From a5969cabbb4660eab42b6ef0412cbbd1200cf14d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 12 Oct 2024 07:10:09 +0000
Subject: [PATCH] 修改led为gpio
---
kernel/fs/proc/base.c | 633 +++++++++++++++++++++++++++++++++++++-------------------
1 files changed, 416 insertions(+), 217 deletions(-)
diff --git a/kernel/fs/proc/base.c b/kernel/fs/proc/base.c
index 0dd4439..8b1ecb5 100644
--- a/kernel/fs/proc/base.c
+++ b/kernel/fs/proc/base.c
@@ -59,6 +59,7 @@
#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fdtable.h>
+#include <linux/generic-radix-tree.h>
#include <linux/string.h>
#include <linux/seq_file.h>
#include <linux/namei.h>
@@ -92,8 +93,9 @@
#include <linux/sched/coredump.h>
#include <linux/sched/debug.h>
#include <linux/sched/stat.h>
-#include <linux/flex_array.h>
#include <linux/posix-timers.h>
+#include <linux/time_namespace.h>
+#include <linux/resctrl.h>
#include <linux/cpufreq_times.h>
#include <trace/events/oom.h>
#include "internal.h"
@@ -141,9 +143,13 @@
#define REG(NAME, MODE, fops) \
NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {})
#define ONE(NAME, MODE, show) \
- NOD(NAME, (S_IFREG|(MODE)), \
+ NOD(NAME, (S_IFREG|(MODE)), \
NULL, &proc_single_file_operations, \
{ .proc_show = show } )
+#define ATTR(LSM, NAME, MODE) \
+ NOD(NAME, (S_IFREG|(MODE)), \
+ NULL, &proc_pid_attr_operations, \
+ { .lsm = LSM })
/*
* Count the number of hardlinks for the pid_entry table, excluding the .
@@ -400,11 +406,11 @@
static int lock_trace(struct task_struct *task)
{
- int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
+ int err = down_read_killable(&task->signal->exec_update_lock);
if (err)
return err;
if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
- mutex_unlock(&task->signal->cred_guard_mutex);
+ up_read(&task->signal->exec_update_lock);
return -EPERM;
}
return 0;
@@ -412,7 +418,7 @@
static void unlock_trace(struct task_struct *task)
{
- mutex_unlock(&task->signal->cred_guard_mutex);
+ up_read(&task->signal->exec_update_lock);
}
#ifdef CONFIG_STACKTRACE
@@ -422,7 +428,6 @@
static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
- struct stack_trace trace;
unsigned long *entries;
int err;
@@ -445,20 +450,17 @@
if (!entries)
return -ENOMEM;
- trace.nr_entries = 0;
- trace.max_entries = MAX_STACK_TRACE_DEPTH;
- trace.entries = entries;
- trace.skip = 0;
-
err = lock_trace(task);
if (!err) {
- unsigned int i;
+ unsigned int i, nr_entries;
- save_stack_trace_tsk(task, &trace);
+ nr_entries = stack_trace_save_tsk(task, entries,
+ MAX_STACK_TRACE_DEPTH, 0);
- for (i = 0; i < trace.nr_entries; i++) {
+ for (i = 0; i < nr_entries; i++) {
seq_printf(m, "[<0>] %pB\n", (void *)entries[i]);
}
+
unlock_trace(task);
}
kfree(entries);
@@ -475,7 +477,7 @@
struct pid *pid, struct task_struct *task)
{
if (unlikely(!sched_info_on()))
- seq_printf(m, "0 0 0\n");
+ seq_puts(m, "0 0 0\n");
else
seq_printf(m, "%llu %llu %lu\n",
(unsigned long long)task->se.sum_exec_runtime,
@@ -504,9 +506,8 @@
lr->count, lr->time, lr->max);
for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
unsigned long bt = lr->backtrace[q];
+
if (!bt)
- break;
- if (bt == ULONG_MAX)
break;
seq_printf(m, " %ps", (void *)bt);
}
@@ -530,7 +531,7 @@
if (!task)
return -ESRCH;
- clear_all_latency_tracing(task);
+ clear_tsk_latency_tracing(task);
put_task_struct(task);
return count;
@@ -549,11 +550,19 @@
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 totalpages = totalram_pages() + total_swap_pages;
unsigned long points = 0;
+ long badness;
- points = oom_badness(task, NULL, NULL, totalpages) *
- 1000 / totalpages;
+ badness = oom_badness(task, totalpages);
+ /*
+ * Special case OOM_SCORE_ADJ_MIN for all others scale the
+ * badness value into [0, 2000] range which we have been
+ * exporting for a long time so userspace might depend on it.
