Providing additional information in fdinfo sufficient for c/r, v2
Subsystems (6)
cover Providing additional information in fdinfo sufficient for c/r, v2
Hi guys, here is an updated series for fdinfo. I've shrunk the buffer attached to inotify mark and updated the changelog for it (still wonder if there some document in Documentation/ which should be updated as well), the signalfd was fixed too. Please review, I tried to address all complains I've got so far, ping me if I missed something please.
Cyrill
PATCH 1/7 procfs: Add ability to plug in auxiliary fdinfo providers
This patch brings ability to print out auxiliary data associated with file in procfs interface /proc/pid/fdinfo/fd.
In particular further patches make eventfd, evenpoll, signalfd and fsnotify to print additional information complete enough to restore these objects after checkpoint.
To simplify the code we add show_fdinfo callback inside struct file_operations (as Al and Pavel are proposing).
--- fs/proc/fd.c | 2 ++ include/linux/fs.h | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-)
fs/proc/fd.c +2 -0
@@ -50,6 +50,8 @@ static int seq_show(struct seq_file *m,if (!ret) {seq_printf (m,"pos:\t%lli\nflags:\t0%o\n" , (long long )file->f_pos, f_flags); +if (file->f_op->show_fdinfo) + ret = file->f_op->show_fdinfo (m, file);fput (file); }
include/linux/fs.h +2 -2
@@ -44,6 +44,7 @@ struct vm_area_struct;struct vfsmount ;struct cred ;struct swap_info_struct ; +struct seq_file ;extern void __init inode_init (void );extern void __init inode_init_early (void );
@@ -1545,6 +1546,7 @@ struct file_operations {int (*setlease)(struct file *,long ,struct file_lock **);long (*fallocate)(struct file *file,int mode,loff_t offset,loff_t len); +int (*show_fdinfo)(struct seq_file *m,struct file *f); };struct inode_operations {
@@ -1580,8 +1582,6 @@ struct inode_operations { umode_t create_mode, int *opened); }____cacheline_aligned ; -struct seq_file ; - ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer,
PATCH 2/7 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
--- fs/eventfd.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+)
fs/eventfd.c +20 -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;
@@ -284,7 +286,25 @@ static ssize_t eventfd_write(struct filereturn res; } +#ifdef CONFIG_PROC_FS +static int eventfd_show_fdinfo (struct seq_file *m,struct file *f) +{ +struct eventfd_ctx *ctx = f->private_data; +int ret; + +spin_lock_irq (&ctx->wqh.lock); + ret =seq_printf (m,"eventfd-count: %16llx\n" , + (unsigned long long )ctx->count); +spin_unlock_irq (&ctx->wqh.lock); + +return ret; +} +#endif +static const struct file_operations eventfd_fops = { +#ifdef CONFIG_PROC_FS + .show_fdinfo = eventfd_show_fdinfo, +#endif .release = eventfd_release, .poll = eventfd_poll, .read = eventfd_read,
PATCH 3/7 fs, epoll: Add procfs fdinfo helper v2
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 enabled: 1
[avagin@: fix for unitialized ret variable]
--- fs/eventpoll.c | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+)
fs/eventpoll.c +29 -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:
@@ -783,8 +785,35 @@ static unsigned int ep_eventpoll_poll(streturn pollflags !=-1 ? pollflags :0 ; } +#ifdef CONFIG_PROC_FS +static int ep_show_fdinfo (struct seq_file *m,struct file *f) +{ +struct eventpoll *ep = f->private_data; +struct rb_node *rbp; +int ret =0 ; + +mutex_lock (&ep->mtx); +for (rbp =rb_first (&ep->rbr); rbp; rbp =rb_next (rbp)) { + struct epitem *epi = rb_entry(rbp, struct epitem, rbn); + + ret =seq_printf (m,"tfd: %8d events: %8x data: %16llx enabled: %d\n" , + epi->ffd.fd, epi->event.events, + (long long )epi->event.data, +ep_is_linked (&epi->rdllink)); +if (ret) +break ; + } +mutex_unlock (&ep->mtx); + +return ret; +} +#endif +/* File callbacks that implement the eventpoll file behaviour */ static const struct file_operations eventpoll_fops = { +#ifdef CONFIG_PROC_FS + .show_fdinfo = ep_show_fdinfo, +#endif .release = ep_eventpoll_release, .poll = ep_eventpoll_poll, .llseek = noop_llseek,
PATCH 4/7 fs, exportfs: Escape nil dereference if no s_export_op present
In reply to Cyrill GorcunovThis routine will be used to generate a file handle in fdinfo output for inotify subsystem, where if no s_export_op present the general export_encode_fh should be used. Thus add a test if s_export_op present inside exportfs_encode_fh itself.
