summaryrefslogtreecommitdiffstats
path: root/kernel/fs/proc
diff options
context:
space:
mode:
authorJosé Pekkarinen <jose.pekkarinen@nokia.com>2016-04-11 10:41:07 +0300
committerJosé Pekkarinen <jose.pekkarinen@nokia.com>2016-04-13 08:17:18 +0300
commite09b41010ba33a20a87472ee821fa407a5b8da36 (patch)
treed10dc367189862e7ca5c592f033dc3726e1df4e3 /kernel/fs/proc
parentf93b97fd65072de626c074dbe099a1fff05ce060 (diff)
These changes are the raw update to linux-4.4.6-rt14. Kernel sources
are taken from kernel.org, and rt patch from the rt wiki download page. During the rebasing, the following patch collided: Force tick interrupt and get rid of softirq magic(I70131fb85). Collisions have been removed because its logic was found on the source already. Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769 Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>
Diffstat (limited to 'kernel/fs/proc')
-rw-r--r--kernel/fs/proc/Kconfig10
-rw-r--r--kernel/fs/proc/array.c45
-rw-r--r--kernel/fs/proc/base.c379
-rw-r--r--kernel/fs/proc/fd.c14
-rw-r--r--kernel/fs/proc/generic.c44
-rw-r--r--kernel/fs/proc/inode.c9
-rw-r--r--kernel/fs/proc/kcore.c4
-rw-r--r--kernel/fs/proc/meminfo.c7
-rw-r--r--kernel/fs/proc/namespaces.c8
-rw-r--r--kernel/fs/proc/nommu.c2
-rw-r--r--kernel/fs/proc/page.c65
-rw-r--r--kernel/fs/proc/proc_sysctl.c2
-rw-r--r--kernel/fs/proc/root.c2
-rw-r--r--kernel/fs/proc/self.c24
-rw-r--r--kernel/fs/proc/task_mmu.c367
-rw-r--r--kernel/fs/proc/task_nommu.c2
-rw-r--r--kernel/fs/proc/thread_self.c22
17 files changed, 657 insertions, 349 deletions
diff --git a/kernel/fs/proc/Kconfig b/kernel/fs/proc/Kconfig
index 2183fcf41..1ade1206b 100644
--- a/kernel/fs/proc/Kconfig
+++ b/kernel/fs/proc/Kconfig
@@ -71,3 +71,13 @@ config PROC_PAGE_MONITOR
/proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap,
/proc/kpagecount, and /proc/kpageflags. Disabling these
interfaces will reduce the size of the kernel by approximately 4kb.
+
+config PROC_CHILDREN
+ bool "Include /proc/<pid>/task/<tid>/children file"
+ default n
+ help
+ Provides a fast way to retrieve first level children pids of a task. See
+ <file:Documentation/filesystems/proc.txt> for more information.
+
+ Say Y if you are running any user-space software which takes benefit from
+ this interface. For example, rkt is such a piece of software.
diff --git a/kernel/fs/proc/array.c b/kernel/fs/proc/array.c
index fd02a9ebf..b6c00ce0e 100644
--- a/kernel/fs/proc/array.c
+++ b/kernel/fs/proc/array.c
@@ -91,18 +91,18 @@
static inline void task_name(struct seq_file *m, struct task_struct *p)
{
char *buf;
+ size_t size;
char tcomm[sizeof(p->comm)];
+ int ret;
get_task_comm(tcomm, p);
seq_puts(m, "Name:\t");
- buf = m->buf + m->count;
- /* Ignore error for now */
- buf += string_escape_str(tcomm, buf, m->size - m->count,
- ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+ size = seq_get_buf(m, &buf);
+ ret = string_escape_str(tcomm, buf, size, ESCAPE_SPACE | ESCAPE_SPECIAL, "\n\\");
+ seq_commit(m, ret < size ? ret : -1);
- m->count = buf - m->buf;
seq_putc(m, '\n');
}
@@ -126,6 +126,14 @@ static inline const char *get_task_state(struct task_struct *tsk)
{
unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT;
+ /*
+ * Parked tasks do not run; they sit in __kthread_parkme().
+ * Without this check, we would report them as running, which is
+ * clearly wrong, so we report them as sleeping instead.
+ */
+ if (tsk->state == TASK_PARKED)
+ state = TASK_INTERRUPTIBLE;
+
BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1);
return task_state_array[fls(state)];
@@ -300,7 +308,8 @@ static void render_cap_t(struct seq_file *m, const char *header,
static inline void task_cap(struct seq_file *m, struct task_struct *p)
{
const struct cred *cred;
- kernel_cap_t cap_inheritable, cap_permitted, cap_effective, cap_bset;
+ kernel_cap_t cap_inheritable, cap_permitted, cap_effective,
+ cap_bset, cap_ambient;
rcu_read_lock();
cred = __task_cred(p);
@@ -308,12 +317,14 @@ static inline void task_cap(struct seq_file *m, struct task_struct *p)
cap_permitted = cred->cap_permitted;
cap_effective = cred->cap_effective;
cap_bset = cred->cap_bset;
+ cap_ambient = cred->cap_ambient;
rcu_read_unlock();
render_cap_t(m, "CapInh:\t", &cap_inheritable);
render_cap_t(m, "CapPrm:\t", &cap_permitted);
render_cap_t(m, "CapEff:\t", &cap_effective);
render_cap_t(m, "CapBnd:\t", &cap_bset);
+ render_cap_t(m, "CapAmb:\t", &cap_ambient);
}
static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
@@ -364,7 +375,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task, int whole)
{
- unsigned long vsize, eip, esp, wchan = ~0UL;
+ unsigned long vsize, eip, esp, wchan = 0;
int priority, nice;
int tty_pgrp = -1, tty_nr = 0;
sigset_t sigign, sigcatch;
@@ -384,7 +395,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
state = *get_task_state(task);
vsize = eip = esp = 0;
- permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT);
+ permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT);
mm = get_task_mm(task);
if (mm) {
vsize = task_vsize(mm);
@@ -496,7 +507,19 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
seq_put_decimal_ull(m, ' ', task->blocked.sig[0] & 0x7fffffffUL);
seq_put_decimal_ull(m, ' ', sigign.sig[0] & 0x7fffffffUL);
seq_put_decimal_ull(m, ' ', sigcatch.sig[0] & 0x7fffffffUL);
- seq_put_decimal_ull(m, ' ', wchan);
+
+ /*
+ * We used to output the absolute kernel address, but that's an
+ * information leak - so instead we show a 0/1 flag here, to signal
+ * to user-space whether there's a wchan field in /proc/PID/wchan.
+ *
+ * This works with older implementations of procps as well.
+ */
+ if (wchan)
+ seq_puts(m, " 1");
+ else
+ seq_puts(m, " 0");
+
seq_put_decimal_ull(m, ' ', 0);
seq_put_decimal_ull(m, ' ', 0);
seq_put_decimal_ll(m, ' ', task->exit_signal);
@@ -569,7 +592,7 @@ int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns,
return 0;
}
-#ifdef CONFIG_CHECKPOINT_RESTORE
+#ifdef CONFIG_PROC_CHILDREN
static struct pid *
get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos)
{
@@ -692,4 +715,4 @@ const struct file_operations proc_tid_children_operations = {
.llseek = seq_lseek,
.release = children_seq_release,
};
-#endif /* CONFIG_CHECKPOINT_RESTORE */
+#endif /* CONFIG_PROC_CHILDREN */
diff --git a/kernel/fs/proc/base.c b/kernel/fs/proc/base.c
index 093ca14f5..b7de324be 100644
--- a/kernel/fs/proc/base.c
+++ b/kernel/fs/proc/base.c
@@ -196,22 +196,214 @@ static int proc_root_link(struct dentry *dentry, struct path *path)
return result;
}
-static int proc_pid_cmdline(struct seq_file *m, struct pid_namespace *ns,
- struct pid *pid, struct task_struct *task)
+static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
+ size_t _count, loff_t *pos)
{
+ struct task_struct *tsk;
+ struct mm_struct *mm;
+ char *page;
+ unsigned long count = _count;
+ unsigned long arg_start, arg_end, env_start, env_end;
+ unsigned long len1, len2, len;
+ unsigned long p;
+ char c;
+ ssize_t rv;
+
+ BUG_ON(*pos < 0);
+
+ tsk = get_proc_task(file_inode(file));
+ if (!tsk)
+ return -ESRCH;
+ mm = get_task_mm(tsk);
+ put_task_struct(tsk);
+ if (!mm)
+ return 0;
+ /* Check if process spawned far enough to have cmdline. */
+ if (!mm->env_end) {
+ rv = 0;
+ goto out_mmput;
+ }
+
+ page = (char *)__get_free_page(GFP_TEMPORARY);
+ if (!page) {
+ rv = -ENOMEM;
+ goto out_mmput;
+ }
+
+ down_read(&mm->mmap_sem);
+ arg_start = mm->arg_start;
+ arg_end = mm->arg_end;
+ env_start = mm->env_start;
+ env_end = mm->env_end;
+ up_read(&mm->mmap_sem);
+
+ BUG_ON(arg_start > arg_end);
+ BUG_ON(env_start > env_end);
+
+ len1 = arg_end - arg_start;
+ len2 = env_end - env_start;
+
+ /* Empty ARGV. */
+ if (len1 == 0) {
+ rv = 0;
+ goto out_free_page;
+ }
/*
- * Rely on struct seq_operations::show() being called once
- * per internal buffer allocation. See single_open(), traverse().