+ */
+ if (badness != LONG_MIN)
+ points = (1000 + badness * 1000 / (long)totalpages) * 2 / 3;
+
seq_printf(m, "%lu\n", points);
return 0;
@@ -600,8 +609,10 @@
/*
* print the file header
*/
- seq_printf(m, "%-25s %-20s %-20s %-10s\n",
- "Limit", "Soft Limit", "Hard Limit", "Units");
+ seq_puts(m, "Limit "
+ "Soft Limit "
+ "Hard Limit "
+ "Units \n");
for (i = 0; i < RLIM_NLIMITS; i++) {
if (rlim[i].rlim_cur == RLIM_INFINITY)
@@ -629,24 +640,25 @@
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;
+ struct syscall_info info;
+ u64 *args = &info.data.args[0];
int res;
res = lock_trace(task);
if (res)
return res;
- if (task_current_syscall(task, &nr, args, 6, &sp, &pc))
+ if (task_current_syscall(task, &info))
seq_puts(m, "running\n");
- else if (nr < 0)
- seq_printf(m, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
+ else if (info.data.nr < 0)
+ seq_printf(m, "%d 0x%llx 0x%llx\n",
+ info.data.nr, info.sp, info.data.instruction_pointer);
else
seq_printf(m,
- "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
- nr,
+ "%d 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx\n",
+ info.data.nr,
args[0], args[1], args[2], args[3], args[4], args[5],
- sp, pc);
+ info.sp, info.data.instruction_pointer);
unlock_trace(task);
return 0;
@@ -695,13 +707,21 @@
* May current process learn task's sched/cmdline info (for hide_pid_min=1)
* or euid/egid (for hide_pid_min=2)?
*/
-static bool has_pid_permissions(struct pid_namespace *pid,
+static bool has_pid_permissions(struct proc_fs_info *fs_info,
struct task_struct *task,
- int hide_pid_min)
+ enum proc_hidepid hide_pid_min)
{
- if (pid->hide_pid < hide_pid_min)
+ /*
+ * If 'hidpid' mount option is set force a ptrace check,
+ * we indicate that we are using a filesystem syscall
+ * by passing PTRACE_MODE_READ_FSCREDS
+ */
+ if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE)
+ return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
+
+ if (fs_info->hide_pid < hide_pid_min)
return true;
- if (in_group_p(pid->pid_gid))
+ if (in_group_p(fs_info->pid_gid))
return true;
return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
}
@@ -709,18 +729,18 @@
static int proc_pid_permission(struct inode *inode, int mask)
{
- struct pid_namespace *pid = proc_pid_ns(inode);
+ struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
struct task_struct *task;
bool has_perms;
task = get_proc_task(inode);
if (!task)
return -ESRCH;
- has_perms = has_pid_permissions(pid, task, HIDEPID_NO_ACCESS);
+ has_perms = has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS);
put_task_struct(task);
if (!has_perms) {
- if (pid->hide_pid == HIDEPID_INVISIBLE) {
+ if (fs_info->hide_pid == HIDEPID_INVISIBLE) {
/*
* Let's make getdents(), stat(), and open()
* consistent with each other. If a process
@@ -744,7 +764,7 @@
static int proc_single_show(struct seq_file *m, void *v)
{
struct inode *inode = m->private;
- struct pid_namespace *ns = proc_pid_ns(inode);
+ struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
struct pid *pid = proc_pid(inode);
struct task_struct *task;
int ret;
@@ -1030,6 +1050,8 @@
oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
OOM_SCORE_ADJ_MAX;
put_task_struct(task);
+ if (oom_adj > OOM_ADJUST_MAX)
+ oom_adj = OOM_ADJUST_MAX;
len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
@@ -1222,7 +1244,7 @@
.llseek = default_llseek,
};
-#ifdef CONFIG_AUDITSYSCALL
+#ifdef CONFIG_AUDIT
#define TMPBUFLEN 11
static ssize_t proc_loginuid_read(struct file * file, char __user * buf,
size_t count, loff_t *ppos)
@@ -1248,6 +1270,10 @@
uid_t loginuid;
kuid_t kloginuid;
int rv;
+
+ /* Don't let kthreads write their own loginuid */
+ if (current->flags & PF_KTHREAD)
+ return -EPERM;
rcu_read_lock();
if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) {
@@ -1412,7 +1438,7 @@
static int sched_show(struct seq_file *m, void *v)
{
struct inode *inode = m->private;
- struct pid_namespace *ns = proc_pid_ns(inode);
+ struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
struct task_struct *p;
p = get_proc_task(inode);
@@ -1532,6 +1558,108 @@
#endif /* CONFIG_SCHED_AUTOGROUP */
