aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Makefile4
-rw-r--r--fs/afs/afs.h23
-rw-r--r--fs/afs/afs_fs.h3
-rw-r--r--fs/afs/dir.c18
-rw-r--r--fs/afs/file.c2
-rw-r--r--fs/afs/fsclient.c298
-rw-r--r--fs/afs/inode.c10
-rw-r--r--fs/afs/internal.h6
-rw-r--r--fs/afs/super.c44
-rw-r--r--fs/afs/vnode.c85
-rw-r--r--fs/afs/write.c5
-rw-r--r--fs/aio.c28
-rw-r--r--fs/anon_inodes.c200
-rw-r--r--fs/autofs/autofs_i.h4
-rw-r--r--fs/autofs/inode.c47
-rw-r--r--fs/autofs/root.c83
-rw-r--r--fs/autofs4/inode.c16
-rw-r--r--fs/autofs4/root.c18
-rw-r--r--fs/compat.c49
-rw-r--r--fs/eventfd.c228
-rw-r--r--fs/eventpoll.c1178
-rw-r--r--fs/exec.c13
-rw-r--r--fs/mpage.c174
-rw-r--r--fs/partitions/Kconfig2
-rw-r--r--fs/partitions/efi.c12
-rw-r--r--fs/signalfd.c349
-rw-r--r--fs/timerfd.c227
27 files changed, 2164 insertions, 962 deletions
diff --git a/fs/Makefile b/fs/Makefile
index 9edf4112bee..720c29d57a6 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -22,6 +22,10 @@ endif
obj-$(CONFIG_INOTIFY) += inotify.o
obj-$(CONFIG_INOTIFY_USER) += inotify_user.o
obj-$(CONFIG_EPOLL) += eventpoll.o
+obj-$(CONFIG_ANON_INODES) += anon_inodes.o
+obj-$(CONFIG_SIGNALFD) += signalfd.o
+obj-$(CONFIG_TIMERFD) += timerfd.o
+obj-$(CONFIG_EVENTFD) += eventfd.o
obj-$(CONFIG_COMPAT) += compat.o compat_ioctl.o
nfsd-$(CONFIG_NFSD) := nfsctl.o
diff --git a/fs/afs/afs.h b/fs/afs/afs.h
index 52d0752265b..24525794814 100644
--- a/fs/afs/afs.h
+++ b/fs/afs/afs.h
@@ -16,6 +16,9 @@
#define AFS_MAXCELLNAME 64 /* maximum length of a cell name */
#define AFS_MAXVOLNAME 64 /* maximum length of a volume name */
+#define AFSNAMEMAX 256 /* maximum length of a filename plus NUL */
+#define AFSPATHMAX 1024 /* maximum length of a pathname plus NUL */
+#define AFSOPAQUEMAX 1024 /* maximum length of an opaque field */
typedef unsigned afs_volid_t;
typedef unsigned afs_vnodeid_t;
@@ -143,4 +146,24 @@ struct afs_volsync {
time_t creation; /* volume creation time */
};
+/*
+ * AFS volume status record
+ */
+struct afs_volume_status {
+ u32 vid; /* volume ID */
+ u32 parent_id; /* parent volume ID */
+ u8 online; /* true if volume currently online and available */
+ u8 in_service; /* true if volume currently in service */
+ u8 blessed; /* same as in_service */
+ u8 needs_salvage; /* true if consistency checking required */
+ u32 type; /* volume type (afs_voltype_t) */
+ u32 min_quota; /* minimum space set aside (blocks) */
+ u32 max_quota; /* maximum space this volume may occupy (blocks) */
+ u32 blocks_in_use; /* space this volume currently occupies (blocks) */
+ u32 part_blocks_avail; /* space available in volume's partition */
+ u32 part_max_blocks; /* size of volume's partition */
+};
+
+#define AFS_BLOCK_SIZE 1024
+
#endif /* AFS_H */
diff --git a/fs/afs/afs_fs.h b/fs/afs/afs_fs.h
index d963ef4daee..a18c374ebe0 100644
--- a/fs/afs/afs_fs.h
+++ b/fs/afs/afs_fs.h
@@ -28,7 +28,8 @@ enum AFS_FS_Operations {
FSMAKEDIR = 141, /* AFS Create a directory */
FSREMOVEDIR = 142, /* AFS Remove a directory */
FSGIVEUPCALLBACKS = 147, /* AFS Discard callback promises */
- FSGETVOLUMEINFO = 148, /* AFS Get root volume information */
+ FSGETVOLUMEINFO = 148, /* AFS Get information about a volume */
+ FSGETVOLUMESTATUS = 149, /* AFS Get volume status information */
FSGETROOTVOLUME = 151, /* AFS Get root volume name */
FSLOOKUP = 161, /* AFS lookup file in directory */
FSFETCHDATA64 = 65537, /* AFS Fetch file data */
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 2fb31276196..719af4fb15d 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -497,7 +497,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
ASSERTCMP(dentry->d_inode, ==, NULL);
- if (dentry->d_name.len > 255) {
+ if (dentry->d_name.len >= AFSNAMEMAX) {
_leave(" = -ENAMETOOLONG");
return ERR_PTR(-ENAMETOOLONG);
}
@@ -736,7 +736,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name, mode);
ret = -ENAMETOOLONG;
- if (dentry->d_name.len > 255)
+ if (dentry->d_name.len >= AFSNAMEMAX)
goto error;
key = afs_request_key(dvnode->volume->cell);
@@ -801,7 +801,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name);
ret = -ENAMETOOLONG;
- if (dentry->d_name.len > 255)
+ if (dentry->d_name.len >= AFSNAMEMAX)
goto error;
key = afs_request_key(dvnode->volume->cell);
@@ -847,7 +847,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry)
dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name);
ret = -ENAMETOOLONG;
- if (dentry->d_name.len > 255)
+ if (dentry->d_name.len >= AFSNAMEMAX)
goto error;
key = afs_request_key(dvnode->volume->cell);
@@ -921,7 +921,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, int mode,
dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name, mode);
ret = -ENAMETOOLONG;
- if (dentry->d_name.len > 255)
+ if (dentry->d_name.len >= AFSNAMEMAX)
goto error;
key = afs_request_key(dvnode->volume->cell);
@@ -990,7 +990,7 @@ static int afs_link(struct dentry *from, struct inode *dir,
dentry->d_name.name);
ret = -ENAMETOOLONG;
- if (dentry->d_name.len > 255)
+ if (dentry->d_name.len >= AFSNAMEMAX)
goto error;
key = afs_request_key(dvnode->volume->cell);
@@ -1038,11 +1038,11 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry,
content);
ret = -ENAMETOOLONG;
- if (dentry->d_name.len > 255)
+ if (dentry->d_name.len >= AFSNAMEMAX)
goto error;
ret = -EINVAL;
- if (strlen(content) > 1023)
+ if (strlen(content) >= AFSPATHMAX)
goto error;
key = afs_request_key(dvnode->volume->cell);
@@ -1112,7 +1112,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
new_dentry->d_name.name);
ret = -ENAMETOOLONG;
- if (new_dentry->d_name.len > 255)
+ if (new_dentry->d_name.len >= AFSNAMEMAX)
goto error;
key = afs_request_key(orig_dvnode->volume->cell);
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 3e25795e5a4..9c0e721d9fc 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -236,7 +236,7 @@ static void afs_invalidatepage(struct page *page, unsigned long offset)
{
int ret = 1;
- kenter("{%lu},%lu", page->index, offset);
+ _enter("{%lu},%lu", page->index, offset);
BUG_ON(!PageLocked(page));
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 56cc0efa2a0..5dff1308b6f 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -202,6 +202,29 @@ static void xdr_encode_AFS_StoreStatus(__be32 **_bp, struct iattr *attr)
}
/*
+ * decode an AFSFetchVolumeStatus block
+ */
+static void xdr_decode_AFSFetchVolumeStatus(const __be32 **_bp,
+ struct afs_volume_status *vs)
+{
+ const __be32 *bp = *_bp;
+
+ vs->vid = ntohl(*bp++);
+ vs->parent_id = ntohl(*bp++);
+ vs->online = ntohl(*bp++);
+ vs->in_service = ntohl(*bp++);
+ vs->blessed = ntohl(*bp++);
+ vs->needs_salvage = ntohl(*bp++);
+ vs->type = ntohl(*bp++);
+ vs->min_quota = ntohl(*bp++);
+ vs->max_quota = ntohl(*bp++);
+ vs->blocks_in_use = ntohl(*bp++);
+ vs->part_blocks_avail = ntohl(*bp++);
+ vs->part_max_blocks = ntohl(*bp++);
+ *_bp = bp;
+}
+
+/*
* deliver reply data to an FS.FetchStatus
*/
static int afs_deliver_fs_fetch_status(struct afs_call *call,
@@ -1450,3 +1473,278 @@ int afs_fs_setattr(struct afs_server *server, struct key *key,
return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
}
+
+/*
+ * deliver reply data to an FS.GetVolumeStatus
+ */
+static int afs_deliver_fs_get_volume_status(struct afs_call *call,
+ struct sk_buff *skb, bool last)
+{
+ const __be32 *bp;
+ char *p;
+ int ret;
+
+ _enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
+
+ switch (call->unmarshall) {
+ case 0:
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the returned status record */
+ case 1:
+ _debug("extract status");
+ ret = afs_extract_data(call, skb, last, call->buffer,
+ 12 * 4);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ bp = call->buffer;
+ xdr_decode_AFSFetchVolumeStatus(&bp, call->reply2);
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the volume name length */
+ case 2:
+ ret = afs_extract_data(call, skb, last, &call->tmp, 4);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->count = ntohl(call->tmp);
+ _debug("volname length: %u", call->count);
+ if (call->count >= AFSNAMEMAX)
+ return -EBADMSG;
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the volume name */
+ case 3:
+ _debug("extract volname");
+ if (call->count > 0) {
+ ret = afs_extract_data(call, skb, last, call->reply3,
+ call->count);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+ }
+
+ p = call->reply3;
+ p[call->count] = 0;
+ _debug("volname '%s'", p);
+
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the volume name padding */
+ if ((call->count & 3) == 0) {
+ call->unmarshall++;
+ goto no_volname_padding;
+ }
+ call->count = 4 - (call->count & 3);
+
+ case 4:
+ ret = afs_extract_data(call, skb, last, call->buffer,
+ call->count);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->offset = 0;
+ call->unmarshall++;
+ no_volname_padding:
+
+ /* extract the offline message length */
+ case 5:
+ ret = afs_extract_data(call, skb, last, &call->tmp, 4);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->count = ntohl(call->tmp);
+ _debug("offline msg length: %u", call->count);
+ if (call->count >= AFSNAMEMAX)
+ return -EBADMSG;
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the offline message */
+ case 6:
+ _debug("extract offline");
+ if (call->count > 0) {
+ ret = afs_extract_data(call, skb, last, call->reply3,
+ call->count);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+ }
+
+ p = call->reply3;
+ p[call->count] = 0;
+ _debug("offline '%s'", p);
+
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the offline message padding */
+ if ((call->count & 3) == 0) {
+ call->unmarshall++;
+ goto no_offline_padding;
+ }
+ call->count = 4 - (call->count & 3);
+
+ case 7:
+ ret = afs_extract_data(call, skb, last, call->buffer,
+ call->count);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->offset = 0;
+ call->unmarshall++;
+ no_offline_padding:
+
+ /* extract the message of the day length */
+ case 8:
+ ret = afs_extract_data(call, skb, last, &call->tmp, 4);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->count = ntohl(call->tmp);
+ _debug("motd length: %u", call->count);
+ if (call->count >= AFSNAMEMAX)
+ return -EBADMSG;
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the message of the day */
+ case 9:
+ _debug("extract motd");
+ if (call->count > 0) {
+ ret = afs_extract_data(call, skb, last, call->reply3,
+ call->count);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+ }
+
+ p = call->reply3;
+ p[call->count] = 0;
+ _debug("motd '%s'", p);
+
+ call->offset = 0;
+ call->unmarshall++;
+
+ /* extract the message of the day padding */
+ if ((call->count & 3) == 0) {
+ call->unmarshall++;
+ goto no_motd_padding;
+ }
+ call->count = 4 - (call->count & 3);
+
+ case 10:
+ ret = afs_extract_data(call, skb, last, call->buffer,
+ call->count);
+ switch (ret) {
+ case 0: break;
+ case -EAGAIN: return 0;
+ default: return ret;
+ }
+
+ call->offset = 0;
+ call->unmarshall++;
+ no_motd_padding:
+
+ case 11:
+ _debug("trailer %d", skb->len);
+ if (skb->len != 0)
+ return -EBADMSG;
+ break;
+ }
+
+ if (!last)
+ return 0;
+
+ _leave(" = 0 [done]");
+ return 0;
+}
+
+/*
+ * destroy an FS.GetVolumeStatus call
+ */
+static void afs_get_volume_status_call_destructor(struct afs_call *call)
+{
+ kfree(call->reply3);
+ call->reply3 = NULL;
+ afs_flat_call_destructor(call);
+}
+
+/*
+ * FS.GetVolumeStatus operation type
+ */
+static const struct afs_call_type afs_RXFSGetVolumeStatus = {
+ .name = "FS.GetVolumeStatus",
+ .deliver = afs_deliver_fs_get_volume_status,
+ .abort_to_error = afs_abort_to_error,
+ .destructor = afs_get_volume_status_call_destructor,
+};
+
+/*
+ * fetch the status of a volume
+ */
+int afs_fs_get_volume_status(struct afs_server *server,
+ struct key *key,
+ struct afs_vnode *vnode,
+ struct afs_volume_status *vs,
+ const struct afs_wait_mode *wait_mode)
+{
+ struct afs_call *call;
+ __be32 *bp;
+ void *tmpbuf;
+
+ _enter("");
+
+ tmpbuf = kmalloc(AFSOPAQUEMAX, GFP_KERNEL);
+ if (!tmpbuf)
+ return -ENOMEM;
+
+ call = afs_alloc_flat_call(&afs_RXFSGetVolumeStatus, 2 * 4, 12 * 4);
+ if (!call) {
+ kfree(tmpbuf);
+ return -ENOMEM;
+ }
+
+ call->key = key;
+ call->reply = vnode;
+ call->reply2 = vs;
+ call->reply3 = tmpbuf;
+ call->service_id = FS_SERVICE;
+ call->port = htons(AFS_FS_PORT);
+
+ /* marshall the parameters */
+ bp = call->request;
+ bp[0] = htonl(FSGETVOLUMESTATUS);
+ bp[1] = htonl(vnode->fid.vid);
+
+ return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+}
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 515a5d12d8f..47f5fed7195 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -209,11 +209,15 @@ bad_inode:
*/
void afs_zap_data(struct afs_vnode *vnode)
{
- _enter("zap data {%x:%u}", vnode->fid.vid, vnode->fid.vnode);
+ _enter("{%x:%u}", vnode->fid.vid, vnode->fid.vnode);
/* nuke all the non-dirty pages that aren't locked, mapped or being
- * written back */
- invalidate_remote_inode(&vnode->vfs_inode);
+ * written back in a regular file and completely discard the pages in a
+ * directory or symlink */
+ if (S_ISREG(vnode->vfs_inode.i_mode))
+ invalidate_remote_inode(&vnode->vfs_inode);
+ else
+ invalidate_inode_pages2(vnode->vfs_inode.i_mapping);
