summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/filesystems/9p.txt3
-rw-r--r--Makefile2
-rw-r--r--drivers/video/xen-fbfront.c8
-rw-r--r--fs/9p/v9fs.c21
-rw-r--r--fs/9p/v9fs.h1
-rw-r--r--fs/9p/vfs_inode.c126
-rw-r--r--fs/9p/vfs_super.c39
-rw-r--r--fs/afs/file.c18
-rw-r--r--fs/dcache.c1
-rw-r--r--fs/locks.c2
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c33
-rw-r--r--fs/notify/inotify/inotify_user.c229
-rw-r--r--include/linux/hardirq.h6
-rw-r--r--include/linux/kernel.h5
-rw-r--r--include/linux/sched.h51
-rw-r--r--include/trace/events/sched.h95
-rw-r--r--kernel/module.c9
-rw-r--r--kernel/sched.c823
-rw-r--r--kernel/sched_cpupri.c30
-rw-r--r--kernel/sched_debug.c4
-rw-r--r--kernel/sched_fair.c47
-rw-r--r--kernel/sched_rt.c56
-rw-r--r--lib/lmb.c2
-rw-r--r--net/9p/client.c21
-rw-r--r--net/9p/error.c2
-rw-r--r--net/9p/trans_fd.c8
-rw-r--r--net/9p/trans_rdma.c9
-rw-r--r--net/9p/trans_virtio.c11
-rw-r--r--net/ipv4/ip_output.c2
29 files changed, 1039 insertions, 625 deletions
diff --git a/Documentation/filesystems/9p.txt b/Documentation/filesystems/9p.txt
index bf8080640eb..6208f55c44c 100644
--- a/Documentation/filesystems/9p.txt
+++ b/Documentation/filesystems/9p.txt
@@ -123,6 +123,9 @@ available from the same CVS repository.
There are user and developer mailing lists available through the v9fs project
on sourceforge (http://sourceforge.net/projects/v9fs).
+A stand-alone version of the module (which should build for any 2.6 kernel)
+is available via (http://github.com/ericvh/9p-sac/tree/master)
+
News and other information is maintained on SWiK (http://swik.net/v9fs).
Bug reports may be issued through the kernel.org bugzilla
diff --git a/Makefile b/Makefile
index 9c87e60d169..25c615e5730 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 31
-EXTRAVERSION = -rc7
+EXTRAVERSION = -rc8
NAME = Man-Eating Seals of Antiquity
# *DOCUMENTATION*
diff --git a/drivers/video/xen-fbfront.c b/drivers/video/xen-fbfront.c
index 15502d5e364..54cd9161017 100644
--- a/drivers/video/xen-fbfront.c
+++ b/drivers/video/xen-fbfront.c
@@ -454,6 +454,10 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
xenfb_init_shared_page(info, fb_info);
+ ret = xenfb_connect_backend(dev, info);
+ if (ret < 0)
+ goto error;
+
ret = register_framebuffer(fb_info);
if (ret) {
fb_deferred_io_cleanup(fb_info);
@@ -464,10 +468,6 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
}
info->fb_info = fb_info;
- ret = xenfb_connect_backend(dev, info);
- if (ret < 0)
- goto error;
-
xenfb_make_preferred_console();
return 0;
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 332b5ff02fe..f7003cfac63 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -76,7 +76,7 @@ static const match_table_t tokens = {
* Return 0 upon success, -ERRNO upon failure.
*/
-static int v9fs_parse_options(struct v9fs_session_info *v9ses)
+static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
{
char *options;
substring_t args[MAX_OPT_ARGS];
@@ -90,10 +90,10 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses)
v9ses->debug = 0;
v9ses->cache = 0;
- if (!v9ses->options)
+ if (!opts)
return 0;
- options = kstrdup(v9ses->options, GFP_KERNEL);
+ options = kstrdup(opts, GFP_KERNEL);
if (!options) {
P9_DPRINTK(P9_DEBUG_ERROR,
"failed to allocate copy of option string\n");
@@ -206,24 +206,14 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
v9ses->uid = ~0;
v9ses->dfltuid = V9FS_DEFUID;
v9ses->dfltgid = V9FS_DEFGID;
- if (data) {
- v9ses->options = kstrdup(data, GFP_KERNEL);
- if (!v9ses->options) {
- P9_DPRINTK(P9_DEBUG_ERROR,
- "failed to allocate copy of option string\n");
- retval = -ENOMEM;
- goto error;
- }
- }
- rc = v9fs_parse_options(v9ses);
+ rc = v9fs_parse_options(v9ses, data);
if (rc < 0) {
retval = rc;
goto error;
}
- v9ses->clnt = p9_client_create(dev_name, v9ses->options);
-
+ v9ses->clnt = p9_client_create(dev_name, data);
if (IS_ERR(v9ses->clnt)) {
retval = PTR_ERR(v9ses->clnt);
v9ses->clnt = NULL;
@@ -280,7 +270,6 @@ void v9fs_session_close(struct v9fs_session_info *v9ses)
__putname(v9ses->uname);
__putname(v9ses->aname);
- kfree(v9ses->options);
}
/**
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index a7d56719299..38762bf102a 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -85,7 +85,6 @@ struct v9fs_session_info {
unsigned int afid;
unsigned int cache;
- char *options; /* copy of mount options */
char *uname; /* user name to mount as */
char *aname; /* name of remote hierarchy being mounted */
unsigned int maxdata; /* max data for client interface */
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 81f8bbf12f9..06a223d50a8 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -171,7 +171,6 @@ int v9fs_uflags2omode(int uflags, int extended)
/**
* v9fs_blank_wstat - helper function to setup a 9P stat structure
- * @v9ses: 9P session info (for determining extended mode)
* @wstat: structure to initialize
*
*/
@@ -207,65 +206,72 @@ v9fs_blank_wstat(struct p9_wstat *wstat)
struct inode *v9fs_get_inode(struct super_block *sb, int mode)
{
+ int err;
struct inode *inode;
struct v9fs_session_info *v9ses = sb->s_fs_info;
P9_DPRINTK(P9_DEBUG_VFS, "super block: %p mode: %o\n", sb, mode);
inode = new_inode(sb);
- if (inode) {
- inode->i_mode = mode;
- inode->i_uid = current_fsuid();
- inode->i_gid = current_fsgid();
- inode->i_blocks = 0;
- inode->i_rdev = 0;
- inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- inode->i_mapping->a_ops = &v9fs_addr_operations;
-
- switch (mode & S_IFMT) {
- case S_IFIFO:
- case S_IFBLK:
- case S_IFCHR:
- case S_IFSOCK:
- if (!v9fs_extended(v9ses)) {
- P9_DPRINTK(P9_DEBUG_ERROR,
- "special files without extended mode\n");
- return ERR_PTR(-EINVAL);
- }
- init_special_inode(inode, inode->i_mode,
- inode->i_rdev);
- break;
- case S_IFREG:
- inode->i_op = &v9fs_file_inode_operations;
- inode->i_fop = &v9fs_file_operations;
- break;
- case S_IFLNK:
- if (!v9fs_extended(v9ses)) {
- P9_DPRINTK(P9_DEBUG_ERROR,
- "extended modes used w/o 9P2000.u\n");
- return ERR_PTR(-EINVAL);
- }
- inode->i_op = &v9fs_symlink_inode_operations;
- break;
- case S_IFDIR:
- inc_nlink(inode);
- if (v9fs_extended(v9ses))
- inode->i_op = &v9fs_dir_inode_operations_ext;
- else
- inode->i_op = &v9fs_dir_inode_operations;
- inode->i_fop = &v9fs_dir_operations;
- break;
- default:
- P9_DPRINTK(P9_DEBUG_ERROR,
- "BAD mode 0x%x S_IFMT 0x%x\n",
- mode, mode & S_IFMT);
- return ERR_PTR(-EINVAL);
- }
- } else {
+ if (!inode) {
P9_EPRINTK(KERN_WARNING, "Problem allocating inode\n");
return ERR_PTR(-ENOMEM);
}
+
+ inode->i_mode = mode;
+ inode->i_uid = current_fsuid();
+ inode->i_gid = current_fsgid();
+ inode->i_blocks = 0;
+ inode->i_rdev = 0;
+ inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ inode->i_mapping->a_ops = &v9fs_addr_operations;
+
+ switch (mode & S_IFMT) {
+ case S_IFIFO:
+ case S_IFBLK:
+ case S_IFCHR:
+ case S_IFSOCK:
+ if (!v9fs_extended(v9ses)) {
+ P9_DPRINTK(P9_DEBUG_ERROR,
+ "special files without extended mode\n");
+ err = -EINVAL;
+ goto error;
+ }
+ init_special_inode(inode, inode->i_mode, inode->i_rdev);
+ break;
+ case S_IFREG:
+ inode->i_op = &v9fs_file_inode_operations;
+ inode->i_fop = &v9fs_file_operations;
+ break;
+ case S_IFLNK:
+ if (!v9fs_extended(v9ses)) {
+ P9_DPRINTK(P9_DEBUG_ERROR,
+ "extended modes used w/o 9P2000.u\n");
+ err = -EINVAL;
+ goto error;
+ }
+ inode->i_op = &v9fs_symlink_inode_operations;
+ break;
+ case S_IFDIR:
+ inc_nlink(inode);
+ if (v9fs_extended(v9ses))
+ inode->i_op = &v9fs_dir_inode_operations_ext;
+ else
+ inode->i_op = &v9fs_dir_inode_operations;
+ inode->i_fop = &v9fs_dir_operations;
+ break;
+ default:
+ P9_DPRINTK(P9_DEBUG_ERROR, "BAD mode 0x%x S_IFMT 0x%x\n",
+ mode, mode & S_IFMT);
+ err = -EINVAL;
+ goto error;
+ }
+
return inode;
+
+error:
+ iput(inode);
+ return ERR_PTR(err);
}
/*
@@ -338,30 +344,25 @@ v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
ret = NULL;
st = p9_client_stat(fid);
- if (IS_ERR(st)) {
- err = PTR_ERR(st);
- st = NULL;
- goto error;
- }
+ if (IS_ERR(st))
+ return ERR_CAST(st);
umode = p9mode2unixmode(v9ses, st->mode);
ret = v9fs_get_inode(sb, umode);
if (IS_ERR(ret)) {
err = PTR_ERR(ret);
- ret = NULL;
goto error;
}
v9fs_stat2inode(st, ret, sb);
ret->i_ino = v9fs_qid2ino(&st->qid);
+ p9stat_free(st);
kfree(st);
return ret;
error:
+ p9stat_free(st);
kfree(st);
- if (ret)
- iput(ret);
-
return ERR_PTR(err);
}
@@ -403,9 +404,9 @@ v9fs_open_created(struct inode *inode, struct file *file)
* @v9ses: session information
* @dir: directory that dentry is being created in
* @dentry: dentry that is being created
+ * @extension: 9p2000.u extension string to support devices, etc.
* @perm: create permissions
* @mode: open mode
- * @extension: 9p2000.u extension string to support devices, etc.