+#ifdef CONFIG_TIME_NS
+static int timens_offsets_show(struct seq_file *m, void *v)
+{
+ struct task_struct *p;
+
+ p = get_proc_task(file_inode(m->file));
+ if (!p)
+ return -ESRCH;
+ proc_timens_show_offsets(p, m);
+
+ put_task_struct(p);
+
+ return 0;
+}
+
+static ssize_t timens_offsets_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct inode *inode = file_inode(file);
+ struct proc_timens_offset offsets[2];
+ char *kbuf = NULL, *pos, *next_line;
+ struct task_struct *p;
+ int ret, noffsets;
+
+ /* Only allow < page size writes at the beginning of the file */
+ if ((*ppos != 0) || (count >= PAGE_SIZE))
+ return -EINVAL;
+
+ /* Slurp in the user data */
+ kbuf = memdup_user_nul(buf, count);
+ if (IS_ERR(kbuf))
+ return PTR_ERR(kbuf);
+
+ /* Parse the user data */
+ ret = -EINVAL;
+ noffsets = 0;
+ for (pos = kbuf; pos; pos = next_line) {
+ struct proc_timens_offset *off = &offsets[noffsets];
+ char clock[10];
+ int err;
+
+ /* Find the end of line and ensure we don't look past it */
+ next_line = strchr(pos, '\n');
+ if (next_line) {
+ *next_line = '\0';
+ next_line++;
+ if (*next_line == '\0')
+ next_line = NULL;
+ }
+
+ err = sscanf(pos, "%9s %lld %lu", clock,
+ &off->val.tv_sec, &off->val.tv_nsec);
+ if (err != 3 || off->val.tv_nsec >= NSEC_PER_SEC)
+ goto out;
+
+ clock[sizeof(clock) - 1] = 0;
+ if (strcmp(clock, "monotonic") == 0 ||
+ strcmp(clock, __stringify(CLOCK_MONOTONIC)) == 0)
+ off->clockid = CLOCK_MONOTONIC;
+ else if (strcmp(clock, "boottime") == 0 ||
+ strcmp(clock, __stringify(CLOCK_BOOTTIME)) == 0)
+ off->clockid = CLOCK_BOOTTIME;
+ else
+ goto out;
+
+ noffsets++;
+ if (noffsets == ARRAY_SIZE(offsets)) {
+ if (next_line)
+ count = next_line - kbuf;
+ break;
+ }
+ }
+
+ ret = -ESRCH;
+ p = get_proc_task(inode);
+ if (!p)
+ goto out;
+ ret = proc_timens_set_offset(file, p, offsets, noffsets);
+ put_task_struct(p);
+ if (ret)
+ goto out;
+
+ ret = count;
+out:
+ kfree(kbuf);
+ return ret;
+}
+
+static int timens_offsets_open(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, timens_offsets_show, inode);
+}
+
+static const struct file_operations proc_timens_offsets_operations = {
+ .open = timens_offsets_open,
+ .read = seq_read,
+ .write = timens_offsets_write,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+#endif /* CONFIG_TIME_NS */
+
static ssize_t comm_write(struct file *file, const char __user *buf,
size_t count, loff_t *offset)
{
@@ -1625,8 +1753,7 @@
if (error)
goto out;
- nd_jump_link(&path);
- return NULL;
+ error = nd_jump_link(&path);
out:
return ERR_PTR(error);
}
@@ -1742,11 +1869,25 @@
*rgid = gid;
}
-struct inode *proc_pid_make_inode(struct super_block * sb,
+void proc_pid_evict_inode(struct proc_inode *ei)
+{
+ struct pid *pid = ei->pid;
+
+ if (S_ISDIR(ei->vfs_inode.i_mode)) {
+ spin_lock(&pid->lock);
+ hlist_del_init_rcu(&ei->sibling_inodes);
+ spin_unlock(&pid->lock);
+ }
+
+ put_pid(pid);
+}
+
+struct inode *proc_pid_make_inode(struct super_block *sb,
struct task_struct *task, umode_t mode)
{
struct inode * inode;
struct proc_inode *ei;
+ struct pid *pid;
/* We need a new inode */
@@ -1764,9 +1905,12 @@
/*
* grab the reference to task.
*/
- ei->pid = get_task_pid(task, PIDTYPE_PID);
- if (!ei->pid)
+ pid = get_task_pid(task, PIDTYPE_PID);
+ if (!pid)
goto out_unlock;
+
+ /* Let the pid remember us for quick removal */
+ ei->pid = pid;
task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
security_task_to_inode(task, inode);
@@ -1779,11 +1923,44 @@
return NULL;
}
+/*
+ * Generating an inode and adding it into @pid->inodes, so that task will
+ * invalidate inode's dentry before being released.
+ *
+ * This helper is used for creating dir-type entries under '/proc' and
+ * '/proc/<tgid>/task'. Other entries(eg. fd, stat) under '/proc/<tgid>'
+ * can be released by invalidating '/proc/<tgid>' dentry.
+ * In theory, dentries under '/proc/<tgid>/task' can also be released by
+ * invalidating '/proc/<tgid>' dentry, we reserve it to handle single
+ * thread exiting situation: Any one of threads should invalidate its
+ * '/proc/<tgid>/task/<pid>' dentry before released.
