summaryrefslogtreecommitdiffstats
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/Makefile1
-rw-r--r--fs/proc/array.c11
-rw-r--r--fs/proc/base.c199
-rw-r--r--fs/proc/fd.c2
-rw-r--r--fs/proc/generic.c32
-rw-r--r--fs/proc/inode.c7
-rw-r--r--fs/proc/internal.h15
-rw-r--r--fs/proc/kcore.c2
-rw-r--r--fs/proc/meminfo.c2
-rw-r--r--fs/proc/proc_net.c4
-rw-r--r--fs/proc/proc_sysctl.c2
-rw-r--r--fs/proc/proc_tty.c4
-rw-r--r--fs/proc/root.c7
-rw-r--r--fs/proc/task_mmu.c27
-rw-r--r--fs/proc/thread_self.c85
-rw-r--r--fs/proc/vmcore.c82
16 files changed, 319 insertions, 163 deletions
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index 239493ec718..7151ea42804 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -23,6 +23,7 @@ proc-y += version.o
proc-y += softirqs.o
proc-y += namespaces.o
proc-y += self.o
+proc-y += thread_self.o
proc-$(CONFIG_PROC_SYSCTL) += proc_sysctl.o
proc-$(CONFIG_NET) += proc_net.o
proc-$(CONFIG_PROC_KCORE) += kcore.o
diff --git a/fs/proc/array.c b/fs/proc/array.c
index d7f9199217b..cd3653e4f35 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -297,15 +297,11 @@ 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[(_KERNEL_CAPABILITY_U32S-1) - __capi]);
+ a->cap[CAP_LAST_U32 - __capi]);
}
seq_putc(m, '\n');
}
-/* Remove non-existent capabilities */
-#define NORM_CAPS(v) (v.cap[CAP_TO_INDEX(CAP_LAST_CAP)] &= \
- CAP_TO_MASK(CAP_LAST_CAP + 1) - 1)
-
static inline void task_cap(struct seq_file *m, struct task_struct *p)
{
const struct cred *cred;
@@ -319,11 +315,6 @@ static inline void task_cap(struct seq_file *m, struct task_struct *p)
cap_bset = cred->cap_bset;
rcu_read_unlock();
- NORM_CAPS(cap_inheritable);
- NORM_CAPS(cap_permitted);
- NORM_CAPS(cap_effective);
- NORM_CAPS(cap_bset);
-
render_cap_t(m, "CapInh:\t", &cap_inheritable);
render_cap_t(m, "CapPrm:\t", &cap_permitted);
render_cap_t(m, "CapEff:\t", &cap_effective);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 2d696b0c93b..baf852b648a 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -105,7 +105,7 @@
*/
struct pid_entry {
- char *name;
+ const char *name;
int len;
umode_t mode;
const struct inode_operations *iop;
@@ -130,10 +130,6 @@ struct pid_entry {
{ .proc_get_link = get_link } )
#define REG(NAME, MODE, fops) \
NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {})
-#define INF(NAME, MODE, read) \
- NOD(NAME, (S_IFREG|(MODE)), \
- NULL, &proc_info_file_operations, \
- { .proc_read = read } )
#define ONE(NAME, MODE, show) \
NOD(NAME, (S_IFREG|(MODE)), \
NULL, &proc_single_file_operations, \
@@ -200,27 +196,32 @@ static int proc_root_link(struct dentry *dentry, struct path *path)
return result;
}
-static int proc_pid_cmdline(struct task_struct *task, char *buffer)
+static int proc_pid_cmdline(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
{
- return get_cmdline(task, buffer, PAGE_SIZE);
+ /*
+ * Rely on struct seq_operations::show() being called once
+ * per internal buffer allocation. See single_open(), traverse().
+ */
+ BUG_ON(m->size < PAGE_SIZE);
+ m->count += get_cmdline(task, m->buf, PAGE_SIZE);
+ return 0;
}
-static int proc_pid_auxv(struct task_struct *task, char *buffer)
+static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
{
struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ);
- int res = PTR_ERR(mm);
if (mm && !IS_ERR(mm)) {
unsigned int nwords = 0;
do {
nwords += 2;
} while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */
- res = nwords * sizeof(mm->saved_auxv[0]);
- if (res > PAGE_SIZE)
- res = PAGE_SIZE;
- memcpy(buffer, mm->saved_auxv, res);
+ seq_write(m, mm->saved_auxv, nwords * sizeof(mm->saved_auxv[0]));
mmput(mm);
- }
- return res;
+ return 0;
+ } else
+ return PTR_ERR(mm);
}
@@ -229,7 +230,8 @@ static int proc_pid_auxv(struct task_struct *task, char *buffer)
* Provides a wchan file via kallsyms in a proper one-value-per-file format.
