- } else if (offset_r >= len1) {
- cd->offset -= len1 >> 2;
- } else {
- /* sitting on the fence */
- BUG_ON(offset_r != len1 - 4);
- cd->offset = p + (cd->offset - tmp);
- cd->offset1 = tmp;
- }
-
- len2 = (num_entry_words << 2) - len1;
-
- /* move from temp page to current and next pages */
- memmove(p, tmp, len1);
- memmove(tmp, (caddr_t)tmp+len1, len2);
-
- p = tmp + (len2 >> 2);
- }
- }
- else {
- cd->common.err = nfserr_toosmall;
- return -EINVAL;
- }
+out_noattrs:
+ if (xdr_stream_encode_item_absent(xdr) < 0)
+ return false;
+ if (xdr_stream_encode_item_absent(xdr) < 0)
+ return false;
+ return true;
+}
- cd->buflen -= num_entry_words;
- cd->buffer = p;
- cd->common.err = nfs_ok;
+/**
+ * nfs3svc_encode_entryplus3 - encode one NFSv3 READDIRPLUS entry
+ * @data: directory context
+ * @name: name of the object to be encoded
+ * @namlen: length of that name, in bytes
+ * @offset: the offset of the previous entry
+ * @ino: the fileid of this entry
+ * @d_type: unused
+ *
+ * Return values:
+ * %0: Entry was successfully encoded.
+ * %-EINVAL: An encoding problem occured, secondary status code in resp->common.err
+ *
+ * On exit, the following fields are updated:
+ * - resp->xdr
+ * - resp->common.err
+ * - resp->cookie_offset
+ */
+int nfs3svc_encode_entryplus3(void *data, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type)
+{
+ struct readdir_cd *ccd = data;
+ struct nfsd3_readdirres *resp = container_of(ccd,
+ struct nfsd3_readdirres,
+ common);
+ unsigned int starting_length = resp->dirlist.len;
+
+ /* The offset cookie for the previous entry */
+ nfs3svc_encode_cookie3(resp, offset);
+
+ if (!svcxdr_encode_entry3_common(resp, name, namlen, offset, ino))
+ goto out_toosmall;
+ if (!svcxdr_encode_entry3_plus(resp, name, namlen, ino))
+ goto out_toosmall;
+
+ xdr_commit_encode(&resp->xdr);
+ resp->common.err = nfs_ok;
return 0;
+out_toosmall:
+ resp->cookie_offset = 0;
+ resp->common.err = nfserr_toosmall;
+ resp->dirlist.len = starting_length;
+ return -EINVAL;
}
-int
-nfs3svc_encode_entry(void *cd, const char *name,
- int namlen, loff_t offset, u64 ino, unsigned int d_type)
+static bool
+svcxdr_encode_fsstat3resok(struct xdr_stream *xdr,
+ const struct nfsd3_fsstatres *resp)
{
- return encode_entry(cd, name, namlen, offset, ino, d_type, 0);
-}
+ const struct kstatfs *s = &resp->stats;
+ u64 bs = s->f_bsize;
+ __be32 *p;
-int
-nfs3svc_encode_entry_plus(void *cd, const char *name,
- int namlen, loff_t offset, u64 ino,
- unsigned int d_type)
-{
- return encode_entry(cd, name, namlen, offset, ino, d_type, 1);
+ p = xdr_reserve_space(xdr, XDR_UNIT * 13);
+ if (!p)
+ return false;
+ p = xdr_encode_hyper(p, bs * s->f_blocks); /* total bytes */
+ p = xdr_encode_hyper(p, bs * s->f_bfree); /* free bytes */
+ p = xdr_encode_hyper(p, bs * s->f_bavail); /* user available bytes */
+ p = xdr_encode_hyper(p, s->f_files); /* total inodes */
+ p = xdr_encode_hyper(p, s->f_ffree); /* free inodes */
+ p = xdr_encode_hyper(p, s->f_ffree); /* user available inodes */
+ *p = cpu_to_be32(resp->invarsec); /* mean unchanged time */
+
+ return true;
}
/* FSSTAT */
int
nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_fsstatres *resp = rqstp->rq_resp;
- struct kstatfs *s = &resp->stats;
- u64 bs = s->f_bsize;
-
- *p++ = resp->status;
- *p++ = xdr_zero; /* no post_op_attr */
-
- if (resp->status == 0) {
- p = xdr_encode_hyper(p, bs * s->f_blocks); /* total bytes */
- p = xdr_encode_hyper(p, bs * s->f_bfree); /* free bytes */
- p = xdr_encode_hyper(p, bs * s->f_bavail); /* user available bytes */
- p = xdr_encode_hyper(p, s->f_files); /* total inodes */
- p = xdr_encode_hyper(p, s->f_ffree); /* free inodes */
- p = xdr_encode_hyper(p, s->f_ffree); /* user available inodes */
- *p++ = htonl(resp->invarsec); /* mean unchanged time */
+
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
+ return 0;
+ if (!svcxdr_encode_fsstat3resok(xdr, resp))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
+ return 0;
}
- return xdr_ressize_check(rqstp, p);
+
+ return 1;
+}
+
+static bool
+svcxdr_encode_fsinfo3resok(struct xdr_stream *xdr,
+ const struct nfsd3_fsinfores *resp)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, XDR_UNIT * 12);
+ if (!p)
+ return false;
+ *p++ = cpu_to_be32(resp->f_rtmax);
+ *p++ = cpu_to_be32(resp->f_rtpref);
+ *p++ = cpu_to_be32(resp->f_rtmult);
+ *p++ = cpu_to_be32(resp->f_wtmax);
+ *p++ = cpu_to_be32(resp->f_wtpref);
+ *p++ = cpu_to_be32(resp->f_wtmult);
+ *p++ = cpu_to_be32(resp->f_dtpref);
+ p = xdr_encode_hyper(p, resp->f_maxfilesize);
+ p = encode_nfstime3(p, &nfs3svc_time_delta);
+ *p = cpu_to_be32(resp->f_properties);
+
+ return true;
}
/* FSINFO */
int
nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_fsinfores *resp = rqstp->rq_resp;
- *p++ = resp->status;
- *p++ = xdr_zero; /* no post_op_attr */
-
- if (resp->status == 0) {
- *p++ = htonl(resp->f_rtmax);
- *p++ = htonl(resp->f_rtpref);
- *p++ = htonl(resp->f_rtmult);
- *p++ = htonl(resp->f_wtmax);
- *p++ = htonl(resp->f_wtpref);
- *p++ = htonl(resp->f_wtmult);
- *p++ = htonl(resp->f_dtpref);
- p = xdr_encode_hyper(p, resp->f_maxfilesize);
- *p++ = xdr_one;
- *p++ = xdr_zero;
- *p++ = htonl(resp->f_properties);
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
+ return 0;
+ if (!svcxdr_encode_fsinfo3resok(xdr, resp))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
+ return 0;
}
- return xdr_ressize_check(rqstp, p);
+ return 1;
+}
+
+static bool
+svcxdr_encode_pathconf3resok(struct xdr_stream *xdr,
+ const struct nfsd3_pathconfres *resp)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, XDR_UNIT * 6);
+ if (!p)
+ return false;
+ *p++ = cpu_to_be32(resp->p_link_max);
+ *p++ = cpu_to_be32(resp->p_name_max);
+ p = xdr_encode_bool(p, resp->p_no_trunc);
+ p = xdr_encode_bool(p, resp->p_chown_restricted);
+ p = xdr_encode_bool(p, resp->p_case_insensitive);
+ xdr_encode_bool(p, resp->p_case_preserving);
+
+ return true;
}
/* PATHCONF */
int
nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_pathconfres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- *p++ = xdr_zero; /* no post_op_attr */
-
- if (resp->status == 0) {
- *p++ = htonl(resp->p_link_max);
- *p++ = htonl(resp->p_name_max);
- *p++ = htonl(resp->p_no_trunc);
- *p++ = htonl(resp->p_chown_restricted);
- *p++ = htonl(resp->p_case_insensitive);
- *p++ = htonl(resp->p_case_preserving);
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
+ return 0;
+ if (!svcxdr_encode_pathconf3resok(xdr, resp))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh))
+ return 0;
}
- return xdr_ressize_check(rqstp, p);
+ return 1;
}
/* COMMIT */
int
nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd3_commitres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- p = encode_wcc_data(rqstp, p, &resp->fh);
- /* Write verifier */
- if (resp->status == 0) {
- *p++ = resp->verf[0];
- *p++ = resp->verf[1];
+ if (!svcxdr_encode_nfsstat3(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_writeverf3(xdr, resp->verf))
+ return 0;
+ break;
+ default:
+ if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh))
+ return 0;
}
- return xdr_ressize_check(rqstp, p);
+
+ return 1;
}
/*
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index dd9f38d072dd..daf43b980d4b 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1383,10 +1383,13 @@ static void nfsd4_init_copy_res(struct nfsd4_copy *copy, bool sync)
static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy)
{
ssize_t bytes_copied = 0;
- size_t bytes_total = copy->cp_count;
+ u64 bytes_total = copy->cp_count;
u64 src_pos = copy->cp_src_pos;
u64 dst_pos = copy->cp_dst_pos;
+ /* See RFC 7862 p.67: */
+ if (bytes_total == 0)
+ bytes_total = ULLONG_MAX;
do {
if (kthread_should_stop())
break;
@@ -1538,8 +1541,8 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (!nfs4_init_copy_state(nn, copy))
goto out_err;
refcount_set(&async_copy->refcount, 1);