+ */
+static struct inode *proc_pid_make_base_inode(struct super_block *sb,
+ struct task_struct *task, umode_t mode)
+{
+ struct inode *inode;
+ struct proc_inode *ei;
+ struct pid *pid;
+
+ inode = proc_pid_make_inode(sb, task, mode);
+ if (!inode)
+ return NULL;
+
+ /* Let proc_flush_pid find this directory inode */
+ ei = PROC_I(inode);
+ pid = ei->pid;
+ spin_lock(&pid->lock);
+ hlist_add_head_rcu(&ei->sibling_inodes, &pid->inodes);
+ spin_unlock(&pid->lock);
+
+ return inode;
+}
+
int pid_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = d_inode(path->dentry);
- struct pid_namespace *pid = proc_pid_ns(inode);
+ struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
struct task_struct *task;
generic_fillattr(inode, stat);
@@ -1793,7 +1970,7 @@
rcu_read_lock();
task = pid_task(proc_pid(inode), PIDTYPE_PID);
if (task) {
- if (!has_pid_permissions(pid, task, HIDEPID_INVISIBLE)) {
+ if (!has_pid_permissions(fs_info, task, HIDEPID_INVISIBLE)) {
rcu_read_unlock();
/*
* This doesn't prevent learning whether PID exists,
@@ -1978,11 +2155,11 @@
goto out;
if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) {
- status = down_read_killable(&mm->mmap_sem);
+ status = mmap_read_lock_killable(mm);
if (!status) {
exact_vma_exists = !!find_exact_vma(mm, vm_start,
vm_end);
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
}
}
@@ -2029,7 +2206,7 @@
if (rc)
goto out_mmput;
- rc = down_read_killable(&mm->mmap_sem);
+ rc = mmap_read_lock_killable(mm);
if (rc)
goto out_mmput;
@@ -2040,7 +2217,7 @@
path_get(path);
rc = 0;
}
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
out_mmput:
mmput(mm);
@@ -2055,16 +2232,16 @@
};
/*
- * Only allow CAP_SYS_ADMIN to follow the links, due to concerns about how the
- * symlinks may be used to bypass permissions on ancestor directories in the
- * path to the file in question.
+ * Only allow CAP_SYS_ADMIN and CAP_CHECKPOINT_RESTORE to follow the links, due
+ * to concerns about how the symlinks may be used to bypass permissions on
+ * ancestor directories in the path to the file in question.
*/
static const char *
proc_map_files_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
- if (!capable(CAP_SYS_ADMIN))
+ if (!checkpoint_restore_ns_capable(&init_user_ns))
return ERR_PTR(-EPERM);
return proc_pid_get_link(dentry, inode, done);
@@ -2130,7 +2307,7 @@
goto out_put_task;
result = ERR_PTR(-EINTR);
- if (down_read_killable(&mm->mmap_sem))
+ if (mmap_read_lock_killable(mm))
goto out_put_mm;
result = ERR_PTR(-ENOENT);
@@ -2143,7 +2320,7 @@
(void *)(unsigned long)vma->vm_file->f_mode);
out_no_vma:
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
out_put_mm:
mmput(mm);
out_put_task:
@@ -2165,10 +2342,11 @@
struct task_struct *task;
struct mm_struct *mm;
unsigned long nr_files, pos, i;
- struct flex_array *fa = NULL;
- struct map_files_info info;
+ GENRADIX(struct map_files_info) fa;
struct map_files_info *p;
int ret;
+
+ genradix_init(&fa);
ret = -ENOENT;
task = get_proc_task(file_inode(file));
@@ -2187,7 +2365,7 @@
if (!mm)
goto out_put_task;
- ret = down_read_killable(&mm->mmap_sem);
+ ret = mmap_read_lock_killable(mm);
if (ret) {
mmput(mm);
goto out_put_task;
@@ -2198,52 +2376,39 @@
/*
* We need two passes here:
*
- * 1) Collect vmas of mapped files with mmap_sem taken
- * 2) Release mmap_sem and instantiate entries
+ * 1) Collect vmas of mapped files with mmap_lock taken
+ * 2) Release mmap_lock and instantiate entries
*
* otherwise we get lockdep complained, since filldir()
- * routine might require mmap_sem taken in might_fault().
+ * routine might require mmap_lock taken in might_fault().