*
*/
static struct p9_fid *
@@ -470,7 +471,10 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
dentry->d_op = &v9fs_dentry_operations;
d_instantiate(dentry, inode);
- v9fs_fid_add(dentry, fid);
+ err = v9fs_fid_add(dentry, fid);
+ if (err < 0)
+ goto error;
+
return ofid;
error:
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 38d695d66a0..8961f1a8f66 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -81,7 +81,7 @@ static int v9fs_set_super(struct super_block *s, void *data)
static void
v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
- int flags)
+ int flags, void *data)
{
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_blocksize_bits = fls(v9ses->maxdata - 1);
@@ -91,6 +91,8 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
sb->s_flags = flags | MS_ACTIVE | MS_SYNCHRONOUS | MS_DIRSYNC |
MS_NOATIME;
+
+ save_mount_options(sb, data);
}
/**
@@ -113,14 +115,11 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
struct v9fs_session_info *v9ses = NULL;
struct p9_wstat *st = NULL;
int mode = S_IRWXUGO | S_ISVTX;
- uid_t uid = current_fsuid();
- gid_t gid = current_fsgid();
struct p9_fid *fid;
int retval = 0;
P9_DPRINTK(P9_DEBUG_VFS, " \n");
- st = NULL;
v9ses = kzalloc(sizeof(struct v9fs_session_info), GFP_KERNEL);
if (!v9ses)
return -ENOMEM;
@@ -142,7 +141,7 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
retval = PTR_ERR(sb);
goto free_stat;
}
- v9fs_fill_super(sb, v9ses, flags);
+ v9fs_fill_super(sb, v9ses, flags, data);
inode = v9fs_get_inode(sb, S_IFDIR | mode);
if (IS_ERR(inode)) {
@@ -150,9 +149,6 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
goto release_sb;
}
- inode->i_uid = uid;
- inode->i_gid = gid;
-
root = d_alloc_root(inode);
if (!root) {
iput(inode);
@@ -173,10 +169,8 @@ P9_DPRINTK(P9_DEBUG_VFS, " simple set mount, return 0\n");
simple_set_mnt(mnt, sb);
return 0;
-release_sb:
- deactivate_locked_super(sb);
-
free_stat:
+ p9stat_free(st);
kfree(st);
clunk_fid:
@@ -185,7 +179,12 @@ clunk_fid:
close_session:
v9fs_session_close(v9ses);
kfree(v9ses);
+ return retval;
+release_sb:
+ p9stat_free(st);
+ kfree(st);
+ deactivate_locked_super(sb);
return retval;
}
@@ -207,24 +206,10 @@ static void v9fs_kill_super(struct super_block *s)
v9fs_session_close(v9ses);
kfree(v9ses);
+ s->s_fs_info = NULL;
P9_DPRINTK(P9_DEBUG_VFS, "exiting kill_super\n");
}
-/**
- * v9fs_show_options - Show mount options in /proc/mounts
- * @m: seq_file to write to
- * @mnt: mount descriptor
- *
- */
-
-static int v9fs_show_options(struct seq_file *m, struct vfsmount *mnt)
-{
- struct v9fs_session_info *v9ses = mnt->mnt_sb->s_fs_info;
-
- seq_printf(m, "%s", v9ses->options);
- return 0;
-}
-
static void
v9fs_umount_begin(struct super_block *sb)
{
@@ -237,7 +222,7 @@ v9fs_umount_begin(struct super_block *sb)
static const struct super_operations v9fs_super_ops = {
.statfs = simple_statfs,
.clear_inode = v9fs_clear_inode,
- .show_options = v9fs_show_options,
+ .show_options = generic_show_options,
.umount_begin = v9fs_umount_begin,
};
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 0149dab365e..681c2a7b013 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -134,9 +134,16 @@ static int afs_readpage(struct file *file, struct page *page)
inode = page->mapping->host;
- ASSERT(file != NULL);
- key = file->private_data;
- ASSERT(key != NULL);
+ if (file) {
+ key = file->private_data;
+ ASSERT(key != NULL);
+ } else {
+ key = afs_request_key(AFS_FS_S(inode->i_sb)->volume->cell);
+ if (IS_ERR(key)) {
+ ret = PTR_ERR(key);
+ goto error_nokey;
+ }
+ }
_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);
@@ -207,12 +214,17 @@ static int afs_readpage(struct file *file, struct page *page)
unlock_page(page);
}
+ if (!file)
+ key_put(key);
_leave(" = 0");
return 0;
error:
SetPageError(page);
unlock_page(page);
+ if (!file)
+ key_put(key);
+error_nokey:
_leave(" = %d", ret);
return ret;
}
diff --git a/fs/dcache.c b/fs/dcache.c
index 9e5cd3c3a6b..a100fa35a48 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -32,6 +32,7 @@
#include <linux/swap.h>
#include <linux/bootmem.h>
#include <linux/fs_struct.h>
+#include <linux/hardirq.h>
#include "internal.h"
int sysctl_vfs_cache_pressure __read_mostly = 100;
diff --git a/fs/locks.c b/fs/locks.c
index b6440f52178..2eb81975c99 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -768,7 +768,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request)
* give it the opportunity to lock the file.
*/
if (found)
- cond_resched_bkl();
+ cond_resched();
find_conflict:
for_each_lock(inode, before) {
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 5dcbafe72d7..c9ee67b442e 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -105,16 +105,45 @@ static bool inotify_should_send_event(struct fsnotify_group *group, struct inode
return send;
}
+/*
+ * This is NEVER supposed to be called. Inotify marks should either have been
+ * removed from the idr when the watch was removed or in the
+ * fsnotify_destroy_mark_by_group() call when the inotify instance was being
+ * torn down. This is only called if the idr is about to be freed but there
+ * are still marks in it.
+ */
static int idr_callback(int id, void *p, void *data)
{
- BUG();
+ struct fsnotify_mark_entry *entry;
+ struct inotify_inode_mark_entry *ientry;
+ static bool warned = false;
+
+ if (warned)
+ return 0;
+
+ warned = false;
+ entry = p;
+ ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
+
+ WARN(1, "inotify closing but id=%d for entry=%p in group=%p still in "
+ "idr. Probably leaking memory\n", id, p, data);
+
+ /*
+ * I'm taking the liberty of assuming that the mark in question is a
+ * valid address and I'm dereferencing it. This might help to figure
+ * out why we got here and the panic is no worse than the original
+ * BUG() that was here.
+ */
+ if (entry)
+ printk(KERN_WARNING "entry->group=%p inode=%p wd=%d\n",
+ entry->group, entry->inode, ientry->wd);
return 0;
}
static void inotify_free_group_priv(struct fsnotify_group *group)
{
/* ideally the idr is empty and we won't hit the BUG in teh callback */
- idr_for_each(&group->inotify_data.idr, idr_callback, NULL);
+ idr_for_each(&group->inotify_data.idr, idr_callback, group);
idr_remove_all(&group->inotify_data.idr);
idr_destroy(&group->inotify_data.idr);
}
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index dc32ed8323b..0e781bc88d1 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -47,9 +47,6 @@
static struct vfsmount *inotify_mnt __read_mostly;
-/* this just sits here and wastes global memory. used to just pad userspace messages with zeros */
-static struct inotify_event nul_inotify_event;
-
/* these are configurable via /proc/sys/fs/inotify/ */
static int inotify_max_user_instances __read_mostly;
static int inotify_max_queued_events __read_mostly;
@@ -199,8 +196,10 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
inotify_free_event_priv(fsn_priv);
}
- /* round up event->name_len so it is a multiple of event_size */
- name_len = roundup(event->name_len, event_size);
+ /* round up event->name_len so it is a multiple of event_size
+ * plus an extra byte for the terminating '\0'.
+ */
+ name_len = roundup(event->name_len + 1, event_size);
inotify_event.len = name_len;
inotify_event.mask = inotify_mask_to_arg(event->mask);
@@ -224,8 +223,8 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
return -EFAULT;
buf += event->name_len;
- /* fill userspace with 0's from nul_inotify_event */
- if (copy_to_user(buf, &nul_inotify_event, len_to_zero))
+ /* fill userspace with 0's */
+ if (clear_user(buf, len_to_zero))
return -EFAULT;
buf += len_to_zero;
event_size += name_len;
@@ -364,20 +363,53 @@ static int inotify_find_inode(const char __user *dirname, struct path *path, uns
return error;
}
+/*
+ * Remove the mark from the idr (if present) and drop the reference
+ * on the mark because it was in the idr.
+ */
static void inotify_remove_from_idr(struct fsnotify_group *group,
struct inotify_inode_mark_entry *ientry)
{
struct idr *idr;
+ struct fsnotify_mark_entry *entry;
+ struct inotify_inode_mark_entry *found_ientry;
+ int wd;
spin_lock(&group->inotify_data.idr_lock);
idr = &group->inotify_data.idr;
- idr_remove(idr, ientry->wd);
- spin_unlock(&group->inotify_data.idr_lock);
+ wd = ientry->wd;
+
+ if (wd == -1)
+ goto out;
+
+ entry = idr_find(&group->inotify_data.idr, wd);
+ if (unlikely(!entry))
+ goto out;
+
+ found_ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
+ if (unlikely(found_ientry != ientry)) {
+ /* We found an entry in the idr with the right wd, but it's
+ * not the entry we were told to remove. eparis seriously
+ * fucked up somewhere. */
+ WARN_ON(1);
+ ientry->wd = -1;
+ goto out;
+ }
+
+ /* One ref for being in the idr, one ref held by the caller */
+ BUG_ON(atomic_read(&entry->refcnt) < 2);
+
+ idr_remove(idr, wd);
ientry->wd = -1;
+
+ /* removed from the idr, drop that ref */
+ fsnotify_put_mark(entry);
+out:
+ spin_unlock(&group->inotify_data.idr_lock);
}
+
/*
- * Send IN_IGNORED for this wd, remove this wd from the idr, and drop the
- * internal reference help on the mark because it is in the idr.
+ * Send IN_IGNORED for this wd, remove this wd from the idr.
*/
void inotify_ignored_and_remove_idr(struct fsnotify_mark_entry *entry,
struct fsnotify_group *group)
@@ -417,9 +449,6 @@ skip_send_ignore:
/* remove this entry from the idr */
inotify_remove_from_idr(group, ientry);
- /* removed from idr, drop that reference */
- fsnotify_put_mark(entry);
-
atomic_dec(&group->inotify_data.user->inotify_watches);
}
@@ -431,80 +460,29 @@ static void inotify_free_mark(struct fsnotify_mark_entry *entry)
kmem_cache_free(inotify_inode_mark_cachep, ientry);
}
-static int inotify_update_watch(struct fsnotify_group *group, struct inode *inode, u32 arg)
+static int inotify_update_existing_watch(struct fsnotify_group *group,
+ struct inode *inode,
+ u32 arg)
{
- struct fsnotify_mark_entry *entry = NULL;
+ struct fsnotify_mark_entry *entry;
struct inotify_inode_mark_entry *ientry;
- struct inotify_inode_mark_entry *tmp_ientry;
- int ret = 0;
- int add = (arg & IN_MASK_ADD);
- __u32 mask;
__u32 old_mask, new_mask;
+ __u32 mask;
+ int add = (arg & IN_MASK_ADD);
+ int ret;
/* don't allow invalid bits: we don't want flags set */
mask = inotify_arg_to_mask(arg);
if (unlikely(!mask))
return -EINVAL;
- tmp_ientry = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
- if (unlikely(!tmp_ientry))
- return -ENOMEM;
- /* we set the mask at the end after attaching it */
- fsnotify_init_mark(&tmp_ientry->fsn_entry, inotify_free_mark);
- tmp_ientry->wd = -1;
-
-find_entry:
spin_lock(&inode->i_lock);
entry = fsnotify_find_mark_entry(group, inode);
spin_unlock(&inode->i_lock);
- if (entry) {
- ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
- } else {
- ret = -ENOSPC;
- if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches)
- goto out_err;
-retry:
- ret = -ENOMEM;
- if (unlikely(!idr_pre_get(&group->inotify_data.idr, GFP_KERNEL)))
- goto out_err;
-
- spin_lock(&group->inotify_data.idr_lock);
- ret = idr_get_new_above(&group->inotify_data.idr, &tmp_ientry->fsn_entry,
- group->inotify_data.last_wd,
- &tmp_ientry->wd);
- spin_unlock(&group->inotify_data.idr_lock);
- if (ret) {
- if (ret == -EAGAIN)
- goto retry;
- goto out_err;
- }
-
- ret = fsnotify_add_mark(&tmp_ientry->fsn_entry, group, inode);
- if (ret) {
- inotify_remove_from_idr(group, tmp_ientry);
- if (ret == -EEXIST)
- goto find_entry;
- goto out_err;
- }
-
- /* tmp_ientry has been added to the inode, so we are all set up.