* Returns the resolved symbol. If that fails, simply return the address.
*/
-static int proc_pid_wchan(struct task_struct *task, char *buffer)
+static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
{
unsigned long wchan;
char symname[KSYM_NAME_LEN];
@@ -240,9 +242,9 @@ static int proc_pid_wchan(struct task_struct *task, char *buffer)
if (!ptrace_may_access(task, PTRACE_MODE_READ))
return 0;
else
- return sprintf(buffer, "%lu", wchan);
+ return seq_printf(m, "%lu", wchan);
else
- return sprintf(buffer, "%s", symname);
+ return seq_printf(m, "%s", symname);
}
#endif /* CONFIG_KALLSYMS */
@@ -304,9 +306,10 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
/*
* Provides /proc/PID/schedstat
*/
-static int proc_pid_schedstat(struct task_struct *task, char *buffer)
+static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
{
- return sprintf(buffer, "%llu %llu %lu\n",
+ return seq_printf(m, "%llu %llu %lu\n",
(unsigned long long)task->se.sum_exec_runtime,
(unsigned long long)task->sched_info.run_delay,
task->sched_info.pcount);
@@ -404,7 +407,8 @@ static const struct file_operations proc_cpuset_operations = {
};
#endif
-static int proc_oom_score(struct task_struct *task, char *buffer)
+static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
{
unsigned long totalpages = totalram_pages + total_swap_pages;
unsigned long points = 0;
@@ -414,12 +418,12 @@ static int proc_oom_score(struct task_struct *task, char *buffer)
points = oom_badness(task, NULL, NULL, totalpages) *
1000 / totalpages;
read_unlock(&tasklist_lock);
- return sprintf(buffer, "%lu\n", points);
+ return seq_printf(m, "%lu\n", points);
}
struct limit_names {
- char *name;
- char *unit;
+ const char *name;
+ const char *unit;
};
static const struct limit_names lnames[RLIM_NLIMITS] = {
@@ -442,12 +446,11 @@ static const struct limit_names lnames[RLIM_NLIMITS] = {
};
/* Display limits for a process */
-static int proc_pid_limits(struct task_struct *task, char *buffer)
+static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
{
unsigned int i;
- int count = 0;
unsigned long flags;
- char *bufptr = buffer;
struct rlimit rlim[RLIM_NLIMITS];
@@ -459,35 +462,34 @@ static int proc_pid_limits(struct task_struct *task, char *buffer)
/*
* print the file header
*/
- count += sprintf(&bufptr[count], "%-25s %-20s %-20s %-10s\n",
+ seq_printf(m, "%-25s %-20s %-20s %-10s\n",
"Limit", "Soft Limit", "Hard Limit", "Units");
for (i = 0; i < RLIM_NLIMITS; i++) {
if (rlim[i].rlim_cur == RLIM_INFINITY)
- count += sprintf(&bufptr[count], "%-25s %-20s ",
+ seq_printf(m, "%-25s %-20s ",
lnames[i].name, "unlimited");
else
- count += sprintf(&bufptr[count], "%-25s %-20lu ",
+ seq_printf(m, "%-25s %-20lu ",
lnames[i].name, rlim[i].rlim_cur);
if (rlim[i].rlim_max == RLIM_INFINITY)
- count += sprintf(&bufptr[count], "%-20s ", "unlimited");
+ seq_printf(m, "%-20s ", "unlimited");
else
- count += sprintf(&bufptr[count], "%-20lu ",
- rlim[i].rlim_max);
+ seq_printf(m, "%-20lu ", rlim[i].rlim_max);
if (lnames[i].unit)
- count += sprintf(&bufptr[count], "%-10s\n",
- lnames[i].unit);
+ seq_printf(m, "%-10s\n", lnames[i].unit);
else
- count += sprintf(&bufptr[count], "\n");
+ seq_putc(m, '\n');
}
- return count;
+ return 0;
}
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
-static int proc_pid_syscall(struct task_struct *task, char *buffer)
+static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
{
long nr;
unsigned long args[6], sp, pc;
@@ -496,11 +498,11 @@ static int proc_pid_syscall(struct task_struct *task, char *buffer)
return res;
if (task_current_syscall(task, &nr, args, 6, &sp, &pc))
- res = sprintf(buffer, "running\n");
+ seq_puts(m, "running\n");
else if (nr < 0)
- res = sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
