diff options
Diffstat (limited to 'fs/proc')
-rw-r--r-- | fs/proc/array.c | 118 | ||||
-rw-r--r-- | fs/proc/base.c | 194 | ||||
-rw-r--r-- | fs/proc/cmdline.c | 17 | ||||
-rw-r--r-- | fs/proc/consoles.c | 14 | ||||
-rw-r--r-- | fs/proc/devices.c | 14 | ||||
-rw-r--r-- | fs/proc/fd.c | 138 | ||||
-rw-r--r-- | fs/proc/generic.c | 252 | ||||
-rw-r--r-- | fs/proc/inode.c | 67 | ||||
-rw-r--r-- | fs/proc/internal.h | 37 | ||||
-rw-r--r-- | fs/proc/interrupts.c | 14 | ||||
-rw-r--r-- | fs/proc/kcore.c | 23 | ||||
-rw-r--r-- | fs/proc/loadavg.c | 16 | ||||
-rw-r--r-- | fs/proc/meminfo.c | 29 | ||||
-rw-r--r-- | fs/proc/namespaces.c | 24 | ||||
-rw-r--r-- | fs/proc/nommu.c | 14 | ||||
-rw-r--r-- | fs/proc/proc_net.c | 113 | ||||
-rw-r--r-- | fs/proc/proc_sysctl.c | 29 | ||||
-rw-r--r-- | fs/proc/proc_tty.c | 22 | ||||
-rw-r--r-- | fs/proc/root.c | 21 | ||||
-rw-r--r-- | fs/proc/self.c | 4 | ||||
-rw-r--r-- | fs/proc/softirqs.c | 14 | ||||
-rw-r--r-- | fs/proc/task_mmu.c | 163 | ||||
-rw-r--r-- | fs/proc/thread_self.c | 4 | ||||
-rw-r--r-- | fs/proc/uptime.c | 14 | ||||
-rw-r--r-- | fs/proc/version.c | 14 |
25 files changed, 701 insertions, 668 deletions
diff --git a/fs/proc/array.c b/fs/proc/array.c index 598803576e4c..004077f1a7bf 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -85,6 +85,7 @@ #include <linux/delayacct.h> #include <linux/seq_file.h> #include <linux/pid_namespace.h> +#include <linux/prctl.h> #include <linux/ptrace.h> #include <linux/tracehook.h> #include <linux/string_helpers.h> @@ -95,22 +96,29 @@ #include <asm/processor.h> #include "internal.h" -static inline void task_name(struct seq_file *m, struct task_struct *p) +void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape) { char *buf; size_t size; - char tcomm[sizeof(p->comm)]; + char tcomm[64]; int ret; - get_task_comm(tcomm, p); - - seq_puts(m, "Name:\t"); + if (p->flags & PF_WQ_WORKER) + wq_worker_comm(tcomm, sizeof(tcomm), p); + else + __get_task_comm(tcomm, sizeof(tcomm), p); size = seq_get_buf(m, &buf); - ret = string_escape_str(tcomm, buf, size, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); - seq_commit(m, ret < size ? ret : -1); + if (escape) { + ret = string_escape_str(tcomm, buf, size, + ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\"); + if (ret >= size) + ret = -1; + } else { + ret = strscpy(buf, tcomm, size); + } - seq_putc(m, '\n'); + seq_commit(m, ret); } /* @@ -141,25 +149,12 @@ static inline const char *get_task_state(struct task_struct *tsk) return task_state_array[task_state_index(tsk)]; } -static inline int get_task_umask(struct task_struct *tsk) -{ - struct fs_struct *fs; - int umask = -ENOENT; - - task_lock(tsk); - fs = tsk->fs; - if (fs) - umask = fs->umask; - task_unlock(tsk); - return umask; -} - static inline void task_state(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *p) { struct user_namespace *user_ns = seq_user_ns(m); struct group_info *group_info; - int g, umask; + int g, umask = -1; struct task_struct *tracer; const struct cred *cred; pid_t ppid, tpid = 0, tgid, ngid; @@ -177,17 +172,18 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, ngid = task_numa_group_id(p); cred = get_task_cred(p); - umask = get_task_umask(p); - if (umask >= 0) - seq_printf(m, "Umask:\t%#04o\n", umask); - task_lock(p); + if (p->fs) + umask = p->fs->umask; if (p->files) max_fds = files_fdtable(p->files)->max_fds; task_unlock(p); rcu_read_unlock(); - seq_printf(m, "State:\t%s", get_task_state(p)); + if (umask >= 0) + seq_printf(m, "Umask:\t%#04o\n", umask); + seq_puts(m, "State:\t"); + seq_puts(m, get_task_state(p)); seq_put_decimal_ull(m, "\nTgid:\t", tgid); seq_put_decimal_ull(m, "\nNgid:\t", ngid); @@ -313,8 +309,8 @@ static void render_cap_t(struct seq_file *m, const char *header, seq_puts(m, header); CAP_FOR_EACH_U32(__capi) { - seq_printf(m, "%08x", - a->cap[CAP_LAST_U32 - __capi]); + seq_put_hex_ll(m, NULL, + a->cap[CAP_LAST_U32 - __capi], 8); } seq_putc(m, '\n'); } @@ -347,6 +343,30 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) #ifdef CONFIG_SECCOMP seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode); #endif + seq_printf(m, "\nSpeculation_Store_Bypass:\t"); + switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) { + case -EINVAL: + seq_printf(m, "unknown"); + break; + case PR_SPEC_NOT_AFFECTED: + seq_printf(m, "not vulnerable"); + break; + case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE: + seq_printf(m, "thread force mitigated"); + break; + case PR_SPEC_PRCTL | PR_SPEC_DISABLE: + seq_printf(m, "thread mitigated"); + break; + case PR_SPEC_PRCTL | PR_SPEC_ENABLE: + seq_printf(m, "thread vulnerable"); + break; + case PR_SPEC_DISABLE: + seq_printf(m, "globally mitigated"); + break; + default: + seq_printf(m, "vulnerable"); + break; + } seq_putc(m, '\n'); } @@ -368,7 +388,8 @@ static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm) { - seq_printf(m, "CoreDumping:\t%d\n", !!mm->core_state); + seq_put_decimal_ull(m, "CoreDumping:\t", !!mm->core_state); + seq_putc(m, '\n'); } int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, @@ -376,7 +397,10 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, { struct mm_struct *mm = get_task_mm(task); - task_name(m, task); + seq_puts(m, "Name:\t"); + proc_task_name(m, task, true); + seq_putc(m, '\n'); + task_state(m, ns, pid, task); if (mm) { @@ -411,7 +435,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, u64 cutime, cstime, utime, stime; u64 cgtime, gtime; unsigned long rsslim = 0; - char tcomm[sizeof(task->comm)]; unsigned long flags; state = *get_task_state(task); @@ -438,8 +461,6 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, } } - get_task_comm(tcomm, task); - sigemptyset(&sigign); sigemptyset(&sigcatch); cutime = cstime = utime = stime = 0; @@ -504,7 +525,11 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, /* convert nsec -> ticks */ start_time = nsec_to_clock_t(task->real_start_time); - seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state); + seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns)); + seq_puts(m, " ("); + proc_task_name(m, task, false); + seq_puts(m, ") "); + seq_putc(m, state); seq_put_decimal_ll(m, " ", ppid); seq_put_decimal_ll(m, " ", pgid); seq_put_decimal_ll(m, " ", sid); @@ -684,25 +709,22 @@ out: static int children_seq_show(struct seq_file *seq, void *v) { - struct inode *inode = seq->private; - pid_t pid; - - pid = pid_nr_ns(v, inode->i_sb->s_fs_info); - seq_printf(seq, "%d ", pid); + struct inode *inode = file_inode(seq->file); + seq_printf(seq, "%d ", pid_nr_ns(v, proc_pid_ns(inode))); return 0; } static void *children_seq_start(struct seq_file *seq, loff_t *pos) { - return get_children_pid(seq->private, NULL, *pos); + return get_children_pid(file_inode(seq->file), NULL, *pos); } static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct pid *pid; - pid = get_children_pid(seq->private, v, *pos + 1); + pid = get_children_pid(file_inode(seq->file), v, *pos + 1); put_pid(v); ++*pos; @@ -723,17 +745,7 @@ static const struct seq_operations children_seq_ops = { static int children_seq_open(struct inode *inode, struct file *file) { - struct seq_file *m; - int ret; - - ret = seq_open(file, &children_seq_ops); - if (ret) - return ret; - - m = file->private_data; - m->private = inode; - - return ret; + return seq_open(file, &children_seq_ops); } const struct file_operations proc_tid_children_operations = { diff --git a/fs/proc/base.c b/fs/proc/base.c index d53246863cfb..af128b374143 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -261,7 +261,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, * Inherently racy -- command line shares address space * with code and data. */ - rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0); + rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON); if (rv <= 0) goto out_free_page; @@ -279,7 +279,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, int nr_read; _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, 0); + nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -325,7 +325,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, bool final; _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, 0); + nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -388,14 +388,17 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, unsigned long wchan; char symname[KSYM_NAME_LEN]; - wchan = get_wchan(task); + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) + goto print0; - if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS) - && !lookup_symbol_name(wchan, symname)) - seq_printf(m, "%s", symname); - else - seq_putc(m, '0'); + wchan = get_wchan(task); + if (wchan && !lookup_symbol_name(wchan, symname)) { + seq_puts(m, symname); + return 0; + } +print0: + seq_putc(m, '0'); return 0; } #endif /* CONFIG_KALLSYMS */ @@ -695,7 +698,7 @@ static bool has_pid_permissions(struct pid_namespace *pid, static int proc_pid_permission(struct inode *inode, int mask) { - struct pid_namespace *pid = inode->i_sb->s_fs_info; + struct pid_namespace *pid = proc_pid_ns(inode); struct task_struct *task; bool has_perms; @@ -730,13 +733,11 @@ static const struct inode_operations proc_def_inode_operations = { static int proc_single_show(struct seq_file *m, void *v) { struct inode *inode = m->private; - struct pid_namespace *ns; - struct pid *pid; + struct pid_namespace *ns = proc_pid_ns(inode); + struct pid *pid = proc_pid(inode); struct task_struct *task; int ret; - ns = inode->i_sb->s_fs_info; - pid = proc_pid(inode); task = get_pid_task(pid, PIDTYPE_PID); if (!task) return -ESRCH; @@ -943,7 +944,7 @@ static ssize_t environ_read(struct file *file, char __user *buf, max_len = min_t(size_t, PAGE_SIZE, count); this_len = min(max_len, this_len); - retval = access_remote_vm(mm, (env_start + src), page, this_len, 0); + retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON); if (retval <= 0) { ret = retval; @@ -1407,7 +1408,7 @@ static const struct file_operations proc_fail_nth_operations = { static int sched_show(struct seq_file *m, void *v) { struct inode *inode = m->private; - struct pid_namespace *ns = inode->i_sb->s_fs_info; + struct pid_namespace *ns = proc_pid_ns(inode); struct task_struct *p; p = get_proc_task(inode); @@ -1562,9 +1563,8 @@ static int comm_show(struct seq_file *m, void *v) if (!p) return -ESRCH; - task_lock(p); - seq_printf(m, "%s\n", p->comm); - task_unlock(p); + proc_task_name(m, p, false); + seq_putc(m, '\n'); put_task_struct(p); @@ -1690,6 +1690,12 @@ void task_dump_owner(struct task_struct *task, umode_t mode, kuid_t uid; kgid_t gid; + if (unlikely(task->flags & PF_KTHREAD)) { + *ruid = GLOBAL_ROOT_UID; + *rgid = GLOBAL_ROOT_GID; + return; + } + /* Default to the tasks effective ownership */ rcu_read_lock(); cred = __task_cred(task); @@ -1773,8 +1779,8 @@ int pid_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); + struct pid_namespace *pid = proc_pid_ns(inode); struct task_struct *task; - struct pid_namespace *pid = path->dentry->d_sb->s_fs_info; generic_fillattr(inode, stat); @@ -1800,15 +1806,22 @@ int pid_getattr(const struct path *path, struct kstat *stat, /* dentry stuff */ /* - * Exceptional case: normally we are not allowed to unhash a busy - * directory. In this case, however, we can do it - no aliasing problems - * due to the way we treat inodes. - * + * Set <pid>/... inode ownership (can change due to setuid(), etc.) + */ +void pid_update_inode(struct task_struct *task, struct inode *inode) +{ + task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid); + + inode->i_mode &= ~(S_ISUID | S_ISGID); + security_task_to_inode(task, inode); +} + +/* * Rewrite the inode's ownerships here because the owning task may have * performed a setuid(), etc. * */ -int pid_revalidate(struct dentry *dentry, unsigned int flags) +static int pid_revalidate(struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; @@ -1820,10 +1833,7 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags) task = get_proc_task(inode); if (task) { - task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid); - - inode->i_mode &= ~(S_ISUID | S_ISGID); - security_task_to_inode(task, inode); + pid_update_inode(task, inode); put_task_struct(task); return 1; } @@ -1871,8 +1881,8 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx, struct dentry *child, *dir = file->f_path.dentry; struct qstr qname = QSTR_INIT(name, len); struct inode *inode; - unsigned type; - ino_t ino; + unsigned type = DT_UNKNOWN; + ino_t ino = 1; child = d_hash_and_lookup(dir, &qname); if (!child) { @@ -1881,22 +1891,23 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx, if (IS_ERR(child)) goto end_instantiate; if (d_in_lookup(child)) { - int err = instantiate(d_inode(dir), child, task, ptr); + struct dentry *res; + res = instantiate(child, task, ptr); d_lookup_done(child); - if (err < 0) { - dput(child); + if (IS_ERR(res)) goto end_instantiate; + if (unlikely(res)) { + dput(child); + child = res; } } } inode = d_inode(child); ino = inode->i_ino; type = inode->i_mode >> 12; +end_instantiate: dput(child); return dir_emit(ctx, name, len, ino, type); - -end_instantiate: - return dir_emit(ctx, name, len, 1, DT_UNKNOWN); } /* @@ -1910,6 +1921,8 @@ static int dname_to_vma_addr(struct dentry *dentry, unsigned long long sval, eval; unsigned int len; + if (str[0] == '0' && str[1] != '-') + return -EINVAL; len = _parse_integer(str, 16, &sval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; @@ -1921,6 +1934,8 @@ static int dname_to_vma_addr(struct dentry *dentry, return -EINVAL; str++; + if (str[0] == '0' && str[1]) + return -EINVAL; len = _parse_integer(str, 16, &eval); if (len & KSTRTOX_OVERFLOW) return -EINVAL; @@ -2054,19 +2069,19 @@ static const struct inode_operations proc_map_files_link_inode_operations = { .setattr = proc_setattr, }; -static int -proc_map_files_instantiate(struct inode *dir, struct dentry *dentry, +static struct dentry * +proc_map_files_instantiate(struct dentry *dentry, struct task_struct *task, const void *ptr) { fmode_t mode = (fmode_t)(unsigned long)ptr; struct proc_inode *ei; struct inode *inode; - inode = proc_pid_make_inode(dir->i_sb, task, S_IFLNK | + inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | ((mode & FMODE_READ ) ? S_IRUSR : 0) | ((mode & FMODE_WRITE) ? S_IWUSR : 0)); if (!inode) - return -ENOENT; + return ERR_PTR(-ENOENT); ei = PROC_I(inode); ei->op.proc_get_link = map_files_get_link; @@ -2075,9 +2090,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry, inode->i_size = 64; d_set_d_op(dentry, &tid_map_files_dentry_operations); - d_add(dentry, inode); - - return 0; + return d_splice_alias(inode, dentry); } static struct dentry *proc_map_files_lookup(struct inode *dir, @@ -2086,19 +2099,19 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, unsigned long vm_start, vm_end; struct vm_area_struct *vma; struct task_struct *task; - int result; + struct dentry *result; struct mm_struct *mm; - result = -ENOENT; + result = ERR_PTR(-ENOENT); task = get_proc_task(dir); if (!task) goto out; - result = -EACCES; + result = ERR_PTR(-EACCES); if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto out_put_task; - result = -ENOENT; + result = ERR_PTR(-ENOENT); if (dname_to_vma_addr(dentry, &vm_start, &vm_end)) goto out_put_task; @@ -2112,7 +2125,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, goto out_no_vma; if (vma->vm_file) - result = proc_map_files_instantiate(dir, dentry, task, + result = proc_map_files_instantiate(dentry, task, (void *)(unsigned long)vma->vm_file->f_mode); out_no_vma: @@ -2121,7 +2134,7 @@ out_no_vma: out_put_task: put_task_struct(task); out: - return ERR_PTR(result); + return result; } static const struct inode_operations proc_map_files_inode_operations = { @@ -2204,6 +2217,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) } } up_read(&mm->mmap_sem); + mmput(mm); for (i = 0; i < nr_files; i++) { char buf[4 * sizeof(long) + 2]; /* max: %lx-%lx\0 */ @@ -2221,7 +2235,6 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx) } if (fa) flex_array_free(fa); - mmput(mm); out_put_task: put_task_struct(task); @@ -2324,7 +2337,7 @@ static int proc_timers_open(struct inode *inode, struct file *file) return -ENOMEM; tp->pid = proc_pid(inode); - tp->ns = inode->i_sb->s_fs_info; + tp->ns = proc_pid_ns(inode); return 0; } @@ -2422,16 +2435,16 @@ static const struct file_operations proc_pid_set_timerslack_ns_operations = { .release = single_release, }; -static int proc_pident_instantiate(struct inode *dir, - struct dentry *dentry, struct task_struct *task, const void *ptr) +static struct dentry *proc_pident_instantiate(struct dentry *dentry, + struct task_struct *task, const void *ptr) { const struct pid_entry *p = ptr; struct inode *inode; struct proc_inode *ei; - inode = proc_pid_make_inode(dir->i_sb, task, p->mode); + inode = proc_pid_make_inode(dentry->d_sb, task, p->mode); if (!inode) - goto out; + return ERR_PTR(-ENOENT); ei = PROC_I(inode); if (S_ISDIR(inode->i_mode)) @@ -2441,13 +2454,9 @@ static int proc_pident_instantiate(struct inode *dir, if (p->fop) inode->i_fop = p->fop; ei->op = p->op; + pid_update_inode(task, inode); d_set_d_op(dentry, &pid_dentry_operations); - d_add(dentry, inode); - /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, 0)) - return 0; -out: - return -ENOENT; + return d_splice_alias(inode, dentry); } static struct dentry *proc_pident_lookup(struct inode *dir, @@ -2455,11 +2464,9 @@ static struct dentry *proc_pident_lookup(struct inode *dir, const struct pid_entry *ents, unsigned int nents) { - int error; struct task_struct *task = get_proc_task(dir); const struct pid_entry *p, *last; - - error = -ENOENT; + struct dentry *res = ERR_PTR(-ENOENT); if (!task) goto out_no_task; @@ -2478,11 +2485,11 @@ static struct dentry *proc_pident_lookup(struct inode *dir, if (p >= last) goto out; - error = proc_pident_instantiate(dir, dentry, task, p); + res = proc_pident_instantiate(dentry, task, p); out: put_task_struct(task); out_no_task: - return ERR_PTR(error); + return res; } static int proc_pident_readdir(struct file *file, struct dir_context *ctx, @@ -3125,38 +3132,32 @@ void proc_flush_task(struct task_struct *task) } } -static int proc_pid_instantiate(struct inode *dir, - struct dentry * dentry, +static struct dentry *proc_pid_instantiate(struct dentry * dentry, struct task_struct *task, const void *ptr) { struct inode *inode; - inode = proc_pid_make_inode(dir->i_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); + inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) - goto out; + return ERR_PTR(-ENOENT); inode->i_op = &proc_tgid_base_inode_operations; inode->i_fop = &proc_tgid_base_operations; inode->i_flags|=S_IMMUTABLE; set_nlink(inode, nlink_tgid); + pid_update_inode(task, inode); d_set_d_op(dentry, &pid_dentry_operations); - - d_add(dentry, inode); - /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, 0)) - return 0; -out: - return -ENOENT; + return d_splice_alias(inode, dentry); } struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { - int result = -ENOENT; struct task_struct *task; unsigned tgid; struct pid_namespace *ns; + struct dentry *result = ERR_PTR(-ENOENT); tgid = name_to_int(&dentry->d_name); if (tgid == ~0U) @@ -3171,10 +3172,10 @@ struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsign if (!task) goto out; - result = proc_pid_instantiate(dir, dentry, task, NULL); + result = proc_pid_instantiate(dentry, task, NULL); put_task_struct(task); out: - return ERR_PTR(result); + return result; } /* @@ -3226,7 +3227,7 @@ retry: int proc_pid_readdir(struct file *file, struct dir_context *ctx) { struct tgid_iter iter; - struct pid_namespace *ns = file_inode(file)->i_sb->s_fs_info; + struct pid_namespace *ns = proc_pid_ns(file_inode(file)); loff_t pos = ctx->pos; if (pos >= PID_MAX_LIMIT + TGID_OFFSET) @@ -3422,37 +3423,32 @@ static const struct inode_operations proc_tid_base_inode_operations = { .setattr = proc_setattr, }; -static int proc_task_instantiate(struct inode *dir, - struct dentry *dentry, struct task_struct *task, const void *ptr) +static struct dentry *proc_task_instantiate(struct dentry *dentry, + struct task_struct *task, const void *ptr) { struct inode *inode; - inode = proc_pid_make_inode(dir->i_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); - + inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO); if (!inode) - goto out; + return ERR_PTR(-ENOENT); + inode->i_op = &proc_tid_base_inode_operations; inode->i_fop = &proc_tid_base_operations; - inode->i_flags|=S_IMMUTABLE; + inode->i_flags |= S_IMMUTABLE; set_nlink(inode, nlink_tid); + pid_update_inode(task, inode); d_set_d_op(dentry, &pid_dentry_operations); - - d_add(dentry, inode); - /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, 0)) - return 0; -out: - return -ENOENT; + return d_splice_alias(inode, dentry); } static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { - int result = -ENOENT; struct task_struct *task; struct task_struct *leader = get_proc_task(dir); unsigned tid; struct pid_namespace *ns; + struct dentry *result = ERR_PTR(-ENOENT); if (!leader) goto out_no_task; @@ -3472,13 +3468,13 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry if (!same_thread_group(leader, task)) goto out_drop_task; - result = proc_task_instantiate(dir, dentry, task, NULL); + result = proc_task_instantiate(dentry, task, NULL); out_drop_task: put_task_struct(task); out: put_task_struct(leader); out_no_task: - return ERR_PTR(result); + return result; } /* @@ -3575,7 +3571,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx) /* f_version caches the tgid value that the last readdir call couldn't * return. lseek aka telldir automagically resets f_version to 0. */ - ns = inode->i_sb->s_fs_info; + ns = proc_pid_ns(inode); tid = (int)file->f_version; file->f_version = 0; for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); diff --git a/fs/proc/cmdline.c b/fs/proc/cmdline.c index 403cbb12a6e9..fa762c5fbcb2 100644 --- a/fs/proc/cmdline.c +++ b/fs/proc/cmdline.c @@ -6,25 +6,14 @@ static int cmdline_proc_show(struct seq_file *m, void *v) { - seq_printf(m, "%s\n", saved_command_line); + seq_puts(m, saved_command_line); + seq_putc(m, '\n'); return 0; } -static int cmdline_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, cmdline_proc_show, NULL); -} - -static const struct file_operations cmdline_proc_fops = { - .open = cmdline_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int __init proc_cmdline_init(void) { - proc_create("cmdline", 0, NULL, &cmdline_proc_fops); + proc_create_single("cmdline", 0, NULL, cmdline_proc_show); return 0; } fs_initcall(proc_cmdline_init); diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c index a8ac48aebd59..954caf0b7fee 100644 --- a/fs/proc/consoles.c +++ b/fs/proc/consoles.c @@ -91,21 +91,9 @@ static const struct seq_operations consoles_op = { .show = show_console_dev }; -static int consoles_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &consoles_op); -} - -static const struct file_operations proc_consoles_operations = { - .open = consoles_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static int __init proc_consoles_init(void) { - proc_create("consoles", 0, NULL, &proc_consoles_operations); + proc_create_seq("consoles", 0, NULL, &consoles_op); return 0; } fs_initcall(proc_consoles_init); diff --git a/fs/proc/devices.c b/fs/proc/devices.c index 2c7f22b14489..37d38697eaf8 100644 --- a/fs/proc/devices.c +++ b/fs/proc/devices.c @@ -51,21 +51,9 @@ static const struct seq_operations devinfo_ops = { .show = devinfo_show }; -static int devinfo_open(struct inode *inode, struct file *filp) -{ - return seq_open(filp, &devinfo_ops); -} - -static const struct file_operations proc_devinfo_operations = { - .open = devinfo_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static int __init proc_devices_init(void) { - proc_create("devices", 0, NULL, &proc_devinfo_operations); + proc_create_seq("devices", 0, NULL, &devinfo_ops); return 0; } fs_initcall(proc_devices_init); diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 6b80cd1e419a..05b9893e9a22 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -81,9 +81,41 @@ static const struct file_operations proc_fdinfo_file_operations = { .release = single_release, }; +static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode) +{ + struct files_struct *files = get_files_struct(task); + struct file *file; + + if (!files) + return false; + + rcu_read_lock(); + file = fcheck_files(files, fd); + if (file) + *mode = file->f_mode; + rcu_read_unlock(); + put_files_struct(files); + return !!file; +} + +static void tid_fd_update_inode(struct task_struct *task, struct inode *inode, + fmode_t f_mode) +{ + task_dump_owner(task, 0, &inode->i_uid, &inode->i_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); +} + static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) { - struct files_struct *files; struct task_struct *task; struct inode *inode; unsigned int fd; @@ -96,35 +128,11 @@ static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) 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); - - task_dump_owner(task, 0, &inode->i_uid, &inode->i_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); + fmode_t f_mode; + if (tid_fd_mode(task, fd, &f_mode)) { + tid_fd_update_inode(task, inode, f_mode); + put_task_struct(task); + return 1; } put_task_struct(task); } @@ -166,34 +174,33 @@ static int proc_fd_link(struct dentry *dentry, struct path *path) return ret; } -static int -proc_fd_instantiate(struct inode *dir, struct dentry *dentry, - struct task_struct *task, const void *ptr) +struct fd_data { + fmode_t mode; + unsigned fd; +}; + +static struct dentry *proc_fd_instantiate(struct dentry *dentry, + struct task_struct *task, const void *ptr) { - unsigned fd = (unsigned long)ptr; + const struct fd_data *data = ptr; struct proc_inode *ei; struct inode *inode; - inode = proc_pid_make_inode(dir->i_sb, task, S_IFLNK); + inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK); if (!inode) - goto out; + return ERR_PTR(-ENOENT); ei = PROC_I(inode); - ei->fd = fd; + ei->fd = data->fd; inode->i_op = &proc_pid_link_inode_operations; inode->i_size = 64; ei->op.proc_get_link = proc_fd_link; + tid_fd_update_inode(task, inode, data->mode); 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)) - return 0; - out: - return -ENOENT; + return d_splice_alias(inode, dentry); } static struct dentry *proc_lookupfd_common(struct inode *dir, @@ -201,19 +208,21 @@ static struct dentry *proc_lookupfd_common(struct inode *dir, instantiate_t instantiate) { struct task_struct *task = get_proc_task(dir); - int result = -ENOENT; - unsigned fd = name_to_int(&dentry->d_name); + struct fd_data data = {.fd = name_to_int(&dentry->d_name)}; + struct dentry *result = ERR_PTR(-ENOENT); if (!task) goto out_no_task; - if (fd == ~0U) + if (data.fd == ~0U) + goto out; + if (!tid_fd_mode(task, data.fd, &data.mode)) goto out; - result = instantiate(dir, dentry, task, (void *)(unsigned long)fd); + result = instantiate(dentry, task, &data); out: put_task_struct(task); out_no_task: - return ERR_PTR(result); + return result; } static int proc_readfd_common(struct file *file, struct dir_context *ctx, @@ -236,17 +245,22 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx, for (fd = ctx->pos - 2; fd < files_fdtable(files)->max_fds; fd++, ctx->pos++) { + struct file *f; + struct fd_data data; char name[10 + 1]; int len; - if (!fcheck_files(files, fd)) + f = fcheck_files(files, fd); + if (!f) continue; + data.mode = f->f_mode; rcu_read_unlock(); + data.fd = fd; len = snprintf(name, sizeof(name), "%u", fd); if (!proc_fill_cache(file, ctx, name, len, instantiate, p, - (void *)(unsigned long)fd)) + &data)) goto out_fd_loop; cond_resched(); rcu_read_lock(); @@ -304,31 +318,25 @@ const struct inode_operations proc_fd_inode_operations = { .setattr = proc_setattr, }; -static int -proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry, - struct task_struct *task, const void *ptr) +static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry, + struct task_struct *task, const void *ptr) { - unsigned fd = (unsigned long)ptr; + const struct fd_data *data = ptr; struct proc_inode *ei; struct inode *inode; - inode = proc_pid_make_inode(dir->i_sb, task, S_IFREG | S_IRUSR); + inode = proc_pid_make_inode(dentry->d_sb, task, S_IFREG | S_IRUSR); if (!inode) - goto out; + return ERR_PTR(-ENOENT); ei = PROC_I(inode); - ei->fd = fd; + ei->fd = data->fd; inode->i_fop = &proc_fdinfo_file_operations; + tid_fd_update_inode(task, inode, 0); 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)) - return 0; - out: - return -ENOENT; + return d_splice_alias(inode, dentry); } static struct dentry * diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 5d709fa8f3a2..7b4d9714f248 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -8,12 +8,14 @@ * Copyright (C) 1997 Theodore Ts'o */ +#include <linux/cache.