- * now we just need to make sure tmp_ientry doesn't get freed and
- * we need to set up entry and ientry so the generic code can
- * do its thing. */
- ientry = tmp_ientry;
- entry = &ientry->fsn_entry;
- tmp_ientry = NULL;
-
- atomic_inc(&group->inotify_data.user->inotify_watches);
-
- /* update the idr hint */
- group->inotify_data.last_wd = ientry->wd;
-
- /* we put the mark on the idr, take a reference */
- fsnotify_get_mark(entry);
- }
+ if (!entry)
+ return -ENOENT;
- ret = ientry->wd;
+ ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
spin_lock(&entry->lock);
@@ -536,18 +514,103 @@ retry:
fsnotify_recalc_group_mask(group);
}
- /* this either matches fsnotify_find_mark_entry, or init_mark_entry
- * depending on which path we took... */
+ /* return the wd */
+ ret = ientry->wd;
+
+ /* match the get from fsnotify_find_mark_entry() */
fsnotify_put_mark(entry);
+ return ret;
+}
+
+static int inotify_new_watch(struct fsnotify_group *group,
+ struct inode *inode,
+ u32 arg)
+{
+ struct inotify_inode_mark_entry *tmp_ientry;
+ __u32 mask;
+ int ret;
+
+ /* don't allow invalid bits: we don't want flags set */
+ mask = inotify_arg_to_mask(arg);
+ if (unlikely(!mask))
+ return -EINVAL;
+
+ tmp_ientry = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
+ if (unlikely(!tmp_ientry))
+ return -ENOMEM;
+
+ fsnotify_init_mark(&tmp_ientry->fsn_entry, inotify_free_mark);
+ tmp_ientry->fsn_entry.mask = mask;
+ tmp_ientry->wd = -1;
+
+ ret = -ENOSPC;
+ if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches)
+ goto out_err;
+retry:
+ ret = -ENOMEM;
+ if (unlikely(!idr_pre_get(&group->inotify_data.idr, GFP_KERNEL)))
+ goto out_err;
+
+ spin_lock(&group->inotify_data.idr_lock);
+ ret = idr_get_new_above(&group->inotify_data.idr, &tmp_ientry->fsn_entry,
+ group->inotify_data.last_wd,
+ &tmp_ientry->wd);
+ spin_unlock(&group->inotify_data.idr_lock);
+ if (ret) {
+ /* idr was out of memory allocate and try again */
+ if (ret == -EAGAIN)
+ goto retry;
+ goto out_err;
+ }
+
+ /* we put the mark on the idr, take a reference */
+ fsnotify_get_mark(&tmp_ientry->fsn_entry);
+
+ /* we are on the idr, now get on the inode */
+ ret = fsnotify_add_mark(&tmp_ientry->fsn_entry, group, inode);
+ if (ret) {
+ /* we failed to get on the inode, get off the idr */
+ inotify_remove_from_idr(group, tmp_ientry);
+ goto out_err;
+ }
+
+ /* update the idr hint, who cares about races, it's just a hint */
+ group->inotify_data.last_wd = tmp_ientry->wd;
+
+ /* increment the number of watches the user has */
+ atomic_inc(&group->inotify_data.user->inotify_watches);
+
+ /* return the watch descriptor for this new entry */
+ ret = tmp_ientry->wd;
+
+ /* match the ref from fsnotify_init_markentry() */
+ fsnotify_put_mark(&tmp_ientry->fsn_entry);
+
out_err:
- /* could be an error, could be that we found an existing mark */
- if (tmp_ientry) {
- /* on the idr but didn't make it on the inode */
- if (tmp_ientry->wd != -1)
- inotify_remove_from_idr(group, tmp_ientry);
+ if (ret < 0)
kmem_cache_free(inotify_inode_mark_cachep, tmp_ientry);
- }
+
+ return ret;
+}
+
+static int inotify_update_watch(struct fsnotify_group *group, struct inode *inode, u32 arg)
+{
+ int ret = 0;
+
+retry:
+ /* try to update and existing watch with the new arg */
+ ret = inotify_update_existing_watch(group, inode, arg);
+ /* no mark present, try to add a new one */
+ if (ret == -ENOENT)
+ ret = inotify_new_watch(group, inode, arg);
+ /*
+ * inotify_new_watch could race with another thread which did an
+ * inotify_new_watch between the update_existing and the add watch
+ * here, go back and try to update an existing mark again.
+ */
+ if (ret == -EEXIST)
+ goto retry;
return ret;
}
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 8246c697863..0d885fd7511 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -64,6 +64,12 @@
#define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT)
#define NMI_OFFSET (1UL << NMI_SHIFT)
+#ifndef PREEMPT_ACTIVE
+#define PREEMPT_ACTIVE_BITS 1
+#define PREEMPT_ACTIVE_SHIFT (NMI_SHIFT + NMI_BITS)
+#define PREEMPT_ACTIVE (__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
+#endif
+
#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS))
#error PREEMPT_ACTIVE is too low!
#endif
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index d6320a3e8de..2b5b1e0899a 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -125,7 +125,7 @@ extern int _cond_resched(void);
#endif
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
- void __might_sleep(char *file, int line);
+ void __might_sleep(char *file, int line, int preempt_offset);
/**
* might_sleep - annotation for functions that can sleep
*
@@ -137,8 +137,9 @@ extern int _cond_resched(void);
* supposed to.
*/
# define might_sleep() \
- do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0)
+ do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
#else
+ static inline void __might_sleep(char *file, int line, int preempt_offset) { }
# define might_sleep() do { might_resched(); } while (0)
#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0f1ea4a6695..9c96ef2f7e6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -38,6 +38,8 @@
#define SCHED_BATCH 3
/* SCHED_ISO: reserved but not implemented yet */
#define SCHED_IDLE 5
+/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
+#define SCHED_RESET_ON_FORK 0x40000000
#ifdef __KERNEL__
@@ -1045,7 +1047,6 @@ struct sched_class {
struct rq *busiest, struct sched_domain *sd,
enum cpu_idle_type idle);
void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
- int (*needs_post_schedule) (struct rq *this_rq);
void (*post_schedule) (struct rq *this_rq);
void (*task_wake_up) (struct rq *this_rq, struct task_struct *task);
@@ -1110,6 +1111,8 @@ struct sched_entity {
u64 wait_max;
u64 wait_count;
u64 wait_sum;
+ u64 iowait_count;
+ u64 iowait_sum;
u64 sleep_start;
u64 sleep_max;
@@ -1230,11 +1233,19 @@ struct task_struct {
unsigned did_exec:1;
unsigned in_execve:1; /* Tell the LSMs that the process is doing an
* execve */
+ unsigned in_iowait:1;
+
+
+ /* Revert to default priority/policy when forking */
+ unsigned sched_reset_on_fork:1;
+
pid_t pid;
pid_t tgid;
+#ifdef CONFIG_CC_STACKPROTECTOR
/* Canary value for the -fstack-protector gcc feature */
unsigned long stack_canary;
+#endif
/*
* pointers to (original) parent process, youngest child, younger sibling,
@@ -2281,23 +2292,31 @@ static inline int need_resched(void)
* cond_resched_softirq() will enable bhs before scheduling.
*/
extern int _cond_resched(void);
-#ifdef CONFIG_PREEMPT_BKL
-static inline int cond_resched(void)
-{
- return 0;
-}
+
+#define cond_resched() ({ \
+ __might_sleep(__FILE__, __LINE__, 0); \
+ _cond_resched(); \
+})
+
+extern int __cond_resched_lock(spinlock_t *lock);
+
+#ifdef CONFIG_PREEMPT
+#define PREEMPT_LOCK_OFFSET PREEMPT_OFFSET
#else
-static inline int cond_resched(void)
-{
- return _cond_resched();
-}
+#define PREEMPT_LOCK_OFFSET 0
#endif
-extern int cond_resched_lock(spinlock_t * lock);
-extern int cond_resched_softirq(void);
-static inline int cond_resched_bkl(void)
-{
- return _cond_resched();
-}
+
+#define cond_resched_lock(lock) ({ \
+ __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \
+ __cond_resched_lock(lock); \
+})
+
+extern int __cond_resched_softirq(void);
+
+#define cond_resched_softirq() ({ \
+ __might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET); \
+ __cond_resched_softirq(); \
+})
/*
* Does a critical section need to be broken due to another
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 8949bb7eb08..a4c369ec328 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -340,6 +340,101 @@ TRACE_EVENT(sched_signal_send,
__entry->sig, __entry->comm, __entry->pid)
);
+/*
+ * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE
+ * adding sched_stat support to SCHED_FIFO/RR would be welcome.
+ */
+
+/*
+ * Tracepoint for accounting wait time (time the task is runnable
+ * but not actually running due to scheduler contention).
+ */
+TRACE_EVENT(sched_stat_wait,
+
+ TP_PROTO(struct task_struct *tsk, u64 delay),
+
+ TP_ARGS(tsk, delay),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( u64, delay )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->delay = delay;
+ )
+ TP_perf_assign(
+ __perf_count(delay);
+ ),
+
+ TP_printk("task: %s:%d wait: %Lu [ns]",
+ __entry->comm, __entry->pid,
+ (unsigned long long)__entry->delay)
+);
+
+/*
+ * Tracepoint for accounting sleep time (time the task is not runnable,
+ * including iowait, see below).
+ */
+TRACE_EVENT(sched_stat_sleep,
+
+ TP_PROTO(struct task_struct *tsk, u64 delay),
+
+ TP_ARGS(tsk, delay),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( u64, delay )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->delay = delay;
+ )
+ TP_perf_assign(
+ __perf_count(delay);
+ ),
+
+ TP_printk("task: %s:%d sleep: %Lu [ns]",
+ __entry->comm, __entry->pid,
+ (unsigned long long)__entry->delay)
+);
+
+/*
+ * Tracepoint for accounting iowait time (time the task is not runnable
+ * due to waiting on IO to complete).