- memcpy(&copy->cp_res.cb_stateid, &copy->cp_stateid,
- sizeof(copy->cp_stateid));
+ memcpy(&copy->cp_res.cb_stateid, &copy->cp_stateid.stid,
+ sizeof(copy->cp_res.cb_stateid));
dup_copy_fields(copy, async_copy);
async_copy->copy_task = kthread_create(nfsd4_do_async_copy,
async_copy, "%s", "copy thread");
@@ -2262,25 +2265,6 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp)
return !(nextd->op_flags & OP_HANDLES_WRONGSEC);
}
-static void svcxdr_init_encode(struct svc_rqst *rqstp,
- struct nfsd4_compoundres *resp)
-{
- struct xdr_stream *xdr = &resp->xdr;
- struct xdr_buf *buf = &rqstp->rq_res;
- struct kvec *head = buf->head;
-
- xdr->buf = buf;
- xdr->iov = head;
- xdr->p = head->iov_base + head->iov_len;
- xdr->end = head->iov_base + PAGE_SIZE - rqstp->rq_auth_slack;
- /* Tail and page_len should be zero at this point: */
- buf->len = buf->head[0].iov_len;
- xdr_reset_scratch_buffer(xdr);
- xdr->page_ptr = buf->pages - 1;
- buf->buflen = PAGE_SIZE * (1 + rqstp->rq_page_end - buf->pages)
- - rqstp->rq_auth_slack;
-}
-
#ifdef CONFIG_NFSD_V4_2_INTER_SSC
static void
check_if_stalefh_allowed(struct nfsd4_compoundargs *args)
@@ -2335,10 +2319,14 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
__be32 status;
- svcxdr_init_encode(rqstp, resp);
- resp->tagp = resp->xdr.p;
+ resp->xdr = &rqstp->rq_res_stream;
+
+ /* reserve space for: NFS status code */
+ xdr_reserve_space(resp->xdr, XDR_UNIT);
+
+ resp->tagp = resp->xdr->p;
/* reserve space for: taglen, tag, and opcnt */
- xdr_reserve_space(&resp->xdr, 8 + args->taglen);
+ xdr_reserve_space(resp->xdr, XDR_UNIT * 2 + args->taglen);
resp->taglen = args->taglen;
resp->tag = args->tag;
resp->rqstp = rqstp;
@@ -2444,7 +2432,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp)
encode_op:
if (op->status == nfserr_replay_me) {
op->replay = &cstate->replay_owner->so_replay;
- nfsd4_encode_replay(&resp->xdr, op);
+ nfsd4_encode_replay(resp->xdr, op);
status = op->status = op->replay->rp_status;
} else {
nfsd4_encode_operation(resp, op);
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 891395c6c7d3..6fedc49726bf 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -626,7 +626,7 @@ nfsd4_legacy_tracking_init(struct net *net)
status = nfsd4_load_reboot_recovery_data(net);
if (status)
goto err;
- printk("NFSD: Using legacy client tracking operations.\n");
+ pr_info("NFSD: Using legacy client tracking operations.\n");
return 0;
err:
@@ -1028,7 +1028,7 @@ nfsd4_init_cld_pipe(struct net *net)
status = __nfsd4_init_cld_pipe(net);
if (!status)
- printk("NFSD: Using old nfsdcld client tracking operations.\n");
+ pr_info("NFSD: Using old nfsdcld client tracking operations.\n");
return status;
}
@@ -1605,7 +1605,7 @@ nfsd4_cld_tracking_init(struct net *net)
nfs4_release_reclaim(nn);
goto err_remove;
} else
- printk("NFSD: Using nfsdcld client tracking operations.\n");
+ pr_info("NFSD: Using nfsdcld client tracking operations.\n");
return 0;
err_remove:
@@ -1864,7 +1864,7 @@ nfsd4_umh_cltrack_init(struct net *net)
ret = nfsd4_umh_cltrack_upcall("init", NULL, grace_start, NULL);
kfree(grace_start);
if (!ret)
- printk("NFSD: Using UMH upcall client tracking operations.\n");
+ pr_info("NFSD: Using UMH upcall client tracking operations.\n");
return ret;
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 97447a64bad0..7698172ac0c7 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -43,6 +43,7 @@
#include <linux/sunrpc/addr.h>
#include <linux/jhash.h>
#include <linux/string_helpers.h>
+#include <linux/fsnotify.h>
#include "xdr4.h"
#include "xdr4cb.h"
#include "vfs.h"
@@ -2352,6 +2353,10 @@ static int client_info_show(struct seq_file *m, void *v)
memcpy(&clid, &clp->cl_clientid, sizeof(clid));
seq_printf(m, "clientid: 0x%llx\n", clid);
seq_printf(m, "address: \"%pISpc\"\n", (struct sockaddr *)&clp->cl_addr);
+ if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
+ seq_puts(m, "status: confirmed\n");
+ else
+ seq_puts(m, "status: unconfirmed\n");
seq_printf(m, "name: ");
seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len);
seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion);
@@ -2702,6 +2707,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
int ret;
struct net *net = SVC_NET(rqstp);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct dentry *dentries[ARRAY_SIZE(client_files)];
clp = alloc_client(name);
if (clp == NULL)
@@ -2721,9 +2727,11 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage));
clp->cl_cb_session = NULL;
clp->net = net;
- clp->cl_nfsd_dentry = nfsd_client_mkdir(nn, &clp->cl_nfsdfs,
- clp->cl_clientid.cl_id - nn->clientid_base,
- client_files);
+ clp->cl_nfsd_dentry = nfsd_client_mkdir(
+ nn, &clp->cl_nfsdfs,
+ clp->cl_clientid.cl_id - nn->clientid_base,
+ client_files, dentries);
+ clp->cl_nfsd_info_dentry = dentries[0];
if (!clp->cl_nfsd_dentry) {
free_client(clp);
return NULL;
@@ -2798,7 +2806,10 @@ move_to_confirmed(struct nfs4_client *clp)
list_move(&clp->cl_idhash, &nn->conf_id_hashtbl[idhashval]);
rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
add_clp_to_name_tree(clp, &nn->conf_name_tree);
- set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags);
+ if (!test_and_set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags) &&
+ clp->cl_nfsd_dentry &&
+ clp->cl_nfsd_info_dentry)
+ fsnotify_dentry(clp->cl_nfsd_info_dentry, FS_MODIFY);
renew_client_locked(clp);
}
@@ -2903,7 +2914,7 @@ out_err:
static void
nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
{
- struct xdr_buf *buf = resp->xdr.buf;
+ struct xdr_buf *buf = resp->xdr->buf;
struct nfsd4_slot *slot = resp->cstate.slot;
unsigned int base;
@@ -2973,7 +2984,7 @@ nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
struct nfsd4_sequence *seq)
{
struct nfsd4_slot *slot = resp->cstate.slot;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
__be32 status;
@@ -3708,7 +3719,7 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
{
struct nfsd4_sequence *seq = &u->sequence;
struct nfsd4_compoundres *resp = rqstp->rq_resp;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct nfsd4_session *session;
struct nfs4_client *clp;
struct nfsd4_slot *slot;
@@ -5338,6 +5349,22 @@ static bool clients_still_reclaiming(struct nfsd_net *nn)
return true;
}
+struct laundry_time {
+ time64_t cutoff;
+ time64_t new_timeo;
+};
+
+static bool state_expired(struct laundry_time *lt, time64_t last_refresh)
+{
+ time64_t time_remaining;
+
+ if (last_refresh < lt->cutoff)
+ return true;
+ time_remaining = last_refresh - lt->cutoff;
+ lt->new_timeo = min(lt->new_timeo, time_remaining);
+ return false;
+}
+
static time64_t
nfs4_laundromat(struct nfsd_net *nn)
{
@@ -5347,14 +5374,16 @@ nfs4_laundromat(struct nfsd_net *nn)
struct nfs4_ol_stateid *stp;
struct nfsd4_blocked_lock *nbl;
struct list_head *pos, *next, reaplist;
- time64_t cutoff = ktime_get_boottime_seconds() - nn->nfsd4_lease;
- time64_t t, new_timeo = nn->nfsd4_lease;
+ struct laundry_time lt = {
+ .cutoff = ktime_get_boottime_seconds() - nn->nfsd4_lease,
+ .new_timeo = nn->nfsd4_lease
+ };
struct nfs4_cpntf_state *cps;
copy_stateid_t *cps_t;
int i;
if (clients_still_reclaiming(nn)) {
- new_timeo = 0;
+ lt.new_timeo = 0;
goto out;
}
nfsd4_end_grace(nn);
@@ -5364,7 +5393,7 @@ nfs4_laundromat(struct nfsd_net *nn)
idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) {
cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid);
if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID &&
- cps->cpntf_time < cutoff)
+ state_expired(&lt, cps->cpntf_time))
_free_cpntf_state_locked(nn, cps);
}
spin_unlock(&nn->s2s_cp_lock);
@@ -5372,11 +5401,8 @@ nfs4_laundromat(struct nfsd_net *nn)
spin_lock(&nn->client_lock);
list_for_each_safe(pos, next, &nn->client_lru) {
clp = list_entry(pos, struct nfs4_client, cl_lru);
- if (clp->cl_time > cutoff) {
- t = clp->cl_time - cutoff;
- new_timeo = min(new_timeo, t);
+ if (!state_expired(&lt, clp->cl_time))
