summaryrefslogtreecommitdiff
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/Kconfig69
-rw-r--r--fs/proc/array.c75
-rw-r--r--fs/proc/base.c120
-rw-r--r--fs/proc/generic.c51
-rw-r--r--fs/proc/inode.c90
-rw-r--r--fs/proc/internal.h10
-rw-r--r--fs/proc/kcore.c10
-rw-r--r--fs/proc/kmsg.c2
-rw-r--r--fs/proc/nommu.c4
-rw-r--r--fs/proc/proc_misc.c47
-rw-r--r--fs/proc/proc_net.c43
-rw-r--r--fs/proc/proc_sysctl.c433
-rw-r--r--fs/proc/proc_tty.c48
-rw-r--r--fs/proc/task_mmu.c102
-rw-r--r--fs/proc/task_nommu.c5
-rw-r--r--fs/proc/vmcore.c6
16 files changed, 604 insertions, 511 deletions
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
new file mode 100644
index 000000000000..50f8f0600f06
--- /dev/null
+++ b/fs/proc/Kconfig
@@ -0,0 +1,69 @@
+config PROC_FS
+ bool "/proc file system support" if EMBEDDED
+ default y
+ help
+ This is a virtual file system providing information about the status
+ of the system. "Virtual" means that it doesn't take up any space on
+ your hard disk: the files are created on the fly by the kernel when
+ you try to access them. Also, you cannot read the files with older
+ version of the program less: you need to use more or cat.
+
+ It's totally cool; for example, "cat /proc/interrupts" gives
+ information about what the different IRQs are used for at the moment
+ (there is a small number of Interrupt ReQuest lines in your computer
+ that are used by the attached devices to gain the CPU's attention --
+ often a source of trouble if two devices are mistakenly configured
+ to use the same IRQ). The program procinfo to display some
+ information about your system gathered from the /proc file system.
+
+ Before you can use the /proc file system, it has to be mounted,
+ meaning it has to be given a location in the directory hierarchy.
+ That location should be /proc. A command such as "mount -t proc proc
+ /proc" or the equivalent line in /etc/fstab does the job.
+
+ The /proc file system is explained in the file
+ <file:Documentation/filesystems/proc.txt> and on the proc(5) manpage
+ ("man 5 proc").
+
+ This option will enlarge your kernel by about 67 KB. Several
+ programs depend on this, so everyone should say Y here.
+
+config PROC_KCORE
+ bool "/proc/kcore support" if !ARM
+ depends on PROC_FS && MMU
+
+config PROC_VMCORE
+ bool "/proc/vmcore support (EXPERIMENTAL)"
+ depends on PROC_FS && CRASH_DUMP
+ default y
+ help
+ Exports the dump image of crashed kernel in ELF format.
+
+config PROC_SYSCTL
+ bool "Sysctl support (/proc/sys)" if EMBEDDED
+ depends on PROC_FS
+ select SYSCTL
+ default y
+ ---help---
+ The sysctl interface provides a means of dynamically changing
+ certain kernel parameters and variables on the fly without requiring
+ a recompile of the kernel or reboot of the system. The primary
+ interface is through /proc/sys. If you say Y here a tree of
+ modifiable sysctl entries will be generated beneath the
+ /proc/sys directory. They are explained in the files
+ in <file:Documentation/sysctl/>. Note that enabling this
+ option will enlarge the kernel by at least 8 KB.
+
+ As it is generally a good thing, you should say Y here unless
+ building a kernel for install/rescue disks or your system is very
+ limited in memory.
+
+config PROC_PAGE_MONITOR
+ default y
+ depends on PROC_FS && MMU
+ bool "Enable /proc page monitoring" if EMBEDDED
+ help
+ Various /proc files exist to monitor process memory utilization:
+ /proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap,
+ /proc/kpagecount, and /proc/kpageflags. Disabling these
+ interfaces will reduce the size of the kernel by approximately 4kb.
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 797d775e0354..f4bc0e789539 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -80,16 +80,12 @@
#include <linux/delayacct.h>
#include <linux/seq_file.h>
#include <linux/pid_namespace.h>
+#include <linux/tracehook.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include "internal.h"
-/* Gcc optimizes away "strlen(x)" for constant x */
-#define ADDBUF(buffer, string) \
-do { memcpy(buffer, string, strlen(string)); \
- buffer += strlen(string); } while (0)
-
static inline void task_name(struct seq_file *m, struct task_struct *p)
{
int i;
@@ -168,8 +164,12 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
rcu_read_lock();
ppid = pid_alive(p) ?
task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
- tpid = pid_alive(p) && p->ptrace ?
- task_pid_nr_ns(rcu_dereference(p->parent), ns) : 0;
+ tpid = 0;
+ if (pid_alive(p)) {
+ struct task_struct *tracer = tracehook_tracer_task(p);
+ if (tracer)
+ tpid = task_pid_nr_ns(tracer, ns);
+ }
seq_printf(m,
"State:\t%s\n"
"Tgid:\t%d\n"
@@ -256,7 +256,6 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p)
sigemptyset(&ignored);
sigemptyset(&caught);
- rcu_read_lock();
if (lock_task_sighand(p, &flags)) {
pending = p->pending.signal;
shpending = p->signal->shared_pending.signal;
@@ -267,7 +266,6 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p)
qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur;
unlock_task_sighand(p, &flags);
}
- rcu_read_unlock();
seq_printf(m, "Threads:\t%d\n", num_threads);
seq_printf(m, "SigQ:\t%lu/%lu\n", qsize, qlim);
@@ -332,65 +330,6 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
return 0;
}
-/*
- * Use precise platform statistics if available:
- */
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-static cputime_t task_utime(struct task_struct *p)
-{
- return p->utime;
-}
-
-static cputime_t task_stime(struct task_struct *p)
-{
- return p->stime;
-}
-#else
-static cputime_t task_utime(struct task_struct *p)
-{
- clock_t utime = cputime_to_clock_t(p->utime),
- total = utime + cputime_to_clock_t(p->stime);
- u64 temp;
-
- /*
- * Use CFS's precise accounting:
- */
- temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
-
- if (total) {
- temp *= utime;
- do_div(temp, total);
- }
- utime = (clock_t)temp;
-
- p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
- return p->prev_utime;
-}
-
-static cputime_t task_stime(struct task_struct *p)
-{
- clock_t stime;
-
- /*
- * Use CFS's precise accounting. (we subtract utime from
- * the total, to make sure the total observed by userspace
- * grows monotonically - apps rely on that):
- */
- stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
- cputime_to_clock_t(task_utime(p));
-
- if (stime >= 0)
- p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
-
- return p->prev_stime;
-}
-#endif
-
-static cputime_t task_gtime(struct task_struct *p)
-{
- return p->gtime;
-}
-
static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task, int whole)
{
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 3b455371e7ff..b5918ae8ca79 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -53,6 +53,7 @@
#include <linux/time.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
+#include <linux/task_io_accounting_ops.h>
#include <linux/init.h>
#include <linux/capability.h>
#include <linux/file.h>
@@ -69,6 +70,7 @@
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/ptrace.h>
+#include <linux/tracehook.h>
#include <linux/cgroup.h>
#include <linux/cpuset.h>
#include <linux/audit.h>
@@ -146,9 +148,6 @@ static unsigned int pid_entry_count_dirs(const struct pid_entry *entries,
return count;
}
-int maps_protect;
-EXPORT_SYMBOL(maps_protect);
-
static struct fs_struct *get_fs_struct(struct task_struct *task)
{
struct fs_struct *fs;
@@ -162,7 +161,6 @@ static struct fs_struct *get_fs_struct(struct task_struct *task)
static int get_nr_threads(struct task_struct *tsk)
{
- /* Must be called with the rcu_read_lock held */
unsigned long flags;
int count = 0;
@@ -231,10 +229,14 @@ static int check_mem_permission(struct task_struct *task)
* If current is actively ptrace'ing, and would also be
* permitted to freshly attach with ptrace now, permit it.
