From faf60af17f8da87e1c87a6be527344791025ce9e Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Thu, 23 Aug 2012 14:43:24 +0400 Subject: 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. Signed-off-by: Cyrill Gorcunov Acked-by: Pavel Emelyanov CC: Al Viro CC: Alexey Dobriyan CC: Andrew Morton CC: James Bottomley CC: "Aneesh Kumar K.V" CC: Alexey Dobriyan CC: Matthew Helsley CC: "J. Bruce Fields" CC: "Aneesh Kumar K.V" Signed-off-by: Al Viro --- 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(-) create mode 100644 fs/proc/fd.c create mode 100644 fs/proc/fd.h (limited to 'fs/proc') diff --git a/fs/proc/Makefile b/fs/proc/Makefile index c1c729335924..99349efbbc2b 100644 --- a/fs/proc/Makefile +++ b/fs/proc/Makefile @@ -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 diff --git a/fs/proc/base.c b/fs/proc/base.c index 1b6c84cbdb73..b55c3bb298e3 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -90,6 +90,7 @@ #endif #include #include "internal.h" +#include "fd.h" /* NOTE: * Implementing inode permission operations in /proc is almost @@ -136,8 +137,6 @@ struct pid_entry { NULL, &proc_single_file_operations, \ { .proc_show = show } ) -static int proc_fd_permission(struct inode *inode, int mask); - /* * Count the number of hardlinks for the pid_entry table, excluding the . * and .. links. @@ -1492,7 +1491,7 @@ out: return error; } -static const struct inode_operations proc_pid_link_inode_operations = { +const struct inode_operations proc_pid_link_inode_operations = { .readlink = proc_pid_readlink, .follow_link = proc_pid_follow_link, .setattr = proc_setattr, @@ -1501,21 +1500,6 @@ static const struct inode_operations proc_pid_link_inode_operations = { /* building an inode */ -static int task_dumpable(struct task_struct *task) -{ - int dumpable = 0; - struct mm_struct *mm; - - task_lock(task); - mm = task->mm; - if (mm) - dumpable = get_dumpable(mm); - task_unlock(task); - if(dumpable == 1) - return 1; - return 0; -} - struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task) { struct inode * inode; @@ -1641,15 +1625,6 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags) return 0; } -static int pid_delete_dentry(const struct dentry * dentry) -{ - /* Is the task we represent dead? - * If so, then don't put the dentry on the lru list, - * kill it immediately. - */ - return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first; -} - const struct dentry_operations pid_dentry_operations = { .d_revalidate = pid_revalidate, @@ -1712,289 +1687,6 @@ end_instantiate: return filldir(dirent, name, len, filp->f_pos, ino, type); } -static unsigned name_to_int(struct dentry *dentry) -{ - const char *name = dentry->d_name.name; - int len = dentry->d_name.len; - unsigned n = 0; - - if (len > 1 && *name == '0') - goto out; - while (len-- > 0) { - unsigned c = *name++ - '0'; - if (c > 9) - goto out; - if (n >= (~0U-9)/10) - goto out; - n *= 10; - n += c; - } - return n; -out: - return ~0U; -} - -#define PROC_FDINFO_MAX 64 - -static int proc_fd_info(struct inode *inode, struct path *path, char *info) -{ - struct task_struct *task = get_proc_task(inode); - struct files_struct *files = NULL; - struct file *file; - int fd = proc_fd(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. - */ - spin_lock(&files->file_lock); - file = fcheck_files(files, fd); - if (file) { - unsigned int f_flags; - struct fdtable *fdt; - - fdt = files_fdtable(files); - f_flags = 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; - } - spin_unlock(&files->file_lock); - put_files_struct(files); - } - return -ENOENT; -} - -static int proc_fd_link(struct dentry *dentry, struct path *path) -{ - return proc_fd_info(dentry->d_inode, path, NULL); -} - -static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) -{ - struct inode *inode; - struct task_struct *task; - int fd; - struct files_struct *files; - const struct cred *cred; - - if (flags & LOOKUP_RCU) - return -ECHILD; - - inode = dentry->d_inode; - task = get_proc_task(inode); - fd = proc_fd(inode); - - if (task) { - files = get_files_struct(task); - if (files) { - struct file *file; - rcu_read_lock(); - file = fcheck_files(files, fd); - if (file) { - unsigned f_mode = file->f_mode; - - rcu_read_unlock(); - put_files_struct(files); - - if (task_dumpable(task)) { - rcu_read_lock(); - cred = __task_cred(task); - inode->i_uid = cred->euid; - inode->i_gid = cred->egid; - rcu_read_unlock(); - } else { - inode->i_uid = GLOBAL_ROOT_UID; - inode->i_gid = GLOBAL_ROOT_GID; - } - - if (S_ISLNK(inode->i_mode)) { - unsigned i_mode = S_IFLNK; - if (f_mode & FMODE_READ) - i_mode |= S_IRUSR | S_IXUSR; - if (f_mode & FMODE_WRITE) - i_mode |= S_IWUSR | S_IXUSR; - inode->i_mode = i_mode; - } - - security_task_to_inode(task, inode); - put_task_struct(task); - return 1; - } - rcu_read_unlock(); - put_files_struct(files); - } - put_task_struct(task); - } - d_drop(dentry); - return 0; -} - -static const struct dentry_operations tid_fd_dentry_operations = -{ - .d_revalidate = tid_fd_revalidate, - .d_delete = pid_delete_dentry, -}; - -static struct dentry *proc_fd_instantiate(struct inode *dir, - struct dentry *dentry, struct task_struct *task, const void *ptr) -{ - unsigned fd = (unsigned long)ptr; - struct inode *inode; - struct proc_inode *ei; - struct dentry *error = ERR_PTR(-ENOENT); - - inode = proc_pid_make_inode(dir->i_sb, task); - if (!inode) - goto out; - ei = PROC_I(inode); - ei->fd = fd; - - inode->i_mode = S_IFLNK; - inode->i_op = &proc_pid_link_inode_operations; - inode->i_size = 64; - ei->op.proc_get_link = proc_fd_link; - d_set_d_op(dentry, &tid_fd_dentry_operations); - d_add(dentry, inode); - /* Close the race of the process dying before we return the dentry */ - if (tid_fd_revalidate(dentry, 0)) - error = NULL; - - out: - return error; -} - -static struct dentry *proc_lookupfd_common(struct inode *dir, - struct dentry *dentry, - instantiate_t instantiate) -{ - struct task_struct *task = get_proc_task(dir); - unsigned fd = name_to_int(dentry); - struct dentry *result = ERR_PTR(-ENOENT); - - if (!task) - goto out_no_task; - if (fd == ~0U) - goto out; - - result = instantiate(dir, dentry, task, (void *)(unsigned long)fd); -out: - put_task_struct(task); -out_no_task: - return result; -} - -static int proc_readfd_common(struct file * filp, void * dirent, - filldir_t filldir, instantiate_t instantiate) -{ - struct dentry *dentry = filp->f_path.dentry; - struct inode *inode = dentry->d_inode; - struct task_struct *p = get_proc_task(inode); - unsigned int fd, ino; - int retval; - struct files_struct * files; - - retval = -ENOENT; - if (!p) - goto out_no_task; - retval = 0; - - fd = filp->f_pos; - switch (fd) { - case 0: - if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0) - goto out; - filp->f_pos++; - case 1: - ino = parent_ino(dentry); - if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0) - goto out; - filp->f_pos++; - default: - files = get_files_struct(p); - if (!files) - goto out; - rcu_read_lock(); - for (fd = filp->f_pos-2; - fd < files_fdtable(files)->max_fds; - fd++, filp->f_pos++) { - char name[PROC_NUMBUF]; - int len; - int rv; - - if (!fcheck_files(files, fd)) - continue; - rcu_read_unlock(); - - len = snprintf(name, sizeof(name), "%d", fd); - rv = proc_fill_cache(filp, dirent, filldir, - name, len, instantiate, p, - (void *)(unsigned long)fd); - if (rv < 0) - goto out_fd_loop; - rcu_read_lock(); - } - rcu_read_unlock(); -out_fd_loop: - put_files_struct(files); - } -out: - put_task_struct(p); -out_no_task: - return retval; -} - -static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry, - unsigned int flags) -{ - return proc_lookupfd_common(dir, dentry, proc_fd_instantiate); -} - -static int proc_readfd(struct file *filp, void *dirent, filldir_t filldir) -{ - return proc_readfd_common(filp, dirent, filldir, proc_fd_instantiate); -} - -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 const struct file_operations proc_fd_operations = { - .read = generic_read_dir, - .readdir = proc_readfd, - .llseek = default_llseek, -}; - #ifdef CONFIG_CHECKPOINT_RESTORE /* @@ -2337,82 +2029,6 @@ static const struct file_operations proc_map_files_operations = { #endif /* CONFIG_CHECKPOINT_RESTORE */ -/* - * /proc/pid/fd needs a special permission handler so that a process can still - * access /proc/self/fd after it has executed a setuid(). - */ -static int proc_fd_permission(struct inode *inode, int mask) -{ - int rv = generic_permission(inode, mask); - if (rv == 0) - return 0; - if (task_pid(current) == proc_pid(inode)) - rv = 0; - return rv; -} - -/* - * proc directories can do almost nothing.. - */ -static const struct inode_operations proc_fd_inode_operations = { - .lookup = proc_lookupfd, - .permission = proc_fd_permission, - .setattr = proc_setattr, -}; - -static struct dentry *proc_fdinfo_instantiate(struct inode *dir, - struct dentry *dentry, struct task_struct *task, const void *ptr) -{ - unsigned fd = (unsigned long)ptr; - struct inode *inode; - struct proc_inode *ei; - struct dentry *error = ERR_PTR(-ENOENT); - - inode = proc_pid_make_inode(dir->i_sb, task); - if (!inode) - goto out; - ei = PROC_I(inode); - ei->fd = fd; - inode->i_mode = S_IFREG | S_IRUSR; - inode->i_fop = &proc_fdinfo_file_operations; - d_set_d_op(dentry, &tid_fd_dentry_operations); - d_add(dentry, inode); - /* Close the race of the process dying before we return the dentry */ - if (tid_fd_revalidate(dentry, 0)) - error = NULL; - - out: - return error; -} - -static struct dentry *proc_lookupfdinfo(struct inode *dir, - struct dentry *dentry, - unsigned int flags) -{ - return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate); -} - -static int proc_readfdinfo(struct file *filp, void *dirent, filldir_t filldir) -{ - return proc_readfd_common(filp, dirent, filldir, - proc_fdinfo_instantiate); -} - -static const struct file_operations proc_fdinfo_operations = { - .read = generic_read_dir, - .readdir = proc_readfdinfo, - .llseek = default_llseek, -}; - -/* - * proc directories can do almost nothing.. - */ -static const struct inode_operations proc_fdinfo_inode_operations = { - .lookup = proc_lookupfdinfo, - .setattr = proc_setattr, -}; - - static struct dentry *proc_pident_instantiate(struct inode *dir, struct dentry *dentry, struct task_struct *task, const void *ptr) { diff --git a/fs/proc/fd.c b/fs/proc/fd.c new file mode 100644 index 000000000000..1b0f932b4bd9 --- /dev/null +++ b/fs/proc/fd.c @@ -0,0 +1,351 @@ +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "internal.h" +#include "fd.h" + +#define PROC_FDINFO_MAX 64 + +static int proc_fd_info(struct inode *inode, struct path *path, char *info) +{ + struct task_struct *task = get_proc_task(inode); + struct files_struct *files = NULL; + int fd = proc_fd(inode); + struct file *file; + + 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. + */ + spin_lock(&files->file_lock); + file = fcheck_files(files, fd); + if (file) { + unsigned int f_flags; + struct fdtable *fdt; + + fdt = files_fdtable(files); + f_flags = 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; + } + spin_unlock(&files->file_lock); + put_files_struct(files); + } + return -ENOENT; +} + +static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) +{ + struct files_struct *files; + struct task_struct *task; + const struct cred *cred; + struct inode *inode; + int fd; + + if (flags & LOOKUP_RCU) + return -ECHILD; + + inode = dentry->d_inode; + task = get_proc_task(inode); + fd = proc_fd(inode); + + if (task) { + files = get_files_struct(task); + if (files) { + struct file *file; + + rcu_read_lock(); + file = fcheck_files(files, fd); + if (file) { + unsigned f_mode = file->f_mode; + + rcu_read_unlock(); + put_files_struct(files); + + if (task_dumpable(task)) { + rcu_read_lock(); + cred = __task_cred(task); + inode->i_uid = cred->euid; + inode->i_gid = cred->egid; + rcu_read_unlock(); + } else { + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + } + + if (S_ISLNK(inode->i_mode)) { + unsigned i_mode = S_IFLNK; + if (f_mode & FMODE_READ) + i_mode |= S_IRUSR | S_IXUSR; + if (f_mode & FMODE_WRITE) + i_mode |= S_IWUSR | S_IXUSR; + inode->i_mode = i_mode; + } + + security_task_to_inode(task, inode); + put_task_struct(task); + return 1; + } + rcu_read_unlock(); + put_files_struct(files); + } + put_task_struct(task); + } + + d_drop(dentry); + return 0; +} + +static const struct dentry_operations tid_fd_dentry_operations = { + .d_revalidate = tid_fd_revalidate, + .d_delete = pid_delete_dentry, +}; + +static int proc_fd_link(struct dentry *dentry, struct path *path) +{ + return proc_fd_info(dentry->d_inode, path, NULL); +} + +static struct dentry * +proc_fd_instantiate(struct inode *dir, struct dentry *dentry, + struct task_struct *task, const void *ptr) +{ + struct dentry *error = ERR_PTR(-ENOENT); + unsigned fd = (unsigned long)ptr; + struct proc_inode *ei; + struct inode *inode; + + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + goto out; + + ei = PROC_I(inode); + ei->fd = fd; + + inode->i_mode = S_IFLNK; + inode->i_op = &proc_pid_link_inode_operations; + inode->i_size = 64; + + ei->op.proc_get_link = proc_fd_link; + + d_set_d_op(dentry, &tid_fd_dentry_operations); + d_add(dentry, inode); + + /* Close the race of the process dying before we return the dentry */ + if (tid_fd_revalidate(dentry, 0)) + error = NULL; + out: + return error; +} + +static struct dentry *proc_lookupfd_common(struct inode *dir, + struct dentry *dentry, + instantiate_t instantiate) +{ + struct task_struct *task = get_proc_task(dir); + struct dentry *result = ERR_PTR(-ENOENT); + unsigned fd = name_to_int(dentry); + + if (!task) + goto out_no_task; + if (fd == ~0U) + goto out; + + result = instantiate(dir, dentry, task, (void *)(unsigned long)fd); +out: + put_task_struct(task); +out_no_task: + return result; +} + +static int proc_readfd_common(struct file * filp, void * dirent, + filldir_t filldir, instantiate_t instantiate) +{ + struct dentry *dentry = filp->f_path.dentry; + struct inode *inode = dentry->d_inode; + struct task_struct *p = get_proc_task(inode); + struct files_struct *files; + unsigned int fd, ino; + int retval; + + retval = -ENOENT; + if (!p) + goto out_no_task; + retval = 0; + + fd = filp->f_pos; + switch (fd) { + case 0: + if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0) + goto out; + filp->f_pos++; + case 1: + ino = parent_ino(dentry); + if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0) + goto out; + filp->f_pos++; + default: + files = get_files_struct(p); + if (!files) + goto out; + rcu_read_lock(); + for (fd = filp->f_pos - 2; + fd < files_fdtable(files)->max_fds; + fd++, filp->f_pos++) { + char name[PROC_NUMBUF]; + int len; + int rv; + + if (!fcheck_files(files, fd)) + continue; + rcu_read_unlock(); + + len = snprintf(name, sizeof(name), "%d", fd); + rv = proc_fill_cache(filp, dirent, filldir, + name, len, instantiate, p, + (void *)(unsigned long)fd); + if (rv < 0) + goto out_fd_loop; + rcu_read_lock(); + } + rcu_read_unlock(); +out_fd_loop: + put_files_struct(files); + } +out: + put_task_struct(p); +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); +} + +const struct file_operations proc_fd_operations = { + .read = generic_read_dir, + .readdir = proc_readfd, + .llseek = default_llseek, +}; + +static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + return proc_lookupfd_common(dir, dentry, proc_fd_instantiate); +} + +/* + * /proc/pid/fd needs a special permission handler so that a process can still + * access /proc/self/fd after it has executed a setuid(). + */ +int proc_fd_permission(struct inode *inode, int mask) +{ + int rv = generic_permission(inode, mask); + if (rv == 0) + return 0; + if (task_pid(current) == proc_pid(inode)) + rv = 0; + return rv; +} + +const struct inode_operations proc_fd_inode_operations = { + .lookup = proc_lookupfd, + .permission = proc_fd_permission, + .setattr = proc_setattr, +}; + +static struct dentry * +proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry, + struct task_struct *task, const void *ptr) +{ + struct dentry *error = ERR_PTR(-ENOENT); + unsigned fd = (unsigned long)ptr; + struct proc_inode *ei; + struct inode *inode; + + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + goto out; + + ei = PROC_I(inode); + ei->fd = fd; + + inode->i_mode = S_IFREG | S_IRUSR; + inode->i_fop = &proc_fdinfo_file_operations; + + d_set_d_op(dentry, &tid_fd_dentry_operations); + d_add(dentry, inode); + + /* Close the race of the process dying before we return the dentry */ + if (tid_fd_revalidate(dentry, 0)) + error = NULL; + out: + return error; +} + +static struct dentry * +proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, unsigned int flags) +{ + return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate); +} + +static int proc_readfdinfo(struct file *filp, void *dirent, filldir_t filldir) +{ + return proc_readfd_common(filp, dirent, filldir, + proc_fdinfo_instantiate); +} + +const