summaryrefslogtreecommitdiff
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/Kconfig2
-rw-r--r--fs/proc/Makefile2
-rw-r--r--fs/proc/array.c2
-rw-r--r--fs/proc/base.c148
-rw-r--r--fs/proc/bootconfig.c6
-rw-r--r--fs/proc/consoles.c7
-rw-r--r--fs/proc/fd.c35
-rw-r--r--fs/proc/generic.c22
-rw-r--r--fs/proc/inode.c85
-rw-r--r--fs/proc/internal.h66
-rw-r--r--fs/proc/kcore.c7
-rw-r--r--fs/proc/meminfo.c3
-rw-r--r--fs/proc/nommu.c2
-rw-r--r--fs/proc/page.c114
-rw-r--r--fs/proc/proc_net.c1
-rw-r--r--fs/proc/proc_sysctl.c123
-rw-r--r--fs/proc/root.c4
-rw-r--r--fs/proc/self.c2
-rw-r--r--fs/proc/task_mmu.c1376
-rw-r--r--fs/proc/task_nommu.c2
-rw-r--r--fs/proc/thread_self.c2
-rw-r--r--fs/proc/vmcore.c7
22 files changed, 1585 insertions, 433 deletions
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index 32b1116ae137..d80a1431ef7b 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -32,7 +32,7 @@ config PROC_FS
config PROC_KCORE
bool "/proc/kcore support" if !ARM
depends on PROC_FS && MMU
- select CRASH_CORE
+ select VMCORE_INFO
help
Provides a virtual ELF core file of the live kernel. This can
be read with gdb and other ELF tools. No modifications can be
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index bd08616ed8ba..7b4db9c56e6a 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -5,7 +5,7 @@
obj-y += proc.o
-CFLAGS_task_mmu.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_task_mmu.o += -Wno-override-init
proc-y := nommu.o task_nommu.o
proc-$(CONFIG_MMU) := task_mmu.o
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 34a47fb0c57f..5e4f7b411fbd 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -500,7 +500,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
* a program is not able to use ptrace(2) in that case. It is
* safe because the task has stopped executing permanently.
*/
- if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE))) {
+ if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE|PF_POSTCOREDUMP))) {
if (try_get_task_stack(task)) {
eip = KSTK_EIP(task);
esp = KSTK_ESP(task);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 699f085d4de7..a2541f5204af 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -98,6 +98,7 @@
#include <linux/resctrl.h>
#include <linux/cn_proc.h>
#include <linux/ksm.h>
+#include <uapi/linux/lsm.h>
#include <trace/events/oom.h>
#include "internal.h"
#include "fd.h"
@@ -181,10 +182,10 @@ struct pid_entry {
NOD(NAME, (S_IFREG|(MODE)), \
NULL, &proc_single_file_operations, \
{ .proc_show = show } )
-#define ATTR(LSM, NAME, MODE) \
+#define ATTR(LSMID, NAME, MODE) \
NOD(NAME, (S_IFREG|(MODE)), \
NULL, &proc_pid_attr_operations, \
- { .lsm = LSM })
+ { .lsmid = LSMID })
/*
* Count the number of hardlinks for the pid_entry table, excluding the .
@@ -416,7 +417,7 @@ static const struct file_operations proc_pid_cmdline_ops = {
#ifdef CONFIG_KALLSYMS
/*
* Provides a wchan file via kallsyms in a proper one-value-per-file format.
- * Returns the resolved symbol. If that fails, simply return the address.
+ * Returns the resolved symbol to user space.
*/
static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
@@ -861,12 +862,9 @@ static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
static int mem_open(struct inode *inode, struct file *file)
{
- int ret = __mem_open(inode, file, PTRACE_MODE_ATTACH);
-
- /* OK to pass negative loff_t, we can catch out-of-range */
- file->f_mode |= FMODE_UNSIGNED_OFFSET;
-
- return ret;
+ if (WARN_ON_ONCE(!(file->f_op->fop_flags & FOP_UNSIGNED_OFFSET)))
+ return -EINVAL;
+ return __mem_open(inode, file, PTRACE_MODE_ATTACH);
}
static bool proc_mem_foll_force(struct file *file, struct mm_struct *mm)
@@ -990,6 +988,7 @@ static const struct file_operations proc_mem_operations = {
.write = mem_write,
.open = mem_open,
.release = mem_release,
+ .fop_flags = FOP_UNSIGNED_OFFSET,
};
static int environ_open(struct inode *inode, struct file *file)
@@ -1212,11 +1211,10 @@ err_unlock:
static ssize_t oom_adj_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
- char buffer[PROC_NUMBUF];
+ char buffer[PROC_NUMBUF] = {};
int oom_adj;
int err;
- memset(buffer, 0, sizeof(buffer));
if (count > sizeof(buffer) - 1)
count = sizeof(buffer) - 1;
if (copy_from_user(buffer, buf, count)) {
@@ -1272,11 +1270,10 @@ static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
- char buffer[PROC_NUMBUF];
+ char buffer[PROC_NUMBUF] = {};
int oom_score_adj;
int err;
- memset(buffer, 0, sizeof(buffer));
if (count > sizeof(buffer) - 1)
count = sizeof(buffer) - 1;
if (copy_from_user(buffer, buf, count)) {
@@ -1417,13 +1414,13 @@ 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];
+ char buffer[PROC_NUMBUF] = {};
int make_it_fail;
int rv;
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
- memset(buffer, 0, sizeof(buffer));
+
if (count > sizeof(buffer) - 1)
count = sizeof(buffer) - 1;
if (copy_from_user(buffer, buf, count))
@@ -1568,11 +1565,10 @@ sched_autogroup_write(struct file *file, const char __user *buf,
{
struct inode *inode = file_inode(file);
struct task_struct *p;
- char buffer[PROC_NUMBUF];
+ char buffer[PROC_NUMBUF] = {};
int nice;
int err;
- memset(buffer, 0, sizeof(buffer));
if (count > sizeof(buffer) - 1)
count = sizeof(buffer) - 1;
if (copy_from_user(buffer, buf, count))
@@ -1725,10 +1721,9 @@ static ssize_t comm_write(struct file *file, const char __user *buf,
{
struct inode *inode = file_inode(file);
struct task_struct *p;
- char buffer[TASK_COMM_LEN];
+ char buffer[TASK_COMM_LEN] = {};
const size_t maxlen = sizeof(buffer) - 1;
- memset(buffer, 0, sizeof(buffer));
if (copy_from_user(buffer, buf, count > maxlen ? maxlen : count))
return -EFAULT;
@@ -1940,8 +1935,6 @@ void proc_pid_evict_inode(struct proc_inode *ei)
hlist_del_init_rcu(&ei->sibling_inodes);
spin_unlock(&pid->lock);
}
-
- put_pid(pid);
}
struct inode *proc_pid_make_inode(struct super_block *sb,
@@ -1961,7 +1954,7 @@ struct inode *proc_pid_make_inode(struct super_block *sb,
ei = PROC_I(inode);
inode->i_mode = mode;
inode->i_ino = get_next_ino();
- inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode);
+ simple_inode_init_ts(inode);
inode->i_op = &proc_def_inode_operations;
/*
@@ -2277,7 +2270,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path)
rc = -ENOENT;
vma = find_exact_vma(mm, vm_start, vm_end);
if (vma && vma->vm_file) {
- *path = vma->vm_file->f_path;
+ *path = *file_user_path(vma->vm_file);
path_get(path);
rc = 0;
}
@@ -2340,8 +2333,8 @@ proc_map_files_instantiate(struct dentry *dentry,
inode->i_op = &proc_map_files_link_inode_operations;
inode->i_size = 64;
- d_set_d_op(dentry, &tid_map_files_dentry_operations);
- return d_splice_alias(inode, dentry);
+ return proc_splice_unmountable(inode, dentry,
+ &tid_map_files_dentry_operations);
}
static struct dentry *proc_map_files_lookup(struct inode *dir,
@@ -2520,13 +2513,13 @@ static void *timers_start(struct seq_file *m, loff_t *pos)
if (!tp->sighand)
return ERR_PTR(-ESRCH);
- return seq_list_start(&tp->task->signal->posix_timers, *pos);
+ return seq_hlist_start(&tp->task->signal->posix_timers, *pos);
}
static void *timers_next(struct seq_file *m, void *v, loff_t *pos)
{
struct timers_private *tp = m->private;
- return seq_list_next(v, &tp->task->signal->posix_timers, pos);
+ return seq_hlist_next(v, &tp->task->signal->posix_timers, pos);
}
static void timers_stop(struct seq_file *m, void *v)
@@ -2555,7 +2548,7 @@ static int show_timer(struct seq_file *m, void *v)
[SIGEV_THREAD] = "thread",
};
- timer = list_entry((struct list_head *)v, struct k_itimer, list);
+ timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list);
notify = timer->it_sigev_notify;
seq_printf(m, "ID: %d\n", timer->it_id);
@@ -2633,10 +2626,11 @@ static ssize_t timerslack_ns_write(struct file *file, const char __user *buf,
}
task_lock(p);
- if (slack_ns == 0)
- p->timer_slack_ns = p->default_timer_slack_ns;
- else
- p->timer_slack_ns = slack_ns;
+ if (rt_or_dl_task_policy(p))
+ slack_ns = 0;
+ else if (slack_ns == 0)
+ slack_ns = p->default_timer_slack_ns;
+ p->timer_slack_ns = slack_ns;
task_unlock(p);
out:
@@ -2789,7 +2783,7 @@ static ssize_t proc_pid_attr_read(struct file * file, char __user * buf,
if (!task)
return -ESRCH;