}
/*
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index a30d4fa768e..4953ba5a6f4 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -506,6 +506,10 @@ extern int afs_fs_store_data(struct afs_server *, struct afs_writeback *,
extern int afs_fs_setattr(struct afs_server *, struct key *,
struct afs_vnode *, struct iattr *,
const struct afs_wait_mode *);
+extern int afs_fs_get_volume_status(struct afs_server *, struct key *,
+ struct afs_vnode *,
+ struct afs_volume_status *,
+ const struct afs_wait_mode *);
/*
* inode.c
@@ -672,6 +676,8 @@ extern int afs_vnode_rename(struct afs_vnode *, struct afs_vnode *,
extern int afs_vnode_store_data(struct afs_writeback *, pgoff_t, pgoff_t,
unsigned, unsigned);
extern int afs_vnode_setattr(struct afs_vnode *, struct key *, struct iattr *);
+extern int afs_vnode_get_volume_status(struct afs_vnode *, struct key *,
+ struct afs_volume_status *);
/*
* volume.c
diff --git a/fs/afs/super.c b/fs/afs/super.c
index d24be334b60..579af632c8e 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -21,22 +21,20 @@
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/parser.h>
+#include <linux/statfs.h>
#include "internal.h"
#define AFS_FS_MAGIC 0x6B414653 /* 'kAFS' */
static void afs_i_init_once(void *foo, struct kmem_cache *cachep,
unsigned long flags);
-
static int afs_get_sb(struct file_system_type *fs_type,
int flags, const char *dev_name,
void *data, struct vfsmount *mnt);
-
static struct inode *afs_alloc_inode(struct super_block *sb);
-
static void afs_put_super(struct super_block *sb);
-
static void afs_destroy_inode(struct inode *inode);
+static int afs_statfs(struct dentry *dentry, struct kstatfs *buf);
struct file_system_type afs_fs_type = {
.owner = THIS_MODULE,
@@ -47,7 +45,7 @@ struct file_system_type afs_fs_type = {
};
static const struct super_operations afs_super_ops = {
- .statfs = simple_statfs,
+ .statfs = afs_statfs,
.alloc_inode = afs_alloc_inode,
.drop_inode = generic_delete_inode,
.write_inode = afs_write_inode,
@@ -488,6 +486,7 @@ static struct inode *afs_alloc_inode(struct super_block *sb)
vnode->flags = 1 << AFS_VNODE_UNSET;
vnode->cb_promised = false;
+ _leave(" = %p", &vnode->vfs_inode);
return &vnode->vfs_inode;
}
@@ -498,7 +497,7 @@ static void afs_destroy_inode(struct inode *inode)
{
struct afs_vnode *vnode = AFS_FS_I(inode);
- _enter("{%lu}", inode->i_ino);
+ _enter("%p{%x:%u}", inode, vnode->fid.vid, vnode->fid.vnode);
_debug("DESTROY INODE %p", inode);
@@ -507,3 +506,36 @@ static void afs_destroy_inode(struct inode *inode)
kmem_cache_free(afs_inode_cachep, vnode);
atomic_dec(&afs_count_active_inodes);
}
+
+/*
+ * return information about an AFS volume
+ */
+static int afs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+ struct afs_volume_status vs;
+ struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode);
+ struct key *key;
+ int ret;
+
+ key = afs_request_key(vnode->volume->cell);
+ if (IS_ERR(key))
+ return PTR_ERR(key);
+
+ ret = afs_vnode_get_volume_status(vnode, key, &vs);
+ key_put(key);
+ if (ret < 0) {
+ _leave(" = %d", ret);
+ return ret;
+ }
+
+ buf->f_type = dentry->d_sb->s_magic;
+ buf->f_bsize = AFS_BLOCK_SIZE;
+ buf->f_namelen = AFSNAMEMAX - 1;
+
+ if (vs.max_quota == 0)
+ buf->f_blocks = vs.part_max_blocks;
+ else
+ buf->f_blocks = vs.max_quota;
+ buf->f_bavail = buf->f_bfree = buf->f_blocks - vs.blocks_in_use;
+ return 0;
+}
diff --git a/fs/afs/vnode.c b/fs/afs/vnode.c
index ec814660209..c36c98ce2c3 100644
--- a/fs/afs/vnode.c
+++ b/fs/afs/vnode.c
@@ -175,24 +175,33 @@ static void afs_vnode_deleted_remotely(struct afs_vnode *vnode)
{
struct afs_server *server;
+ _enter("{%p}", vnode->server);
+
set_bit(AFS_VNODE_DELETED, &vnode->flags);
server = vnode->server;
- if (vnode->cb_promised) {
- spin_lock(&server->cb_lock);
+ if (server) {
if (vnode->cb_promised) {
- rb_erase(&vnode->cb_promise, &server->cb_promises);
- vnode->cb_promised = false;
+ spin_lock(&server->cb_lock);
+ if (vnode->cb_promised) {
+ rb_erase(&vnode->cb_promise,
+ &server->cb_promises);
+ vnode->cb_promised = false;
+ }
+ spin_unlock(&server->cb_lock);
}
- spin_unlock(&server->cb_lock);
- }
- spin_lock(&vnode->server->fs_lock);
- rb_erase(&vnode->server_rb, &vnode->server->fs_vnodes);
- spin_unlock(&vnode->server->fs_lock);
+ spin_lock(&server->fs_lock);
+ rb_erase(&vnode->server_rb, &server->fs_vnodes);
+ spin_unlock(&server->fs_lock);
- vnode->server = NULL;
- afs_put_server(server);
+ vnode->server = NULL;
+ afs_put_server(server);
+ } else {
+ ASSERT(!vnode->cb_promised);
+ }
+
+ _leave("");
}
/*
@@ -225,7 +234,7 @@ void afs_vnode_finalise_status_update(struct afs_vnode *vnode,
*/
static void afs_vnode_status_update_failed(struct afs_vnode *vnode, int ret)
{
- _enter("%p,%d", vnode, ret);
+ _enter("{%x:%u},%d", vnode->fid.vid, vnode->fid.vnode, ret);
spin_lock(&vnode->lock);
@@ -860,3 +869,55 @@ no_server:
spin_unlock(&vnode->lock);
return PTR_ERR(server);
}
+
+/*
+ * get the status of a volume
+ */
+int afs_vnode_get_volume_status(struct afs_vnode *vnode, struct key *key,
+ struct afs_volume_status *vs)
+{
+ struct afs_server *server;
+ int ret;
+
+ _enter("%s{%x:%u.%u},%x,",
+ vnode->volume->vlocation->vldb.name,
+ vnode->fid.vid,
+ vnode->fid.vnode,
+ vnode->fid.unique,
+ key_serial(key));
+
+ /* this op will fetch the status */
+ spin_lock(&vnode->lock);
+ vnode->update_cnt++;
+ spin_unlock(&vnode->lock);
+
+ do {
+ /* pick a server to query */
+ server = afs_volume_pick_fileserver(vnode);
+ if (IS_ERR(server))
+ goto no_server;
+
+ _debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
+
+ ret = afs_fs_get_volume_status(server, key, vnode, vs, &afs_sync_call);
+
+ } while (!afs_volume_release_fileserver(vnode, server, ret));
+
+ /* adjust the flags */
+ if (ret == 0) {
+ afs_vnode_finalise_status_update(vnode, server);
+ afs_put_server(server);
+ } else {
+ afs_vnode_status_update_failed(vnode, ret);
+ }
+
+ _leave(" = %d", ret);
+ return ret;
+
+no_server:
+ spin_lock(&vnode->lock);
+ vnode->update_cnt--;
+ ASSERTCMP(vnode->update_cnt, >=, 0);
+ spin_unlock(&vnode->lock);
+ return PTR_ERR(server);
+}
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 67ae4dbf66b..28f37516c12 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -395,8 +395,9 @@ static int afs_write_back_from_locked_page(struct afs_writeback *wb,
if (n == 0)
goto no_more;
if (pages[0]->index != start) {
- for (n--; n >= 0; n--)
- put_page(pages[n]);
+ do {
+ put_page(pages[--n]);
+ } while (n > 0);
goto no_more;
}
diff --git a/fs/aio.c b/fs/aio.c
index ac1c1587aa0..dbe699e9828 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -30,6 +30,7 @@
#include <linux/highmem.h>
#include <linux/workqueue.h>
#include <linux/security.h>
+#include <linux/eventfd.h>
#include <asm/kmap_types.h>
#include <asm/uaccess.h>
@@ -417,6 +418,7 @@ static struct kiocb fastcall *__aio_get_req(struct kioctx *ctx)
req->private = NULL;
req->ki_iovec = NULL;
INIT_LIST_HEAD(&req->ki_run_list);
+ req->ki_eventfd = ERR_PTR(-EINVAL);
/* Check if the completion queue has enough free space to
* accept an event from this io.
@@ -458,6 +460,8 @@ static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
{
assert_spin_locked(&ctx->ctx_lock);
+ if (!IS_ERR(req->ki_eventfd))
+ fput(req->ki_eventfd);
if (req->ki_dtor)
req->ki_dtor(req);
if (req->ki_iovec != &req->ki_inline_vec)
@@ -942,6 +946,14 @@ int fastcall aio_complete(struct kiocb *iocb, long res, long res2)
return 1;
}
+ /*
+ * Check if the user asked us to deliver the result through an
+ * eventfd. The eventfd_signal() function is safe to be called
+ * from IRQ context.
+ */
+ if (!IS_ERR(iocb->ki_eventfd))
+ eventfd_signal(iocb->ki_eventfd, 1);
+
info = &ctx->ring_info;
/* add a completion event to the ring buffer.
@@ -1526,8 +1538,7 @@ int fastcall io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
ssize_t ret;
/* enforce forwards compatibility on users */
- if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2 ||
- iocb->aio_reserved3)) {
+ if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2)) {
pr_debug("EINVAL: io_submit: reserve field set\n");
return -EINVAL;
}
@@ -1551,6 +1562,19 @@ int fastcall io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
fput(file);
return -EAGAIN;
}
+ if (iocb->aio_flags & IOCB_FLAG_RESFD) {
+ /*
+ * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
+ * instance of the file* now. The file descriptor must be
+ * an eventfd() fd, and will be signaled for each completed
+ * event using the eventfd_signal() function.
+ */
+ req->ki_eventfd = eventfd_fget((int) iocb->aio_resfd);
+ if (unlikely(IS_ERR(req->ki_eventfd))) {
+ ret = PTR_ERR(req->ki_eventfd);
+ goto out_put_req;
+ }
+ }
req->ki_filp = file;
ret = put_user(req->ki_key, &user_iocb->aio_key);
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
new file mode 100644
index 00000000000..40fe3a3222e
--- /dev/null
+++ b/fs/anon_inodes.c
@@ -0,0 +1,200 @@
+/*
+ * fs/anon_inodes.c
+ *
+ * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
+ *
+ * Thanks to Arnd Bergmann for code review and suggestions.
+ * More changes for Thomas Gleixner suggestions.
+ *
+ */
+
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/magic.h>
+#include <linux/anon_inodes.h>
+
+#include <asm/uaccess.h>
+
+static struct vfsmount *anon_inode_mnt __read_mostly;
+static struct inode *anon_inode_inode;
+static const struct file_operations anon_inode_fops;
+
+static int anon_inodefs_get_sb(struct file_system_type *fs_type, int flags,
+ const char *dev_name, void *data,
+ struct vfsmount *mnt)
+{
+ return get_sb_pseudo(fs_type, "anon_inode:", NULL, ANON_INODE_FS_MAGIC,
+ mnt);
+}
+
+static int anon_inodefs_delete_dentry(struct dentry *dentry)
+{
+ /*
+ * We faked vfs to believe the dentry was hashed when we created it.
+ * Now we restore the flag so that dput() will work correctly.
+ */
+ dentry->d_flags |= DCACHE_UNHASHED;
+ return 1;
+}
+
+static struct file_system_type anon_inode_fs_type = {
+ .name = "anon_inodefs",
+ .get_sb = anon_inodefs_get_sb,
+ .kill_sb = kill_anon_super,
+};
+static struct dentry_operations anon_inodefs_dentry_operations = {
+ .d_delete = anon_inodefs_delete_dentry,
+};
+
+/**
+ * anon_inode_getfd - creates a new file instance by hooking it up to and
+ * anonymous inode, and a dentry that describe the "class"
+ * of the file
+ *
+ * @pfd: [out] pointer to the file descriptor
+ * @dpinode: [out] pointer to the inode
+ * @pfile: [out] pointer to the file struct
+ * @name: [in] name of the "class" of the new file
+ * @fops [in] file operations for the new file
+ * @priv [in] private data for the new file (will be file's private_data)
+ *
+ * Creates a new file by hooking it on a single inode. This is useful for files
+ * that do not need to have a full-fledged inode in order to operate correctly.
+ * All the files created with anon_inode_getfd() will share a single inode, by
+ * hence saving memory and avoiding code duplication for the file/inode/dentry
+ * setup.
+ */
+int anon_inode_getfd(int *pfd, struct inode **pinode, struct file **pfile,
+ const char *name, const struct file_operations *fops,
+ void *priv)
+{
+ struct qstr this;
+ struct dentry *dentry;
+ struct inode *inode;
+ struct file *file;
+ int error, fd;
+
+ if (IS_ERR(anon_inode_inode))
+ return -ENODEV;
+ file = get_empty_filp();
+ if (!file)
+ return -ENFILE;
+
+ inode = igrab(anon_inode_inode);
+ if (IS_ERR(inode)) {
+ error = PTR_ERR(inode);
+ goto err_put_filp;
+ }
+
+ error = get_unused_fd();
+ if (error < 0)
+ goto err_iput;
+ fd = error;
+
+ /*
+ * Link the inode to a directory entry by creating a unique name
+ * using the inode sequence number.
+ */
+ error = -ENOMEM;
+ this.name = name;
+ this.len = strlen(name);
+ this.hash = 0;
+ dentry = d_alloc(anon_inode_mnt->mnt_sb->s_root, &this);
+ if (!dentry)
+ goto err_put_unused_fd;
+ dentry->d_op = &anon_inodefs_dentry_operations;
+ /* Do not publish this dentry inside the global dentry hash table */
+ dentry->d_flags &= ~DCACHE_UNHASHED;
+ d_instantiate(dentry, inode);
+
+ file->f_path.mnt = mntget(anon_inode_mnt);
+ file->f_path.dentry = dentry;
+ file->f_mapping = inode->i_mapping;
+
+ file->f_pos = 0;
+ file->f_flags = O_RDWR;
+ file->f_op = fops;
+ file->f_mode = FMODE_READ | FMODE_WRITE;
+ file->f_version = 0;
+ file->private_data = priv;
+
+ fd_install(fd, file);
+
+ *pfd = fd;
+ *pinode = inode;
+ *pfile = file;
+ return 0;
+
+err_put_unused_fd:
+ put_unused_fd(fd);
+err_iput:
+ iput(inode);
+err_put_filp:
+ put_filp(file);
+ return error;
+}
+
+/*
+ * A single inode exist for all anon_inode files. Contrary to pipes,
+ * anon_inode inodes has no per-instance data associated, so we can avoid
+ * the allocation of multiple of them.
+ */
+static struct inode *anon_inode_mkinode(void)
+{
+ struct inode *inode = new_inode(anon_inode_mnt->mnt_sb);
+
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+
+ inode->i_fop = &anon_inode_fops;
+
+ /*
+ * Mark the inode dirty from the very beginning,
+ * that way it will never be moved to the dirty
+ * list because mark_inode_dirty() will think
+ * that it already _is_ on the dirty list.