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> #include <linux/stat.h> #include <linux/mm.h> #include <linux/module.h> +#include <linux/namei.h> #include <linux/slab.h> #include <linux/printk.h> #include <linux/mount.h> @@ -23,11 +25,23 @@ #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/uaccess.h> +#include <linux/seq_file.h> #include "internal.h" static DEFINE_RWLOCK(proc_subdir_lock); +struct kmem_cache *proc_dir_entry_cache __ro_after_init; + +void pde_free(struct proc_dir_entry *pde) +{ + if (S_ISLNK(pde->mode)) + kfree(pde->data); + if (pde->name != pde->inline_name) + kfree(pde->name); + kmem_cache_free(proc_dir_entry_cache, pde); +} + static int proc_match(const char *name, struct proc_dir_entry *de, unsigned int len) { if (len < de->namelen) @@ -40,8 +54,8 @@ static int proc_match(const char *name, struct proc_dir_entry *de, unsigned int static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir) { - return rb_entry_safe(rb_first_cached(&dir->subdir), - struct proc_dir_entry, subdir_node); + return rb_entry_safe(rb_first(&dir->subdir), struct proc_dir_entry, + subdir_node); } static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir) @@ -54,7 +68,7 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir, const char *name, unsigned int len) { - struct rb_node *node = dir->subdir.rb_root.rb_node; + struct rb_node *node = dir->subdir.rb_node; while (node) { struct proc_dir_entry *de = rb_entry(node, @@ -75,9 +89,8 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir, static bool pde_subdir_insert(struct proc_dir_entry *dir, struct proc_dir_entry *de) { - struct rb_root_cached *root = &dir->subdir; - struct rb_node **new = &root->rb_root.rb_node, *parent = NULL; - bool leftmost = true; + struct rb_root *root = &dir->subdir; + struct rb_node **new = &root->rb_node, *parent = NULL; /* Figure out where to put new node */ while (*new) { @@ -89,16 +102,15 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir, parent = *new; if (result < 0) new = &(*new)->rb_left; - else if (result > 0) { + else if (result > 0) new = &(*new)->rb_right; - leftmost = false; - } else + else return false; } /* Add new node and rebalance tree. */ rb_link_node(&de->subdir_node, parent, new); - rb_insert_color_cached(&de->subdir_node, root, leftmost); + rb_insert_color(&de->subdir_node, root); return true; } @@ -207,6 +219,26 @@ void proc_free_inum(unsigned int inum) ida_simple_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST); } +static int proc_misc_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + if (flags & LOOKUP_RCU) + return -ECHILD; + + if (atomic_read(&PDE(d_inode(dentry))->in_use) < 0) + return 0; /* revalidate */ + return 1; +} + +static int proc_misc_d_delete(const struct dentry *dentry) +{ + return atomic_read(&PDE(d_inode(dentry))->in_use) < 0; +} + +static const struct dentry_operations proc_misc_dentry_ops = { + .d_revalidate = proc_misc_d_revalidate, + .d_delete = proc_misc_d_delete, +}; + /* * Don't create negative dentries here, return -ENOENT by hand * instead. @@ -224,9 +256,8 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, inode = proc_get_inode(dir->i_sb, de); if (!inode) return ERR_PTR(-ENOMEM); - d_set_d_op(dentry, &simple_dentry_operations); - d_add(dentry, inode); - return NULL; + d_set_d_op(dentry, &proc_misc_dentry_ops); + return d_splice_alias(inode, dentry); } read_unlock(&proc_subdir_lock); return ERR_PTR(-ENOENT); @@ -315,13 +346,12 @@ static const struct inode_operations proc_dir_inode_operations = { .setattr = proc_notify_change, }; -static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp) +/* returns the registered entry, or frees dp and returns NULL on failure */ +struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, + struct proc_dir_entry *dp) { - int ret; - - ret = proc_alloc_inum(&dp->low_ino); - if (ret) - return ret; + if (proc_alloc_inum(&dp->low_ino)) + goto out_free_entry; write_lock(&proc_subdir_lock); dp->parent = dir; @@ -329,12 +359,16 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp WARN(1, "proc_dir_entry '%s/%s' already registered\n", dir->name, dp->name); write_unlock(&proc_subdir_lock); - proc_free_inum(dp->low_ino); - return -EEXIST; + goto out_free_inum; } write_unlock(&proc_subdir_lock); - return 0; + return dp; +out_free_inum: + proc_free_inum(dp->low_ino); +out_free_entry: + pde_free(dp); + return NULL; } static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, @@ -354,6 +388,14 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, WARN(1, "name len %u\n", qstr.len); return NULL; } + if (qstr.len == 1 && fn[0] == '.') { + WARN(1, "name '.'\n"); + return NULL; + } + if (qstr.len == 2 && fn[0] == '.' && fn[1] == '.') { + WARN(1, "name '..'\n"); + return NULL; + } if (*parent == &proc_root && name_to_int(&qstr) != ~0U) { WARN(1, "create '/proc/%s' by hand\n", qstr.name); return NULL; @@ -363,16 +405,26 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, return NULL; } - ent = kzalloc(sizeof(struct proc_dir_entry) + qstr.len + 1, GFP_KERNEL); + ent = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!ent) goto out; + if (qstr.len + 1 <= sizeof(ent->inline_name)) { + ent->name = ent->inline_name; + } else { + ent->name = kmalloc(qstr.len + 1, GFP_KERNEL); + if (!ent->name) { + pde_free(ent); + return NULL; + } + } + memcpy(ent->name, fn, qstr.len + 1); ent->namelen = qstr.len; ent->mode = mode; ent->nlink = nlink; - ent->subdir = RB_ROOT_CACHED; - atomic_set(&ent->count, 1); + ent->subdir = RB_ROOT; + refcount_set(&ent->refcnt, 1); spin_lock_init(&ent->pde_unload_lock); INIT_LIST_HEAD(&ent->pde_openers); proc_set_user(ent, (*parent)->uid, (*parent)->gid); @@ -394,13 +446,9 @@ struct proc_dir_entry *proc_symlink(const char *name, if (ent->data) { strcpy((char*)ent->data,dest); ent->proc_iops = &proc_link_inode_operations; - if (proc_register(parent, ent) < 0) { - kfree(ent->data); - kfree(ent); - ent = NULL; - } + ent = proc_register(parent, ent); } else { - kfree(ent); + pde_free(ent); ent = NULL; } } @@ -422,11 +470,9 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, ent->proc_fops = &proc_dir_operations; ent->proc_iops = &proc_dir_inode_operations; parent->nlink++; - if (proc_register(parent, ent) < 0) { - kfree(ent); + ent = proc_register(parent, ent); + if (!ent) parent->nlink--; - ent = NULL; - } } return ent; } @@ -457,47 +503,47 @@ struct proc_dir_entry *proc_create_mount_point(const char *name) ent->proc_fops = NULL; ent->proc_iops = NULL; parent->nlink++; - if (proc_register(parent, ent) < 0) { - kfree(ent); + ent = proc_register(parent, ent); + if (!ent) parent->nlink--; - ent = NULL; - } } return ent; } EXPORT_SYMBOL(proc_create_mount_point); -struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, - struct proc_dir_entry *parent, - const struct file_operations *proc_fops, - void *data) +struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, + struct proc_dir_entry **parent, void *data) { - struct proc_dir_entry *pde; + struct proc_dir_entry *p; + if ((mode & S_IFMT) == 0) mode |= S_IFREG; - - if (!S_ISREG(mode)) { - WARN_ON(1); /* use proc_mkdir() */ + if ((mode & S_IALLUGO) == 0) + mode |= S_IRUGO; + if (WARN_ON_ONCE(!S_ISREG(mode))) return NULL; + + p = __proc_create(parent, name, mode, 1); + if (p) { + p->proc_iops = &proc_file_inode_operations; + p->data = data; } + return p; +} + +struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, + const struct file_operations *proc_fops, void *data) +{ + struct proc_dir_entry *p; BUG_ON(proc_fops == NULL); - if ((mode & S_IALLUGO) == 0) - mode |= S_IRUGO; - pde = __proc_create(&parent, name, mode, 1); - if (!pde) - goto out; - pde->proc_fops = proc_fops; - pde->data = data; - pde->proc_iops = &proc_file_inode_operations; - if (proc_register(parent, pde) < 0) - goto out_free; - return pde; -out_free: - kfree(pde); -out: - return NULL; + p = proc_create_reg(name, mode, &parent, data); + if (!p) + return NULL; + p->proc_fops = proc_fops; + return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_data); @@ -509,6 +555,67 @@ struct proc_dir_entry *proc_create(const char *name, umode_t mode, } EXPORT_SYMBOL(proc_create); +static int proc_seq_open(struct inode *inode, struct file *file) +{ + struct proc_dir_entry *de = PDE(inode); + + if (de->state_size) + return seq_open_private(file, de->seq_ops, de->state_size); + return seq_open(file, de->seq_ops); +} + +static const struct file_operations proc_seq_fops = { + .open = proc_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, + struct proc_dir_entry *parent, const struct seq_operations *ops, + unsigned int state_size, void *data) +{ + struct proc_dir_entry *p; + + p = proc_create_reg(name, mode, &parent, data); + if (!p) + return NULL; + p->proc_fops = &proc_seq_fops; + p->seq_ops = ops; + p->state_size = state_size; + return proc_register(parent, p); +} +EXPORT_SYMBOL(proc_create_seq_private); + +static int proc_single_open(struct inode *inode, struct file *file) +{ + struct proc_dir_entry *de = PDE(inode); + + return single_open(file, de->single_show, de->data); +} + +static const struct file_operations proc_single_fops = { + .open = proc_single_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, + int (*show)(struct seq_file *, void *), void *data) +{ + struct proc_dir_entry *p; + + p = proc_create_reg(name, mode, &parent, data); + if (!p) + return NULL; + p->proc_fops = &proc_single_fops; + p->single_show = show; + return proc_register(parent, p); +} +EXPORT_SYMBOL(proc_create_single_data); + void proc_set_size(struct proc_dir_entry *de, loff_t size) { de->size = size; @@ -522,19 +629,12 @@ void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) } EXPORT_SYMBOL(proc_set_user); -static void free_proc_entry(struct proc_dir_entry *de) -{ - proc_free_inum(de->low_ino); - - if (S_ISLNK(de->mode)) - kfree(de->data); - kfree(de); -} - void pde_put(struct proc_dir_entry *pde) { - if (atomic_dec_and_test(&pde->count)) - free_proc_entry(pde); + if (refcount_dec_and_test(&pde->refcnt)) { + proc_free_inum(pde->low_ino); + pde_free(pde); + } } /* @@ -555,7 +655,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) de = pde_subdir_find(parent, fn, len); if (de) - rb_erase_cached(&de->subdir_node, &parent->subdir); + rb_erase(&de->subdir_node, &parent->subdir); write_unlock(&proc_subdir_lock); if (!de) { WARN(1, "name '%s'\n", name); @@ -592,13 +692,13 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) write_unlock(&proc_subdir_lock); return -ENOENT; } - rb_erase_cached(&root->subdir_node, &parent->subdir); + rb_erase(&root->subdir_node, &parent->subdir); de = root; while (1) { next = pde_subdir_first(de); if (next) { - rb_erase_cached(&next->subdir_node, &de->subdir); + rb_erase(&next->subdir_node, &de->subdir); de = next; continue; } diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 6e8724958116..2cf3b74391ca 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -54,6 +54,7 @@ static void proc_evict_inode(struct inode *inode) } static struct kmem_cache *proc_inode_cachep __ro_after_init; +static struct kmem_cache *pde_opener_cache __ro_after_init; static struct inode *proc_alloc_inode(struct super_block *sb) { @@ -92,7 +93,7 @@ static void init_once(void *foo) inode_init_once(&ei->vfs_inode); } -void __init proc_init_inodecache(void) +void __init proc_init_kmemcache(void) { proc_inode_cachep = kmem_cache_create("proc_inode_cache", sizeof(struct proc_inode), @@ -100,6 +101,13 @@ void __init proc_init_inodecache(void) SLAB_MEM_SPREAD|SLAB_ACCOUNT| SLAB_PANIC), init_once); + pde_opener_cache = + kmem_cache_create("pde_opener", sizeof(struct pde_opener), 0, + SLAB_ACCOUNT|SLAB_PANIC, NULL); + proc_dir_entry_cache = kmem_cache_create_usercopy( + "proc_dir_entry", sizeof(struct proc_dir_entry), 0, SLAB_PANIC, + offsetof(struct proc_dir_entry, inline_name), + sizeof_field(struct proc_dir_entry, inline_name), NULL); } static int proc_show_options(struct seq_file *seq, struct dentry *root) @@ -138,7 +146,7 @@ static void unuse_pde(struct proc_dir_entry *pde) complete(pde->pde_unload_completion); } -/* pde is locked */ +/* pde is locked on entry, unlocked on exit */ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) { /* @@ -157,9 +165,10 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) pdeo->c = &c; spin_unlock(&pde->pde_unload_lock); wait_for_completion(&c); - spin_lock(&pde->pde_unload_lock); } else { struct file *file; + struct completion *c; + pdeo->closing = true; spin_unlock(&pde->pde_unload_lock); file = pdeo->file; @@ -167,9 +176,11 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo) spin_lock(&pde->pde_unload_lock); /* After ->release. */ list_del(&pdeo->lh); - if (unlikely(pdeo->c)) - complete(pdeo->c); - kfree(pdeo); + c = pdeo->c; + spin_unlock(&pde->pde_unload_lock); + if (unlikely(c)) + complete(c); + kmem_cache_free(pde_opener_cache, pdeo); } } @@ -188,6 +199,7 @@ void proc_entry_rundown(struct proc_dir_entry *de) struct pde_opener *pdeo; pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh); close_pdeo(de, pdeo); + spin_lock(&de->pde_unload_lock); } spin_unlock(&de->pde_unload_lock); } @@ -338,31 +350,36 @@ static int proc_reg_open(struct inode *inode, struct file *file) * * Save every "struct file" with custom ->release hook. */ - pdeo = kmalloc(sizeof(struct pde_opener), GFP_KERNEL); - if (!pdeo) - return -ENOMEM; - - if (!use_pde(pde)) { - kfree(pdeo); + if (!use_pde(pde)) return -ENOENT; - } - open = pde->proc_fops->open; + release = pde->proc_fops->release; + if (release) { + pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL); + if (!pdeo) { + rv = -ENOMEM; + goto out_unuse; + } + } + open = pde->proc_fops->open; if (open) rv = open(inode, file); - if (rv == 0 && release) { - /* To know what to release. */ - pdeo->file = file; - pdeo->closing = false; - pdeo->c = NULL; - spin_lock(&pde->pde_unload_lock); - list_add(&pdeo->lh, &pde->pde_openers); - spin_unlock(&pde->pde_unload_lock); - } else - kfree(pdeo); + if (release) { + if (rv == 0) { + /* To know what to release. */ + pdeo->file = file; + pdeo->closing = false; + pdeo->c = NULL; + spin_lock(&pde->pde_unload_lock); + list_add(&pdeo->lh, &pde->pde_openers); + spin_unlock(&pde->pde_unload_lock); + } else + kmem_cache_free(pde_opener_cache, pdeo); + } +out_unuse: unuse_pde(pde); return rv; } @@ -375,7 +392,7 @@ static int proc_reg_release(struct inode *inode, struct file *file) list_for_each_entry(pdeo, &pde->pde_openers, lh) { if (pdeo->file == file) { close_pdeo(pde, pdeo); - break; + return 0; } } spin_unlock(&pde->pde_unload_lock); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index d697c8ab0a14..93eb1906c28d 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -11,6 +11,7 @@ #include <linux/proc_fs.h> #include <linux/proc_ns.h> +#include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/binfmts.h> @@ -36,27 +37,41 @@ struct proc_dir_entry { * negative -> it's going away RSN */ atomic_t in_use; - atomic_t count; /* use count */ + refcount_t refcnt; struct list_head pde_openers; /* who did ->open, but not ->release */ /* protects ->pde_openers and all struct pde_opener instances */ spinlock_t pde_unload_lock; struct completion *pde_unload_completion; const struct inode_operations *proc_iops; const struct file_operations *proc_fops; + union { + const struct seq_operations *seq_ops; + int (*single_show)(struct seq_file *, void *); + }; void *data; + unsigned int state_size; unsigned int low_ino; nlink_t nlink; kuid_t uid; kgid_t gid; loff_t size; struct proc_dir_entry *parent; - struct rb_root_cached subdir; + struct rb_root subdir; struct rb_node subdir_node; + char *name; umode_t mode; u8 namelen; - char name[]; +#ifdef CONFIG_64BIT +#define SIZEOF_PDE_INLINE_NAME (192-155) +#else +#define SIZEOF_PDE_INLINE_NAME (128-95) +#endif + char inline_name[SIZEOF_PDE_INLINE_NAME]; } __randomize_layout; +extern struct kmem_cache *proc_dir_entry_cache; +void pde_free(struct proc_dir_entry *pde); + union proc_op { int (*proc_get_link)(struct dentry *, struct path *); int (*proc_show)(struct seq_file *m, @@ -121,6 +136,8 @@ unsigned name_to_int(const struct qstr *qstr); */ extern const struct file_operations proc_tid_children_operations; +extern void proc_task_name(struct seq_file *m, struct task_struct *p, + bool escape); extern int proc_tid_stat(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *, @@ -137,14 +154,14 @@ extern const struct dentry_operations pid_dentry_operations; extern int pid_getattr(const struct path *, struct kstat *, u32, unsigned int); extern int proc_setattr(struct dentry *, struct iattr *); extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t); -extern int pid_revalidate(struct dentry *, unsigned int); +extern void pid_update_inode(struct task_struct *, struct inode *); extern int pid_delete_dentry(const struct dentry *); extern int proc_pid_readdir(struct file *, struct dir_context *); extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int); extern loff_t mem_lseek(struct file *, loff_t, int); /* Lookups */ -typedef int instantiate_t(struct inode *, struct dentry *, +typedef struct dentry *instantiate_t(struct dentry *, struct task_struct *, const void *); extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, int, instantiate_t, struct task_struct *, const void *); @@ -152,6 +169,10 @@ extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, i /* * generic.c */ +struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, + struct proc_dir_entry **parent, void *data); +struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, + struct proc_dir_entry *dp); extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int); struct dentry *proc_lookup_de(struct inode *, struct dentry *, struct proc_dir_entry *); extern int proc_readdir(struct file *, struct dir_context *); @@ -159,7 +180,7 @@ int proc_readdir_de(struct file *, struct dir_context *, struct proc_dir_entry * static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde) { - atomic_inc(&pde->count); + refcount_inc(&pde->refcnt); return pde; } extern void pde_put(struct proc_dir_entry *); @@ -177,12 +198,12 @@ struct pde_opener { struct list_head lh; bool closing; struct completion *c; -}; +} __randomize_layout; extern const struct inode_operations proc_link_inode_operations; extern const struct inode_operations proc_pid_link_inode_operations; -extern void proc_init_inodecache(void); +void proc_init_kmemcache(void); void set_proc_pid_nlink(void); extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *); extern int proc_fill_super(struct super_block *, void *data, int flags); diff --git a/fs/proc/interrupts.c b/fs/proc/interrupts.c index 6a6bee9c603c..cb0edc7cbf09 100644 --- a/fs/proc/interrupts.c +++ b/fs/proc/interrupts.c @@ -34,21 +34,9 @@ static const struct seq_operations int_seq_ops = { .show = show_interrupts }; -static int interrupts_open(struct inode *inode, struct file *filp) -{ - return seq_open(filp, &int_seq_ops); -} - -static const struct file_operations proc_interrupts_operations = { - .open = interrupts_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static int __init proc_interrupts_init(void) { - proc_create("interrupts", 0, NULL, &proc_interrupts_operations); + proc_create_seq("interrupts", 0, NULL, &int_seq_ops); return 0; } fs_initcall(proc_interrupts_init); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index d1e82761de81..e64ecb9f2720 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -209,25 +209,34 @@ kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg) { struct list_head *head = (struct list_head *)arg; struct kcore_list *ent; + struct page *p; + + if (!pfn_valid(pfn)) + return 1; + + p = pfn_to_page(pfn); + if (!memmap_valid_within(pfn, p, page_zone(p))) + return 1; ent = kmalloc(sizeof(*ent), GFP_KERNEL); if (!ent) return -ENOMEM; - ent->addr = (unsigned long)__va((pfn << PAGE_SHIFT)); + ent->addr = (unsigned long)page_to_virt(p); ent->size = nr_pages << PAGE_SHIFT; - /* Sanity check: Can happen in 32bit arch...maybe */ - if (ent->addr < (unsigned long) __va(0)) + if (!virt_addr_valid(ent->addr)) goto free_out; /* cut not-mapped area. ....from ppc-32 code. */ if (ULONG_MAX - ent->addr < ent->size) ent->size = ULONG_MAX - ent->addr; - /* cut when vmalloc() area is higher than direct-map area */ - if (VMALLOC_START > (unsigned long)__va(0)) { - if (ent->addr > VMALLOC_START) - goto free_out; + /* + * We've already checked virt_addr_valid so we know this address + * is a valid pointer, therefore we can check against it to determine + * if we need to trim + */ + if (VMALLOC_START > ent->addr) { if (VMALLOC_START - ent->addr < ent->size) ent->size = VMALLOC_START - ent->addr; } diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c index a000d7547479..d06694757201 100644 --- a/fs/proc/loadavg.c +++ b/fs/proc/loadavg.c @@ -24,25 +24,13 @@ static int loadavg_proc_show(struct seq_file *m, void *v) LOAD_INT(avnrun[1]), LOAD_FRAC(avnrun[1]), LOAD_INT(avnrun[2]), LOAD_FRAC(avnrun[2]), nr_running(), nr_threads, - idr_get_cursor(&task_active_pid_ns(current)->idr)); + idr_get_cursor(&task_active_pid_ns(current)->idr) - 1); return 0; } -static int loadavg_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, loadavg_proc_show, NULL); -} - -static const struct file_operations loadavg_proc_fops = { - .open = loadavg_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int __init proc_loadavg_init(void) { - proc_create("loadavg", 0, NULL, &loadavg_proc_fops); + proc_create_single("loadavg", 0, NULL, loadavg_proc_show); return 0; } fs_initcall(proc_loadavg_init); diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 6bb20f864259..2fb04846ed11 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -26,20 +26,7 @@ void __attribute__((weak)) arch_report_meminfo(struct seq_file *m) static void show_val_kb(struct seq_file *m, const char *s, unsigned long num) { - char v[32]; - static const char blanks[7] = {' ', ' ', ' ', ' ',' ', ' ', ' '}; - int len; - - len = num_to_str(v, sizeof(v), num << (PAGE_SHIFT - 10)); - - seq_write(m, s, 16); - - if (len > 0) { - if (len < 8) - seq_write(m, blanks, 8 - len); - - seq_write(m, v, len); - } + seq_put_decimal_ull_width(m, s, num << (PAGE_SHIFT - 10), 8); seq_write(m, " kB\n", 4); } @@ -162,21 +149,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v) return 0; } -static int meminfo_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, meminfo_proc_show, NULL); -} - -static const struct file_operations meminfo_proc_fops = { - .open = meminfo_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int __init proc_meminfo_init(void) { - proc_create("meminfo", 0, NULL, &meminfo_proc_fops); + proc_create_single("meminfo", 0, NULL, meminfo_proc_show); return 0; } fs_initcall(proc_meminfo_init); diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c index 59b17e509f46..dd2b35f78b09 100644 --- a/fs/proc/namespaces.c +++ b/fs/proc/namespaces.c @@ -87,28 +87,24 @@ static const struct inode_operations proc_ns_link_inode_operations = { .setattr = proc_setattr, }; -static int proc_ns_instantiate(struct inode *dir, - struct dentry *dentry, struct task_struct *task, const void *ptr) +static struct dentry *proc_ns_instantiate(struct dentry *dentry, + struct task_struct *task, const void *ptr) { const struct proc_ns_operations *ns_ops = ptr; struct inode *inode; struct proc_inode *ei; - inode = proc_pid_make_inode(dir->i_sb, task, S_IFLNK | S_IRWXUGO); + inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRWXUGO); if (!inode) - goto out; + return ERR_PTR(-ENOENT); ei = PROC_I(inode); inode->i_op = &proc_ns_link_inode_operations; ei->ns_ops = ns_ops; + pid_update_inode(task, inode); d_set_d_op(dentry, &pid_dentry_operations); - d_add(dentry, inode); - /* Close the race of the process dying before we return the dentry */ - if (pid_revalidate(dentry, 0)) - return 0; -out: - return -ENOENT; + return d_splice_alias(inode, dentry); } static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx) @@ -147,12 +143,10 @@ const struct file_operations proc_ns_dir_operations = { static struct dentry *proc_ns_dir_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { - int error; struct task_struct *task = get_proc_task(dir); const struct proc_ns_operations **entry, **last; unsigned int len = dentry->d_name.len; - - error = -ENOENT; + struct dentry *res = ERR_PTR(-ENOENT); if (!task) goto out_no_task; @@ -167,11 +161,11 @@ static struct dentry *proc_ns_dir_lookup(struct inode *dir, if (entry == last) goto out; - error = proc_ns_instantiate(dir, dentry, task, *entry); + res = proc_ns_instantiate(dentry, task, *entry); out: put_task_struct(task); out_no_task: - return ERR_PTR(error); + return res; } const struct inode_operations proc_ns_dir_inode_operations = { diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 75634379f82e..3b63be64e436 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -113,21 +113,9 @@ static const struct seq_operations proc_nommu_region_list_seqop = { .show = nommu_region_list_show }; -static int proc_nommu_region_list_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &proc_nommu_region_list_seqop); -} - -static const struct file_operations proc_nommu_region_list_operations = { - .open = proc_nommu_region_list_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - static int __init proc_nommu_init(void) { - proc_create("maps", S_IRUGO, NULL, &proc_nommu_region_list_operations); + proc_create_seq("maps", S_IRUGO, NULL, &proc_nommu_region_list_seqop); return 0; } diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 68c06ae7888c..7d94fa005b0d 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -38,20 +38,20 @@ static struct net *get_proc_net(const struct inode *inode) return maybe_get_net(PDE_NET(PDE(inode))); } -int seq_open_net(struct inode *ino, struct file *f, - const struct seq_operations *ops, int size) +static int seq_open_net(struct inode *inode, struct file *file) { - struct net *net; + unsigned int state_size = PDE(inode)->state_size; struct seq_net_private *p; + struct net *net; - BUG_ON(size < sizeof(*p)); + WARN_ON_ONCE(state_size < sizeof(*p)); - net = get_proc_net(ino); - if (net == NULL) + net = get_proc_net(inode); + if (!net) return -ENXIO; - p = __seq_open_private(f, ops, size); - if (p == NULL) { + p = __seq_open_private(file, PDE(inode)->seq_ops, state_size); + if (!p) { put_net(net); return -ENOMEM; } @@ -60,51 +60,83 @@ int seq_open_net(struct inode *ino, struct file *f, #endif return 0; } -EXPORT_SYMBOL_GPL(seq_open_net); -int single_open_net(struct inode *inode, struct file *file, - int (*show)(struct seq_file *, void *)) +static int seq_release_net(struct inode *ino, struct file *f) { - int err; - struct net *net; - - err = -ENXIO; - net = get_proc_net(inode); - if (net == NULL) - goto err_net; - - err = single_open(file, show, net); - if (err < 0) - goto err_open; + struct seq_file *seq = f->private_data; + put_net(seq_file_net(seq)); + seq_release_private(ino, f); return 0; +} -err_open: - put_net(net); -err_net: - return err; +static const struct file_operations proc_net_seq_fops = { + .open = seq_open_net, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, + struct proc_dir_entry *parent, const struct seq_operations *ops, + unsigned int state_size, void *data) +{ + struct proc_dir_entry *p; + + p = proc_create_reg(name, mode, &parent, data); + if (!p) + return NULL; + p->proc_fops = &proc_net_seq_fops; + p->seq_ops = ops; + p->state_size = state_size; + return proc_register(parent, p); } -EXPORT_SYMBOL_GPL(single_open_net); +EXPORT_SYMBOL_GPL(proc_create_net_data); -int seq_release_net(struct inode *ino, struct file *f) +static int single_open_net(struct inode *inode, struct file *file) { - struct seq_file *seq; + struct proc_dir_entry *de = PDE(inode); + struct net *net; + int err; - seq = f->private_data; + net = get_proc_net(inode); + if (!net) + return -ENXIO; - put_net(seq_file_net(seq)); - seq_release_private(ino, f); - return 0; + err = single_open(file, de->single_show, net); + if (err) + put_net(net); + return err; } -EXPORT_SYMBOL_GPL(seq_release_net); -int single_release_net(struct inode *ino, struct file *f) +static int single_release_net(struct inode *ino, struct file *f) { struct seq_file *seq = f->private_data; put_net(seq->private); return single_release(ino, f); } -EXPORT_SYMBOL_GPL(single_release_net); + +static const struct file_operations proc_net_single_fops = { + .open = single_open_net, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release_net, +}; + +struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, + struct proc_dir_entry *parent, + int (*show)(struct seq_file *, void *), void *data) +{ + struct proc_dir_entry *p; + + p = proc_create_reg(name, mode, &parent, data); + if (!p) + return NULL; + p->proc_fops = &proc_net_single_fops; + p->single_show = show; + return proc_register(parent, p); +} +EXPORT_SYMBOL_GPL(proc_create_net_single); static struct net *get_proc_task_net(struct inode *dir) { @@ -192,15 +224,16 @@ static __net_init int proc_net_ns_init(struct net *net) int err; err = -ENOMEM; - netd = kzalloc(sizeof(*netd) + 4, GFP_KERNEL); + netd = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL); if (!netd) goto out; - netd->subdir = RB_ROOT_CACHED; + netd->subdir = RB_ROOT; netd->data = net; netd->nlink = 2; netd->namelen = 3; netd->parent = &proc_root; + netd->name = netd->inline_name; memcpy(netd->name, "net", 4); uid = make_kuid(net->user_ns, 0); @@ -223,7 +256,7 @@ static __net_init int proc_net_ns_init(struct net *net) return 0; free_net: - kfree(netd); + pde_free(netd); out: return err; } @@ -231,7 +264,7 @@ out: static __net_exit void proc_net_ns_exit(struct net *net) { remove_proc_entry("stat", net->proc_net); - kfree(net->proc_net); + pde_free(net->proc_net); } static struct pernet_operations __net_initdata proc_net_ns_ops = { diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index c41ab261397d..4d765e5e91ed 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -554,9 +554,8 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry, if (!inode) goto out; - err = NULL; d_set_d_op(dentry, &proc_sys_dentry_operations); - d_add(dentry, inode); + err = d_splice_alias(inode, dentry); out: if (h) @@ -684,6 +683,7 @@ static bool proc_sys_fill_cache(struct file *file, if (IS_ERR(child)) return false; if (d_in_lookup(child)) { + struct dentry *res; inode = proc_sys_make_inode(dir->d_sb, head, table); if (!inode) { d_lookup_done(child); @@ -691,7 +691,16 @@ static bool proc_sys_fill_cache(struct file *file, return false; } d_set_d_op(child, &proc_sys_dentry_operations); - d_add(child, inode); + res = d_splice_alias(inode, child); + d_lookup_done(child); + if (unlikely(res)) { + if (IS_ERR(res)) { + dput(child); + return false; + } + dput(child); + child = res; + } } } inode = d_inode(child); @@ -707,14 +716,14 @@ static bool proc_sys_link_fill_cache(struct file *file, struct ctl_table *table) { bool ret = true; + head = sysctl_head_grab(head); + if (IS_ERR(head)) + return false; - if (S_ISLNK(table->mode)) { - /* It is not an error if we can not follow the link ignore it */ - int err = sysctl_follow_link(&head, &table); - if (err) - goto out; - } + /* It is not an error if we can not follow the link ignore it */ + if (sysctl_follow_link(&head, &table)) + goto out; ret = proc_sys_fill_cache(file, ctx, head, table); out: @@ -1086,7 +1095,7 @@ static int sysctl_check_table_array(const char *path, struct ctl_table *table) if ((table->proc_handler == proc_douintvec) || (table->proc_handler == proc_douintvec_minmax)) { if (table->maxlen != sizeof(unsigned int)) - err |= sysctl_err(path, table, "array now allowed"); + err |= sysctl_err(path, table, "array not allowed"); } return err; diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c index d0cf1c50bb6c..c69ff191e5d8 100644 --- a/fs/proc/proc_tty.c +++ b/fs/proc/proc_tty.c @@ -126,18 +126,6 @@ static const struct seq_operations tty_drivers_op = { .show = show_tty_driver }; -static int tty_drivers_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &tty_drivers_op); -} - -static const struct file_operations proc_tty_drivers_operations = { - .open = tty_drivers_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; - /* * This function is called by tty_register_driver() to handle * registering the driver's /proc handler into /proc/tty/driver/<foo> @@ -147,11 +135,11 @@ void proc_tty_register_driver(struct tty_driver *driver) struct proc_dir_entry *ent; if (!driver->driver_name || driver->proc_entry || - !driver->ops->proc_fops) + !driver->ops->proc_show) return; - ent = proc_create_data(driver->driver_name, 0, proc_tty_driver, - driver->ops->proc_fops, driver); + ent = proc_create_single_data(driver->driver_name, 0, proc_tty_driver, + driver->ops->proc_show, driver); driver->proc_entry = ent; } @@ -186,6 +174,6 @@ void __init proc_tty_init(void) * entry. */ proc_tty_driver = proc_mkdir_mode("tty/driver", S_IRUSR|S_IXUSR, NULL); - proc_create("tty/ldiscs", 0, NULL, &tty_ldiscs_proc_fops); - proc_create("tty/drivers", 0, NULL, &proc_tty_drivers_operations); + proc_create_seq("tty/ldiscs", 0, NULL, &tty_ldiscs_seq_ops); + proc_create_seq("tty/drivers", 0, NULL, &tty_drivers_op); } diff --git a/fs/proc/root.c b/fs/proc/root.c index ede8e64974be..61b7340b357a 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -123,23 +123,13 @@ static struct file_system_type proc_fs_type = { void __init proc_root_init(void) { - int err; - - proc_init_inodecache(); + proc_init_kmemcache(); set_proc_pid_nlink(); - err = register_filesystem(&proc_fs_type); - if (err) - return; - proc_self_init(); proc_thread_self_init(); proc_symlink("mounts", NULL, "self/mounts"); proc_net_init(); - -#ifdef CONFIG_SYSVIPC - proc_mkdir("sysvipc", NULL); -#endif proc_mkdir("fs", NULL); proc_mkdir("driver", NULL); proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */ @@ -150,6 +140,8 @@ void __init proc_root_init(void) proc_tty_init(); proc_mkdir("bus", NULL); proc_sys_init(); + + register_filesystem(&proc_fs_type); } static int proc_root_getattr(const struct path *path, struct kstat *stat, @@ -207,12 +199,13 @@ struct proc_dir_entry proc_root = { .namelen = 5, .mode = S_IFDIR | S_IRUGO | S_IXUGO, .nlink = 2, - .count = ATOMIC_INIT(1), + .refcnt = REFCOUNT_INIT(1), .proc_iops = &proc_root_inode_operations, .proc_fops = &proc_root_operations, .parent = &proc_root, - .subdir = RB_ROOT_CACHED, - .name = "/proc", + .subdir = RB_ROOT, + .name = proc_root.inline_name, + .inline_name = "/proc", }; int pid_ns_prepare_proc(struct pid_namespace *ns) diff --git a/fs/proc/self.c b/fs/proc/self.c index 4d7d061696b3..127265e5c55f 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -12,7 +12,7 @@ static const char *proc_self_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - struct pid_namespace *ns = inode->i_sb->s_fs_info; + struct pid_namespace *ns = proc_pid_ns(inode); pid_t tgid = task_tgid_nr_ns(current, ns); char *name; @@ -36,7 +36,7 @@ static unsigned self_inum __ro_after_init; int proc_setup_self(struct super_block *s) { struct inode *root_inode = d_inode(s->s_root); - struct pid_namespace *ns = s->s_fs_info; + struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *self; inode_lock(root_inode); diff --git a/fs/proc/softirqs.c b/fs/proc/softirqs.c index 24072cc06e65..12901dcf57e2 100644 --- a/fs/proc/softirqs.c +++ b/fs/proc/softirqs.c @@ -25,21 +25,9 @@ static int show_softirqs(struct seq_file *p, void *v) return 0; } -static int softirqs_open(struct inode *inode, struct file *file) -{ - return single_open(file, show_softirqs, NULL); -} - -static const struct file_operations proc_softirqs_operations = { - .open = softirqs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int __init proc_softirqs_init(void) { - proc_create("softirqs", 0, NULL, &proc_softirqs_operations); + proc_create_single("softirqs", 0, NULL, show_softirqs); return 0; } fs_initcall(proc_softirqs_init); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ec6d2983a5cb..a20c6e495bb2 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -24,6 +24,8 @@ #include <asm/tlbflush.h> #include "internal.h" +#define SEQ_PUT_DEC(str, val) \ + seq_put_decimal_ull_width(m, str, (val) << (PAGE_SHIFT-10), 8) void task_mem(struct seq_file *m, struct mm_struct *mm) { unsigned long text, lib, swap, anon, file, shmem; @@ -53,39 +55,28 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) lib = (mm->exec_vm << PAGE_SHIFT) - text; swap = get_mm_counter(mm, MM_SWAPENTS); - seq_printf(m, - "VmPeak:\t%8lu