break;
- }
if (mark_client_expired_locked(clp)) {
trace_nfsd_clid_expired(&clp->cl_clientid);
continue;
@@ -5393,11 +5419,8 @@ nfs4_laundromat(struct nfsd_net *nn)
spin_lock(&state_lock);
list_for_each_safe(pos, next, &nn->del_recall_lru) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
- if (dp->dl_time > cutoff) {
- t = dp->dl_time - cutoff;
- new_timeo = min(new_timeo, t);
+ if (!state_expired(&lt, dp->dl_time))
break;
- }
WARN_ON(!unhash_delegation_locked(dp));
list_add(&dp->dl_recall_lru, &reaplist);
}
@@ -5413,11 +5436,8 @@ nfs4_laundromat(struct nfsd_net *nn)
while (!list_empty(&nn->close_lru)) {
oo = list_first_entry(&nn->close_lru, struct nfs4_openowner,
oo_close_lru);
- if (oo->oo_time > cutoff) {
- t = oo->oo_time - cutoff;
- new_timeo = min(new_timeo, t);
+ if (!state_expired(&lt, oo->oo_time))
break;
- }
list_del_init(&oo->oo_close_lru);
stp = oo->oo_last_closed_stid;
oo->oo_last_closed_stid = NULL;
@@ -5443,11 +5463,8 @@ nfs4_laundromat(struct nfsd_net *nn)
while (!list_empty(&nn->blocked_locks_lru)) {
nbl = list_first_entry(&nn->blocked_locks_lru,
struct nfsd4_blocked_lock, nbl_lru);
- if (nbl->nbl_time > cutoff) {
- t = nbl->nbl_time - cutoff;
- new_timeo = min(new_timeo, t);
+ if (!state_expired(&lt, nbl->nbl_time))
break;
- }
list_move(&nbl->nbl_lru, &reaplist);
list_del_init(&nbl->nbl_list);
}
@@ -5460,8 +5477,7 @@ nfs4_laundromat(struct nfsd_net *nn)
free_blocked_lock(nbl);
}
out:
- new_timeo = max_t(time64_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
- return new_timeo;
+ return max_t(time64_t, lt.new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
}
static struct workqueue_struct *laundry_wq;
@@ -7321,14 +7337,9 @@ nfs4_state_start_net(struct net *net)
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
int ret;
- ret = get_nfsdfs(net);
- if (ret)
- return ret;
ret = nfs4_state_create_net(net);
- if (ret) {
- mntput(nn->nfsd_mnt);
+ if (ret)
return ret;
- }
locks_start_grace(net, &nn->nfsd4_manager);
nfsd4_client_tracking_init(net);
if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0)
@@ -7398,7 +7409,6 @@ nfs4_state_shutdown_net(struct net *net)
nfsd4_client_tracking_exit(net);
nfs4_state_destroy_net(net);
- mntput(nn->nfsd_mnt);
}
void
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index eaaa1605b5b5..e0f06d3cbd44 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3581,7 +3581,7 @@ nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid)
static __be32
nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 8);
@@ -3594,7 +3594,7 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 8);
@@ -3611,7 +3611,7 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp,
static __be32
nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_encode_stateid(xdr, &close->cl_stateid);
}
@@ -3620,7 +3620,7 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c
static __be32
nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, NFS4_VERIFIER_SIZE);
@@ -3634,7 +3634,7 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
static __be32
nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 20);
@@ -3649,7 +3649,7 @@ static __be32
nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_getattr *getattr)
{
struct svc_fh *fhp = getattr->ga_fhp;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_encode_fattr(xdr, fhp, fhp->fh_export, fhp->fh_dentry,
getattr->ga_bmval, resp->rqstp, 0);
@@ -3658,7 +3658,7 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
static __be32
nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh **fhpp)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct svc_fh *fhp = *fhpp;
unsigned int len;
__be32 *p;
@@ -3713,7 +3713,7 @@ again:
static __be32
nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
if (!nfserr)
nfserr = nfsd4_encode_stateid(xdr, &lock->lk_resp_stateid);
@@ -3726,7 +3726,7 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lo
static __be32
nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
if (nfserr == nfserr_denied)
nfsd4_encode_lock_denied(xdr, &lockt->lt_denied);
@@ -3736,7 +3736,7 @@ nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l
static __be32
nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_encode_stateid(xdr, &locku->lu_stateid);
}
@@ -3745,7 +3745,7 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l
static __be32
nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 20);
@@ -3759,7 +3759,7 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li
static __be32
nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
nfserr = nfsd4_encode_stateid(xdr, &open->op_stateid);
@@ -3853,7 +3853,7 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op
static __be32
nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid);
}
@@ -3861,7 +3861,7 @@ nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct
static __be32
nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_encode_stateid(xdr, &od->od_stateid);
}
@@ -3871,7 +3871,7 @@ static __be32 nfsd4_encode_splice_read(
struct nfsd4_read *read,
struct file *file, unsigned long maxcount)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct xdr_buf *buf = xdr->buf;
int status, space_left;
u32 eof;
@@ -3937,7 +3937,7 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp,
struct nfsd4_read *read,
struct file *file, unsigned long maxcount)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
u32 eof;
int starting_len = xdr->buf->len - 8;
__be32 nfserr;
@@ -3976,7 +3976,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_read *read)
{
unsigned long maxcount;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct file *file;
int starting_len = xdr->buf->len;
__be32 *p;
@@ -3990,7 +3990,7 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr,
WARN_ON_ONCE(test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags));
return nfserr_resource;
}
- if (resp->xdr.buf->page_len &&
+ if (resp->xdr->buf->page_len &&
test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) {
WARN_ON_ONCE(1);
return nfserr_resource;
@@ -4020,7 +4020,7 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd
int maxcount;
__be32 wire_count;
int zero = 0;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
int length_offset = xdr->buf->len;
int status;
__be32 *p;
@@ -4072,7 +4072,7 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
int bytes_left;
loff_t offset;
__be64 wire_offset;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
int starting_len = xdr->buf->len;
__be32 *p;
@@ -4083,8 +4083,8 @@ nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
/* XXX: Following NFSv3, we ignore the READDIR verifier for now. */
*p++ = cpu_to_be32(0);
*p++ = cpu_to_be32(0);
- resp->xdr.buf->head[0].iov_len = ((char *)resp->xdr.p)
- - (char *)resp->xdr.buf->head[0].iov_base;
+ xdr->buf->head[0].iov_len = (char *)xdr->p -
+ (char *)xdr->buf->head[0].iov_base;
/*
* Number of bytes left for directory entries allowing for the
@@ -4159,7 +4159,7 @@ err_no_verf:
static __be32
nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 20);
@@ -4172,7 +4172,7 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
static __be32
nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 40);
@@ -4255,7 +4255,7 @@ static __be32
nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_secinfo *secinfo)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_do_encode_secinfo(xdr, secinfo->si_exp);
}
@@ -4264,7 +4264,7 @@ static __be32
nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_secinfo_no_name *secinfo)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
return nfsd4_do_encode_secinfo(xdr, secinfo->sin_exp);
}
@@ -4276,7 +4276,7 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr,
static __be32
nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 16);
@@ -4300,7 +4300,7 @@ nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4
static __be32
nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