struct inode_operations proc_fdinfo_inode_operations = { + .lookup = proc_lookupfdinfo, + .setattr = proc_setattr, +}; + +const struct file_operations proc_fdinfo_operations = { + .read = generic_read_dir, + .readdir = proc_readfdinfo, + .llseek = default_llseek, +}; diff --git a/fs/proc/fd.h b/fs/proc/fd.h new file mode 100644 index 000000000000..cbb1d47deda8 --- /dev/null +++ b/fs/proc/fd.h @@ -0,0 +1,14 @@ +#ifndef __PROCFS_FD_H__ +#define __PROCFS_FD_H__ + +#include + +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__ */ diff --git a/fs/proc/internal.h b/fs/proc/internal.h index e1167a1c9126..67925a7bd8cb 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -9,6 +9,7 @@ * 2 of the License, or (at your option) any later version. */ +#include #include struct ctl_table_header; @@ -65,6 +66,7 @@ extern const struct file_operations proc_clear_refs_operations; extern const struct file_operations proc_pagemap_operations; extern const struct file_operations proc_net_operations; extern const struct inode_operations proc_net_inode_operations; +extern const struct inode_operations proc_pid_link_inode_operations; struct proc_maps_private { struct pid *pid; @@ -91,6 +93,52 @@ static inline int proc_fd(struct inode *inode) return PROC_I(inode)->fd; } +static inline int task_dumpable(struct task_struct *task) +{ + int dumpable = 0; + struct mm_struct *mm; + + task_lock(task); + mm = task->mm; + if (mm) + dumpable = get_dumpable(mm); + task_unlock(task); + if(dumpable == 1) + return 1; + return 0; +} + +static inline int pid_delete_dentry(const struct dentry * dentry) +{ + /* Is the task we represent dead? + * If so, then don't put the dentry on the lru list, + * kill it immediately. + */ + return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first; +} + +static inline unsigned name_to_int(struct dentry *dentry) +{ + const char *name = dentry->d_name.name; + int len = dentry->d_name.len; + unsigned n = 0; + + if (len > 1 && *name == '0') + goto out; + while (len-- > 0) { + unsigned c = *name++ - '0'; + if (c > 9) + goto out; + if (n >= (~0U-9)/10) + goto out; + n *= 10; + n += c; + } + return n; +out: + return ~0U; +} + struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *ino, struct dentry *dentry); int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent, -- cgit v1.2.3-58-ga151 From ddd3e0771bc7b869c550687c204e21f0155d5496 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Sun, 26 Aug 2012 18:28:20 +0400 Subject: procfs: Convert /proc/pid/fdinfo/ handling routines to seq-file v2 This 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. Note the proc_fd_link no longer call for proc_fd_info, simply because the guts of proc_fd_info() got merged into ->show() of that seq_file Signed-off-by: Al Viro --- fs/proc/fd.c | 112 ++++++++++++++++++++++++++++++++++------------------------- 1 file changed, 64 insertions(+), 48 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 1b0f932b4bd9..9cef449c0f76 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -6,61 +6,68 @@ #include #include #include +#include +#include #include #include "internal.h" #include "fd.h" -#define PROC_FDINFO_MAX 64 - -static int proc_fd_info(struct inode *inode, struct path *path, char *info) +static int seq_show(struct seq_file *m, void *v) { - struct task_struct *task = get_proc_task(inode); struct files_struct *files = NULL; - int fd = proc_fd(inode); - struct file *file; + int f_flags = 0, ret = -ENOENT; + struct file *file = NULL; + struct task_struct *task; + + task = get_proc_task(m->private); + if (!task) + return -ENOENT; + + files = get_files_struct(task); + put_task_struct(task); - 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(m->private); + spin_lock(&files->file_lock); file = fcheck_files(files, fd); if (file) { - unsigned int f_flags; - struct fdtable *fdt; + struct fdtable *fdt = files_fdtable(files); - fdt = files_fdtable(files); f_flags = 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; + get_file(file); + ret = 0; } spin_unlock(&files->file_lock); put_files_struct(files); } - return -ENOENT; + + if (!ret) { + seq_printf(m, "pos:\t%lli\nflags:\t0%o\n", + (long long)file->f_pos, f_flags); + fput(file); + } + + return ret; } +static