procfs, fdinfo seqfile providers
Subsystems (6)
cover procfs, fdinfo seqfile providers
Hi guys,
here is a bit updated version of procfs fdinfo providers (I've ported the series to 3.5-rc4 kernel). Please review if you have time.
The base idea remains the same -- provide additional information specified for file type (fanotify/eventpoll) via /proc/pid/fdinfo/$fd suitable to restore suct file.
Cyrill
RFC 1/7 procfs: Move /proc/pid/fd[info] handling code to fd.[ch]
This patch prepares the ground for further extension of /proc/pid/fd[info] handling code by moving fdinfo handling code into fs/proc/fd.c.
I think such move makes both fs/proc/base.c and fs/proc/fd.c easier to read.
--- fs/proc/Makefile | 2 fs/proc/base.c | 388 ----------------------------------------------------- fs/proc/fd.c | 351 +++++++++++++++++++++++++++++++++++++++++++++++ fs/proc/fd.h | 14 + fs/proc/internal.h | 48 ++++++ 5 files changed, 416 insertions(+), 387 deletions(-)
fs/proc/Makefile +1 -1
@@ -8,7 +8,7 @@ proc-y := nommu.o task_nommu.o proc-$(CONFIG_MMU) := mmu.o task_mmu.o proc-y += inode.o root.o base.o generic.o array.o \ - proc_tty.o + proc_tty.o fd.o proc-y += cmdline.o proc-y += consoles.o proc-y += cpuinfo.o
fs/proc/base.c +2 -386
430 lines not on this page · raw message
fs/proc/fd.c new file +351 -0
351 lines not on this page · raw message
fs/proc/fd.h new file +14 -0
@@ -0,0 +1,14 @@ +#ifndef __PROCFS_FD_H__ +#define __PROCFS_FD_H__ + +#include <linux/fs.h> + +extern const struct file_operations proc_fd_operations; +extern const struct inode_operations proc_fd_inode_operations; + +extern const struct file_operations proc_fdinfo_operations; +extern const struct inode_operations proc_fdinfo_inode_operations; + +extern int proc_fd_permission (struct inode *inode,int mask); + +#endif /* __PROCFS_FD_H__ */
fs/proc/internal.h +48 -0
66 lines not on this page · raw message
RFC 2/7 procfs: Convert /proc/pid/fdinfo/ handling routines to seq-file
In reply to Cyrill GorcunovThis patch converts /proc/pid/fdinfo/ handling routines to seq-file which is needed to extend seq operations and plug in auxiliary fdinfo provides from subsystems like eventfd/eventpoll/fsnotify.
--- fs/proc/fd.c | 133 +++++++++++++++++++++++++++++++++++++---------------------- 1 file changed, 85 insertions(+), 48 deletions(-)
fs/proc/fd.c +85 -48
@@ -6,61 +6,90 @@#include <linux/namei.h> #include <linux/pid.h> #include <linux/security.h> +#include <linux/file.h> +#include <linux/seq_file.h> #include <linux/proc_fs.h> #include "internal.h" #include "fd.h" -#define PROC_FDINFO_MAX 64 +struct proc_fdinfo { +loff_t f_pos; +int f_flags; +}; + +static int seq_show (struct seq_file *m,void *v) +{ +struct proc_fdinfo *fdinfo = m->private; +seq_printf (m,"pos:\t%lli\nflags:\t0%o\n" , + (long long )fdinfo->f_pos, + fdinfo->f_flags); +return 0 ; +} -static int proc_fd_info (struct inode *inode,struct path *path,char *info) +static int seq_fdinfo_open (struct inode *inode,struct file *file) { -struct task_struct *task =get_proc_task (inode);struct files_struct *files =NULL ; -int fd =proc_fd (inode); -struct file *file; +struct proc_fdinfo *fdinfo =NULL ; +struct task_struct *task; +int ret = -ENOENT ; + fdinfo =kzalloc (sizeof (*fdinfo),GFP_KERNEL ); +if (!fdinfo) +return -ENOMEM ; + + task =get_proc_task (inode);if (task) { files =get_files_struct (task);put_task_struct (task); } +if (files) { -/* -* We are not taking a ref to the file structure, so we must -* hold ->file_lock. -*/ +int fd =proc_fd (inode); +struct file *fd_file; +spin_lock (&files->file_lock); - file =fcheck_files (files, fd); -if (file) { -unsigned int f_flags; -struct fdtable *fdt; + fd_file =fcheck_files (files, fd); +if (fd_file) { +struct fdtable *fdt =files_fdtable (files); - fdt =files_fdtable (files); - f_flags = file->f_flags & ~O_CLOEXEC ; + fdinfo->f_flags = fd_file->f_flags & ~O_CLOEXEC ;if (close_on_exec (fd, fdt)) - f_flags |=O_CLOEXEC ; - -if (path) { - *path = file->f_path; -path_get (&file->f_path); - } -if (info) -snprintf (info,PROC_FDINFO_MAX , -"pos:\t%lli\n" -"flags:\t0%o\n" , - (long long ) file->f_pos, - f_flags); -spin_unlock (&files->file_lock); -put_files_struct (files); -return 0 ; + fdinfo->f_flags |=O_CLOEXEC ; + ret =0 ; }spin_unlock (&files->file_lock);put_files_struct (files); } -return -ENOENT ; + +if (!ret) { + ret =single_open (file, seq_show, fdinfo); +if (!ret) + fdinfo =NULL ; + } + +kfree (fdinfo); +return ret; } +static int seq_fdinfo_release (struct inode *inode,struct file *file) +{ +struct seq_file *m = file->private_data; +struct proc_fdinfo *fdinfo = m->private; + +kfree (fdinfo); + +return single_release (inode, file); +} + +static const struct file_operations proc_fdinfo_file_operations = { + .open = seq_fdinfo_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_fdinfo_release, +}; +static int tid_fd_revalidate (struct dentry *dentry,struct nameidata *nd) {struct files_struct *files;