+ seq_printf(m, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
else
- res = sprintf(buffer,
+ seq_printf(m,
"%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],
@@ -598,43 +600,6 @@ static const struct inode_operations proc_def_inode_operations = {
.setattr = proc_setattr,
};
-#define PROC_BLOCK_SIZE (3*1024) /* 4K page size but our output routines use some slack for overruns */
-
-static ssize_t proc_info_read(struct file * file, char __user * buf,
- size_t count, loff_t *ppos)
-{
- struct inode * inode = file_inode(file);
- unsigned long page;
- ssize_t length;
- struct task_struct *task = get_proc_task(inode);
-
- length = -ESRCH;
- if (!task)
- goto out_no_task;
-
- if (count > PROC_BLOCK_SIZE)
- count = PROC_BLOCK_SIZE;
-
- length = -ENOMEM;
- if (!(page = __get_free_page(GFP_TEMPORARY)))
- goto out;
-
- length = PROC_I(inode)->op.proc_read(task, (char*)page);
-
- if (length >= 0)
- length = simple_read_from_buffer(buf, count, ppos, (char *)page, length);
- free_page(page);
-out:
- put_task_struct(task);
-out_no_task:
- return length;
-}
-
-static const struct file_operations proc_info_file_operations = {
- .read = proc_info_read,
- .llseek = generic_file_llseek,
-};
-
static int proc_single_show(struct seq_file *m, void *v)
{
struct inode *inode = m->private;
@@ -2056,7 +2021,7 @@ static int show_timer(struct seq_file *m, void *v)
struct k_itimer *timer;
struct timers_private *tp = m->private;
int notify;
- static char *nstr[] = {
+ static const char * const nstr[] = {
[SIGEV_SIGNAL] = "signal",
[SIGEV_NONE] = "none",
[SIGEV_THREAD] = "thread",
@@ -2392,7 +2357,7 @@ static const struct file_operations proc_coredump_filter_operations = {
#endif
#ifdef CONFIG_TASK_IO_ACCOUNTING
-static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
+static int do_io_accounting(struct task_struct *task, struct seq_file *m, int whole)
{
struct task_io_accounting acct = task->ioac;
unsigned long flags;
@@ -2416,7 +2381,7 @@ static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
unlock_task_sighand(task, &flags);
}
- result = sprintf(buffer,
+ result = seq_printf(m,
"rchar: %llu\n"
"wchar: %llu\n"
"syscr: %llu\n"
@@ -2436,20 +2401,22 @@ out_unlock:
return result;
}
-static int proc_tid_io_accounting(struct task_struct *task, char *buffer)
+static int proc_tid_io_accounting(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
{
- return do_io_accounting(task, buffer, 0);
+ return do_io_accounting(task, m, 0);
}
-static int proc_tgid_io_accounting(struct task_struct *task, char *buffer)
+static int proc_tgid_io_accounting(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
{
- return do_io_accounting(task, buffer, 1);
+ return do_io_accounting(task, m, 1);
}
#endif /* CONFIG_TASK_IO_ACCOUNTING */
#ifdef CONFIG_USER_NS
static int proc_id_map_open(struct inode *inode, struct file *file,
- struct seq_operations *seq_ops)
+ const struct seq_operations *seq_ops)
{
struct user_namespace *ns = NULL;
struct task_struct *task;
@@ -2557,10 +2524,10 @@ static const struct pid_entry tgid_base_stuff[] = {
DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
#endif
REG("environ", S_IRUSR, proc_environ_operations),
- INF("auxv", S_IRUSR, proc_pid_auxv),
+ ONE("auxv", S_IRUSR, proc_pid_auxv),
ONE("status", S_IRUGO, proc_pid_status),
ONE("personality", S_IRUSR, proc_pid_personality),
- INF("limits", S_IRUGO, proc_pid_limits),
+ ONE("limits", S_IRUGO, proc_pid_limits),
#ifdef CONFIG_SCHED_DEBUG
REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations),
#endif
@@ -2569,9 +2536,9 @@ static const struct pid_entry tgid_base_stuff[] = {
#endif
REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
- INF("syscall", S_IRUSR, proc_pid_syscall),
+ ONE("syscall", S_IRUSR, proc_pid_syscall),