*/
for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) {
- if (vma->vm_file && ++pos > ctx->pos)
- nr_files++;
- }
+ if (!vma->vm_file)
+ continue;
+ if (++pos <= ctx->pos)
+ continue;
- if (nr_files) {
- fa = flex_array_alloc(sizeof(info), nr_files,
- GFP_KERNEL);
- if (!fa || flex_array_prealloc(fa, 0, nr_files,
- GFP_KERNEL)) {
+ p = genradix_ptr_alloc(&fa, nr_files++, GFP_KERNEL);
+ if (!p) {
ret = -ENOMEM;
- if (fa)
- flex_array_free(fa);
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
mmput(mm);
goto out_put_task;
}
- for (i = 0, vma = mm->mmap, pos = 2; vma;
- vma = vma->vm_next) {
- if (!vma->vm_file)
- continue;
- if (++pos <= ctx->pos)
- continue;
- info.start = vma->vm_start;
- info.end = vma->vm_end;
- info.mode = vma->vm_file->f_mode;
- if (flex_array_put(fa, i++, &info, GFP_KERNEL))
- BUG();
- }
+ p->start = vma->vm_start;
+ p->end = vma->vm_end;
+ p->mode = vma->vm_file->f_mode;
}
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
mmput(mm);
for (i = 0; i < nr_files; i++) {
char buf[4 * sizeof(long) + 2]; /* max: %lx-%lx\0 */
unsigned int len;
- p = flex_array_get(fa, i);
+ p = genradix_ptr(&fa, i);
len = snprintf(buf, sizeof(buf), "%lx-%lx", p->start, p->end);
if (!proc_fill_cache(file, ctx,
buf, len,
@@ -2253,12 +2418,11 @@
break;
ctx->pos++;
}
- if (fa)
- flex_array_free(fa);
out_put_task:
put_task_struct(task);
out:
+ genradix_free(&fa);
return ret;
}
@@ -2357,7 +2521,7 @@
return -ENOMEM;
tp->pid = proc_pid(inode);
- tp->ns = proc_pid_ns(inode);
+ tp->ns = proc_pid_ns(inode->i_sb);
return 0;
}
@@ -2386,10 +2550,13 @@
return -ESRCH;
if (p != current) {
- if (!capable(CAP_SYS_NICE)) {
+ rcu_read_lock();
+ if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
+ rcu_read_unlock();
count = -EPERM;
goto out;
}
+ rcu_read_unlock();
err = security_task_setscheduler(p);
if (err) {
@@ -2422,11 +2589,14 @@
return -ESRCH;
if (p != current) {
-
- if (!capable(CAP_SYS_NICE)) {
+ rcu_read_lock();
+ if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
+ rcu_read_unlock();
err = -EPERM;
goto out;
}
+ rcu_read_unlock();
+
err = security_task_getscheduler(p);
if (err)
goto out;
@@ -2481,11 +2651,10 @@
static struct dentry *proc_pident_lookup(struct inode *dir,
struct dentry *dentry,
- const struct pid_entry *ents,
- unsigned int nents)
+ const struct pid_entry *p,
+ const struct pid_entry *end)
{
struct task_struct *task = get_proc_task(dir);
- const struct pid_entry *p, *last;
struct dentry *res = ERR_PTR(-ENOENT);
if (!task)
@@ -2495,8 +2664,7 @@
* Yes, it does not scale. And it should not. Don't add
* new entries into /proc/<tgid>/ without very good reasons.
*/
- last = &ents[nents];
- for (p = ents; p < last; p++) {
+ for (; p < end; p++) {
if (p->len != dentry->d_name.len)
continue;
if (!memcmp(dentry->d_name.name, p->name, p->len)) {
@@ -2554,7 +2722,7 @@
if (!task)
return -ESRCH;
- length = security_getprocattr(task,
+ length = security_getprocattr(task, PROC_I(inode)->op.lsm,
(char*)file->f_path.dentry->d_name.name,
&p);
put_task_struct(task);
@@ -2612,7 +2780,9 @@
if (rv < 0)
goto out_free;
- rv = security_setprocattr(file->f_path.dentry->d_name.name, page, count);
+ rv = security_setprocattr(PROC_I(inode)->op.lsm,
+ file->f_path.dentry->d_name.name, page,
+ count);
mutex_unlock(¤t->signal->cred_guard_mutex);
out_free:
kfree(page);
@@ -2628,13 +2798,66 @@
.release = mem_release,
};
+#define LSM_DIR_OPS(LSM) \
+static int proc_##LSM##_attr_dir_iterate(struct file *filp, \
+ struct dir_context *ctx) \
+{ \
+ return proc_pident_readdir(filp, ctx, \
+ LSM##_attr_dir_stuff, \
+ ARRAY_SIZE(LSM##_attr_dir_stuff)); \
+} \
+\
+static const struct file_operations proc_##LSM##_attr_dir_ops = { \
+ .read = generic_read_dir, \
+ .iterate = proc_##LSM##_attr_dir_iterate, \
+ .llseek = default_llseek, \
+}; \
+\
+static struct dentry *proc_##LSM##_attr_dir_lookup(struct inode *dir, \
+ struct dentry *dentry, unsigned int flags) \
+{ \
+ return proc_pident_lookup(dir, dentry, \
+ LSM##_attr_dir_stuff, \
+ LSM##_attr_dir_stuff + ARRAY_SIZE(LSM##_attr_dir_stuff)); \
+} \
+\
+static const struct inode_operations proc_##LSM##_attr_dir_inode_ops = { \
+ .lookup = proc_##LSM##_attr_dir_lookup, \
+ .getattr = pid_getattr, \
+ .setattr = proc_setattr, \
+}
+
+#ifdef CONFIG_SECURITY_SMACK
+static const struct pid_entry smack_attr_dir_stuff[] = {
+ ATTR("smack", "current", 0666),
+};
+LSM_DIR_OPS(smack);
+#endif
+
+#ifdef CONFIG_SECURITY_APPARMOR
+static const struct pid_entry apparmor_attr_dir_stuff[] = {
+ ATTR("apparmor", "current", 0666),
+ ATTR("apparmor", "prev", 0444),
+ ATTR("apparmor", "exec", 0666),
+};
+LSM_DIR_OPS(apparmor);
+#endif
+
static const struct pid_entry attr_dir_stuff[] = {
- REG("current", S_IRUGO|S_IWUGO, proc_pid_attr_operations),
- REG("prev", S_IRUGO, proc_pid_attr_operations),
- REG("exec", S_IRUGO|S_IWUGO, proc_pid_attr_operations),
- REG("fscreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations),