@@ -130,7 +159,31 @@ static const struct dentry_operations tistatic int proc_fd_link (struct dentry *dentry,struct path *path) { -return proc_fd_info (dentry->d_inode, path,NULL ); +struct inode *inode = dentry->d_inode; +struct task_struct *task =get_proc_task (inode); +struct files_struct *files =NULL ; +int fd =proc_fd (inode); +struct file *file; +int err = -ENOENT ; + +if (task) { + files =get_files_struct (task); +put_task_struct (task); + } + +if (files) { +spin_lock (&files->file_lock); + file =fcheck_files (files, fd); +if (file) { + *path = file->f_path; +path_get (&file->f_path); + } +spin_unlock (&files->file_lock); +put_files_struct (files); + err =0 ; + } + +return err; } static struct dentry *
@@ -245,22 +298,6 @@ out_no_task:return retval; } -static ssize_t proc_fdinfo_read (struct file *file,char __user *buf, -size_t len,loff_t *ppos) -{ -char tmp[PROC_FDINFO_MAX ]; -int err =proc_fd_info (file->f_path.dentry->d_inode,NULL , tmp); -if (!err) - err =simple_read_from_buffer (buf, len, ppos, tmp,strlen (tmp)); -return err; -} - -static const struct file_operations proc_fdinfo_file_operations = { - .open = nonseekable_open, - .read = proc_fdinfo_read, - .llseek = no_llseek, -}; -static int proc_readfd (struct file *filp,void *dirent,filldir_t filldir) {return proc_readfd_common (filp, dirent, filldir, proc_fd_instantiate);
Re: [rfc 2/7] procfs: Convert /proc/pid/fdinfo/ handling routines to seq-file
Quoted 37 lines
fs/proc/fd.c +25
-1@@ -130,7 +159,31 @@ static const struct dentry_operations tistatic int proc_fd_link (struct dentry *dentry,struct path *path) { -return proc_fd_info (dentry->d_inode, path,NULL ); +struct inode *inode = dentry->d_inode; +struct task_struct *task =get_proc_task (inode); +struct files_struct *files =NULL ; +int fd =proc_fd (inode); +struct file *file; +int err = -ENOENT ; + +if (task) { + files =get_files_struct (task); +put_task_struct (task); + } + +if (files) { +spin_lock (&files->file_lock); + file =fcheck_files (files, fd); +if (file) { + *path = file->f_path; +path_get (&file->f_path); + } +spin_unlock (&files->file_lock); +put_files_struct (files); + err =0 ; + } + +return err; } static struct dentry *@@ -245,22 +298,6 @@ out_no_task:return retval; }
fs/proc/fd.c out_no_task: · line 257
Quoted 10 lines
fs/proc/fd.c +0
-10-static ssize_t proc_fdinfo_read (struct file *file,char __user *buf, -size_t len,loff_t *ppos) -{ -char tmp[PROC_FDINFO_MAX ]; -int err =proc_fd_info (file->f_path.dentry->d_inode,NULL , tmp); -if (!err) - err =simple_read_from_buffer (buf, len, ppos, tmp,strlen (tmp)); -return err; -} -
I believe we can still have the proc_fdinfo_read and proc_fd_link code non-splitted. Just push a callback pointer ino the proc_fd_info (as usual -- we an opaque void *argument).
Thanks,
Pavel
Re: [rfc 2/7] procfs: Convert /proc/pid/fdinfo/ handling routines to seq-file
Quoted 14 lines · Pavel Emelyanov
fs/proc/fd.c out_no_task: · line 257
Quoted 11 lines
fs/proc/fd.c +0
-10-static ssize_t proc_fdinfo_read (struct file *file,char __user *buf, -size_t len,loff_t *ppos) -{ -char tmp[PROC_FDINFO_MAX ]; -int err =proc_fd_info (file->f_path.dentry->d_inode,NULL , tmp); -if (!err) - err =simple_read_from_buffer (buf, len, ppos, tmp,strlen (tmp)); -return err; -} -I believe we can still have the
proc_fdinfo_readandproc_fd_linkcode non-splitted. Just push a callback pointer ino theproc_fd_info(as usual -- we an opaque void *argument).
Thanks! Will try.
Cyrill
Re: [rfc 2/7] procfs: Convert /proc/pid/fdinfo/ handling routines to seq-file
In reply to Pavel EmelyanovOn Wed, Jul 04, 2012 at 11:37:26AM +0400, Pavel Emelyanov wrote:
...
Quoted 3 lines
I believe we can still have the
proc_fdinfo_readandproc_fd_linkcode non-splitted. Just push a callback pointer ino theproc_fd_info(as usual -- we an opaque void *argument).
Hi Pavel, sorry for delay (was busy a bit). It seems this wont work. Look, previously we have had
static int proc_fd_info(struct inode *inode, struct path *path, char *info)
{
struct task_struct *task = get_proc_task(inode);
...
if (info) {
...
}
this makes info argument optional
}static int proc_fd_link(struct dentry *dentry, struct path *path)
{
return proc_fd_info(dentry->d_inode, path, NULL);
}it's possible because we didn't use seq-files engine. One we switch to seq-files the old proc_fd_info become a part of
static const struct file_operations proc_fdinfo_file_operations = {
.open = seq_fdinfo_open,ie the declaration of seq_fdinfo_open is restricted to file_operations::open method and I can't add opaque void *argument here.
Sure I can add one more wrapper function but I guess this increase code complexity which I tried to escape.
Cyrill
RFC 3/7 procfs: Add ability to plugin auxiliary fdinfo providers
In reply to Cyrill GorcunovThis patch brings ability to plugin auxiliary fdinfo providers. For example in further patches eventfd, evenpoll and fsnotify will print out information associated with files.
This feature is CONFIG_CHECKPOINT_RESTORE guarded to eliminate overhead for those who don't need it at all (this unfortunately makes patch bigger than I wanted).