+ * Inherently racy -- command line shares address space
+ * with code and data.
*/
- BUG_ON(m->size < PAGE_SIZE);
- m->count += get_cmdline(task, m->buf, PAGE_SIZE);
- return 0;
+ rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0);
+ if (rv <= 0)
+ goto out_free_page;
+
+ rv = 0;
+
+ if (c == '\0') {
+ /* Command line (set of strings) occupies whole ARGV. */
+ if (len1 <= *pos)
+ goto out_free_page;
+
+ p = arg_start + *pos;
+ len = len1 - *pos;
+ while (count > 0 && len > 0) {
+ unsigned int _count;
+ int nr_read;
+
+ _count = min3(count, len, PAGE_SIZE);
+ nr_read = access_remote_vm(mm, p, page, _count, 0);
+ if (nr_read < 0)
+ rv = nr_read;
+ if (nr_read <= 0)
+ goto out_free_page;
+
+ if (copy_to_user(buf, page, nr_read)) {
+ rv = -EFAULT;
+ goto out_free_page;
+ }
+
+ p += nr_read;
+ len -= nr_read;
+ buf += nr_read;
+ count -= nr_read;
+ rv += nr_read;
+ }
+ } else {
+ /*
+ * Command line (1 string) occupies ARGV and maybe
+ * extends into ENVP.
+ */
+ if (len1 + len2 <= *pos)
+ goto skip_argv_envp;
+ if (len1 <= *pos)
+ goto skip_argv;
+
+ p = arg_start + *pos;
+ len = len1 - *pos;
+ while (count > 0 && len > 0) {
+ unsigned int _count, l;
+ int nr_read;
+ bool final;
+
+ _count = min3(count, len, PAGE_SIZE);
+ nr_read = access_remote_vm(mm, p, page, _count, 0);
+ if (nr_read < 0)
+ rv = nr_read;
+ if (nr_read <= 0)
+ goto out_free_page;
+
+ /*
+ * Command line can be shorter than whole ARGV
+ * even if last "marker" byte says it is not.
+ */
+ final = false;
+ l = strnlen(page, nr_read);
+ if (l < nr_read) {
+ nr_read = l;
+ final = true;
+ }
+
+ if (copy_to_user(buf, page, nr_read)) {
+ rv = -EFAULT;
+ goto out_free_page;
+ }
+
+ p += nr_read;
+ len -= nr_read;
+ buf += nr_read;
+ count -= nr_read;
+ rv += nr_read;
+
+ if (final)
+ goto out_free_page;
+ }
+skip_argv:
+ /*
+ * Command line (1 string) occupies ARGV and
+ * extends into ENVP.
+ */
+ if (len1 <= *pos) {
+ p = env_start + *pos - len1;
+ len = len1 + len2 - *pos;
+ } else {
+ p = env_start;
+ len = len2;
+ }
+ while (count > 0 && len > 0) {
+ unsigned int _count, l;
+ int nr_read;
+ bool final;
+
+ _count = min3(count, len, PAGE_SIZE);
+ nr_read = access_remote_vm(mm, p, page, _count, 0);
+ if (nr_read < 0)
+ rv = nr_read;
+ if (nr_read <= 0)
+ goto out_free_page;
+
+ /* Find EOS. */
+ final = false;
+ l = strnlen(page, nr_read);
+ if (l < nr_read) {
+ nr_read = l;
+ final = true;
+ }
+
+ if (copy_to_user(buf, page, nr_read)) {
+ rv = -EFAULT;
+ goto out_free_page;
+ }
+
+ p += nr_read;
+ len -= nr_read;
+ buf += nr_read;
+ count -= nr_read;
+ rv += nr_read;
+
+ if (final)
+ goto out_free_page;
+ }
+skip_argv_envp:
+ ;
+ }
+
+out_free_page:
+ free_page((unsigned long)page);
+out_mmput:
+ mmput(mm);
+ if (rv > 0)
+ *pos += rv;
+ return rv;
}
+static const struct file_operations proc_pid_cmdline_ops = {
+ .read = proc_pid_cmdline_read,
+ .llseek = generic_file_llseek,
+};
+
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);
+ struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
if (mm && !IS_ERR(mm)) {
unsigned int nwords = 0;
do {
@@ -238,13 +430,11 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
wchan = get_wchan(task);
- if (lookup_symbol_name(wchan, symname) < 0) {
- if (!ptrace_may_access(task, PTRACE_MODE_READ))
- return 0;
- seq_printf(m, "%lu", wchan);
- } else {
+ if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)
+ && !lookup_symbol_name(wchan, symname))
seq_printf(m, "%s", symname);
- }
+ else
+ seq_putc(m, '0');
return 0;
}
@@ -255,7 +445,7 @@ static int lock_trace(struct task_struct *task)
int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
if (err)
return err;
- if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
+ if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
mutex_unlock(&task->signal->cred_guard_mutex);
return -EPERM;
}
@@ -304,14 +494,17 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
}
#endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
/*
* Provides /proc/PID/schedstat
*/
static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
- seq_printf(m, "%llu %llu %lu\n",
+ if (unlikely(!sched_info_on()))
+ seq_printf(m, "0 0 0\n");
+ else
+ 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);
@@ -505,7 +698,7 @@ static int proc_fd_access_allowed(struct inode *inode)
*/
task = get_proc_task(inode);
if (task) {
- allowed = ptrace_may_access(task, PTRACE_MODE_READ);
+ allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
put_task_struct(task);
}
return allowed;
@@ -540,7 +733,7 @@ static bool has_pid_permissions(struct pid_namespace *pid,
return true;
if (in_group_p(pid->pid_gid))
return true;
- return ptrace_may_access(task, PTRACE_MODE_READ);
+ return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
}
@@ -617,7 +810,7 @@ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
struct mm_struct *mm = ERR_PTR(-ESRCH);
if (task) {
- mm = mm_access(task, mode);
+ mm = mm_access(task, mode | PTRACE_MODE_FSCREDS);
put_task_struct(task);
if (!IS_ERR_OR_NULL(mm)) {
@@ -840,6 +1033,16 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
+/*
+ * /proc/pid/oom_adj exists solely for backwards compatibility with previous
+ * kernels. The effective policy is defined by oom_score_adj, which has a
+ * different scale: oom_adj grew exponentially and oom_score_adj grows linearly.
+ * Values written to oom_adj are simply mapped linearly to oom_score_adj.
+ * Processes that become oom disabled via oom_adj will still be oom disabled
+ * with this implementation.
+ *
+ * oom_adj cannot be removed since existing userspace binaries use it.