if (!nfserr) {
@@ -4324,7 +4324,7 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n
static __be32
nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 16);
@@ -4341,7 +4341,7 @@ static __be32
nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_exchange_id *exid)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
char *major_id;
char *server_scope;
@@ -4419,7 +4419,7 @@ static __be32
nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_create_session *sess)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 24);
@@ -4472,7 +4472,7 @@ static __be32
nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_sequence *seq)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, NFS4_MAX_SESSIONID_LEN + 20);
@@ -4495,7 +4495,7 @@ static __be32
nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_test_stateid *test_stateid)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct nfsd4_test_stateid_id *stateid, *next;
__be32 *p;
@@ -4516,7 +4516,7 @@ static __be32
nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_getdeviceinfo *gdev)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
const struct nfsd4_layout_ops *ops;
u32 starting_len = xdr->buf->len, needed_len;
__be32 *p;
@@ -4572,7 +4572,7 @@ static __be32
nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_layoutget *lgp)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
const struct nfsd4_layout_ops *ops;
__be32 *p;
@@ -4599,7 +4599,7 @@ static __be32
nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_layoutcommit *lcp)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 4);
@@ -4620,7 +4620,7 @@ static __be32
nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_layoutreturn *lrp)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 4);
@@ -4638,7 +4638,7 @@ nfsd42_encode_write_res(struct nfsd4_compoundres *resp,
struct nfsd42_write_res *write, bool sync)
{
__be32 *p;
- p = xdr_reserve_space(&resp->xdr, 4);
+ p = xdr_reserve_space(resp->xdr, 4);
if (!p)
return nfserr_resource;
@@ -4647,11 +4647,11 @@ nfsd42_encode_write_res(struct nfsd4_compoundres *resp,
else {
__be32 nfserr;
*p++ = cpu_to_be32(1);
- nfserr = nfsd4_encode_stateid(&resp->xdr, &write->cb_stateid);
+ nfserr = nfsd4_encode_stateid(resp->xdr, &write->cb_stateid);
if (nfserr)
return nfserr;
}
- p = xdr_reserve_space(&resp->xdr, 8 + 4 + NFS4_VERIFIER_SIZE);
+ p = xdr_reserve_space(resp->xdr, 8 + 4 + NFS4_VERIFIER_SIZE);
if (!p)
return nfserr_resource;
@@ -4665,7 +4665,7 @@ nfsd42_encode_write_res(struct nfsd4_compoundres *resp,
static __be32
nfsd42_encode_nl4_server(struct nfsd4_compoundres *resp, struct nl4_server *ns)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct nfs42_netaddr *addr;
__be32 *p;
@@ -4713,7 +4713,7 @@ nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr,
if (nfserr)
return nfserr;
- p = xdr_reserve_space(&resp->xdr, 4 + 4);
+ p = xdr_reserve_space(resp->xdr, 4 + 4);
*p++ = xdr_one; /* cr_consecutive */
*p++ = cpu_to_be32(copy->cp_synchronous);
return 0;
@@ -4723,7 +4723,7 @@ static __be32
nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_offload_status *os)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 8 + 4);
@@ -4740,7 +4740,7 @@ nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp,
unsigned long *maxcount, u32 *eof,
loff_t *pos)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct file *file = read->rd_nf->nf_file;
int starting_len = xdr->buf->len;
loff_t hole_pos;
@@ -4799,7 +4799,7 @@ nfsd4_encode_read_plus_hole(struct nfsd4_compoundres *resp,
count = data_pos - read->rd_offset;
/* Content type, offset, byte count */
- p = xdr_reserve_space(&resp->xdr, 4 + 8 + 8);
+ p = xdr_reserve_space(resp->xdr, 4 + 8 + 8);
if (!p)
return nfserr_resource;
@@ -4817,7 +4817,7 @@ nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_read *read)
{
unsigned long maxcount, count;
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct file *file;
int starting_len = xdr->buf->len;
int last_segment = xdr->buf->len;
@@ -4888,7 +4888,7 @@ static __be32
nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_copy_notify *cn)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
if (nfserr)
@@ -4924,7 +4924,7 @@ nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr,
{
__be32 *p;
- p = xdr_reserve_space(&resp->xdr, 4 + 8);
+ p = xdr_reserve_space(resp->xdr, 4 + 8);
*p++ = cpu_to_be32(seek->seek_eof);
p = xdr_encode_hyper(p, seek->seek_pos);
@@ -4985,7 +4985,7 @@ static __be32
nfsd4_encode_getxattr(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_getxattr *getxattr)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p, err;
p = xdr_reserve_space(xdr, 4);
@@ -5009,7 +5009,7 @@ static __be32
nfsd4_encode_setxattr(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_setxattr *setxattr)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 20);
@@ -5050,7 +5050,7 @@ static __be32
nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_listxattrs *listxattrs)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
u32 cookie_offset, count_offset, eof;
u32 left, xdrleft, slen, count;
u32 xdrlen, offset;
@@ -5161,7 +5161,7 @@ static __be32
nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_removexattr *removexattr)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
__be32 *p;
p = xdr_reserve_space(xdr, 20);
@@ -5301,7 +5301,7 @@ __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 respsize)
void
nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op)
{
- struct xdr_stream *xdr = &resp->xdr;
+ struct xdr_stream *xdr = resp->xdr;
struct nfs4_stateowner *so = resp->cstate.replay_owner;
struct svc_rqst *rqstp = resp->rqstp;
const struct nfsd4_operation *opdesc = op->opdesc;
@@ -5430,14 +5430,14 @@ int
nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p)
{
struct nfsd4_compoundres *resp = rqstp->rq_resp;
- struct xdr_buf *buf = resp->xdr.buf;
+ struct xdr_buf *buf = resp->xdr->buf;
WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len +
buf->tail[0].iov_len);
*p = resp->cstate.status;
- rqstp->rq_next_page = resp->xdr.page_ptr + 1;
+ rqstp->rq_next_page = resp->xdr->page_ptr + 1;
p = resp->tagp;
*p++ = htonl(resp->taglen);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index ef86ed23af82..853bf50a2a9b 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1266,7 +1266,8 @@ static void nfsdfs_remove_files(struct dentry *root)
/* XXX: cut'n'paste from simple_fill_super; figure out if we could share
* code instead. */
static int nfsdfs_create_files(struct dentry *root,
- const struct tree_descr *files)
+ const struct tree_descr *files,
+ struct dentry **fdentries)
{
struct inode *dir = d_inode(root);
struct inode *inode;
@@ -1275,8 +1276,6 @@ static int nfsdfs_create_files(struct dentry *root,
inode_lock(dir);
for (i = 0; files->name && files->name[0]; i++, files++) {
- if (!files->name)
- continue;
dentry = d_alloc_name(root, files->name);
if (!dentry)
goto out;
@@ -1290,6 +1289,8 @@ static int nfsdfs_create_files(struct dentry *root,
inode->i_private = __get_nfsdfs_client(dir);
d_add(dentry, inode);
fsnotify_create(dir, dentry);
+ if (fdentries)
+ fdentries[i] = dentry;
}
inode_unlock(dir);
return 0;
@@ -1301,8 +1302,9 @@ out:
/* on success, returns positive number unique to that client. */
struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
- struct nfsdfs_client *ncl, u32 id,
- const struct tree_descr *files)
+ struct nfsdfs_client *ncl, u32 id,
+ const struct tree_descr *files,
+ struct dentry **fdentries)
{
struct dentry *dentry;
char name[11];
@@ -1313,7 +1315,7 @@ struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
dentry = nfsd_mkdir(nn->nfsd_client_dir, ncl, name);
if (IS_ERR(dentry)) /* XXX: tossing errors? */
return NULL;
- ret = nfsdfs_create_files(dentry, files);
+ ret = nfsdfs_create_files(dentry, files, fdentries);
if (ret) {
nfsd_client_rmdir(dentry);
return NULL;
@@ -1416,6 +1418,8 @@ static void nfsd_umount(struct super_block *sb)