--- fs/proc/fd.c | 208 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/proc_fs.h | 28 ++++++ 2 files changed, 236 insertions(+)
fs/proc/fd.c +208 -0
@@ -8,12 +8,218 @@#include <linux/security.h> #include <linux/file.h> #include <linux/seq_file.h> +#include <linux/spinlock.h> #include <linux/proc_fs.h> #include "internal.h" #include "fd.h" +#ifdef CONFIG_CHECKPOINT_RESTORE + +static LIST_HEAD(fdinfo_drivers); +static DECLARE_RWSEM(fdinfo_drivers_sem); + +int proc_register_fdinfo_driver(struct proc_fdinfo_driver *s) +{ + struct proc_fdinfo_driver *i; + int ret = 0; + + if (!s->ops || !s->probe) + return -EINVAL; + + down_write(&fdinfo_drivers_sem); + list_for_each_entry(i, &fdinfo_drivers, list) { + if (i == s) { + WARN_ONCE("Trying reassign fdinfo driver `%s'\n", + i->name); + ret = -EINVAL; + break; + } + } + if (!ret) + list_add(&s->list, &fdinfo_drivers); + up_write(&fdinfo_drivers_sem); + + return ret; +} + +void proc_unregister_fdinfo_driver(struct proc_fdinfo_driver *s) +{ + struct proc_fdinfo_driver *i; + + down_write(&fdinfo_drivers_sem); + list_for_each_entry(i, &fdinfo_drivers, list) { + if (i == s) { + list_del(&i->list); + break; + } + } + up_write(&fdinfo_drivers_sem); +} + +static int prep_fdinfo_driver(struct proc_fdinfo_extra *extra) +{ + struct proc_fdinfo_driver *s; + int ret = 0; + + down_read(&fdinfo_drivers_sem); + list_for_each_entry(s, &fdinfo_drivers, list) { + if (s->probe(extra->f_file)) { + extra->driver = s; + break; + } + } + up_read(&fdinfo_drivers_sem); + + if (extra->driver && extra->driver->priv_size) { + extra->priv = kmalloc(extra->driver->priv_size, GFP_KERNEL); + if (!extra->priv) + ret = -ENOMEM; + } + + return ret; +} + +static void *seq_start(struct seq_file *m, loff_t *pos) +{ + struct proc_fdinfo_extra *extra = m->private; + + down_read(&fdinfo_drivers_sem); + extra->pos = *pos; + + return *pos == 0 ? extra : + (extra->driver ? extra->driver->ops->start(m, pos) : NULL); +} + +static void seq_stop(struct seq_file *m, void *v) +{ + struct proc_fdinfo_extra *extra = m->private; + + if (extra->driver && extra->pos > 0) + extra->driver->ops->stop(m, v); + up_read(&fdinfo_drivers_sem); +} + +static void *seq_next(struct seq_file *m, void *p, loff_t *pos) +{ + struct proc_fdinfo_extra *extra = m->private; + void *v = NULL; + + if (extra->driver) { + int ret = 0; + + if (*pos == 0) { + v = extra->driver->ops->start(m, pos); + if (v) { + ret = extra->driver->ops->show(m, v); + p = v; + } else + ret = -1; + } + + if (!ret) + v = extra->driver->ops->next(m, p, pos); + } else + ++*pos; + + extra->pos = *pos; + return v; +} + +static int seq_show(struct seq_file *m, void *v) +{ + struct proc_fdinfo_extra *extra = m->private; + + if (extra->driver && extra->pos > 0) + return extra->driver->ops->show(m, v); + + seq_printf(m, "pos:\t%lli\nflags:\t0%o\n", + (long long)extra->f_file->f_pos, + extra->f_flags); + return 0; +} + +static const struct seq_operations fdinfo_seq_ops = { + .start = seq_start, + .next = seq_next, + .stop = seq_stop, + .show = seq_show, +}; + +static int seq_fdinfo_open(struct inode *inode, struct file *file) +{ + struct files_struct *files = NULL; + struct proc_fdinfo_extra *extra; + struct task_struct *task; + struct seq_file *m; + int ret; + + extra = kzalloc(sizeof(*extra), GFP_KERNEL); + if (!extra) + return -ENOMEM; + + ret = seq_open(file, &fdinfo_seq_ops); + if (!ret) { + ret = -ENOENT; + m = file->private_data; + m->private = extra; + + task = get_proc_task(inode); + if (task) { + files = get_files_struct(task); + put_task_struct(task); + } + + if (files) { + int fd = proc_fd(inode); + + spin_lock(&files->file_lock); + extra->f_file = fcheck_files(files, fd); + if (extra->f_file) { + struct fdtable *fdt = files_fdtable(files); + + extra->f_flags = extra->f_file->f_flags & ~O_CLOEXEC; + if (close_on_exec(fd, fdt)) + extra->f_flags |= O_CLOEXEC; + get_file(extra->f_file); + } + spin_unlock(&files->file_lock); + put_files_struct(files); + + ret = prep_fdinfo_driver(extra); + } + } + + if (ret) { + if (extra->f_file) + put_filp(extra->f_file); + kfree(extra); + } + return ret; +} + +static int seq_fdinfo_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + struct proc_fdinfo_extra *extra = m->private; + + put_filp(extra->f_file); + kfree(extra->priv); + kfree(m->private); + + return seq_release(inode, file); +} + +static const struct file_operations proc_fdinfo_file_operations = { + .open = seq_fdinfo_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_fdinfo_release, +}; + +#else /* CONFIG_CHECKPOINT_RESTORE */ + struct proc_fdinfo { loff_t f_pos; int f_flags;
@@ -90,6 +296,8 @@ static const struct file_operations proc .release = seq_fdinfo_release, }; +#endif /* CONFIG_CHECKPOINT_RESTORE */ +static int tid_fd_revalidate (struct dentry *dentry,struct nameidata *nd) {struct files_struct *files;
include/linux/proc_fs.h +28 -0
@@ -100,6 +100,26 @@ struct vmcore {loff_t offset; }; +struct seq_operations ; + +/* fdinfo auxiliary information drivers */ +struct proc_fdinfo_driver { +struct list_head list; +const char *name; +const struct seq_operations *ops; +int (*probe)(struct file *file); +size_t priv_size; +}; + +/* auxiliary data allocated per fdinfo reader */ +struct proc_fdinfo_extra { +struct proc_fdinfo_driver *driver; +void *priv; +loff_t pos; +struct file *f_file; +unsigned int f_flags; +}; +#ifdef CONFIG_PROC_FS extern void proc_root_init (void );