+ */
+ inode->i_state = I_DIRTY;
+ inode->i_mode = S_IRUSR | S_IWUSR;
+ inode->i_uid = current->fsuid;
+ inode->i_gid = current->fsgid;
+ inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ return inode;
+}
+
+static int __init anon_inode_init(void)
+{
+ int error;
+
+ error = register_filesystem(&anon_inode_fs_type);
+ if (error)
+ goto err_exit;
+ anon_inode_mnt = kern_mount(&anon_inode_fs_type);
+ if (IS_ERR(anon_inode_mnt)) {
+ error = PTR_ERR(anon_inode_mnt);
+ goto err_unregister_filesystem;
+ }
+ anon_inode_inode = anon_inode_mkinode();
+ if (IS_ERR(anon_inode_inode)) {
+ error = PTR_ERR(anon_inode_inode);
+ goto err_mntput;
+ }
+
+ return 0;
+
+err_mntput:
+ mntput(anon_inode_mnt);
+err_unregister_filesystem:
+ unregister_filesystem(&anon_inode_fs_type);
+err_exit:
+ panic(KERN_ERR "anon_inode_init() failed (%d)\n", error);
+}
+
+fs_initcall(anon_inode_init);
+
diff --git a/fs/autofs/autofs_i.h b/fs/autofs/autofs_i.h
index 4ef544434b5..8b4cca3c470 100644
--- a/fs/autofs/autofs_i.h
+++ b/fs/autofs/autofs_i.h
@@ -101,7 +101,7 @@ struct autofs_symlink {
struct autofs_sb_info {
u32 magic;
struct file *pipe;
- pid_t oz_pgrp;
+ struct pid *oz_pgrp;
int catatonic;
struct super_block *sb;
unsigned long exp_timeout;
@@ -122,7 +122,7 @@ static inline struct autofs_sb_info *autofs_sbi(struct super_block *sb)
filesystem without "magic".) */
static inline int autofs_oz_mode(struct autofs_sb_info *sbi) {
- return sbi->catatonic || process_group(current) == sbi->oz_pgrp;
+ return sbi->catatonic || task_pgrp(current) == sbi->oz_pgrp;
}
/* Hash operations */
diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c
index aa0b61ff827..e7204d71acc 100644
--- a/fs/autofs/inode.c
+++ b/fs/autofs/inode.c
@@ -34,12 +34,14 @@ void autofs_kill_sb(struct super_block *sb)
if (!sbi)
goto out_kill_sb;
- if ( !sbi->catatonic )
+ if (!sbi->catatonic)
autofs_catatonic_mode(sbi); /* Free wait queues, close pipe */
+ put_pid(sbi->oz_pgrp);
+
autofs_hash_nuke(sbi);
- for ( n = 0 ; n < AUTOFS_MAX_SYMLINKS ; n++ ) {
- if ( test_bit(n, sbi->symlink_bitmap) )
+ for (n = 0; n < AUTOFS_MAX_SYMLINKS; n++) {
+ if (test_bit(n, sbi->symlink_bitmap))
kfree(sbi->symlink[n].data);
}
@@ -69,7 +71,8 @@ static match_table_t autofs_tokens = {
{Opt_err, NULL}
};
-static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid, pid_t *pgrp, int *minproto, int *maxproto)
+static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid,
+ pid_t *pgrp, int *minproto, int *maxproto)
{
char *p;
substring_t args[MAX_OPT_ARGS];
@@ -138,9 +141,10 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
int pipefd;
struct autofs_sb_info *sbi;
int minproto, maxproto;
+ pid_t pgid;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
- if ( !sbi )
+ if (!sbi)
goto fail_unlock;
DPRINTK(("autofs: starting up, sbi = %p\n",sbi));
@@ -149,7 +153,6 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
sbi->pipe = NULL;
sbi->catatonic = 1;
sbi->exp_timeout = 0;
- sbi->oz_pgrp = process_group(current);
autofs_initialize_hash(&sbi->dirhash);
sbi->queues = NULL;
memset(sbi->symlink_bitmap, 0, sizeof(long)*AUTOFS_SYMLINK_BITMAP_LEN);
@@ -169,26 +172,36 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
goto fail_iput;
/* Can this call block? - WTF cares? s is locked. */
- if ( parse_options(data,&pipefd,&root_inode->i_uid,&root_inode->i_gid,&sbi->oz_pgrp,&minproto,&maxproto) ) {
+ if (parse_options(data, &pipefd, &root_inode->i_uid,
+ &root_inode->i_gid, &pgid, &minproto,
+ &maxproto)) {
printk("autofs: called with bogus options\n");
goto fail_dput;
}
/* Couldn't this be tested earlier? */
- if ( minproto > AUTOFS_PROTO_VERSION ||
- maxproto < AUTOFS_PROTO_VERSION ) {
+ if (minproto > AUTOFS_PROTO_VERSION ||
+ maxproto < AUTOFS_PROTO_VERSION) {
printk("autofs: kernel does not match daemon version\n");
goto fail_dput;
}
- DPRINTK(("autofs: pipe fd = %d, pgrp = %u\n", pipefd, sbi->oz_pgrp));
+ DPRINTK(("autofs: pipe fd = %d, pgrp = %u\n", pipefd, pgid));
+ sbi->oz_pgrp = find_get_pid(pgid);
+
+ if (!sbi->oz_pgrp) {
+ printk("autofs: could not find process group %d\n", pgid);
+ goto fail_dput;
+ }
+
pipe = fget(pipefd);
- if ( !pipe ) {
+ if (!pipe) {
printk("autofs: could not open pipe file descriptor\n");
- goto fail_dput;
+ goto fail_put_pid;
}
- if ( !pipe->f_op || !pipe->f_op->write )
+
+ if (!pipe->f_op || !pipe->f_op->write)
goto fail_fput;
sbi->pipe = pipe;
sbi->catatonic = 0;
@@ -202,6 +215,8 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
fail_fput:
printk("autofs: pipe file descriptor does not contain proper ops\n");
fput(pipe);
+fail_put_pid:
+ put_pid(sbi->oz_pgrp);
fail_dput:
dput(root);
goto fail_free;
@@ -230,7 +245,7 @@ static void autofs_read_inode(struct inode *inode)
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
inode->i_blocks = 0;
- if ( ino == AUTOFS_ROOT_INO ) {
+ if (ino == AUTOFS_ROOT_INO) {
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR;
inode->i_op = &autofs_root_inode_operations;
inode->i_fop = &autofs_root_operations;
@@ -241,12 +256,12 @@ static void autofs_read_inode(struct inode *inode)
inode->i_uid = inode->i_sb->s_root->d_inode->i_uid;
inode->i_gid = inode->i_sb->s_root->d_inode->i_gid;
- if ( ino >= AUTOFS_FIRST_SYMLINK && ino < AUTOFS_FIRST_DIR_INO ) {
+ if (ino >= AUTOFS_FIRST_SYMLINK && ino < AUTOFS_FIRST_DIR_INO) {
/* Symlink inode - should be in symlink list */
struct autofs_symlink *sl;
n = ino - AUTOFS_FIRST_SYMLINK;
- if ( n >= AUTOFS_MAX_SYMLINKS || !test_bit(n,sbi->symlink_bitmap)) {
+ if (n >= AUTOFS_MAX_SYMLINKS || !test_bit(n,sbi->symlink_bitmap)) {
printk("autofs: Looking for bad symlink inode %u\n", (unsigned int) ino);
return;
}
diff --git a/fs/autofs/root.c b/fs/autofs/root.c
index f2597205939..c1489533277 100644
--- a/fs/autofs/root.c
+++ b/fs/autofs/root.c
@@ -67,8 +67,8 @@ static int autofs_root_readdir(struct file *filp, void *dirent, filldir_t filldi
filp->f_pos = ++nr;
/* fall through */
default:
- while ( onr = nr, ent = autofs_hash_enum(dirhash,&nr,ent) ) {
- if ( !ent->dentry || d_mountpoint(ent->dentry) ) {
+ while (onr = nr, ent = autofs_hash_enum(dirhash,&nr,ent)) {
+ if (!ent->dentry || d_mountpoint(ent->dentry)) {
if (filldir(dirent,ent->name,ent->len,onr,ent->ino,DT_UNKNOWN) < 0)
goto out;
filp->f_pos = nr;
@@ -88,10 +88,10 @@ static int try_to_fill_dentry(struct dentry *dentry, struct super_block *sb, str
struct autofs_dir_ent *ent;
int status = 0;
- if ( !(ent = autofs_hash_lookup(&sbi->dirhash, &dentry->d_name)) ) {
+ if (!(ent = autofs_hash_lookup(&sbi->dirhash, &dentry->d_name))) {
do {
- if ( status && dentry->d_inode ) {
- if ( status != -ENOENT )
+ if (status && dentry->d_inode) {
+ if (status != -ENOENT)
printk("autofs warning: lookup failure on positive dentry, status = %d, name = %s\n", status, dentry->d_name.name);
return 0; /* Try to get the kernel to invalidate this dentry */
}
@@ -106,7 +106,7 @@ static int try_to_fill_dentry(struct dentry *dentry, struct super_block *sb, str
return 1;
}
status = autofs_wait(sbi, &dentry->d_name);
- } while (!(ent = autofs_hash_lookup(&sbi->dirhash, &dentry->d_name)) );
+ } while (!(ent = autofs_hash_lookup(&sbi->dirhash, &dentry->d_name)));
}
/* Abuse this field as a pointer to the directory entry, used to
@@ -124,13 +124,13 @@ static int try_to_fill_dentry(struct dentry *dentry, struct super_block *sb, str
/* If this is a directory that isn't a mount point, bitch at the
daemon and fix it in user space */
- if ( S_ISDIR(dentry->d_inode->i_mode) && !d_mountpoint(dentry) ) {
+ if (S_ISDIR(dentry->d_inode->i_mode) && !d_mountpoint(dentry)) {
return !autofs_wait(sbi, &dentry->d_name);
}
/* We don't update the usages for the autofs daemon itself, this
is necessary for recursive autofs mounts */
- if ( !autofs_oz_mode(sbi) ) {
+ if (!autofs_oz_mode(sbi)) {
autofs_update_usage(&sbi->dirhash,ent);
}
@@ -157,7 +157,7 @@ static int autofs_revalidate(struct dentry * dentry, struct nameidata *nd)
sbi = autofs_sbi(dir->i_sb);
/* Pending dentry */
- if ( dentry->d_flags & DCACHE_AUTOFS_PENDING ) {
+ if (dentry->d_flags & DCACHE_AUTOFS_PENDING) {
if (autofs_oz_mode(sbi))
res = 1;
else
@@ -173,7 +173,7 @@ static int autofs_revalidate(struct dentry * dentry, struct nameidata *nd)
}
/* Check for a non-mountpoint directory */
- if ( S_ISDIR(dentry->d_inode->i_mode) && !d_mountpoint(dentry) ) {
+ if (S_ISDIR(dentry->d_inode->i_mode) && !d_mountpoint(dentry)) {
if (autofs_oz_mode(sbi))
res = 1;
else
@@ -183,9 +183,9 @@ static int autofs_revalidate(struct dentry * dentry, struct nameidata *nd)
}
/* Update the usage list */
- if ( !autofs_oz_mode(sbi) ) {
+ if (!autofs_oz_mode(sbi)) {
ent = (struct autofs_dir_ent *) dentry->d_time;
- if ( ent )
+ if (ent)
autofs_update_usage(&sbi->dirhash,ent);
}
unlock_kernel();
@@ -213,8 +213,10 @@ static struct dentry *autofs_root_lookup(struct inode *dir, struct dentry *dentr
sbi = autofs_sbi(dir->i_sb);
oz_mode = autofs_oz_mode(sbi);
- DPRINTK(("autofs_lookup: pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d\n",
- current->pid, process_group(current), sbi->catatonic, oz_mode));
+ DPRINTK(("autofs_lookup: pid = %u, pgrp = %u, catatonic = %d, "
+ "oz_mode = %d\n", pid_nr(task_pid(current)),
+ process_group(current), sbi->catatonic,
+ oz_mode));
/*
* Mark the dentry incomplete, but add it. This is needed so
@@ -258,7 +260,7 @@ static struct dentry *autofs_root_lookup(struct inode *dir, struct dentry *dentr
* doesn't do the right thing for all system calls, but it should
* be OK for the operations we permit from an autofs.
*/
- if ( dentry->d_inode && d_unhashed(dentry) )
+ if (dentry->d_inode && d_unhashed(dentry))
return ERR_PTR(-ENOENT);
return NULL;
@@ -277,18 +279,18 @@ static int autofs_root_symlink(struct inode *dir, struct dentry *dentry, const c
autofs_say(dentry->d_name.name,dentry->d_name.len);
lock_kernel();
- if ( !autofs_oz_mode(sbi) ) {
+ if (!autofs_oz_mode(sbi)) {
unlock_kernel();
return -EACCES;
}
- if ( autofs_hash_lookup(dh, &dentry->d_name) ) {
+ if (autofs_hash_lookup(dh, &dentry->d_name)) {
unlock_kernel();
return -EEXIST;
}
n = find_first_zero_bit(sbi->symlink_bitmap,AUTOFS_MAX_SYMLINKS);
- if ( n >= AUTOFS_MAX_SYMLINKS ) {
+ if (n >= AUTOFS_MAX_SYMLINKS) {
unlock_kernel();
return -ENOSPC;
}
@@ -297,14 +299,14 @@ static int autofs_root_symlink(struct inode *dir, struct dentry *dentry, const c
sl = &sbi->symlink[n];
sl->len = strlen(symname);
sl->data = kmalloc(slsize = sl->len+1, GFP_KERNEL);
- if ( !sl->data ) {
+ if (!sl->data) {
clear_bit(n,sbi->symlink_bitmap);
unlock_kernel();
return -ENOSPC;
}
ent = kmalloc(sizeof(struct autofs_dir_ent), GFP_KERNEL);
- if ( !ent ) {
+ if (!ent) {
kfree(sl->data);
clear_bit(n,sbi->symlink_bitmap);
unlock_kernel();
@@ -312,7 +314,7 @@ static int autofs_root_symlink(struct inode *dir, struct dentry *dentry, const c
}
ent->name = kmalloc(dentry->d_name.len+1, GFP_KERNEL);
- if ( !ent->name ) {
+ if (!ent->name) {
kfree(sl->data);
kfree(ent);
clear_bit(n,sbi->symlink_bitmap);
@@ -354,23 +356,23 @@ static int autofs_root_unlink(struct inode *dir, struct dentry *dentry)
/* This allows root to remove symlinks */
lock_kernel();
- if ( !autofs_oz_mode(sbi) && !capable(CAP_SYS_ADMIN) ) {
+ if (!autofs_oz_mode(sbi) && !capable(CAP_SYS_ADMIN)) {
unlock_kernel();
return -EACCES;
}
ent = autofs_hash_lookup(dh, &dentry->d_name);
- if ( !ent ) {
+ if (!ent) {
unlock_kernel();
return -ENOENT;
}
n = ent->ino - AUTOFS_FIRST_SYMLINK;
- if ( n >= AUTOFS_MAX_SYMLINKS ) {
+ if (n >= AUTOFS_MAX_SYMLINKS) {
unlock_kernel();
return -EISDIR; /* It's a directory, dummy */
}
- if ( !test_bit(n,sbi->symlink_bitmap) ) {
+ if (!test_bit(n,sbi->symlink_bitmap)) {
unlock_kernel();
return -EINVAL; /* Nonexistent symlink? Shouldn't happen */
}
@@ -392,23 +394,23 @@ static int autofs_root_rmdir(struct inode *dir, struct dentry *dentry)
struct autofs_dir_ent *ent;
lock_kernel();
- if ( !autofs_oz_mode(sbi) ) {
+ if (!autofs_oz_mode(sbi)) {
unlock_kernel();
return -EACCES;
}
ent = autofs_hash_lookup(dh, &dentry->d_name);
- if ( !ent ) {
+ if (!ent) {
unlock_kernel();
return -ENOENT;
}
- if ( (unsigned int)ent->ino < AUTOFS_FIRST_DIR_INO ) {
+ if ((unsigned int)ent->ino < AUTOFS_FIRST_DIR_INO) {
unlock_kernel();
return -ENOTDIR; /* Not a directory */
}
- if ( ent->dentry != dentry ) {
+ if (ent->dentry != dentry) {
printk("autofs_rmdir: odentry != dentry for entry %s\n", dentry->d_name.name);
}
@@ -429,18 +431,18 @@ static int autofs_root_mkdir(struct inode *dir, struct dentry *dentry, int mode)
ino_t ino;
lock_kernel();
- if ( !autofs_oz_mode(sbi) ) {
+ if (!autofs_oz_mode(sbi)) {
unlock_kernel();
return -EACCES;
}
ent = autofs_hash_lookup(dh, &dentry->d_name);
- if ( ent ) {
+ if (ent) {
unlock_kernel();
return -EEXIST;
}
- if ( sbi->next_dir_ino < AUTOFS_FIRST_DIR_INO ) {
+ if (sbi->next_dir_ino < AUTOFS_FIRST_DIR_INO) {
printk("autofs: Out of inode numbers -- what the heck did you do??\n");
unlock_kernel();
return -ENOSPC;
@@ -448,13 +450,13 @@ static int autofs_root_mkdir(struct inode *dir, struct dentry *dentry, int mode)
ino = sbi->next_dir_ino++;
ent = kmalloc(sizeof(struct autofs_dir_ent), GFP_KERNEL);
- if ( !ent ) {
+ if (!ent) {
unlock_kernel();
return -ENOSPC;
}
ent->name = kmalloc(dentry->d_name.len+1, GFP_KERNEL);
- if ( !ent->name ) {
+ if (!ent->name) {
kfree(ent);
unlock_kernel();
return -ENOSPC;
@@ -483,7 +485,7 @@ static inline int autofs_get_set_timeout(struct autofs_sb_info *sbi,
put_user(sbi->exp_timeout / HZ, p))
return -EFAULT;
- if ( ntimeout > ULONG_MAX/HZ )
+ if (ntimeout > ULONG_MAX/HZ)
sbi->exp_timeout = 0;
else
sbi->exp_timeout = ntimeout * HZ;
@@ -511,15 +513,14 @@ static inline int autofs_expire_run(struct super_block *sb,
pkt.hdr.proto_version = AUTOFS_PROTO_VERSION;
pkt.hdr.type = autofs_ptype_expire;
- if ( !sbi->exp_timeout ||
- !(ent = autofs_expire(sb,sbi,mnt)) )
+ if (!sbi->exp_timeout || !(ent = autofs_expire(sb,sbi,mnt)))
return -EAGAIN;
pkt.len = ent->len;
memcpy(pkt.name, ent->name, pkt.len);
pkt.name[pkt.len] = '\0';
- if ( copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)) )
+ if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)))
return -EFAULT;
return 0;
@@ -537,11 +538,11 @@ static int autofs_root_ioctl(struct inode *inode, struct file *filp,
DPRINTK(("autofs_ioctl: cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u\n",cmd,arg,sbi,process_group(current)));
- if ( _IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) ||
- _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT )
+ if (_IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) ||
+ _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT)
return -ENOTTY;
- if ( !autofs_oz_mode(sbi) && !capable(CAP_SYS_ADMIN) )
+ if (!autofs_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
return -EPERM;
switch(cmd) {
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index 5769a2f9ad6..692364e8ffc 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -218,8 +218,7 @@ static match_table_t tokens = {