{
struct net *net = sb->s_fs_info;
+ nfsd_shutdown_threads(net);
+
kill_litter_super(sb);
put_net(net);
}
@@ -1428,18 +1432,6 @@ static struct file_system_type nfsd_fs_type = {
};
MODULE_ALIAS_FS("nfsd");
-int get_nfsdfs(struct net *net)
-{
- struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- struct vfsmount *mnt;
-
- mnt = vfs_kern_mount(&nfsd_fs_type, SB_KERNMOUNT, "nfsd", NULL);
- if (IS_ERR(mnt))
- return PTR_ERR(mnt);
- nn->nfsd_mnt = mnt;
- return 0;
-}
-
#ifdef CONFIG_PROC_FS
static int create_proc_exports_entry(void)
{
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 8bdc37aa2c2e..14dbfa75059d 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -93,13 +93,12 @@ int nfsd_get_nrthreads(int n, int *, struct net *);
int nfsd_set_nrthreads(int n, int *, struct net *);
int nfsd_pool_stats_open(struct inode *, struct file *);
int nfsd_pool_stats_release(struct inode *, struct file *);
+void nfsd_shutdown_threads(struct net *net);
void nfsd_destroy(struct net *net);
bool i_am_nfsd(void);
-int get_nfsdfs(struct net *);
-
struct nfsdfs_client {
struct kref cl_ref;
void (*cl_release)(struct kref *kref);
@@ -107,7 +106,9 @@ struct nfsdfs_client {
struct nfsdfs_client *get_nfsdfs_client(struct inode *);
struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
- struct nfsdfs_client *ncl, u32 id, const struct tree_descr *);
+ struct nfsdfs_client *ncl, u32 id,
+ const struct tree_descr *,
+ struct dentry **fdentries);
void nfsd_client_rmdir(struct dentry *dentry);
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 10b44421eace..c475d2271f9c 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -711,7 +711,7 @@ char * SVCFH_fmt(struct svc_fh *fhp)
return buf;
}
-enum fsid_source fsid_source(struct svc_fh *fhp)
+enum fsid_source fsid_source(const struct svc_fh *fhp)
{
if (fhp->fh_handle.fh_version != 1)
return FSIDSOURCE_DEV;
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index f58933519f38..aff2cda5c6c3 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -82,7 +82,7 @@ enum fsid_source {
FSIDSOURCE_FSID,
FSIDSOURCE_UUID,
};
-extern enum fsid_source fsid_source(struct svc_fh *fhp);
+extern enum fsid_source fsid_source(const struct svc_fh *fhp);
/*
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index a8d5449dd0e9..c2cd2984e41d 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -151,13 +151,14 @@ nfsd_proc_readlink(struct svc_rqst *rqstp)
{
struct nfsd_fhandle *argp = rqstp->rq_argp;
struct nfsd_readlinkres *resp = rqstp->rq_resp;
- char *buffer = page_address(*(rqstp->rq_next_page++));
dprintk("nfsd: READLINK %s\n", SVCFH_fmt(&argp->fh));
/* Read the symlink. */
resp->len = NFS_MAXPATHLEN;
- resp->status = nfsd_readlink(rqstp, &argp->fh, buffer, &resp->len);
+ resp->page = *(rqstp->rq_next_page++);
+ resp->status = nfsd_readlink(rqstp, &argp->fh,
+ page_address(resp->page), &resp->len);
fh_put(&argp->fh);
return rpc_success;
@@ -184,6 +185,7 @@ nfsd_proc_read(struct svc_rqst *rqstp)
v = 0;
len = argp->count;
+ resp->pages = rqstp->rq_next_page;
while (len > 0) {
struct page *page = *(rqstp->rq_next_page++);
@@ -557,14 +559,27 @@ static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp,
struct nfsd_readdirres *resp,
int count)
{
+ struct xdr_buf *buf = &resp->dirlist;
+ struct xdr_stream *xdr = &resp->xdr;
+
count = min_t(u32, count, PAGE_SIZE);
- /* Convert byte count to number of words (i.e. >> 2),
- * and reserve room for the NULL ptr & eof flag (-2 words) */
- resp->buflen = (count >> 2) - 2;
+ memset(buf, 0, sizeof(*buf));
- resp->buffer = page_address(*rqstp->rq_next_page);
+ /* Reserve room for the NULL ptr & eof flag (-2 words) */
+ buf->buflen = count - sizeof(__be32) * 2;
+ buf->pages = rqstp->rq_next_page;
rqstp->rq_next_page++;
+
+ /* This is xdr_init_encode(), but it assumes that
+ * the head kvec has already been consumed. */
+ xdr_set_scratch_buffer(xdr, NULL, 0);
+ xdr->buf = buf;
+ xdr->page_ptr = buf->pages;
+ xdr->iov = NULL;
+ xdr->p = page_address(*buf->pages);
+ xdr->end = xdr->p + (PAGE_SIZE >> 2);
+ xdr->rqst = NULL;
}
/*
@@ -576,25 +591,19 @@ nfsd_proc_readdir(struct svc_rqst *rqstp)
struct nfsd_readdirargs *argp = rqstp->rq_argp;
struct nfsd_readdirres *resp = rqstp->rq_resp;
loff_t offset;
- __be32 *buffer;
dprintk("nfsd: READDIR %s %d bytes at %d\n",
SVCFH_fmt(&argp->fh),
argp->count, argp->cookie);
nfsd_init_dirlist_pages(rqstp, resp, argp->count);
- buffer = resp->buffer;
- resp->offset = NULL;
resp->common.err = nfs_ok;
- /* Read directory and encode entries on the fly */
+ resp->cookie_offset = 0;
offset = argp->cookie;
resp->status = nfsd_readdir(rqstp, &argp->fh, &offset,
&resp->common, nfssvc_encode_entry);
-
- resp->count = resp->buffer - buffer;
- if (resp->offset)
- *resp->offset = htonl(offset);
+ nfssvc_encode_nfscookie(resp, offset);
fh_put(&argp->fh);
return rpc_success;
@@ -640,7 +649,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_GETATTR] = {
.pc_func = nfsd_proc_getattr,
.pc_decode = nfssvc_decode_fhandleargs,
- .pc_encode = nfssvc_encode_attrstat,
+ .pc_encode = nfssvc_encode_attrstatres,
.pc_release = nfssvc_release_attrstat,
.pc_argsize = sizeof(struct nfsd_fhandle),
.pc_ressize = sizeof(struct nfsd_attrstat),
@@ -651,7 +660,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_SETATTR] = {
.pc_func = nfsd_proc_setattr,
.pc_decode = nfssvc_decode_sattrargs,
- .pc_encode = nfssvc_encode_attrstat,
+ .pc_encode = nfssvc_encode_attrstatres,
.pc_release = nfssvc_release_attrstat,
.pc_argsize = sizeof(struct nfsd_sattrargs),
.pc_ressize = sizeof(struct nfsd_attrstat),
@@ -714,7 +723,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_WRITE] = {
.pc_func = nfsd_proc_write,
.pc_decode = nfssvc_decode_writeargs,
- .pc_encode = nfssvc_encode_attrstat,
+ .pc_encode = nfssvc_encode_attrstatres,
.pc_release = nfssvc_release_attrstat,
.pc_argsize = sizeof(struct nfsd_writeargs),
.pc_ressize = sizeof(struct nfsd_attrstat),
@@ -736,7 +745,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_REMOVE] = {
.pc_func = nfsd_proc_remove,
.pc_decode = nfssvc_decode_diropargs,
- .pc_encode = nfssvc_encode_stat,
+ .pc_encode = nfssvc_encode_statres,
.pc_argsize = sizeof(struct nfsd_diropargs),
.pc_ressize = sizeof(struct nfsd_stat),
.pc_cachetype = RC_REPLSTAT,
@@ -746,7 +755,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_RENAME] = {
.pc_func = nfsd_proc_rename,
.pc_decode = nfssvc_decode_renameargs,
- .pc_encode = nfssvc_encode_stat,
+ .pc_encode = nfssvc_encode_statres,
.pc_argsize = sizeof(struct nfsd_renameargs),
.pc_ressize = sizeof(struct nfsd_stat),
.pc_cachetype = RC_REPLSTAT,
@@ -756,7 +765,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_LINK] = {
.pc_func = nfsd_proc_link,
.pc_decode = nfssvc_decode_linkargs,
- .pc_encode = nfssvc_encode_stat,
+ .pc_encode = nfssvc_encode_statres,
.pc_argsize = sizeof(struct nfsd_linkargs),
.pc_ressize = sizeof(struct nfsd_stat),
.pc_cachetype = RC_REPLSTAT,
@@ -766,7 +775,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_SYMLINK] = {
.pc_func = nfsd_proc_symlink,
.pc_decode = nfssvc_decode_symlinkargs,
- .pc_encode = nfssvc_encode_stat,
+ .pc_encode = nfssvc_encode_statres,
.pc_argsize = sizeof(struct nfsd_symlinkargs),
.pc_ressize = sizeof(struct nfsd_stat),
.pc_cachetype = RC_REPLSTAT,
@@ -787,7 +796,7 @@ static const struct svc_procedure nfsd_procedures2[18] = {
[NFSPROC_RMDIR] = {
.pc_func = nfsd_proc_rmdir,
.pc_decode = nfssvc_decode_diropargs,
- .pc_encode = nfssvc_encode_stat,
+ .pc_encode = nfssvc_encode_statres,
.pc_argsize = sizeof(struct nfsd_diropargs),
.pc_ressize = sizeof(struct nfsd_stat),
.pc_cachetype = RC_REPLSTAT,
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 6de406322106..82ba034fa579 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -84,7 +84,7 @@ DEFINE_MUTEX(nfsd_mutex);
* version 4.1 DRC caches.
* nfsd_drc_pages_used tracks the current version 4.1 DRC memory usage.