*/
- if (task->parent == current && (task->ptrace & PT_PTRACED) &&
- task_is_stopped_or_traced(task) &&
- ptrace_may_attach(task))
- return 0;
+ if (task_is_stopped_or_traced(task)) {
+ int match;
+ rcu_read_lock();
+ match = (tracehook_tracer_task(task) == current);
+ rcu_read_unlock();
+ if (match && ptrace_may_access(task, PTRACE_MODE_ATTACH))
+ return 0;
+ }
/*
* Noone else is allowed.
@@ -251,7 +253,8 @@ struct mm_struct *mm_for_maps(struct task_struct *task)
task_lock(task);
if (task->mm != mm)
goto out;
- if (task->mm != current->mm && __ptrace_may_attach(task) < 0)
+ if (task->mm != current->mm &&
+ __ptrace_may_access(task, PTRACE_MODE_READ) < 0)
goto out;
task_unlock(task);
return mm;
@@ -464,14 +467,10 @@ static int proc_pid_limits(struct task_struct *task, char *buffer)
struct rlimit rlim[RLIM_NLIMITS];
- rcu_read_lock();
- if (!lock_task_sighand(task,&flags)) {
- rcu_read_unlock();
+ if (!lock_task_sighand(task, &flags))
return 0;
- }
memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS);
unlock_task_sighand(task, &flags);
- rcu_read_unlock();
/*
* print the file header
@@ -503,6 +502,26 @@ static int proc_pid_limits(struct task_struct *task, char *buffer)
return count;
}
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+static int proc_pid_syscall(struct task_struct *task, char *buffer)
+{
+ long nr;
+ unsigned long args[6], sp, pc;
+
+ if (task_current_syscall(task, &nr, args, 6, &sp, &pc))
+ return sprintf(buffer, "running\n");
+
+ if (nr < 0)
+ return sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
+
+ return sprintf(buffer,
+ "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
+ nr,
+ args[0], args[1], args[2], args[3], args[4], args[5],
+ sp, pc);
+}
+#endif /* CONFIG_HAVE_ARCH_TRACEHOOK */
+
/************************************************************************/
/* Here the fs part begins */
/************************************************************************/
@@ -518,7 +537,7 @@ static int proc_fd_access_allowed(struct inode *inode)
*/
task = get_proc_task(inode);
if (task) {
- allowed = ptrace_may_attach(task);
+ allowed = ptrace_may_access(task, PTRACE_MODE_READ);
put_task_struct(task);
}
return allowed;
@@ -904,7 +923,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
if (!task)
goto out_no_task;
- if (!ptrace_may_attach(task))
+ if (!ptrace_may_access(task, PTRACE_MODE_READ))
goto out;
ret = -ENOMEM;
@@ -1833,8 +1852,7 @@ static const struct file_operations proc_fd_operations = {
* /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,
- struct nameidata *nd)
+static int proc_fd_permission(struct inode *inode, int mask)
{
int rv;
@@ -2375,29 +2393,54 @@ static int proc_base_fill_cache(struct file *filp, void *dirent,
}
#ifdef CONFIG_TASK_IO_ACCOUNTING
-static int proc_pid_io_accounting(struct task_struct *task, char *buffer)
+static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
{
+ struct task_io_accounting acct = task->ioac;
+ unsigned long flags;
+
+ if (whole && lock_task_sighand(task, &flags)) {
+ struct task_struct *t = task;
+
+ task_io_accounting_add(&acct, &task->signal->ioac);
+ while_each_thread(task, t)
+ task_io_accounting_add(&acct, &t->ioac);
+
+ unlock_task_sighand(task, &flags);
+ }
return sprintf(buffer,
-#ifdef CONFIG_TASK_XACCT
"rchar: %llu\n"
"wchar: %llu\n"
"syscr: %llu\n"
"syscw: %llu\n"
-#endif
"read_bytes: %llu\n"
"write_bytes: %llu\n"
"cancelled_write_bytes: %llu\n",
-#ifdef CONFIG_TASK_XACCT
- (unsigned long long)task->rchar,
- (unsigned long long)task->wchar,
- (unsigned long long)task->syscr,
- (unsigned long long)task->syscw,
-#endif
- (unsigned long long)task->ioac.read_bytes,
- (unsigned long long)task->ioac.write_bytes,
- (unsigned long long)task->ioac.cancelled_write_bytes);
+ (unsigned long long)acct.rchar,
+ (unsigned long long)acct.wchar,
+ (unsigned long long)acct.syscr,
+ (unsigned long long)acct.syscw,
+ (unsigned long long)acct.read_bytes,
+ (unsigned long long)acct.write_bytes,
+ (unsigned long long)acct.cancelled_write_bytes);
+}
+
+static int proc_tid_io_accounting(struct task_struct *task, char *buffer)
+{
+ return do_io_accounting(task, buffer, 0);
+}
+
+static int proc_tgid_io_accounting(struct task_struct *task, char *buffer)
+{
+ return do_io_accounting(task, buffer, 1);
+}
+#endif /* CONFIG_TASK_IO_ACCOUNTING */
+
+static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
+{
+ seq_printf(m, "%08x\n", task->personality);
+ return 0;
}
-#endif
/*
* Thread groups
@@ -2415,10 +2458,14 @@ static const struct pid_entry tgid_base_stuff[] = {
REG("environ", S_IRUSR, environ),
INF("auxv", S_IRUSR, pid_auxv),
ONE("status", S_IRUGO, pid_status),
+ ONE("personality", S_IRUSR, pid_personality),
INF("limits", S_IRUSR, pid_limits),
#ifdef CONFIG_SCHED_DEBUG
REG("sched", S_IRUGO|S_IWUSR, pid_sched),
#endif
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+ INF("syscall", S_IRUSR, pid_syscall),
+#endif
INF("cmdline", S_IRUGO, pid_cmdline),
ONE("stat", S_IRUGO, tgid_stat),
ONE("statm", S_IRUGO, pid_statm),
@@ -2469,7 +2516,7 @@ static const struct pid_entry tgid_base_stuff[] = {
REG("coredump_filter", S_IRUGO|S_IWUSR, coredump_filter),
#endif
#ifdef CONFIG_TASK_IO_ACCOUNTING
- INF("io", S_IRUGO, pid_io_accounting),
+ INF("io", S_IRUGO, tgid_io_accounting),
#endif
};
@@ -2747,10 +2794,14 @@ static const struct pid_entry tid_base_stuff[] = {
REG("environ", S_IRUSR, environ),
INF("auxv", S_IRUSR, pid_auxv),
ONE("status", S_IRUGO, pid_status),
+ ONE("personality", S_IRUSR, pid_personality),
INF("limits", S_IRUSR, pid_limits),
#ifdef CONFIG_SCHED_DEBUG
REG("sched", S_IRUGO|S_IWUSR, pid_sched),
#endif
+#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
+ INF("syscall", S_IRUSR, pid_syscall),
+#endif
INF("cmdline", S_IRUGO, pid_cmdline),
ONE("stat", S_IRUGO, tid_stat),
ONE("statm", S_IRUGO, pid_statm),
@@ -2796,6 +2847,9 @@ static const struct pid_entry tid_base_stuff[] = {
#ifdef CONFIG_FAULT_INJECTION
REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject),
#endif
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+ INF("io", S_IRUGO, tid_io_accounting),
+#endif
};
static int proc_tid_base_readdir(struct file * filp,
@@ -3035,9 +3089,7 @@ static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct
generic_fillattr(inode, stat);
if (p) {
- rcu_read_lock();
stat->nlink += get_nr_threads(p);
- rcu_read_unlock();
put_task_struct(p);
}
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 43e54e86cefd..7821589a17d5 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -300,10 +300,10 @@ out:
return rtn;
}
-static DEFINE_IDR(proc_inum_idr);
+static DEFINE_IDA(proc_inum_ida);
static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */
-#define PROC_DYNAMIC_FIRST 0xF0000000UL
+#define PROC_DYNAMIC_FIRST 0xF0000000U
/*
* Return an inode number between PROC_DYNAMIC_FIRST and
@@ -311,36 +311,34 @@ static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */
*/
static unsigned int get_inode_number(void)
{
- int i, inum = 0;
+ unsigned int i;
int error;
retry:
- if (idr_pre_get(&proc_inum_idr, GFP_KERNEL) == 0)
+ if (ida_pre_get(&proc_inum_ida, GFP_KERNEL) == 0)
return 0;
spin_lock(&proc_inum_lock);
- error = idr_get_new(&proc_inum_idr, NULL, &i);
+ error = ida_get_new(&proc_inum_ida, &i);
spin_unlock(&proc_inum_lock);
if (error == -EAGAIN)
goto retry;
else if (error)
return 0;
- inum = (i & MAX_ID_MASK) + PROC_DYNAMIC_FIRST;
-
- /* inum will never be more than 0xf0ffffff, so no check
- * for overflow.