- REG("keycreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations),
- REG("sockcreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations),
+ ATTR(NULL, "current", 0666),
+ ATTR(NULL, "prev", 0444),
+ ATTR(NULL, "exec", 0666),
+ ATTR(NULL, "fscreate", 0666),
+ ATTR(NULL, "keycreate", 0666),
+ ATTR(NULL, "sockcreate", 0666),
+#ifdef CONFIG_SECURITY_SMACK
+ DIR("smack", 0555,
+ proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops),
+#endif
+#ifdef CONFIG_SECURITY_APPARMOR
+ DIR("apparmor", 0555,
+ proc_apparmor_attr_dir_inode_ops, proc_apparmor_attr_dir_ops),
+#endif
};
static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx)
@@ -2653,7 +2876,8 @@
struct dentry *dentry, unsigned int flags)
{
return proc_pident_lookup(dir, dentry,
- attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff));
+ attr_dir_stuff,
+ attr_dir_stuff + ARRAY_SIZE(attr_dir_stuff));
}
static const struct inode_operations proc_attr_dir_inode_operations = {
@@ -2748,7 +2972,7 @@
unsigned long flags;
int result;
- result = mutex_lock_killable(&task->signal->cred_guard_mutex);
+ result = down_read_killable(&task->signal->exec_update_lock);
if (result)
return result;
@@ -2784,7 +3008,7 @@
result = 0;
out_unlock:
- mutex_unlock(&task->signal->cred_guard_mutex);
+ up_read(&task->signal->exec_update_lock);
return result;
}
@@ -2953,6 +3177,21 @@
}
#endif /* CONFIG_LIVEPATCH */
+#ifdef CONFIG_STACKLEAK_METRICS
+static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns,
+ struct pid *pid, struct task_struct *task)
+{
+ unsigned long prev_depth = THREAD_SIZE -
+ (task->prev_lowest_stack & (THREAD_SIZE - 1));
+ unsigned long depth = THREAD_SIZE -
+ (task->lowest_stack & (THREAD_SIZE - 1));
+
+ seq_printf(m, "previous stack depth: %lu\nstack depth: %lu\n",
+ prev_depth, depth);
+ return 0;
+}
+#endif /* CONFIG_STACKLEAK_METRICS */
+
/*
* Thread groups
*/
@@ -2963,7 +3202,7 @@
DIR("task", S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations),
DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
DIR("map_files", S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations),
- DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
+ DIR("fdinfo", S_IRUGO|S_IXUGO, 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),
@@ -2978,6 +3217,9 @@
#endif
#ifdef CONFIG_SCHED_AUTOGROUP
REG("autogroup", S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations),
+#endif
+#ifdef CONFIG_TIME_NS
+ REG("timens_offsets", S_IRUGO|S_IWUSR, proc_timens_offsets_operations),
#endif
REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
@@ -3024,10 +3266,13 @@
#ifdef CONFIG_CGROUPS
ONE("cgroup", S_IRUGO, proc_cgroup_show),
#endif
+#ifdef CONFIG_PROC_CPU_RESCTRL
+ ONE("cpu_resctrl_groups", S_IRUGO, proc_resctrl_show),
+#endif
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
+#ifdef CONFIG_AUDIT
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
REG("sessionid", S_IRUGO, proc_sessionid_operations),
#endif
@@ -3057,6 +3302,12 @@
#ifdef CONFIG_CPU_FREQ_TIMES
ONE("time_in_state", 0444, proc_time_in_state_show),
#endif
+#ifdef CONFIG_STACKLEAK_METRICS
+ ONE("stack_depth", S_IRUGO, proc_stack_depth),
+#endif
+#ifdef CONFIG_PROC_PID_ARCH_STATUS
+ ONE("arch_status", S_IRUGO, proc_pid_arch_status),
+#endif
};
static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
@@ -3073,8 +3324,7 @@
struct pid *tgid_pidfd_to_pid(const struct file *file)
{
- if (!d_is_dir(file->f_path.dentry) ||
- (file->f_op != &proc_tgid_base_operations))
+ if (file->f_op != &proc_tgid_base_operations)
return ERR_PTR(-EBADF);
return proc_pid(file_inode(file));
@@ -3083,7 +3333,8 @@
static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
return proc_pident_lookup(dir, dentry,
- tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff));
+ tgid_base_stuff,
+ tgid_base_stuff + ARRAY_SIZE(tgid_base_stuff));
}
static const struct inode_operations proc_tgid_base_inode_operations = {
@@ -3093,90 +3344,28 @@
.permission = proc_pid_permission,
};
-static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
-{
- struct dentry *dentry, *leader, *dir;
- char buf[10 + 1];
- struct qstr name;
-
- name.name = buf;
- name.len = snprintf(buf, sizeof(buf), "%u", pid);
- /* no ->d_hash() rejects on procfs */
- dentry = d_hash_and_lookup(mnt->mnt_root, &name);
- if (dentry) {
- d_invalidate(dentry);
- dput(dentry);
- }
-
- if (pid == tgid)
- return;
-
- name.name = buf;
- name.len = snprintf(buf, sizeof(buf), "%u", tgid);
- leader = d_hash_and_lookup(mnt->mnt_root, &name);
- if (!leader)
- goto out;
-
- name.name = "task";
- name.len = strlen(name.name);
- dir = d_hash_and_lookup(leader, &name);
- if (!dir)
- goto out_put_leader;
-
- name.name = buf;
- name.len = snprintf(buf, sizeof(buf), "%u", pid);
- dentry = d_hash_and_lookup(dir, &name);
- if (dentry) {
- d_invalidate(dentry);
- dput(dentry);
- }
-
- dput(dir);
-out_put_leader:
- dput(leader);
-out:
- return;
-}
-
/**
- * proc_flush_task - Remove dcache entries for @task from the /proc dcache.