*/
-spinlock_t nfsd_drc_lock;
+DEFINE_SPINLOCK(nfsd_drc_lock);
unsigned long nfsd_drc_max_mem;
unsigned long nfsd_drc_mem_used;
@@ -563,7 +563,6 @@ static void set_max_drc(void)
nfsd_drc_max_mem = (nr_free_buffer_pages()
>> NFSD_DRC_SIZE_SHIFT) * PAGE_SIZE;
nfsd_drc_mem_used = 0;
- spin_lock_init(&nfsd_drc_lock);
dprintk("%s nfsd_drc_max_mem %lu \n", __func__, nfsd_drc_max_mem);
}
@@ -596,6 +595,37 @@ static const struct svc_serv_ops nfsd_thread_sv_ops = {
.svo_module = THIS_MODULE,
};
+static void nfsd_complete_shutdown(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+ WARN_ON(!mutex_is_locked(&nfsd_mutex));
+
+ nn->nfsd_serv = NULL;
+ complete(&nn->nfsd_shutdown_complete);
+}
+
+void nfsd_shutdown_threads(struct net *net)
+{
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct svc_serv *serv;
+
+ mutex_lock(&nfsd_mutex);
+ serv = nn->nfsd_serv;
+ if (serv == NULL) {
+ mutex_unlock(&nfsd_mutex);
+ return;
+ }
+
+ svc_get(serv);
+ /* Kill outstanding nfsd threads */
+ serv->sv_ops->svo_setup(serv, NULL, 0);
+ nfsd_destroy(net);
+ mutex_unlock(&nfsd_mutex);
+ /* Wait for shutdown of nfsd_serv to complete */
+ wait_for_completion(&nn->nfsd_shutdown_complete);
+}
+
bool i_am_nfsd(void)
{
return kthread_func(current) == nfsd;
@@ -618,11 +648,13 @@ int nfsd_create_serv(struct net *net)
&nfsd_thread_sv_ops);
if (nn->nfsd_serv == NULL)
return -ENOMEM;
+ init_completion(&nn->nfsd_shutdown_complete);
nn->nfsd_serv->sv_maxconn = nn->max_connections;
error = svc_bind(nn->nfsd_serv, net);
if (error < 0) {
svc_destroy(nn->nfsd_serv);
+ nfsd_complete_shutdown(net);
return error;
}
@@ -671,7 +703,7 @@ void nfsd_destroy(struct net *net)
svc_shutdown_net(nn->nfsd_serv, net);
svc_destroy(nn->nfsd_serv);
if (destroy)
- nn->nfsd_serv = NULL;
+ nfsd_complete_shutdown(net);
}
int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
@@ -997,7 +1029,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
* NFSv4 does some encoding while processing
*/
p = resv->iov_base + resv->iov_len;
- resv->iov_len += sizeof(__be32);
+ svcxdr_init_encode(rqstp);
*statp = proc->pc_func(rqstp);
if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags))
@@ -1052,7 +1084,7 @@ int nfssvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p)
*/
int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
{
- return xdr_ressize_check(rqstp, p);
+ return 1;
}
int nfsd_pool_stats_open(struct inode *inode, struct file *file)
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 5d79ef6a0c7f..a06c05fe3b42 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -9,12 +9,10 @@
#include "xdr.h"
#include "auth.h"
-#define NFSDDBG_FACILITY NFSDDBG_XDR
-
/*
* Mapping of S_IF* types to NFS file types
*/
-static u32 nfs_ftypes[] = {
+static const u32 nfs_ftypes[] = {
NFNON, NFCHR, NFCHR, NFBAD,
NFDIR, NFBAD, NFBLK, NFBAD,
NFREG, NFBAD, NFLNK, NFBAD,
@@ -27,6 +25,28 @@ static u32 nfs_ftypes[] = {
*/
/**
+ * svcxdr_encode_stat - Encode an NFSv2 status code
+ * @xdr: XDR stream
+ * @status: status value to encode
+ *
+ * Return values:
+ * %false: Send buffer space was exhausted
+ * %true: Success
+ */
+bool
+svcxdr_encode_stat(struct xdr_stream *xdr, __be32 status)
+{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, sizeof(status));
+ if (!p)
+ return false;
+ *p = status;
+
+ return true;
+}
+
+/**
* svcxdr_decode_fhandle - Decode an NFSv2 file handle
* @xdr: XDR stream positioned at an encoded NFSv2 FH
* @fhp: OUT: filled-in server file handle
@@ -50,11 +70,28 @@ svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp)
return true;
}
-static __be32 *
-encode_fh(__be32 *p, struct svc_fh *fhp)
+static bool
+svcxdr_encode_fhandle(struct xdr_stream *xdr, const struct svc_fh *fhp)
{
+ __be32 *p;
+
+ p = xdr_reserve_space(xdr, NFS_FHSIZE);
+ if (!p)
+ return false;
memcpy(p, &fhp->fh_handle.fh_base, NFS_FHSIZE);
- return p + (NFS_FHSIZE>> 2);
+
+ return true;
+}
+
+static __be32 *
+encode_timeval(__be32 *p, const struct timespec64 *time)
+{
+ *p++ = cpu_to_be32((u32)time->tv_sec);
+ if (time->tv_nsec)
+ *p++ = cpu_to_be32(time->tv_nsec / NSEC_PER_USEC);
+ else
+ *p++ = xdr_zero;
+ return p;
}
static bool
@@ -162,68 +199,73 @@ svcxdr_decode_sattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
return true;
}
-static __be32 *
-encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
- struct kstat *stat)
+/**
+ * svcxdr_encode_fattr - Encode NFSv2 file attributes
+ * @rqstp: Context of a completed RPC transaction
+ * @xdr: XDR stream
+ * @fhp: File handle to encode
+ * @stat: Attributes to encode
+ *
+ * Return values:
+ * %false: Send buffer space was exhausted
+ * %true: Success
+ */
+bool
+svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ const struct svc_fh *fhp, const struct kstat *stat)
{
struct user_namespace *userns = nfsd_user_namespace(rqstp);
- struct dentry *dentry = fhp->fh_dentry;
- int type;
+ struct dentry *dentry = fhp->fh_dentry;
+ int type = stat->mode & S_IFMT;
struct timespec64 time;
- u32 f;
+ __be32 *p;
+ u32 fsid;
- type = (stat->mode & S_IFMT);
+ p = xdr_reserve_space(xdr, XDR_UNIT * 17);
+ if (!p)
+ return false;
- *p++ = htonl(nfs_ftypes[type >> 12]);
- *p++ = htonl((u32) stat->mode);
- *p++ = htonl((u32) stat->nlink);
- *p++ = htonl((u32) from_kuid_munged(userns, stat->uid));
- *p++ = htonl((u32) from_kgid_munged(userns, stat->gid));
+ *p++ = cpu_to_be32(nfs_ftypes[type >> 12]);
+ *p++ = cpu_to_be32((u32)stat->mode);
+ *p++ = cpu_to_be32((u32)stat->nlink);
+ *p++ = cpu_to_be32((u32)from_kuid_munged(userns, stat->uid));
+ *p++ = cpu_to_be32((u32)from_kgid_munged(userns, stat->gid));
- if (S_ISLNK(type) && stat->size > NFS_MAXPATHLEN) {
- *p++ = htonl(NFS_MAXPATHLEN);
- } else {
- *p++ = htonl((u32) stat->size);
- }
- *p++ = htonl((u32) stat->blksize);
+ if (S_ISLNK(type) && stat->size > NFS_MAXPATHLEN)
+ *p++ = cpu_to_be32(NFS_MAXPATHLEN);
+ else
+ *p++ = cpu_to_be32((u32) stat->size);
+ *p++ = cpu_to_be32((u32) stat->blksize);
if (S_ISCHR(type) || S_ISBLK(type))
- *p++ = htonl(new_encode_dev(stat->rdev));
+ *p++ = cpu_to_be32(new_encode_dev(stat->rdev));
else
- *p++ = htonl(0xffffffff);
- *p++ = htonl((u32) stat->blocks);
+ *p++ = cpu_to_be32(0xffffffff);
+ *p++ = cpu_to_be32((u32)stat->blocks);
+
switch (fsid_source(fhp)) {
- default:
- case FSIDSOURCE_DEV:
- *p++ = htonl(new_encode_dev(stat->dev));
- break;
case FSIDSOURCE_FSID:
- *p++ = htonl((u32) fhp->fh_export->ex_fsid);
+ fsid = (u32)fhp->fh_export->ex_fsid;
break;
case FSIDSOURCE_UUID:
- f = ((u32*)fhp->fh_export->ex_uuid)[0];
- f ^= ((u32*)fhp->fh_export->ex_uuid)[1];
- f ^= ((u32*)fhp->fh_export->ex_uuid)[2];
- f ^= ((u32*)fhp->fh_export->ex_uuid)[3];
- *p++ = htonl(f);
+ fsid = ((u32 *)fhp->fh_export->ex_uuid)[0];
+ fsid ^= ((u32 *)fhp->fh_export->ex_uuid)[1];
+ fsid ^= ((u32 *)fhp->fh_export->ex_uuid)[2];
+ fsid ^= ((u32 *)fhp->fh_export->ex_uuid)[3];
+ break;
+ default:
+ fsid = new_encode_dev(stat->dev);
break;
}
- *p++ = htonl((u32) stat->ino);
- *p++ = htonl((u32) stat->atime.tv_sec);
- *p++ = htonl(stat->atime.tv_nsec ? stat->atime.tv_nsec / 1000 : 0);
- time = stat->mtime;
- lease_get_mtime(d_inode(dentry), &time);
- *p++ = htonl((u32) time.tv_sec);
- *p++ = htonl(time.tv_nsec ? time.tv_nsec / 1000 : 0);
- *p++ = htonl((u32) stat->ctime.tv_sec);
- *p++ = htonl(stat->ctime.tv_nsec ? stat->ctime.tv_nsec / 1000 : 0);
+ *p++ = cpu_to_be32(fsid);
- return p;
-}
+ *p++ = cpu_to_be32((u32)stat->ino);
+ p = encode_timeval(p, &stat->atime);
+ time = stat->mtime;
+ lease_get_mtime(d_inode(dentry), &time);
+ p = encode_timeval(p, &time);