- */
-
- return inum;
+ if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {
+ spin_lock(&proc_inum_lock);
+ ida_remove(&proc_inum_ida, i);
+ spin_unlock(&proc_inum_lock);
+ return 0;
+ }
+ return PROC_DYNAMIC_FIRST + i;
}
static void release_inode_number(unsigned int inum)
{
- int id = (inum - PROC_DYNAMIC_FIRST) | ~MAX_ID_MASK;
-
spin_lock(&proc_inum_lock);
- idr_remove(&proc_inum_idr, id);
+ ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
spin_unlock(&proc_inum_lock);
}
@@ -549,8 +547,8 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
for (tmp = dir->subdir; tmp; tmp = tmp->next)
if (strcmp(tmp->name, dp->name) == 0) {
- printk(KERN_WARNING "proc_dir_entry '%s' already "
- "registered\n", dp->name);
+ printk(KERN_WARNING "proc_dir_entry '%s/%s' already registered\n",
+ dir->name, dp->name);
dump_stack();
break;
}
@@ -597,6 +595,7 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
ent->pde_users = 0;
spin_lock_init(&ent->pde_unload_lock);
ent->pde_unload_completion = NULL;
+ INIT_LIST_HEAD(&ent->pde_openers);
out:
return ent;
}
@@ -789,15 +788,25 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
spin_unlock(&de->pde_unload_lock);
continue_removing:
+ spin_lock(&de->pde_unload_lock);
+ while (!list_empty(&de->pde_openers)) {
+ struct pde_opener *pdeo;
+
+ pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh);
+ list_del(&pdeo->lh);
+ spin_unlock(&de->pde_unload_lock);
+ pdeo->release(pdeo->inode, pdeo->file);
+ kfree(pdeo);
+ spin_lock(&de->pde_unload_lock);
+ }
+ spin_unlock(&de->pde_unload_lock);
+
if (S_ISDIR(de->mode))
parent->nlink--;
de->nlink = 0;
- if (de->subdir) {
- printk(KERN_WARNING "%s: removing non-empty directory "
+ WARN(de->subdir, KERN_WARNING "%s: removing non-empty directory "
"'%s/%s', leaking at least '%s'\n", __func__,
de->parent->name, de->name, de->subdir->name);
- WARN_ON(1);
- }
if (atomic_dec_and_test(&de->count))
free_proc_entry(de);
}
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index b08d10017911..c6b4fa7e3b49 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -17,6 +17,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/smp_lock.h>
+#include <linux/sysctl.h>
#include <asm/system.h>
#include <asm/uaccess.h>
@@ -65,6 +66,8 @@ static void proc_delete_inode(struct inode *inode)
module_put(de->owner);
de_put(de);
}
+ if (PROC_I(inode)->sysctl)
+ sysctl_head_put(PROC_I(inode)->sysctl);
clear_inode(inode);
}
@@ -84,6 +87,8 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
ei->fd = 0;
ei->op.proc_get_link = NULL;
ei->pde = NULL;
+ ei->sysctl = NULL;
+ ei->sysctl_entry = NULL;
inode = &ei->vfs_inode;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
return inode;
@@ -94,7 +99,7 @@ static void proc_destroy_inode(struct inode *inode)
kmem_cache_free(proc_inode_cachep, PROC_I(inode));
}
-static void init_once(struct kmem_cache * cachep, void *foo)
+static void init_once(void *foo)
{
struct proc_inode *ei = (struct proc_inode *) foo;
@@ -111,27 +116,25 @@ int __init proc_init_inodecache(void)
return 0;
}
-static int proc_remount(struct super_block *sb, int *flags, char *data)
-{
- *flags |= MS_NODIRATIME;
- return 0;
-}
-
static const struct super_operations proc_sops = {
.alloc_inode = proc_alloc_inode,
.destroy_inode = proc_destroy_inode,
.drop_inode = generic_delete_inode,
.delete_inode = proc_delete_inode,
.statfs = simple_statfs,
- .remount_fs = proc_remount,
};
-static void pde_users_dec(struct proc_dir_entry *pde)
+static void __pde_users_dec(struct proc_dir_entry *pde)
{
- spin_lock(&pde->pde_unload_lock);
pde->pde_users--;
if (pde->pde_unload_completion && pde->pde_users == 0)
complete(pde->pde_unload_completion);
+}
+
+static void pde_users_dec(struct proc_dir_entry *pde)
+{
+ spin_lock(&pde->pde_unload_lock);
+ __pde_users_dec(pde);
spin_unlock(&pde->pde_unload_lock);
}
@@ -318,36 +321,97 @@ static int proc_reg_open(struct inode *inode, struct file *file)
struct proc_dir_entry *pde = PDE(inode);
int rv = 0;
int (*open)(struct inode *, struct file *);
+ int (*release)(struct inode *, struct file *);
+ struct pde_opener *pdeo;
+
+ /*
+ * What for, you ask? Well, we can have open, rmmod, remove_proc_entry
+ * sequence. ->release won't be called because ->proc_fops will be
+ * cleared. Depending on complexity of ->release, consequences vary.
+ *
+ * We can't wait for mercy when close will be done for real, it's
+ * deadlockable: rmmod foo </proc/foo . So, we're going to do ->release
+ * by hand in remove_proc_entry(). For this, save opener's credentials
+ * for later.