- length = security_getprocattr(task, PROC_I(inode)->op.lsm,
+ length = security_getprocattr(task, PROC_I(inode)->op.lsmid,
file->f_path.dentry->d_name.name,
&p);
put_task_struct(task);
@@ -2847,7 +2841,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
if (rv < 0)
goto out_free;
- rv = security_setprocattr(PROC_I(inode)->op.lsm,
+ rv = security_setprocattr(PROC_I(inode)->op.lsmid,
file->f_path.dentry->d_name.name, page,
count);
mutex_unlock(&current->signal->cred_guard_mutex);
@@ -2896,27 +2890,27 @@ static const struct inode_operations proc_##LSM##_attr_dir_inode_ops = { \
#ifdef CONFIG_SECURITY_SMACK
static const struct pid_entry smack_attr_dir_stuff[] = {
- ATTR("smack", "current", 0666),
+ ATTR(LSM_ID_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),
+ ATTR(LSM_ID_APPARMOR, "current", 0666),
+ ATTR(LSM_ID_APPARMOR, "prev", 0444),
+ ATTR(LSM_ID_APPARMOR, "exec", 0666),
};
LSM_DIR_OPS(apparmor);
#endif
static const struct pid_entry attr_dir_stuff[] = {
- ATTR(NULL, "current", 0666),
- ATTR(NULL, "prev", 0444),
- ATTR(NULL, "exec", 0666),
- ATTR(NULL, "fscreate", 0666),
- ATTR(NULL, "keycreate", 0666),
- ATTR(NULL, "sockcreate", 0666),
+ ATTR(LSM_ID_UNDEF, "current", 0666),
+ ATTR(LSM_ID_UNDEF, "prev", 0444),
+ ATTR(LSM_ID_UNDEF, "exec", 0666),
+ ATTR(LSM_ID_UNDEF, "fscreate", 0666),
+ ATTR(LSM_ID_UNDEF, "keycreate", 0666),
+ ATTR(LSM_ID_UNDEF, "sockcreate", 0666),
#ifdef CONFIG_SECURITY_SMACK
DIR("smack", 0555,
proc_smack_attr_dir_inode_ops, proc_smack_attr_dir_ops),
@@ -3035,8 +3029,7 @@ static const struct file_operations proc_coredump_filter_operations = {
#ifdef CONFIG_TASK_IO_ACCOUNTING
static int do_io_accounting(struct task_struct *task, struct seq_file *m, int whole)
{
- struct task_io_accounting acct = task->ioac;
- unsigned long flags;
+ struct task_io_accounting acct;
int result;
result = down_read_killable(&task->signal->exec_update_lock);
@@ -3048,15 +3041,28 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
goto out_unlock;
}
- if (whole && lock_task_sighand(task, &flags)) {
- struct task_struct *t = task;
+ if (whole) {
+ struct signal_struct *sig = task->signal;
+ struct task_struct *t;
+ unsigned int seq = 1;
+ unsigned long flags;
+
+ rcu_read_lock();
+ do {
+ seq++; /* 2 on the 1st/lockless path, otherwise odd */
+ flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
- task_io_accounting_add(&acct, &task->signal->ioac);
- while_each_thread(task, t)
- task_io_accounting_add(&acct, &t->ioac);
+ acct = sig->ioac;
+ __for_each_thread(sig, t)
+ task_io_accounting_add(&acct, &t->ioac);
- unlock_task_sighand(task, &flags);
+ } while (need_seqretry(&sig->stats_lock, seq));
+ done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
+ rcu_read_unlock();
+ } else {
+ acct = task->ioac;
}
+
seq_printf(m,
"rchar: %llu\n"
"wchar: %llu\n"
@@ -3877,7 +3883,7 @@ static struct task_struct *first_tid(struct pid *pid, int tid, loff_t f_pos,
for_each_thread(task, pos) {
if (!nr--)
goto found;
- };
+ }
fail:
pos = NULL;
goto out;
@@ -3899,10 +3905,8 @@ static struct task_struct *next_tid(struct task_struct *start)
struct task_struct *pos = NULL;
rcu_read_lock();
if (pid_alive(start)) {
- pos = next_thread(start);
- if (thread_group_leader(pos))
- pos = NULL;
- else
+ pos = __next_thread(start);
+ if (pos)
get_task_struct(pos);
}
rcu_read_unlock();
@@ -3924,12 +3928,12 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
if (!dir_emit_dots(file, ctx))
return 0;
- /* f_version caches the tgid value that the last readdir call couldn't
- * return. lseek aka telldir automagically resets f_version to 0.
+ /* We cache the tgid value that the last readdir call couldn't
+ * return and lseek resets it to 0.
*/
ns = proc_pid_ns(inode->i_sb);
- tid = (int)file->f_version;
- file->f_version = 0;
+ tid = (int)(intptr_t)file->private_data;
+ file->private_data = NULL;
for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns);
task;
task = next_tid(task), ctx->pos++) {
@@ -3944,7 +3948,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
proc_task_instantiate, task, NULL)) {
/* returning this tgid failed, save it as the first
* pid for the next readir call */
- file->f_version = (u64)tid;
+ file->private_data = (void *)(intptr_t)tid;
put_task_struct(task);
break;
}
@@ -3969,6 +3973,24 @@ static int proc_task_getattr(struct mnt_idmap *idmap,
return 0;
}
+/*
+ * proc_task_readdir() set @file->private_data to a positive integer
+ * value, so casting that to u64 is safe. generic_llseek_cookie() will
+ * set @cookie to 0, so casting to an int is safe. The WARN_ON_ONCE() is
+ * here to catch any unexpected change in behavior either in
+ * proc_task_readdir() or generic_llseek_cookie().
+ */
+static loff_t proc_dir_llseek(struct file *file, loff_t offset, int whence)
+{
+ u64 cookie = (u64)(intptr_t)file->private_data;
+ loff_t off;
+
+ off = generic_llseek_cookie(file, offset, whence, &cookie);
+ WARN_ON_ONCE(cookie > INT_MAX);
+ file->private_data = (void *)(intptr_t)cookie; /* serialized by f_pos_lock */
+ return off;
+}
+
static const struct inode_operations proc_task_inode_operations = {
.lookup = proc_task_lookup,
.getattr = proc_task_getattr,
@@ -3979,7 +4001,7 @@ static const struct inode_operations proc_task_inode_operations = {
static const struct file_operations proc_task_operations = {
.read = generic_read_dir,
.iterate_shared = proc_task_readdir,
- .llseek = generic_file_llseek,
+ .llseek = proc_dir_llseek,
};
void __init set_proc_pid_nlink(void)
diff --git a/fs/proc/bootconfig.c b/fs/proc/bootconfig.c
index 2e244ada1f97..87dcaae32ff8 100644
--- a/fs/proc/bootconfig.c
+++ b/fs/proc/bootconfig.c
@@ -63,6 +63,12 @@ static int __init copy_xbc_key_value_list(char *dst, size_t size)
dst += ret;
}
}
+ if (cmdline_has_extra_options() && ret >= 0 && boot_command_line[0]) {
+ ret = snprintf(dst, rest(dst, end), "# Parameters from bootloader:\n# %s\n",
+ boot_command_line);
+ if (ret > 0)
+ dst += ret;
+ }
out:
kfree(key);
diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c
index e0758fe7936d..b7cab1ad990d 100644
--- a/fs/proc/consoles.c
+++ b/fs/proc/consoles.c
@@ -21,6 +21,7 @@ static int show_console_dev(struct seq_file *m, void *v)
{ CON_ENABLED, 'E' },
{ CON_CONSDEV, 'C' },
{ CON_BOOT, 'B' },
+ { CON_NBCON, 'N' },
{ CON_PRINTBUFFER, 'p' },
{ CON_BRL, 'b' },
{ CON_ANYTIME, 'a' },
@@ -58,8 +59,8 @@ static int show_console_dev(struct seq_file *m, void *v)
seq_printf(m, "%s%d", con->name, con->index);
seq_pad(m, ' ');
seq_printf(m, "%c%c%c (%s)", con->read ? 'R' : '-',
- con->write ? 'W' : '-', con->unblank ? 'U' : '-',
- flags);
+ ((con->flags & CON_NBCON) || con->write) ? 'W' : '-',
+ con->unblank ? 'U' : '-', flags);
if (dev)
seq_printf(m, " %4d:%d", MAJOR(dev), MINOR(dev));
@@ -68,6 +69,7 @@ static int show_console_dev(struct seq_file *m, void *v)
}
static void *c_start(struct seq_file *m, loff_t *pos)
+ __acquires(&console_mutex)
{
struct console *con;
loff_t off = 0;
@@ -94,6 +96,7 @@ static void *c_next(struct seq_file *m, void *v, loff_t *pos)
}
static void c_stop(struct seq_file *m, void *v)
+ __releases(&console_mutex)
{
console_list_unlock();
}
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 4297287f6ca0..5e391cbca7a3 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -39,10 +39,8 @@ static int seq_show(struct seq_file *m, void *v)
spin_lock(&files->file_lock);
file = files_lookup_fd_locked(files, fd);
if (file) {
- struct fdtable *fdt = files_fdtable(files);
-
f_flags = file->f_flags;
- if (close_on_exec(fd, fdt))
+ if (close_on_exec(fd, files))
f_flags |= O_CLOEXEC;
get_file(file);
@@ -61,7 +59,7 @@ static int seq_show(struct seq_file *m, void *v)
real_mount(file->f_path.mnt)->mnt_id,
file_inode(file)->i_ino);
- /* show_fd_locks() never deferences files so a stale value is safe */
+ /* show_fd_locks() never dereferences files, so a stale value is safe */
show_fd_locks(m, file, files);
if (seq_has_overflowed(m))
goto out;
@@ -79,7 +77,7 @@ static int seq_fdinfo_open(struct inode *inode, struct file *file)
return single_open(file, seq_show, inode);
}
-/**
+/*
* Shared /proc/pid/fdinfo and /proc/pid/fdinfo/fd permission helper to ensure
* that the current task has PTRACE_MODE_READ in addition to the normal
* POSIX-like checks.