+ */
+TRACE_EVENT(sched_stat_iowait,
+
+ TP_PROTO(struct task_struct *tsk, u64 delay),
+
+ TP_ARGS(tsk, delay),
+
+ TP_STRUCT__entry(
+ __array( char, comm, TASK_COMM_LEN )
+ __field( pid_t, pid )
+ __field( u64, delay )
+ ),
+
+ TP_fast_assign(
+ memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+ __entry->pid = tsk->pid;
+ __entry->delay = delay;
+ )
+ TP_perf_assign(
+ __perf_count(delay);
+ ),
+
+ TP_printk("task: %s:%d iowait: %Lu [ns]",
+ __entry->comm, __entry->pid,
+ (unsigned long long)__entry->delay)
+);
+
#endif /* _TRACE_SCHED_H */
/* This part must be outside protection */
diff --git a/kernel/module.c b/kernel/module.c
index fd141140355..eccb561dd8a 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -909,16 +909,18 @@ void __symbol_put(const char *symbol)
}
EXPORT_SYMBOL(__symbol_put);
+/* Note this assumes addr is a function, which it currently always is. */
void symbol_put_addr(void *addr)
{
struct module *modaddr;
+ unsigned long a = (unsigned long)dereference_function_descriptor(addr);
- if (core_kernel_text((unsigned long)addr))
+ if (core_kernel_text(a))
return;
/* module_text_address is safe here: we're supposed to have reference
* to module from symbol_get, so it can't go away. */
- modaddr = __module_text_address((unsigned long)addr);
+ modaddr = __module_text_address(a);
BUG_ON(!modaddr);
module_put(modaddr);
}
@@ -2353,7 +2355,8 @@ static noinline struct module *load_module(void __user *umod,
if (err < 0)
goto unlink;
add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
- add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
+ if (mod->sect_attrs)
+ add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
/* Get rid of temporary copy */
vfree(hdr);
diff --git a/kernel/sched.c b/kernel/sched.c
index 1b59e265273..da1edc8277d 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -309,8 +309,8 @@ void set_tg_uid(struct user_struct *user)
/*
* Root task group.
- * Every UID task group (including init_task_group aka UID-0) will
- * be a child to this group.
+ * Every UID task group (including init_task_group aka UID-0) will
+ * be a child to this group.
*/
struct task_group root_task_group;
@@ -318,7 +318,7 @@ struct task_group root_task_group;
/* Default task group's sched entity on each cpu */
static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
/* Default task group's cfs_rq on each cpu */
-static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU(struct cfs_rq, init_tg_cfs_rq) ____cacheline_aligned_in_smp;
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
@@ -616,6 +616,7 @@ struct rq {
unsigned char idle_at_tick;
/* For active balancing */
+ int post_schedule;
int active_balance;
int push_cpu;
/* cpu of this runqueue: */
@@ -693,6 +694,7 @@ static inline int cpu_of(struct rq *rq)
#define this_rq() (&__get_cpu_var(runqueues))
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
+#define raw_rq() (&__raw_get_cpu_var(runqueues))
inline void update_rq_clock(struct rq *rq)
{
@@ -1513,28 +1515,35 @@ static unsigned long cpu_avg_load_per_task(int cpu)
#ifdef CONFIG_FAIR_GROUP_SCHED
+struct update_shares_data {
+ unsigned long rq_weight[NR_CPUS];
+};
+
+static DEFINE_PER_CPU(struct update_shares_data, update_shares_data);
+
static void __set_se_shares(struct sched_entity *se, unsigned long shares);
/*
* Calculate and set the cpu's group shares.
*/
-static void
-update_group_shares_cpu(struct task_group *tg, int cpu,
- unsigned long sd_shares, unsigned long sd_rq_weight)
+static void update_group_shares_cpu(struct task_group *tg, int cpu,
+ unsigned long sd_shares,
+ unsigned long sd_rq_weight,
+ struct update_shares_data *usd)
{
- unsigned long shares;
- unsigned long rq_weight;
-
- if (!tg->se[cpu])
- return;
+ unsigned long shares, rq_weight;
+ int boost = 0;
- rq_weight = tg->cfs_rq[cpu]->rq_weight;
+ rq_weight = usd->rq_weight[cpu];
+ if (!rq_weight) {
+ boost = 1;
+ rq_weight = NICE_0_LOAD;
+ }
/*
- * \Sum shares * rq_weight
- * shares = -----------------------
- * \Sum rq_weight
- *
+ * \Sum_j shares_j * rq_weight_i
+ * shares_i = -----------------------------
+ * \Sum_j rq_weight_j
*/
shares = (sd_shares * rq_weight) / sd_rq_weight;
shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
@@ -1545,8 +1554,8 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
unsigned long flags;
spin_lock_irqsave(&rq->lock, flags);
- tg->cfs_rq[cpu]->shares = shares;
-
+ tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
+ tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
__set_se_shares(tg->se[cpu], shares);
spin_unlock_irqrestore(&rq->lock, flags);
}
@@ -1559,22 +1568,30 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
*/
static int tg_shares_up(struct task_group *tg, void *data)
{
- unsigned long weight, rq_weight = 0;
- unsigned long shares = 0;
+ unsigned long weight, rq_weight = 0, shares = 0;
+ struct update_shares_data *usd;
struct sched_domain *sd = data;
+ unsigned long flags;
int i;
+ if (!tg->se[0])
+ return 0;
+
+ local_irq_save(flags);
+ usd = &__get_cpu_var(update_shares_data);
+
for_each_cpu(i, sched_domain_span(sd)) {
+ weight = tg->cfs_rq[i]->load.weight;
+ usd->rq_weight[i] = weight;
+
/*
* If there are currently no tasks on the cpu pretend there
* is one of average load so that when a new task gets to
* run here it will not get delayed by group starvation.
*/
- weight = tg->cfs_rq[i]->load.weight;
if (!weight)
weight = NICE_0_LOAD;
- tg->cfs_rq[i]->rq_weight = weight;
rq_weight += weight;
shares += tg->cfs_rq[i]->shares;
}
@@ -1586,7 +1603,9 @@ static int tg_shares_up(struct task_group *tg, void *data)
shares = tg->shares;
for_each_cpu(i, sched_domain_span(sd))
- update_group_shares_cpu(tg, i, shares, rq_weight);
+ update_group_shares_cpu(tg, i, shares, rq_weight, usd);
+
+ local_irq_restore(flags);
return 0;
}
@@ -1616,8 +1635,14 @@ static int tg_load_down(struct task_group *tg, void *data)
static void update_shares(struct sched_domain *sd)
{
- u64 now = cpu_clock(raw_smp_processor_id());
- s64 elapsed = now - sd->last_update;
+ s64 elapsed;
+ u64 now;
+
+ if (root_task_group_empty())
+ return;
+
+ now = cpu_clock(raw_smp_processor_id());
+ elapsed = now - sd->last_update;
if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
sd->last_update = now;
@@ -1627,6 +1652,9 @@ static void update_shares(struct sched_domain *sd)
static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
{
+ if (root_task_group_empty())
+ return;
+
spin_unlock(&rq->lock);
update_shares(sd);
spin_lock(&rq->lock);
@@ -1634,6 +1662,9 @@ static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
static void update_h_load(long cpu)
{
+ if (root_task_group_empty())
+ return;
+
walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
}
@@ -2637,9 +2668,32 @@ void sched_fork(struct task_struct *p, int clone_flags)
set_task_cpu(p, cpu);
/*
- * Make sure we do not leak PI boosting priority to the child:
+ * Make sure we do not leak PI boosting priority to the child.
*/
p->prio = current->normal_prio;
+
+ /*
+ * Revert to default priority/policy on fork if requested.
+ */
+ if (unlikely(p->sched_reset_on_fork)) {
+ if (p->policy == SCHED_FIFO || p->policy == SCHED_RR)
+ p->policy = SCHED_NORMAL;
+
+ if (p->normal_prio < DEFAULT_PRIO)
+ p->prio = DEFAULT_PRIO;
+
+ if (PRIO_TO_NICE(p->static_prio) < 0) {
+ p->static_prio = NICE_TO_PRIO(0);
+ set_load_weight(p);
+ }
+
+ /*
+ * We don't need the reset flag anymore after the fork. It has
+ * fulfilled its duty:
+ */
+ p->sched_reset_on_fork = 0;
+ }
+
if (!rt_prio(p->prio))
p->sched_class = &fair_sched_class;
@@ -2796,12 +2850,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
{
struct mm_struct *mm = rq->prev_mm;
long prev_state;
-#ifdef CONFIG_SMP
- int post_schedule = 0;
-
- if (current->sched_class->needs_post_schedule)
- post_schedule = current->sched_class->needs_post_schedule(rq);
-#endif
rq->prev_mm = NULL;
@@ -2820,10 +2868,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
finish_arch_switch(prev);
perf_counter_task_sched_in(current, cpu_of(rq));
finish_lock_switch(rq, prev);
-#ifdef CONFIG_SMP
- if (post_schedule)
- current->sched_class->post_schedule(rq);
-#endif
fire_sched_in_preempt_notifiers(current);
if (mm)
@@ -2838,6 +2882,42 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
}
}
+#ifdef CONFIG_SMP
+
+/* assumes rq->lock is held */
+static inline void pre_schedule(struct rq *rq, struct task_struct *prev)
+{
+ if (prev->sched_class->pre_schedule)
+ prev->sched_class->pre_schedule(rq, prev);
+}
+
+/* rq->lock is NOT held, but preemption is disabled */
+static inline void post_schedule(struct rq *rq)
+{
+ if (rq->post_schedule) {
+ unsigned long flags;
+
+ spin_lock_irqsave(&rq->lock, flags);
+ if (rq->curr->sched_class->post_schedule)
+ rq->curr->sched_class->post_schedule(rq);
+ spin_unlock_irqrestore(&rq->lock, flags);
+
+ rq->post_schedule = 0;
+ }
+}
+
+#else
+
+static inline void pre_schedule(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline void post_schedule(struct rq *rq)
+{
+}
+
+#endif
+
/**
* schedule_tail - first thing a freshly forked thread must call.
* @prev: the thread we just switched away from.
@@ -2848,6 +2928,13 @@ asmlinkage void schedule_tail(struct task_struct *prev)
struct rq *rq = this_rq();
finish_task_switch(rq, prev);
+
+ /*
+ * FIXME: do we need to worry about rq being invalidated by the
+ * task_switch?