};
static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid,
- pid_t *pgrp, unsigned int *type,
- int *minproto, int *maxproto)
+ pid_t *pgrp, unsigned int *type, int *minproto, int *maxproto)
{
char *p;
substring_t args[MAX_OPT_ARGS];
@@ -314,7 +313,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
struct autofs_info *ino;
sbi = kmalloc(sizeof(*sbi), GFP_KERNEL);
- if ( !sbi )
+ if (!sbi)
goto fail_unlock;
DPRINTK("starting up, sbi = %p",sbi);
@@ -363,10 +362,9 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
root->d_fsdata = ino;
/* Can this call block? */
- if (parse_options(data, &pipefd,
- &root_inode->i_uid, &root_inode->i_gid,
- &sbi->oz_pgrp, &sbi->type,
- &sbi->min_proto, &sbi->max_proto)) {
+ if (parse_options(data, &pipefd, &root_inode->i_uid, &root_inode->i_gid,
+ &sbi->oz_pgrp, &sbi->type, &sbi->min_proto,
+ &sbi->max_proto)) {
printk("autofs: called with bogus options\n");
goto fail_dput;
}
@@ -396,11 +394,11 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
DPRINTK("pipe fd = %d, pgrp = %u", pipefd, sbi->oz_pgrp);
pipe = fget(pipefd);
- if ( !pipe ) {
+ if (!pipe) {
printk("autofs: could not open pipe file descriptor\n");
goto fail_dput;
}
- if ( !pipe->f_op || !pipe->f_op->write )
+ if (!pipe->f_op || !pipe->f_op->write)
goto fail_fput;
sbi->pipe = pipe;
sbi->pipefd = pipefd;
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 15170f4e13a..2d4c8a3e604 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -759,7 +759,7 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
struct autofs_info *p_ino;
/* This allows root to remove symlinks */
- if ( !autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN) )
+ if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
return -EACCES;
if (atomic_dec_and_test(&ino->count)) {
@@ -833,7 +833,7 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode)
struct autofs_info *p_ino;
struct inode *inode;
- if ( !autofs4_oz_mode(sbi) )
+ if (!autofs4_oz_mode(sbi))
return -EACCES;
DPRINTK("dentry %p, creating %.*s",
@@ -871,11 +871,11 @@ static inline int autofs4_get_set_timeout(struct autofs_sb_info *sbi,
int rv;
unsigned long ntimeout;
- if ( (rv = get_user(ntimeout, p)) ||
- (rv = put_user(sbi->exp_timeout/HZ, p)) )
+ if ((rv = get_user(ntimeout, p)) ||
+ (rv = put_user(sbi->exp_timeout/HZ, p)))
return rv;
- if ( ntimeout > ULONG_MAX/HZ )
+ if (ntimeout > ULONG_MAX/HZ)
sbi->exp_timeout = 0;
else
sbi->exp_timeout = ntimeout * HZ;
@@ -906,7 +906,7 @@ static inline int autofs4_ask_reghost(struct autofs_sb_info *sbi, int __user *p)
DPRINTK("returning %d", sbi->needs_reghost);
status = put_user(sbi->needs_reghost, p);
- if ( status )
+ if (status)
return status;
sbi->needs_reghost = 0;
@@ -975,11 +975,11 @@ static int autofs4_root_ioctl(struct inode *inode, struct file *filp,
DPRINTK("cmd = 0x%08x, arg = 0x%08lx, sbi = %p, pgrp = %u",
cmd,arg,sbi,process_group(current));
- if ( _IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) ||
- _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT )
+ if (_IOC_TYPE(cmd) != _IOC_TYPE(AUTOFS_IOC_FIRST) ||
+ _IOC_NR(cmd) - _IOC_NR(AUTOFS_IOC_FIRST) >= AUTOFS_IOC_COUNT)
return -ENOTTY;
- if ( !autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN) )
+ if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
return -EPERM;
switch(cmd) {
diff --git a/fs/compat.c b/fs/compat.c
index 9cf75df9b2b..7b21b0a8259 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -46,6 +46,7 @@
#include <linux/tsacct_kern.h>
#include <linux/security.h>
#include <linux/highmem.h>
+#include <linux/signal.h>
#include <linux/poll.h>
#include <linux/mm.h>
#include <linux/eventpoll.h>
@@ -2199,3 +2200,51 @@ asmlinkage long compat_sys_epoll_pwait(int epfd,
#endif /* TIF_RESTORE_SIGMASK */
#endif /* CONFIG_EPOLL */
+
+#ifdef CONFIG_SIGNALFD
+
+asmlinkage long compat_sys_signalfd(int ufd,
+ const compat_sigset_t __user *sigmask,
+ compat_size_t sigsetsize)
+{
+ compat_sigset_t ss32;
+ sigset_t tmp;
+ sigset_t __user *ksigmask;
+
+ if (sigsetsize != sizeof(compat_sigset_t))
+ return -EINVAL;
+ if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
+ return -EFAULT;
+ sigset_from_compat(&tmp, &ss32);
+ ksigmask = compat_alloc_user_space(sizeof(sigset_t));
+ if (copy_to_user(ksigmask, &tmp, sizeof(sigset_t)))
+ return -EFAULT;
+
+ return sys_signalfd(ufd, ksigmask, sizeof(sigset_t));
+}
+
+#endif /* CONFIG_SIGNALFD */
+
+#ifdef CONFIG_TIMERFD
+
+asmlinkage long compat_sys_timerfd(int ufd, int clockid, int flags,
+ const struct compat_itimerspec __user *utmr)
+{
+ long res;
+ struct itimerspec t;
+ struct itimerspec __user *ut;
+
+ res = -EFAULT;
+ if (get_compat_itimerspec(&t, utmr))
+ goto err_exit;
+ ut = compat_alloc_user_space(sizeof(*ut));
+ if (copy_to_user(ut, &t, sizeof(t)) )
+ goto err_exit;
+
+ res = sys_timerfd(ufd, clockid, flags, ut);
+err_exit:
+ return res;
+}
+
+#endif /* CONFIG_TIMERFD */
+
diff --git a/fs/eventfd.c b/fs/eventfd.c
new file mode 100644
index 00000000000..480e2b3c416
--- /dev/null
+++ b/fs/eventfd.c
@@ -0,0 +1,228 @@
+/*
+ * fs/eventfd.c
+ *
+ * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
+ *
+ */
+
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/anon_inodes.h>
+#include <linux/eventfd.h>
+
+struct eventfd_ctx {
+ spinlock_t lock;
+ wait_queue_head_t wqh;
+ /*
+ * Every time that a write(2) is performed on an eventfd, the
+ * value of the __u64 being written is added to "count" and a
+ * wakeup is performed on "wqh". A read(2) will return the "count"
+ * value to userspace, and will reset "count" to zero. The kernel
+ * size eventfd_signal() also, adds to the "count" counter and
+ * issue a wakeup.
+ */
+ __u64 count;
+};
+
+/*
+ * Adds "n" to the eventfd counter "count". Returns "n" in case of
+ * success, or a value lower then "n" in case of coutner overflow.
+ * This function is supposed to be called by the kernel in paths
+ * that do not allow sleeping. In this function we allow the counter
+ * to reach the ULLONG_MAX value, and we signal this as overflow
+ * condition by returining a POLLERR to poll(2).
+ */
+int eventfd_signal(struct file *file, int n)
+{
+ struct eventfd_ctx *ctx = file->private_data;
+ unsigned long flags;
+
+ if (n < 0)
+ return -EINVAL;
+ spin_lock_irqsave(&ctx->lock, flags);
+ if (ULLONG_MAX - ctx->count < n)
+ n = (int) (ULLONG_MAX - ctx->count);
+ ctx->count += n;
+ if (waitqueue_active(&ctx->wqh))
+ wake_up_locked(&ctx->wqh);
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ return n;
+}
+
+static int eventfd_release(struct inode *inode, struct file *file)
+{
+ kfree(file->private_data);
+ return 0;
+}
+
+static unsigned int eventfd_poll(struct file *file, poll_table *wait)
+{
+ struct eventfd_ctx *ctx = file->private_data;
+ unsigned int events = 0;
+ unsigned long flags;
+
+ poll_wait(file, &ctx->wqh, wait);
+
+ spin_lock_irqsave(&ctx->lock, flags);
+ if (ctx->count > 0)
+ events |= POLLIN;
+ if (ctx->count == ULLONG_MAX)
+ events |= POLLERR;
+ if (ULLONG_MAX - 1 > ctx->count)
+ events |= POLLOUT;
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ return events;
+}
+
+static ssize_t eventfd_read(struct file *file, char __user *buf, size_t count,
+ loff_t *ppos)
+{
+ struct eventfd_ctx *ctx = file->private_data;
+ ssize_t res;
+ __u64 ucnt;
+ DECLARE_WAITQUEUE(wait, current);
+
+ if (count < sizeof(ucnt))
+ return -EINVAL;
+ spin_lock_irq(&ctx->lock);
+ res = -EAGAIN;
+ ucnt = ctx->count;
+ if (ucnt > 0)
+ res = sizeof(ucnt);
+ else if (!(file->f_flags & O_NONBLOCK)) {
+ __add_wait_queue(&ctx->wqh, &wait);
+ for (res = 0;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (ctx->count > 0) {
+ ucnt = ctx->count;
+ res = sizeof(ucnt);
+ break;
+ }
+ if (signal_pending(current)) {
+ res = -ERESTARTSYS;
+ break;
+ }
+ spin_unlock_irq(&ctx->lock);
+ schedule();
+ spin_lock_irq(&ctx->lock);
+ }
+ __remove_wait_queue(&ctx->wqh, &wait);
+ __set_current_state(TASK_RUNNING);
+ }
+ if (res > 0) {
+ ctx->count = 0;
+ if (waitqueue_active(&ctx->wqh))
+ wake_up_locked(&ctx->wqh);
+ }
+ spin_unlock_irq(&ctx->lock);
+ if (res > 0 && put_user(ucnt, (__u64 __user *) buf))
+ return -EFAULT;
+
+ return res;
+}
+
+static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t count,
+ loff_t *ppos)
+{
+ struct eventfd_ctx *ctx = file->private_data;
+ ssize_t res;
+ __u64 ucnt;
+ DECLARE_WAITQUEUE(wait, current);
+
+ if (count < sizeof(ucnt))
+ return -EINVAL;
+ if (copy_from_user(&ucnt, buf, sizeof(ucnt)))
+ return -EFAULT;
+ if (ucnt == ULLONG_MAX)
+ return -EINVAL;
+ spin_lock_irq(&ctx->lock);
+ res = -EAGAIN;
+ if (ULLONG_MAX - ctx->count > ucnt)
+ res = sizeof(ucnt);
+ else if (!(file->f_flags & O_NONBLOCK)) {
+ __add_wait_queue(&ctx->wqh, &wait);
+ for (res = 0;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (ULLONG_MAX - ctx->count > ucnt) {
+ res = sizeof(ucnt);
+ break;
+ }
+ if (signal_pending(current)) {
+ res = -ERESTARTSYS;
+ break;
+ }
+ spin_unlock_irq(&ctx->lock);
+ schedule();
+ spin_lock_irq(&ctx->lock);
+ }
+ __remove_wait_queue(&ctx->wqh, &wait);
+ __set_current_state(TASK_RUNNING);
+ }
+ if (res > 0) {
+ ctx->count += ucnt;
+ if (waitqueue_active(&ctx->wqh))
+ wake_up_locked(&ctx->wqh);
+ }
+ spin_unlock_irq(&ctx->lock);
+
+ return res;
+}
+
+static const struct file_operations eventfd_fops = {
+ .release = eventfd_release,
+ .poll = eventfd_poll,
+ .read = eventfd_read,
+ .write = eventfd_write,
+};
+
+struct file *eventfd_fget(int fd)
+{
+ struct file *file;
+
+ file = fget(fd);
+ if (!file)
+ return ERR_PTR(-EBADF);
+ if (file->f_op != &eventfd_fops) {
+ fput(file);
+ return ERR_PTR(-EINVAL);
+ }
+
+ return file;
+}
+
+asmlinkage long sys_eventfd(unsigned int count)
+{
+ int error, fd;
+ struct eventfd_ctx *ctx;
+ struct file *file;
+ struct inode *inode;
+
+ ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ init_waitqueue_head(&ctx->wqh);
+ spin_lock_init(&ctx->lock);
+ ctx->count = count;
+
+ /*
+ * When we call this, the initialization must be complete, since
+ * anon_inode_getfd() will install the fd.
+ */
+ error = anon_inode_getfd(&fd, &inode, &file, "[eventfd]",
+ &eventfd_fops, ctx);
+ if (!error)
+ return fd;
+
+ kfree(ctx);
+ return error;
+}
+
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index b5c7ca58493..1aad34ea61a 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -11,7 +11,6 @@
*
*/
-#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/sched.h>
@@ -34,6 +33,7 @@
#include <linux/mount.h>
#include <linux/bitops.h>
#include <linux/mutex.h>
+#include <linux/anon_inodes.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/io.h>
@@ -41,7 +41,6 @@
#include <asm/atomic.h>
#include <asm/semaphore.h>
-
/*
* LOCKING:
* There are three level of locking required by epoll :
@@ -74,9 +73,6 @@
* a greater scalability.
*/
-
-#define EVENTPOLLFS_MAGIC 0x03111965 /* My birthday should work for this :) */
-
#define DEBUG_EPOLL 0
#if DEBUG_EPOLL > 0
@@ -106,7 +102,6 @@
#define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))
-
struct epoll_filefd {
struct file *file;
int fd;
@@ -224,43 +219,6 @@ struct ep_pqueue {
struct epitem *epi;
};
-
-
-static void ep_poll_safewake_init(struct poll_safewake *psw);
-static void ep_poll_safewake(struct poll_safewake *psw, wait_queue_head_t *wq);
-static int ep_getfd(int *efd, struct inode **einode, struct file **efile,
- struct eventpoll *ep);
-static int ep_alloc(struct eventpoll **pep);
-static void ep_free(struct eventpoll *ep);
-static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd);
-static void ep_use_epitem(struct epitem *epi);
-static void ep_release_epitem(struct epitem *epi);
-static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
- poll_table *pt);
-static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi);
-static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
- struct file *tfile, int fd);
-static int ep_modify(struct eventpoll *ep, struct epitem *epi,
- struct epoll_event *event);
-static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi);
-static int ep_unlink(struct eventpoll *ep, struct epitem *epi);
-static int ep_remove(struct eventpoll *ep, struct epitem *epi);
-static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key);
-static int ep_eventpoll_close(struct inode *inode, struct file *file);
-static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait);
-static int ep_send_events(struct eventpoll *ep, struct list_head *txlist,
- struct epoll_event __user *events, int maxevents);
-static int ep_events_transfer(struct eventpoll *ep,
- struct epoll_event __user *events,
- int maxevents);
-static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
- int maxevents, long timeout);
-static int eventpollfs_delete_dentry(struct dentry *dentry);
-static struct inode *ep_eventpoll_inode(void);
-static int eventpollfs_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name,
- void *data, struct vfsmount *mnt);
-
/*
* This semaphore is used to serialize ep_free() and eventpoll_release_file().
*/
@@ -275,37 +233,6 @@ static struct kmem_cache *epi_cache __read_mostly;
/* Slab cache used to allocate "struct eppoll_entry" */
static struct kmem_cache *pwq_cache __read_mostly;
-/* Virtual fs used to allocate inodes for eventpoll files */
-static struct vfsmount *eventpoll_mnt __read_mostly;
-
-/* File callbacks that implement the eventpoll file behaviour */
-static const struct file_operations eventpoll_fops = {
- .release = ep_eventpoll_close,
- .poll = ep_eventpoll_poll
-};
-
-/*
- * This is used to register the virtual file system from where
- * eventpoll inodes are allocated.
- */
-static struct file_system_type eventpoll_fs_type = {
- .name = "eventpollfs",
- .get_sb = eventpollfs_get_sb,
- .kill_sb = kill_anon_super,
-};
-
-/* Very basic directory entry operations for the eventpoll virtual file system */
-static struct dentry_operations eventpollfs_dentry_operations = {
- .d_delete = eventpollfs_delete_dentry,
-};
-
-
-
-/* Fast test to see if the file is an evenpoll file */
-static inline int is_file_epoll(struct file *f)
-{
- return f->f_op == &eventpoll_fops;
-}
/* Setup the structure that is used as key for the rb-tree */
static inline void ep_set_ffd(struct epoll_filefd *ffd,
@@ -374,7 +301,6 @@ static void ep_poll_safewake_init(struct poll_safewake *psw)
spin_lock_init(&psw->lock);
}
-
/*
* Perform a safe wake up of the poll wait list. The problem is that
* with the new callback'd wake up system, it is possible that the
@@ -429,399 +355,144 @@ static void ep_poll_safewake(struct poll_safewake *psw, wait_queue_head_t *wq)
spin_unlock_irqrestore(&psw->lock, flags);
}
-
/*
- * This is called from eventpoll_release() to unlink files from the eventpoll
- * interface. We need to have this facility to cleanup correctly files that are
- * closed without being removed from the eventpoll interface.
+ * This function unregister poll callbacks from the associated file descriptor.