+ encode_timeval(p, &stat->ctime);
-/* Helper function for NFSv2 ACL code */
-__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat)
-{
- return encode_fattr(rqstp, p, fhp, stat);
+ return true;
}
/*
@@ -390,106 +432,118 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
*/
int
-nfssvc_encode_stat(struct svc_rqst *rqstp, __be32 *p)
+nfssvc_encode_statres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_stat *resp = rqstp->rq_resp;
- *p++ = resp->status;
- return xdr_ressize_check(rqstp, p);
+ return svcxdr_encode_stat(xdr, resp->status);
}
int
-nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p)
+nfssvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_attrstat *resp = rqstp->rq_resp;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- goto out;
- p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
-out:
- return xdr_ressize_check(rqstp, p);
+ if (!svcxdr_encode_stat(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+ return 0;
+ break;
+ }
+
+ return 1;
}
int
nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_diropres *resp = rqstp->rq_resp;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- goto out;
- p = encode_fh(p, &resp->fh);
- p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
-out:
- return xdr_ressize_check(rqstp, p);
+ if (!svcxdr_encode_stat(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_fhandle(xdr, &resp->fh))
+ return 0;
+ if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+ return 0;
+ break;
+ }
+
+ return 1;
}
int
nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_readlinkres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- return xdr_ressize_check(rqstp, p);
-
- *p++ = htonl(resp->len);
- xdr_ressize_check(rqstp, p);
- rqstp->rq_res.page_len = resp->len;
- if (resp->len & 3) {
- /* need to pad the tail */
- rqstp->rq_res.tail[0].iov_base = p;
- *p = 0;
- rqstp->rq_res.tail[0].iov_len = 4 - (resp->len&3);
- }
- if (svc_encode_result_payload(rqstp, head->iov_len, resp->len))
+ if (!svcxdr_encode_stat(xdr, resp->status))
return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (xdr_stream_encode_u32(xdr, resp->len) < 0)
+ return 0;
+ xdr_write_pages(xdr, &resp->page, 0, resp->len);
+ if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0)
+ return 0;
+ break;
+ }
+
return 1;
}
int
nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_readres *resp = rqstp->rq_resp;
struct kvec *head = rqstp->rq_res.head;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- return xdr_ressize_check(rqstp, p);
-
- p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
- *p++ = htonl(resp->count);
- xdr_ressize_check(rqstp, p);
-
- /* now update rqstp->rq_res to reflect data as well */
- rqstp->rq_res.page_len = resp->count;
- if (resp->count & 3) {
- /* need to pad the tail */
- rqstp->rq_res.tail[0].iov_base = p;
- *p = 0;
- rqstp->rq_res.tail[0].iov_len = 4 - (resp->count&3);
- }
- if (svc_encode_result_payload(rqstp, head->iov_len, resp->count))
+ if (!svcxdr_encode_stat(xdr, resp->status))
return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat))
+ return 0;
+ if (xdr_stream_encode_u32(xdr, resp->count) < 0)
+ return 0;
+ xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base,
+ resp->count);
+ if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0)
+ return 0;
+ break;
+ }
+
return 1;
}
int
nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_readdirres *resp = rqstp->rq_resp;
+ struct xdr_buf *dirlist = &resp->dirlist;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- return xdr_ressize_check(rqstp, p);
-
- xdr_ressize_check(rqstp, p);
- p = resp->buffer;
- *p++ = 0; /* no more entries */
- *p++ = htonl((resp->common.err == nfserr_eof));
- rqstp->rq_res.page_len = (((unsigned long)p-1) & ~PAGE_MASK)+1;
+ if (!svcxdr_encode_stat(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len);
+ /* no more entries */
+ if (xdr_stream_encode_item_absent(xdr) < 0)
+ return 0;
+ if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0)
+ return 0;
+ break;
+ }
return 1;
}
@@ -497,64 +551,113 @@ nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
int
nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p)
{
+ struct xdr_stream *xdr = &rqstp->rq_res_stream;
struct nfsd_statfsres *resp = rqstp->rq_resp;
struct kstatfs *stat = &resp->stats;
- *p++ = resp->status;
- if (resp->status != nfs_ok)
- return xdr_ressize_check(rqstp, p);
+ if (!svcxdr_encode_stat(xdr, resp->status))
+ return 0;
+ switch (resp->status) {
+ case nfs_ok:
+ p = xdr_reserve_space(xdr, XDR_UNIT * 5);
+ if (!p)
+ return 0;
+ *p++ = cpu_to_be32(NFSSVC_MAXBLKSIZE_V2);
+ *p++ = cpu_to_be32(stat->f_bsize);
+ *p++ = cpu_to_be32(stat->f_blocks);
+ *p++ = cpu_to_be32(stat->f_bfree);
+ *p = cpu_to_be32(stat->f_bavail);
+ break;
+ }
- *p++ = htonl(NFSSVC_MAXBLKSIZE_V2); /* max transfer size */
- *p++ = htonl(stat->f_bsize);
- *p++ = htonl(stat->f_blocks);
- *p++ = htonl(stat->f_bfree);
- *p++ = htonl(stat->f_bavail);
- return xdr_ressize_check(rqstp, p);
+ return 1;
}
-int
-nfssvc_encode_entry(void *ccdv, const char *name,
- int namlen, loff_t offset, u64 ino, unsigned int d_type)
+/**
+ * nfssvc_encode_nfscookie - Encode a directory offset cookie
+ * @resp: readdir result context
+ * @offset: offset cookie to encode
+ *
+ * The buffer space for the offset cookie has already been reserved
+ * by svcxdr_encode_entry_common().
+ */
+void nfssvc_encode_nfscookie(struct nfsd_readdirres *resp, u32 offset)
{
- struct readdir_cd *ccd = ccdv;
- struct nfsd_readdirres *cd = container_of(ccd, struct nfsd_readdirres, common);
- __be32 *p = cd->buffer;
- int buflen, slen;
+ __be32 cookie = cpu_to_be32(offset);
- /*
- dprintk("nfsd: entry(%.*s off %ld ino %ld)\n",
- namlen, name, offset, ino);
- */
+ if (!resp->cookie_offset)
+ return;
- if (offset > ~((u32) 0)) {
- cd->common.err = nfserr_fbig;
- return -EINVAL;
- }
- if (cd->offset)
- *cd->offset = htonl(offset);
+ write_bytes_to_xdr_buf(&resp->dirlist, resp->cookie_offset, &cookie,
+ sizeof(cookie));
+ resp->cookie_offset = 0;
+}
- /* truncate filename */
- namlen = min(namlen, NFS2_MAXNAMLEN);
- slen = XDR_QUADLEN(namlen);
+static bool
+svcxdr_encode_entry_common(struct nfsd_readdirres *resp, const char *name,
+ int namlen, loff_t offset, u64 ino)
+{
+ struct xdr_buf *dirlist = &resp->dirlist;
+ struct xdr_stream *xdr = &resp->xdr;
- if ((buflen = cd->buflen - slen - 4) < 0) {
- cd->common.err = nfserr_toosmall;
- return -EINVAL;
- }
- if (ino > ~((u32) 0)) {
- cd->common.err = nfserr_fbig;
- return -EINVAL;
- }
- *p++ = xdr_one; /* mark entry present */
- *p++ = htonl((u32) ino); /* file id */
- p = xdr_encode_array(p, name, namlen);/* name length & name */
- cd->offset = p; /* remember pointer */
- *p++ = htonl(~0U); /* offset of next entry */
-
- cd->buflen = buflen;
- cd->buffer = p;
- cd->common.err = nfs_ok;
+ if (xdr_stream_encode_item_present(xdr) < 0)
+ return false;
+ /* fileid */
+ if (xdr_stream_encode_u32(xdr, (u32)ino) < 0)
+ return false;
+ /* name */
+ if (xdr_stream_encode_opaque(xdr, name, min(namlen, NFS2_MAXNAMLEN)) < 0)
+ return false;
+ /* cookie */
+ resp->cookie_offset = dirlist->len;
+ if (xdr_stream_encode_u32(xdr, ~0U) < 0)
+ return false;
+
+ return true;
+}
+
+/**
+ * nfssvc_encode_entry - encode one NFSv2 READDIR entry
+ * @data: directory context
+ * @name: name of the object to be encoded
+ * @namlen: length of that name, in bytes
+ * @offset: the offset of the previous entry
+ * @ino: the fileid of this entry
+ * @d_type: unused
+ *
+ * Return values:
+ * %0: Entry was successfully encoded.