+ */
+ pdeo = kmalloc(sizeof(struct pde_opener), GFP_KERNEL);
+ if (!pdeo)
+ return -ENOMEM;
spin_lock(&pde->pde_unload_lock);
if (!pde->proc_fops) {
spin_unlock(&pde->pde_unload_lock);
- return rv;
+ kfree(pdeo);
+ return -EINVAL;
}
pde->pde_users++;
open = pde->proc_fops->open;
+ release = pde->proc_fops->release;
spin_unlock(&pde->pde_unload_lock);
if (open)
rv = open(inode, file);
- pde_users_dec(pde);
+ spin_lock(&pde->pde_unload_lock);
+ if (rv == 0 && release) {
+ /* To know what to release. */
+ pdeo->inode = inode;
+ pdeo->file = file;
+ /* Strictly for "too late" ->release in proc_reg_release(). */
+ pdeo->release = release;
+ list_add(&pdeo->lh, &pde->pde_openers);
+ } else
+ kfree(pdeo);
+ __pde_users_dec(pde);
+ spin_unlock(&pde->pde_unload_lock);
return rv;
}
+static struct pde_opener *find_pde_opener(struct proc_dir_entry *pde,
+ struct inode *inode, struct file *file)
+{
+ struct pde_opener *pdeo;
+
+ list_for_each_entry(pdeo, &pde->pde_openers, lh) {
+ if (pdeo->inode == inode && pdeo->file == file)
+ return pdeo;
+ }
+ return NULL;
+}
+
static int proc_reg_release(struct inode *inode, struct file *file)
{
struct proc_dir_entry *pde = PDE(inode);
int rv = 0;
int (*release)(struct inode *, struct file *);
+ struct pde_opener *pdeo;
spin_lock(&pde->pde_unload_lock);
+ pdeo = find_pde_opener(pde, inode, file);
if (!pde->proc_fops) {
- spin_unlock(&pde->pde_unload_lock);
+ /*
+ * Can't simply exit, __fput() will think that everything is OK,
+ * and move on to freeing struct file. remove_proc_entry() will
+ * find slacker in opener's list and will try to do non-trivial
+ * things with struct file. Therefore, remove opener from list.
+ *
+ * But if opener is removed from list, who will ->release it?
+ */
+ if (pdeo) {
+ list_del(&pdeo->lh);
+ spin_unlock(&pde->pde_unload_lock);
+ rv = pdeo->release(inode, file);
+ kfree(pdeo);
+ } else
+ spin_unlock(&pde->pde_unload_lock);
return rv;
}
pde->pde_users++;
release = pde->proc_fops->release;
+ if (pdeo) {
+ list_del(&pdeo->lh);
+ kfree(pdeo);
+ }
spin_unlock(&pde->pde_unload_lock);
if (release)
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 28cbca805905..3bfb7b8747b3 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -45,8 +45,6 @@ do { \
extern int nommu_vma_show(struct seq_file *, struct vm_area_struct *);
#endif
-extern int maps_protect;
-
extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task);
extern int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
@@ -63,6 +61,7 @@ extern const struct file_operations proc_smaps_operations;
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 file_operations proc_kmsg_operations;
extern const struct inode_operations proc_net_inode_operations;
void free_proc_entry(struct proc_dir_entry *de);
@@ -88,3 +87,10 @@ 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,
filldir_t filldir);
+
+struct pde_opener {
+ struct inode *inode;
+ struct file *file;
+ int (*release)(struct inode *, struct file *);
+ struct list_head lh;
+};
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index e78c81fcf547..c2370c76fb71 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -23,6 +23,10 @@
#define CORE_STR "CORE"
+#ifndef ELF_CORE_EFLAGS
+#define ELF_CORE_EFLAGS 0
+#endif
+
static int open_kcore(struct inode * inode, struct file * filp)
{
return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
@@ -164,11 +168,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff)
elf->e_entry = 0;
elf->e_phoff = sizeof(struct elfhdr);
elf->e_shoff = 0;
-#if defined(CONFIG_H8300)
- elf->e_flags = ELF_FLAGS;
-#else
- elf->e_flags = 0;
-#endif
+ elf->e_flags = ELF_CORE_EFLAGS;
elf->e_ehsize = sizeof(struct elfhdr);
elf->e_phentsize= sizeof(struct elf_phdr);
elf->e_phnum = nphdr;
diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c
index ff3b90b56e9d..9fd5df3f40ce 100644
--- a/fs/proc/kmsg.c
+++ b/fs/proc/kmsg.c
@@ -15,6 +15,8 @@
#include <asm/uaccess.h>
#include <asm/io.h>
+#include "internal.h"
+
extern wait_queue_head_t log_wait;
extern int do_syslog(int type, char __user *bug, int count);
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index 79ecd281d2cb..3f87d2632947 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -52,14 +52,14 @@ int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
}
seq_printf(m,
- "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n",
+ "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
vma->vm_start,
vma->vm_end,
flags & VM_READ ? 'r' : '-',
flags & VM_WRITE ? 'w' : '-',
flags & VM_EXEC ? 'x' : '-',
flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p',
- vma->vm_pgoff << PAGE_SHIFT,
+ ((loff_t)vma->vm_pgoff) << PAGE_SHIFT,
MAJOR(dev), MINOR(dev), ino, &len);
if (file) {
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 7e277f2ad466..b675a49c1823 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -24,6 +24,7 @@
#include <linux/tty.h>
#include <linux/string.h>
#include <linux/mman.h>
+#include <linux/quicklist.h>
#include <linux/proc_fs.h>
#include <linux/ioport.h>
#include <linux/mm.h>
@@ -67,7 +68,6 @@
extern int get_hardware_list(char *);
extern int get_stram_list(char *);
extern int get_exec_domain_list(char *);
-extern int get_dma_list(char *);
static int proc_calc_metrics(char *page, char **start, off_t off,
int count, int *eof, int len)
@@ -123,6 +123,11 @@ static int uptime_read_proc(char *page, char **start, off_t off,
return proc_calc_metrics(page, start, off, count, eof, len);
}
+int __attribute__((weak)) arch_report_meminfo(char *page)
+{
+ return 0;
+}
+
static int meminfo_read_proc(char *page, char **start, off_t off,
int count, int *eof, void *data)
{
@@ -177,6 +182,9 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
"SReclaimable: %8lu kB\n"
"SUnreclaim: %8lu kB\n"
"PageTables: %8lu kB\n"
+#ifdef CONFIG_QUICKLIST
+ "Quicklists: %8lu kB\n"
+#endif
"NFS_Unstable: %8lu kB\n"
"Bounce: %8lu kB\n"
"WritebackTmp: %8lu kB\n"
@@ -209,6 +217,9 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
K(global_page_state(NR_SLAB_RECLAIMABLE)),
K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
K(global_page_state(NR_PAGETABLE)),
+#ifdef CONFIG_QUICKLIST
+ K(quicklist_total_size()),
+#endif
K(global_page_state(NR_UNSTABLE_NFS)),
K(global_page_state(NR_BOUNCE)),
K(global_page_state(NR_WRITEBACK_TEMP)),
@@ -221,11 +232,12 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
len += hugetlb_report_meminfo(page + len);
+ len += arch_report_meminfo(page + len);
+
return proc_calc_metrics(page, start, off, count, eof, len);
#undef K
}
-extern const struct seq_operations fragmentation_op;
static int fragmentation_open(struct inode *inode, struct file *file)
{
(void)inode;
@@ -239,7 +251,6 @@ static const struct file_operations fragmentation_file_operations = {
.release = seq_release,
};
-extern const struct seq_operations pagetypeinfo_op;
static int pagetypeinfo_open(struct inode *inode, struct file *file)
{
return seq_open(file, &pagetypeinfo_op);
@@ -252,7 +263,6 @@ static const struct file_operations pagetypeinfo_file_ops = {
.release = seq_release,
};