+ * Since this must be called without holding "ep->lock" the atomic exchange trick
+ * will protect us from multiple unregister.
*/
-void eventpoll_release_file(struct file *file)
+static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
{
- struct list_head *lsthead = &file->f_ep_links;
- struct eventpoll *ep;
- struct epitem *epi;
+ int nwait;
+ struct list_head *lsthead = &epi->pwqlist;
+ struct eppoll_entry *pwq;
- /*
- * We don't want to get "file->f_ep_lock" because it is not
- * necessary. It is not necessary because we're in the "struct file"
- * cleanup path, and this means that noone is using this file anymore.
- * The only hit might come from ep_free() but by holding the semaphore
- * will correctly serialize the operation. We do need to acquire
- * "ep->sem" after "epmutex" because ep_remove() requires it when called
- * from anywhere but ep_free().
- */
- mutex_lock(&epmutex);
+ /* This is called without locks, so we need the atomic exchange */
+ nwait = xchg(&epi->nwait, 0);
- while (!list_empty(lsthead)) {
- epi = list_first_entry(lsthead, struct epitem, fllink);
+ if (nwait) {
+ while (!list_empty(lsthead)) {
+ pwq = list_first_entry(lsthead, struct eppoll_entry, llink);
- ep = epi->ep;
- list_del_init(&epi->fllink);
- down_write(&ep->sem);
- ep_remove(ep, epi);
- up_write(&ep->sem);
+ list_del_init(&pwq->llink);
+ remove_wait_queue(pwq->whead, &pwq->wait);
+ kmem_cache_free(pwq_cache, pwq);
+ }
}
-
- mutex_unlock(&epmutex);
}
-
/*
- * It opens an eventpoll file descriptor by suggesting a storage of "size"
- * file descriptors. The size parameter is just an hint about how to size
- * data structures. It won't prevent the user to store more than "size"
- * file descriptors inside the epoll interface. It is the kernel part of
- * the userspace epoll_create(2).
+ * Unlink the "struct epitem" from all places it might have been hooked up.
+ * This function must be called with write IRQ lock on "ep->lock".
*/
-asmlinkage long sys_epoll_create(int size)
+static int ep_unlink(struct eventpoll *ep, struct epitem *epi)
{
- int error, fd = -1;
- struct eventpoll *ep;
- struct inode *inode;
- struct file *file;
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n",
- current, size));
-
- /*
- * Sanity check on the size parameter, and create the internal data
- * structure ( "struct eventpoll" ).
- */
- error = -EINVAL;
- if (size <= 0 || (error = ep_alloc(&ep)) != 0)
- goto eexit_1;
+ int error;
/*
- * Creates all the items needed to setup an eventpoll file. That is,
- * a file structure, and inode and a free file descriptor.
+ * It can happen that this one is called for an item already unlinked.
+ * The check protect us from doing a double unlink ( crash ).
*/
- error = ep_getfd(&fd, &inode, &file, ep);
- if (error)
- goto eexit_2;
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
- current, size, fd));
-
- return fd;
-
-eexit_2:
- ep_free(ep);
- kfree(ep);
-eexit_1:
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
- current, size, error));
- return error;
-}
-
-
-/*
- * The following function implements the controller interface for
- * the eventpoll file that enables the insertion/removal/change of
- * file descriptors inside the interest set. It represents
- * the kernel part of the user space epoll_ctl(2).
- */
-asmlinkage long
-sys_epoll_ctl(int epfd, int op, int fd, struct epoll_event __user *event)
-{
- int error;
- struct file *file, *tfile;
- struct eventpoll *ep;
- struct epitem *epi;
- struct epoll_event epds;
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p)\n",
- current, epfd, op, fd, event));
-
- error = -EFAULT;
- if (ep_op_has_event(op) &&
- copy_from_user(&epds, event, sizeof(struct epoll_event)))
- goto eexit_1;
-
- /* Get the "struct file *" for the eventpoll file */
- error = -EBADF;
- file = fget(epfd);
- if (!file)
- goto eexit_1;
-
- /* Get the "struct file *" for the target file */
- tfile = fget(fd);
- if (!tfile)
- goto eexit_2;
-
- /* The target file descriptor must support poll */
- error = -EPERM;
- if (!tfile->f_op || !tfile->f_op->poll)
- goto eexit_3;
+ error = -ENOENT;
+ if (!ep_rb_linked(&epi->rbn))
+ goto error_return;
/*
- * We have to check that the file structure underneath the file descriptor
- * the user passed to us _is_ an eventpoll file. And also we do not permit
- * adding an epoll file descriptor inside itself.
+ * Clear the event mask for the unlinked item. This will avoid item
+ * notifications to be sent after the unlink operation from inside
+ * the kernel->userspace event transfer loop.
*/
- error = -EINVAL;
- if (file == tfile || !is_file_epoll(file))
- goto eexit_3;
+ epi->event.events = 0;
/*
- * At this point it is safe to assume that the "private_data" contains
- * our own data structure.
+ * At this point is safe to do the job, unlink the item from our rb-tree.
+ * This operation togheter with the above check closes the door to
+ * double unlinks.
*/
- ep = file->private_data;
-
- down_write(&ep->sem);
-
- /* Try to lookup the file inside our RB tree */
- epi = ep_find(ep, tfile, fd);
-
- error = -EINVAL;
- switch (op) {
- case EPOLL_CTL_ADD:
- if (!epi) {
- epds.events |= POLLERR | POLLHUP;
-
- error = ep_insert(ep, &epds, tfile, fd);
- } else
- error = -EEXIST;
- break;
- case EPOLL_CTL_DEL:
- if (epi)
- error = ep_remove(ep, epi);
- else
- error = -ENOENT;
- break;
- case EPOLL_CTL_MOD:
- if (epi) {
- epds.events |= POLLERR | POLLHUP;
- error = ep_modify(ep, epi, &epds);
- } else
- error = -ENOENT;
- break;
- }
+ ep_rb_erase(&epi->rbn, &ep->rbr);
/*
- * The function ep_find() increments the usage count of the structure
- * so, if this is not NULL, we need to release it.
+ * If the item we are going to remove is inside the ready file descriptors
+ * we want to remove it from this list to avoid stale events.
*/
- if (epi)
- ep_release_epitem(epi);
+ if (ep_is_linked(&epi->rdllink))
+ list_del_init(&epi->rdllink);
- up_write(&ep->sem);
+ error = 0;
+error_return:
-eexit_3:
- fput(tfile);
-eexit_2:
- fput(file);
-eexit_1:
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p) = %d\n",
- current, epfd, op, fd, event, error));
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_unlink(%p, %p) = %d\n",
+ current, ep, epi->ffd.file, error));
return error;
}
-
/*
- * Implement the event wait interface for the eventpoll file. It is the kernel
- * part of the user space epoll_wait(2).
+ * Increment the usage count of the "struct epitem" making it sure
+ * that the user will have a valid pointer to reference.
*/
-asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events,
- int maxevents, int timeout)
+static void ep_use_epitem(struct epitem *epi)
{
- int error;
- struct file *file;
- struct eventpoll *ep;
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d)\n",
- current, epfd, events, maxevents, timeout));
-
- /* The maximum number of event must be greater than zero */
- if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
- return -EINVAL;
-
- /* Verify that the area passed by the user is writeable */
- if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))) {
- error = -EFAULT;
- goto eexit_1;
- }
-
- /* Get the "struct file *" for the eventpoll file */
- error = -EBADF;
- file = fget(epfd);
- if (!file)
- goto eexit_1;
-
- /*
- * We have to check that the file structure underneath the fd
- * the user passed to us _is_ an eventpoll file.
- */
- error = -EINVAL;
- if (!is_file_epoll(file))
- goto eexit_2;
-
- /*
- * At this point it is safe to assume that the "private_data" contains
- * our own data structure.
- */
- ep = file->private_data;
-
- /* Time to fish for events ... */
- error = ep_poll(ep, events, maxevents, timeout);
-
-eexit_2:
- fput(file);
-eexit_1:
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d) = %d\n",
- current, epfd, events, maxevents, timeout, error));
-
- return error;
+ atomic_inc(&epi->usecnt);
}
-
-#ifdef TIF_RESTORE_SIGMASK
-
/*
- * Implement the event wait interface for the eventpoll file. It is the kernel
- * part of the user space epoll_pwait(2).
+ * Decrement ( release ) the usage count by signaling that the user
+ * has finished using the structure. It might lead to freeing the
+ * structure itself if the count goes to zero.
*/
-asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
- int maxevents, int timeout, const sigset_t __user *sigmask,
- size_t sigsetsize)
+static void ep_release_epitem(struct epitem *epi)
{
- int error;
- sigset_t ksigmask, sigsaved;
-
- /*
- * If the caller wants a certain signal mask to be set during the wait,
- * we apply it here.
- */
- if (sigmask) {
- if (sigsetsize != sizeof(sigset_t))
- return -EINVAL;
- if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
- return -EFAULT;
- sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
- sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
- }
-
- error = sys_epoll_wait(epfd, events, maxevents, timeout);
-
- /*
- * If we changed the signal mask, we need to restore the original one.
- * In case we've got a signal while waiting, we do not restore the
- * signal mask yet, and we allow do_signal() to deliver the signal on
- * the way back to userspace, before the signal mask is restored.
- */
- if (sigmask) {
- if (error == -EINTR) {
- memcpy(&current->saved_sigmask, &sigsaved,
- sizeof(sigsaved));
- set_thread_flag(TIF_RESTORE_SIGMASK);
- } else
- sigprocmask(SIG_SETMASK, &sigsaved, NULL);
- }
-
- return error;
+ if (atomic_dec_and_test(&epi->usecnt))
+ kmem_cache_free(epi_cache, epi);
}
-#endif /* #ifdef TIF_RESTORE_SIGMASK */
-
-
/*
- * Creates the file descriptor to be used by the epoll interface.
+ * Removes a "struct epitem" from the eventpoll RB tree and deallocates
+ * all the associated resources.
*/
-static int ep_getfd(int *efd, struct inode **einode, struct file **efile,
- struct eventpoll *ep)
+static int ep_remove(struct eventpoll *ep, struct epitem *epi)
{
- struct qstr this;
- char name[32];
- struct dentry *dentry;
- struct inode *inode;
- struct file *file;
- int error, fd;
-
- /* Get an ready to use file */
- error = -ENFILE;
- file = get_empty_filp();
- if (!file)
- goto eexit_1;
-
- /* Allocates an inode from the eventpoll file system */
- inode = ep_eventpoll_inode();
- if (IS_ERR(inode)) {
- error = PTR_ERR(inode);
- goto eexit_2;
- }
-
- /* Allocates a free descriptor to plug the file onto */
- error = get_unused_fd();
- if (error < 0)
- goto eexit_3;
- fd = error;
+ int error;
+ unsigned long flags;
+ struct file *file = epi->ffd.file;
/*
- * Link the inode to a directory entry by creating a unique name
- * using the inode number.
+ * Removes poll wait queue hooks. We _have_ to do this without holding
+ * the "ep->lock" otherwise a deadlock might occur. This because of the
+ * sequence of the lock acquisition. Here we do "ep->lock" then the wait
+ * queue head lock when unregistering the wait queue. The wakeup callback
+ * will run by holding the wait queue head lock and will call our callback
+ * that will try to get "ep->lock".
*/
- error = -ENOMEM;
- sprintf(name, "[%lu]", inode->i_ino);
- this.name = name;
- this.len = strlen(name);
- this.hash = inode->i_ino;
- dentry = d_alloc(eventpoll_mnt->mnt_sb->s_root, &this);
- if (!dentry)
- goto eexit_4;
- dentry->d_op = &eventpollfs_dentry_operations;
- d_add(dentry, inode);
- file->f_path.mnt = mntget(eventpoll_mnt);
- file->f_path.dentry = dentry;
- file->f_mapping = inode->i_mapping;
-
- file->f_pos = 0;
- file->f_flags = O_RDONLY;
- file->f_op = &eventpoll_fops;
- file->f_mode = FMODE_READ;
- file->f_version = 0;
- file->private_data = ep;
-
- /* Install the new setup file into the allocated fd. */
- fd_install(fd, file);
-
- *efd = fd;
- *einode = inode;
- *efile = file;
- return 0;
+ ep_unregister_pollwait(ep, epi);
-eexit_4:
- put_unused_fd(fd);
-eexit_3:
- iput(inode);
-eexit_2:
- put_filp(file);
-eexit_1:
- return error;
-}
+ /* Remove the current item from the list of epoll hooks */
+ spin_lock(&file->f_ep_lock);
+ if (ep_is_linked(&epi->fllink))
+ list_del_init(&epi->fllink);
+ spin_unlock(&file->f_ep_lock);
+ /* We need to acquire the write IRQ lock before calling ep_unlink() */
+ write_lock_irqsave(&ep->lock, flags);
-static int ep_alloc(struct eventpoll **pep)
-{
- struct eventpoll *ep = kzalloc(sizeof(*ep), GFP_KERNEL);
+ /* Really unlink the item from the RB tree */
+ error = ep_unlink(ep, epi);
- if (!ep)
- return -ENOMEM;
+ write_unlock_irqrestore(&ep->lock, flags);
- rwlock_init(&ep->lock);
- init_rwsem(&ep->sem);
- init_waitqueue_head(&ep->wq);
- init_waitqueue_head(&ep->poll_wait);
- INIT_LIST_HEAD(&ep->rdllist);
- ep->rbr = RB_ROOT;
+ if (error)
+ goto error_return;
- *pep = ep;
+ /* At this point it is safe to free the eventpoll item */
+ ep_release_epitem(epi);
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_alloc() ep=%p\n",
- current, ep));
- return 0;
-}
+ error = 0;
+error_return:
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_remove(%p, %p) = %d\n",
+ current, ep, file, error));
+ return error;
+}
static void ep_free(struct eventpoll *ep)
{
@@ -865,6 +536,104 @@ static void ep_free(struct eventpoll *ep)
mutex_unlock(&epmutex);
}
+static int ep_eventpoll_release(struct inode *inode, struct file *file)
+{
+ struct eventpoll *ep = file->private_data;
+
+ if (ep) {
+ ep_free(ep);
+ kfree(ep);
+ }
+
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: close() ep=%p\n", current, ep));
+ return 0;
+}
+
+static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
+{
+ unsigned int pollflags = 0;
+ unsigned long flags;
+ struct eventpoll *ep = file->private_data;
+
+ /* Insert inside our poll wait queue */
+ poll_wait(file, &ep->poll_wait, wait);
+
+ /* Check our condition */
+ read_lock_irqsave(&ep->lock, flags);
+ if (!list_empty(&ep->rdllist))
+ pollflags = POLLIN | POLLRDNORM;
+ read_unlock_irqrestore(&ep->lock, flags);
+
+ return pollflags;
+}
+
+/* File callbacks that implement the eventpoll file behaviour */
+static const struct file_operations eventpoll_fops = {
+ .release = ep_eventpoll_release,
+ .poll = ep_eventpoll_poll
+};
+
+/* Fast test to see if the file is an evenpoll file */
+static inline int is_file_epoll(struct file *f)
+{
+ return f->f_op == &eventpoll_fops;
+}
+
+/*
+ * This is called from eventpoll_release() to unlink files from the eventpoll
+ * interface. We need to have this facility to cleanup correctly files that are
+ * closed without being removed from the eventpoll interface.
+ */
+void eventpoll_release_file(struct file *file)
+{
+ struct list_head *lsthead = &file->f_ep_links;
+ struct eventpoll *ep;
+ struct epitem *epi;
+
+ /*
+ * We don't want to get "file->f_ep_lock" because it is not
+ * necessary. It is not necessary because we're in the "struct file"
+ * cleanup path, and this means that noone is using this file anymore.
+ * The only hit might come from ep_free() but by holding the semaphore
+ * will correctly serialize the operation. We do need to acquire
+ * "ep->sem" after "epmutex" because ep_remove() requires it when called
+ * from anywhere but ep_free().
+ */
+ mutex_lock(&epmutex);
+
+ while (!list_empty(lsthead)) {
+ epi = list_first_entry(lsthead, struct epitem, fllink);
+
+ ep = epi->ep;
+ list_del_init(&epi->fllink);
+ down_write(&ep->sem);
+ ep_remove(ep, epi);
+ up_write(&ep->sem);
+ }
+
+ mutex_unlock(&epmutex);
+}
+
+static int ep_alloc(struct eventpoll **pep)
+{
+ struct eventpoll *ep = kzalloc(sizeof(*ep), GFP_KERNEL);
+
+ if (!ep)
+ return -ENOMEM;
+
+ rwlock_init(&ep->lock);
+ init_rwsem(&ep->sem);
+ init_waitqueue_head(&ep->wq);
+ init_waitqueue_head(&ep->poll_wait);
+ INIT_LIST_HEAD(&ep->rdllist);
+ ep->rbr = RB_ROOT;
+
+ *pep = ep;
+
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_alloc() ep=%p\n",
+ current, ep));
+ return 0;
+}
/*
* Search the file inside the eventpoll tree. It add usage count to
@@ -902,30 +671,58 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
return epir;
}
-
/*
- * Increment the usage count of the "struct epitem" making it sure
- * that the user will have a valid pointer to reference.