+ */
static ssize_t oom_adj_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
@@ -1035,10 +1238,9 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
size_t count, loff_t *ppos)
{
struct inode * inode = file_inode(file);
- char *page, *tmp;
- ssize_t length;
uid_t loginuid;
kuid_t kloginuid;
+ int rv;
rcu_read_lock();
if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) {
@@ -1047,46 +1249,28 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
}
rcu_read_unlock();
- if (count >= PAGE_SIZE)
- count = PAGE_SIZE - 1;
-
if (*ppos != 0) {
/* No partial writes. */
return -EINVAL;
}
- page = (char*)__get_free_page(GFP_TEMPORARY);
- if (!page)
- return -ENOMEM;
- length = -EFAULT;
- if (copy_from_user(page, buf, count))
- goto out_free_page;
- page[count] = '\0';
- loginuid = simple_strtoul(page, &tmp, 10);
- if (tmp == page) {
- length = -EINVAL;
- goto out_free_page;
-
- }
+ rv = kstrtou32_from_user(buf, count, 10, &loginuid);
+ if (rv < 0)
+ return rv;
/* is userspace tring to explicitly UNSET the loginuid? */
if (loginuid == AUDIT_UID_UNSET) {
kloginuid = INVALID_UID;
} else {
kloginuid = make_kuid(file->f_cred->user_ns, loginuid);
- if (!uid_valid(kloginuid)) {
- length = -EINVAL;
- goto out_free_page;
- }
+ if (!uid_valid(kloginuid))
+ return -EINVAL;
}
- length = audit_set_loginuid(kloginuid);
- if (likely(length == 0))
- length = count;
-
-out_free_page:
- free_page((unsigned long) page);
- return length;
+ rv = audit_set_loginuid(kloginuid);
+ if (rv < 0)
+ return rv;
+ return count;
}
static const struct file_operations proc_loginuid_operations = {
@@ -1140,8 +1324,9 @@ static ssize_t proc_fault_inject_write(struct file * file,
const char __user * buf, size_t count, loff_t *ppos)
{
struct task_struct *task;
- char buffer[PROC_NUMBUF], *end;
+ char buffer[PROC_NUMBUF];
int make_it_fail;
+ int rv;
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
@@ -1150,9 +1335,9 @@ static ssize_t proc_fault_inject_write(struct file * file,
count = sizeof(buffer) - 1;
if (copy_from_user(buffer, buf, count))
return -EFAULT;
- make_it_fail = simple_strtol(strstrip(buffer), &end, 0);
- if (*end)
- return -EINVAL;
+ rv = kstrtoint(strstrip(buffer), 0, &make_it_fail);
+ if (rv < 0)
+ return rv;
if (make_it_fail < 0 || make_it_fail > 1)
return -EINVAL;
@@ -1380,7 +1565,7 @@ static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
return -ENOENT;
}
-static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_pid_follow_link(struct dentry *dentry, void **cookie)
{
struct inode *inode = d_inode(dentry);
struct path path;
@@ -1394,7 +1579,7 @@ static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
if (error)
goto out;
- nd_jump_link(nd, &path);
+ nd_jump_link(&path);
return NULL;
out:
return ERR_PTR(error);
@@ -1641,8 +1826,6 @@ end_instantiate:
return dir_emit(ctx, name, len, 1, DT_UNKNOWN);
}
-#ifdef CONFIG_CHECKPOINT_RESTORE
-
/*
* dname_to_vma_addr - maps a dentry name into two unsigned longs
* which represent vma start and end addresses.
@@ -1669,17 +1852,12 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
if (flags & LOOKUP_RCU)
return -ECHILD;
- if (!capable(CAP_SYS_ADMIN)) {
- status = -EPERM;
- goto out_notask;
- }
-
inode = d_inode(dentry);
task = get_proc_task(inode);
if (!task)
goto out_notask;
- mm = mm_access(task, PTRACE_MODE_READ);
+ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
if (IS_ERR_OR_NULL(mm))
goto out;
@@ -1762,6 +1940,29 @@ struct map_files_info {
unsigned char name[4*sizeof(long)+2]; /* max: %lx-%lx\0 */
};
+/*
+ * 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.
+ */
+static const char *
+proc_map_files_follow_link(struct dentry *dentry, void **cookie)
+{
+ if (!capable(CAP_SYS_ADMIN))
+ return ERR_PTR(-EPERM);
+
+ return proc_pid_follow_link(dentry, NULL);
+}
+
+/*
+ * Identical to proc_pid_link_inode_operations except for follow_link()
+ */
+static const struct inode_operations proc_map_files_link_inode_operations = {
+ .readlink = proc_pid_readlink,
+ .follow_link = proc_map_files_follow_link,
+ .setattr = proc_setattr,
+};
+
static int
proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
struct task_struct *task, const void *ptr)
@@ -1777,7 +1978,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
ei = PROC_I(inode);
ei->op.proc_get_link = proc_map_files_get_link;
- inode->i_op = &proc_pid_link_inode_operations;
+ inode->i_op = &proc_map_files_link_inode_operations;
inode->i_size = 64;
inode->i_mode = S_IFLNK;
@@ -1801,17 +2002,13 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
int result;
struct mm_struct *mm;
- result = -EPERM;
- if (!capable(CAP_SYS_ADMIN))
- goto out;
-
result = -ENOENT;
task = get_proc_task(dir);
if (!task)
goto out;
result = -EACCES;
- if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
goto out_put_task;
result = -ENOENT;
@@ -1858,17 +2055,13 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
struct map_files_info *p;
int ret;
- ret = -EPERM;
- if (!capable(CAP_SYS_ADMIN))
- goto out;
-
ret = -ENOENT;
task = get_proc_task(file_inode(file));
if (!task)
goto out;
ret = -EACCES;
- if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
goto out_put_task;
ret = 0;
@@ -2050,7 +2243,6 @@ static const struct file_operations proc_timers_operations = {
.llseek = seq_lseek,
.release = seq_release_private,
};
-#endif /* CONFIG_CHECKPOINT_RESTORE */
static int proc_pident_instantiate(struct inode *dir,
struct dentry *dentry, struct task_struct *task, const void *ptr)
@@ -2286,35 +2478,24 @@ static ssize_t proc_coredump_filter_write(struct file *file,
{
struct task_struct *task;
struct mm_struct *mm;
- char buffer[PROC_NUMBUF], *end;
unsigned int val;
int ret;
int i;
unsigned long mask;
- ret = -EFAULT;
- memset(buffer, 0, sizeof(buffer));
- if (count > sizeof(buffer) - 1)
- count = sizeof(buffer) - 1;
- if (copy_from_user(buffer, buf, count))
- goto out_no_task;
-
- ret = -EINVAL;
- val = (unsigned int)simple_strtoul(buffer, &end, 0);
- if (*end == '\n')
- end++;
- if (end - buffer == 0)
- goto out_no_task;
+ ret = kstrtouint_from_user(buf, count, 0, &val);
+ if (ret < 0)
+ return ret;
ret = -ESRCH;
task = get_proc_task(file_inode(file));
if (!task)
goto out_no_task;
- ret = end - buffer;
mm = get_task_mm(task);
if (!mm)
goto out_no_mm;
+ ret = 0;
for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) {
if (val & mask)
@@ -2327,7 +2508,9 @@ static ssize_t proc_coredump_filter_write(struct file *file,
out_no_mm:
put_task_struct(task);
out_no_task:
- return ret;
+ if (ret < 0)
+ return ret;
+ return count;
}
static const struct file_operations proc_coredump_filter_operations = {
@@ -2348,7 +2531,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
if (result)
return result;
- if (!ptrace_may_access(task, PTRACE_MODE_READ)) {
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
result = -EACCES;
goto out_unlock;
}
@@ -2549,9 +2732,7 @@ static const struct inode_operations proc_task_inode_operations;
static const struct pid_entry tgid_base_stuff[] = {
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),
-#ifdef CONFIG_CHECKPOINT_RESTORE
DIR("map_files", S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations),
-#endif