+ * %-EINVAL: An encoding problem occured, secondary status code in resp->common.err
+ *
+ * On exit, the following fields are updated:
+ * - resp->xdr
+ * - resp->common.err
+ * - resp->cookie_offset
+ */
+int nfssvc_encode_entry(void *data, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type)
+{
+ struct readdir_cd *ccd = data;
+ struct nfsd_readdirres *resp = container_of(ccd,
+ struct nfsd_readdirres,
+ common);
+ unsigned int starting_length = resp->dirlist.len;
+
+ /* The offset cookie for the previous entry */
+ nfssvc_encode_nfscookie(resp, offset);
+
+ if (!svcxdr_encode_entry_common(resp, name, namlen, offset, ino))
+ goto out_toosmall;
+
+ xdr_commit_encode(&resp->xdr);
+ resp->common.err = nfs_ok;
return 0;
+
+out_toosmall:
+ resp->cookie_offset = 0;
+ resp->common.err = nfserr_toosmall;
+ resp->dirlist.len = starting_length;
+ return -EINVAL;
}
/*
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 73deea353169..54cab651ac1d 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -371,6 +371,10 @@ struct nfs4_client {
/* debugging info directory under nfsd/clients/ : */
struct dentry *cl_nfsd_dentry;
+ /* 'info' file within that directory. Ref is not counted,
+ * but will remain valid iff cl_nfsd_dentry != NULL
+ */
+ struct dentry *cl_nfsd_info_dentry;
/* for nfs41 callbacks */
/* We currently support a single back channel with a single slot */
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 92a0973dd671..27a93ebd1d80 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -391,6 +391,30 @@ DEFINE_EVENT(nfsd_err_class, nfsd_##name, \
DEFINE_NFSD_ERR_EVENT(read_err);
DEFINE_NFSD_ERR_EVENT(write_err);
+TRACE_EVENT(nfsd_dirent,
+ TP_PROTO(struct svc_fh *fhp,
+ u64 ino,
+ const char *name,
+ int namlen),
+ TP_ARGS(fhp, ino, name, namlen),
+ TP_STRUCT__entry(
+ __field(u32, fh_hash)
+ __field(u64, ino)
+ __field(int, len)
+ __dynamic_array(unsigned char, name, namlen)
+ ),
+ TP_fast_assign(
+ __entry->fh_hash = fhp ? knfsd_fh_hash(&fhp->fh_handle) : 0;
+ __entry->ino = ino;
+ __entry->len = namlen;
+ memcpy(__get_str(name), name, namlen);
+ __assign_str(name, name);
+ ),
+ TP_printk("fh_hash=0x%08x ino=%llu name=%.*s",
+ __entry->fh_hash, __entry->ino,
+ __entry->len, __get_str(name))
+)
+
#include "state.h"
#include "filecache.h"
#include "vfs.h"
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index fd6be35a1642..15adf1f6ab21 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1968,8 +1968,9 @@ static int nfsd_buffered_filldir(struct dir_context *ctx, const char *name,
return 0;
}
-static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
- struct readdir_cd *cdp, loff_t *offsetp)
+static __be32 nfsd_buffered_readdir(struct file *file, struct svc_fh *fhp,
+ nfsd_filldir_t func, struct readdir_cd *cdp,
+ loff_t *offsetp)
{
struct buffered_dirent *de;
int host_err;
@@ -2015,6 +2016,8 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
if (cdp->err != nfs_ok)
break;
+ trace_nfsd_dirent(fhp, de->ino, de->name, de->namlen);
+
reclen = ALIGN(sizeof(*de) + de->namlen,
sizeof(u64));
size -= reclen;
@@ -2062,7 +2065,7 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp,
goto out_close;
}
- err = nfsd_buffered_readdir(file, func, cdp, offsetp);
+ err = nfsd_buffered_readdir(file, fhp, func, cdp, offsetp);
if (err == nfserr_eof || err == nfserr_toosmall)
err = nfs_ok; /* can still be found in ->err */
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index a2442ebe5acf..b21b76e6b9a8 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -152,7 +152,7 @@ static inline void fh_drop_write(struct svc_fh *fh)
}
}
-static inline __be32 fh_getattr(struct svc_fh *fh, struct kstat *stat)
+static inline __be32 fh_getattr(const struct svc_fh *fh, struct kstat *stat)
{
struct path p = {.mnt = fh->fh_export->ex_path.mnt,
.dentry = fh->fh_dentry};
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
index 3018b52b6d5e..f45b4bc93f52 100644
--- a/fs/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -94,6 +94,7 @@ struct nfsd_diropres {
struct nfsd_readlinkres {
__be32 status;
int len;
+ struct page *page;
};
struct nfsd_readres {
@@ -101,17 +102,20 @@ struct nfsd_readres {
struct svc_fh fh;
unsigned long count;
struct kstat stat;
+ struct page **pages;
};
struct nfsd_readdirres {
+ /* Components of the reply */
__be32 status;
int count;
+ /* Used to encode the reply's entry list */
+ struct xdr_stream xdr;
+ struct xdr_buf dirlist;
struct readdir_cd common;
- __be32 * buffer;
- int buflen;
- __be32 * offset;
+ unsigned int cookie_offset;
};
struct nfsd_statfsres {
@@ -147,23 +151,26 @@ int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *);
int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *);
int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *);
int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *);
-int nfssvc_encode_stat(struct svc_rqst *, __be32 *);
-int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *);
+int nfssvc_encode_statres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_attrstatres(struct svc_rqst *, __be32 *);
int nfssvc_encode_diropres(struct svc_rqst *, __be32 *);
int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *);
int nfssvc_encode_readres(struct svc_rqst *, __be32 *);
int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *);
int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *);
-int nfssvc_encode_entry(void *, const char *name,
- int namlen, loff_t offset, u64 ino, unsigned int);
+void nfssvc_encode_nfscookie(struct nfsd_readdirres *resp, u32 offset);
+int nfssvc_encode_entry(void *data, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type);
void nfssvc_release_attrstat(struct svc_rqst *rqstp);
void nfssvc_release_diropres(struct svc_rqst *rqstp);
void nfssvc_release_readres(struct svc_rqst *rqstp);
/* Helper functions for NFSv2 ACL code */
-__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat);
bool svcxdr_decode_fhandle(struct xdr_stream *xdr, struct svc_fh *fhp);
+bool svcxdr_encode_stat(struct xdr_stream *xdr, __be32 status);
+bool svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ const struct svc_fh *fhp, const struct kstat *stat);
#endif /* LINUX_NFSD_H */
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 3e1578953f54..933008382bbe 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -137,6 +137,7 @@ struct nfsd3_readlinkres {
__be32 status;
struct svc_fh fh;
__u32 len;
+ struct page **pages;
};
struct nfsd3_readres {
@@ -144,6 +145,7 @@ struct nfsd3_readres {
struct svc_fh fh;
unsigned long count;
__u32 eof;
+ struct page **pages;
};
struct nfsd3_writeres {
@@ -167,19 +169,17 @@ struct nfsd3_linkres {
};
struct nfsd3_readdirres {
+ /* Components of the reply */
__be32 status;
struct svc_fh fh;
- /* Just to save kmalloc on every readdirplus entry (svc_fh is a
- * little large for the stack): */
- struct svc_fh scratch;
- int count;
__be32 verf[2];
+ /* Used to encode the reply's entry list */
+ struct xdr_stream xdr;
+ struct xdr_buf dirlist;
+ struct svc_fh scratch;
struct readdir_cd common;
- __be32 * buffer;
- int buflen;
- __be32 * offset;
- __be32 * offset1;
+ unsigned int cookie_offset;
struct svc_rqst * rqstp;
};
@@ -280,9 +280,9 @@ int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *);
int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *);
int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *);
int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_getattrres(struct svc_rqst *, __be32 *);
int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *);
-int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_lookupres(struct svc_rqst *, __be32 *);
int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *);
int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *);
int nfs3svc_encode_readres(struct svc_rqst *, __be32 *);
@@ -298,15 +298,16 @@ int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *);
void nfs3svc_release_fhandle(struct svc_rqst *);
void nfs3svc_release_fhandle2(struct svc_rqst *);
-int nfs3svc_encode_entry(void *, const char *name,
- int namlen, loff_t offset, u64 ino,
- unsigned int);
-int nfs3svc_encode_entry_plus(void *, const char *name,
- int namlen, loff_t offset, u64 ino,
- unsigned int);
+
+void nfs3svc_encode_cookie3(struct nfsd3_readdirres *resp, u64 offset);
+int nfs3svc_encode_entry3(void *data, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type);
+int nfs3svc_encode_entryplus3(void *data, const char *name, int namlen,
+ loff_t offset, u64 ino, unsigned int d_type);
/* Helper functions for NFSv3 ACL code */
-__be32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p,
- struct svc_fh *fhp);
bool svcxdr_decode_nfs_fh3(struct xdr_stream *xdr, struct svc_fh *fhp);
+bool svcxdr_encode_nfsstat3(struct xdr_stream *xdr, __be32 status);
+bool svcxdr_encode_post_op_attr(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ const struct svc_fh *fhp);
#endif /* _LINUX_NFSD_XDR3_H */
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index c300885ae75d..fe540a3415c6 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -698,7 +698,7 @@ struct nfsd4_compoundargs {
struct nfsd4_compoundres {
/* scratch variables for XDR encode */
- struct xdr_stream xdr;
+ struct xdr_stream *xdr;
struct svc_rqst * rqstp;
u32 taglen;
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index dbfb35fb0ff7..3847cdc069b5 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -430,20 +430,11 @@ static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
if (WARN_ON(file != vma->vm_file))
return -EIO;
- vma->vm_file = get_file(realfile);
+ vma_set_file(vma, realfile);
old_cred = ovl_override_creds(file_inode(file)->i_sb);
ret = call_mmap(vma->vm_file, vma);
revert_creds(old_cred);
-
- if (ret) {
- /* Drop reference count from new vm_file value */
- fput(realfile);
- } else {
- /* Drop reference count from previous vm_file value */
- fput(file);
- }
-
ovl_file_accessed(file);
return ret;
diff --git a/fs/verity/Kconfig b/fs/verity/Kconfig
index 88fb25119899..24d1b54de807 100644
--- a/fs/verity/Kconfig
+++ b/fs/verity/Kconfig
@@ -3,9 +3,13 @@
config FS_VERITY
bool "FS Verity (read-only file-based authenticity protection)"
select CRYPTO
- # SHA-256 is selected as it's intended to be the default hash algorithm.
+ # SHA-256 is implied as it's intended to be the default hash algorithm.
# To avoid bloat, other wanted algorithms must be selected explicitly.
- select CRYPTO_SHA256
+ # Note that CRYPTO_SHA256 denotes the generic C implementation, but
+ # some architectures provided optimized implementations of the same
+ # algorithm that may be used instead. In this case, CRYPTO_SHA256 may
+ # be omitted even if SHA-256 is being used.
+ imply CRYPTO_SHA256
help
This option enables fs-verity. fs-verity is the dm-verity
mechanism implemented at the file level. On supported