+ * This is the callback that is passed to the wait queue wakeup
+ * machanism. It is called by the stored file descriptors when they
+ * have events to report.
*/
-static void ep_use_epitem(struct epitem *epi)
+static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
+ int pwake = 0;
+ unsigned long flags;
+ struct epitem *epi = ep_item_from_wait(wait);
+ struct eventpoll *ep = epi->ep;
- atomic_inc(&epi->usecnt);
-}
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: poll_callback(%p) epi=%p ep=%p\n",
+ current, epi->ffd.file, epi, ep));
+ write_lock_irqsave(&ep->lock, flags);
-/*
- * Decrement ( release ) the usage count by signaling that the user
- * has finished using the structure. It might lead to freeing the
- * structure itself if the count goes to zero.
- */
-static void ep_release_epitem(struct epitem *epi)
-{
+ /*
+ * If the event mask does not contain any poll(2) event, we consider the
+ * descriptor to be disabled. This condition is likely the effect of the
+ * EPOLLONESHOT bit that disables the descriptor when an event is received,
+ * until the next EPOLL_CTL_MOD will be issued.
+ */
+ if (!(epi->event.events & ~EP_PRIVATE_BITS))
+ goto is_disabled;
- if (atomic_dec_and_test(&epi->usecnt))
- kmem_cache_free(epi_cache, epi);
-}
+ /* If this file is already in the ready list we exit soon */
+ if (ep_is_linked(&epi->rdllink))
+ goto is_linked;
+ list_add_tail(&epi->rdllink, &ep->rdllist);
+
+is_linked:
+ /*
+ * Wake up ( if active ) both the eventpoll wait list and the ->poll()
+ * wait list.
+ */
+ if (waitqueue_active(&ep->wq))
+ __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE |
+ TASK_INTERRUPTIBLE);
+ if (waitqueue_active(&ep->poll_wait))
+ pwake++;
+
+is_disabled:
+ write_unlock_irqrestore(&ep->lock, flags);
+
+ /* We have to call this outside the lock */
+ if (pwake)
+ ep_poll_safewake(&psw, &ep->poll_wait);
+
+ return 1;
+}
/*
* This is the callback that is used to add our wait queue to the
@@ -950,7 +747,6 @@ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
}
}
-
static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
{
int kcmp;
@@ -970,7 +766,6 @@ static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
rb_insert_color(&epi->rbn, &ep->rbr);
}
-
static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
struct file *tfile, int fd)
{
@@ -981,7 +776,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
error = -ENOMEM;
if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
- goto eexit_1;
+ goto error_return;
/* Item initialization follow here ... */
ep_rb_initnode(&epi->rbn);
@@ -1011,7 +806,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
* high memory pressure.
*/
if (epi->nwait < 0)
- goto eexit_2;
+ goto error_unregister;
/* Add the current item to the list of active epoll hook for this file */
spin_lock(&tfile->f_ep_lock);
@@ -1046,7 +841,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
return 0;
-eexit_2:
+error_unregister:
ep_unregister_pollwait(ep, epi);
/*
@@ -1059,11 +854,10 @@ eexit_2:
write_unlock_irqrestore(&ep->lock, flags);
kmem_cache_free(epi_cache, epi);
-eexit_1:
+error_return:
return error;
}
-
/*
* Modify the interest event mask by dropping an event if the new mask
* has a match in the current file status.
@@ -1126,216 +920,6 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
return 0;
}
-
-/*
- * This function unregister poll callbacks from the associated file descriptor.
- * Since this must be called without holding "ep->lock" the atomic exchange trick
- * will protect us from multiple unregister.
- */
-static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
-{
- int nwait;
- struct list_head *lsthead = &epi->pwqlist;
- struct eppoll_entry *pwq;
-
- /* This is called without locks, so we need the atomic exchange */
- nwait = xchg(&epi->nwait, 0);
-
- if (nwait) {
- while (!list_empty(lsthead)) {
- pwq = list_first_entry(lsthead, struct eppoll_entry, llink);
-
- list_del_init(&pwq->llink);
- remove_wait_queue(pwq->whead, &pwq->wait);
- kmem_cache_free(pwq_cache, pwq);
- }
- }
-}
-
-
-/*
- * Unlink the "struct epitem" from all places it might have been hooked up.
- * This function must be called with write IRQ lock on "ep->lock".
- */
-static int ep_unlink(struct eventpoll *ep, struct epitem *epi)
-{
- int error;
-
- /*
- * It can happen that this one is called for an item already unlinked.
- * The check protect us from doing a double unlink ( crash ).
- */
- error = -ENOENT;
- if (!ep_rb_linked(&epi->rbn))
- goto eexit_1;
-
- /*
- * Clear the event mask for the unlinked item. This will avoid item
- * notifications to be sent after the unlink operation from inside
- * the kernel->userspace event transfer loop.
- */
- epi->event.events = 0;
-
- /*
- * At this point is safe to do the job, unlink the item from our rb-tree.
- * This operation togheter with the above check closes the door to
- * double unlinks.
- */
- ep_rb_erase(&epi->rbn, &ep->rbr);
-
- /*
- * If the item we are going to remove is inside the ready file descriptors
- * we want to remove it from this list to avoid stale events.
- */
- if (ep_is_linked(&epi->rdllink))
- list_del_init(&epi->rdllink);
-
- error = 0;
-eexit_1:
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_unlink(%p, %p) = %d\n",
- current, ep, epi->ffd.file, error));
-
- return error;
-}
-
-
-/*
- * Removes a "struct epitem" from the eventpoll RB tree and deallocates
- * all the associated resources.
- */
-static int ep_remove(struct eventpoll *ep, struct epitem *epi)
-{
- int error;
- unsigned long flags;
- struct file *file = epi->ffd.file;
-
- /*
- * Removes poll wait queue hooks. We _have_ to do this without holding
- * the "ep->lock" otherwise a deadlock might occur. This because of the
- * sequence of the lock acquisition. Here we do "ep->lock" then the wait
- * queue head lock when unregistering the wait queue. The wakeup callback
- * will run by holding the wait queue head lock and will call our callback
- * that will try to get "ep->lock".
- */
- ep_unregister_pollwait(ep, epi);
-
- /* Remove the current item from the list of epoll hooks */
- spin_lock(&file->f_ep_lock);
- if (ep_is_linked(&epi->fllink))
- list_del_init(&epi->fllink);
- spin_unlock(&file->f_ep_lock);
-
- /* We need to acquire the write IRQ lock before calling ep_unlink() */
- write_lock_irqsave(&ep->lock, flags);
-
- /* Really unlink the item from the RB tree */
- error = ep_unlink(ep, epi);
-
- write_unlock_irqrestore(&ep->lock, flags);
-
- if (error)
- goto eexit_1;
-
- /* At this point it is safe to free the eventpoll item */
- ep_release_epitem(epi);
-
- error = 0;
-eexit_1:
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_remove(%p, %p) = %d\n",
- current, ep, file, error));
-
- return error;
-}
-
-
-/*
- * This is the callback that is passed to the wait queue wakeup
- * machanism. It is called by the stored file descriptors when they
- * have events to report.
- */
-static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
-{
- int pwake = 0;
- unsigned long flags;
- struct epitem *epi = ep_item_from_wait(wait);
- struct eventpoll *ep = epi->ep;
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: poll_callback(%p) epi=%p ep=%p\n",
- current, epi->ffd.file, epi, ep));
-
- write_lock_irqsave(&ep->lock, flags);
-
- /*
- * If the event mask does not contain any poll(2) event, we consider the
- * descriptor to be disabled. This condition is likely the effect of the
- * EPOLLONESHOT bit that disables the descriptor when an event is received,
- * until the next EPOLL_CTL_MOD will be issued.
- */
- if (!(epi->event.events & ~EP_PRIVATE_BITS))
- goto is_disabled;
-
- /* If this file is already in the ready list we exit soon */
- if (ep_is_linked(&epi->rdllink))
- goto is_linked;
-
- list_add_tail(&epi->rdllink, &ep->rdllist);
-
-is_linked:
- /*
- * Wake up ( if active ) both the eventpoll wait list and the ->poll()
- * wait list.
- */
- if (waitqueue_active(&ep->wq))
- __wake_up_locked(&ep->wq, TASK_UNINTERRUPTIBLE |
- TASK_INTERRUPTIBLE);
- if (waitqueue_active(&ep->poll_wait))
- pwake++;
-
-is_disabled:
- write_unlock_irqrestore(&ep->lock, flags);
-
- /* We have to call this outside the lock */
- if (pwake)
- ep_poll_safewake(&psw, &ep->poll_wait);
-
- return 1;
-}
-
-
-static int ep_eventpoll_close(struct inode *inode, struct file *file)
-{
- struct eventpoll *ep = file->private_data;
-
- if (ep) {
- ep_free(ep);
- kfree(ep);
- }
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: close() ep=%p\n", current, ep));
- return 0;
-}
-
-
-static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
-{
- unsigned int pollflags = 0;
- unsigned long flags;
- struct eventpoll *ep = file->private_data;
-
- /* Insert inside our poll wait queue */
- poll_wait(file, &ep->poll_wait, wait);
-
- /* Check our condition */
- read_lock_irqsave(&ep->lock, flags);
- if (!list_empty(&ep->rdllist))
- pollflags = POLLIN | POLLRDNORM;
- read_unlock_irqrestore(&ep->lock, flags);
-
- return pollflags;
-}
-
-
/*
* This function is called without holding the "ep->lock" since the call to
* __copy_to_user() might sleep, and also f_op->poll() might reenable the IRQ
@@ -1447,7 +1031,6 @@ static int ep_send_events(struct eventpoll *ep, struct list_head *txlist,
return eventcnt == 0 ? error: eventcnt;
}
-
/*
* Perform the transfer of events to user space.
*/
@@ -1483,7 +1066,6 @@ static int ep_events_transfer(struct eventpoll *ep,
return eventcnt;
}
-
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
int maxevents, long timeout)
{
@@ -1553,52 +1135,262 @@ retry:
return res;
}
-static int eventpollfs_delete_dentry(struct dentry *dentry)
+/*
+ * It opens an eventpoll file descriptor by suggesting a storage of "size"
+ * file descriptors. The size parameter is just an hint about how to size
+ * data structures. It won't prevent the user to store more than "size"
+ * file descriptors inside the epoll interface. It is the kernel part of
+ * the userspace epoll_create(2).
+ */
+asmlinkage long sys_epoll_create(int size)
{
+ int error, fd = -1;
+ struct eventpoll *ep;
+ struct inode *inode;
+ struct file *file;
- return 1;
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n",
+ current, size));
+
+ /*
+ * Sanity check on the size parameter, and create the internal data
+ * structure ( "struct eventpoll" ).
+ */
+ error = -EINVAL;
+ if (size <= 0 || (error = ep_alloc(&ep)) != 0)
+ goto error_return;
+
+ /*
+ * Creates all the items needed to setup an eventpoll file. That is,
+ * a file structure, and inode and a free file descriptor.
+ */
+ error = anon_inode_getfd(&fd, &inode, &file, "[eventpoll]",
+ &eventpoll_fops, ep);
+ if (error)
+ goto error_free;
+
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
+ current, size, fd));
+
+ return fd;
+
+error_free:
+ ep_free(ep);
+ kfree(ep);
+error_return:
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
+ current, size, error));
+ return error;
}
-static struct inode *ep_eventpoll_inode(void)
+/*
+ * The following function implements the controller interface for
+ * the eventpoll file that enables the insertion/removal/change of
+ * file descriptors inside the interest set. It represents
+ * the kernel part of the user space epoll_ctl(2).
+ */
+asmlinkage long sys_epoll_ctl(int epfd, int op, int fd,
+ struct epoll_event __user *event)
{
- int error = -ENOMEM;
- struct inode *inode = new_inode(eventpoll_mnt->mnt_sb);
+ int error;
+ struct file *file, *tfile;
+ struct eventpoll *ep;
+ struct epitem *epi;
+ struct epoll_event epds;
+
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p)\n",
+ current, epfd, op, fd, event));
+
+ error = -EFAULT;
+ if (ep_op_has_event(op) &&
+ copy_from_user(&epds, event, sizeof(struct epoll_event)))
+ goto error_return;
+
+ /* Get the "struct file *" for the eventpoll file */
+ error = -EBADF;
+ file = fget(epfd);
+ if (!file)
+ goto error_return;
+
+ /* Get the "struct file *" for the target file */
+ tfile = fget(fd);
+ if (!tfile)
+ goto error_fput;
+
+ /* The target file descriptor must support poll */
+ error = -EPERM;
+ if (!tfile->f_op || !tfile->f_op->poll)
+ goto error_tgt_fput;
+
+ /*
+ * We have to check that the file structure underneath the file descriptor
+ * the user passed to us _is_ an eventpoll file. And also we do not permit
+ * adding an epoll file descriptor inside itself.
+ */
+ error = -EINVAL;
+ if (file == tfile || !is_file_epoll(file))
+ goto error_tgt_fput;
- if (!inode)
- goto eexit_1;
+ /*
+ * At this point it is safe to assume that the "private_data" contains
+ * our own data structure.
+ */
+ ep = file->private_data;
+
+ down_write(&ep->sem);
- inode->i_fop = &eventpoll_fops;
+ /* Try to lookup the file inside our RB tree */
+ epi = ep_find(ep, tfile, fd);
+
+ error = -EINVAL;
+ switch (op) {
+ case EPOLL_CTL_ADD:
+ if (!epi) {
+ epds.events |= POLLERR | POLLHUP;
+ error = ep_insert(ep, &epds, tfile, fd);
+ } else
+ error = -EEXIST;
+ break;
+ case EPOLL_CTL_DEL:
+ if (epi)
+ error = ep_remove(ep, epi);
+ else
+ error = -ENOENT;
+ break;
+ case EPOLL_CTL_MOD:
+ if (epi) {
+ epds.events |= POLLERR | POLLHUP;
+ error = ep_modify(ep, epi, &epds);
+ } else
+ error = -ENOENT;
+ break;
+ }
/*
- * Mark the inode dirty from the very beginning,
- * that way it will never be moved to the dirty
- * list because mark_inode_dirty() will think
- * that it already _is_ on the dirty list.
+ * The function ep_find() increments the usage count of the structure
+ * so, if this is not NULL, we need to release it.
*/
- inode->i_state = I_DIRTY;
- inode->i_mode = S_IRUSR | S_IWUSR;
- inode->i_uid = current->fsuid;
- inode->i_gid = current->fsgid;
- inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- return inode;
-
-eexit_1:
- return ERR_PTR(error);
+ if (epi)
+ ep_release_epitem(epi);
+ up_write(&ep->sem);
+
+error_tgt_fput:
+ fput(tfile);
+error_fput:
+ fput(file);
+error_return:
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_ctl(%d, %d, %d, %p) = %d\n",
+ current, epfd, op, fd, event, error));
+
+ return error;
}
-static int
-eventpollfs_get_sb(struct file_system_type *fs_type, int flags,
- const char *dev_name, void *data, struct vfsmount *mnt)
+/*
+ * Implement the event wait interface for the eventpoll file. It is the kernel
+ * part of the user space epoll_wait(2).
+ */
+asmlinkage long sys_epoll_wait(int epfd, struct epoll_event __user *events,
+ int maxevents, int timeout)
{
- return get_sb_pseudo(fs_type, "eventpoll:", NULL, EVENTPOLLFS_MAGIC,
- mnt);
+ int error;
+ struct file *file;
+ struct eventpoll *ep;
+
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d)\n",
+ current, epfd, events, maxevents, timeout));
+
+ /* The maximum number of event must be greater than zero */
+ if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)
+ return -EINVAL;
+
+ /* Verify that the area passed by the user is writeable */
+ if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))) {
+ error = -EFAULT;
+ goto error_return;
+ }
+
+ /* Get the "struct file *" for the eventpoll file */
+ error = -EBADF;
+ file = fget(epfd);
+ if (!file)
+ goto error_return;
+
+ /*
+ * We have to check that the file structure underneath the fd
+ * the user passed to us _is_ an eventpoll file.
+ */
+ error = -EINVAL;
+ if (!is_file_epoll(file))
+ goto error_fput;
+
+ /*
+ * At this point it is safe to assume that the "private_data" contains
+ * our own data structure.
+ */
+ ep = file->private_data;
+
+ /* Time to fish for events ... */
+ error = ep_poll(ep, events, maxevents, timeout);
+
+error_fput:
+ fput(file);
+error_return:
+ DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_wait(%d, %p, %d, %d) = %d\n",
+ current, epfd, events, maxevents, timeout, error));
+
+ return error;
}
+#ifdef TIF_RESTORE_SIGMASK
-static int __init eventpoll_init(void)
+/*
+ * Implement the event wait interface for the eventpoll file. It is the kernel
+ * part of the user space epoll_pwait(2).