- * @task: task that should be flushed.
+ * proc_flush_pid - Remove dcache entries for @pid from the /proc dcache.
+ * @pid: pid that should be flushed.
*
- * When flushing dentries from proc, one needs to flush them from global
- * proc (proc_mnt) and from all the namespaces' procs this task was seen
- * in. This call is supposed to do all of this job.
- *
- * Looks in the dcache for
- * /proc/@pid
- * /proc/@tgid/task/@pid
- * if either directory is present flushes it and all of it'ts children
- * from the dcache.
+ * This function walks a list of inodes (that belong to any proc
+ * filesystem) that are attached to the pid and flushes them from
+ * the dentry cache.
*
* It is safe and reasonable to cache /proc entries for a task until
* that task exits. After that they just clog up the dcache with
* useless entries, possibly causing useful dcache entries to be
- * flushed instead. This routine is proved to flush those useless
- * dcache entries at process exit time.
+ * flushed instead. This routine is provided to flush those useless
+ * dcache entries when a process is reaped.
*
* NOTE: This routine is just an optimization so it does not guarantee
- * that no dcache entries will exist at process exit time it
- * just makes it very unlikely that any will persist.
+ * that no dcache entries will exist after a process is reaped
+ * it just makes it very unlikely that any will persist.
*/
-void proc_flush_task(struct task_struct *task)
+void proc_flush_pid(struct pid *pid)
{
- int i;
- struct pid *pid, *tgid;
- struct upid *upid;
-
- pid = task_pid(task);
- tgid = task_tgid(task);
-
- for (i = 0; i <= pid->level; i++) {
- upid = &pid->numbers[i];
- proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr,
- tgid->numbers[i].nr);
- }
+ proc_invalidate_siblings_dcache(&pid->inodes, &pid->lock);
}
static struct dentry *proc_pid_instantiate(struct dentry * dentry,
@@ -3184,7 +3373,8 @@
{
struct inode *inode;
- inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO);
+ inode = proc_pid_make_base_inode(dentry->d_sb, task,
+ S_IFDIR | S_IRUGO | S_IXUGO);
if (!inode)
return ERR_PTR(-ENOENT);
@@ -3199,10 +3389,11 @@
return d_splice_alias(inode, dentry);
}
-struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
+struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags)
{
struct task_struct *task;
unsigned tgid;
+ struct proc_fs_info *fs_info;
struct pid_namespace *ns;
struct dentry *result = ERR_PTR(-ENOENT);
@@ -3210,7 +3401,8 @@
if (tgid == ~0U)
goto out;
- ns = dentry->d_sb->s_fs_info;
+ fs_info = proc_sb_info(dentry->d_sb);
+ ns = fs_info->pid_ns;
rcu_read_lock();
task = find_task_by_pid_ns(tgid, ns);
if (task)
@@ -3219,7 +3411,14 @@
if (!task)
goto out;
+ /* Limit procfs to only ptraceable tasks */
+ if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) {
+ if (!has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS))
+ goto out_put_task;
+ }
+
result = proc_pid_instantiate(dentry, task, NULL);
+out_put_task:
put_task_struct(task);
out:
return result;
@@ -3245,20 +3444,8 @@
pid = find_ge_pid(iter.tgid, ns);
if (pid) {
iter.tgid = pid_nr_ns(pid, ns);
- iter.task = pid_task(pid, PIDTYPE_PID);
- /* What we to know is if the pid we have find is the
- * pid of a thread_group_leader. Testing for task
- * being a thread_group_leader is the obvious thing
- * todo but there is a window when it fails, due to
- * the pid transfer logic in de_thread.