#endif
- INF("cmdline", S_IRUGO, proc_pid_cmdline),
+ ONE("cmdline", S_IRUGO, proc_pid_cmdline),
ONE("stat", S_IRUGO, proc_tgid_stat),
ONE("statm", S_IRUGO, proc_pid_statm),
REG("maps", S_IRUGO, proc_pid_maps_operations),
@@ -2594,13 +2561,13 @@ static const struct pid_entry tgid_base_stuff[] = {
DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
#endif
#ifdef CONFIG_KALLSYMS
- INF("wchan", S_IRUGO, proc_pid_wchan),
+ ONE("wchan", S_IRUGO, proc_pid_wchan),
#endif
#ifdef CONFIG_STACKTRACE
ONE("stack", S_IRUSR, proc_pid_stack),
#endif
#ifdef CONFIG_SCHEDSTATS
- INF("schedstat", S_IRUGO, proc_pid_schedstat),
+ ONE("schedstat", S_IRUGO, proc_pid_schedstat),
#endif
#ifdef CONFIG_LATENCYTOP
REG("latency", S_IRUGO, proc_lstats_operations),
@@ -2611,7 +2578,7 @@ static const struct pid_entry tgid_base_stuff[] = {
#ifdef CONFIG_CGROUPS
REG("cgroup", S_IRUGO, proc_cgroup_operations),
#endif
- INF("oom_score", S_IRUGO, proc_oom_score),
+ ONE("oom_score", S_IRUGO, proc_oom_score),
REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations),
REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
@@ -2625,10 +2592,10 @@ static const struct pid_entry tgid_base_stuff[] = {
REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations),
#endif
#ifdef CONFIG_TASK_IO_ACCOUNTING
- INF("io", S_IRUSR, proc_tgid_io_accounting),
+ ONE("io", S_IRUSR, proc_tgid_io_accounting),
#endif
#ifdef CONFIG_HARDWALL
- INF("hardwall", S_IRUGO, proc_pid_hardwall),
+ ONE("hardwall", S_IRUGO, proc_pid_hardwall),
#endif
#ifdef CONFIG_USER_NS
REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations),
@@ -2780,12 +2747,12 @@ out:
struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
- int result = 0;
+ int result = -ENOENT;
struct task_struct *task;
unsigned tgid;
struct pid_namespace *ns;
- tgid = name_to_int(dentry);
+ tgid = name_to_int(&dentry->d_name);
if (tgid == ~0U)
goto out;
@@ -2847,7 +2814,7 @@ retry:
return iter;
}
-#define TGID_OFFSET (FIRST_PROCESS_ENTRY + 1)
+#define TGID_OFFSET (FIRST_PROCESS_ENTRY + 2)
/* for the /proc/ directory itself, after non-process stuff has been done */
int proc_pid_readdir(struct file *file, struct dir_context *ctx)
@@ -2859,14 +2826,19 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
if (pos >= PID_MAX_LIMIT + TGID_OFFSET)
return 0;
- if (pos == TGID_OFFSET - 1) {
+ if (pos == TGID_OFFSET - 2) {
struct inode *inode = ns->proc_self->d_inode;
if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK))
return 0;
- iter.tgid = 0;
- } else {
- iter.tgid = pos - TGID_OFFSET;
+ ctx->pos = pos = pos + 1;
}
+ if (pos == TGID_OFFSET - 1) {
+ struct inode *inode = ns->proc_thread_self->d_inode;
+ if (!dir_emit(ctx, "thread-self", 11, inode->i_ino, DT_LNK))
+ return 0;
+ ctx->pos = pos = pos + 1;
+ }
+ iter.tgid = pos - TGID_OFFSET;
iter.task = NULL;
for (iter = next_tgid(ns, iter);
iter.task;
@@ -2895,19 +2867,22 @@ static const struct pid_entry tid_base_stuff[] = {
DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations),
+#ifdef CONFIG_NET
+ DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations),
+#endif
REG("environ", S_IRUSR, proc_environ_operations),
- INF("auxv", S_IRUSR, proc_pid_auxv),
+ ONE("auxv", S_IRUSR, proc_pid_auxv),
ONE("status", S_IRUGO, proc_pid_status),
ONE("personality", S_IRUSR, proc_pid_personality),
- INF("limits", S_IRUGO, proc_pid_limits),
+ ONE("limits", S_IRUGO, proc_pid_limits),
#ifdef CONFIG_SCHED_DEBUG
REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations),
#endif
REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
- INF("syscall", S_IRUSR, proc_pid_syscall),
+ ONE("syscall", S_IRUSR, proc_pid_syscall),
#endif
- INF("cmdline", S_IRUGO, proc_pid_cmdline),
+ ONE("cmdline", S_IRUGO, proc_pid_cmdline),