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
@@ -2572,7 +2753,7 @@ static const struct pid_entry tgid_base_stuff[] = {
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
ONE("syscall", S_IRUSR, proc_pid_syscall),
#endif
- ONE("cmdline", S_IRUGO, proc_pid_cmdline),
+ REG("cmdline", S_IRUGO, proc_pid_cmdline_ops),
ONE("stat", S_IRUGO, proc_tgid_stat),
ONE("statm", S_IRUGO, proc_pid_statm),
REG("maps", S_IRUGO, proc_pid_maps_operations),
@@ -2600,7 +2781,7 @@ static const struct pid_entry tgid_base_stuff[] = {
#ifdef CONFIG_STACKTRACE
ONE("stack", S_IRUSR, proc_pid_stack),
#endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
ONE("schedstat", S_IRUGO, proc_pid_schedstat),
#endif
#ifdef CONFIG_LATENCYTOP
@@ -2918,11 +3099,11 @@ static const struct pid_entry tid_base_stuff[] = {
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
ONE("syscall", S_IRUSR, proc_pid_syscall),
#endif
- ONE("cmdline", S_IRUGO, proc_pid_cmdline),
+ REG("cmdline", S_IRUGO, proc_pid_cmdline_ops),
ONE("stat", S_IRUGO, proc_tid_stat),
ONE("statm", S_IRUGO, proc_pid_statm),
REG("maps", S_IRUGO, proc_tid_maps_operations),
-#ifdef CONFIG_CHECKPOINT_RESTORE
+#ifdef CONFIG_PROC_CHILDREN
REG("children", S_IRUGO, proc_tid_children_operations),
#endif
#ifdef CONFIG_NUMA
@@ -2948,7 +3129,7 @@ static const struct pid_entry tid_base_stuff[] = {
#ifdef CONFIG_STACKTRACE
ONE("stack", S_IRUSR, proc_pid_stack),
#endif
-#ifdef CONFIG_SCHEDSTATS
+#ifdef CONFIG_SCHED_INFO
ONE("schedstat", S_IRUGO, proc_pid_schedstat),
#endif
#ifdef CONFIG_LATENCYTOP
diff --git a/kernel/fs/proc/fd.c b/kernel/fs/proc/fd.c
index 6e5fcd007..3c2a915c6 100644
--- a/kernel/fs/proc/fd.c
+++ b/kernel/fs/proc/fd.c
@@ -291,11 +291,19 @@ static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
*/
int proc_fd_permission(struct inode *inode, int mask)
{
- int rv = generic_permission(inode, mask);
+ struct task_struct *p;
+ int rv;
+
+ rv = generic_permission(inode, mask);
if (rv == 0)
- return 0;
- if (task_tgid(current) == proc_pid(inode))
+ return rv;
+
+ rcu_read_lock();
+ p = pid_task(proc_pid(inode), PIDTYPE_PID);
+ if (p && same_thread_group(p, current))
rv = 0;
+ rcu_read_unlock();
+
return rv;
}
diff --git a/kernel/fs/proc/generic.c b/kernel/fs/proc/generic.c
index e5dee5c31..ff3ffc76a 100644
--- a/kernel/fs/proc/generic.c
+++ b/kernel/fs/proc/generic.c
@@ -26,7 +26,7 @@
#include "internal.h"
-static DEFINE_SPINLOCK(proc_subdir_lock);
+static DEFINE_RWLOCK(proc_subdir_lock);
static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
{
@@ -172,9 +172,9 @@ static int xlate_proc_name(const char *name, struct proc_dir_entry **ret,
{
int rv;
- spin_lock(&proc_subdir_lock);
+ read_lock(&proc_subdir_lock);
rv = __xlate_proc_name(name, ret, residual);
- spin_unlock(&proc_subdir_lock);
+ read_unlock(&proc_subdir_lock);
return rv;
}
@@ -231,11 +231,11 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
{
struct inode *inode;
- spin_lock(&proc_subdir_lock);
+ read_lock(&proc_subdir_lock);
de = pde_subdir_find(de, dentry->d_name.name, dentry->d_name.len);
if (de) {
pde_get(de);
- spin_unlock(&proc_subdir_lock);
+ read_unlock(&proc_subdir_lock);
inode = proc_get_inode(dir->i_sb, de);
if (!inode)
return ERR_PTR(-ENOMEM);
@@ -243,7 +243,7 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
d_add(dentry, inode);
return NULL;
}
- spin_unlock(&proc_subdir_lock);
+ read_unlock(&proc_subdir_lock);
return ERR_PTR(-ENOENT);
}
@@ -270,12 +270,12 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
if (!dir_emit_dots(file, ctx))
return 0;
- spin_lock(&proc_subdir_lock);
+ read_lock(&proc_subdir_lock);
de = pde_subdir_first(de);
i = ctx->pos - 2;
for (;;) {
if (!de) {
- spin_unlock(&proc_subdir_lock);
+ read_unlock(&proc_subdir_lock);
return 0;
}
if (!i)
@@ -287,19 +287,19 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
do {
struct proc_dir_entry *next;
pde_get(de);
- spin_unlock(&proc_subdir_lock);
+ read_unlock(&proc_subdir_lock);
if (!dir_emit(ctx, de->name, de->namelen,
de->low_ino, de->mode >> 12)) {
pde_put(de);
return 0;
}
- spin_lock(&proc_subdir_lock);
+ read_lock(&proc_subdir_lock);
ctx->pos++;
next = pde_subdir_next(de);
pde_put(de);
de = next;
} while (de);
- spin_unlock(&proc_subdir_lock);
+ read_unlock(&proc_subdir_lock);
return 1;
}
@@ -338,16 +338,16 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
if (ret)
return ret;
- spin_lock(&proc_subdir_lock);
+ write_lock(&proc_subdir_lock);
dp->parent = dir;
if (pde_subdir_insert(dir, dp) == false) {
WARN(1, "proc_dir_entry '%s/%s' already registered\n",
dir->name, dp->name);
- spin_unlock(&proc_subdir_lock);
+ write_unlock(&proc_subdir_lock);
proc_free_inum(dp->low_ino);
return -EEXIST;
}
- spin_unlock(&proc_subdir_lock);
+ write_unlock(&proc_subdir_lock);
return 0;
}
@@ -549,9 +549,9 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
const char *fn = name;
unsigned int len;
- spin_lock(&proc_subdir_lock);
+ write_lock(&proc_subdir_lock);
if (__xlate_proc_name(name, &parent, &fn) != 0) {
- spin_unlock(&proc_subdir_lock);
+ write_unlock(&proc_subdir_lock);
return;
}
len = strlen(fn);
@@ -559,7 +559,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
de = pde_subdir_find(parent, fn, len);
if (de)
rb_erase(&de->subdir_node, &parent->subdir);
- spin_unlock(&proc_subdir_lock);
+ write_unlock(&proc_subdir_lock);
if (!de) {
WARN(1, "name '%s'\n", name);
return;
@@ -583,16 +583,16 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
const char *fn = name;
unsigned int len;
- spin_lock(&proc_subdir_lock);
+ write_lock(&proc_subdir_lock);
if (__xlate_proc_name(name, &parent, &fn) != 0) {
- spin_unlock(&proc_subdir_lock);
+ write_unlock(&proc_subdir_lock);
return -ENOENT;
}
len = strlen(fn);
root = pde_subdir_find(parent, fn, len);
if (!root) {
- spin_unlock(&proc_subdir_lock);
+ write_unlock(&proc_subdir_lock);
return -ENOENT;
}
rb_erase(&root->subdir_node, &parent->subdir);
@@ -605,7 +605,7 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
de = next;
continue;
}
- spin_unlock(&proc_subdir_lock);
+ write_unlock(&proc_subdir_lock);
proc_entry_rundown(de);
next = de->parent;
@@ -616,7 +616,7 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
break;
pde_put(de);
- spin_lock(&proc_subdir_lock);
+ write_lock(&proc_subdir_lock);
de = next;
}
pde_put(root);
diff --git a/kernel/fs/proc/inode.c b/kernel/fs/proc/inode.c
index e3eb55246..bd95b9fde 100644
--- a/kernel/fs/proc/inode.c
+++ b/kernel/fs/proc/inode.c
@@ -23,7 +23,6 @@
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/magic.h>
-#include <linux/namei.h>
#include <asm/uaccess.h>
@@ -394,16 +393,16 @@ static const struct file_operations proc_reg_file_ops_no_compat = {
};
#endif
-static void *proc_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_follow_link(struct dentry *dentry, void **cookie)
{
struct proc_dir_entry *pde = PDE(d_inode(dentry));
if (unlikely(!use_pde(pde)))
return ERR_PTR(-EINVAL);
- nd_set_link(nd, pde->data);
- return pde;
+ *cookie = pde;
+ return pde->data;
}
-static void proc_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
+static void proc_put_link(struct inode *unused, void *p)
{
unuse_pde(p);
}
diff --git a/kernel/fs/proc/kcore.c b/kernel/fs/proc/kcore.c