--- fs/exportfs/expfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
fs/exportfs/expfs.c +1 -1
@@ -357,7 +357,7 @@ int exportfs_encode_fh(struct dentry *de*/ parent = p->d_inode; } -if (nop->encode_fh) +if (nop && nop->encode_fh) error = nop->encode_fh (inode, fid->raw, max_len, parent);else error =export_encode_fh (inode, fid, max_len, parent);
PATCH 5/7 fdinfo: Show sigmask for signalfd fd v3
In reply to Cyrill GorcunovThe sigmask is read in lockless manner for a sake of code simplicity, thus if precise data needed here the tasks which refer to the signalfd should be stopped before read.
--- fs/proc/array.c | 2 +- fs/signalfd.c | 18 ++++++++++++++++++ include/linux/proc_fs.h | 3 +++ 3 files changed, 22 insertions(+), 1 deletion(-)
fs/proc/array.c +1 -1
@@ -220,7 +220,7 @@ static inline void task_state(struct seqseq_putc (m,'\n' ); } -static void render_sigset_t (struct seq_file *m,const char *header, +void render_sigset_t (struct seq_file *m,const char *header,sigset_t *set) {int i;
fs/signalfd.c +18 -0
@@ -29,6 +29,7 @@#include <linux/anon_inodes.h> #include <linux/signalfd.h> #include <linux/syscalls.h> +#include <linux/proc_fs.h> void signalfd_cleanup (struct sighand_struct *sighand) {
@@ -227,7 +228,24 @@ static ssize_t signalfd_read(struct filereturn total ? total: ret; } +#ifdef CONFIG_PROC_FS +static int signalfd_show_fdinfo (struct seq_file *m,struct file *f) +{ +struct signalfd_ctx *ctx = f->private_data; +sigset_t sigmask; + + sigmask = ctx->sigmask; +signotset (&sigmask); +render_sigset_t (m,"sigmask:\t" , &sigmask); + +return 0 ; +} +#endif +static const struct file_operations signalfd_fops = { +#ifdef CONFIG_PROC_FS + .show_fdinfo = signalfd_show_fdinfo, +#endif .release = signalfd_release, .poll = signalfd_poll, .read = signalfd_read,
include/linux/proc_fs.h +3 -0
@@ -290,4 +290,7 @@ static inline struct net *PDE_NET(struct return pde->parent->data; } +#include <linux/signal.h> + +void render_sigset_t (struct seq_file *m,const char *header,sigset_t *set);#endif /* _LINUX_PROC_FS_H */
PATCH 6/7 fs, notify: Add file handle entry into inotify_inode_mark v2
In reply to Cyrill GorcunovThis file handle will be provided as auxiliay information associated with the file descriptor in /proc/pid/fdinfo/fd output.
The file handle is needed in a sake of C/R becasue it provides back to a userspace information sufficient for opening the target file on restore procedure.
As a minimum size of the file handle storage the 64 bytes chosen since it's the value the nfs3 is uses at moment. Still, if there no room left in a buffer carried with the mark, we yield a warning but don't fail, because the inotify system doesn't depend on file handle at all and can continue working without problems.
The reason for this patch is that on restore we need to reconstruct the path to the watched target and use inotify_add_watch() syscall then.