+ */
+ post_schedule(rq);
+
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
/* In this case, finish_task_switch does not reenable preemption */
preempt_enable();
@@ -3379,9 +3466,10 @@ static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
{
const struct sched_class *class;
- for (class = sched_class_highest; class; class = class->next)
+ for_each_class(class) {
if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
return 1;
+ }
return 0;
}
@@ -5349,10 +5437,7 @@ need_resched_nonpreemptible:
switch_count = &prev->nvcsw;
}
-#ifdef CONFIG_SMP
- if (prev->sched_class->pre_schedule)
- prev->sched_class->pre_schedule(rq, prev);
-#endif
+ pre_schedule(rq, prev);
if (unlikely(!rq->nr_running))
idle_balance(cpu, rq);
@@ -5378,6 +5463,8 @@ need_resched_nonpreemptible:
} else
spin_unlock_irq(&rq->lock);
+ post_schedule(rq);
+
if (unlikely(reacquire_kernel_lock(current) < 0))
goto need_resched_nonpreemptible;
@@ -6123,17 +6210,25 @@ static int __sched_setscheduler(struct task_struct *p, int policy,
unsigned long flags;
const struct sched_class *prev_class = p->sched_class;
struct rq *rq;
+ int reset_on_fork;
/* may grab non-irq protected spin_locks */
BUG_ON(in_interrupt());
recheck:
/* double check policy once rq lock held */
- if (policy < 0)
+ if (policy < 0) {
+ reset_on_fork = p->sched_reset_on_fork;
policy = oldpolicy = p->policy;
- else if (policy != SCHED_FIFO && policy != SCHED_RR &&
- policy != SCHED_NORMAL && policy != SCHED_BATCH &&
- policy != SCHED_IDLE)
- return -EINVAL;
+ } else {
+ reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
+ policy &= ~SCHED_RESET_ON_FORK;
+
+ if (policy != SCHED_FIFO && policy != SCHED_RR &&
+ policy != SCHED_NORMAL && policy != SCHED_BATCH &&
+ policy != SCHED_IDLE)
+ return -EINVAL;
+ }
+
/*
* Valid priorities for SCHED_FIFO and SCHED_RR are
* 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
@@ -6177,6 +6272,10 @@ recheck:
/* can't change other user's priorities */
if (!check_same_owner(p))
return -EPERM;
+
+ /* Normal users shall not reset the sched_reset_on_fork flag */
+ if (p->sched_reset_on_fork && !reset_on_fork)
+ return -EPERM;
}
if (user) {
@@ -6220,6 +6319,8 @@ recheck:
if (running)
p->sched_class->put_prev_task(rq, p);
+ p->sched_reset_on_fork = reset_on_fork;
+
oldprio = p->prio;
__setscheduler(rq, p, policy, param->sched_priority);
@@ -6336,14 +6437,15 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
if (p) {
retval = security_task_getscheduler(p);
if (!retval)
- retval = p->policy;
+ retval = p->policy
+ | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
}
read_unlock(&tasklist_lock);
return retval;
}
/**
- * sys_sched_getscheduler - get the RT priority of a thread
+ * sys_sched_getparam - get the RT priority of a thread
* @pid: the pid in question.
* @param: structure containing the RT priority.
*/
@@ -6571,19 +6673,9 @@ static inline int should_resched(void)
static void __cond_resched(void)
{
-#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
- __might_sleep(__FILE__, __LINE__);
-#endif
- /*
- * The BKS might be reacquired before we have dropped
- * PREEMPT_ACTIVE, which could trigger a second
- * cond_resched() call.
- */
- do {
- add_preempt_count(PREEMPT_ACTIVE);
- schedule();
- sub_preempt_count(PREEMPT_ACTIVE);
- } while (need_resched());
+ add_preempt_count(PREEMPT_ACTIVE);
+ schedule();
+ sub_preempt_count(PREEMPT_ACTIVE);
}
int __sched _cond_resched(void)
@@ -6597,14 +6689,14 @@ int __sched _cond_resched(void)
EXPORT_SYMBOL(_cond_resched);
/*
- * cond_resched_lock() - if a reschedule is pending, drop the given lock,
+ * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
* call schedule, and on return reacquire the lock.
*
* This works OK both with and without CONFIG_PREEMPT. We do strange low-level
* operations here to prevent schedule() from being called twice (once via
* spin_unlock(), once by hand).
*/
-int cond_resched_lock(spinlock_t *lock)
+int __cond_resched_lock(spinlock_t *lock)
{
int resched = should_resched();
int ret = 0;
@@ -6620,9 +6712,9 @@ int cond_resched_lock(spinlock_t *lock)
}
return ret;
}
-EXPORT_SYMBOL(cond_resched_lock);
+EXPORT_SYMBOL(__cond_resched_lock);
-int __sched cond_resched_softirq(void)
+int __sched __cond_resched_softirq(void)
{
BUG_ON(!in_softirq());
@@ -6634,7 +6726,7 @@ int __sched cond_resched_softirq(void)
}
return 0;
}
-EXPORT_SYMBOL(cond_resched_softirq);
+EXPORT_SYMBOL(__cond_resched_softirq);
/**
* yield - yield the current processor to other threads.
@@ -6658,11 +6750,13 @@ EXPORT_SYMBOL(yield);
*/
void __sched io_schedule(void)
{
- struct rq *rq = &__raw_get_cpu_var(runqueues);
+ struct rq *rq = raw_rq();
delayacct_blkio_start();
atomic_inc(&rq->nr_iowait);
+ current->in_iowait = 1;
schedule();
+ current->in_iowait = 0;
atomic_dec(&rq->nr_iowait);
delayacct_blkio_end();
}
@@ -6670,12 +6764,14 @@ EXPORT_SYMBOL(io_schedule);
long __sched io_schedule_timeout(long timeout)
{
- struct rq *rq = &__raw_get_cpu_var(runqueues);
+ struct rq *rq = raw_rq();
long ret;
delayacct_blkio_start();
atomic_inc(&rq->nr_iowait);
+ current->in_iowait = 1;
ret = schedule_timeout(timeout);
+ current->in_iowait = 0;
atomic_dec(&rq->nr_iowait);
delayacct_blkio_end();
return ret;
@@ -6992,8 +7088,12 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
/* Need help from migration thread: drop lock and wait. */
+ struct task_struct *mt = rq->migration_thread;
+
+ get_task_struct(mt);
task_rq_unlock(rq, &flags);
wake_up_process(rq->migration_thread);
+ put_task_struct(mt);
wait_for_completion(&req.done);
tlb_migrate_finish(p->mm);
return 0;
@@ -7625,7 +7725,7 @@ static int __init migration_init(void)
migration_call(&migration_notifier, CPU_ONLINE, cpu);
register_cpu_notifier(&migration_notifier);
- return err;
+ return 0;
}
early_initcall(migration_init);
#endif
@@ -7841,7 +7941,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
rq->rd = rd;
cpumask_set_cpu(rq->cpu, rd->span);
- if (cpumask_test_cpu(rq->cpu, cpu_online_mask))
+ if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
set_rq_online(rq);
spin_unlock_irqrestore(&rq->lock, flags);
@@ -8091,6 +8191,39 @@ struct static_sched_domain {
DECLARE_BITMAP(span, CONFIG_NR_CPUS);
};
+struct s_data {
+#ifdef CONFIG_NUMA
+ int sd_allnodes;
+ cpumask_var_t domainspan;
+ cpumask_var_t covered;
+ cpumask_var_t notcovered;
+#endif
+ cpumask_var_t nodemask;
+ cpumask_var_t this_sibling_map;
+ cpumask_var_t this_core_map;
+ cpumask_var_t send_covered;
+ cpumask_var_t tmpmask;
+ struct sched_group **sched_group_nodes;
+ struct root_domain *rd;
+};
+
+enum s_alloc {
+ sa_sched_groups = 0,
+ sa_rootdomain,
+ sa_tmpmask,
+ sa_send_covered,
+ sa_this_core_map,
+ sa_this_sibling_map,
+ sa_nodemask,
+ sa_sched_group_nodes,
+#ifdef CONFIG_NUMA
+ sa_notcovered,
+ sa_covered,
+ sa_domainspan,
+#endif
+ sa_none,
+};
+
/*
* SMT sched-domains:
*/
@@ -8213,6 +8346,71 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
sg = sg->next;
} while (sg != group_head);
}
+
+static int build_numa_sched_groups(struct s_data *d,
+ const struct cpumask *cpu_map, int num)
+{
+ struct sched_domain *sd;
+ struct sched_group *sg, *prev;
+ int n, j;
+
+ cpumask_clear(d->covered);
+ cpumask_and(d->nodemask, cpumask_of_node(num), cpu_map);
+ if (cpumask_empty(d->nodemask)) {
+ d->sched_group_nodes[num] = NULL;
+ goto out;
+ }
+
+ sched_domain_node_span(num, d->domainspan);
+ cpumask_and(d->domainspan, d->domainspan, cpu_map);
+
+ sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
+ GFP_KERNEL, num);
+ if (!sg) {
+ printk(KERN_WARNING "Can not alloc domain group for node %d\n",
+ num);
+ return -ENOMEM;
+ }
+ d->sched_group_nodes[num] = sg;
+
+ for_each_cpu(j, d->nodemask) {
+ sd = &per_cpu(node_domains, j).sd;
+ sd->groups = sg;
+ }
+
+ sg->__cpu_power = 0;
+ cpumask_copy(sched_group_cpus(sg), d->nodemask);
+ sg->next = sg;
+ cpumask_or(d->covered, d->covered, d->nodemask);
+
+ prev = sg;
+ for (j = 0; j < nr_node_ids; j++) {
+ n = (num + j) % nr_node_ids;
+ cpumask_complement(d->notcovered, d->covered);
+ cpumask_and(d->tmpmask, d->notcovered, cpu_map);
+ cpumask_and(d->tmpmask, d->tmpmask, d->domainspan);
+ if (cpumask_empty(d->tmpmask))
+ break;
+ cpumask_and(d->tmpmask, d->tmpmask, cpumask_of_node(n));
+ if (cpumask_empty(d->tmpmask))
+ continue;
+ sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
+ GFP_KERNEL, num);
+ if (!sg) {
+ printk(KERN_WARNING
+ "Can not alloc domain group for node %d\n", j);
+ return -ENOMEM;
+ }
+ sg->__cpu_power = 0;
+ cpumask_copy(sched_group_cpus(sg), d->tmpmask);
+ sg->next = prev->next;
+ cpumask_or(d->covered, d->covered, d->tmpmask);
+ prev->next = sg;
+ prev = sg;
+ }
+out:
+ return 0;
+}
#endif /* CONFIG_NUMA */
#ifdef CONFIG_NUMA
@@ -8378,280 +8576,285 @@ static void set_domain_attribute(struct sched_domain *sd,
}
}
-/*
- * Build sched domains for a given set of cpus and attach the sched domains
- * to the individual cpus
- */
-static int __build_sched_domains(const struct cpumask *cpu_map,
- struct sched_domain_attr *attr)
-{
- int i, err = -ENOMEM;
- struct root_domain *rd;
- cpumask_var_t nodemask, this_sibling_map, this_core_map, send_covered,
- tmpmask;
+static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
+ const struct cpumask *cpu_map)
+{
+ switch (what) {
+ case sa_sched_groups:
+ free_sched_groups(cpu_map, d->tmpmask); /* fall through */
+ d->sched_group_nodes = NULL;
+ case sa_rootdomain:
+ free_rootdomain(d->rd); /* fall through */
+ case sa_tmpmask:
+ free_cpumask_var(d->tmpmask); /* fall through */
+ case sa_send_covered:
+ free_cpumask_var(d->send_covered); /* fall through */
+ case sa_this_core_map:
+ free_cpumask_var(d->this_core_map); /* fall through */
+ case sa_this_sibling_map:
+ free_cpumask_var(d->this_sibling_map); /* fall through */
+ case sa_nodemask:
+ free_cpumask_var(d->nodemask); /* fall through */
+ case sa_sched_group_nodes:
#ifdef CONFIG_NUMA
- cpumask_var_t domainspan, covered, notcovered;
- struct sched_group **sched_group_nodes = NULL;
- int sd_allnodes = 0;
-
- if (!alloc_cpumask_var(&domainspan, GFP_KERNEL))
- goto out;
- if (!alloc_cpumask_var(&covered, GFP_KERNEL))
- goto free_domainspan;
- if (!alloc_cpumask_var(&notcovered, GFP_KERNEL))
- goto free_covered;
-#endif
-
- if (!alloc_cpumask_var(&nodemask, GFP_KERNEL))
- goto free_notcovered;
- if (!alloc_cpumask_var(&this_sibling_map, GFP_KERNEL))
- goto free_nodemask;
- if (!alloc_cpumask_var(&this_core_map, GFP_KERNEL))
- goto free_this_sibling_map;
- if (!alloc_cpumask_var(&send_covered, GFP_KERNEL))
- goto free_this_core_map;
- if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
- goto free_send_covered;
+ kfree(d->sched_group_nodes); /* fall through */
+ case sa_notcovered:
+ free_cpumask_var(d->notcovered); /* fall through */
+ case sa_covered:
+ free_cpumask_var(d->covered); /* fall through */
+ case sa_domainspan:
+ free_cpumask_var(d->domainspan); /* fall through */
+#endif
+ case sa_none:
+ break;
+ }
+}
+static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
+ const struct cpumask *cpu_map)
+{
#ifdef CONFIG_NUMA
- /*
- * Allocate the per-node list of sched groups
- */
- sched_group_nodes = kcalloc(nr_node_ids, sizeof(struct sched_group *),
- GFP_KERNEL);
- if (!sched_group_nodes) {
+ if (!alloc_cpumask_var(&d->domainspan, GFP_KERNEL))
+ return sa_none;
+ if (!alloc_cpumask_var(&d->covered, GFP_KERNEL))
+ return sa_domainspan;
+ if (!alloc_cpumask_var(&d->notcovered, GFP_KERNEL))
+ return sa_covered;
+ /* Allocate the per-node list of sched groups */
+ d->sched_group_nodes = kcalloc(nr_node_ids,
+ sizeof(struct sched_group *), GFP_KERNEL);
+ if (!d->sched_group_nodes) {
printk(KERN_WARNING "Can not alloc sched group node list\n");
- goto free_tmpmask;
- }
-#endif
-
- rd = alloc_rootdomain();
- if (!rd) {
+ return sa_notcovered;
+ }
+ sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes;
+#endif
+ if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL))
+ return sa_sched_group_nodes;
+ if (!alloc_cpumask_var(&d->this_sibling_map, GFP_KERNEL))
+ return sa_nodemask;
+ if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL))
+ return sa_this_sibling_map;
+ if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+ return sa_this_core_map;
+ if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
+ return sa_send_covered;
+ d->rd = alloc_rootdomain();
+ if (!d->rd) {
printk(KERN_WARNING "Cannot alloc root domain\n");
- goto free_sched_groups;
+ return sa_tmpmask;
}
+ return sa_rootdomain;
+}
+static struct sched_domain *__build_numa_sched_domains(struct s_data *d,
+ const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i)
+{
+ struct sched_domain *sd = NULL;
#ifdef CONFIG_NUMA
- sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes;
-#endif
-
- /*
- * Set up domains for cpus specified by the cpu_map.