ONE("stat", S_IRUGO, proc_tid_stat),
ONE("statm", S_IRUGO, proc_pid_statm),
REG("maps", S_IRUGO, proc_tid_maps_operations),
@@ -2932,13 +2907,13 @@ static const struct pid_entry tid_base_stuff[] = {
DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations),
#endif
#ifdef CONFIG_KALLSYMS
- INF("wchan", S_IRUGO, proc_pid_wchan),
+ ONE("wchan", S_IRUGO, proc_pid_wchan),
#endif
#ifdef CONFIG_STACKTRACE
ONE("stack", S_IRUSR, proc_pid_stack),
#endif
#ifdef CONFIG_SCHEDSTATS
- INF("schedstat", S_IRUGO, proc_pid_schedstat),
+ ONE("schedstat", S_IRUGO, proc_pid_schedstat),
#endif
#ifdef CONFIG_LATENCYTOP
REG("latency", S_IRUGO, proc_lstats_operations),
@@ -2949,7 +2924,7 @@ static const struct pid_entry tid_base_stuff[] = {
#ifdef CONFIG_CGROUPS
REG("cgroup", S_IRUGO, proc_cgroup_operations),
#endif
- INF("oom_score", S_IRUGO, proc_oom_score),
+ ONE("oom_score", S_IRUGO, proc_oom_score),
REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations),
REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations),
#ifdef CONFIG_AUDITSYSCALL
@@ -2960,10 +2935,10 @@ static const struct pid_entry tid_base_stuff[] = {
REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
#endif
#ifdef CONFIG_TASK_IO_ACCOUNTING
- INF("io", S_IRUSR, proc_tid_io_accounting),
+ ONE("io", S_IRUSR, proc_tid_io_accounting),
#endif
#ifdef CONFIG_HARDWALL
- INF("hardwall", S_IRUGO, proc_pid_hardwall),
+ ONE("hardwall", S_IRUGO, proc_pid_hardwall),
#endif
#ifdef CONFIG_USER_NS
REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations),
@@ -3033,7 +3008,7 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry
if (!leader)
goto out_no_task;
- tid = name_to_int(dentry);
+ tid = name_to_int(&dentry->d_name);
if (tid == ~0U)
goto out;
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 0788d093f5d..955bb55fab8 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -206,7 +206,7 @@ static struct dentry *proc_lookupfd_common(struct inode *dir,
{
struct task_struct *task = get_proc_task(dir);
int result = -ENOENT;
- unsigned fd = name_to_int(dentry);
+ unsigned fd = name_to_int(&dentry->d_name);
if (!task)
goto out_no_task;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index b7f268eb5f4..317b72641eb 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -27,7 +27,7 @@
#include "internal.h"
-DEFINE_SPINLOCK(proc_subdir_lock);
+static DEFINE_SPINLOCK(proc_subdir_lock);
static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
{
@@ -330,28 +330,28 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
nlink_t nlink)
{
struct proc_dir_entry *ent = NULL;
- const char *fn = name;
- unsigned int len;
-
- /* make sure name is valid */
- if (!name || !strlen(name))
- goto out;
+ const char *fn;
+ struct qstr qstr;
if (xlate_proc_name(name, parent, &fn) != 0)
goto out;
+ qstr.name = fn;
+ qstr.len = strlen(fn);
+ if (qstr.len == 0 || qstr.len >= 256) {
+ WARN(1, "name len %u\n", qstr.len);
+ return NULL;
+ }
+ if (*parent == &proc_root && name_to_int(&qstr) != ~0U) {
+ WARN(1, "create '/proc/%s' by hand\n", qstr.name);
+ return NULL;
+ }
- /* At this point there must not be any '/' characters beyond *fn */
- if (strchr(fn, '/'))
- goto out;
-
- len = strlen(fn);
-
- ent = kzalloc(sizeof(struct proc_dir_entry) + len + 1, GFP_KERNEL);
+ ent = kzalloc(sizeof(struct proc_dir_entry) + qstr.len + 1, GFP_KERNEL);
if (!ent)
goto out;
- memcpy(ent->name, fn, len + 1);
- ent->namelen = len;
+ memcpy(ent->name, fn, qstr.len + 1);
+ ent->namelen = qstr.len;
ent->mode = mode;
ent->nlink = nlink;
atomic_set(&ent->count, 1);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 0adbc02d60e..333080d7a67 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -442,6 +442,7 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
int proc_fill_super(struct super_block *s)
