summaryrefslogtreecommitdiff
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/Kconfig59
-rw-r--r--fs/proc/array.c2
-rw-r--r--fs/proc/base.c128
-rw-r--r--fs/proc/generic.c14
-rw-r--r--fs/proc/inode.c81
-rw-r--r--fs/proc/internal.h8
-rw-r--r--fs/proc/kcore.c10
-rw-r--r--fs/proc/kmsg.c2
-rw-r--r--fs/proc/proc_misc.c41
-rw-r--r--fs/proc/proc_net.c43
-rw-r--r--fs/proc/proc_tty.c48
-rw-r--r--fs/proc/task_mmu.c181
-rw-r--r--fs/proc/task_nommu.c2
13 files changed, 431 insertions, 188 deletions
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
new file mode 100644
index 000000000000..73cd7a418f06
--- /dev/null
+++ b/fs/proc/Kconfig
@@ -0,0 +1,59 @@
+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.
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 9e3b8c33c24b..797d775e0354 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -288,7 +288,7 @@ static void render_cap_t(struct seq_file *m, const char *header,
seq_printf(m, "%s", header);
CAP_FOR_EACH_U32(__capi) {
seq_printf(m, "%08x",
- a->cap[(_LINUX_CAPABILITY_U32S-1) - __capi]);
+ a->cap[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
}
seq_printf(m, "\n");
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index c447e0743a3c..a891fe4cb43b 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -127,6 +127,25 @@ struct pid_entry {
NULL, &proc_single_file_operations, \
{ .proc_show = &proc_##OTYPE } )
+/*
+ * Count the number of hardlinks for the pid_entry table, excluding the .
+ * and .. links.
+ */
+static unsigned int pid_entry_count_dirs(const struct pid_entry *entries,
+ unsigned int n)
+{
+ unsigned int i;
+ unsigned int count;
+
+ count = 0;
+ for (i = 0; i < n; ++i) {
+ if (S_ISDIR(entries[i].mode))
+ ++count;
+ }
+
+ return count;
+}
+
int maps_protect;
EXPORT_SYMBOL(maps_protect);
@@ -214,7 +233,7 @@ static int check_mem_permission(struct task_struct *task)
*/
if (task->parent == current && (task->ptrace & PT_PTRACED) &&
task_is_stopped_or_traced(task) &&
- ptrace_may_attach(task))
+ ptrace_may_access(task, PTRACE_MODE_ATTACH))
return 0;
/*
@@ -232,7 +251,8 @@ 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;
@@ -499,7 +519,7 @@ 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;
@@ -885,7 +905,7 @@ 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;
@@ -2356,29 +2376,82 @@ 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)
+{
+ u64 rchar, wchar, syscr, syscw;
+ struct task_io_accounting ioac;
+
+ if (!whole) {
+ rchar = task->rchar;
+ wchar = task->wchar;
+ syscr = task->syscr;
+ syscw = task->syscw;
+ memcpy(&ioac, &task->ioac, sizeof(ioac));
+ } else {
+ unsigned long flags;
+ struct task_struct *t = task;
+ rchar = wchar = syscr = syscw = 0;
+ memset(&ioac, 0, sizeof(ioac));
+
+ rcu_read_lock();
+ do {
+ rchar += t->rchar;
+ wchar += t->wchar;
+ syscr += t->syscr;
+ syscw += t->syscw;
+
+ ioac.read_bytes += t->ioac.read_bytes;
+ ioac.write_bytes += t->ioac.write_bytes;
+ ioac.cancelled_write_bytes +=
+ t->ioac.cancelled_write_bytes;
+ t = next_thread(t);
+ } while (t != task);
+ rcu_read_unlock();
+
+ if (lock_task_sighand(task, &flags)) {
+ struct signal_struct *sig = task->signal;
+
+ rchar += sig->rchar;
+ wchar += sig->wchar;
+ syscr += sig->syscr;
+ syscw += sig->syscw;
+
+ ioac.read_bytes += sig->ioac.read_bytes;
+ ioac.write_bytes += sig->ioac.write_bytes;
+ ioac.cancelled_write_bytes +=
+ sig->ioac.cancelled_write_bytes;
+
+ 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)rchar,
+ (unsigned long long)wchar,
+ (unsigned long long)syscr,
+ (unsigned long long)syscw,
+ (unsigned long long)ioac.read_bytes,
+ (unsigned long long)ioac.write_bytes,
+ (unsigned long long)ioac.cancelled_write_bytes);
}
-#endif
+
+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 */
/*
* Thread groups
@@ -2450,7 +2523,7 @@ 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
};
@@ -2585,10 +2658,9 @@ static struct dentry *proc_pid_instantiate(struct inode *dir,
inode->i_op = &proc_tgid_base_inode_operations;
inode->i_fop = &proc_tgid_base_operations;
inode->i_flags|=S_IMMUTABLE;
- inode->i_nlink = 5;
-#ifdef CONFIG_SECURITY
- inode->i_nlink += 1;
-#endif
+
+ inode->i_nlink = 2 + pid_entry_count_dirs(tgid_base_stuff,
+ ARRAY_SIZE(tgid_base_stuff));
dentry->d_op = &pid_dentry_operations;
@@ -2778,6 +2850,9 @@ 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,
@@ -2816,10 +2891,9 @@ static struct dentry *proc_task_instantiate(struct inode *dir,
inode->i_op = &proc_tid_base_inode_operations;
inode->i_fop = &proc_tid_base_operations;
inode->i_flags|=S_IMMUTABLE;
- inode->i_nlink = 4;
-#ifdef CONFIG_SECURITY
- inode->i_nlink += 1;
-#endif
+
+ inode->i_nlink = 2 + pid_entry_count_dirs(tid_base_stuff,
+ ARRAY_SIZE(tid_base_stuff));
dentry->d_op = &pid_dentry_operations;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 43e54e86cefd..bc0a0dd2d844 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -597,6 +597,7 @@ 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;