+ */
+asmlinkage long sys_epoll_pwait(int epfd, struct epoll_event __user *events,
+ int maxevents, int timeout, const sigset_t __user *sigmask,
+ size_t sigsetsize)
{
int error;
+ sigset_t ksigmask, sigsaved;
+
+ /*
+ * If the caller wants a certain signal mask to be set during the wait,
+ * we apply it here.
+ */
+ if (sigmask) {
+ if (sigsetsize != sizeof(sigset_t))
+ return -EINVAL;
+ if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
+ return -EFAULT;
+ sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+ sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+ }
+
+ error = sys_epoll_wait(epfd, events, maxevents, timeout);
+
+ /*
+ * If we changed the signal mask, we need to restore the original one.
+ * In case we've got a signal while waiting, we do not restore the
+ * signal mask yet, and we allow do_signal() to deliver the signal on
+ * the way back to userspace, before the signal mask is restored.
+ */
+ if (sigmask) {
+ if (error == -EINTR) {
+ memcpy(&current->saved_sigmask, &sigsaved,
+ sizeof(sigsaved));
+ set_thread_flag(TIF_RESTORE_SIGMASK);
+ } else
+ sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+ }
+
+ return error;
+}
+#endif /* #ifdef TIF_RESTORE_SIGMASK */
+
+static int __init eventpoll_init(void)
+{
mutex_init(&epmutex);
/* Initialize the structure used to perform safe poll wait head wake ups */
@@ -1614,39 +1406,7 @@ static int __init eventpoll_init(void)
sizeof(struct eppoll_entry), 0,
EPI_SLAB_DEBUG|SLAB_PANIC, NULL, NULL);
- /*
- * Register the virtual file system that will be the source of inodes
- * for the eventpoll files
- */
- error = register_filesystem(&eventpoll_fs_type);
- if (error)
- goto epanic;
-
- /* Mount the above commented virtual file system */
- eventpoll_mnt = kern_mount(&eventpoll_fs_type);
- error = PTR_ERR(eventpoll_mnt);
- if (IS_ERR(eventpoll_mnt))
- goto epanic;
-
- DNPRINTK(3, (KERN_INFO "[%p] eventpoll: successfully initialized.\n",
- current));
return 0;
-
-epanic:
- panic("eventpoll_init() failed\n");
}
+fs_initcall(eventpoll_init);
-
-static void __exit eventpoll_exit(void)
-{
- /* Undo all operations done inside eventpoll_init() */
- unregister_filesystem(&eventpoll_fs_type);
- mntput(eventpoll_mnt);
- kmem_cache_destroy(pwq_cache);
- kmem_cache_destroy(epi_cache);
-}
-
-module_init(eventpoll_init);
-module_exit(eventpoll_exit);
-
-MODULE_LICENSE("GPL");
diff --git a/fs/exec.c b/fs/exec.c
index 7cf078ec758..70fa36554c1 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -50,6 +50,7 @@
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/audit.h>
+#include <linux/signalfd.h>
#include <asm/uaccess.h>
#include <asm/mmu_context.h>
@@ -582,6 +583,13 @@ static int de_thread(struct task_struct *tsk)
int count;
/*
+ * Tell all the sighand listeners that this sighand has
+ * been detached. The signalfd_detach() function grabs the
+ * sighand lock, if signal listeners are present on the sighand.
+ */
+ signalfd_detach(tsk);
+
+ /*
* If we don't share sighandlers, then we aren't sharing anything
* and we can just re-use it all.
*/
@@ -702,7 +710,7 @@ static int de_thread(struct task_struct *tsk)
*/
detach_pid(tsk, PIDTYPE_PID);
tsk->pid = leader->pid;
- attach_pid(tsk, PIDTYPE_PID, tsk->pid);
+ attach_pid(tsk, PIDTYPE_PID, find_pid(tsk->pid));
transfer_pid(leader, tsk, PIDTYPE_PGID);
transfer_pid(leader, tsk, PIDTYPE_SID);
list_replace_rcu(&leader->tasks, &tsk->tasks);
@@ -757,8 +765,7 @@ no_thread_group:
spin_unlock(&oldsighand->siglock);
write_unlock_irq(&tasklist_lock);
- if (atomic_dec_and_test(&oldsighand->count))
- kmem_cache_free(sighand_cachep, oldsighand);
+ __cleanup_sighand(oldsighand);
}
BUG_ON(!thread_group_leader(tsk));
diff --git a/fs/mpage.c b/fs/mpage.c
index 0fb914fc2ee..c1698f2291a 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -454,11 +454,18 @@ EXPORT_SYMBOL(mpage_readpage);
* written, so it can intelligently allocate a suitably-sized BIO. For now,
* just allocate full-size (16-page) BIOs.
*/
-static struct bio *
-__mpage_writepage(struct bio *bio, struct page *page, get_block_t get_block,
- sector_t *last_block_in_bio, int *ret, struct writeback_control *wbc,
- writepage_t writepage_fn)
+struct mpage_data {
+ struct bio *bio;
+ sector_t last_block_in_bio;
+ get_block_t *get_block;
+ unsigned use_writepage;
+};
+
+static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
+ void *data)
{
+ struct mpage_data *mpd = data;
+ struct bio *bio = mpd->bio;
struct address_space *mapping = page->mapping;
struct inode *inode = page->mapping->host;
const unsigned blkbits = inode->i_blkbits;
@@ -476,6 +483,7 @@ __mpage_writepage(struct bio *bio, struct page *page, get_block_t get_block,
int length;
struct buffer_head map_bh;
loff_t i_size = i_size_read(inode);
+ int ret = 0;
if (page_has_buffers(page)) {
struct buffer_head *head = page_buffers(page);
@@ -538,7 +546,7 @@ __mpage_writepage(struct bio *bio, struct page *page, get_block_t get_block,
map_bh.b_state = 0;
map_bh.b_size = 1 << blkbits;
- if (get_block(inode, block_in_file, &map_bh, 1))
+ if (mpd->get_block(inode, block_in_file, &map_bh, 1))
goto confused;
if (buffer_new(&map_bh))
unmap_underlying_metadata(map_bh.b_bdev,
@@ -584,7 +592,7 @@ page_is_mapped:
/*
* This page will go to BIO. Do we need to send this BIO off first?
*/
- if (bio && *last_block_in_bio != blocks[0] - 1)
+ if (bio && mpd->last_block_in_bio != blocks[0] - 1)
bio = mpage_bio_submit(WRITE, bio);
alloc_new:
@@ -641,7 +649,7 @@ alloc_new:
boundary_block, 1 << blkbits);
}
} else {
- *last_block_in_bio = blocks[blocks_per_page - 1];
+ mpd->last_block_in_bio = blocks[blocks_per_page - 1];
}
goto out;
@@ -649,18 +657,19 @@ confused:
if (bio)
bio = mpage_bio_submit(WRITE, bio);
- if (writepage_fn) {
- *ret = (*writepage_fn)(page, wbc);
+ if (mpd->use_writepage) {
+ ret = mapping->a_ops->writepage(page, wbc);
} else {
- *ret = -EAGAIN;
+ ret = -EAGAIN;
goto out;
}
/*
* The caller has a ref on the inode, so *mapping is stable
*/
- mapping_set_error(mapping, *ret);
+ mapping_set_error(mapping, ret);
out:
- return bio;
+ mpd->bio = bio;
+ return ret;
}
/**
@@ -683,120 +692,27 @@ out:
* the call was made get new I/O started against them. If wbc->sync_mode is
* WB_SYNC_ALL then we were called for data integrity and we must wait for
* existing IO to complete.
- *
- * If you fix this you should check generic_writepages() also!
*/
int
mpage_writepages(struct address_space *mapping,
struct writeback_control *wbc, get_block_t get_block)
{
- struct backing_dev_info *bdi = mapping->backing_dev_info;
- struct bio *bio = NULL;
- sector_t last_block_in_bio = 0;
- int ret = 0;
- int done = 0;
- int (*writepage)(struct page *page, struct writeback_control *wbc);
- struct pagevec pvec;
- int nr_pages;
- pgoff_t index;
- pgoff_t end; /* Inclusive */
- int scanned = 0;
- int range_whole = 0;
-
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
- wbc->encountered_congestion = 1;
- return 0;
- }
-
- writepage = NULL;
- if (get_block == NULL)
- writepage = mapping->a_ops->writepage;
-
- pagevec_init(&pvec, 0);
- if (wbc->range_cyclic) {
- index = mapping->writeback_index; /* Start from prev offset */
- end = -1;
- } else {
- index = wbc->range_start >> PAGE_CACHE_SHIFT;
- end = wbc->range_end >> PAGE_CACHE_SHIFT;
- if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
- range_whole = 1;
- scanned = 1;
+ int ret;
+
+ if (!get_block)
+ ret = generic_writepages(mapping, wbc);
+ else {
+ struct mpage_data mpd = {
+ .bio = NULL,
+ .last_block_in_bio = 0,
+ .get_block = get_block,
+ .use_writepage = 1,
+ };
+
+ ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
+ if (mpd.bio)
+ mpage_bio_submit(WRITE, mpd.bio);
}
-retry:
- while (!done && (index <= end) &&
- (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
- PAGECACHE_TAG_DIRTY,
- min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
- unsigned i;
-
- scanned = 1;
- for (i = 0; i < nr_pages; i++) {
- struct page *page = pvec.pages[i];
-
- /*
- * At this point we hold neither mapping->tree_lock nor
- * lock on the page itself: the page may be truncated or
- * invalidated (changing page->mapping to NULL), or even
- * swizzled back from swapper_space to tmpfs file
- * mapping
- */
-
- lock_page(page);
-
- if (unlikely(page->mapping != mapping)) {
- unlock_page(page);
- continue;
- }
-
- if (!wbc->range_cyclic && page->index > end) {
- done = 1;
- unlock_page(page);
- continue;
- }
-
- if (wbc->sync_mode != WB_SYNC_NONE)
- wait_on_page_writeback(page);
-
- if (PageWriteback(page) ||
- !clear_page_dirty_for_io(page)) {
- unlock_page(page);
- continue;
- }
-
- if (writepage) {
- ret = (*writepage)(page, wbc);
- mapping_set_error(mapping, ret);
- } else {
- bio = __mpage_writepage(bio, page, get_block,
- &last_block_in_bio, &ret, wbc,
- page->mapping->a_ops->writepage);
- }
- if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE))
- unlock_page(page);
- if (ret || (--(wbc->nr_to_write) <= 0))
- done = 1;
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
- wbc->encountered_congestion = 1;
- done = 1;
- }
- }
- pagevec_release(&pvec);
- cond_resched();
- }
- if (!scanned && !done) {
- /*
- * We hit the last page and there is more work to be done: wrap
- * back to the start of the file
- */
- scanned = 1;
- index = 0;
- goto retry;
- }
- if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
- mapping->writeback_index = index;
- if (bio)
- mpage_bio_submit(WRITE, bio);
return ret;
}
EXPORT_SYMBOL(mpage_writepages);
@@ -804,15 +720,15 @@ EXPORT_SYMBOL(mpage_writepages);
int mpage_writepage(struct page *page, get_block_t get_block,
struct writeback_control *wbc)
{
- int ret = 0;
- struct bio *bio;
- sector_t last_block_in_bio = 0;
-
- bio = __mpage_writepage(NULL, page, get_block,
- &last_block_in_bio, &ret, wbc, NULL);
- if (bio)
- mpage_bio_submit(WRITE, bio);
-
+ struct mpage_data mpd = {
+ .bio = NULL,
+ .last_block_in_bio = 0,
+ .get_block = get_block,
+ .use_writepage = 0,
+ };
+ int ret = __mpage_writepage(page, wbc, &mpd);
+ if (mpd.bio)
+ mpage_bio_submit(WRITE, mpd.bio);
return ret;
}
EXPORT_SYMBOL(mpage_writepage);
diff --git a/fs/partitions/Kconfig b/fs/partitions/Kconfig
index 01207042048..7638a1c42a7 100644
--- a/fs/partitions/Kconfig
+++ b/fs/partitions/Kconfig
@@ -239,7 +239,7 @@ config EFI_PARTITION
config SYSV68_PARTITION
bool "SYSV68 partition table support" if PARTITION_ADVANCED
- default y if M68K
+ default y if VME
help
Say Y here if you would like to be able to read the hard disk
partition table format used by Motorola Delta machines (using
diff --git a/fs/partitions/efi.c b/fs/partitions/efi.c
index 1bea610078b..e7b07006bc4 100644
--- a/fs/partitions/efi.c
+++ b/fs/partitions/efi.c
@@ -152,7 +152,7 @@ last_lba(struct block_device *bdev)
}
static inline int
-pmbr_part_valid(struct partition *part, u64 lastlba)
+pmbr_part_valid(struct partition *part)
{
if (part->sys_ind == EFI_PMBR_OSTYPE_EFI_GPT &&
le32_to_cpu(part->start_sect) == 1UL)
@@ -163,7 +163,6 @@ pmbr_part_valid(struct partition *part, u64 lastlba)
/**
* is_pmbr_valid(): test Protective MBR for validity
* @mbr: pointer to a legacy mbr structure
- * @lastlba: last_lba for the whole device
*
* Description: Returns 1 if PMBR is valid, 0 otherwise.
* Validity depends on two things:
@@ -171,13 +170,13 @@ pmbr_part_valid(struct partition *part, u64 lastlba)
* 2) One partition of type 0xEE is found
*/
static int
-is_pmbr_valid(legacy_mbr *mbr, u64 lastlba)
+is_pmbr_valid(legacy_mbr *mbr)
{
int i;
if (!mbr || le16_to_cpu(mbr->signature) != MSDOS_MBR_SIGNATURE)
return 0;
for (i = 0; i < 4; i++)
- if (pmbr_part_valid(&mbr->partition_record[i], lastlba))
+ if (pmbr_part_valid(&mbr->partition_record[i]))
return 1;
return 0;
}
@@ -516,7 +515,7 @@ find_valid_gpt(struct block_device *bdev, gpt_header **gpt, gpt_entry **ptes)
int good_pgpt = 0, good_agpt = 0, good_pmbr = 0;
gpt_header *pgpt = NULL, *agpt = NULL;
gpt_entry *pptes = NULL, *aptes = NULL;
- legacy_mbr *legacymbr = NULL;
+ legacy_mbr *legacymbr;
u64 lastlba;
if (!bdev || !gpt || !ptes)
return 0;
@@ -528,9 +527,8 @@ find_valid_gpt(struct block_device *bdev, gpt_header **gpt, gpt_entry **ptes)
if (legacymbr) {
read_lba(bdev, 0, (u8 *) legacymbr,
sizeof (*legacymbr));
- good_pmbr = is_pmbr_valid(legacymbr, lastlba);
+ good_pmbr = is_pmbr_valid(legacymbr);
kfree(legacymbr);
- legacymbr=NULL;
}
if (!good_pmbr)
goto fail;
diff --git a/fs/signalfd.c b/fs/signalfd.c
new file mode 100644
index 00000000000..7cfeab412b4
--- /dev/null
+++ b/fs/signalfd.c
@@ -0,0 +1,349 @@
+/*
+ * fs/signalfd.c
+ *
+ * Copyright (C) 2003 Linus Torvalds
+ *
+ * Mon Mar 5, 2007: Davide Libenzi <davidel@xmailserver.org>
+ * Changed ->read() to return a siginfo strcture instead of signal number.
+ * Fixed locking in ->poll().
+ * Added sighand-detach notification.
+ * Added fd re-use in sys_signalfd() syscall.
+ * Now using anonymous inode source.
+ * Thanks to Oleg Nesterov for useful code review and suggestions.
+ * More comments and suggestions from Arnd Bergmann.
+ */
+
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/signal.h>
+#include <linux/list.h>
+#include <linux/anon_inodes.h>
+#include <linux/signalfd.h>
+
+struct signalfd_ctx {
+ struct list_head lnk;
+ wait_queue_head_t wqh;
+ sigset_t sigmask;
+ struct task_struct *tsk;
+};
+
+struct signalfd_lockctx {
+ struct task_struct *tsk;
+ unsigned long flags;
+};
+
+/*
+ * Tries to acquire the sighand lock. We do not increment the sighand
+ * use count, and we do not even pin the task struct, so we need to
+ * do it inside an RCU read lock, and we must be prepared for the
+ * ctx->tsk going to NULL (in signalfd_deliver()), and for the sighand
+ * being detached. We return 0 if the sighand has been detached, or
+ * 1 if we were able to pin the sighand lock.