@@ -119,10 +117,12 @@ static bool tid_fd_mode(struct task_struct *task, unsigned fd, fmode_t *mode)
struct file *file;
rcu_read_lock();
- file = task_lookup_fd_rcu(task, fd);
- if (file)
- *mode = file->f_mode;
+ file = task_lookup_fdget_rcu(task, fd);
rcu_read_unlock();
+ if (file) {
+ *mode = file->f_mode;
+ fput(file);
+ }
return !!file;
}
@@ -220,8 +220,8 @@ static struct dentry *proc_fd_instantiate(struct dentry *dentry,
ei->op.proc_get_link = proc_fd_link;
tid_fd_update_inode(task, inode, data->mode);
- d_set_d_op(dentry, &tid_fd_dentry_operations);
- return d_splice_alias(inode, dentry);
+ return proc_splice_unmountable(inode, dentry,
+ &tid_fd_dentry_operations);
}
static struct dentry *proc_lookupfd_common(struct inode *dir,
@@ -265,12 +265,13 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
char name[10 + 1];
unsigned int len;
- f = task_lookup_next_fd_rcu(p, &fd);
+ f = task_lookup_next_fdget_rcu(p, &fd);
ctx->pos = fd + 2LL;
if (!f)
break;
data.mode = f->f_mode;
rcu_read_unlock();
+ fput(f);
data.fd = fd;
len = snprintf(name, sizeof(name), "%u", fd);
@@ -311,14 +312,14 @@ static int proc_readfd_count(struct inode *inode, loff_t *count)
return 0;
}
-static int proc_readfd(struct file *file, struct dir_context *ctx)
+static int proc_fd_iterate(struct file *file, struct dir_context *ctx)
{
return proc_readfd_common(file, ctx, proc_fd_instantiate);
}
const struct file_operations proc_fd_operations = {
.read = generic_read_dir,
- .iterate_shared = proc_readfd,
+ .iterate_shared = proc_fd_iterate,
.llseek = generic_file_llseek,
};
@@ -396,8 +397,8 @@ static struct dentry *proc_fdinfo_instantiate(struct dentry *dentry,
inode->i_fop = &proc_fdinfo_file_operations;
tid_fd_update_inode(task, inode, 0);
- d_set_d_op(dentry, &tid_fd_dentry_operations);
- return d_splice_alias(inode, dentry);
+ return proc_splice_unmountable(inode, dentry,
+ &tid_fd_dentry_operations);
}
static struct dentry *
@@ -406,7 +407,7 @@ proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, unsigned int flags)
return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
}
-static int proc_readfdinfo(struct file *file, struct dir_context *ctx)
+static int proc_fdinfo_iterate(struct file *file, struct dir_context *ctx)
{
return proc_readfd_common(file, ctx,
proc_fdinfo_instantiate);
@@ -420,6 +421,6 @@ const struct inode_operations proc_fdinfo_inode_operations = {
const struct file_operations proc_fdinfo_operations = {
.read = generic_read_dir,
- .iterate_shared = proc_readfdinfo,
+ .iterate_shared = proc_fdinfo_iterate,
.llseek = generic_file_llseek,
};
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 775ce0bcf08c..e21d99fa9263 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -202,8 +202,8 @@ int proc_alloc_inum(unsigned int *inum)
{
int i;
- i = ida_simple_get(&proc_inum_ida, 0, UINT_MAX - PROC_DYNAMIC_FIRST + 1,
- GFP_KERNEL);
+ i = ida_alloc_max(&proc_inum_ida, UINT_MAX - PROC_DYNAMIC_FIRST,
+ GFP_KERNEL);
if (i < 0)
return i;
@@ -213,7 +213,7 @@ int proc_alloc_inum(unsigned int *inum)
void proc_free_inum(unsigned int inum)
{
- ida_simple_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
+ ida_free(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
}
static int proc_misc_d_revalidate(struct dentry *dentry, unsigned int flags)
@@ -464,9 +464,9 @@ struct proc_dir_entry *proc_symlink(const char *name,
(S_IFLNK | S_IRUGO | S_IWUGO | S_IXUGO),1);
if (ent) {
- ent->data = kmalloc((ent->size=strlen(dest))+1, GFP_KERNEL);
+ ent->size = strlen(dest);
+ ent->data = kmemdup(dest, ent->size + 1, GFP_KERNEL);
if (ent->data) {
- strcpy((char*)ent->data,dest);
ent->proc_iops = &proc_link_inode_operations;
ent = proc_register(parent, ent);
} else {
@@ -557,10 +557,18 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
return p;
}
-static inline void pde_set_flags(struct proc_dir_entry *pde)
+static void pde_set_flags(struct proc_dir_entry *pde)
{
if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT)
pde->flags |= PROC_ENTRY_PERMANENT;
+ if (pde->proc_ops->proc_read_iter)
+ pde->flags |= PROC_ENTRY_proc_read_iter;
+#ifdef CONFIG_COMPAT
+ if (pde->proc_ops->proc_compat_ioctl)
+ pde->flags |= PROC_ENTRY_proc_compat_ioctl;
+#endif
+ if (pde->proc_ops->proc_lseek)
+ pde->flags |= PROC_ENTRY_proc_lseek;
}
struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
@@ -624,6 +632,7 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
p->proc_ops = &proc_seq_ops;
p->seq_ops = ops;
p->state_size = state_size;
+ pde_set_flags(p);
return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_seq_private);
@@ -654,6 +663,7 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
return NULL;
p->proc_ops = &proc_single_ops;
p->single_show = show;
+ pde_set_flags(p);
return proc_register(parent, p);
}
EXPORT_SYMBOL(proc_create_single_data);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 532dc9d240f7..129490151be1 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -30,7 +30,6 @@
static void proc_evict_inode(struct inode *inode)
{
- struct proc_dir_entry *de;
struct ctl_table_header *head;
struct proc_inode *ei = PROC_I(inode);
@@ -38,21 +37,12 @@ static void proc_evict_inode(struct inode *inode)
clear_inode(inode);
/* Stop tracking associated processes */
- if (ei->pid) {
+ if (ei->pid)
proc_pid_evict_inode(ei);
- ei->pid = NULL;
- }
-
- /* Let go of any associated proc directory entry */
- de = ei->pde;
- if (de) {
- pde_put(de);
- ei->pde = NULL;
- }
head = ei->sysctl;
if (head) {
- RCU_INIT_POINTER(ei->sysctl, NULL);
+ WRITE_ONCE(ei->sysctl, NULL);
proc_sys_evict_inode(inode, head);
}
}
@@ -80,6 +70,13 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
static void proc_free_inode(struct inode *inode)
{
+ struct proc_inode *ei = PROC_I(inode);
+
+ if (ei->pid)
+ put_pid(ei->pid);
+ /* Let go of any associated proc directory entry */
+ if (ei->pde)
+ pde_put(ei->pde);
kmem_cache_free(proc_inode_cachep, PROC_I(inode));
}
@@ -95,7 +92,7 @@ void __init proc_init_kmemcache(void)
proc_inode_cachep = kmem_cache_create("proc_inode_cache",
sizeof(struct proc_inode),
0, (SLAB_RECLAIM_ACCOUNT|
- SLAB_MEM_SPREAD|SLAB_ACCOUNT|
+ SLAB_ACCOUNT|
SLAB_PANIC),
init_once);
pde_opener_cache =
@@ -110,18 +107,15 @@ void __init proc_init_kmemcache(void)
void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock)
{
- struct inode *inode;
- struct proc_inode *ei;
struct hlist_node *node;
struct super_block *old_sb = NULL;
rcu_read_lock();
- for (;;) {
+ while ((node = hlist_first_rcu(inodes))) {
+ struct proc_inode *ei = hlist_entry(node, struct proc_inode, sibling_inodes);
struct super_block *sb;
- node = hlist_first_rcu(inodes);
- if (!node)
- break;
- ei = hlist_entry(node, struct proc_inode, sibling_inodes);
+ struct inode *inode;
+
spin_lock(lock);
hlist_del_init_rcu(&ei->sibling_inodes);
spin_unlock(lock);
@@ -309,9 +303,7 @@ static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter)
static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
- typeof_member(struct proc_ops, proc_read) read;
-
- read = pde->proc_ops->proc_read;
+ __auto_type read = pde->proc_ops->proc_read;
if (read)
return read(file, buf, count, ppos);
return -EIO;
@@ -333,9 +325,7 @@ static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count,
static ssize_t pde_write(struct proc_dir_entry *pde, struct file *file, const char __user *buf, size_t count, loff_t *ppos)
{
- typeof_member(struct proc_ops, proc_write) write;
-
- write = pde->proc_ops->proc_write;
+ __auto_type write = pde->proc_ops->proc_write;
if (write)
return write(file, buf, count, ppos);
return -EIO;
@@ -357,9 +347,7 @@ static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t
static __poll_t pde_poll(struct proc_dir_entry *pde, struct file *file, struct poll_table_struct *pts)
{
- typeof_member(struct proc_ops, proc_poll) poll;
-
- poll = pde->proc_ops->proc_poll;
+ __auto_type poll = pde->proc_ops->proc_poll;
if (poll)
return poll(file, pts);
return DEFAULT_POLLMASK;
@@ -381,9 +369,7 @@ static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts)
static long pde_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg)
{
- typeof_member(struct proc_ops, proc_ioctl) ioctl;
-
- ioctl = pde->proc_ops->proc_ioctl;
+ __auto_type ioctl = pde->proc_ops->proc_ioctl;
if (ioctl)
return ioctl(file, cmd, arg);
return -ENOTTY;
@@ -406,9 +392,7 @@ static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigne
#ifdef CONFIG_COMPAT