}
@@ -789,6 +790,19 @@ 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;
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index b08d10017911..02eca2ed9dd7 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -111,27 +111,25 @@ 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 +316,97 @@ 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);
+ kfree(pdeo);
return rv;
}
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..442202314d53 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -63,6 +63,7 @@ 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 +89,10 @@ 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/proc_misc.c b/fs/proc/proc_misc.c
index 32dc14cd8900..ded969862960 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -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)
{
@@ -221,11 +226,12 @@ 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 +245,6 @@ 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 +257,6 @@ 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 +353,6 @@ 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 +464,35 @@ 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 +530,9 @@ 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),
@@ -716,7 +739,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
pfn = src / KPMSIZE;
count = min_t(size_t, count, (max_pfn * KPMSIZE) - src);
if (src & KPMMASK || count & KPMMASK)
- return -EIO;
+ return -EINVAL;
while (count > 0) {
ppage = NULL;
@@ -726,7 +749,7 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
if (!ppage)
pcount = 0;
else
- pcount = atomic_read(&ppage->_count);
+ pcount = page_mapcount(ppage);
if (put_user(pcount, out++)) {
ret = -EFAULT;
@@ -782,7 +805,7 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf,
pfn = src / KPMSIZE;
count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
if (src & KPMMASK || count & KPMMASK)
- return -EIO;
+ return -EINVAL;
while (count > 0) {
ppage = NULL;
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_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 88717c0f941b..7546a918f790 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -210,7 +210,7 @@ static int show_map(struct seq_file *m, void *v)
dev_t dev = 0;
int len;
- if (maps_protect && !ptrace_may_attach(task))
+ if (maps_protect && !ptrace_may_access(task, PTRACE_MODE_READ))
return -EACCES;
if (file) {
@@ -315,9 +315,9 @@ struct mem_size_stats {
};
static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
- void *private)
+ struct mm_walk *walk)
{
- struct mem_size_stats *mss = private;
+ struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = mss->vma;
pte_t *pte, ptent;
spinlock_t *ptl;
@@ -365,19 +365,21 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
return 0;
}
-static struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range };
-
static int show_smap(struct seq_file *m, void *v)
{
struct vm_area_struct *vma = v;
struct mem_size_stats mss;
int ret;
+ struct mm_walk smaps_walk = {
+ .pmd_entry = smaps_pte_range,
+ .mm = vma->vm_mm,
+ .private = &mss,
+ };
memset(&mss, 0, sizeof mss);
mss.vma = vma;
if (vma->vm_mm && !is_vm_hugetlb_page(vma))
- walk_page_range(vma->vm_mm, vma->vm_start, vma->vm_end,
- &smaps_walk, &mss);
+ walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk);
ret = show_map(m, v);
if (ret)
@@ -426,9 +428,9 @@ const struct file_operations proc_smaps_operations = {
};
static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
- unsigned long end, void *private)
+ unsigned long end, struct mm_walk *walk)
{
- struct vm_area_struct *vma = private;
+ struct vm_area_struct *vma = walk->private;
pte_t *pte, ptent;
spinlock_t *ptl;
struct page *page;
@@ -452,8 +454,6 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
return 0;
}
-static struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range };
-
static ssize_t clear_refs_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
@@ -476,11 +476,17 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
return -ESRCH;
mm = get_task_mm(task);
if (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)
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ clear_refs_walk.private = vma;
if (!is_vm_hugetlb_page(vma))
- walk_page_range(mm, vma->vm_start, vma->vm_end,
- &clear_refs_walk, vma);
+ walk_page_range(vma->vm_start, vma->vm_end,
+ &clear_refs_walk);
+ }
flush_tlb_mm(mm);
up_read(&mm->mmap_sem);
mmput(mm);
@@ -496,7 +502,7 @@ const struct file_operations proc_clear_refs_operations = {
};
struct pagemapread {
- char __user *out, *end;
+ u64 __user *out, *end;
};
#define PM_ENTRY_BYTES sizeof(u64)
@@ -519,28 +525,18 @@ struct pagemapread {
static int add_to_pagemap(unsigned long addr, u64 pfn,
struct pagemapread *pm)
{
- /*
- * Make sure there's room in the buffer for an
- * entire entry. Otherwise, only copy part of
- * the pfn.