- */
- for_each_cpu(i, cpu_map) {
- struct sched_domain *sd = NULL, *p;
-
- cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map);
-
-#ifdef CONFIG_NUMA
- if (cpumask_weight(cpu_map) >
- SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
- sd = &per_cpu(allnodes_domains, i).sd;
- SD_INIT(sd, ALLNODES);
- set_domain_attribute(sd, attr);
- cpumask_copy(sched_domain_span(sd), cpu_map);
- cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask);
- p = sd;
- sd_allnodes = 1;
- } else
- p = NULL;
+ struct sched_domain *parent;
- sd = &per_cpu(node_domains, i).sd;
- SD_INIT(sd, NODE);
+ d->sd_allnodes = 0;
+ if (cpumask_weight(cpu_map) >
+ SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) {
+ sd = &per_cpu(allnodes_domains, i).sd;
+ SD_INIT(sd, ALLNODES);
set_domain_attribute(sd, attr);
- sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
- sd->parent = p;
- if (p)
- p->child = sd;
- cpumask_and(sched_domain_span(sd),
- sched_domain_span(sd), cpu_map);
+ cpumask_copy(sched_domain_span(sd), cpu_map);
+ cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask);
+ d->sd_allnodes = 1;
+ }
+ parent = sd;
+
+ sd = &per_cpu(node_domains, i).sd;
+ SD_INIT(sd, NODE);
+ set_domain_attribute(sd, attr);
+ sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
+ sd->parent = parent;
+ if (parent)
+ parent->child = sd;
+ cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map);
#endif
+ return sd;
+}
- p = sd;
- sd = &per_cpu(phys_domains, i).sd;
- SD_INIT(sd, CPU);
- set_domain_attribute(sd, attr);
- cpumask_copy(sched_domain_span(sd), nodemask);
- sd->parent = p;
- if (p)
- p->child = sd;
- cpu_to_phys_group(i, cpu_map, &sd->groups, tmpmask);
+static struct sched_domain *__build_cpu_sched_domain(struct s_data *d,
+ const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+ struct sched_domain *parent, int i)
+{
+ struct sched_domain *sd;
+ sd = &per_cpu(phys_domains, i).sd;
+ SD_INIT(sd, CPU);
+ set_domain_attribute(sd, attr);
+ cpumask_copy(sched_domain_span(sd), d->nodemask);
+ sd->parent = parent;
+ if (parent)
+ parent->child = sd;
+ cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask);
+ return sd;
+}
+static struct sched_domain *__build_mc_sched_domain(struct s_data *d,
+ const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+ struct sched_domain *parent, int i)
+{
+ struct sched_domain *sd = parent;
#ifdef CONFIG_SCHED_MC
- p = sd;
- sd = &per_cpu(core_domains, i).sd;
- SD_INIT(sd, MC);
- set_domain_attribute(sd, attr);
- cpumask_and(sched_domain_span(sd), cpu_map,
- cpu_coregroup_mask(i));
- sd->parent = p;
- p->child = sd;
- cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask);
+ sd = &per_cpu(core_domains, i).sd;
+ SD_INIT(sd, MC);
+ set_domain_attribute(sd, attr);
+ cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i));
+ sd->parent = parent;
+ parent->child = sd;
+ cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask);
#endif
+ return sd;
+}
+static struct sched_domain *__build_smt_sched_domain(struct s_data *d,
+ const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+ struct sched_domain *parent, int i)
+{
+ struct sched_domain *sd = parent;
#ifdef CONFIG_SCHED_SMT
- p = sd;
- sd = &per_cpu(cpu_domains, i).sd;
- SD_INIT(sd, SIBLING);
- set_domain_attribute(sd, attr);
- cpumask_and(sched_domain_span(sd),
- topology_thread_cpumask(i), cpu_map);
- sd->parent = p;
- p->child = sd;
- cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
+ sd = &per_cpu(cpu_domains, i).sd;
+ SD_INIT(sd, SIBLING);
+ set_domain_attribute(sd, attr);
+ cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i));
+ sd->parent = parent;
+ parent->child = sd;
+ cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask);
#endif
- }
+ return sd;
+}
+static void build_sched_groups(struct s_data *d, enum sched_domain_level l,
+ const struct cpumask *cpu_map, int cpu)
+{
+ switch (l) {
#ifdef CONFIG_SCHED_SMT
- /* Set up CPU (sibling) groups */
- for_each_cpu(i, cpu_map) {
- cpumask_and(this_sibling_map,
- topology_thread_cpumask(i), cpu_map);
- if (i != cpumask_first(this_sibling_map))
- continue;
-
- init_sched_build_groups(this_sibling_map, cpu_map,
- &cpu_to_cpu_group,
- send_covered, tmpmask);
- }
+ case SD_LV_SIBLING: /* set up CPU (sibling) groups */
+ cpumask_and(d->this_sibling_map, cpu_map,
+ topology_thread_cpumask(cpu));
+ if (cpu == cpumask_first(d->this_sibling_map))
+ init_sched_build_groups(d->this_sibling_map, cpu_map,
+ &cpu_to_cpu_group,
+ d->send_covered, d->tmpmask);
+ break;
#endif
-
#ifdef CONFIG_SCHED_MC
- /* Set up multi-core groups */
- for_each_cpu(i, cpu_map) {
- cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map);
- if (i != cpumask_first(this_core_map))
- continue;
-
- init_sched_build_groups(this_core_map, cpu_map,
- &cpu_to_core_group,
- send_covered, tmpmask);
- }
+ case SD_LV_MC: /* set up multi-core groups */
+ cpumask_and(d->this_core_map, cpu_map, cpu_coregroup_mask(cpu));
+ if (cpu == cpumask_first(d->this_core_map))
+ init_sched_build_groups(d->this_core_map, cpu_map,
+ &cpu_to_core_group,
+ d->send_covered, d->tmpmask);
+ break;
#endif
-
- /* Set up physical groups */
- for (i = 0; i < nr_node_ids; i++) {
- cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
- if (cpumask_empty(nodemask))
- continue;
-
- init_sched_build_groups(nodemask, cpu_map,
- &cpu_to_phys_group,
- send_covered, tmpmask);
- }
-
+ case SD_LV_CPU: /* set up physical groups */
+ cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
+ if (!cpumask_empty(d->nodemask))
+ init_sched_build_groups(d->nodemask, cpu_map,
+ &cpu_to_phys_group,
+ d->send_covered, d->tmpmask);
+ break;
#ifdef CONFIG_NUMA
- /* Set up node groups */
- if (sd_allnodes) {
- init_sched_build_groups(cpu_map, cpu_map,
- &cpu_to_allnodes_group,
- send_covered, tmpmask);
+ case SD_LV_ALLNODES:
+ init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group,
+ d->send_covered, d->tmpmask);
+ break;
+#endif
+ default:
+ break;
}
+}
- for (i = 0; i < nr_node_ids; i++) {
- /* Set up node groups */
- struct sched_group *sg, *prev;
- int j;
-
- cpumask_clear(covered);
- cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
- if (cpumask_empty(nodemask)) {
- sched_group_nodes[i] = NULL;
- continue;
- }
+/*
+ * Build sched domains for a given set of cpus and attach the sched domains
+ * to the individual cpus
+ */
+static int __build_sched_domains(const struct cpumask *cpu_map,
+ struct sched_domain_attr *attr)
+{
+ enum s_alloc alloc_state = sa_none;
+ struct s_data d;
+ struct sched_domain *sd;
+ int i;
+#ifdef CONFIG_NUMA
+ d.sd_allnodes = 0;
+#endif
- sched_domain_node_span(i, domainspan);
- cpumask_and(domainspan, domainspan, cpu_map);
+ alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
+ if (alloc_state != sa_rootdomain)
+ goto error;
+ alloc_state = sa_sched_groups;
- sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
- GFP_KERNEL, i);
- if (!sg) {
- printk(KERN_WARNING "Can not alloc domain group for "
- "node %d\n", i);
- goto error;
- }
- sched_group_nodes[i] = sg;
- for_each_cpu(j, nodemask) {
- struct sched_domain *sd;
+ /*
+ * Set up domains for cpus specified by the cpu_map.