index 91a4e6426..92e6726f6 100644
--- a/kernel/fs/proc/kcore.c
+++ b/kernel/fs/proc/kcore.c
@@ -92,7 +92,7 @@ static size_t get_kcore_size(int *nphdr, size_t *elf_buflen)
roundup(sizeof(CORE_STR), 4)) +
roundup(sizeof(struct elf_prstatus), 4) +
roundup(sizeof(struct elf_prpsinfo), 4) +
- roundup(sizeof(struct task_struct), 4);
+ roundup(arch_task_struct_size, 4);
*elf_buflen = PAGE_ALIGN(*elf_buflen);
return size + *elf_buflen;
}
@@ -415,7 +415,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff)
/* set up the task structure */
notes[2].name = CORE_STR;
notes[2].type = NT_TASKSTRUCT;
- notes[2].datasz = sizeof(struct task_struct);
+ notes[2].datasz = arch_task_struct_size;
notes[2].data = current;
nhdr->p_filesz += notesize(&notes[2]);
diff --git a/kernel/fs/proc/meminfo.c b/kernel/fs/proc/meminfo.c
index d3ebf2e61..9155a5a0d 100644
--- a/kernel/fs/proc/meminfo.c
+++ b/kernel/fs/proc/meminfo.c
@@ -27,7 +27,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
{
struct sysinfo i;
unsigned long committed;
- struct vmalloc_info vmi;
long cached;
long available;
unsigned long pagecache;
@@ -49,8 +48,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
if (cached < 0)
cached = 0;
- get_vmalloc_info(&vmi);
-
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
pages[lru] = global_page_state(NR_LRU_BASE + lru);
@@ -191,8 +188,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
K(vm_commit_limit()),
K(committed),
(unsigned long)VMALLOC_TOTAL >> 10,
- vmi.used >> 10,
- vmi.largest_chunk >> 10
+ 0ul, // used to be vmalloc 'used'
+ 0ul // used to be vmalloc 'largest_chunk'
#ifdef CONFIG_MEMORY_FAILURE
, atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
#endif
diff --git a/kernel/fs/proc/namespaces.c b/kernel/fs/proc/namespaces.c
index e512642db..1b0ea4a5d 100644
--- a/kernel/fs/proc/namespaces.c
+++ b/kernel/fs/proc/namespaces.c
@@ -30,7 +30,7 @@ static const struct proc_ns_operations *ns_entries[] = {
&mntns_operations,
};
-static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_ns_follow_link(struct dentry *dentry, void **cookie)
{
struct inode *inode = d_inode(dentry);
const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
@@ -42,10 +42,10 @@ static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
if (!task)
return error;
- if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+ if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
error = ns_get_path(&ns_path, task, ns_ops);
if (!error)
- nd_jump_link(nd, &ns_path);
+ nd_jump_link(&ns_path);
}
put_task_struct(task);
return error;
@@ -63,7 +63,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
if (!task)
return res;
- if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+ if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
res = ns_get_name(name, sizeof(name), task, ns_ops);
if (res >= 0)
res = readlink_copy(buffer, buflen, name);
diff --git a/kernel/fs/proc/nommu.c b/kernel/fs/proc/nommu.c
index d4a35746c..f8595e8b5 100644
--- a/kernel/fs/proc/nommu.c
+++ b/kernel/fs/proc/nommu.c
@@ -64,7 +64,7 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
if (file) {
seq_pad(m, ' ');
- seq_path(m, &file->f_path, "");
+ seq_file_path(m, file, "");
}
seq_putc(m, '\n');
diff --git a/kernel/fs/proc/page.c b/kernel/fs/proc/page.c
index 7eee2d8b9..93484034a 100644
--- a/kernel/fs/proc/page.c
+++ b/kernel/fs/proc/page.c
@@ -9,12 +9,16 @@
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/hugetlb.h>
+#include <linux/memcontrol.h>
+#include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
#include <linux/kernel-page-flags.h>
#include <asm/uaccess.h>
#include "internal.h"
#define KPMSIZE sizeof(u64)
#define KPMMASK (KPMSIZE - 1)
+#define KPMBITS (KPMSIZE * BITS_PER_BYTE)
/* /proc/kpagecount - an array exposing page counts
*
@@ -54,6 +58,8 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
pfn++;
out++;
count -= KPMSIZE;
+
+ cond_resched();
}
*ppos += (char __user *)out - buf;
@@ -146,6 +152,9 @@ u64 stable_page_flags(struct page *page)
if (PageBalloon(page))
u |= 1 << KPF_BALLOON;
+ if (page_is_idle(page))
+ u |= 1 << KPF_IDLE;
+
u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked);
u |= kpf_copy_bit(k, KPF_SLAB, PG_slab);
@@ -212,6 +221,8 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf,
pfn++;
out++;
count -= KPMSIZE;
+
+ cond_resched();
}
*ppos += (char __user *)out - buf;
@@ -225,10 +236,64 @@ static const struct file_operations proc_kpageflags_operations = {
.read = kpageflags_read,
};
+#ifdef CONFIG_MEMCG
+static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ u64 __user *out = (u64 __user *)buf;
+ struct page *ppage;
+ unsigned long src = *ppos;
+ unsigned long pfn;
+ ssize_t ret = 0;
+ u64 ino;
+
+ pfn = src / KPMSIZE;
+ count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
+ if (src & KPMMASK || count & KPMMASK)
+ return -EINVAL;
+
+ while (count > 0) {
+ if (pfn_valid(pfn))
+ ppage = pfn_to_page(pfn);
+ else
+ ppage = NULL;
+
+ if (ppage)
+ ino = page_cgroup_ino(ppage);
+ else
+ ino = 0;
+
+ if (put_user(ino, out)) {
+ ret = -EFAULT;
+ break;
+ }
+
+ pfn++;
+ out++;
+ count -= KPMSIZE;
+
+ cond_resched();
+ }
+
+ *ppos += (char __user *)out - buf;
+ if (!ret)
+ ret = (char __user *)out - buf;
+ return ret;
+}
+
+static const struct file_operations proc_kpagecgroup_operations = {
+ .llseek = mem_lseek,
+ .read = kpagecgroup_read,
+};
+#endif /* CONFIG_MEMCG */
+
static int __init proc_page_init(void)
{
proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
+#ifdef CONFIG_MEMCG
+ proc_create("kpagecgroup", S_IRUSR, NULL, &proc_kpagecgroup_operations);
+#endif
return 0;
}
fs_initcall(proc_page_init);
diff --git a/kernel/fs/proc/proc_sysctl.c b/kernel/fs/proc/proc_sysctl.c
index fdda62e61..fe5b6e6c4 100644
--- a/kernel/fs/proc/proc_sysctl.c
+++ b/kernel/fs/proc/proc_sysctl.c
@@ -948,7 +948,7 @@ static struct ctl_dir *get_subdir(struct ctl_dir *dir,
found:
subdir->header.nreg++;
failed:
- if (unlikely(IS_ERR(subdir))) {
+ if (IS_ERR(subdir)) {
pr_err("sysctl could not get directory: ");
sysctl_print_dir(dir);
pr_cont("/%*.*s %ld\n",
diff --git a/kernel/fs/proc/root.c b/kernel/fs/proc/root.c
index 68feb0f70..361ab4ee4 100644
--- a/kernel/fs/proc/root.c
+++ b/kernel/fs/proc/root.c
@@ -134,6 +134,8 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
}
sb->s_flags |= MS_ACTIVE;
+ /* User space would break if executables appear on proc */
+ sb->s_iflags |= SB_I_NOEXEC;
}
return dget(sb->s_root);
diff --git a/kernel/fs/proc/self.c b/kernel/fs/proc/self.c
index 6195b4a7c..113b8d061 100644
--- a/kernel/fs/proc/self.c
+++ b/kernel/fs/proc/self.c
@@ -1,5 +1,4 @@
#include <linux/sched.h>
-#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/pid_namespace.h>
#include "internal.h"
@@ -19,21 +18,20 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
return readlink_copy(buffer, buflen, tmp);
}
-static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_self_follow_link(struct dentry *dentry, void **cookie)
{
struct pid_namespace *ns = dentry->d_sb->s_fs_info;
pid_t tgid = task_tgid_nr_ns(current, ns);
- char *name = ERR_PTR(-ENOENT);
- if (tgid) {
- /* 11 for max length of signed int in decimal + NULL term */