This feature is CONFIG_CHECKPOINT_RESTORE only.
v2:
- shrink the buffer down to 64 bytes
- declare fhandle as a structure and align it
- don't fail to add a watch descriptor if buffer is too small to carry the fhandle
--- fs/notify/inotify/inotify.h | 11 +++++++++ fs/notify/inotify/inotify_user.c | 46 ++++++++++++++++++++++++++++++++++----- 2 files changed, 52 insertions(+), 5 deletions(-)
fs/notify/inotify/inotify.h +11 -0
@@ -1,6 +1,7 @@#include <linux/fsnotify_backend.h> #include <linux/inotify.h> #include <linux/slab.h> /* struct kmem_cache */ +#include <linux/exportfs.h> extern struct kmem_cache *event_priv_cachep;
@@ -9,9 +10,19 @@ struct inotify_event_private_data {int wd; }; +#if defined(CONFIG_PROC_FS ) && defined(CONFIG_EXPORTFS ) && defined(CONFIG_CHECKPOINT_RESTORE ) +# define INOTIFY_USE_FHANDLE +#endif +struct inotify_inode_mark {struct fsnotify_mark fsn_mark;int wd; +#ifdef INOTIFY_USE_FHANDLE +struct { +struct file_handle handle; +u8 pad[64 ]; + }__aligned(8) fh; +#endif }; extern void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
fs/notify/inotify/inotify_user.c +41 -5
86 lines not on this page · raw message
PATCH 7/7 fs, notify: Add procfs fdinfo helper v5
In reply to Cyrill GorcunovThis allow us to print out fsnotify details such as watchee inode, device, mask and optionally a file handle.
For inotify objects if kernel compiled with exportfs support the output will be
| 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
If kernel compiled without exportfs support, the file handle won't be provided but inode and device only.
| pos: 0 | flags: 02000000 | inotify wd: 3 ino: 9e7e sdev: 800013 mask: 800afce ignored_mask: 0 | inotify wd: 2 ino: a111 sdev: 800013 mask: 800afce ignored_mask: 0 | inotify wd: 1 ino: 6b149 sdev: 800013 mask: 800afce ignored_mask: 0
For fanotify the output is like
| pos: 0 | flags: 02 | fanotify ino: 68f71 sdev: 800013 mask: 1 ignored_mask: 40000000 | fanotify mnt_id: 13 mask: 1 ignored_mask: 40000000
To minimize impact on general fsnotify code the new functionality is gathered in fs/notify/fdinfo.c file.
--- fs/notify/Makefile | 2 fs/notify/fanotify/fanotify_user.c | 2 fs/notify/fdinfo.c | 129 +++++++++++++++++++++++++++++++++++++ fs/notify/fdinfo.h | 22 ++++++ fs/notify/inotify/inotify_user.c | 2 5 files changed, 156 insertions(+), 1 deletion(-)
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 +2 -0
@@ -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
@@ -427,6 +428,7 @@ static long fanotify_ioctl(struct file * }static const struct file_operations fanotify_fops = { + .show_fdinfo = fanotify_show_fdinfo, .poll = fanotify_poll, .read = fanotify_read, .write = fanotify_write,
fs/notify/fdinfo.c new file +129 -0
129 lines not on this page · raw message
fs/notify/fdinfo.h new file +22 -0
@@ -0,0 +1,22 @@ +#ifndef __FSNOTIFY_FDINFO_H__ +#define __FSNOTIFY_FDINFO_H__ + +#include <linux/errno.h> +#include <linux/proc_fs.h> + +struct seq_file ; +struct file ; + +#ifdef CONFIG_PROC_FS + +#ifdef CONFIG_INOTIFY_USER +extern int inotify_show_fdinfo (struct seq_file *m,struct file *f); +#endif + +#ifdef CONFIG_FANOTIFY +extern int fanotify_show_fdinfo (struct seq_file *m,struct file *f); +#endif + +#endif /* CONFIG_PROC_FS */ + +#endif /* __FSNOTIFY_FDINFO_H__ */
fs/notify/inotify/inotify_user.c +2 -0
@@ -40,6 +40,7 @@#include <linux/wait.h> #include "inotify.h" +#include "../fdinfo.h" #include <asm/ioctls.h>
@@ -335,6 +336,7 @@ static long inotify_ioctl(struct file *f }static const struct file_operations inotify_fops = { + .show_fdinfo = inotify_show_fdinfo, .poll = inotify_poll, .read = inotify_read, .fasync = inotify_fasync,