-extern const struct seq_operations zoneinfo_op;
static int zoneinfo_open(struct inode *inode, struct file *file)
{
return seq_open(file, &zoneinfo_op);
@@ -349,7 +359,6 @@ static const struct file_operations proc_devinfo_operations = {
.release = seq_release,
};
-extern const struct seq_operations vmstat_op;
static int vmstat_open(struct inode *inode, struct file *file)
{
return seq_open(file, &vmstat_op);
@@ -461,17 +470,35 @@ static const struct file_operations proc_slabstats_operations = {
#ifdef CONFIG_MMU
static int vmalloc_open(struct inode *inode, struct file *file)
{
- return seq_open(file, &vmalloc_op);
+ unsigned int *ptr = NULL;
+ int ret;
+
+ if (NUMA_BUILD)
+ ptr = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
+ ret = seq_open(file, &vmalloc_op);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+ m->private = ptr;
+ } else
+ kfree(ptr);
+ return ret;
}
static const struct file_operations proc_vmalloc_operations = {
.open = vmalloc_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release,
+ .release = seq_release_private,
};
#endif
+#ifndef arch_irq_stat_cpu
+#define arch_irq_stat_cpu(cpu) 0
+#endif
+#ifndef arch_irq_stat
+#define arch_irq_stat() 0
+#endif
+
static int show_stat(struct seq_file *p, void *v)
{
int i;
@@ -509,7 +536,9 @@ static int show_stat(struct seq_file *p, void *v)
sum += temp;
per_irq_sum[j] += temp;
}
+ sum += arch_irq_stat_cpu(i);
}
+ sum += arch_irq_stat();
seq_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu\n",
(unsigned long long)cputime64_to_clock_t(user),
@@ -654,6 +683,7 @@ static int cmdline_read_proc(char *page, char **start, off_t off,
return proc_calc_metrics(page, start, off, count, eof, len);
}
+#ifdef CONFIG_FILE_LOCKING
static int locks_open(struct inode *inode, struct file *filp)
{
return seq_open(filp, &locks_seq_operations);
@@ -665,6 +695,7 @@ static const struct file_operations proc_locks_operations = {
.llseek = seq_lseek,
.release = seq_release,
};
+#endif /* CONFIG_FILE_LOCKING */
static int execdomains_read_proc(char *page, char **start, off_t off,
int count, int *eof, void *data)
@@ -858,7 +889,9 @@ void __init proc_misc_init(void)
#ifdef CONFIG_PRINTK
proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations);
#endif
+#ifdef CONFIG_FILE_LOCKING
proc_create("locks", 0, NULL, &proc_locks_operations);
+#endif
proc_create("devices", 0, NULL, &proc_devinfo_operations);
proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations);
#ifdef CONFIG_BLOCK
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 83f357b30d71..7bc296f424ae 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -27,6 +27,11 @@
#include "internal.h"
+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)
{
@@ -51,6 +56,30 @@ int seq_open_net(struct inode *ino, struct file *f,
}
EXPORT_SYMBOL_GPL(seq_open_net);
+int single_open_net(struct inode *inode, struct file *file,
+ int (*show)(struct seq_file *, void *))
+{
+ 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;
+
+ return 0;
+
+err_open:
+ put_net(net);
+err_net:
+ return err;
+}
+EXPORT_SYMBOL_GPL(single_open_net);
+
int seq_release_net(struct inode *ino, struct file *f)
{
struct seq_file *seq;
@@ -63,6 +92,14 @@ int seq_release_net(struct inode *ino, struct file *f)
}
EXPORT_SYMBOL_GPL(seq_release_net);
+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 struct net *get_proc_task_net(struct inode *dir)
{
struct task_struct *task;
@@ -153,12 +190,6 @@ void proc_net_remove(struct net *net, const char *name)
}
EXPORT_SYMBOL_GPL(proc_net_remove);
-struct net *get_proc_net(const struct inode *inode)
-{
- return maybe_get_net(PDE_NET(PDE(inode)));
-}
-EXPORT_SYMBOL_GPL(get_proc_net);
-
static __net_init int proc_net_ns_init(struct net *net)
{
struct proc_dir_entry *netd, *net_statd;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 5acc001d49f6..945a81043ba2 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -10,149 +10,110 @@
static struct dentry_operations proc_sys_dentry_operations;
static const struct file_operations proc_sys_file_operations;
static const struct inode_operations proc_sys_inode_operations;
+static const struct file_operations proc_sys_dir_file_operations;
+static const struct inode_operations proc_sys_dir_operations;
-static void proc_sys_refresh_inode(struct inode *inode, struct ctl_table *table)
-{
- /* Refresh the cached information bits in the inode */
- if (table) {
- inode->i_uid = 0;
- inode->i_gid = 0;
- inode->i_mode = table->mode;
- if (table->proc_handler) {
- inode->i_mode |= S_IFREG;
- inode->i_nlink = 1;
- } else {
- inode->i_mode |= S_IFDIR;
- inode->i_nlink = 0; /* It is too hard to figure out */
- }
- }
-}
-
-static struct inode *proc_sys_make_inode(struct inode *dir, struct ctl_table *table)
+static struct inode *proc_sys_make_inode(struct super_block *sb,
+ struct ctl_table_header *head, struct ctl_table *table)
{
struct inode *inode;
- struct proc_inode *dir_ei, *ei;
- int depth;
+ struct proc_inode *ei;
- inode = new_inode(dir->i_sb);
+ inode = new_inode(sb);
if (!inode)
goto out;
- /* A directory is always one deeper than it's parent */
- dir_ei = PROC_I(dir);
- depth = dir_ei->fd + 1;
-
+ sysctl_head_get(head);
ei = PROC_I(inode);
- ei->fd = depth;
+ ei->sysctl = head;
+ ei->sysctl_entry = table;
+
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
- inode->i_op = &proc_sys_inode_operations;
- inode->i_fop = &proc_sys_file_operations;
inode->i_flags |= S_PRIVATE; /* tell selinux to ignore this inode */
- proc_sys_refresh_inode(inode, table);
+ inode->i_mode = table->mode;
+ if (!table->child) {
+ inode->i_mode |= S_IFREG;
+ inode->i_op = &proc_sys_inode_operations;
+ inode->i_fop = &proc_sys_file_operations;
+ } else {
+ inode->i_mode |= S_IFDIR;
+ inode->i_nlink = 0;
+ inode->i_op = &proc_sys_dir_operations;
+ inode->i_fop = &proc_sys_dir_file_operations;
+ }
out:
return inode;
}
-static struct dentry *proc_sys_ancestor(struct dentry *dentry, int depth)
-{
- for (;;) {
- struct proc_inode *ei;
-
- ei = PROC_I(dentry->d_inode);
- if (ei->fd == depth)
- break; /* found */
-
- dentry = dentry->d_parent;
- }
- return dentry;
-}
-
-static struct ctl_table *proc_sys_lookup_table_one(struct ctl_table *table,
- struct qstr *name)
+static struct ctl_table *find_in_table(struct ctl_table *p, struct qstr *name)
{
int len;
- for ( ; table->ctl_name || table->procname; table++) {
+ for ( ; p->ctl_name || p->procname; p++) {
- if (!table->procname)
+ if (!p->procname)
continue;
- len = strlen(table->procname);
+ len = strlen(p->procname);
if (len != name->len)
continue;
- if (memcmp(table->procname, name->name, len) != 0)
+ if (memcmp(p->procname, name->name, len) != 0)
continue;
/* I have a match */
- return table;
+ return p;
}
return NULL;
}
-static struct ctl_table *proc_sys_lookup_table(struct dentry *dentry,
- struct ctl_table *table)
+static struct ctl_table_header *grab_header(struct inode *inode)
{
- struct dentry *ancestor;
- struct proc_inode *ei;
- int depth, i;
+ if (PROC_I(inode)->sysctl)
+ return sysctl_head_grab(PROC_I(inode)->sysctl);
+ else