+ */
+static int signalfd_lock(struct signalfd_ctx *ctx, struct signalfd_lockctx *lk)
+{
+ struct sighand_struct *sighand = NULL;
+
+ rcu_read_lock();
+ lk->tsk = rcu_dereference(ctx->tsk);
+ if (likely(lk->tsk != NULL))
+ sighand = lock_task_sighand(lk->tsk, &lk->flags);
+ rcu_read_unlock();
+
+ if (sighand && !ctx->tsk) {
+ unlock_task_sighand(lk->tsk, &lk->flags);
+ sighand = NULL;
+ }
+
+ return sighand != NULL;
+}
+
+static void signalfd_unlock(struct signalfd_lockctx *lk)
+{
+ unlock_task_sighand(lk->tsk, &lk->flags);
+}
+
+/*
+ * This must be called with the sighand lock held.
+ */
+void signalfd_deliver(struct task_struct *tsk, int sig)
+{
+ struct sighand_struct *sighand = tsk->sighand;
+ struct signalfd_ctx *ctx, *tmp;
+
+ BUG_ON(!sig);
+ list_for_each_entry_safe(ctx, tmp, &sighand->signalfd_list, lnk) {
+ /*
+ * We use a negative signal value as a way to broadcast that the
+ * sighand has been orphaned, so that we can notify all the
+ * listeners about this. Remember the ctx->sigmask is inverted,
+ * so if the user is interested in a signal, that corresponding
+ * bit will be zero.
+ */
+ if (sig < 0) {
+ if (ctx->tsk == tsk) {
+ ctx->tsk = NULL;
+ list_del_init(&ctx->lnk);
+ wake_up(&ctx->wqh);
+ }
+ } else {
+ if (!sigismember(&ctx->sigmask, sig))
+ wake_up(&ctx->wqh);
+ }
+ }
+}
+
+static void signalfd_cleanup(struct signalfd_ctx *ctx)
+{
+ struct signalfd_lockctx lk;
+
+ /*
+ * This is tricky. If the sighand is gone, we do not need to remove
+ * context from the list, the list itself won't be there anymore.
+ */
+ if (signalfd_lock(ctx, &lk)) {
+ list_del(&ctx->lnk);
+ signalfd_unlock(&lk);
+ }
+ kfree(ctx);
+}
+
+static int signalfd_release(struct inode *inode, struct file *file)
+{
+ signalfd_cleanup(file->private_data);
+ return 0;
+}
+
+static unsigned int signalfd_poll(struct file *file, poll_table *wait)
+{
+ struct signalfd_ctx *ctx = file->private_data;
+ unsigned int events = 0;
+ struct signalfd_lockctx lk;
+
+ poll_wait(file, &ctx->wqh, wait);
+
+ /*
+ * Let the caller get a POLLIN in this case, ala socket recv() when
+ * the peer disconnects.
+ */
+ if (signalfd_lock(ctx, &lk)) {
+ if (next_signal(&lk.tsk->pending, &ctx->sigmask) > 0 ||
+ next_signal(&lk.tsk->signal->shared_pending,
+ &ctx->sigmask) > 0)
+ events |= POLLIN;
+ signalfd_unlock(&lk);
+ } else
+ events |= POLLIN;
+
+ return events;
+}
+
+/*
+ * Copied from copy_siginfo_to_user() in kernel/signal.c
+ */
+static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo,
+ siginfo_t const *kinfo)
+{
+ long err;
+
+ BUILD_BUG_ON(sizeof(struct signalfd_siginfo) != 128);
+
+ /*
+ * Unused memebers should be zero ...
+ */
+ err = __clear_user(uinfo, sizeof(*uinfo));
+
+ /*
+ * If you change siginfo_t structure, please be sure
+ * this code is fixed accordingly.
+ */
+ err |= __put_user(kinfo->si_signo, &uinfo->signo);
+ err |= __put_user(kinfo->si_errno, &uinfo->err);
+ err |= __put_user((short)kinfo->si_code, &uinfo->code);
+ switch (kinfo->si_code & __SI_MASK) {
+ case __SI_KILL:
+ err |= __put_user(kinfo->si_pid, &uinfo->pid);
+ err |= __put_user(kinfo->si_uid, &uinfo->uid);
+ break;
+ case __SI_TIMER:
+ err |= __put_user(kinfo->si_tid, &uinfo->tid);
+ err |= __put_user(kinfo->si_overrun, &uinfo->overrun);
+ err |= __put_user((long)kinfo->si_ptr, &uinfo->svptr);
+ break;
+ case __SI_POLL:
+ err |= __put_user(kinfo->si_band, &uinfo->band);
+ err |= __put_user(kinfo->si_fd, &uinfo->fd);
+ break;
+ case __SI_FAULT:
+ err |= __put_user((long)kinfo->si_addr, &uinfo->addr);
+#ifdef __ARCH_SI_TRAPNO
+ err |= __put_user(kinfo->si_trapno, &uinfo->trapno);
+#endif
+ break;
+ case __SI_CHLD:
+ err |= __put_user(kinfo->si_pid, &uinfo->pid);
+ err |= __put_user(kinfo->si_uid, &uinfo->uid);
+ err |= __put_user(kinfo->si_status, &uinfo->status);
+ err |= __put_user(kinfo->si_utime, &uinfo->utime);
+ err |= __put_user(kinfo->si_stime, &uinfo->stime);
+ break;
+ case __SI_RT: /* This is not generated by the kernel as of now. */
+ case __SI_MESGQ: /* But this is */
+ err |= __put_user(kinfo->si_pid, &uinfo->pid);
+ err |= __put_user(kinfo->si_uid, &uinfo->uid);
+ err |= __put_user((long)kinfo->si_ptr, &uinfo->svptr);
+ break;
+ default: /* this is just in case for now ... */
+ err |= __put_user(kinfo->si_pid, &uinfo->pid);
+ err |= __put_user(kinfo->si_uid, &uinfo->uid);
+ break;
+ }
+
+ return err ? -EFAULT: sizeof(*uinfo);
+}
+
+/*
+ * Returns either the size of a "struct signalfd_siginfo", or zero if the
+ * sighand we are attached to, has been orphaned. The "count" parameter
+ * must be at least the size of a "struct signalfd_siginfo".
+ */
+static ssize_t signalfd_read(struct file *file, char __user *buf, size_t count,
+ loff_t *ppos)
+{
+ struct signalfd_ctx *ctx = file->private_data;
+ ssize_t res = 0;
+ int locked, signo;
+ siginfo_t info;
+ struct signalfd_lockctx lk;
+ DECLARE_WAITQUEUE(wait, current);
+
+ if (count < sizeof(struct signalfd_siginfo))
+ return -EINVAL;
+ locked = signalfd_lock(ctx, &lk);
+ if (!locked)
+ return 0;
+ res = -EAGAIN;
+ signo = dequeue_signal(lk.tsk, &ctx->sigmask, &info);
+ if (signo == 0 && !(file->f_flags & O_NONBLOCK)) {
+ add_wait_queue(&ctx->wqh, &wait);
+ for (;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ signo = dequeue_signal(lk.tsk, &ctx->sigmask, &info);
+ if (signo != 0)
+ break;
+ if (signal_pending(current)) {
+ res = -ERESTARTSYS;
+ break;
+ }
+ signalfd_unlock(&lk);
+ schedule();
+ locked = signalfd_lock(ctx, &lk);
+ if (unlikely(!locked)) {
+ /*
+ * Let the caller read zero byte, ala socket
+ * recv() when the peer disconnect. This test
+ * must be done before doing a dequeue_signal(),
+ * because if the sighand has been orphaned,
+ * the dequeue_signal() call is going to crash.
+ */
+ res = 0;
+ break;
+ }
+ }
+ remove_wait_queue(&ctx->wqh, &wait);
+ __set_current_state(TASK_RUNNING);
+ }
+ if (likely(locked))
+ signalfd_unlock(&lk);
+ if (likely(signo))
+ res = signalfd_copyinfo((struct signalfd_siginfo __user *) buf,
+ &info);
+
+ return res;
+}
+
+static const struct file_operations signalfd_fops = {
+ .release = signalfd_release,
+ .poll = signalfd_poll,
+ .read = signalfd_read,
+};
+
+/*
+ * Create a file descriptor that is associated with our signal
+ * state. We can pass it around to others if we want to, but
+ * it will always be _our_ signal state.
+ */
+asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask)
+{
+ int error;
+ sigset_t sigmask;
+ struct signalfd_ctx *ctx;
+ struct sighand_struct *sighand;
+ struct file *file;
+ struct inode *inode;
+ struct signalfd_lockctx lk;
+
+ if (sizemask != sizeof(sigset_t) ||
+ copy_from_user(&sigmask, user_mask, sizeof(sigmask)))
+ return error = -EINVAL;
+ sigdelsetmask(&sigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
+ signotset(&sigmask);
+
+ if (ufd == -1) {
+ ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ init_waitqueue_head(&ctx->wqh);
+ ctx->sigmask = sigmask;
+ ctx->tsk = current;
+
+ sighand = current->sighand;
+ /*
+ * Add this fd to the list of signal listeners.
+ */
+ spin_lock_irq(&sighand->siglock);
+ list_add_tail(&ctx->lnk, &sighand->signalfd_list);
+ spin_unlock_irq(&sighand->siglock);
+
+ /*
+ * When we call this, the initialization must be complete, since
+ * anon_inode_getfd() will install the fd.
+ */
+ error = anon_inode_getfd(&ufd, &inode, &file, "[signalfd]",
+ &signalfd_fops, ctx);
+ if (error)
+ goto err_fdalloc;
+ } else {
+ file = fget(ufd);
+ if (!file)
+ return -EBADF;
+ ctx = file->private_data;
+ if (file->f_op != &signalfd_fops) {
+ fput(file);
+ return -EINVAL;
+ }
+ /*
+ * We need to be prepared of the fact that the sighand this fd
+ * is attached to, has been detched. In that case signalfd_lock()
+ * will return 0, and we'll just skip setting the new mask.
+ */
+ if (signalfd_lock(ctx, &lk)) {
+ ctx->sigmask = sigmask;
+ signalfd_unlock(&lk);
+ }
+ wake_up(&ctx->wqh);
+ fput(file);
+ }
+
+ return ufd;
+
+err_fdalloc:
+ signalfd_cleanup(ctx);
+ return error;
+}
+
diff --git a/fs/timerfd.c b/fs/timerfd.c
new file mode 100644
index 00000000000..e329e37f15a
--- /dev/null
+++ b/fs/timerfd.c
@@ -0,0 +1,227 @@
+/*
+ * fs/timerfd.c
+ *
+ * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
+ *
+ *
+ * Thanks to Thomas Gleixner for code reviews and useful comments.
+ *
+ */
+
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/time.h>
+#include <linux/hrtimer.h>
+#include <linux/anon_inodes.h>
+#include <linux/timerfd.h>
+
+struct timerfd_ctx {
+ struct hrtimer tmr;
+ ktime_t tintv;
+ spinlock_t lock;
+ wait_queue_head_t wqh;
+ int expired;
+};
+
+/*
+ * This gets called when the timer event triggers. We set the "expired"
+ * flag, but we do not re-arm the timer (in case it's necessary,
+ * tintv.tv64 != 0) until the timer is read.
+ */
+static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr)
+{
+ struct timerfd_ctx *ctx = container_of(htmr, struct timerfd_ctx, tmr);
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->lock, flags);
+ ctx->expired = 1;
+ wake_up_locked(&ctx->wqh);
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ return HRTIMER_NORESTART;
+}
+
+static void timerfd_setup(struct timerfd_ctx *ctx, int clockid, int flags,
+ const struct itimerspec *ktmr)
+{
+ enum hrtimer_mode htmode;
+ ktime_t texp;
+
+ htmode = (flags & TFD_TIMER_ABSTIME) ?
+ HRTIMER_MODE_ABS: HRTIMER_MODE_REL;
+
+ texp = timespec_to_ktime(ktmr->it_value);
+ ctx->expired = 0;
+ ctx->tintv = timespec_to_ktime(ktmr->it_interval);
+ hrtimer_init(&ctx->tmr, clockid, htmode);
+ ctx->tmr.expires = texp;
+ ctx->tmr.function = timerfd_tmrproc;
+ if (texp.tv64 != 0)
+ hrtimer_start(&ctx->tmr, texp, htmode);
+}
+
+static int timerfd_release(struct inode *inode, struct file *file)
+{
+ struct timerfd_ctx *ctx = file->private_data;
+
+ hrtimer_cancel(&ctx->tmr);
+ kfree(ctx);
+ return 0;
+}
+
+static unsigned int timerfd_poll(struct file *file, poll_table *wait)
+{
+ struct timerfd_ctx *ctx = file->private_data;
+ unsigned int events = 0;
+ unsigned long flags;
+
+ poll_wait(file, &ctx->wqh, wait);
+
+ spin_lock_irqsave(&ctx->lock, flags);
+ if (ctx->expired)
+ events |= POLLIN;
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ return events;
+}
+
+static ssize_t timerfd_read(struct file *file, char __user *buf, size_t count,
+ loff_t *ppos)
+{
+ struct timerfd_ctx *ctx = file->private_data;
+ ssize_t res;
+ u32 ticks = 0;
+ DECLARE_WAITQUEUE(wait, current);
+
+ if (count < sizeof(ticks))
+ return -EINVAL;
+ spin_lock_irq(&ctx->lock);
+ res = -EAGAIN;
+ if (!ctx->expired && !(file->f_flags & O_NONBLOCK)) {
+ __add_wait_queue(&ctx->wqh, &wait);
+ for (res = 0;;) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (ctx->expired) {
+ res = 0;
+ break;
+ }
+ if (signal_pending(current)) {
+ res = -ERESTARTSYS;
+ break;
+ }
+ spin_unlock_irq(&ctx->lock);
+ schedule();
+ spin_lock_irq(&ctx->lock);
+ }
+ __remove_wait_queue(&ctx->wqh, &wait);
+ __set_current_state(TASK_RUNNING);
+ }
+ if (ctx->expired) {
+ ctx->expired = 0;
+ if (ctx->tintv.tv64 != 0) {
+ /*
+ * If tintv.tv64 != 0, this is a periodic timer that
+ * needs to be re-armed. We avoid doing it in the timer
+ * callback to avoid DoS attacks specifying a very
+ * short timer period.
+ */
+ ticks = (u32)
+ hrtimer_forward(&ctx->tmr,
+ hrtimer_cb_get_time(&ctx->tmr),
+ ctx->tintv);
+ hrtimer_restart(&ctx->tmr);
+ } else
+ ticks = 1;
+ }
+ spin_unlock_irq(&ctx->lock);
+ if (ticks)
+ res = put_user(ticks, buf) ? -EFAULT: sizeof(ticks);
+ return res;
+}
+
+static const struct file_operations timerfd_fops = {
+ .release = timerfd_release,
+ .poll = timerfd_poll,
+ .read = timerfd_read,
+};
+
+asmlinkage long sys_timerfd(int ufd, int clockid, int flags,
+ const struct itimerspec __user *utmr)
+{
+ int error;
+ struct timerfd_ctx *ctx;
+ struct file *file;
+ struct inode *inode;
+ struct itimerspec ktmr;
+
+ if (copy_from_user(&ktmr, utmr, sizeof(ktmr)))
+ return -EFAULT;
+
+ if (clockid != CLOCK_MONOTONIC &&
+ clockid != CLOCK_REALTIME)
+ return -EINVAL;
+ if (!timespec_valid(&ktmr.it_value) ||
+ !timespec_valid(&ktmr.it_interval))
+ return -EINVAL;
+
+ if (ufd == -1) {
+ ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ init_waitqueue_head(&ctx->wqh);
+ spin_lock_init(&ctx->lock);
+
+ timerfd_setup(ctx, clockid, flags, &ktmr);
+
+ /*
+ * When we call this, the initialization must be complete, since
+ * anon_inode_getfd() will install the fd.
+ */
+ error = anon_inode_getfd(&ufd, &inode, &file, "[timerfd]",
+ &timerfd_fops, ctx);
+ if (error)
+ goto err_tmrcancel;
+ } else {
+ file = fget(ufd);
+ if (!file)
+ return -EBADF;
+ ctx = file->private_data;
+ if (file->f_op != &timerfd_fops) {
+ fput(file);
+ return -EINVAL;
+ }
+ /*
+ * We need to stop the existing timer before reprogramming
+ * it to the new values.
+ */
+ for (;;) {
+ spin_lock_irq(&ctx->lock);
+ if (hrtimer_try_to_cancel(&ctx->tmr) >= 0)
+ break;
+ spin_unlock_irq(&ctx->lock);
+ cpu_relax();
+ }
+ /*
+ * Re-program the timer to the new value ...
+ */
+ timerfd_setup(ctx, clockid, flags, &ktmr);
+
+ spin_unlock_irq(&ctx->lock);
+ fput(file);
+ }
+
+ return ufd;
+
+err_tmrcancel:
+ hrtimer_cancel(&ctx->tmr);
+ kfree(ctx);
+ return error;
+}
+
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-25 07:18:35 +0000