- name = kmalloc(12, GFP_KERNEL);
- if (!name)
- name = ERR_PTR(-ENOMEM);
- else
- sprintf(name, "%d", tgid);
- }
- nd_set_link(nd, name);
- return NULL;
+ char *name;
+
+ if (!tgid)
+ return ERR_PTR(-ENOENT);
+ /* 11 for max length of signed int in decimal + NULL term */
+ name = kmalloc(12, GFP_KERNEL);
+ if (!name)
+ return ERR_PTR(-ENOMEM);
+ sprintf(name, "%d", tgid);
+ return *cookie = name;
}
static const struct inode_operations proc_self_inode_operations = {
diff --git a/kernel/fs/proc/task_mmu.c b/kernel/fs/proc/task_mmu.c
index 6dee68d01..09cd3edde 100644
--- a/kernel/fs/proc/task_mmu.c
+++ b/kernel/fs/proc/task_mmu.c
@@ -13,6 +13,7 @@
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
#include <asm/elf.h>
#include <asm/uaccess.h>
@@ -69,6 +70,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
ptes >> 10,
pmds >> 10,
swap << (PAGE_SHIFT-10));
+ hugetlb_report_usage(m, mm);
}
unsigned long task_vsize(struct mm_struct *mm)
@@ -310,7 +312,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
*/
if (file) {
seq_pad(m, ' ');
- seq_path(m, &file->f_path, "\n");
+ seq_file_path(m, file, "\n");
goto done;
}
@@ -445,7 +447,10 @@ struct mem_size_stats {
unsigned long anonymous;
unsigned long anonymous_thp;
unsigned long swap;
+ unsigned long shared_hugetlb;
+ unsigned long private_hugetlb;
u64 pss;
+ u64 swap_pss;
};
static void smaps_account(struct mem_size_stats *mss, struct page *page,
@@ -458,7 +463,7 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
mss->resident += size;
/* Accumulate the size in pages that have been accessed. */
- if (young || PageReferenced(page))
+ if (young || page_is_young(page) || PageReferenced(page))
mss->referenced += size;
mapcount = page_mapcount(page);
if (mapcount >= 2) {
@@ -492,9 +497,20 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
} else if (is_swap_pte(*pte)) {
swp_entry_t swpent = pte_to_swp_entry(*pte);
- if (!non_swap_entry(swpent))
+ if (!non_swap_entry(swpent)) {
+ int mapcount;
+
mss->swap += PAGE_SIZE;
- else if (is_migration_entry(swpent))
+ mapcount = swp_swapcount(swpent);
+ if (mapcount >= 2) {
+ u64 pss_delta = (u64)PAGE_SIZE << PSS_SHIFT;
+
+ do_div(pss_delta, mapcount);
+ mss->swap_pss += pss_delta;
+ } else {
+ mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT;
+ }
+ } else if (is_migration_entry(swpent))
page = migration_entry_to_page(swpent);
}
@@ -597,6 +613,8 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
[ilog2(VM_HUGEPAGE)] = "hg",
[ilog2(VM_NOHUGEPAGE)] = "nh",
[ilog2(VM_MERGEABLE)] = "mg",
+ [ilog2(VM_UFFD_MISSING)]= "um",
+ [ilog2(VM_UFFD_WP)] = "uw",
};
size_t i;
@@ -610,12 +628,44 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
seq_putc(m, '\n');
}
+#ifdef CONFIG_HUGETLB_PAGE
+static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
+ unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ struct mem_size_stats *mss = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+ struct page *page = NULL;
+
+ if (pte_present(*pte)) {
+ page = vm_normal_page(vma, addr, *pte);
+ } else if (is_swap_pte(*pte)) {
+ swp_entry_t swpent = pte_to_swp_entry(*pte);
+
+ if (is_migration_entry(swpent))
+ page = migration_entry_to_page(swpent);
+ }
+ if (page) {
+ int mapcount = page_mapcount(page);
+
+ if (mapcount >= 2)
+ mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
+ else
+ mss->private_hugetlb += huge_page_size(hstate_vma(vma));
+ }
+ return 0;
+}
+#endif /* HUGETLB_PAGE */
+
static int show_smap(struct seq_file *m, void *v, int is_pid)
{
struct vm_area_struct *vma = v;
struct mem_size_stats mss;
struct mm_walk smaps_walk = {
.pmd_entry = smaps_pte_range,
+#ifdef CONFIG_HUGETLB_PAGE
+ .hugetlb_entry = smaps_hugetlb_range,
+#endif
.mm = vma->vm_mm,
.private = &mss,
};
@@ -637,7 +687,10 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
"Referenced: %8lu kB\n"
"Anonymous: %8lu kB\n"
"AnonHugePages: %8lu kB\n"
+ "Shared_Hugetlb: %8lu kB\n"
+ "Private_Hugetlb: %7lu kB\n"
"Swap: %8lu kB\n"
+ "SwapPss: %8lu kB\n"
"KernelPageSize: %8lu kB\n"
"MMUPageSize: %8lu kB\n"
"Locked: %8lu kB\n",
@@ -651,7 +704,10 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
mss.referenced >> 10,
mss.anonymous >> 10,
mss.anonymous_thp >> 10,
+ mss.shared_hugetlb >> 10,
+ mss.private_hugetlb >> 10,
mss.swap >> 10,
+ (unsigned long)(mss.swap_pss >> (10 + PSS_SHIFT)),
vma_kernel_pagesize(vma) >> 10,
vma_mmu_pagesize(vma) >> 10,
(vma->vm_flags & VM_LOCKED) ?
@@ -710,23 +766,6 @@ const struct file_operations proc_tid_smaps_operations = {
.release = proc_map_release,
};
-/*
- * We do not want to have constant page-shift bits sitting in
- * pagemap entries and are about to reuse them some time soon.
- *
- * Here's the "migration strategy":
- * 1. when the system boots these bits remain what they are,
- * but a warning about future change is printed in log;
- * 2. once anyone clears soft-dirty bits via clear_refs file,
- * these flag is set to denote, that user is aware of the
- * new API and those page-shift bits change their meaning.
- * The respective warning is printed in dmesg;
- * 3. In a couple of releases we will remove all the mentions
- * of page-shift in pagemap entries.
- */
-
-static bool soft_dirty_cleared __read_mostly;
-
enum clear_refs_types {
CLEAR_REFS_ALL = 1,
CLEAR_REFS_ANON,
@@ -753,36 +792,37 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
pte_t ptent = *pte;
if (pte_present(ptent)) {
+ ptent = ptep_modify_prot_start(vma->vm_mm, addr, pte);
ptent = pte_wrprotect(ptent);
- ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+ ptent = pte_clear_soft_dirty(ptent);
+ ptep_modify_prot_commit(vma->vm_mm, addr, pte, ptent);
} else if (is_swap_pte(ptent)) {
ptent = pte_swp_clear_soft_dirty(ptent);
+ set_pte_at(vma->vm_mm, addr, pte, ptent);
}
-
- set_pte_at(vma->vm_mm, addr, pte, ptent);
}
+#else
+static inline void clear_soft_dirty(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *pte)
+{
+}
+#endif
+#if defined(CONFIG_MEM_SOFT_DIRTY) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
- pmd_t pmd = *pmdp;
+ pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp);
pmd = pmd_wrprotect(pmd);
- pmd = pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY);
+ pmd = pmd_clear_soft_dirty(pmd);
if (vma->vm_flags & VM_SOFTDIRTY)
vma->vm_flags &= ~VM_SOFTDIRTY;
set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
}
-
#else
-
-static inline void clear_soft_dirty(struct vm_area_struct *vma,
- unsigned long addr, pte_t *pte)
-{
-}
-
static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
@@ -808,6 +848,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
/* Clear accessed and referenced bits. */
pmdp_test_and_clear_young(vma, addr, pmd);
+ test_and_clear_page_young(page);
ClearPageReferenced(page);
out:
spin_unlock(ptl);
@@ -835,6 +876,7 @@ out:
/* Clear accessed and referenced bits. */
ptep_test_and_clear_young(vma, addr, pte);
+ test_and_clear_page_young(page);
ClearPageReferenced(page);
}
pte_unmap_unlock(pte - 1, ptl);
@@ -887,13 +929,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST)
return -EINVAL;
- if (type == CLEAR_REFS_SOFT_DIRTY) {
- soft_dirty_cleared = true;
- pr_warn_once("The pagemap bits 55-60 has changed their meaning!"