static long pde_compat_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg)
{
- typeof_member(struct proc_ops, proc_compat_ioctl) compat_ioctl;
-
- compat_ioctl = pde->proc_ops->proc_compat_ioctl;
+ __auto_type compat_ioctl = pde->proc_ops->proc_compat_ioctl;
if (compat_ioctl)
return compat_ioctl(file, cmd, arg);
return -ENOTTY;
@@ -430,9 +414,7 @@ static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned
static int pde_mmap(struct proc_dir_entry *pde, struct file *file, struct vm_area_struct *vma)
{
- typeof_member(struct proc_ops, proc_mmap) mmap;
-
- mmap = pde->proc_ops->proc_mmap;
+ __auto_type mmap = pde->proc_ops->proc_mmap;
if (mmap)
return mmap(file, vma);
return -EIO;
@@ -457,15 +439,13 @@ pde_get_unmapped_area(struct proc_dir_entry *pde, struct file *file, unsigned lo
unsigned long len, unsigned long pgoff,
unsigned long flags)
{
- typeof_member(struct proc_ops, proc_get_unmapped_area) get_area;
+ if (pde->proc_ops->proc_get_unmapped_area)
+ return pde->proc_ops->proc_get_unmapped_area(file, orig_addr, len, pgoff, flags);
- get_area = pde->proc_ops->proc_get_unmapped_area;
#ifdef CONFIG_MMU
- if (!get_area)
- get_area = current->mm->get_unmapped_area;
+ return mm_get_unmapped_area(current->mm, file, orig_addr, len, pgoff, flags);
#endif
- if (get_area)
- return get_area(file, orig_addr, len, pgoff, flags);
+
return orig_addr;
}
@@ -491,10 +471,9 @@ static int proc_reg_open(struct inode *inode, struct file *file)
struct proc_dir_entry *pde = PDE(inode);
int rv = 0;
typeof_member(struct proc_ops, proc_open) open;
- typeof_member(struct proc_ops, proc_release) release;
struct pde_opener *pdeo;
- if (!pde->proc_ops->proc_lseek)
+ if (!pde_has_proc_lseek(pde))
file->f_mode &= ~FMODE_LSEEK;
if (pde_is_permanent(pde)) {
@@ -518,7 +497,7 @@ static int proc_reg_open(struct inode *inode, struct file *file)
if (!use_pde(pde))
return -ENOENT;
- release = pde->proc_ops->proc_release;
+ __auto_type release = pde->proc_ops->proc_release;
if (release) {
pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL);
if (!pdeo) {
@@ -555,9 +534,7 @@ static int proc_reg_release(struct inode *inode, struct file *file)
struct pde_opener *pdeo;
if (pde_is_permanent(pde)) {
- typeof_member(struct proc_ops, proc_release) release;
-
- release = pde->proc_ops->proc_release;
+ __auto_type release = pde->proc_ops->proc_release;
if (release) {
return release(inode, file);
}
@@ -660,7 +637,7 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
inode->i_private = de->data;
inode->i_ino = de->low_ino;
- inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode);
+ simple_inode_init_ts(inode);
PROC_I(inode)->pde = de;
if (is_empty_pde(de)) {
make_empty_dir_inode(inode);
@@ -679,13 +656,13 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
if (S_ISREG(inode->i_mode)) {
inode->i_op = de->proc_iops;
- if (de->proc_ops->proc_read_iter)
+ if (pde_has_proc_read_iter(de))
inode->i_fop = &proc_iter_file_ops;
else
inode->i_fop = &proc_reg_file_ops;
#ifdef CONFIG_COMPAT
- if (de->proc_ops->proc_compat_ioctl) {
- if (de->proc_ops->proc_read_iter)
+ if (pde_has_proc_compat_ioctl(de)) {
+ if (pde_has_proc_read_iter(de))
inode->i_fop = &proc_iter_file_ops_compat;
else
inode->i_fop = &proc_reg_file_ops_compat;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 9a8f32f21ff5..edd4eb6fa12a 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -13,6 +13,7 @@
#include <linux/binfmts.h>
#include <linux/sched/coredump.h>
#include <linux/sched/task.h>
+#include <linux/mm.h>
struct ctl_table_header;
struct mempolicy;
@@ -84,6 +85,25 @@ static inline void pde_make_permanent(struct proc_dir_entry *pde)
pde->flags |= PROC_ENTRY_PERMANENT;
}
+static inline bool pde_has_proc_read_iter(const struct proc_dir_entry *pde)
+{
+ return pde->flags & PROC_ENTRY_proc_read_iter;
+}
+
+static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde)
+{
+#ifdef CONFIG_COMPAT
+ return pde->flags & PROC_ENTRY_proc_compat_ioctl;
+#else
+ return false;
+#endif
+}
+
+static inline bool pde_has_proc_lseek(const struct proc_dir_entry *pde)
+{
+ return pde->flags & PROC_ENTRY_proc_lseek;
+}
+
extern struct kmem_cache *proc_dir_entry_cache;
void pde_free(struct proc_dir_entry *pde);
@@ -92,7 +112,7 @@ union proc_op {
int (*proc_show)(struct seq_file *m,
struct pid_namespace *ns, struct pid *pid,
struct task_struct *task);
- const char *lsm;
+ int lsmid;
};
struct proc_inode {
@@ -142,6 +162,37 @@ unsigned name_to_int(const struct qstr *qstr);
/* Worst case buffer size needed for holding an integer. */
#define PROC_NUMBUF 13
+/**
+ * folio_precise_page_mapcount() - Number of mappings of this folio page.
+ * @folio: The folio.
+ * @page: The page.
+ *
+ * The number of present user page table entries that reference this page
+ * as tracked via the RMAP: either referenced directly (PTE) or as part of
+ * a larger area that covers this page (e.g., PMD).
+ *
+ * Use this function only for the calculation of existing statistics
+ * (USS, PSS, mapcount_max) and for debugging purposes (/proc/kpagecount).
+ *
+ * Do not add new users.
+ *
+ * Returns: The number of mappings of this folio page. 0 for
+ * folios that are not mapped to user space or are not tracked via the RMAP
+ * (e.g., shared zeropage).
+ */
+static inline int folio_precise_page_mapcount(struct folio *folio,
+ struct page *page)
+{
+ int mapcount = atomic_read(&page->_mapcount) + 1;
+
+ if (page_mapcount_is_type(mapcount))
+ mapcount = 0;
+ if (folio_test_large(folio))
+ mapcount += folio_entire_mapcount(folio);
+
+ return mapcount;
+}
+
/*
* array.c
*/
@@ -316,3 +367,16 @@ static inline void pde_force_lookup(struct proc_dir_entry *pde)
/* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
pde->proc_dops = &proc_net_dentry_ops;
}
+
+/*
+ * Add a new procfs dentry that can't serve as a mountpoint. That should
+ * encompass anything that is ephemeral and can just disappear while the
+ * process is still around.
+ */
+static inline struct dentry *proc_splice_unmountable(struct inode *inode,
+ struct dentry *dentry, const struct dentry_operations *d_ops)
+{
+ d_set_d_op(dentry, d_ops);
+ dont_mount(dentry);
+ return d_splice_alias(inode, dentry);
+}
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 1127457d0fcb..e376f48c4b8b 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -10,7 +10,7 @@
* Safe accesses to vmalloc/direct-mapped discontiguous areas, Kanoj Sarcar <kanoj@sgi.com>
*/
-#include <linux/crash_core.h>
+#include <linux/vmcore_info.h>
#include <linux/mm.h>
#include <linux/proc_fs.h>
#include <linux/kcore.h>
@@ -249,7 +249,7 @@ static int kcore_ram_list(struct list_head *list)
int nid, ret;
unsigned long end_pfn;
- /* Not inialized....update now */
+ /* Not initialized....update now */
/* find out "max pfn" */
end_pfn = 0;
for_each_node_state(nid, N_MEMORY) {
@@ -563,7 +563,8 @@ static ssize_t read_kcore_iter(struct kiocb *iocb, struct iov_iter *iter)
* and explicitly excluded physical ranges.
*/
if (!page || PageOffline(page) ||
- is_page_hwpoison(page) || !pfn_is_ram(pfn)) {
+ is_page_hwpoison(page) || !pfn_is_ram(pfn) ||
+ pfn_is_unaccepted_memory(pfn)) {
if (iov_iter_zero(tsz, iter) != tsz) {
ret = -EFAULT;
goto out;
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 45af9a989d40..245171d9164b 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -89,8 +89,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
show_val_kb(m, "SwapTotal: ", i.totalswap);
show_val_kb(m, "SwapFree: ", i.freeswap);
#ifdef CONFIG_ZSWAP
- seq_printf(m, "Zswap: %8lu kB\n",
- (unsigned long)(zswap_pool_total_size >> 10));
+ show_val_kb(m, "Zswap: ", zswap_total_pages());
seq_printf(m, "Zswapped: %8lu kB\n",
(unsigned long)atomic_read(&zswap_stored_pages) <<
(PAGE_SHIFT - 10));
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index 4d3493579458..c6e7ebc63756 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -58,7 +58,7 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
if (file) {
seq_pad(m, ' ');
- seq_file_path(m, file, "");
+ seq_path(m, file_user_path(file), "");
}
seq_putc(m, '\n');
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 9223856c934b..a55f5acefa97 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -37,21 +37,19 @@ static inline unsigned long get_max_dump_pfn(void)
#endif
}
-/* /proc/kpagecount - an array exposing page counts
+/* /proc/kpagecount - an array exposing page mapcounts
*
* Each entry is a u64 representing the corresponding
- * physical page count.