{
struct inode *root_inode;
+ int ret;
s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC;
s->s_blocksize = 1024;
@@ -463,5 +464,9 @@ int proc_fill_super(struct super_block *s)
return -ENOMEM;
}
- return proc_setup_self(s);
+ ret = proc_setup_self(s);
+ if (ret) {
+ return ret;
+ }
+ return proc_setup_thread_self(s);
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 3ab6d14e71c..7da13e49128 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -52,7 +52,6 @@ struct proc_dir_entry {
union proc_op {
int (*proc_get_link)(struct dentry *, struct path *);
- int (*proc_read)(struct task_struct *task, char *page);
int (*proc_show)(struct seq_file *m,
struct pid_namespace *ns, struct pid *pid,
struct task_struct *task);
@@ -112,10 +111,10 @@ static inline int task_dumpable(struct task_struct *task)
return 0;
}
-static inline unsigned name_to_int(struct dentry *dentry)
+static inline unsigned name_to_int(const struct qstr *qstr)
{
- const char *name = dentry->d_name.name;
- int len = dentry->d_name.len;
+ const char *name = qstr->name;
+ int len = qstr->len;
unsigned n = 0;
if (len > 1 && *name == '0')
@@ -178,8 +177,6 @@ extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, i
/*
* generic.c
*/
-extern spinlock_t proc_subdir_lock;
-
extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
extern struct dentry *proc_lookup_de(struct proc_dir_entry *, struct inode *,
struct dentry *);
@@ -234,6 +231,12 @@ static inline int proc_net_init(void) { return 0; }
extern int proc_setup_self(struct super_block *);
/*
+ * proc_thread_self.c
+ */
+extern int proc_setup_thread_self(struct super_block *);
+extern void proc_thread_self_init(void);
+
+/*
* proc_sysctl.c
*/
#ifdef CONFIG_PROC_SYSCTL
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 39e6ef32f0b..6df8d0722c9 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -172,7 +172,7 @@ get_sparsemem_vmemmap_info(struct kcore_list *ent, struct list_head *head)
start = ((unsigned long)pfn_to_page(pfn)) & PAGE_MASK;
end = ((unsigned long)pfn_to_page(pfn + nr_pages)) - 1;
- end = ALIGN(end, PAGE_SIZE);
+ end = PAGE_ALIGN(end);
/* overlap check (because we have to align page */
list_for_each_entry(tmp, head, list) {
if (tmp->type != KCORE_VMEMMAP)
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 7445af0b1aa..aa1eee06420 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -168,7 +168,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
K(global_page_state(NR_WRITEBACK)),
K(global_page_state(NR_ANON_PAGES)),
K(global_page_state(NR_FILE_MAPPED)),
- K(global_page_state(NR_SHMEM)),
+ K(i.sharedram),
K(global_page_state(NR_SLAB_RECLAIMABLE) +
global_page_state(NR_SLAB_UNRECLAIMABLE)),
K(global_page_state(NR_SLAB_RECLAIMABLE)),
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 4677bb7dc7c..a63af3e0a61 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -113,9 +113,11 @@ static struct net *get_proc_task_net(struct inode *dir)
rcu_read_lock();
task = pid_task(proc_pid(dir), PIDTYPE_PID);
if (task != NULL) {
- ns = task_nsproxy(task);
+ task_lock(task);
+ ns = task->nsproxy;
if (ns != NULL)
net = get_net(ns->net_ns);
+ task_unlock(task);
}
rcu_read_unlock();
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 71290463a1d..f92d5dd578a 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -632,7 +632,7 @@ out:
return ret;
}
-static int scan(struct ctl_table_header *head, ctl_table *table,
+static int scan(struct ctl_table_header *head, struct ctl_table *table,
unsigned long *pos, struct file *file,
struct dir_context *ctx)
{
diff --git a/fs/proc/proc_tty.c b/fs/proc/proc_tty.c
index cb761f01030..15f327bed8c 100644
--- a/fs/proc/proc_tty.c
+++ b/fs/proc/proc_tty.c
@@ -18,7 +18,7 @@
/*
* The /proc/tty directory inodes...