- */
- if (pm->out + PM_ENTRY_BYTES >= pm->end) {
- if (copy_to_user(pm->out, &pfn, pm->end - pm->out))
- return -EFAULT;
- pm->out = pm->end;
- return PM_END_OF_BUFFER;
- }
-
if (put_user(pfn, pm->out))
return -EFAULT;
- pm->out += PM_ENTRY_BYTES;
+ pm->out++;
+ if (pm->out >= pm->end)
+ return PM_END_OF_BUFFER;
return 0;
}
static int pagemap_pte_hole(unsigned long start, unsigned long end,
- void *private)
+ struct mm_walk *walk)
{
- struct pagemapread *pm = private;
+ struct pagemapread *pm = walk->private;
unsigned long addr;
int err = 0;
for (addr = start; addr < end; addr += PAGE_SIZE) {
@@ -557,24 +553,45 @@ static u64 swap_pte_to_pagemap_entry(pte_t pte)
return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
}
+static unsigned long pte_to_pagemap_entry(pte_t pte)
+{
+ unsigned long pme = 0;
+ if (is_swap_pte(pte))
+ pme = PM_PFRAME(swap_pte_to_pagemap_entry(pte))
+ | PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
+ else if (pte_present(pte))
+ pme = PM_PFRAME(pte_pfn(pte))
+ | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
+ return pme;
+}
+
static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
- void *private)
+ struct mm_walk *walk)
{
- struct pagemapread *pm = private;
+ struct vm_area_struct *vma;
+ struct pagemapread *pm = walk->private;
pte_t *pte;
int err = 0;
+ /* find the first VMA at or above 'addr' */
+ vma = find_vma(walk->mm, addr);
for (; addr != end; addr += PAGE_SIZE) {
u64 pfn = PM_NOT_PRESENT;
- pte = pte_offset_map(pmd, addr);
- if (is_swap_pte(*pte))
- pfn = PM_PFRAME(swap_pte_to_pagemap_entry(*pte))
- | PM_PSHIFT(PAGE_SHIFT) | PM_SWAP;
- else if (pte_present(*pte))
- pfn = PM_PFRAME(pte_pfn(*pte))
- | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT;
- /* unmap so we're not in atomic when we copy to userspace */
- pte_unmap(pte);
+
+ /* check to see if we've left 'vma' behind
+ * and need a new, higher one */
+ if (vma && (addr >= vma->vm_end))
+ vma = find_vma(walk->mm, addr);
+
+ /* check that 'vma' actually covers this address,
+ * and that it isn't a huge page vma */
+ if (vma && (vma->vm_start <= addr) &&
+ !is_vm_hugetlb_page(vma)) {
+ pte = pte_offset_map(pmd, addr);
+ pfn = pte_to_pagemap_entry(*pte);
+ /* unmap before userspace copy */
+ pte_unmap(pte);
+ }
err = add_to_pagemap(addr, pfn, pm);
if (err)
return err;
@@ -585,11 +602,6 @@ 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
*
@@ -624,17 +636,22 @@ 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;
/* file position must be aligned */
- if (*ppos % PM_ENTRY_BYTES)
+ if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
goto out_task;
ret = 0;
@@ -642,11 +659,15 @@ 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;
@@ -664,36 +685,36 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
goto out_pages;
}
- pm.out = buf;
- pm.end = buf + count;
+ 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(mm, start_vaddr, end_vaddr,
- &pagemap_walk, &pm);
- if (ret == PM_END_OF_BUFFER)
- ret = 0;
- /* don't need mmap_sem for these, but this looks cleaner */
- *ppos += pm.out - buf;
- if (!ret)
- ret = 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--) {
@@ -726,7 +747,7 @@ 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))
+ if (maps_protect && !ptrace_may_access(task, PTRACE_MODE_READ))
return -EACCES;
return show_numa_map(m, v);
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 4b4f9cc2f186..5d84e7121df8 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -113,7 +113,7 @@ static int show_map(struct seq_file *m, void *_vml)
struct proc_maps_private *priv = m->private;
struct task_struct *task = priv->task;
- if (maps_protect && !ptrace_may_attach(task))
+ if (maps_protect && !ptrace_may_access(task, PTRACE_MODE_READ))
return -EACCES;
return nommu_vma_show(m, vml->vma);
generated by cgit v1.2.3 (git 2.25.1) at 2026-01-06 08:16:37 +0000