@@ -175,6 +195,11 @@ extern struct proc_dir_entry *proc_net_mextern struct file *proc_ns_fget (int fd); +#ifdef CONFIG_CHECKPOINT_RESTORE +extern int proc_register_fdinfo_driver (struct proc_fdinfo_driver *s); +extern void proc_unregister_fdinfo_driver (struct proc_fdinfo_driver *s); +#endif /* CONFIG_CHECKPOINT_RESTORE */ +#else #define proc_net_fops_create (net, name, mode, fops) ({ (void)(mode), NULL; })
@@ -229,6 +254,9 @@ static inline struct file *proc_ns_fget( return ERR_PTR(-EINVAL); } +static inline int proc_register_fdinfo_driver (struct proc_fdinfo_driver *s) {return -EINVAL ; } +static inline void proc_unregister_fdinfo_driver (struct proc_fdinfo_driver *s) { } +#endif /* CONFIG_PROC_FS */ #if !defined(CONFIG_PROC_KCORE )
Re: [rfc 3/7] procfs: Add ability to plugin auxiliary fdinfo providers
Quoted 14 lines · Cyrill Gorcunov
This patch brings ability to plugin auxiliary fdinfo providers. For example in further patches eventfd, evenpoll and fsnotify will print out information associated with files.
This feature is
CONFIG_CHECKPOINT_RESTOREguarded to eliminate overhead for those who don't need it at all (this unfortunately makes patch bigger than I wanted).Signed-off-by Cyrill Gorcunov <[email protected]>CC Al Viro <[email protected]>CC Alexey Dobriyan <[email protected]>CC Andrew Morton <[email protected]>CC Pavel Emelyanov <[email protected]>CC James Bottomley <[email protected]>
Quoted 4 lines
--- fs/proc/fd.c | 208 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/proc_fs.h | 28 ++++++ 2 files changed, 236 insertions(+)
How about introducing one more file_operations member and call it in the seq_show() (if exists)? Only inotify, eventfd and eventpoll will implement one. This will allow to avoid all this complexity with drivers.
Re: [rfc 3/7] procfs: Add ability to plugin auxiliary fdinfo providers
Quoted 4 lines · Pavel Emelyanov
How about introducing one more
file_operationsmember and call it in theseq_show()(if exists)? Only inotify, eventfd and eventpoll will implement one. This will allow to avoid all this complexity with drivers.
Hmm. Thanks for idea, I need to estimate which impact it will have. Will ping back once it's done.
Cyrill
Re: [rfc 3/7] procfs: Add ability to plugin auxiliary fdinfo providers
In reply to Pavel EmelyanovQuoted 5 lines · Pavel Emelyanov
Quoted 4 lines · Cyrill Gorcunov
This patch brings ability to plugin auxiliary fdinfo providers. For example in further patches eventfd, evenpoll and fsnotify will print out information associated with files.
Quoted 7 lines
Quoted 3 lines
This feature is
CONFIG_CHECKPOINT_RESTOREguarded to eliminate overhead for those who don't need it at all (this unfortunately makes patch bigger than I wanted).How about introducing one more
file_operationsmember and call it in theseq_show()(if exists)? Only inotify, eventfd and eventpoll will implement one. This will allow to avoid all this complexity with drivers.
Hi Pavel, yes, this might be an option, if people agree with this approach I'll redo my patches (this will require to remake all the rest patches so I would like to know people opinion before start doint that). Anyone?
Cyrill
RFC 4/7 fs, eventfd: Add procfs fdinfo helper
In reply to Cyrill GorcunovThis allow us to print out raw counter value. The /proc/pid/fdinfo/fd output is
| pos: 0 | flags: 04002 | eventfd-count: 5a
This feature is CONFIG_CHECKPOINT_RESTORE only.
--- fs/eventfd.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+)
fs/eventfd.c +55 -0
@@ -19,6 +19,8 @@#include <linux/export.h> #include <linux/kref.h> #include <linux/eventfd.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> struct eventfd_ctx {struct kref kref;
@@ -433,3 +435,56 @@ SYSCALL_DEFINE1(eventfd, unsigned int, creturn sys_eventfd2 (count,0 ); } +#if defined(CONFIG_PROC_FS ) && defined(CONFIG_CHECKPOINT_RESTORE ) + +static void *seq_start (struct seq_file *m,loff_t *pos) +{ +struct proc_fdinfo_extra *extra = m->private; +return *pos ==0 ? extra->f_file :NULL ; +} + +static void *seq_next (struct seq_file *m,void *p,loff_t *pos) +{ + ++*pos; +return NULL ; +} + +static int seq_show (struct seq_file *m,void *v) +{ +struct eventfd_ctx *ctx = ((struct file *)v)->private_data; + +spin_lock_irq (&ctx->wqh.lock); +seq_printf (m,"eventfd-count: %16llx\n" , + (unsigned long long )ctx->count); +spin_unlock_irq (&ctx->wqh.lock); + +return 0 ; +} + +static void seq_stop (struct seq_file *p,void *v) { } + +static const struct seq_operations eventfd_fdinfo_ops = { + .start = seq_start, + .next = seq_next, + .stop = seq_stop, + .show = seq_show, +}; + +static int is_eventfd_file (struct file *file) +{ +return file->f_op == &eventfd_fops; +} + +static struct proc_fdinfo_driver eventfd_fdinfo = { + .name ="eventfd" , + .ops = &eventfd_fdinfo_ops, + .probe = is_eventfd_file, +}; + +static int __init eventfd_init (void ) +{ +return proc_register_fdinfo_driver (&eventfd_fdinfo); +} +fs_initcall (eventfd_init); + +#endif /* CONFIG_PROC_FS && CONFIG_CHECKPOINT_RESTORE */
RFC 5/7 fs, epoll: Add procfs fdinfo helper
In reply to Cyrill GorcunovThis allow us to print out eventpoll target file descriptor, events and data, the /proc/pid/fdinfo/fd consists of
| pos: 0 | flags: 02 | tfd: 5 events: 1d data: ffffffffffffffff
This feature is CONFIG_CHECKPOINT_RESTORE only.