- " See the linux/Documentation/vm/pagemap.txt for "
- "details.\n");
- }
-
task = get_proc_task(file_inode(file));
if (!task)
return -ESRCH;
@@ -961,36 +996,26 @@ typedef struct {
struct pagemapread {
int pos, len; /* units: PM_ENTRY_BYTES, not bytes */
pagemap_entry_t *buffer;
- bool v2;
+ bool show_pfn;
};
#define PAGEMAP_WALK_SIZE (PMD_SIZE)
#define PAGEMAP_WALK_MASK (PMD_MASK)
-#define PM_ENTRY_BYTES sizeof(pagemap_entry_t)
-#define PM_STATUS_BITS 3
-#define PM_STATUS_OFFSET (64 - PM_STATUS_BITS)
-#define PM_STATUS_MASK (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
-#define PM_STATUS(nr) (((nr) << PM_STATUS_OFFSET) & PM_STATUS_MASK)
-#define PM_PSHIFT_BITS 6
-#define PM_PSHIFT_OFFSET (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
-#define PM_PSHIFT_MASK (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
-#define __PM_PSHIFT(x) (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
-#define PM_PFRAME_MASK ((1LL << PM_PSHIFT_OFFSET) - 1)
-#define PM_PFRAME(x) ((x) & PM_PFRAME_MASK)
-/* in "new" pagemap pshift bits are occupied with more status bits */
-#define PM_STATUS2(v2, x) (__PM_PSHIFT(v2 ? x : PAGE_SHIFT))
-
-#define __PM_SOFT_DIRTY (1LL)
-#define PM_PRESENT PM_STATUS(4LL)
-#define PM_SWAP PM_STATUS(2LL)
-#define PM_FILE PM_STATUS(1LL)
-#define PM_NOT_PRESENT(v2) PM_STATUS2(v2, 0)
+#define PM_ENTRY_BYTES sizeof(pagemap_entry_t)
+#define PM_PFRAME_BITS 55
+#define PM_PFRAME_MASK GENMASK_ULL(PM_PFRAME_BITS - 1, 0)
+#define PM_SOFT_DIRTY BIT_ULL(55)
+#define PM_MMAP_EXCLUSIVE BIT_ULL(56)
+#define PM_FILE BIT_ULL(61)
+#define PM_SWAP BIT_ULL(62)
+#define PM_PRESENT BIT_ULL(63)
+
#define PM_END_OF_BUFFER 1
-static inline pagemap_entry_t make_pme(u64 val)
+static inline pagemap_entry_t make_pme(u64 frame, u64 flags)
{
- return (pagemap_entry_t) { .pme = val };
+ return (pagemap_entry_t) { .pme = (frame & PM_PFRAME_MASK) | flags };
}
static int add_to_pagemap(unsigned long addr, pagemap_entry_t *pme,
@@ -1011,7 +1036,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
while (addr < end) {
struct vm_area_struct *vma = find_vma(walk->mm, addr);
- pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ pagemap_entry_t pme = make_pme(0, 0);
/* End of address space hole, which we mark as non-present. */
unsigned long hole_end;
@@ -1031,7 +1056,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
/* Addresses in the VMA. */
if (vma->vm_flags & VM_SOFTDIRTY)
- pme.pme |= PM_STATUS2(pm->v2, __PM_SOFT_DIRTY);
+ pme = make_pme(0, PM_SOFT_DIRTY);
for (; addr < min(end, vma->vm_end); addr += PAGE_SIZE) {
err = add_to_pagemap(addr, &pme, pm);
if (err)
@@ -1042,67 +1067,42 @@ out:
return err;
}
-static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
+static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
struct vm_area_struct *vma, unsigned long addr, pte_t pte)
{
- u64 frame, flags;
+ u64 frame = 0, flags = 0;
struct page *page = NULL;
- int flags2 = 0;
if (pte_present(pte)) {
- frame = pte_pfn(pte);
- flags = PM_PRESENT;
+ if (pm->show_pfn)
+ frame = pte_pfn(pte);
+ flags |= PM_PRESENT;
page = vm_normal_page(vma, addr, pte);
if (pte_soft_dirty(pte))
- flags2 |= __PM_SOFT_DIRTY;
+ flags |= PM_SOFT_DIRTY;
} else if (is_swap_pte(pte)) {
swp_entry_t entry;
if (pte_swp_soft_dirty(pte))
- flags2 |= __PM_SOFT_DIRTY;
+ flags |= PM_SOFT_DIRTY;
entry = pte_to_swp_entry(pte);
frame = swp_type(entry) |
(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
- flags = PM_SWAP;
+ flags |= PM_SWAP;
if (is_migration_entry(entry))
page = migration_entry_to_page(entry);
- } else {
- if (vma->vm_flags & VM_SOFTDIRTY)
- flags2 |= __PM_SOFT_DIRTY;
- *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
- return;
}
if (page && !PageAnon(page))
flags |= PM_FILE;
- if ((vma->vm_flags & VM_SOFTDIRTY))
- flags2 |= __PM_SOFT_DIRTY;
+ if (page && page_mapcount(page) == 1)
+ flags |= PM_MMAP_EXCLUSIVE;
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ flags |= PM_SOFT_DIRTY;
- *pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
+ return make_pme(frame, flags);
}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
- pmd_t pmd, int offset, int pmd_flags2)
-{
- /*
- * Currently pmd for thp is always present because thp can not be
- * swapped-out, migrated, or HWPOISONed (split in such cases instead.)
- * This if-check is just to prepare for future implementation.
- */
- if (pmd_present(pmd))
- *pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
- | PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT);
- else
- *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, pmd_flags2));
-}
-#else
-static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
- pmd_t pmd, int offset, int pmd_flags2)
-{
-}
-#endif
-
-static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->vma;
@@ -1111,41 +1111,58 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
pte_t *pte, *orig_pte;
int err = 0;
- if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
- int pmd_flags2;
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if (pmd_trans_huge_lock(pmdp, vma, &ptl) == 1) {
+ u64 flags = 0, frame = 0;
+ pmd_t pmd = *pmdp;
- if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
- pmd_flags2 = __PM_SOFT_DIRTY;
- else
- pmd_flags2 = 0;
+ if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(pmd))
+ flags |= PM_SOFT_DIRTY;
+
+ /*
+ * Currently pmd for thp is always present because thp
+ * can not be swapped-out, migrated, or HWPOISONed
+ * (split in such cases instead.)
+ * This if-check is just to prepare for future implementation.
+ */
+ if (pmd_present(pmd)) {
+ struct page *page = pmd_page(pmd);
+
+ if (page_mapcount(page) == 1)
+ flags |= PM_MMAP_EXCLUSIVE;
+
+ flags |= PM_PRESENT;
+ if (pm->show_pfn)
+ frame = pmd_pfn(pmd) +
+ ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+ }
for (; addr != end; addr += PAGE_SIZE) {
- unsigned long offset;
- pagemap_entry_t pme;
+ pagemap_entry_t pme = make_pme(frame, flags);
- offset = (addr & ~PAGEMAP_WALK_MASK) >>
- PAGE_SHIFT;
- thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset, pmd_flags2);
err = add_to_pagemap(addr, &pme, pm);
if (err)
break;
+ if (pm->show_pfn && (flags & PM_PRESENT))
+ frame++;
}
spin_unlock(ptl);
return err;
}
- if (pmd_trans_unstable(pmd))
+ if (pmd_trans_unstable(pmdp))
return 0;
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
* We can assume that @vma always points to a valid one and @end never
* goes beyond vma->vm_end.