+ return sysctl_head_next(NULL);
+}
- ei = PROC_I(dentry->d_inode);
- depth = ei->fd;
+static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
+ struct nameidata *nd)
+{
+ struct ctl_table_header *head = grab_header(dir);
+ struct ctl_table *table = PROC_I(dir)->sysctl_entry;
+ struct ctl_table_header *h = NULL;
+ struct qstr *name = &dentry->d_name;
+ struct ctl_table *p;
+ struct inode *inode;
+ struct dentry *err = ERR_PTR(-ENOENT);
- if (depth == 0)
- return table;
+ if (IS_ERR(head))
+ return ERR_CAST(head);
- for (i = 1; table && (i <= depth); i++) {
- ancestor = proc_sys_ancestor(dentry, i);
- table = proc_sys_lookup_table_one(table, &ancestor->d_name);
- if (table)
- table = table->child;
+ if (table && !table->child) {
+ WARN_ON(1);
+ goto out;
}
- return table;
-}
-static struct ctl_table *proc_sys_lookup_entry(struct dentry *dparent,
- struct qstr *name,
- struct ctl_table *table)
-{
- table = proc_sys_lookup_table(dparent, table);
- if (table)
- table = proc_sys_lookup_table_one(table, name);
- return table;
-}
+ table = table ? table->child : head->ctl_table;
-static struct ctl_table *do_proc_sys_lookup(struct dentry *parent,
- struct qstr *name,
- struct ctl_table_header **ptr)
-{
- struct ctl_table_header *head;
- struct ctl_table *table = NULL;
-
- for (head = sysctl_head_next(NULL); head;
- head = sysctl_head_next(head)) {
- table = proc_sys_lookup_entry(parent, name, head->ctl_table);
- if (table)
- break;
+ p = find_in_table(table, name);
+ if (!p) {
+ for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
+ if (h->attached_to != table)
+ continue;
+ p = find_in_table(h->attached_by, name);
+ if (p)
+ break;
+ }
}
- *ptr = head;
- return table;
-}
-
-static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
-{
- struct ctl_table_header *head;
- struct inode *inode;
- struct dentry *err;
- struct ctl_table *table;
- err = ERR_PTR(-ENOENT);
- table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
- if (!table)
+ if (!p)
goto out;
err = ERR_PTR(-ENOMEM);
- inode = proc_sys_make_inode(dir, table);
+ inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
+ if (h)
+ sysctl_head_finish(h);
+
if (!inode)
goto out;
@@ -168,22 +129,14 @@ out:
static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
size_t count, loff_t *ppos, int write)
{
- struct dentry *dentry = filp->f_dentry;
- struct ctl_table_header *head;
- struct ctl_table *table;
+ struct inode *inode = filp->f_path.dentry->d_inode;
+ struct ctl_table_header *head = grab_header(inode);
+ struct ctl_table *table = PROC_I(inode)->sysctl_entry;
ssize_t error;
size_t res;
- table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
- /* Has the sysctl entry disappeared on us? */
- error = -ENOENT;
- if (!table)
- goto out;
-
- /* Has the sysctl entry been replaced by a directory? */
- error = -EISDIR;
- if (!table->proc_handler)
- goto out;
+ if (IS_ERR(head))
+ return PTR_ERR(head);
/*
* At this point we know that the sysctl was not unregistered
@@ -193,6 +146,11 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *buf,
if (sysctl_perm(head->root, table, write ? MAY_WRITE : MAY_READ))
goto out;
+ /* if that can happen at all, it should be -EINVAL, not -EISDIR */
+ error = -EINVAL;
+ if (!table->proc_handler)
+ goto out;
+
/* careful: calling conventions are nasty here */
res = count;
error = table->proc_handler(table, write, filp, buf, &res, ppos);
@@ -218,82 +176,86 @@ static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
static int proc_sys_fill_cache(struct file *filp, void *dirent,
- filldir_t filldir, struct ctl_table *table)
+ filldir_t filldir,
+ struct ctl_table_header *head,
+ struct ctl_table *table)
{
- struct ctl_table_header *head;
- struct ctl_table *child_table = NULL;
struct dentry *child, *dir = filp->f_path.dentry;
struct inode *inode;
struct qstr qname;
ino_t ino = 0;
unsigned type = DT_UNKNOWN;
- int ret;
qname.name = table->procname;
qname.len = strlen(table->procname);
qname.hash = full_name_hash(qname.name, qname.len);
- /* Suppress duplicates.
- * Only fill a directory entry if it is the value that
- * an ordinary lookup of that name returns. Hide all
- * others.
- *
- * If we ever cache this translation in the dcache
- * I should do a dcache lookup first. But for now
- * it is just simpler not to.
- */
- ret = 0;
- child_table = do_proc_sys_lookup(dir, &qname, &head);
- sysctl_head_finish(head);
- if (child_table != table)
- return 0;
-
child = d_lookup(dir, &qname);
if (!child) {
- struct dentry *new;
- new = d_alloc(dir, &qname);
- if (new) {
- inode = proc_sys_make_inode(dir->d_inode, table);
- if (!inode)
- child = ERR_PTR(-ENOMEM);
- else {
- new->d_op = &proc_sys_dentry_operations;
- d_add(new, inode);
+ child = d_alloc(dir, &qname);
+ if (child) {
+ inode = proc_sys_make_inode(dir->d_sb, head, table);
+ if (!inode) {
+ dput(child);
+ return -ENOMEM;
+ } else {
+ child->d_op = &proc_sys_dentry_operations;
+ d_add(child, inode);
}
- if (child)
- dput(new);
- else
- child = new;
+ } else {
+ return -ENOMEM;
}
}
- if (!child || IS_ERR(child) || !child->d_inode)
- goto end_instantiate;
inode = child->d_inode;
- if (inode) {
- ino = inode->i_ino;
- type = inode->i_mode >> 12;
- }
+ ino = inode->i_ino;
+ type = inode->i_mode >> 12;
dput(child);
-end_instantiate:
- if (!ino)
- ino= find_inode_number(dir, &qname);
- if (!ino)
- ino = 1;
- return filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
+ return !!filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
+}
+
+static int scan(struct ctl_table_header *head, ctl_table *table,
+ unsigned long *pos, struct file *file,
+ void *dirent, filldir_t filldir)
+{
+
+ for (; table->ctl_name || table->procname; table++, (*pos)++) {
+ int res;
+
+ /* Can't do anything without a proc name */
+ if (!table->procname)
+ continue;
+
+ if (*pos < file->f_pos)
+ continue;
+
+ res = proc_sys_fill_cache(file, dirent, filldir, head, table);
+ if (res)
+ return res;
+
+ file->f_pos = *pos + 1;
+ }
+ return 0;
}
static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
- struct dentry *dentry = filp->f_dentry;
+ struct dentry *dentry = filp->f_path.dentry;
struct inode *inode = dentry->d_inode;
- struct ctl_table_header *head = NULL;
- struct ctl_table *table;
+ struct ctl_table_header *head = grab_header(inode);
+ struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+ struct ctl_table_header *h = NULL;
unsigned long pos;
- int ret;
+ int ret = -EINVAL;
- ret = -ENOTDIR;
- if (!S_ISDIR(inode->i_mode))
+ if (IS_ERR(head))
+ return PTR_ERR(head);
+
+ if (table && !table->child) {
+ WARN_ON(1);
goto out;
+ }
+
+ table = table ? table->child : head->ctl_table;
ret = 0;
/* Avoid a switch here: arm builds fail with missing __cmpdi2 */
@@ -311,30 +273,17 @@ static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
}
pos = 2;
- /* - Find each instance of the directory
- * - Read all entries in each instance
- * - Before returning an entry to user space lookup the entry
- * by name and if I find a different entry don't return
- * this one because it means it is a buried dup.