+ * physical page mapcount.
*/
static ssize_t kpagecount_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
const unsigned long max_dump_pfn = get_max_dump_pfn();
u64 __user *out = (u64 __user *)buf;
- struct page *ppage;
unsigned long src = *ppos;
unsigned long pfn;
ssize_t ret = 0;
- u64 pcount;
pfn = src / KPMSIZE;
if (src & KPMMASK || count & KPMMASK)
@@ -61,18 +59,19 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
while (count > 0) {
+ struct page *page;
+ u64 mapcount = 0;
+
/*
* TODO: ZONE_DEVICE support requires to identify
* memmaps that were actually initialized.
*/
- ppage = pfn_to_online_page(pfn);
+ page = pfn_to_online_page(pfn);
+ if (page)
+ mapcount = folio_precise_page_mapcount(page_folio(page),
+ page);
- if (!ppage)
- pcount = 0;
- else
- pcount = page_mapcount(ppage);
-
- if (put_user(pcount, out)) {
+ if (put_user(mapcount, out)) {
ret = -EFAULT;
break;
}
@@ -107,10 +106,13 @@ static inline u64 kpf_copy_bit(u64 kflags, int ubit, int kbit)
return ((kflags >> kbit) & 1) << ubit;
}
-u64 stable_page_flags(struct page *page)
+u64 stable_page_flags(const struct page *page)
{
- u64 k;
- u64 u;
+ const struct folio *folio;
+ unsigned long k;
+ unsigned long mapping;
+ bool is_anon;
+ u64 u = 0;
/*
* pseudo flag: KPF_NOPAGE
@@ -118,48 +120,43 @@ u64 stable_page_flags(struct page *page)
*/
if (!page)
return 1 << KPF_NOPAGE;
+ folio = page_folio(page);
- k = page->flags;
- u = 0;
+ k = folio->flags;
+ mapping = (unsigned long)folio->mapping;
+ is_anon = mapping & PAGE_MAPPING_ANON;
/*
* pseudo flags for the well known (anonymous) memory mapped pages
*/
if (page_mapped(page))
u |= 1 << KPF_MMAP;
- if (PageAnon(page))
+ if (is_anon) {
u |= 1 << KPF_ANON;
- if (PageKsm(page))
- u |= 1 << KPF_KSM;
+ if (mapping & PAGE_MAPPING_KSM)
+ u |= 1 << KPF_KSM;
+ }
/*
* compound pages: export both head/tail info
* they together define a compound page's start/end pos and order
*/
- if (PageHead(page))
- u |= 1 << KPF_COMPOUND_HEAD;
- if (PageTail(page))
+ if (page == &folio->page)
+ u |= kpf_copy_bit(k, KPF_COMPOUND_HEAD, PG_head);
+ else
u |= 1 << KPF_COMPOUND_TAIL;
- if (PageHuge(page))
+ if (folio_test_hugetlb(folio))
u |= 1 << KPF_HUGE;
- /*
- * PageTransCompound can be true for non-huge compound pages (slab
- * pages or pages allocated by drivers with __GFP_COMP) because it
- * just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
- * to make sure a given page is a thp, not a non-huge compound page.
- */
- else if (PageTransCompound(page)) {
- struct page *head = compound_head(page);
-
- if (PageLRU(head) || PageAnon(head))
- u |= 1 << KPF_THP;
- else if (is_huge_zero_page(head)) {
- u |= 1 << KPF_ZERO_PAGE;
- u |= 1 << KPF_THP;
- }
- } else if (is_zero_pfn(page_to_pfn(page)))
+ else if (folio_test_large(folio) &&
+ folio_test_large_rmappable(folio)) {
+ /* Note: we indicate any THPs here, not just PMD-sized ones */
+ u |= 1 << KPF_THP;
+ } else if (is_huge_zero_folio(folio)) {
u |= 1 << KPF_ZERO_PAGE;
-
+ u |= 1 << KPF_THP;
+ } else if (is_zero_folio(folio)) {
+ u |= 1 << KPF_ZERO_PAGE;
+ }
/*
* Caveats on high order pages: PG_buddy and PG_slab will only be set
@@ -174,17 +171,17 @@ u64 stable_page_flags(struct page *page)
u |= 1 << KPF_OFFLINE;
if (PageTable(page))
u |= 1 << KPF_PGTABLE;
+ if (folio_test_slab(folio))
+ u |= 1 << KPF_SLAB;
- if (page_is_idle(page))
+#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
+ u |= kpf_copy_bit(k, KPF_IDLE, PG_idle);
+#else
+ if (folio_test_idle(folio))
u |= 1 << KPF_IDLE;
+#endif
u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked);
-
- u |= kpf_copy_bit(k, KPF_SLAB, PG_slab);
- if (PageTail(page) && PageSlab(page))
- u |= 1 << KPF_SLAB;
-
- u |= kpf_copy_bit(k, KPF_ERROR, PG_error);
u |= kpf_copy_bit(k, KPF_DIRTY, PG_dirty);
u |= kpf_copy_bit(k, KPF_UPTODATE, PG_uptodate);
u |= kpf_copy_bit(k, KPF_WRITEBACK, PG_writeback);
@@ -194,7 +191,8 @@ u64 stable_page_flags(struct page *page)
u |= kpf_copy_bit(k, KPF_ACTIVE, PG_active);
u |= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim);
- if (PageSwapCache(page))
+#define SWAPCACHE ((1 << PG_swapbacked) | (1 << PG_swapcache))
+ if ((k & SWAPCACHE) == SWAPCACHE)
u |= 1 << KPF_SWAPCACHE;
u |= kpf_copy_bit(k, KPF_SWAPBACKED, PG_swapbacked);
@@ -202,21 +200,22 @@ u64 stable_page_flags(struct page *page)
u |= kpf_copy_bit(k, KPF_MLOCKED, PG_mlocked);
#ifdef CONFIG_MEMORY_FAILURE
- u |= kpf_copy_bit(k, KPF_HWPOISON, PG_hwpoison);
-#endif
-
-#ifdef CONFIG_ARCH_USES_PG_UNCACHED
- u |= kpf_copy_bit(k, KPF_UNCACHED, PG_uncached);
+ if (u & (1 << KPF_HUGE))
+ u |= kpf_copy_bit(k, KPF_HWPOISON, PG_hwpoison);
+ else
+ u |= kpf_copy_bit(page->flags, KPF_HWPOISON, PG_hwpoison);
#endif
u |= kpf_copy_bit(k, KPF_RESERVED, PG_reserved);
- u |= kpf_copy_bit(k, KPF_MAPPEDTODISK, PG_mappedtodisk);
+ u |= kpf_copy_bit(k, KPF_OWNER_2, PG_owner_2);
u |= kpf_copy_bit(k, KPF_PRIVATE, PG_private);
u |= kpf_copy_bit(k, KPF_PRIVATE_2, PG_private_2);
u |= kpf_copy_bit(k, KPF_OWNER_PRIVATE, PG_owner_priv_1);
u |= kpf_copy_bit(k, KPF_ARCH, PG_arch_1);
-#ifdef CONFIG_ARCH_USES_PG_ARCH_X
+#ifdef CONFIG_ARCH_USES_PG_ARCH_2
u |= kpf_copy_bit(k, KPF_ARCH_2, PG_arch_2);
+#endif
+#ifdef CONFIG_ARCH_USES_PG_ARCH_3
u |= kpf_copy_bit(k, KPF_ARCH_3, PG_arch_3);
#endif
@@ -228,7 +227,6 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf,
{
const unsigned long max_dump_pfn = get_max_dump_pfn();
u64 __user *out = (u64 __user *)buf;
- struct page *ppage;
unsigned long src = *ppos;
unsigned long pfn;
ssize_t ret = 0;
@@ -245,9 +243,9 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf,
* TODO: ZONE_DEVICE support requires to identify
* memmaps that were actually initialized.
*/
- ppage = pfn_to_online_page(pfn);
+ struct page *page = pfn_to_online_page(pfn);
- if (put_user(stable_page_flags(ppage), out)) {
+ if (put_user(stable_page_flags(page), out)) {
ret = -EFAULT;
break;
}
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 2ba31b6d68c0..52f0b75cbce2 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -135,6 +135,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_data);
* @parent: The parent directory in which to create.
* @ops: The seq_file ops with which to read the file.
* @write: The write method with which to 'modify' the file.
+ * @state_size: The size of the per-file private state to allocate.
* @data: Data for retrieval by pde_data().
*
* Create a network namespaced proc file in the @parent directory with the
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 071a71eb1a2d..e785db5fa499 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -21,7 +21,7 @@
#define list_for_each_table_entry(entry, header) \
entry = header->ctl_table; \
- for (size_t i = 0 ; i < header->ctl_table_size && entry->procname; ++i, entry++)
+ for (size_t i = 0 ; i < header->ctl_table_size; ++i, entry++)
static const struct dentry_operations proc_sys_dentry_operations;
static const struct file_operations proc_sys_file_operations;
@@ -29,9 +29,12 @@ static const struct inode_operations proc_sys_inode_operations;
static const struct file_operations proc_sys_dir_file_operations;
static const struct inode_operations proc_sys_dir_operations;
-/* Support for permanently empty directories */
+/*
+ * Support for permanently empty directories.
+ * Must be non-empty to avoid sharing an address with other tables.