+ */
+ for_each_cpu(i, cpu_map) {
+ cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)),
+ cpu_map);
- sd = &per_cpu(node_domains, j).sd;
- sd->groups = sg;
- }
- sg->__cpu_power = 0;
- cpumask_copy(sched_group_cpus(sg), nodemask);
- sg->next = sg;
- cpumask_or(covered, covered, nodemask);
- prev = sg;
+ sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
+ sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
+ sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
+ sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
+ }
- for (j = 0; j < nr_node_ids; j++) {
- int n = (i + j) % nr_node_ids;
+ for_each_cpu(i, cpu_map) {
+ build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
+ build_sched_groups(&d, SD_LV_MC, cpu_map, i);
+ }
- cpumask_complement(notcovered, covered);
- cpumask_and(tmpmask, notcovered, cpu_map);
- cpumask_and(tmpmask, tmpmask, domainspan);
- if (cpumask_empty(tmpmask))
- break;
+ /* Set up physical groups */
+ for (i = 0; i < nr_node_ids; i++)
+ build_sched_groups(&d, SD_LV_CPU, cpu_map, i);
- cpumask_and(tmpmask, tmpmask, cpumask_of_node(n));
- if (cpumask_empty(tmpmask))
- continue;
+#ifdef CONFIG_NUMA
+ /* Set up node groups */
+ if (d.sd_allnodes)
+ build_sched_groups(&d, SD_LV_ALLNODES, cpu_map, 0);
- sg = kmalloc_node(sizeof(struct sched_group) +
- cpumask_size(),
- GFP_KERNEL, i);
- if (!sg) {
- printk(KERN_WARNING
- "Can not alloc domain group for node %d\n", j);
- goto error;
- }
- sg->__cpu_power = 0;
- cpumask_copy(sched_group_cpus(sg), tmpmask);
- sg->next = prev->next;
- cpumask_or(covered, covered, tmpmask);
- prev->next = sg;
- prev = sg;
- }
- }
+ for (i = 0; i < nr_node_ids; i++)
+ if (build_numa_sched_groups(&d, cpu_map, i))
+ goto error;
#endif
/* Calculate CPU power for physical packages and nodes */
#ifdef CONFIG_SCHED_SMT
for_each_cpu(i, cpu_map) {
- struct sched_domain *sd = &per_cpu(cpu_domains, i).sd;
-
+ sd = &per_cpu(cpu_domains, i).sd;
init_sched_groups_power(i, sd);
}
#endif
#ifdef CONFIG_SCHED_MC
for_each_cpu(i, cpu_map) {
- struct sched_domain *sd = &per_cpu(core_domains, i).sd;
-
+ sd = &per_cpu(core_domains, i).sd;
init_sched_groups_power(i, sd);
}
#endif
for_each_cpu(i, cpu_map) {
- struct sched_domain *sd = &per_cpu(phys_domains, i).sd;
-
+ sd = &per_cpu(phys_domains, i).sd;
init_sched_groups_power(i, sd);
}
#ifdef CONFIG_NUMA
for (i = 0; i < nr_node_ids; i++)
- init_numa_sched_groups_power(sched_group_nodes[i]);
+ init_numa_sched_groups_power(d.sched_group_nodes[i]);
- if (sd_allnodes) {
+ if (d.sd_allnodes) {
struct sched_group *sg;
cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg,
- tmpmask);
+ d.tmpmask);
init_numa_sched_groups_power(sg);
}
#endif
/* Attach the domains */
for_each_cpu(i, cpu_map) {
- struct sched_domain *sd;
#ifdef CONFIG_SCHED_SMT
sd = &per_cpu(cpu_domains, i).sd;
#elif defined(CONFIG_SCHED_MC)
@@ -8659,44 +8862,16 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
#else
sd = &per_cpu(phys_domains, i).sd;
#endif
- cpu_attach_domain(sd, rd, i);
+ cpu_attach_domain(sd, d.rd, i);
}
- err = 0;
-
-free_tmpmask:
- free_cpumask_var(tmpmask);
-free_send_covered:
- free_cpumask_var(send_covered);
-free_this_core_map:
- free_cpumask_var(this_core_map);
-free_this_sibling_map:
- free_cpumask_var(this_sibling_map);
-free_nodemask:
- free_cpumask_var(nodemask);
-free_notcovered:
-#ifdef CONFIG_NUMA
- free_cpumask_var(notcovered);
-free_covered:
- free_cpumask_var(covered);
-free_domainspan:
- free_cpumask_var(domainspan);
-out:
-#endif
- return err;
-
-free_sched_groups:
-#ifdef CONFIG_NUMA
- kfree(sched_group_nodes);
-#endif
- goto free_tmpmask;
+ d.sched_group_nodes = NULL; /* don't free this we still need it */
+ __free_domain_allocs(&d, sa_tmpmask, cpu_map);
+ return 0;
-#ifdef CONFIG_NUMA
error:
- free_sched_groups(cpu_map, tmpmask);
- free_rootdomain(rd);
- goto free_tmpmask;
-#endif
+ __free_domain_allocs(&d, alloc_state, cpu_map);
+ return -ENOMEM;
}
static int build_sched_domains(const struct cpumask *cpu_map)
@@ -9304,11 +9479,11 @@ void __init sched_init(void)
* system cpu resource, based on the weight assigned to root
* user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished
* by letting tasks of init_task_group sit in a separate cfs_rq
- * (init_cfs_rq) and having one entity represent this group of
+ * (init_tg_cfs_rq) and having one entity represent this group of
* tasks in rq->cfs (i.e init_task_group->se[] != NULL).
*/
init_tg_cfs_entry(&init_task_group,
- &per_cpu(init_cfs_rq, i),
+ &per_cpu(init_tg_cfs_rq, i),
&per_cpu(init_sched_entity, i), i, 1,
root_task_group.se[i]);
@@ -9334,6 +9509,7 @@ void __init sched_init(void)
#ifdef CONFIG_SMP
rq->sd = NULL;
rq->rd = NULL;
+ rq->post_schedule = 0;
rq->active_balance = 0;
rq->next_balance = jiffies;
rq->push_cpu = 0;
@@ -9398,13 +9574,20 @@ void __init sched_init(void)
}
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
-void __might_sleep(char *file, int line)
+static inline int preempt_count_equals(int preempt_offset)
+{
+ int nested = preempt_count() & ~PREEMPT_ACTIVE;
+
+ return (nested == PREEMPT_INATOMIC_BASE + preempt_offset);
+}
+
+void __might_sleep(char *file, int line, int preempt_offset)
{
#ifdef in_atomic
static unsigned long prev_jiffy; /* ratelimiting */
- if ((!in_atomic() && !irqs_disabled()) ||
- system_state != SYSTEM_RUNNING || oops_in_progress)
+ if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
+ system_state != SYSTEM_RUNNING || oops_in_progress)
return;
if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
return;
diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c
index d014efbf947..0f052fc674d 100644
--- a/kernel/sched_cpupri.c
+++ b/kernel/sched_cpupri.c
@@ -127,21 +127,11 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
/*
* If the cpu was currently mapped to a different value, we
- * first need to unmap the old value
+ * need to map it to the new value then remove the old value.
+ * Note, we must add the new value first, otherwise we risk the
+ * cpu being cleared from pri_active, and this cpu could be
+ * missed for a push or pull.
*/
- if (likely(oldpri != CPUPRI_INVALID)) {
- struct cpupri_vec *vec = &cp->pri_to_cpu[oldpri];
-
- spin_lock_irqsave(&vec->lock, flags);
-
- vec->count--;
- if (!vec->count)
- clear_bit(oldpri, cp->pri_active);
- cpumask_clear_cpu(cpu, vec->mask);
-
- spin_unlock_irqrestore(&vec->lock, flags);
- }
-
if (likely(newpri != CPUPRI_INVALID)) {
struct cpupri_vec *vec = &cp->pri_to_cpu[newpri];
@@ -154,6 +144,18 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri)
spin_unlock_irqrestore(&vec->lock, flags);
}
+ if (likely(oldpri != CPUPRI_INVALID)) {
+ struct cpupri_vec *vec = &cp->pri_to_cpu[oldpri];
+
+ spin_lock_irqsave(&vec->lock, flags);
+
+ vec->count--;
+ if (!vec->count)
+ clear_bit(oldpri, cp->pri_active);
+ cpumask_clear_cpu(cpu, vec->mask);
+
+ spin_unlock_irqrestore(&vec->lock, flags);
+ }
*currpri = newpri;
}
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 70c7e0b7994..5ddbd089126 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -409,6 +409,8 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
PN(se.wait_max);
PN(se.wait_sum);
P(se.wait_count);
+ PN(se.iowait_sum);
+ P(se.iowait_count);
P(sched_info.bkl_count);
P(se.nr_migrations);
P(se.nr_migrations_cold);
@@ -479,6 +481,8 @@ void proc_sched_set_task(struct task_struct *p)
p->se.wait_max = 0;
p->se.wait_sum = 0;
p->se.wait_count = 0;
+ p->se.iowait_sum = 0;
+ p->se.iowait_count = 0;
p->se.sleep_max = 0;
p->se.sum_sleep_runtime = 0;
p->se.block_max = 0;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 652e8bdef9a..2ff850f90d1 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -79,11 +79,6 @@ static const struct sched_class fair_sched_class;
* CFS operations on generic schedulable entities:
*/
-static inline struct task_struct *task_of(struct sched_entity *se)
-{
- return container_of(se, struct task_struct, se);
-}
-
#ifdef CONFIG_FAIR_GROUP_SCHED
/* cpu runqueue to which this cfs_rq is attached */
@@ -95,6 +90,14 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
/* An entity is a task if it doesn't "own" a runqueue */
#define entity_is_task(se) (!se->my_q)
+static inline struct task_struct *task_of(struct sched_entity *se)
+{
+#ifdef CONFIG_SCHED_DEBUG
+ WARN_ON_ONCE(!entity_is_task(se));
+#endif
+ return container_of(se, struct task_struct, se);
+}
+
/* Walk up scheduling entities hierarchy */
#define for_each_sched_entity(se) \
for (; se; se = se->parent)
@@ -186,7 +189,12 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
}
}
-#else /* CONFIG_FAIR_GROUP_SCHED */
+#else /* !CONFIG_FAIR_GROUP_SCHED */
+
+static inline struct task_struct *task_of(struct sched_entity *se)
+{
+ return container_of(se, struct task_struct, se);
+}
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
@@ -538,6 +546,13 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
schedstat_set(se->wait_sum, se->wait_sum +
rq_of(cfs_rq)->clock - se->wait_start);
schedstat_set(se->wait_start, 0);
+
+#ifdef CONFIG_SCHEDSTATS
+ if (entity_is_task(se)) {
+ trace_sched_stat_wait(task_of(se),
+ rq_of(cfs_rq)->clock - se->wait_start);
+ }
+#endif
}
static inline void
@@ -628,8 +643,10 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
se->sleep_start = 0;
se->sum_sleep_runtime += delta;
- if (tsk)
+ if (tsk) {
account_scheduler_latency(tsk, delta >> 10, 1);
+ trace_sched_stat_sleep(tsk, delta);
+ }
}
if (se->block_start) {
u64 delta = rq_of(cfs_rq)->clock - se->block_start;
@@ -644,6 +661,12 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
se->sum_sleep_runtime += delta;
if (tsk) {
+ if (tsk->in_iowait) {
+ se->iowait_sum += delta;
+ se->iowait_count++;
+ trace_sched_stat_iowait(tsk, delta);
+ }
+
/*
* Blocking time is in units of nanosecs, so shift by
* 20 to get a milliseconds-range estimation of the
@@ -1046,17 +1069,21 @@ static void yield_task_fair(struct rq *rq)
* search starts with cpus closest then further out as needed,
* so we always favor a closer, idle cpu.