- * For sysctl this should only happen for directory entries.
- */
- for (head = sysctl_head_next(NULL); head; head = sysctl_head_next(head)) {
- table = proc_sys_lookup_table(dentry, head->ctl_table);
+ ret = scan(head, table, &pos, filp, dirent, filldir);
+ if (ret)
+ goto out;
- if (!table)
+ for (h = sysctl_head_next(NULL); h; h = sysctl_head_next(h)) {
+ if (h->attached_to != table)
continue;
-
- for (; table->ctl_name || table->procname; table++, pos++) {
- /* Can't do anything without a proc name */
- if (!table->procname)
- continue;
-
- if (pos < filp->f_pos)
- continue;
-
- if (proc_sys_fill_cache(filp, dirent, filldir, table) < 0)
- goto out;
- filp->f_pos = pos + 1;
+ ret = scan(h, h->attached_by, &pos, filp, dirent, filldir);
+ if (ret) {
+ sysctl_head_finish(h);
+ break;
}
}
ret = 1;
@@ -343,53 +292,24 @@ out:
return ret;
}
-static int proc_sys_permission(struct inode *inode, int mask, struct nameidata *nd)
+static int proc_sys_permission(struct inode *inode, int mask)
{
/*
* sysctl entries that are not writeable,
* are _NOT_ writeable, capabilities or not.
*/
- struct ctl_table_header *head;
- struct ctl_table *table;
- struct dentry *dentry;
- int mode;
- int depth;
+ struct ctl_table_header *head = grab_header(inode);
+ struct ctl_table *table = PROC_I(inode)->sysctl_entry;
int error;
- head = NULL;
- depth = PROC_I(inode)->fd;
-
- /* First check the cached permissions, in case we don't have
- * enough information to lookup the sysctl table entry.
- */
- error = -EACCES;
- mode = inode->i_mode;
-
- if (current->euid == 0)
- mode >>= 6;
- else if (in_group_p(0))
- mode >>= 3;
-
- if ((mode & mask & (MAY_READ|MAY_WRITE|MAY_EXEC)) == mask)
- error = 0;
-
- /* If we can't get a sysctl table entry the permission
- * checks on the cached mode will have to be enough.
- */
- if (!nd || !depth)
- goto out;
-
- dentry = nd->path.dentry;
- table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
+ if (IS_ERR(head))
+ return PTR_ERR(head);
- /* If the entry does not exist deny permission */
- error = -EACCES;
- if (!table)
- goto out;
+ if (!table) /* global root - r-xr-xr-x */
+ error = mask & MAY_WRITE ? -EACCES : 0;
+ else /* Use the permissions on the sysctl table entry */
+ error = sysctl_perm(head->root, table, mask);
- /* Use the permissions on the sysctl table entry */
- error = sysctl_perm(head->root, table, mask);
-out:
sysctl_head_finish(head);
return error;
}
@@ -409,42 +329,79 @@ static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
return error;
}
-/* I'm lazy and don't distinguish between files and directories,
- * until access time.
- */
+static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+ struct inode *inode = dentry->d_inode;
+ struct ctl_table_header *head = grab_header(inode);
+ struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+
+ if (IS_ERR(head))
+ return PTR_ERR(head);
+
+ generic_fillattr(inode, stat);
+ if (table)
+ stat->mode = (stat->mode & S_IFMT) | table->mode;
+
+ sysctl_head_finish(head);
+ return 0;
+}
+
static const struct file_operations proc_sys_file_operations = {
.read = proc_sys_read,
.write = proc_sys_write,
+};
+
+static const struct file_operations proc_sys_dir_file_operations = {
.readdir = proc_sys_readdir,
};
static const struct inode_operations proc_sys_inode_operations = {
+ .permission = proc_sys_permission,
+ .setattr = proc_sys_setattr,
+ .getattr = proc_sys_getattr,
+};
+
+static const struct inode_operations proc_sys_dir_operations = {
.lookup = proc_sys_lookup,
.permission = proc_sys_permission,
.setattr = proc_sys_setattr,
+ .getattr = proc_sys_getattr,
};
static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd)
{
- struct ctl_table_header *head;
- struct ctl_table *table;
- table = do_proc_sys_lookup(dentry->d_parent, &dentry->d_name, &head);
- proc_sys_refresh_inode(dentry->d_inode, table);
- sysctl_head_finish(head);
- return !!table;
+ return !PROC_I(dentry->d_inode)->sysctl->unregistering;
+}
+
+static int proc_sys_delete(struct dentry *dentry)
+{
+ return !!PROC_I(dentry->d_inode)->sysctl->unregistering;
+}
+
+static int proc_sys_compare(struct dentry *dir, struct qstr *qstr,
+ struct qstr *name)
+{
+ struct dentry *dentry = container_of(qstr, struct dentry, d_name);
+ if (qstr->len != name->len)
+ return 1;
+ if (memcmp(qstr->name, name->name, name->len))
+ return 1;
+ return !sysctl_is_seen(PROC_I(dentry->d_inode)->sysctl);
}
static struct dentry_operations proc_sys_dentry_operations = {
.d_revalidate = proc_sys_revalidate,
+ .d_delete = proc_sys_delete,
+ .d_compare = proc_sys_compare,
};
-static struct proc_dir_entry *proc_sys_root;
-
int proc_sys_init(void)
{
+ struct proc_dir_entry *proc_sys_root;
+
proc_sys_root = proc_mkdir("sys", NULL);
- proc_sys_root->proc_iops = &proc_sys_inode_operations;
- proc_sys_root->proc_fops = &proc_sys_file_operations;
+ proc_sys_root->proc_iops = &proc_sys_dir_operations;
+ proc_sys_root->proc_fops = &proc_sys_dir_file_operations;
proc_sys_root->nlink = 0;
return 0;
}
diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c
index 21f490f5d65c..d153946d6d15 100644
--- a/fs/proc/proc_tty.c
+++ b/fs/proc/proc_tty.c
@@ -136,54 +136,6 @@ static const struct file_operations proc_tty_drivers_operations = {
.release = seq_release,
};
-static void * tty_ldiscs_seq_start(struct seq_file *m, loff_t *pos)
-{
- return (*pos < NR_LDISCS) ? pos : NULL;
-}
-
-static void * tty_ldiscs_seq_next(struct seq_file *m, void *v, loff_t *pos)
-{
- (*pos)++;
- return (*pos < NR_LDISCS) ? pos : NULL;
-}
-
-static void tty_ldiscs_seq_stop(struct seq_file *m, void *v)
-{
-}
-
-static int tty_ldiscs_seq_show(struct seq_file *m, void *v)
-{
- int i = *(loff_t *)v;
- struct tty_ldisc *ld;
-
- ld = tty_ldisc_get(i);
- if (ld == NULL)
- return 0;
- seq_printf(m, "%-10s %2d\n", ld->name ? ld->name : "???", i);
- tty_ldisc_put(i);
- return 0;
-}
-
-static const struct seq_operations tty_ldiscs_seq_ops = {
- .start = tty_ldiscs_seq_start,
- .next = tty_ldiscs_seq_next,
- .stop = tty_ldiscs_seq_stop,
- .show = tty_ldiscs_seq_show,
-};
-
-static int proc_tty_ldiscs_open(struct inode *inode, struct file *file)