*/
-static struct proc_dir_entry *proc_tty_ldisc, *proc_tty_driver;
+static struct proc_dir_entry *proc_tty_driver;
/*
* This is the handler for /proc/tty/drivers
@@ -176,7 +176,7 @@ void __init proc_tty_init(void)
{
if (!proc_mkdir("tty", NULL))
return;
- proc_tty_ldisc = proc_mkdir("tty/ldisc", NULL);
+ proc_mkdir("tty/ldisc", NULL); /* Preserved: it's userspace visible */
/*
* /proc/tty/driver/serial reveals the exact character counts for
* serial links which is just too easy to abuse for inferring
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 5dbadecb234..094e44d4a6b 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -149,6 +149,8 @@ static void proc_kill_sb(struct super_block *sb)
ns = (struct pid_namespace *)sb->s_fs_info;
if (ns->proc_self)
dput(ns->proc_self);
+ if (ns->proc_thread_self)
+ dput(ns->proc_thread_self);
kill_anon_super(sb);
put_pid_ns(ns);
}
@@ -170,6 +172,7 @@ void __init proc_root_init(void)
return;
proc_self_init();
+ proc_thread_self_init();
proc_symlink("mounts", NULL, "self/mounts");
proc_net_init();
@@ -199,10 +202,10 @@ static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct
static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
{
- if (!proc_lookup(dir, dentry, flags))
+ if (!proc_pid_lookup(dir, dentry, flags))
return NULL;
- return proc_pid_lookup(dir, dentry, flags);
+ return proc_lookup(dir, dentry, flags);
}
static int proc_root_readdir(struct file *file, struct dir_context *ctx)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index cfa63ee92c9..dfc791c42d6 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -925,15 +925,30 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
struct pagemapread *pm = walk->private;
- unsigned long addr;
+ unsigned long addr = start;
int err = 0;
- pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
- for (addr = start; addr < end; addr += PAGE_SIZE) {
- err = add_to_pagemap(addr, &pme, pm);
- if (err)
- break;
+ while (addr < end) {
+ struct vm_area_struct *vma = find_vma(walk->mm, addr);
+ pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ unsigned long vm_end;
+
+ if (!vma) {
+ vm_end = end;
+ } else {
+ vm_end = min(end, vma->vm_end);
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ pme.pme |= PM_STATUS2(pm->v2, __PM_SOFT_DIRTY);
+ }
+
+ for (; addr < vm_end; addr += PAGE_SIZE) {
+ err = add_to_pagemap(addr, &pme, pm);
+ if (err)
+ goto out;
+ }
}
+
+out:
return err;
}
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
new file mode 100644
index 00000000000..59075b509df
--- /dev/null
+++ b/fs/proc/thread_self.c
@@ -0,0 +1,85 @@
+#include <linux/sched.h>
+#include <linux/namei.h>
+#include <linux/slab.h>
+#include <linux/pid_namespace.h>
+#include "internal.h"
+
+/*
+ * /proc/thread_self:
+ */
+static int proc_thread_self_readlink(struct dentry *dentry, char __user *buffer,
+ int buflen)
+{
+ struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+ pid_t tgid = task_tgid_nr_ns(current, ns);
+ pid_t pid = task_pid_nr_ns(current, ns);
+ char tmp[PROC_NUMBUF + 6 + PROC_NUMBUF];
+ if (!pid)
+ return -ENOENT;
+ sprintf(tmp, "%d/task/%d", tgid, pid);
+ return readlink_copy(buffer, buflen, tmp);
+}
+
+static void *proc_thread_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+ struct pid_namespace *ns = dentry->d_sb->s_fs_info;
+ pid_t tgid = task_tgid_nr_ns(current, ns);
+ pid_t pid = task_pid_nr_ns(current, ns);
+ char *name = ERR_PTR(-ENOENT);
+ if (pid) {
+ name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL);
+ if (!name)
+ name = ERR_PTR(-ENOMEM);
+ else
+ sprintf(name, "%d/task/%d", tgid, pid);
+ }
+ nd_set_link(nd, name);
+ return NULL;
+}
+
+static const struct inode_operations proc_thread_self_inode_operations = {
+ .readlink = proc_thread_self_readlink,
+ .follow_link = proc_thread_self_follow_link,
+ .put_link = kfree_put_link,
+};
+
+static unsigned thread_self_inum;
+
+int proc_setup_thread_self(struct super_block *s)