--- fs/eventpoll.c | 81 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 81 insertions(+)
fs/eventpoll.c +81 -0
@@ -38,6 +38,8 @@#include <asm/io.h> #include <asm/mman.h> #include <linux/atomic.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> /* * LOCKING:
@@ -1897,6 +1899,83 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd,return error; } +#if defined(CONFIG_PROC_FS ) && defined(CONFIG_CHECKPOINT_RESTORE ) + +struct epitem_fdinfo { +struct epoll_event ev; +int fd; +}; + +static struct epitem_fdinfo * +seq_lookup_fdinfo (struct proc_fdinfo_extra *extra,struct eventpoll *ep,loff_t num) +{ +struct epitem_fdinfo *fdinfo = extra->priv; +struct epitem *epi =NULL ; +struct rb_node *rbp; + +mutex_lock (&ep->mtx); +for (rbp =rb_first (&ep->rbr); rbp; rbp =rb_next (rbp)) { +if (num-- ==0 ) { + epi = rb_entry(rbp, struct epitem, rbn); + fdinfo->fd = epi->ffd.fd; + fdinfo->ev = epi->event; +break ; + } + } +mutex_unlock (&ep->mtx); + +return epi ? fdinfo :NULL ; +} + +static void *seq_start (struct seq_file *m,loff_t *pos) +{ +struct proc_fdinfo_extra *extra = m->private; +struct eventpoll *ep = extra->f_file->private_data; + +return seq_lookup_fdinfo (extra, ep, *pos); +} + +static void seq_stop (struct seq_file *m,void *v) { } + +static void *seq_next (struct seq_file *m,void *p,loff_t *pos) +{ +struct proc_fdinfo_extra *extra = m->private; +struct eventpoll *ep = extra->f_file->private_data; + ++*pos; +return (void *)seq_lookup_fdinfo (extra, ep, *pos); +} + +static int seq_show (struct seq_file *m,void *v) +{ +struct epitem_fdinfo *fdinfo = v; +seq_printf (m,"tfd: %8d events: %8x data: %16llx\n" , + fdinfo->fd, fdinfo->ev.events, + (long long )fdinfo->ev.data); +return 0 ; +} + +static const struct seq_operations ep_fdinfo_ops = { + .start = seq_start, + .next = seq_next, + .stop = seq_stop, + .show = seq_show, +}; + +static struct proc_fdinfo_driver ep_fdinfo = { + .name ="eventpoll" , + .ops = &ep_fdinfo_ops, + .probe = is_file_epoll, + .priv_size =sizeof (struct epitem_fdinfo ), +}; + +static int __init ep_register_fdinfo_driver (void ) +{ +return proc_register_fdinfo_driver (&ep_fdinfo); +} +#else +static void ep_register_fdinfo_driver (void ) { } +#endif /* CONFIG_PROC_FS && CONFIG_CHECKPOINT_RESTORE */ +static int __init eventpoll_init (void ) {struct sysinfo si;
@@ -1929,6 +2008,8 @@ static int __init eventpoll_init(void) pwq_cache =kmem_cache_create ("eventpoll_pwq" ,sizeof (struct eppoll_entry ),0 ,SLAB_PANIC ,NULL ); +ep_register_fdinfo_driver (); +return 0 ; }fs_initcall (eventpoll_init);
Re: [rfc 5/7] fs, epoll: Add procfs fdinfo helper
Quoted 47 lines · Cyrill Gorcunov
This allow us to print out eventpoll target file descriptor, events and data, the
/proc/pid/fdinfo/fdconsists of| pos: 0 | flags: 02 | tfd: 5 events: 1d data: ffffffffffffffffThis feature is
CONFIG_CHECKPOINT_RESTOREonly.Signed-off-by Cyrill Gorcunov <[email protected]>CC Al Viro <[email protected]>CC Alexey Dobriyan <[email protected]>CC Andrew Morton <[email protected]>CC Pavel Emelyanov <[email protected]>CC James Bottomley <[email protected]>--- fs/eventpoll.c | 81 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 81 insertions(+)Index:
linux-2.6.git/fs/eventpoll.c
===================================================================fs/eventpoll.c +13
-0@@ -38,6 +38,8 @@#include <asm/io.h> #include <asm/mman.h> #include <linux/atomic.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> /* * LOCKING: @@ -1897,6 +1899,83 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd,return error; } +#if defined(CONFIG_PROC_FS ) && defined(CONFIG_CHECKPOINT_RESTORE ) + +struct epitem_fdinfo { +struct epoll_event ev; +int fd; +}; + +static struct epitem_fdinfo * +seq_lookup_fdinfo (struct proc_fdinfo_extra *extra,struct eventpoll *ep,loff_t num) +{ +struct epitem_fdinfo *fdinfo = extra->priv;
fs/eventpoll.c SYSCALL_DEFINE6(epoll_pwait, int, epfd, · line 1922
Quoted 10 lines
fs/eventpoll.c +10
-0+struct epitem *epi =NULL ; +struct rb_node *rbp; + +mutex_lock (&ep->mtx); +for (rbp =rb_first (&ep->rbr); rbp; rbp =rb_next (rbp)) { +if (num-- ==0 ) { + epi = rb_entry(rbp, struct epitem, rbn); + fdinfo->fd = epi->ffd.fd; + fdinfo->ev = epi->event; +break ;
This will be incredibly slow. epoll was designed to scale to tens of thousands of file descriptors. This algorithm is O(N^2) because each time we show a new epoll item we walk through the whole rb tree again (we're not doing a search so it isn't O(NlogN)).