-{
- return seq_open(file, &tty_ldiscs_seq_ops);
-}
-
-static const struct file_operations tty_ldiscs_proc_fops = {
- .owner = THIS_MODULE,
- .open = proc_tty_ldiscs_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>
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ab8ccc9d14ff..4806830ea2a1 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -210,23 +210,20 @@ static int show_map(struct seq_file *m, void *v)
dev_t dev = 0;
int len;
- if (maps_protect && !ptrace_may_attach(task))
- return -EACCES;
-
if (file) {
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
}
- seq_printf(m, "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n",
+ seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
vma->vm_start,
vma->vm_end,
flags & VM_READ ? 'r' : '-',
flags & VM_WRITE ? 'w' : '-',
flags & VM_EXEC ? 'x' : '-',
flags & VM_MAYSHARE ? 's' : 'p',
- vma->vm_pgoff << PAGE_SHIFT,
+ ((loff_t)vma->vm_pgoff) << PAGE_SHIFT,
MAJOR(dev), MINOR(dev), ino, &len);
/*
@@ -476,10 +473,10 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
return -ESRCH;
mm = get_task_mm(task);
if (mm) {
- static struct mm_walk clear_refs_walk;
- memset(&clear_refs_walk, 0, sizeof(clear_refs_walk));
- clear_refs_walk.pmd_entry = clear_refs_pte_range;
- clear_refs_walk.mm = mm;
+ struct mm_walk clear_refs_walk = {
+ .pmd_entry = clear_refs_pte_range,
+ .mm = mm,
+ };
down_read(&mm->mmap_sem);
for (vma = mm->mmap; vma; vma = vma->vm_next) {
clear_refs_walk.private = vma;
@@ -602,11 +599,6 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
return err;
}
-static struct mm_walk pagemap_walk = {
- .pmd_entry = pagemap_pte_range,
- .pte_hole = pagemap_pte_hole
-};
-
/*
* /proc/pid/pagemap - an array mapping virtual pages to pfns
*
@@ -641,12 +633,17 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
struct pagemapread pm;
int pagecount;
int ret = -ESRCH;
+ struct mm_walk pagemap_walk = {};
+ unsigned long src;
+ unsigned long svpfn;
+ unsigned long start_vaddr;
+ unsigned long end_vaddr;
if (!task)
goto out;
ret = -EACCES;
- if (!ptrace_may_attach(task))
+ if (!ptrace_may_access(task, PTRACE_MODE_READ))
goto out_task;
ret = -EINVAL;
@@ -659,11 +656,15 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
if (!mm)
goto out_task;
- ret = -ENOMEM;
+
uaddr = (unsigned long)buf & PAGE_MASK;
uend = (unsigned long)(buf + count);
pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE;
- pages = kmalloc(pagecount * sizeof(struct page *), GFP_KERNEL);
+ ret = 0;
+ if (pagecount == 0)
+ goto out_mm;
+ pages = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
+ ret = -ENOMEM;
if (!pages)
goto out_mm;
@@ -684,33 +685,33 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
pm.out = (u64 *)buf;
pm.end = (u64 *)(buf + count);
- if (!ptrace_may_attach(task)) {
- ret = -EIO;
- } else {
- unsigned long src = *ppos;
- unsigned long svpfn = src / PM_ENTRY_BYTES;
- unsigned long start_vaddr = svpfn << PAGE_SHIFT;
- unsigned long end_vaddr = TASK_SIZE_OF(task);
-
- /* watch out for wraparound */
- if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT)
- start_vaddr = end_vaddr;
-
- /*
- * The odds are that this will stop walking way
- * before end_vaddr, because the length of the
- * user buffer is tracked in "pm", and the walk
- * will stop when we hit the end of the buffer.
- */
- ret = walk_page_range(start_vaddr, end_vaddr,
- &pagemap_walk);
- if (ret == PM_END_OF_BUFFER)
- ret = 0;
- /* don't need mmap_sem for these, but this looks cleaner */
- *ppos += (char *)pm.out - buf;
- if (!ret)
- ret = (char *)pm.out - buf;
- }
+ pagemap_walk.pmd_entry = pagemap_pte_range;
+ pagemap_walk.pte_hole = pagemap_pte_hole;
+ pagemap_walk.mm = mm;
+ pagemap_walk.private = &pm;
+
+ src = *ppos;
+ svpfn = src / PM_ENTRY_BYTES;
+ start_vaddr = svpfn << PAGE_SHIFT;
+ end_vaddr = TASK_SIZE_OF(task);
+
+ /* watch out for wraparound */
+ if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT)
+ start_vaddr = end_vaddr;
+
+ /*
+ * The odds are that this will stop walking way
+ * before end_vaddr, because the length of the
+ * user buffer is tracked in "pm", and the walk
+ * will stop when we hit the end of the buffer.
+ */
+ ret = walk_page_range(start_vaddr, end_vaddr, &pagemap_walk);
+ if (ret == PM_END_OF_BUFFER)
+ ret = 0;
+ /* don't need mmap_sem for these, but this looks cleaner */
+ *ppos += (char *)pm.out - buf;
+ if (!ret)
+ ret = (char *)pm.out - buf;
out_pages:
for (; pagecount; pagecount--) {
@@ -738,22 +739,11 @@ const struct file_operations proc_pagemap_operations = {
#ifdef CONFIG_NUMA
extern int show_numa_map(struct seq_file *m, void *v);
-static int show_numa_map_checked(struct seq_file *m, void *v)
-{
- struct proc_maps_private *priv = m->private;
- struct task_struct *task = priv->task;
-
- if (maps_protect && !ptrace_may_attach(task))
- return -EACCES;
-
- return show_numa_map(m, v);
-}
-
static const struct seq_operations proc_pid_numa_maps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
- .show = show_numa_map_checked
+ .show = show_numa_map,
};
static int numa_maps_open(struct inode *inode, struct file *file)
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 4b4f9cc2f186..219bd79ea894 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -110,11 +110,6 @@ int task_statm(struct mm_struct *mm, int *shared, int *text,
static int show_map(struct seq_file *m, void *_vml)
{
struct vm_list_struct *vml = _vml;
- struct proc_maps_private *priv = m->private;
- struct task_struct *task = priv->task;
-
- if (maps_protect && !ptrace_may_attach(task))
- return -EACCES;
return nommu_vma_show(m, vml->vma);
}
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 9ac0f5e064e0..841368b87a29 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -165,14 +165,8 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
return acc;
}
-static int open_vmcore(struct inode *inode, struct file *filp)
-{
- return 0;
-}
-
const struct file_operations proc_vmcore_operations = {
.read = read_vmcore,
- .open = open_vmcore,
};
static struct vmcore* __init get_new_element(void)
generated by cgit v1.2.3 (git 2.0.4) at 2025-05-25 13:27:16 +0000