int seq_fdinfo_open(struct inode *inode, struct file *file) +{ + return single_open(file, seq_show, inode); +} + +static const struct file_operations proc_fdinfo_file_operations = { + .open = seq_fdinfo_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) { struct files_struct *files; @@ -130,7 +137,32 @@ static const struct dentry_operations tid_fd_dentry_operations = { static int proc_fd_link(struct dentry *dentry, struct path *path) { - return proc_fd_info(dentry->d_inode, path, NULL); + struct files_struct *files = NULL; + struct task_struct *task; + int ret = -ENOENT; + + task = get_proc_task(dentry->d_inode); + if (task) { + files = get_files_struct(task); + put_task_struct(task); + } + + if (files) { + int fd = proc_fd(dentry->d_inode); + struct file *fd_file; + + spin_lock(&files->file_lock); + fd_file = fcheck_files(files, fd); + if (fd_file) { + *path = fd_file->f_path; + path_get(&fd_file->f_path); + ret = 0; + } + spin_unlock(&files->file_lock); + put_files_struct(files); + } + + return ret; } static struct dentry * @@ -245,22 +277,6 @@ 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); -- cgit v1.2.3-58-ga151 From c6f3d81115989e274c42a852222b80d2e14ced6f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 26 Aug 2012 11:01:04 -0400 Subject: don't leak O_CLOEXEC into ->f_flags Signed-off-by: Al Viro --- fs/open.c | 2 +- fs/proc/fd.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/proc') diff --git a/fs/open.c b/fs/open.c index 30760017deed..03028d0e7487 100644 --- a/fs/open.c +++ b/fs/open.c @@ -814,7 +814,7 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o op->mode = 0; /* Must never be set by userspace */ - flags &= ~FMODE_NONOTIFY; + flags &= ~FMODE_NONOTIFY & ~O_CLOEXEC; /* * O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 9cef449c0f76..f28a875f8779 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -36,7 +36,7 @@ static int seq_show(struct seq_file *m, void *v) if (file) { struct fdtable *fdt = files_fdtable(files); - f_flags = file->f_flags & ~O_CLOEXEC; + f_flags = file->f_flags; if (close_on_exec(fd, fdt)) f_flags |= O_CLOEXEC; -- cgit v1.2.3-58-ga151 From cb0942b81249798e15c3f04eee2946ef543e8115 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 27 Aug 2012 14:48:26 -0400 Subject: make get_file() return its argument simplifies a bunch of callers... Signed-off-by: Al Viro --- arch/ia64/kernel/perfmon.c | 4 +--- drivers/base/dma-buf.c | 3 +-- drivers/staging/omapdrm/omap_gem.c | 3 +-- drivers/tty/tty_io.c | 9 +++------ fs/autofs4/waitq.c | 3 +-- fs/fuse/dev.c | 3 +-- fs/nfsd/nfs4state.c | 3 +-- fs/proc/base.c | 3 +-- fs/select.c | 3 +-- include/linux/fs.h | 6 +++++- mm/fremap.c | 3 +-- mm/mmap.c | 3 +-- mm/nommu.c | 6 ++---- net/compat.c | 3 +-- net/core/scm.c | 3 +-- security/selinux/hooks.c | 3 +-- 16 files changed, 23 insertions(+), 38 deletions(-) (limited to 'fs/proc') diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 79826c13b8b6..ff5d4e4c3733 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2306,7 +2306,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t * partially initialize the vma for the sampling buffer */ vma->vm_mm = mm; - vma->vm_file = filp; + vma->vm_file = get_file(filp); vma->vm_flags = VM_READ| VM_MAYREAD |VM_RESERVED; vma->vm_page_prot = PAGE_READONLY; /* XXX may need to change */ @@ -2345,8 +2345,6 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t goto error; } - get_file(filp); - /* * now insert the vma in the vm list for the process, must be * done with mmap lock held diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c index c30f3e1d0efc..460e22dee36d 100644 --- a/drivers/base/dma-buf.c +++ b/drivers/base/dma-buf.c @@ -460,8 +460,7 @@ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma, if (vma->vm_file) fput(vma->vm_file); - vma->vm_file = dmabuf->file; - get_file(vma->vm_file); + vma->vm_file = get_file(dmabuf->file); vma->vm_pgoff = pgoff; diff --git a/drivers/staging/omapdrm/omap_gem.c b/drivers/staging/omapdrm/omap_gem.c index 3a0d035a9e03..2a6bb7f9ee68 100644 --- a/drivers/staging/omapdrm/omap_gem.c +++ b/drivers/staging/omapdrm/omap_gem.c @@ -566,9 +566,8 @@ int omap_gem_mmap_obj(struct drm_gem_object *obj, * in particular in the case of