Also, we could miss one or more later items if one of the earlier items is removed from the epoll set in between "seq_lookup_fdinfo" calls. This isn't a problem for checkpoint because we assume the task (and everything with this eventpoll file in its fd table) is frozen. However it means the file will be worse than useless for almost any other purpose because they are unlikely to realize they need to freeze all the task(s) to get consistent data.
Cheers,
-Matt Helsley
Re: [rfc 5/7] fs, epoll: Add procfs fdinfo helper
Quoted 26 lines · Matthew Helsley
Quoted 25 lines · Cyrill Gorcunov
This allow us to print out eventpoll target file descriptor, events and data, the
/proc/pid/fdinfo/fdconsists of| pos: 0 | flags: 02 | tfd: 5 events: 1d data: fffffffffffffffffs/eventpoll.c +18
-0+#if defined(CONFIG_PROC_FS ) && defined(CONFIG_CHECKPOINT_RESTORE ) + +struct epitem_fdinfo { +struct epoll_event ev; +int fd; +}; + +static struct epitem_fdinfo * +seq_lookup_fdinfo (struct proc_fdinfo_extra *extra,struct eventpoll *ep,loff_t num) +{ +struct epitem_fdinfo *fdinfo = extra->priv; +struct epitem *epi =NULL ; +struct rb_node *rbp; + +mutex_lock (&ep->mtx); +for (rbp =rb_first (&ep->rbr); rbp; rbp =rb_next (rbp)) { +if (num-- ==0 ) { + epi = rb_entry(rbp, struct epitem, rbn);
Quoted 8 lines
fs/eventpoll.c SYSCALL_DEFINE6(epoll_pwait, int, epfd, · line 1922
Quoted 3 lines
fs/eventpoll.c +3
-0+ fdinfo->fd = epi->ffd.fd; + fdinfo->ev = epi->event; +break ;This will be incredibly slow. epoll was designed to scale to tens of thousands of file descriptors. This algorithm is O(N^2) because each time we show a new epoll item we walk through the whole rb tree again (we're not doing a search so it isn't O(NlogN)).
Yeah, I know, it's quadratic. I'll be reworking this series to use immediate seq-printf and print out the whole tree once the appropriate fdinfo file get read.
Quoted 7 lines
Also, we could miss one or more later items if one of the earlier items is removed from the epoll set in between "
seq_lookup_fdinfo" calls. This isn't a problem for checkpoint because we assume the task (and everything with this eventpoll file in its fd table) is frozen. However it means the file will be worse than useless for almost any other purpose because they are unlikely to realize they need to freeze all the task(s) to get consistent data.
Well, a bunch of data read from proc is consistent only at moment of reading.
Cyrill
RFC 6/7 fs, exportfs: Add export_encode_inode_fh helper
In reply to Cyrill GorcunovTo provide fsnotify object inodes being watched without binding to alphabetical path we need to encode them with exportfs help. This patch adds a helper which operates with plain inodes directly.
This feature is CONFIG_CHECKPOINT_RESTORE only.
--- fs/exportfs/expfs.c | 21 +++++++++++++++++++++ include/linux/exportfs.h | 4 ++++ 2 files changed, 25 insertions(+)
fs/exportfs/expfs.c +21 -0
@@ -302,6 +302,27 @@ out:return error; } +#ifdef CONFIG_CHECKPOINT_RESTORE +int export_encode_inode_fh (struct inode *inode,struct fid *fid,int *max_len) +{ +int len = *max_len; +int type =FILEID_INO32_GEN ; + +if (len <2 ) { + *max_len =2 ; +return 255 ; + } + + len =2 ; + fid->i32.ino = inode->i_ino; + fid->i32.gen = inode->i_generation; + *max_len = len; + +return type; +} +EXPORT_SYMBOL_GPL (export_encode_inode_fh); +#endif +/** * export_encode_fh - default export_operations->encode_fh function * @inode: the object to encode
include/linux/exportfs.h +4 -0
@@ -177,6 +177,10 @@ struct export_operations {int (*commit_metadata)(struct inode *inode); }; +#ifdef CONFIG_CHECKPOINT_RESTORE +extern int export_encode_inode_fh (struct inode *inode,struct fid *fid,int *max_len); +#endif +extern int exportfs_encode_fh (struct dentry *dentry,struct fid *fid,int *max_len,int connectable); extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
RFC 7/7 fs, notify: Add procfs fdinfo helper
In reply to Cyrill GorcunovThis allow us to print out fsnotify details such as watchee inode, device, mask and file handle.
For example for inotify objects the output is
| pos: 0 | flags: 02000000 | inotify wd: 3 ino: 9e7e sdev: 800013 mask 800afce ignored_mask 0 fhandle-bytes: 8 fhandle-type: 1 f_handle: 7e9e0000640d1b6d | inotify wd: 2 ino: a111 sdev: 800013 mask 800afce ignored_mask 0 fhandle-bytes: 8 fhandle-type: 1 f_handle: 11a1000020542153 | inotify wd: 1 ino: 6b149 sdev: 800013 mask 800afce ignored_mask 0 fhandle-bytes: 8 fhandle-type: 1 f_handle: 49b1060023552153
For fanotify it is like
| pos: 0 | flags: 02 | fanotify ino: 68f71 sdev: 800013 mask 1 ignored_mask 40000000 fhandle-bytes: 8 fhandle-type: 1 f_handle: 718f0600b9f42053 | fanotify mnt_id: 13 mask 1 ignored_mask 40000000
This feature is CONFIG_CHECKPOINT_RESTORE only. To minimize impact on general fsnotify code the new functionality is gathered in fs/notify/fdinfo.c file mostly.