+{
+ struct inode *root_inode = s->s_root->d_inode;
+ struct pid_namespace *ns = s->s_fs_info;
+ struct dentry *thread_self;
+
+ mutex_lock(&root_inode->i_mutex);
+ thread_self = d_alloc_name(s->s_root, "thread-self");
+ if (thread_self) {
+ struct inode *inode = new_inode_pseudo(s);
+ if (inode) {
+ inode->i_ino = thread_self_inum;
+ inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+ inode->i_mode = S_IFLNK | S_IRWXUGO;
+ inode->i_uid = GLOBAL_ROOT_UID;
+ inode->i_gid = GLOBAL_ROOT_GID;
+ inode->i_op = &proc_thread_self_inode_operations;
+ d_add(thread_self, inode);
+ } else {
+ dput(thread_self);
+ thread_self = ERR_PTR(-ENOMEM);
+ }
+ } else {
+ thread_self = ERR_PTR(-ENOMEM);
+ }
+ mutex_unlock(&root_inode->i_mutex);
+ if (IS_ERR(thread_self)) {
+ pr_err("proc_fill_super: can't allocate /proc/thread_self\n");
+ return PTR_ERR(thread_self);
+ }
+ ns->proc_thread_self = thread_self;
+ return 0;
+}
+
+void __init proc_thread_self_init(void)
+{
+ proc_alloc_inum(&thread_self_inum);
+}
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 382aa890e22..a90d6d35419 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -328,6 +328,82 @@ static inline char *alloc_elfnotes_buf(size_t notes_sz)
* virtually contiguous user-space in ELF layout.
*/
#ifdef CONFIG_MMU
+/*
+ * remap_oldmem_pfn_checked - do remap_oldmem_pfn_range replacing all pages
+ * reported as not being ram with the zero page.
+ *
+ * @vma: vm_area_struct describing requested mapping
+ * @from: start remapping from
+ * @pfn: page frame number to start remapping to
+ * @size: remapping size
+ * @prot: protection bits
+ *
+ * Returns zero on success, -EAGAIN on failure.
+ */
+static int remap_oldmem_pfn_checked(struct vm_area_struct *vma,
+ unsigned long from, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ unsigned long map_size;
+ unsigned long pos_start, pos_end, pos;
+ unsigned long zeropage_pfn = my_zero_pfn(0);
+ size_t len = 0;
+
+ pos_start = pfn;
+ pos_end = pfn + (size >> PAGE_SHIFT);
+
+ for (pos = pos_start; pos < pos_end; ++pos) {
+ if (!pfn_is_ram(pos)) {
+ /*
+ * We hit a page which is not ram. Remap the continuous
+ * region between pos_start and pos-1 and replace
+ * the non-ram page at pos with the zero page.
+ */
+ if (pos > pos_start) {
+ /* Remap continuous region */
+ map_size = (pos - pos_start) << PAGE_SHIFT;
+ if (remap_oldmem_pfn_range(vma, from + len,
+ pos_start, map_size,
+ prot))
+ goto fail;
+ len += map_size;
+ }
+ /* Remap the zero page */
+ if (remap_oldmem_pfn_range(vma, from + len,
+ zeropage_pfn,
+ PAGE_SIZE, prot))
+ goto fail;
+ len += PAGE_SIZE;
+ pos_start = pos + 1;
+ }
+ }
+ if (pos > pos_start) {
+ /* Remap the rest */
+ map_size = (pos - pos_start) << PAGE_SHIFT;
+ if (remap_oldmem_pfn_range(vma, from + len, pos_start,
+ map_size, prot))
+ goto fail;
+ }
+ return 0;
+fail:
+ do_munmap(vma->vm_mm, from, len);
+ return -EAGAIN;
+}
+
+static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma,
+ unsigned long from, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ /*
+ * Check if oldmem_pfn_is_ram was registered to avoid
+ * looping over all pages without a reason.
+ */
+ if (oldmem_pfn_is_ram)
+ return remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
+ else
+ return remap_oldmem_pfn_range(vma, from, pfn, size, prot);
+}
+
static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
{
size_t size = vma->vm_end - vma->vm_start;
@@ -387,9 +463,9 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
tsz = min_t(size_t, m->offset + m->size - start, size);
paddr = m->paddr + start - m->offset;
- if (remap_oldmem_pfn_range(vma, vma->vm_start + len,
- paddr >> PAGE_SHIFT, tsz,
- vma->vm_page_prot))
+ if (vmcore_remap_oldmem_pfn(vma, vma->vm_start + len,
+ paddr >> PAGE_SHIFT, tsz,
+ vma->vm_page_prot))
goto fail;
size -= tsz;
start += tsz;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-23 17:04:36 +0000