+ */
static struct ctl_table sysctl_mount_point[] = {
- {.type = SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY }
+ { }
};
/**
@@ -44,18 +47,16 @@ static struct ctl_table sysctl_mount_point[] = {
*/
struct ctl_table_header *register_sysctl_mount_point(const char *path)
{
- return register_sysctl(path, sysctl_mount_point);
+ return register_sysctl_sz(path, sysctl_mount_point, 0);
}
EXPORT_SYMBOL(register_sysctl_mount_point);
-#define sysctl_is_perm_empty_ctl_table(tptr) \
- (tptr[0].type == SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY)
#define sysctl_is_perm_empty_ctl_header(hptr) \
- (sysctl_is_perm_empty_ctl_table(hptr->ctl_table))
+ (hptr->type == SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY)
#define sysctl_set_perm_empty_ctl_header(hptr) \
- (hptr->ctl_table[0].type = SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY)
+ (hptr->type = SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY)
#define sysctl_clear_perm_empty_ctl_header(hptr) \
- (hptr->ctl_table[0].type = SYSCTL_TABLE_TYPE_DEFAULT)
+ (hptr->type = SYSCTL_TABLE_TYPE_DEFAULT)
void proc_sys_poll_notify(struct ctl_table_poll *poll)
{
@@ -71,7 +72,6 @@ static struct ctl_table root_table[] = {
.procname = "",
.mode = S_IFDIR|S_IRUGO|S_IXUGO,
},
- { }
};
static struct ctl_table_root sysctl_table_root = {
.default_set.dir.header = {
@@ -211,6 +211,8 @@ static void init_header(struct ctl_table_header *head,
node++;
}
}
+ if (table == sysctl_mount_point)
+ sysctl_set_perm_empty_ctl_header(head);
}
static void erase_header(struct ctl_table_header *head)
@@ -233,8 +235,7 @@ static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header)
return -EROFS;
/* Am I creating a permanently empty directory? */
- if (header->ctl_table_size > 0 &&
- sysctl_is_perm_empty_ctl_table(header->ctl_table)) {
+ if (sysctl_is_perm_empty_ctl_header(header)) {
if (!RB_EMPTY_ROOT(&dir->root))
return -EINVAL;
sysctl_set_perm_empty_ctl_header(dir_h);
@@ -466,7 +467,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
head->count++;
spin_unlock(&sysctl_lock);
- inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode);
+ simple_inode_init_ts(inode);
inode->i_mode = table->mode;
if (!S_ISDIR(table->mode)) {
inode->i_mode |= S_IFREG;
@@ -533,13 +534,8 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
goto out;
}
- inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
- if (IS_ERR(inode)) {
- err = ERR_CAST(inode);
- goto out;
- }
-
d_set_d_op(dentry, &proc_sys_dentry_operations);
+ inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p);
err = d_splice_alias(inode, dentry);
out:
@@ -697,13 +693,8 @@ static bool proc_sys_fill_cache(struct file *file,
return false;
if (d_in_lookup(child)) {
struct dentry *res;
- inode = proc_sys_make_inode(dir->d_sb, head, table);
- if (IS_ERR(inode)) {
- d_lookup_done(child);
- dput(child);
- return false;
- }
d_set_d_op(child, &proc_sys_dentry_operations);
+ inode = proc_sys_make_inode(dir->d_sb, head, table);
res = d_splice_alias(inode, child);
d_lookup_done(child);
if (unlikely(res)) {
@@ -920,17 +911,21 @@ static int proc_sys_compare(const struct dentry *dentry,
struct ctl_table_header *head;
struct inode *inode;
- /* Although proc doesn't have negative dentries, rcu-walk means
- * that inode here can be NULL */
- /* AV: can it, indeed? */
- inode = d_inode_rcu(dentry);
- if (!inode)
- return 1;
if (name->len != len)
return 1;
if (memcmp(name->name, str, len))
return 1;
- head = rcu_dereference(PROC_I(inode)->sysctl);
+
+ // false positive is fine here - we'll recheck anyway
+ if (d_in_lookup(dentry))
+ return 0;
+
+ inode = d_inode_rcu(dentry);
+ // we just might have run into dentry in the middle of __dentry_kill()
+ if (!inode)
+ return 1;
+
+ head = READ_ONCE(PROC_I(inode)->sysctl);
return !head || !sysctl_is_seen(head);
}
@@ -963,14 +958,14 @@ static struct ctl_dir *new_dir(struct ctl_table_set *set,
char *new_name;
new = kzalloc(sizeof(*new) + sizeof(struct ctl_node) +
- sizeof(struct ctl_table)*2 + namelen + 1,
+ sizeof(struct ctl_table) + namelen + 1,
GFP_KERNEL);
if (!new)
return NULL;
node = (struct ctl_node *)(new + 1);
table = (struct ctl_table *)(node + 1);
- new_name = (char *)(table + 2);
+ new_name = (char *)(table + 1);
memcpy(new_name, name, namelen);
table[0].procname = new_name;
table[0].mode = S_IFDIR|S_IRUGO|S_IXUGO;
@@ -1105,6 +1100,7 @@ static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
static int sysctl_check_table_array(const char *path, struct ctl_table *table)
{
+ unsigned int extra;
int err = 0;
if ((table->proc_handler == proc_douintvec) ||
@@ -1116,6 +1112,19 @@ static int sysctl_check_table_array(const char *path, struct ctl_table *table)
if (table->proc_handler == proc_dou8vec_minmax) {
if (table->maxlen != sizeof(u8))
err |= sysctl_err(path, table, "array not allowed");
+
+ if (table->extra1) {
+ extra = *(unsigned int *) table->extra1;
+ if (extra > 255U)
+ err |= sysctl_err(path, table,
+ "range value too large for proc_dou8vec_minmax");
+ }
+ if (table->extra2) {
+ extra = *(unsigned int *) table->extra2;
+ if (extra > 255U)
+ err |= sysctl_err(path, table,
+ "range value too large for proc_dou8vec_minmax");
+ }
}
if (table->proc_handler == proc_dobool) {
@@ -1131,6 +1140,8 @@ static int sysctl_check_table(const char *path, struct ctl_table_header *header)
struct ctl_table *entry;
int err = 0;
list_for_each_table_entry(entry, header) {
+ if (!entry->procname)
+ err |= sysctl_err(path, entry, "procname is null");
if ((entry->proc_handler == proc_dostring) ||
(entry->proc_handler == proc_dobool) ||
(entry->proc_handler == proc_dointvec) ||
@@ -1166,18 +1177,16 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table_
struct ctl_table_header *links;
struct ctl_node *node;
char *link_name;
- int nr_entries, name_bytes;
+ int name_bytes;
name_bytes = 0;
- nr_entries = 0;
list_for_each_table_entry(entry, head) {
- nr_entries++;
name_bytes += strlen(entry->procname) + 1;
}
links = kzalloc(sizeof(struct ctl_table_header) +
- sizeof(struct ctl_node)*nr_entries +
- sizeof(struct ctl_table)*(nr_entries + 1) +
+ sizeof(struct ctl_node)*head->ctl_table_size +
+ sizeof(struct ctl_table)*head->ctl_table_size +
name_bytes,
GFP_KERNEL);
@@ -1185,8 +1194,8 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table_
return NULL;
node = (struct ctl_node *)(links + 1);
- link_table = (struct ctl_table *)(node + nr_entries);
- link_name = (char *)&link_table[nr_entries + 1];
+ link_table = (struct ctl_table *)(node + head->ctl_table_size);
+ link_name = (char *)(link_table + head->ctl_table_size);
link = link_table;
list_for_each_table_entry(entry, head) {
@@ -1200,7 +1209,7 @@ static struct ctl_table_header *new_links(struct ctl_dir *dir, struct ctl_table_
}
init_header(links, dir->header.root, dir->header.set, node, link_table,
head->ctl_table_size);
- links->nreg = nr_entries;
+ links->nreg = head->ctl_table_size;
return links;
}
@@ -1213,7 +1222,7 @@ static bool get_links(struct ctl_dir *dir,
struct ctl_table *entry, *link;
if (header->ctl_table_size == 0 ||
- sysctl_is_perm_empty_ctl_table(header->ctl_table))
+ sysctl_is_perm_empty_ctl_header(header))
return true;
/* Are there links available for every entry in table? */
@@ -1312,28 +1321,23 @@ static struct ctl_dir *sysctl_mkdir_p(struct ctl_dir *dir, const char *path)
* __register_sysctl_table - register a leaf sysctl table
* @set: Sysctl tree to register on
* @path: The path to the directory the sysctl table is in.
- * @table: the top-level table structure without any child. This table
- * should not be free'd after registration. So it should not be
- * used on stack. It can either be a global or dynamically allocated
- * by the caller and free'd later after sysctl unregistration.
+ *
+ * @table: the top-level table structure. This table should not be free'd
+ * after registration. So it should not be used on stack. It can either
+ * be a global or dynamically allocated by the caller and free'd later
+ * after sysctl unregistration.
* @table_size : The number of elements in table
*
* Register a sysctl table hierarchy. @table should be a filled in ctl_table
- * array. A completely 0 filled entry terminates the table.
+ * array.
*
* The members of the &struct ctl_table structure are used as follows:
- *
* procname - the name of the sysctl file under /proc/sys. Set to %NULL to not
* enter a sysctl file
- *
- * data - a pointer to data for use by proc_handler
- *
- * maxlen - the maximum size in bytes of the data
- *
- * mode - the file permissions for the /proc/sys file
- *
- * child - must be %NULL.