--- fs/notify/Makefile | 2 fs/notify/fanotify/fanotify_user.c | 17 ++ fs/notify/fdinfo.c | 218 +++++++++++++++++++++++++++++++++++++ fs/notify/fdinfo.h | 19 +++ fs/notify/inotify/inotify_user.c | 32 +++++ 5 files changed, 286 insertions(+), 2 deletions(-)
fs/notify/Makefile +1 -1
@@ -1,5 +1,5 @@ obj-$(CONFIG_FSNOTIFY) += fsnotify.o notification.o group.o inode_mark.o \ - mark.o vfsmount_mark.o + mark.o vfsmount_mark.o fdinfo.o obj-y += dnotify/ obj-y += inotify/
fs/notify/fanotify/fanotify_user.c +16 -1
@@ -17,6 +17,7 @@#include <asm/ioctls.h> #include "../../mount.h" +#include "../fdinfo.h" #define FANOTIFY_DEFAULT_MAX_EVENTS 16384#define FANOTIFY_DEFAULT_MAX_MARKS 8192
@@ -877,6 +878,20 @@ asmlinkage long SyS_fanotify_mark(long fSYSCALL_ALIAS (sys_fanotify_mark, SyS_fanotify_mark);#endif +#if defined(CONFIG_PROC_FS ) && defined(CONFIG_CHECKPOINT_RESTORE ) +int is_file_fanotify (struct file *file) +{ +return file->f_op == &fanotify_fops; +} + +static int __init fanotify_register_fdinfo_driver (void ) +{ +return proc_register_fdinfo_driver (&fanotify_fdinfo); +} +#else +void fanotify_register_fdinfo_driver (void ) { } +#endif /* CONFIG_PROC_FS && CONFIG_CHECKPOINT_RESTORE */ +/* * fanotify_user_setup - Our initialization function. Note that we cannot return * error because we have compiled-in VFS hooks. So an (unlikely) failure here
@@ -887,7 +902,7 @@ static int __init fanotify_user_setup(vo fanotify_mark_cache =KMEM_CACHE (fsnotify_mark,SLAB_PANIC ); fanotify_response_event_cache =KMEM_CACHE (fanotify_response_event,SLAB_PANIC ); - +fanotify_register_fdinfo_driver ();return 0 ; }device_initcall (fanotify_user_setup);
fs/notify/fdinfo.c new file +218 -0
218 lines not on this page · raw message
fs/notify/fdinfo.h new file +19 -0
@@ -0,0 +1,19 @@ +#ifndef __FSNOTIFY_FDINFO_H__ +#define __FSNOTIFY_FDINFO_H__ + +#include <linux/errno.h> +#include <linux/proc_fs.h> + +#if defined(CONFIG_PROC_FS ) && defined(CONFIG_CHECKPOINT_RESTORE ) + +#ifdef CONFIG_INOTIFY_USER +extern struct proc_fdinfo_driver inotify_fdinfo; +#endif + +#ifdef CONFIG_FANOTIFY +extern struct proc_fdinfo_driver fanotify_fdinfo; +#endif + +#endif + +#endif /* __FSNOTIFY_FDINFO_H__ */
fs/notify/inotify/inotify_user.c +32 -0
@@ -38,8 +38,12 @@#include <linux/uaccess.h> #include <linux/poll.h> #include <linux/wait.h> +#include <linux/seq_file.h> +#include <linux/exportfs.h> +#include <linux/proc_fs.h> #include "inotify.h" +#include "../fdinfo.h" #include <asm/ioctls.h>
@@ -827,6 +831,26 @@ out:return ret; } +#if defined(CONFIG_PROC_FS ) && defined(CONFIG_CHECKPOINT_RESTORE ) +int is_file_inotify (struct file *file) +{ +return file->f_op == &inotify_fops; +} + +static int __init inotify_register_fdinfo_driver (void ) +{ +return proc_register_fdinfo_driver (&inotify_fdinfo); +} + +static void __exit inotify_unregister_fdinfo_driver(void) +{ +proc_unregister_fdinfo_driver (&inotify_fdinfo); +} +#else +static int __init inotify_register_fdinfo_driver (void ) {return 0 ; } +static void __exit inotify_unregister_fdinfo_driver(void) { } +#endif /* CONFIG_PROC_FS && CONFIG_CHECKPOINT_RESTORE */ +/* * inotify_user_setup - Our initialization function. Note that we cannot return * error because we have compiled-in VFS hooks. So an (unlikely) failure here
@@ -862,6 +886,14 @@ static int __init inotify_user_setup(voi inotify_max_user_instances =128 ; inotify_max_user_watches =8192 ; +inotify_register_fdinfo_driver (); +return 0 ; }module_init (inotify_user_setup); + +static void __exit inotify_user_exit(void) +{ +inotify_unregister_fdinfo_driver (); +} +module_exit (inotify_user_exit);
Re: [rfc 7/7] fs, notify: Add procfs fdinfo helper
Quoted 3 lines · Cyrill Gorcunov
This allow us to print out fsnotify details such as watchee inode, device, mask and file handle.
A slightly updated version below (I've missed colons in a couple of printk places).
---
From: Cyrill Gorcunov <[email protected]>
Subject: fs, notify: Add procfs fdinfo helper v2
This allow us to print out fsnotify details such as watchee inode, device, mask and file handle.