kB\n" - "VmSize:\t%8lu kB\n" - "VmLck:\t%8lu kB\n" - "VmPin:\t%8lu kB\n" - "VmHWM:\t%8lu kB\n" - "VmRSS:\t%8lu kB\n" - "RssAnon:\t%8lu kB\n" - "RssFile:\t%8lu kB\n" - "RssShmem:\t%8lu kB\n" - "VmData:\t%8lu kB\n" - "VmStk:\t%8lu kB\n" - "VmExe:\t%8lu kB\n" - "VmLib:\t%8lu kB\n" - "VmPTE:\t%8lu kB\n" - "VmSwap:\t%8lu kB\n", - hiwater_vm << (PAGE_SHIFT-10), - total_vm << (PAGE_SHIFT-10), - mm->locked_vm << (PAGE_SHIFT-10), - mm->pinned_vm << (PAGE_SHIFT-10), - hiwater_rss << (PAGE_SHIFT-10), - total_rss << (PAGE_SHIFT-10), - anon << (PAGE_SHIFT-10), - file << (PAGE_SHIFT-10), - shmem << (PAGE_SHIFT-10), - mm->data_vm << (PAGE_SHIFT-10), - mm->stack_vm << (PAGE_SHIFT-10), - text >> 10, - lib >> 10, - mm_pgtables_bytes(mm) >> 10, - swap << (PAGE_SHIFT-10)); + SEQ_PUT_DEC("VmPeak:\t", hiwater_vm); + SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm); + SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm); + SEQ_PUT_DEC(" kB\nVmPin:\t", mm->pinned_vm); + SEQ_PUT_DEC(" kB\nVmHWM:\t", hiwater_rss); + SEQ_PUT_DEC(" kB\nVmRSS:\t", total_rss); + SEQ_PUT_DEC(" kB\nRssAnon:\t", anon); + SEQ_PUT_DEC(" kB\nRssFile:\t", file); + SEQ_PUT_DEC(" kB\nRssShmem:\t", shmem); + SEQ_PUT_DEC(" kB\nVmData:\t", mm->data_vm); + SEQ_PUT_DEC(" kB\nVmStk:\t", mm->stack_vm); + seq_put_decimal_ull_width(m, + " kB\nVmExe:\t", text >> 10, 8); + seq_put_decimal_ull_width(m, + " kB\nVmLib:\t", lib >> 10, 8); + seq_put_decimal_ull_width(m, + " kB\nVmPTE:\t", mm_pgtables_bytes(mm) >> 10, 8); + SEQ_PUT_DEC(" kB\nVmSwap:\t", swap); + seq_puts(m, " kB\n"); hugetlb_report_usage(m, mm); } +#undef SEQ_PUT_DEC unsigned long task_vsize(struct mm_struct *mm) { @@ -287,15 +278,18 @@ static void show_vma_header_prefix(struct seq_file *m, dev_t dev, unsigned long ino) { seq_setwidth(m, 25 + sizeof(void *) * 6 - 1); - seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ", - start, - end, - flags & VM_READ ? 'r' : '-', - flags & VM_WRITE ? 'w' : '-', - flags & VM_EXEC ? 'x' : '-', - flags & VM_MAYSHARE ? 's' : 'p', - pgoff, - MAJOR(dev), MINOR(dev), ino); + seq_put_hex_ll(m, NULL, start, 8); + seq_put_hex_ll(m, "-", end, 8); + seq_putc(m, ' '); + seq_putc(m, flags & VM_READ ? 'r' : '-'); + seq_putc(m, flags & VM_WRITE ? 'w' : '-'); + seq_putc(m, flags & VM_EXEC ? 'x' : '-'); + seq_putc(m, flags & VM_MAYSHARE ? 's' : 'p'); + seq_put_hex_ll(m, " ", pgoff, 8); + seq_put_hex_ll(m, " ", MAJOR(dev), 2); + seq_put_hex_ll(m, ":", MINOR(dev), 2); + seq_put_decimal_ull(m, " ", ino); + seq_putc(m, ' '); } static void @@ -694,8 +688,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) if (!mnemonics[i][0]) continue; if (vma->vm_flags & (1UL << i)) { - seq_printf(m, "%c%c ", - mnemonics[i][0], mnemonics[i][1]); + seq_putc(m, mnemonics[i][0]); + seq_putc(m, mnemonics[i][1]); + seq_putc(m, ' '); } } seq_putc(m, '\n'); @@ -736,6 +731,8 @@ void __weak arch_show_smap(struct seq_file *m, struct vm_area_struct *vma) { } +#define SEQ_PUT_DEC(str, val) \ + seq_put_decimal_ull_width(m, str, (val) >> 10, 8) static int show_smap(struct seq_file *m, void *v, int is_pid) { struct proc_maps_private *priv = m->private; @@ -809,51 +806,34 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) ret = SEQ_SKIP; } - if (!rollup_mode) - seq_printf(m, - "Size: %8lu kB\n" - "KernelPageSize: %8lu kB\n" - "MMUPageSize: %8lu kB\n", - (vma->vm_end - vma->vm_start) >> 10, - vma_kernel_pagesize(vma) >> 10, - vma_mmu_pagesize(vma) >> 10); - - - if (!rollup_mode || last_vma) - seq_printf(m, - "Rss: %8lu kB\n" - "Pss: %8lu kB\n" - "Shared_Clean: %8lu kB\n" - "Shared_Dirty: %8lu kB\n" - "Private_Clean: %8lu kB\n" - "Private_Dirty: %8lu kB\n" - "Referenced: %8lu kB\n" - "Anonymous: %8lu kB\n" - "LazyFree: %8lu kB\n" - "AnonHugePages: %8lu kB\n" - "ShmemPmdMapped: %8lu kB\n" - "Shared_Hugetlb: %8lu kB\n" - "Private_Hugetlb: %7lu kB\n" - "Swap: %8lu kB\n" - "SwapPss: %8lu kB\n" - "Locked: %8lu kB\n", - mss->resident >> 10, - (unsigned long)(mss->pss >> (10 + PSS_SHIFT)), - mss->shared_clean >> 10, - mss->shared_dirty >> 10, - mss->private_clean >> 10, - mss->private_dirty >> 10, - mss->referenced >> 10, - mss->anonymous >> 10, - mss->lazyfree >> 10, - mss->anonymous_thp >> 10, - mss->shmem_thp >> 10, - mss->shared_hugetlb >> 10, - mss->private_hugetlb >> 10, - mss->swap >> 10, - (unsigned long)(mss->swap_pss >> (10 + PSS_SHIFT)), - (unsigned long)(mss->pss >> (10 + PSS_SHIFT))); + if (!rollup_mode) { + SEQ_PUT_DEC("Size: ", vma->vm_end - vma->vm_start); + SEQ_PUT_DEC(" kB\nKernelPageSize: ", vma_kernel_pagesize(vma)); + SEQ_PUT_DEC(" kB\nMMUPageSize: ", vma_mmu_pagesize(vma)); + seq_puts(m, " kB\n"); + } + if (!rollup_mode || last_vma) { + SEQ_PUT_DEC("Rss: ", mss->resident); + SEQ_PUT_DEC(" kB\nPss: ", mss->pss >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nShared_Clean: ", mss->shared_clean); + SEQ_PUT_DEC(" kB\nShared_Dirty: ", mss->shared_dirty); + SEQ_PUT_DEC(" kB\nPrivate_Clean: ", mss->private_clean); + SEQ_PUT_DEC(" kB\nPrivate_Dirty: ", mss->private_dirty); + SEQ_PUT_DEC(" kB\nReferenced: ", mss->referenced); + SEQ_PUT_DEC(" kB\nAnonymous: ", mss->anonymous); + SEQ_PUT_DEC(" kB\nLazyFree: ", mss->lazyfree); + SEQ_PUT_DEC(" kB\nAnonHugePages: ", mss->anonymous_thp); + SEQ_PUT_DEC(" kB\nShmemPmdMapped: ", mss->shmem_thp); + SEQ_PUT_DEC(" kB\nShared_Hugetlb: ", mss->shared_hugetlb); + seq_put_decimal_ull_width(m, " kB\nPrivate_Hugetlb: ", + mss->private_hugetlb >> 10, 7); + SEQ_PUT_DEC(" kB\nSwap: ", mss->swap); + SEQ_PUT_DEC(" kB\nSwapPss: ", + mss->swap_pss >> PSS_SHIFT); + SEQ_PUT_DEC(" kB\nLocked: ", mss->pss >> PSS_SHIFT); + seq_puts(m, " kB\n"); + } if (!rollup_mode) { arch_show_smap(m, vma); show_smap_vma_flags(m, vma); @@ -861,6 +841,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) m_cache_vma(m, vma); return ret; } +#undef SEQ_PUT_DEC static int show_pid_smap(struct seq_file *m, void *v) { @@ -956,7 +937,7 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, /* * The soft-dirty tracker uses #PF-s to catch writes * to pages, so write-protect the pte as well. See the - * Documentation/vm/soft-dirty.txt for full description + * Documentation/admin-guide/mm/soft-dirty.rst for full description * of how soft-dirty works. */ pte_t ptent = *pte; @@ -1329,9 +1310,11 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION else if (is_swap_pmd(pmd)) { swp_entry_t entry = pmd_to_swp_entry(pmd); + unsigned long offset = swp_offset(entry); + offset += (addr & ~PMD_MASK) >> PAGE_SHIFT; frame = swp_type(entry) | - (swp_offset(entry) << MAX_SWAPFILES_SHIFT); + (offset << MAX_SWAPFILES_SHIFT); flags |= PM_SWAP; if (pmd_swp_soft_dirty(pmd)) flags |= PM_SOFT_DIRTY; @@ -1351,6 +1334,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, break; if (pm->show_pfn && (flags & PM_PRESENT)) frame++; + else if (flags & PM_SWAP) + frame += (1 << MAX_SWAPFILES_SHIFT); } spin_unlock(ptl); return err; @@ -1436,7 +1421,7 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, * Bits 0-54 page frame number (PFN) if present * Bits 0-4 swap type if swapped * Bits 5-54 swap offset if swapped - * Bit 55 pte is soft-dirty (see Documentation/vm/soft-dirty.txt) + * Bit 55 pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst) * Bit 56 page exclusively mapped * Bits 57-60 zero * Bit 61 page is file-page or shared-anon diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c index 9d2efaca499f..b905010ca9eb 100644 --- a/fs/proc/thread_self.c +++ b/fs/proc/thread_self.c @@ -12,7 +12,7 @@ static const char *proc_thread_self_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { - struct pid_namespace *ns = inode->i_sb->s_fs_info; + struct pid_namespace *ns = proc_pid_ns(inode); pid_t tgid = task_tgid_nr_ns(current, ns); pid_t pid = task_pid_nr_ns(current, ns); char *name; @@ -36,7 +36,7 @@ static unsigned thread_self_inum __ro_after_init; int proc_setup_thread_self(struct super_block *s) { struct inode *root_inode = d_inode(s->s_root); - struct pid_namespace *ns = s->s_fs_info; + struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *thread_self; inode_lock(root_inode); diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index 95a708d83721..3bd12f955867 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -30,21 +30,9 @@ static int uptime_proc_show(struct seq_file *m, void *v) return 0; } -static int uptime_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, uptime_proc_show, NULL); -} - -static const struct file_operations uptime_proc_fops = { - .open = uptime_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int __init proc_uptime_init(void) { - proc_create("uptime", 0, NULL, &uptime_proc_fops); + proc_create_single("uptime", 0, NULL, uptime_proc_show); return 0; } fs_initcall(proc_uptime_init); diff --git a/fs/proc/version.c b/fs/proc/version.c index 94901e8e700d..b449f186577f 100644 --- a/fs/proc/version.c +++ b/fs/proc/version.c @@ -15,21 +15,9 @@ static int version_proc_show(struct seq_file *m, void *v) return 0; } -static int version_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, version_proc_show, NULL); -} - -static const struct file_operations version_proc_fops = { - .open = version_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int __init proc_version_init(void) { - proc_create("version", 0, NULL, &version_proc_fops); + proc_create_single("version", 0, NULL, version_proc_show); return 0; } fs_initcall(proc_version_init); |