- *
- * So we perform the straight forward test of seeing
- * if the pid we have found is the pid of a thread
- * group leader, and don't worry if the task we have
- * found doesn't happen to be a thread group leader.
- * As we don't care in the case of readdir.
- */
- if (!iter.task || !has_group_leader_pid(iter.task)) {
+ iter.task = pid_task(pid, PIDTYPE_TGID);
+ if (!iter.task) {
iter.tgid += 1;
goto retry;
}
@@ -3274,20 +3461,21 @@
int proc_pid_readdir(struct file *file, struct dir_context *ctx)
{
struct tgid_iter iter;
- struct pid_namespace *ns = proc_pid_ns(file_inode(file));
+ struct proc_fs_info *fs_info = proc_sb_info(file_inode(file)->i_sb);
+ struct pid_namespace *ns = proc_pid_ns(file_inode(file)->i_sb);
loff_t pos = ctx->pos;
if (pos >= PID_MAX_LIMIT + TGID_OFFSET)
return 0;
if (pos == TGID_OFFSET - 2) {
- struct inode *inode = d_inode(ns->proc_self);
+ struct inode *inode = d_inode(fs_info->proc_self);
if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK))
return 0;
ctx->pos = pos = pos + 1;
}
if (pos == TGID_OFFSET - 1) {
- struct inode *inode = d_inode(ns->proc_thread_self);
+ struct inode *inode = d_inode(fs_info->proc_thread_self);
if (!dir_emit(ctx, "thread-self", 11, inode->i_ino, DT_LNK))
return 0;
ctx->pos = pos = pos + 1;
@@ -3301,7 +3489,7 @@
unsigned int len;
cond_resched();
- if (!has_pid_permissions(ns, iter.task, HIDEPID_INVISIBLE))
+ if (!has_pid_permissions(fs_info, iter.task, HIDEPID_INVISIBLE))
continue;
len = snprintf(name, sizeof(name), "%u", iter.tgid);
@@ -3351,7 +3539,8 @@
}
static const struct inode_operations proc_tid_comm_inode_operations = {
- .permission = proc_tid_comm_permission,
+ .setattr = proc_setattr,
+ .permission = proc_tid_comm_permission,
};
/*
@@ -3359,7 +3548,7 @@
*/
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("fdinfo", S_IRUGO|S_IXUGO, 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),
@@ -3421,10 +3610,13 @@
#ifdef CONFIG_CGROUPS
ONE("cgroup", S_IRUGO, proc_cgroup_show),
#endif
+#ifdef CONFIG_PROC_CPU_RESCTRL
+ ONE("cpu_resctrl_groups", S_IRUGO, proc_resctrl_show),
+#endif
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
+#ifdef CONFIG_AUDIT
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
REG("sessionid", S_IRUGO, proc_sessionid_operations),
#endif
@@ -3444,6 +3636,9 @@
#ifdef CONFIG_LIVEPATCH
ONE("patch_state", S_IRUSR, proc_pid_patch_state),
#endif
+#ifdef CONFIG_PROC_PID_ARCH_STATUS
+ ONE("arch_status", S_IRUGO, proc_pid_arch_status),
+#endif
#ifdef CONFIG_CPU_FREQ_TIMES
ONE("time_in_state", 0444, proc_time_in_state_show),
#endif
@@ -3458,7 +3653,8 @@
static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
return proc_pident_lookup(dir, dentry,
- tid_base_stuff, ARRAY_SIZE(tid_base_stuff));
+ tid_base_stuff,
+ tid_base_stuff + ARRAY_SIZE(tid_base_stuff));
}
static const struct file_operations proc_tid_base_operations = {
@@ -3477,7 +3673,8 @@
struct task_struct *task, const void *ptr)
{
struct inode *inode;
- inode = proc_pid_make_inode(dentry->d_sb, task, S_IFDIR | S_IRUGO | S_IXUGO);
+ inode = proc_pid_make_base_inode(dentry->d_sb, task,
+ S_IFDIR | S_IRUGO | S_IXUGO);
if (!inode)
return ERR_PTR(-ENOENT);
@@ -3497,6 +3694,7 @@
struct task_struct *task;
struct task_struct *leader = get_proc_task(dir);
unsigned tid;
+ struct proc_fs_info *fs_info;
struct pid_namespace *ns;
struct dentry *result = ERR_PTR(-ENOENT);
@@ -3507,7 +3705,8 @@
if (tid == ~0U)
goto out;
- ns = dentry->d_sb->s_fs_info;
+ fs_info = proc_sb_info(dentry->d_sb);
+ ns = fs_info->pid_ns;
rcu_read_lock();
task = find_task_by_pid_ns(tid, ns);
if (task)
@@ -3621,7 +3820,7 @@
/* f_version caches the tgid value that the last readdir call couldn't
* return. lseek aka telldir automagically resets f_version to 0.
*/
- ns = proc_pid_ns(inode);
+ ns = proc_pid_ns(inode->i_sb);
tid = (int)file->f_version;
file->f_version = 0;
for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns);
--
Gitblit v1.6.2