For example for inotify objects the output is
| pos: 0 | flags: 02000000 | inotify wd: 3 ino: 9e7e sdev: 800013 mask: 800afce ignored_mask: 0 fhandle-bytes: 8 fhandle-type: 1 f_handle: 7e9e0000640d1b6d | inotify wd: 2 ino: a111 sdev: 800013 mask: 800afce ignored_mask: 0 fhandle-bytes: 8 fhandle-type: 1 f_handle: 11a1000020542153 | inotify wd: 1 ino: 6b149 sdev: 800013 mask: 800afce ignored_mask: 0 fhandle-bytes: 8 fhandle-type: 1 f_handle: 49b1060023552153
For fanotify it is like
| pos: 0 | flags: 02 | fanotify ino: 68f71 sdev: 800013 mask: 1 ignored_mask: 40000000 fhandle-bytes: 8 fhandle-type: 1 f_handle: 718f0600b9f42053 | fanotify mnt_id: 13 mask: 1 ignored_mask: 40000000
This feature is CONFIG_CHECKPOINT_RESTORE only. To minimize impact on general fsnotify code the new functionality is gathered in fs/notify/fdinfo.c file mostly.
v2:
- append missing colons to terms
--- fs/notify/Makefile | 2 fs/notify/fanotify/fanotify_user.c | 17 ++ fs/notify/fdinfo.c | 219 +++++++++++++++++++++++++++++++++++++ fs/notify/fdinfo.h | 19 +++ fs/notify/inotify/inotify_user.c | 32 +++++ 5 files changed, 287 insertions(+), 2 deletions(-)
fs/notify/Makefile +1 -1
@@ -1,5 +1,5 @@ obj-$(CONFIG_FSNOTIFY) += fsnotify.o notification.o group.o inode_mark.o \ - mark.o vfsmount_mark.o + mark.o vfsmount_mark.o fdinfo.o obj-y += dnotify/ obj-y += inotify/
fs/notify/fanotify/fanotify_user.c +16 -1
@@ -17,6 +17,7 @@#include <asm/ioctls.h> #include "../../mount.h" +#include "../fdinfo.h" #define FANOTIFY_DEFAULT_MAX_EVENTS 16384#define FANOTIFY_DEFAULT_MAX_MARKS 8192
@@ -877,6 +878,20 @@ asmlinkage long SyS_fanotify_mark(long fSYSCALL_ALIAS (sys_fanotify_mark, SyS_fanotify_mark);#endif +#if defined(CONFIG_PROC_FS ) && defined(CONFIG_CHECKPOINT_RESTORE ) +int is_file_fanotify (struct file *file) +{ +return file->f_op == &fanotify_fops; +} + +static int __init fanotify_register_fdinfo_driver (void ) +{ +return proc_register_fdinfo_driver (&fanotify_fdinfo); +} +#else +void fanotify_register_fdinfo_driver (void ) { } +#endif /* CONFIG_PROC_FS && CONFIG_CHECKPOINT_RESTORE */ +/* * fanotify_user_setup - Our initialization function. Note that we cannot return * error because we have compiled-in VFS hooks. So an (unlikely) failure here
@@ -887,7 +902,7 @@ static int __init fanotify_user_setup(vo fanotify_mark_cache =KMEM_CACHE (fsnotify_mark,SLAB_PANIC ); fanotify_response_event_cache =KMEM_CACHE (fanotify_response_event,SLAB_PANIC ); - +fanotify_register_fdinfo_driver ();return 0 ; }device_initcall (fanotify_user_setup);
fs/notify/fdinfo.c new file +219 -0
219 lines not on this page · raw message
fs/notify/fdinfo.h new file +19 -0
@@ -0,0 +1,19 @@ +#ifndef __FSNOTIFY_FDINFO_H__ +#define __FSNOTIFY_FDINFO_H__ + +#include <linux/errno.h> +#include <linux/proc_fs.h> + +#if defined(CONFIG_PROC_FS ) && defined(CONFIG_CHECKPOINT_RESTORE ) + +#ifdef CONFIG_INOTIFY_USER +extern struct proc_fdinfo_driver inotify_fdinfo; +#endif + +#ifdef CONFIG_FANOTIFY +extern struct proc_fdinfo_driver fanotify_fdinfo; +#endif + +#endif + +#endif /* __FSNOTIFY_FDINFO_H__ */
fs/notify/inotify/inotify_user.c +32 -0
@@ -38,8 +38,12 @@#include <linux/uaccess.h> #include <linux/poll.h> #include <linux/wait.h> +#include <linux/seq_file.h> +#include <linux/exportfs.h> +#include <linux/proc_fs.h> #include "inotify.h" +#include "../fdinfo.h" #include <asm/ioctls.h>
@@ -827,6 +831,26 @@ out:return ret; } +#if defined(CONFIG_PROC_FS ) && defined(CONFIG_CHECKPOINT_RESTORE ) +int is_file_inotify (struct file *file) +{ +return file->f_op == &inotify_fops; +} + +static int __init inotify_register_fdinfo_driver (void ) +{ +return proc_register_fdinfo_driver (&inotify_fdinfo); +} + +static void __exit inotify_unregister_fdinfo_driver(void) +{ +proc_unregister_fdinfo_driver (&inotify_fdinfo); +} +#else +static int __init inotify_register_fdinfo_driver (void ) {return 0 ; } +static void __exit inotify_unregister_fdinfo_driver(void) { } +#endif /* CONFIG_PROC_FS && CONFIG_CHECKPOINT_RESTORE */ +/* * inotify_user_setup - Our initialization function. Note that we cannot return * error because we have compiled-in VFS hooks. So an (unlikely) failure here
@@ -862,6 +886,14 @@ static int __init inotify_user_setup(voi inotify_max_user_instances =128 ; inotify_max_user_watches =8192 ; +inotify_register_fdinfo_driver (); +return 0 ; }module_init (inotify_user_setup); + +static void __exit inotify_user_exit(void) +{ +inotify_unregister_fdinfo_driver (); +} +module_exit (inotify_user_exit);