* Domains may include CPUs that are not usable for migration,
- * hence we need to mask them out (cpu_active_mask)
+ * hence we need to mask them out (rq->rd->online)
*
* Returns the CPU we should wake onto.
*/
#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
+
+#define cpu_rd_active(cpu, rq) cpumask_test_cpu(cpu, rq->rd->online)
+
static int wake_idle(int cpu, struct task_struct *p)
{
struct sched_domain *sd;
int i;
unsigned int chosen_wakeup_cpu;
int this_cpu;
+ struct rq *task_rq = task_rq(p);
/*
* At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu
@@ -1089,10 +1116,10 @@ static int wake_idle(int cpu, struct task_struct *p)
for_each_domain(cpu, sd) {
if ((sd->flags & SD_WAKE_IDLE)
|| ((sd->flags & SD_WAKE_IDLE_FAR)
- && !task_hot(p, task_rq(p)->clock, sd))) {
+ && !task_hot(p, task_rq->clock, sd))) {
for_each_cpu_and(i, sched_domain_span(sd),
&p->cpus_allowed) {
- if (cpu_active(i) && idle_cpu(i)) {
+ if (cpu_rd_active(i, task_rq) && idle_cpu(i)) {
if (i != task_cpu(p)) {
schedstat_inc(p,
se.nr_wakeups_idle);
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 3918e01994e..3d4020a9ba1 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -3,15 +3,18 @@
* policies)
*/
+#ifdef CONFIG_RT_GROUP_SCHED
+
+#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
+
static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
{
+#ifdef CONFIG_SCHED_DEBUG
+ WARN_ON_ONCE(!rt_entity_is_task(rt_se));
+#endif
return container_of(rt_se, struct task_struct, rt);
}
-#ifdef CONFIG_RT_GROUP_SCHED
-
-#define rt_entity_is_task(rt_se) (!(rt_se)->my_q)
-
static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
return rt_rq->rq;
@@ -26,6 +29,11 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se)
#define rt_entity_is_task(rt_se) (1)
+static inline struct task_struct *rt_task_of(struct sched_rt_entity *rt_se)
+{
+ return container_of(rt_se, struct task_struct, rt);
+}
+
static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq)
{
return container_of(rt_rq, struct rq, rt);
@@ -128,6 +136,11 @@ static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
}
+static inline int has_pushable_tasks(struct rq *rq)
+{
+ return !plist_head_empty(&rq->rt.pushable_tasks);
+}
+
#else
static inline void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
@@ -1064,6 +1077,14 @@ static struct task_struct *pick_next_task_rt(struct rq *rq)
if (p)
dequeue_pushable_task(rq, p);
+#ifdef CONFIG_SMP
+ /*
+ * We detect this state here so that we can avoid taking the RQ
+ * lock again later if there is no need to push
+ */
+ rq->post_schedule = has_pushable_tasks(rq);
+#endif
+
return p;
}
@@ -1162,13 +1183,6 @@ static int find_lowest_rq(struct task_struct *task)
return -1; /* No targets found */
/*
- * Only consider CPUs that are usable for migration.
- * I guess we might want to change cpupri_find() to ignore those
- * in the first place.
- */
- cpumask_and(lowest_mask, lowest_mask, cpu_active_mask);
-
- /*
* At this point we have built a mask of cpus representing the
* lowest priority tasks in the system. Now we want to elect
* the best one based on our affinity and topology.
@@ -1262,11 +1276,6 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
return lowest_rq;
}
-static inline int has_pushable_tasks(struct rq *rq)
-{
- return !plist_head_empty(&rq->rt.pushable_tasks);
-}
-
static struct task_struct *pick_next_pushable_task(struct rq *rq)
{
struct task_struct *p;
@@ -1466,23 +1475,9 @@ static void pre_schedule_rt(struct rq *rq, struct task_struct *prev)
pull_rt_task(rq);
}
-/*
- * assumes rq->lock is held
- */
-static int needs_post_schedule_rt(struct rq *rq)
-{
- return has_pushable_tasks(rq);
-}
-
static void post_schedule_rt(struct rq *rq)
{
- /*
- * This is only called if needs_post_schedule_rt() indicates that
- * we need to push tasks away
- */
- spin_lock_irq(&rq->lock);
push_rt_tasks(rq);
- spin_unlock_irq(&rq->lock);
}
/*
@@ -1758,7 +1753,6 @@ static const struct sched_class rt_sched_class = {
.rq_online = rq_online_rt,
.rq_offline = rq_offline_rt,
.pre_schedule = pre_schedule_rt,
- .needs_post_schedule = needs_post_schedule_rt,
.post_schedule = post_schedule_rt,
.task_wake_up = task_wake_up_rt,
.switched_from = switched_from_rt,
diff --git a/lib/lmb.c b/lib/lmb.c
index e4a6482d8b2..0343c05609f 100644
--- a/lib/lmb.c
+++ b/lib/lmb.c
@@ -429,7 +429,7 @@ u64 __init lmb_phys_mem_size(void)
return lmb.memory.size;
}
-u64 __init lmb_end_of_DRAM(void)
+u64 lmb_end_of_DRAM(void)
{
int idx = lmb.memory.cnt - 1;
diff --git a/net/9p/client.c b/net/9p/client.c
index 787ccddb85e..5bf5f227dbe 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -60,9 +60,9 @@ static struct p9_req_t *
p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...);
/**
- * v9fs_parse_options - parse mount options into session structure
- * @options: options string passed from mount
- * @v9ses: existing v9fs session information
+ * parse_options - parse mount options into client structure
+ * @opts: options string passed from mount
+ * @clnt: existing v9fs client information
*
* Return 0 upon success, -ERRNO upon failure
*/
@@ -232,7 +232,7 @@ EXPORT_SYMBOL(p9_tag_lookup);
/**
* p9_tag_init - setup tags structure and contents
- * @tags: tags structure from the client struct
+ * @c: v9fs client struct
*
* This initializes the tags structure for each client instance.
*
@@ -258,7 +258,7 @@ error:
/**
* p9_tag_cleanup - cleans up tags structure and reclaims resources
- * @tags: tags structure from the client struct
+ * @c: v9fs client struct
*
* This frees resources associated with the tags structure
*
@@ -411,14 +411,9 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
if (c->dotu)
err = -ecode;
- if (!err) {
+ if (!err || !IS_ERR_VALUE(err))
err = p9_errstr2errno(ename, strlen(ename));
- /* string match failed */
- if (!err)
- err = -ESERVERFAULT;
- }
-
P9_DPRINTK(P9_DEBUG_9P, "<<< RERROR (%d) %s\n", -ecode, ename);
kfree(ename);
@@ -430,8 +425,8 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
/**
* p9_client_flush - flush (cancel) a request
- * c: client state
- * req: request to cancel
+ * @c: client state
+ * @oldreq: request to cancel
*
* This sents a flush for a particular requests and links
* the flush request to the original request. The current
diff --git a/net/9p/error.c b/net/9p/error.c
index fdebe431406..52518512a93 100644
--- a/net/9p/error.c
+++ b/net/9p/error.c
@@ -239,7 +239,7 @@ int p9_errstr2errno(char *errstr, int len)
errstr[len] = 0;
printk(KERN_ERR "%s: server reported unknown error %s\n",
__func__, errstr);
- errno = 1;
+ errno = ESERVERFAULT;
}
return -errno;
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 8c2588e4edc..8d934dd7fd5 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -119,8 +119,8 @@ struct p9_poll_wait {
* @wpos: write position for current frame
* @wsize: amount of data to write for current frame
* @wbuf: current write buffer
+ * @poll_pending_link: pending links to be polled per conn
* @poll_wait: array of wait_q's for various worker threads
- * @poll_waddr: ????
* @pt: poll state
* @rq: current read work
* @wq: current write work
@@ -700,9 +700,9 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
}
/**
- * parse_options - parse mount options into session structure
- * @options: options string passed from mount
- * @opts: transport-specific structure to parse options into
+ * parse_opts - parse mount options into p9_fd_opts structure
+ * @params: options string passed from mount
+ * @opts: fd transport-specific structure to parse options into
*
* Returns 0 upon success, -ERRNO upon failure
*/
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index ac4990041eb..65cb29db03f 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -67,14 +67,15 @@
* @pd: Protection Domain pointer
* @qp: Queue Pair pointer
* @cq: Completion Queue pointer
+ * @dm_mr: DMA Memory Region pointer
* @lkey: The local access only memory region key
* @timeout: Number of uSecs to wait for connection management events
* @sq_depth: The depth of the Send Queue
* @sq_sem: Semaphore for the SQ
* @rq_depth: The depth of the Receive Queue.
+ * @rq_count: Count of requests in the Receive Queue.
* @addr: The remote peer's address
* @req_lock: Protects the active request list
- * @send_wait: Wait list when the SQ fills up
* @cm_done: Completion event for connection management tracking
*/
struct p9_trans_rdma {
@@ -154,9 +155,9 @@ static match_table_t tokens = {
};
/**
- * parse_options - parse mount options into session structure
- * @options: options string passed from mount
- * @opts: transport-specific structure to parse options into
+ * parse_opts - parse mount options into rdma options structure
+ * @params: options string passed from mount
+ * @opts: rdma transport-specific structure to parse options into
*
* Returns 0 upon success, -ERRNO upon failure
*/
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index a49484e67e1..9bf0b737aa5 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -57,11 +57,9 @@ static int chan_index;
* @initialized: whether the channel is initialized
* @inuse: whether the channel is in use
* @lock: protects multiple elements within this structure
+ * @client: client instance
* @vdev: virtio dev associated with this channel
* @vq: virtio queue associated with this channel
- * @tagpool: accounting for tag ids (and request slots)
- * @reqs: array of request slots
- * @max_tag: current number of request_slots allocated
* @sg: scatter gather list which is used to pack a request (protected?)
*
* We keep all per-channel information in a structure.
@@ -92,7 +90,7 @@ static unsigned int rest_of_page(void *data)
/**
* p9_virtio_close - reclaim resources of a channel
- * @trans: transport state
+ * @client: client instance
*
* This reclaims a channel by freeing its resources and
* reseting its inuse flag.
@@ -181,9 +179,8 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
/**
* p9_virtio_request - issue a request
- * @t: transport state
- * @tc: &p9_fcall request to transmit
- * @rc: &p9_fcall to put reponse into
+ * @client: client instance issuing the request
+ * @req: request to be issued
*
*/
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 7d082105472..7ffcd96fe59 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -813,6 +813,8 @@ int ip_append_data(struct sock *sk,
inet->cork.addr = ipc->addr;
}
rt = *rtp;
+ if (unlikely(!rt))
+ return -EFAULT;
/*
* We steal reference to this route, caller should not release it
*/
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-22 03:33:00 +0000