- *
+ * data - a pointer to data for use by proc_handler
+ * maxlen - the maximum size in bytes of the data
+ * mode - the file permissions for the /proc/sys file
+ * type - Defines the target type (described in struct definition)
* proc_handler - the text handler routine (described below)
*
* extra1, extra2 - extra pointers usable by the proc handler routines
@@ -1341,8 +1345,7 @@ static struct ctl_dir *sysctl_mkdir_p(struct ctl_dir *dir, const char *path)
* [0] https://lkml.kernel.org/87zgpte9o4.fsf@email.froward.int.ebiederm.org
*
* Leaf nodes in the sysctl tree will be represented by a single file
- * under /proc; non-leaf nodes (where child is not NULL) are not allowed,
- * sysctl_check_table() verifies this.
+ * under /proc; non-leaf nodes are not allowed.
*
* There must be a proc_handler routine for any terminal nodes.
* Several default handlers are available to cover common cases -
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 9191248f2dac..06a297a27ba3 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -188,7 +188,7 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
/* procfs dentries and inodes don't require IO to create */
- s->s_shrink.seeks = 0;
+ s->s_shrink->seeks = 0;
pde_get(&proc_root);
root_inode = proc_get_inode(s, &proc_root);
@@ -271,7 +271,7 @@ static void proc_kill_sb(struct super_block *sb)
kill_anon_super(sb);
put_pid_ns(fs_info->pid_ns);
- kfree(fs_info);
+ kfree_rcu(fs_info, rcu);
}
static struct file_system_type proc_fs_type = {
diff --git a/fs/proc/self.c b/fs/proc/self.c
index ecc4da8d265e..b46fbfd22681 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -46,7 +46,7 @@ int proc_setup_self(struct super_block *s)
struct inode *inode = new_inode(s);
if (inode) {
inode->i_ino = self_inum;
- inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode);
+ simple_inode_init_ts(inode);
inode->i_mode = S_IFLNK | S_IRWXUGO;
inode->i_uid = GLOBAL_ROOT_UID;
inode->i_gid = GLOBAL_ROOT_GID;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 59571737e167..2257bf52fb2a 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -20,6 +20,9 @@
#include <linux/shmem_fs.h>
#include <linux/uaccess.h>
#include <linux/pkeys.h>
+#include <linux/minmax.h>
+#include <linux/overflow.h>
+#include <linux/buildid.h>
#include <asm/elf.h>
#include <asm/tlb.h>
@@ -33,9 +36,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
unsigned long text, lib, swap, anon, file, shmem;
unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
- anon = get_mm_counter(mm, MM_ANONPAGES);
- file = get_mm_counter(mm, MM_FILEPAGES);
- shmem = get_mm_counter(mm, MM_SHMEMPAGES);
+ anon = get_mm_counter_sum(mm, MM_ANONPAGES);
+ file = get_mm_counter_sum(mm, MM_FILEPAGES);
+ shmem = get_mm_counter_sum(mm, MM_SHMEMPAGES);
/*
* Note: to minimize their overhead, mm maintains hiwater_vm and
@@ -56,7 +59,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
text = min(text, mm->exec_vm << PAGE_SHIFT);
lib = (mm->exec_vm << PAGE_SHIFT) - text;
- swap = get_mm_counter(mm, MM_SWAPENTS);
+ swap = get_mm_counter_sum(mm, MM_SWAPENTS);
SEQ_PUT_DEC("VmPeak:\t", hiwater_vm);
SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm);
SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm);
@@ -89,12 +92,12 @@ unsigned long task_statm(struct mm_struct *mm,
unsigned long *shared, unsigned long *text,
unsigned long *data, unsigned long *resident)
{
- *shared = get_mm_counter(mm, MM_FILEPAGES) +
- get_mm_counter(mm, MM_SHMEMPAGES);
+ *shared = get_mm_counter_sum(mm, MM_FILEPAGES) +
+ get_mm_counter_sum(mm, MM_SHMEMPAGES);
*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
>> PAGE_SHIFT;
*data = mm->data_vm + mm->stack_vm;
- *resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
+ *resident = *shared + get_mm_counter_sum(mm, MM_ANONPAGES);
return mm->total_vm;
}
@@ -237,6 +240,67 @@ static int do_maps_open(struct inode *inode, struct file *file,
sizeof(struct proc_maps_private));
}
+static void get_vma_name(struct vm_area_struct *vma,
+ const struct path **path,
+ const char **name,
+ const char **name_fmt)
+{
+ struct anon_vma_name *anon_name = vma->vm_mm ? anon_vma_name(vma) : NULL;
+
+ *name = NULL;
+ *path = NULL;
+ *name_fmt = NULL;
+
+ /*
+ * Print the dentry name for named mappings, and a
+ * special [heap] marker for the heap:
+ */
+ if (vma->vm_file) {
+ /*
+ * If user named this anon shared memory via
+ * prctl(PR_SET_VMA ..., use the provided name.
+ */
+ if (anon_name) {
+ *name_fmt = "[anon_shmem:%s]";
+ *name = anon_name->name;
+ } else {
+ *path = file_user_path(vma->vm_file);
+ }
+ return;
+ }
+
+ if (vma->vm_ops && vma->vm_ops->name) {
+ *name = vma->vm_ops->name(vma);
+ if (*name)
+ return;
+ }
+
+ *name = arch_vma_name(vma);
+ if (*name)
+ return;
+
+ if (!vma->vm_mm) {
+ *name = "[vdso]";
+ return;
+ }
+
+ if (vma_is_initial_heap(vma)) {
+ *name = "[heap]";
+ return;
+ }
+
+ if (vma_is_initial_stack(vma)) {
+ *name = "[stack]";
+ return;
+ }
+
+ if (anon_name) {
+ *name_fmt = "[anon:%s]";
+ *name = anon_name->name;
+ return;
+ }
+}
+
static void show_vma_header_prefix(struct seq_file *m,
unsigned long start, unsigned long end,
vm_flags_t flags, unsigned long long pgoff,
@@ -260,18 +324,17 @@ static void show_vma_header_prefix(struct seq_file *m,
static void
show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
{
- struct anon_vma_name *anon_name = NULL;
- struct mm_struct *mm = vma->vm_mm;
- struct file *file = vma->vm_file;
+ const struct path *path;
+ const char *name_fmt, *name;
vm_flags_t flags = vma->vm_flags;
unsigned long ino = 0;
unsigned long long pgoff = 0;
unsigned long start, end;
dev_t dev = 0;
- const char *name = NULL;
- if (file) {
- struct inode *inode = file_inode(vma->vm_file);
+ if (vma->vm_file) {
+ const struct inode *inode = file_user_inode(vma->vm_file);
+
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
@@ -280,57 +343,15 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
start = vma->vm_start;
end = vma->vm_end;
show_vma_header_prefix(m, start, end, flags, pgoff, dev, ino);
- if (mm)
- anon_name = anon_vma_name(vma);
- /*
- * Print the dentry name for named mappings, and a
- * special [heap] marker for the heap:
- */
- if (file) {
+ get_vma_name(vma, &path, &name, &name_fmt);
+ if (path) {
seq_pad(m, ' ');
- /*
- * If user named this anon shared memory via
- * prctl(PR_SET_VMA ..., use the provided name.
- */
- if (anon_name)
- seq_printf(m, "[anon_shmem:%s]", anon_name->name);
- else
- seq_file_path(m, file, "\n");
- goto done;
- }
-
- if (vma->vm_ops && vma->vm_ops->name) {
- name = vma->vm_ops->name(vma);
- if (name)
- goto done;
- }
-
- name = arch_vma_name(vma);
- if (!name) {
- if (!mm) {
- name = "[vdso]";
- goto done;
- }
-
- if (vma_is_initial_heap(vma)) {
- name = "[heap]";
- goto done;
- }
-
- if (vma_is_initial_stack(vma)) {
- name = "[stack]";
- goto done;
- }
-
- if (anon_name) {
- seq_pad(m, ' ');
- seq_printf(m, "[anon:%s]", anon_name->name);
- }
- }
-
-done:
- if (name) {
+ seq_path(m, path, "\n");
+ } else if (name_fmt) {
+ seq_pad(m, ' ');
+ seq_printf(m, name_fmt, name);
+ } else if (name) {
seq_pad(m, ' ');
seq_puts(m, name);
}
@@ -355,11 +376,253 @@ static int pid_maps_open(struct inode *inode, struct file *file)
return do_maps_open(inode, file, &proc_pid_maps_op);
}
+#define PROCMAP_QUERY_VMA_FLAGS ( \
+ PROCMAP_QUERY_VMA_READABLE | \
+ PROCMAP_QUERY_VMA_WRITABLE | \
+ PROCMAP_QUERY_VMA_EXECUTABLE | \
+ PROCMAP_QUERY_VMA_SHARED \
+)
+
+#define PROCMAP_QUERY_VALID_FLAGS_MASK ( \
+ PROCMAP_QUERY_COVERING_OR_NEXT_VMA | \
+ PROCMAP_QUERY_FILE_BACKED_VMA | \
+ PROCMAP_QUERY_VMA_FLAGS \
+)
+
+static int query_vma_setup(struct mm_struct *mm)
+{
+ return mmap_read_lock_killable(mm);
+}
+
+static void query_vma_teardown(struct mm_struct *mm, struct vm_area_struct *vma)
+{
+ mmap_read_unlock(mm);
+}
+
+static struct vm_area_struct *query_vma_find_by_addr(struct mm_struct *mm, unsigned long addr)
+{
+ return find_vma(mm, addr);
+}
+
+static struct vm_area_struct *query_matching_vma(struct mm_struct *mm,
+ unsigned long addr, u32 flags)
+{
+ struct vm_area_struct *vma;
+
+next_vma:
+ vma = query_vma_find_by_addr(mm, addr);
+ if (!vma)
+ goto no_vma;
+
+ /* user requested only file-backed VMA, keep iterating */
+ if ((flags & PROCMAP_QUERY_FILE_BACKED_VMA) && !vma->vm_file)
+ goto skip_vma;
+
+ /* VMA permissions should satisfy query flags */
+ if (flags & PROCMAP_QUERY_VMA_FLAGS) {
+ u32 perm = 0;
+
+ if (flags & PROCMAP_QUERY_VMA_READABLE)
+ perm |= VM_READ;
+ if (flags & PROCMAP_QUERY_VMA_WRITABLE)
+ perm |= VM_WRITE;
+ if (flags & PROCMAP_QUERY_VMA_EXECUTABLE)
+ perm |= VM_EXEC;
+ if (flags & PROCMAP_QUERY_VMA_SHARED)
+ perm |= VM_MAYSHARE;
+
+ if ((vma->vm_flags & perm) != perm)
+ goto skip_vma;
+ }
+
+ /* found covering VMA or user is OK with the matching next VMA */
+ if ((flags & PROCMAP_QUERY_COVERING_OR_NEXT_VMA) || vma->vm_start <= addr)
+ return vma;
+
+skip_vma:
+ /*
+ * If the user needs closest matching VMA, keep iterating.