*/
- orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ orig_pte = pte = pte_offset_map_lock(walk->mm, pmdp, addr, &ptl);
for (; addr < end; pte++, addr += PAGE_SIZE) {
pagemap_entry_t pme;
- pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
+ pme = pte_to_pagemap_entry(pm, vma, addr, *pte);
err = add_to_pagemap(addr, &pme, pm);
if (err)
break;
@@ -1158,40 +1175,44 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
}
#ifdef CONFIG_HUGETLB_PAGE
-static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
- pte_t pte, int offset, int flags2)
-{
- if (pte_present(pte))
- *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset) |
- PM_STATUS2(pm->v2, flags2) |
- PM_PRESENT);
- else
- *pme = make_pme(PM_NOT_PRESENT(pm->v2) |
- PM_STATUS2(pm->v2, flags2));
-}
-
/* This function walks within one hugetlb entry in the single call */
-static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
+static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct pagemapread *pm = walk->private;
struct vm_area_struct *vma = walk->vma;
+ u64 flags = 0, frame = 0;
int err = 0;
- int flags2;
- pagemap_entry_t pme;
+ pte_t pte;
if (vma->vm_flags & VM_SOFTDIRTY)
- flags2 = __PM_SOFT_DIRTY;
- else
- flags2 = 0;
+ flags |= PM_SOFT_DIRTY;
+
+ pte = huge_ptep_get(ptep);
+ if (pte_present(pte)) {
+ struct page *page = pte_page(pte);
+
+ if (!PageAnon(page))
+ flags |= PM_FILE;
+
+ if (page_mapcount(page) == 1)
+ flags |= PM_MMAP_EXCLUSIVE;
+
+ flags |= PM_PRESENT;
+ if (pm->show_pfn)
+ frame = pte_pfn(pte) +
+ ((addr & ~hmask) >> PAGE_SHIFT);
+ }
for (; addr != end; addr += PAGE_SIZE) {
- int offset = (addr & ~hmask) >> PAGE_SHIFT;
- huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2);
+ pagemap_entry_t pme = make_pme(frame, flags);
+
err = add_to_pagemap(addr, &pme, pm);
if (err)
return err;
+ if (pm->show_pfn && (flags & PM_PRESENT))
+ frame++;
}
cond_resched();
@@ -1209,7 +1230,9 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
* Bits 0-54 page frame number (PFN) if present
* Bits 0-4 swap type if swapped
* Bits 5-54 swap offset if swapped
- * Bits 55-60 page shift (page size = 1<<page shift)
+ * Bit 55 pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
+ * Bit 56 page exclusively mapped
+ * Bits 57-60 zero
* Bit 61 page is file-page or shared-anon
* Bit 62 page swapped
* Bit 63 page present
@@ -1227,42 +1250,37 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
static ssize_t pagemap_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
- struct task_struct *task = get_proc_task(file_inode(file));
- struct mm_struct *mm;
+ struct mm_struct *mm = file->private_data;
struct pagemapread pm;
- int ret = -ESRCH;
struct mm_walk pagemap_walk = {};
unsigned long src;
unsigned long svpfn;
unsigned long start_vaddr;
unsigned long end_vaddr;
- int copied = 0;
+ int ret = 0, copied = 0;
- if (!task)
+ if (!mm || !atomic_inc_not_zero(&mm->mm_users))
goto out;
ret = -EINVAL;
/* file position must be aligned */
if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES))
- goto out_task;
+ goto out_mm;
ret = 0;
if (!count)
- goto out_task;
+ goto out_mm;
+
+ /* do not disclose physical addresses: attack vector */
+ pm.show_pfn = file_ns_capable(file, &init_user_ns, CAP_SYS_ADMIN);
- pm.v2 = soft_dirty_cleared;
pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY);
ret = -ENOMEM;
if (!pm.buffer)
- goto out_task;
-
- mm = mm_access(task, PTRACE_MODE_READ);
- ret = PTR_ERR(mm);
- if (!mm || IS_ERR(mm))
- goto out_free;
+ goto out_mm;
- pagemap_walk.pmd_entry = pagemap_pte_range;
+ pagemap_walk.pmd_entry = pagemap_pmd_range;
pagemap_walk.pte_hole = pagemap_pte_hole;
#ifdef CONFIG_HUGETLB_PAGE
pagemap_walk.hugetlb_entry = pagemap_hugetlb_range;
@@ -1273,10 +1291,10 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
src = *ppos;
svpfn = src / PM_ENTRY_BYTES;
start_vaddr = svpfn << PAGE_SHIFT;
- end_vaddr = TASK_SIZE_OF(task);
+ end_vaddr = mm->task_size;
/* watch out for wraparound */
- if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT)
+ if (svpfn > mm->task_size >> PAGE_SHIFT)
start_vaddr = end_vaddr;
/*
@@ -1303,7 +1321,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
len = min(count, PM_ENTRY_BYTES * pm.pos);
if (copy_to_user(buf, pm.buffer, len)) {
ret = -EFAULT;
- goto out_mm;
+ goto out_free;
}
copied += len;
buf += len;
@@ -1313,24 +1331,31 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
if (!ret || ret == PM_END_OF_BUFFER)
ret = copied;
-out_mm:
- mmput(mm);
out_free:
kfree(pm.buffer);
-out_task:
- put_task_struct(task);
+out_mm:
+ mmput(mm);
out:
return ret;
}
static int pagemap_open(struct inode *inode, struct file *file)
{
- /* do not disclose physical addresses: attack vector */
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
- pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about "
- "to stop being page-shift some time soon. See the "
- "linux/Documentation/vm/pagemap.txt for details.\n");
+ struct mm_struct *mm;
+
+ mm = proc_mem_open(inode, PTRACE_MODE_READ);
+ if (IS_ERR(mm))
+ return PTR_ERR(mm);
+ file->private_data = mm;
+ return 0;
+}
+
+static int pagemap_release(struct inode *inode, struct file *file)
+{
+ struct mm_struct *mm = file->private_data;
+
+ if (mm)
+ mmdrop(mm);
return 0;
}
@@ -1338,6 +1363,7 @@ const struct file_operations proc_pagemap_operations = {
.llseek = mem_lseek, /* borrow this */
.read = pagemap_read,
.open = pagemap_open,
+ .release = pagemap_release,
};
#endif /* CONFIG_PROC_PAGE_MONITOR */
@@ -1447,18 +1473,19 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
unsigned long addr, unsigned long end, struct mm_walk *walk)
{
+ pte_t huge_pte = huge_ptep_get(pte);
struct numa_maps *md;
struct page *page;
- if (!pte_present(*pte))
+ if (!pte_present(huge_pte))
return 0;
- page = pte_page(*pte);
+ page = pte_page(huge_pte);
if (!page)
return 0;
md = walk->private;
- gather_stats(page, md, pte_dirty(*pte), 1);
+ gather_stats(page, md, pte_dirty(huge_pte), 1);
return 0;
}
@@ -1509,7 +1536,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
if (file) {
seq_puts(m, " file=");
- seq_path(m, &file->f_path, "\n\t= ");
+ seq_file_path(m, file, "\n\t= ");
} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
seq_puts(m, " heap");
} else {
diff --git a/kernel/fs/proc/task_nommu.c b/kernel/fs/proc/task_nommu.c
index 599ec2e20..e0d64c92e 100644
--- a/kernel/fs/proc/task_nommu.c
+++ b/kernel/fs/proc/task_nommu.c
@@ -180,7 +180,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
if (file) {
seq_pad(m, ' ');
- seq_path(m, &file->f_path, "");
+ seq_file_path(m, file, "");
} else if (mm) {
pid_t tid = pid_of_stack(priv, vma, is_pid);
diff --git a/kernel/fs/proc/thread_self.c b/kernel/fs/proc/thread_self.c
index a8371993b..947b0f4fd 100644
--- a/kernel/fs/proc/thread_self.c
+++ b/kernel/fs/proc/thread_self.c
@@ -1,5 +1,4 @@
#include <linux/sched.h>
-#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/pid_namespace.h>
#include "internal.h"
@@ -20,21 +19,20 @@ static int proc_thread_self_readlink(struct dentry *dentry, char __user *buffer,
return readlink_copy(buffer, buflen, tmp);
}
-static void *proc_thread_self_follow_link(struct dentry *dentry, struct nameidata *nd)
+static const char *proc_thread_self_follow_link(struct dentry *dentry, void **cookie)
{
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;
+ char *name;
+
+ if (!pid)
+ return ERR_PTR(-ENOENT);
+ name = kmalloc(PROC_NUMBUF + 6 + PROC_NUMBUF, GFP_KERNEL);
+ if (!name)
+ return ERR_PTR(-ENOMEM);
+ sprintf(name, "%d/task/%d", tgid, pid);
+ return *cookie = name;
}
static const struct inode_operations proc_thread_self_inode_operations = {