mmap'd dmabufs) */ fput(vma->vm_file); - get_file(obj->filp); vma->vm_pgoff = 0; - vma->vm_file = obj->filp; + vma->vm_file = get_file(obj->filp); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); } diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 71d95cfbabec..c7561f29d894 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -1163,10 +1163,8 @@ ssize_t redirected_tty_write(struct file *file, const char __user *buf, struct file *p = NULL; spin_lock(&redirect_lock); - if (redirect) { - get_file(redirect); - p = redirect; - } + if (redirect) + p = get_file(redirect); spin_unlock(&redirect_lock); if (p) { @@ -2246,8 +2244,7 @@ static int tioccons(struct file *file) spin_unlock(&redirect_lock); return -EBUSY; } - get_file(file); - redirect = file; + redirect = get_file(file); spin_unlock(&redirect_lock); return 0; } diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index da8876d38a7b..dce436e595c1 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -175,8 +175,7 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, return; } - pipe = sbi->pipe; - get_file(pipe); + pipe = get_file(sbi->pipe); mutex_unlock(&sbi->wq_mutex); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index f4246cfc8d87..8c23fa7a91e6 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -148,8 +148,7 @@ static struct fuse_req *get_reserved_req(struct fuse_conn *fc, if (ff->reserved_req) { req = ff->reserved_req; ff->reserved_req = NULL; - get_file(file); - req->stolen_file = file; + req->stolen_file = get_file(file); } spin_unlock(&fc->lock); } while (!req); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index cc894eda385a..48a1bad37334 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2837,8 +2837,7 @@ static int nfs4_setlease(struct nfs4_delegation *dp, int flag) return -ENOMEM; } fp->fi_lease = fl; - fp->fi_deleg_file = fl->fl_file; - get_file(fp->fi_deleg_file); + fp->fi_deleg_file = get_file(fl->fl_file); atomic_set(&fp->fi_delegees, 1); list_add(&dp->dl_perfile, &fp->fi_delegations); return 0; diff --git a/fs/proc/base.c b/fs/proc/base.c index b55c3bb298e3..f1e8438d21b5 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1979,8 +1979,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) if (++pos <= filp->f_pos) continue; - get_file(vma->vm_file); - info.file = vma->vm_file; + info.file = get_file(vma->vm_file); info.len = snprintf(info.name, sizeof(info.name), "%lx-%lx", vma->vm_start, vma->vm_end); diff --git a/fs/select.c b/fs/select.c index db14c781335e..ffdd16d6e691 100644 --- a/fs/select.c +++ b/fs/select.c @@ -220,8 +220,7 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, struct poll_table_entry *entry = poll_get_entry(pwq); if (!entry) return; - get_file(filp); - entry->filp = filp; + entry->filp = get_file(filp); entry->wait_address = wait_address; entry->key = p->_key; init_waitqueue_func_entry(&entry->wait, pollwake); diff --git a/include/linux/fs.h b/include/linux/fs.h index aa110476a95b..de1db1c12080 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1074,7 +1074,11 @@ struct file_handle { unsigned char f_handle[0]; }; -#define get_file(x) atomic_long_inc(&(x)->f_count) +static inline struct file *get_file(struct file *f) +{ + atomic_long_inc(&f->f_count); + return f; +} #define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1) #define file_count(x) atomic_long_read(&(x)->f_count) diff --git a/mm/fremap.c b/mm/fremap.c index 9ed4fd432467..048659c0c03d 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -195,10 +195,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, */ if (mapping_cap_account_dirty(mapping)) { unsigned long addr; - struct file *file = vma->vm_file; + struct file *file = get_file(vma->vm_file); flags &= MAP_NONBLOCK; - get_file(file); addr = mmap_region(file, start, size, flags, vma->vm_flags, pgoff); fput(file); diff --git a/mm/mmap.c b/mm/mmap.c index ae18a48e7e4e..872441e81914 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1301,8 +1301,7 @@ munmap_back: goto free_vma; correct_wcount = 1; } - vma->vm_file = file; - get_file(file); + vma->vm_file = get_file(file); error = file->f_op->mmap(file, vma); if (error) goto unmap_and_free_vma; diff --git a/mm/nommu.c b/mm/nommu.c index d4b0c10872de..dee2ff89fd58 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1282,10 +1282,8 @@ unsigned long do_mmap_pgoff(struct file *file, vma->vm_pgoff = pgoff; if (file) { - region->vm_file = file; - get_file(file); - vma->vm_file = file; - get_file(file); + region->vm_file = get_file(file); + vma->vm_file = get_file(file); if (vm_flags & VM_EXECUTABLE) { added_exe_file_vma(current->mm); vma->vm_mm = current->mm; diff --git a/net/compat.c b/net/compat.c index 74ed1d7a84a2..79ae88485001 100644 --- a/net/compat.c +++ b/net/compat.c @@ -301,8 +301,7 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm) break; } /* Bump the usage count and install the file. */ - get_file(fp[i]); - fd_install(new_fd, fp[i]); + fd_install(new_fd, get_file(fp[i])); } if (i > 0) { diff --git a/net/core/scm.c b/net/core/scm.c index 040cebeed45b..b0098d259233 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -281,11 +281,10 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) break; } /* Bump the usage count and install the file. */ - get_file(fp[i]); sock = sock_from_file(fp[i], &err); if (sock) sock_update_netprioidx(sock->sk, current); - fd_install(new_fd, fp[i]); + fd_install(new_fd, get_file(fp[i])); } if (i > 0) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 4dfbcea10eb7..651d8456611a 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2135,8 +2135,7 @@ static inline void flush_unauthorized_files(const struct cred *cred, if (!IS_ERR(devnull)) { /* replace all the matching ones with this */ do { - get_file(devnull); - replace_fd(n - 1, devnull, 0); + replace_fd(n - 1, get_file(devnull), 0); } while ((n = iterate_fd(files, n, match_file, cred)) != 0); fput(devnull); } else { -- cgit v1.2.3-58-ga151 From 7b540d0646ce122f0ba4520412be91e530719742 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 27 Aug 2012 14:55:26 -0400 Subject: proc_map_files_readdir(): don't bother with grabbing files all we need is their ->f_mode, so just collect _that_ Signed-off-by: Al Viro --- fs/proc/base.c | 28 +++++++++------------------- 1 file changed, 9 insertions(+), 19 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/base.c b/fs/proc/base.c index f1e8438d21b5..df18db61d6d8 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1805,7 +1805,7 @@ out: } struct map_files_info { - struct file *file; + fmode_t mode; unsigned long len; unsigned char name[4*sizeof(long)+2]; /* max: %lx-%lx\0 */ }; @@ -1814,13 +1814,10 @@ static struct dentry * proc_map_files_instantiate(struct inode *dir, struct dentry *dentry, struct task_struct *task, const void *ptr) { - const struct file *file = ptr; + fmode_t mode = (fmode_t)(unsigned long)ptr; struct proc_inode *ei; struct inode *inode; - if (!file) - return ERR_PTR(-ENOENT); - inode = proc_pid_make_inode(dir->i_sb, task); if (!inode) return ERR_PTR(-ENOENT); @@ -1832,9 +1829,9 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry, inode->i_size = 64; inode->i_mode = S_IFLNK; - if (file->f_mode & FMODE_READ) + if (mode & FMODE_READ) inode->i_mode |= S_IRUSR; - if (file->f_mode & FMODE_WRITE) + if (mode & FMODE_WRITE) inode->i_mode |= S_IWUSR; d_set_d_op(dentry, &tid_map_files_dentry_operations); @@ -1878,7 +1875,8 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, if (!vma) goto out_no_vma; - result = proc_map_files_instantiate(dir, dentry, task, vma->vm_file); + result = proc_map_files_instantiate(dir, dentry, task, + (void *)(unsigned long)vma->vm_file->f_mode); out_no_vma: up_read(&mm->mmap_sem); @@ -1979,7 +1977,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) if (++pos <= filp->f_pos) continue; - info.file = get_file(vma->vm_file); + info.mode = vma->vm_file->f_mode; info.len = snprintf(info.name, sizeof(info.name), "%lx-%lx", vma->vm_start, vma->vm_end); @@ -1994,19 +1992,11 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) ret = proc_fill_cache(filp, dirent, filldir, p->name, p->len, proc_map_files_instantiate, - task, p->file); + task, + (void *)(unsigned long)p->mode); if (ret) break; filp->f_pos++; - fput(p->file); - } - for (; i < nr_files; i++) { - /* - * In case of error don't forget - * to put rest of file refs. - */ - p = flex_array_get(fa, i); - fput(p->file); } if (fa) flex_array_free(fa); -- cgit v1.2.3-58-ga151