+ */
+ addr = vma->vm_end;
+ if (flags & PROCMAP_QUERY_COVERING_OR_NEXT_VMA)
+ goto next_vma;
+
+no_vma:
+ return ERR_PTR(-ENOENT);
+}
+
+static int do_procmap_query(struct proc_maps_private *priv, void __user *uarg)
+{
+ struct procmap_query karg;
+ struct vm_area_struct *vma;
+ struct mm_struct *mm;
+ const char *name = NULL;
+ char build_id_buf[BUILD_ID_SIZE_MAX], *name_buf = NULL;
+ __u64 usize;
+ int err;
+
+ if (copy_from_user(&usize, (void __user *)uarg, sizeof(usize)))
+ return -EFAULT;
+ /* argument struct can never be that large, reject abuse */
+ if (usize > PAGE_SIZE)
+ return -E2BIG;
+ /* argument struct should have at least query_flags and query_addr fields */
+ if (usize < offsetofend(struct procmap_query, query_addr))
+ return -EINVAL;
+ err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize);
+ if (err)
+ return err;
+
+ /* reject unknown flags */
+ if (karg.query_flags & ~PROCMAP_QUERY_VALID_FLAGS_MASK)
+ return -EINVAL;
+ /* either both buffer address and size are set, or both should be zero */
+ if (!!karg.vma_name_size != !!karg.vma_name_addr)
+ return -EINVAL;
+ if (!!karg.build_id_size != !!karg.build_id_addr)
+ return -EINVAL;
+
+ mm = priv->mm;
+ if (!mm || !mmget_not_zero(mm))
+ return -ESRCH;
+
+ err = query_vma_setup(mm);
+ if (err) {
+ mmput(mm);
+ return err;
+ }
+
+ vma = query_matching_vma(mm, karg.query_addr, karg.query_flags);
+ if (IS_ERR(vma)) {
+ err = PTR_ERR(vma);
+ vma = NULL;
+ goto out;
+ }
+
+ karg.vma_start = vma->vm_start;
+ karg.vma_end = vma->vm_end;
+
+ karg.vma_flags = 0;
+ if (vma->vm_flags & VM_READ)
+ karg.vma_flags |= PROCMAP_QUERY_VMA_READABLE;
+ if (vma->vm_flags & VM_WRITE)
+ karg.vma_flags |= PROCMAP_QUERY_VMA_WRITABLE;
+ if (vma->vm_flags & VM_EXEC)
+ karg.vma_flags |= PROCMAP_QUERY_VMA_EXECUTABLE;
+ if (vma->vm_flags & VM_MAYSHARE)
+ karg.vma_flags |= PROCMAP_QUERY_VMA_SHARED;
+
+ karg.vma_page_size = vma_kernel_pagesize(vma);
+
+ if (vma->vm_file) {
+ const struct inode *inode = file_user_inode(vma->vm_file);
+
+ karg.vma_offset = ((__u64)vma->vm_pgoff) << PAGE_SHIFT;
+ karg.dev_major = MAJOR(inode->i_sb->s_dev);
+ karg.dev_minor = MINOR(inode->i_sb->s_dev);
+ karg.inode = inode->i_ino;
+ } else {
+ karg.vma_offset = 0;
+ karg.dev_major = 0;
+ karg.dev_minor = 0;
+ karg.inode = 0;
+ }
+
+ if (karg.build_id_size) {
+ __u32 build_id_sz;
+
+ err = build_id_parse(vma, build_id_buf, &build_id_sz);
+ if (err) {
+ karg.build_id_size = 0;
+ } else {
+ if (karg.build_id_size < build_id_sz) {
+ err = -ENAMETOOLONG;
+ goto out;
+ }
+ karg.build_id_size = build_id_sz;
+ }
+ }
+
+ if (karg.vma_name_size) {
+ size_t name_buf_sz = min_t(size_t, PATH_MAX, karg.vma_name_size);
+ const struct path *path;
+ const char *name_fmt;
+ size_t name_sz = 0;
+
+ get_vma_name(vma, &path, &name, &name_fmt);
+
+ if (path || name_fmt || name) {
+ name_buf = kmalloc(name_buf_sz, GFP_KERNEL);
+ if (!name_buf) {
+ err = -ENOMEM;
+ goto out;
+ }
+ }
+ if (path) {
+ name = d_path(path, name_buf, name_buf_sz);
+ if (IS_ERR(name)) {
+ err = PTR_ERR(name);
+ goto out;
+ }
+ name_sz = name_buf + name_buf_sz - name;
+ } else if (name || name_fmt) {
+ name_sz = 1 + snprintf(name_buf, name_buf_sz, name_fmt ?: "%s", name);
+ name = name_buf;
+ }
+ if (name_sz > name_buf_sz) {
+ err = -ENAMETOOLONG;
+ goto out;
+ }
+ karg.vma_name_size = name_sz;
+ }
+
+ /* unlock vma or mmap_lock, and put mm_struct before copying data to user */
+ query_vma_teardown(mm, vma);
+ mmput(mm);
+
+ if (karg.vma_name_size && copy_to_user(u64_to_user_ptr(karg.vma_name_addr),
+ name, karg.vma_name_size)) {
+ kfree(name_buf);
+ return -EFAULT;
+ }
+ kfree(name_buf);
+
+ if (karg.build_id_size && copy_to_user(u64_to_user_ptr(karg.build_id_addr),
+ build_id_buf, karg.build_id_size))
+ return -EFAULT;
+
+ if (copy_to_user(uarg, &karg, min_t(size_t, sizeof(karg), usize)))
+ return -EFAULT;
+
+ return 0;
+
+out:
+ query_vma_teardown(mm, vma);
+ mmput(mm);
+ kfree(name_buf);
+ return err;
+}
+
+static long procfs_procmap_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct seq_file *seq = file->private_data;
+ struct proc_maps_private *priv = seq->private;
+
+ switch (cmd) {
+ case PROCMAP_QUERY:
+ return do_procmap_query(priv, (void __user *)arg);
+ default:
+ return -ENOIOCTLCMD;
+ }
+}
+
const struct file_operations proc_pid_maps_operations = {
.open = pid_maps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = proc_map_release,
+ .unlocked_ioctl = procfs_procmap_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
};
/*
@@ -408,14 +671,14 @@ struct mem_size_stats {
};
static void smaps_page_accumulate(struct mem_size_stats *mss,
- struct page *page, unsigned long size, unsigned long pss,
+ struct folio *folio, unsigned long size, unsigned long pss,
bool dirty, bool locked, bool private)
{
mss->pss += pss;
- if (PageAnon(page))
+ if (folio_test_anon(folio))
mss->pss_anon += pss;
- else if (PageSwapBacked(page))
+ else if (folio_test_swapbacked(folio))
mss->pss_shmem += pss;
else
mss->pss_file += pss;
@@ -423,7 +686,7 @@ static void smaps_page_accumulate(struct mem_size_stats *mss,
if (locked)
mss->pss_locked += pss;
- if (dirty || PageDirty(page)) {
+ if (dirty || folio_test_dirty(folio)) {
mss->pss_dirty += pss;
if (private)
mss->private_dirty += size;
@@ -439,8 +702,9 @@ static void smaps_page_accumulate(struct mem_size_stats *mss,
static void smaps_account(struct mem_size_stats *mss, struct page *page,
bool compound, bool young, bool dirty, bool locked,
- bool migration)
+ bool present)
{
+ struct folio *folio = page_folio(page);
int i, nr = compound ? compound_nr(page) : 1;
unsigned long size = nr * PAGE_SIZE;
@@ -448,47 +712,53 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
* First accumulate quantities that depend only on |size| and the type
* of the compound page.
*/
- if (PageAnon(page)) {
+ if (folio_test_anon(folio)) {
mss->anonymous += size;
- if (!PageSwapBacked(page) && !dirty && !PageDirty(page))
+ if (!folio_test_swapbacked(folio) && !dirty &&
+ !folio_test_dirty(folio))
mss->lazyfree += size;
}
- if (PageKsm(page))
+ if (folio_test_ksm(folio))
mss->ksm += size;
mss->resident += size;
/* Accumulate the size in pages that have been accessed. */
- if (young || page_is_young(page) || PageReferenced(page))
+ if (young || folio_test_young(folio) || folio_test_referenced(folio))
mss->referenced += size;
/*
* Then accumulate quantities that may depend on sharing, or that may
* differ page-by-page.
*
- * page_count(page) == 1 guarantees the page is mapped exactly once.
- * If any subpage of the compound page mapped with PTE it would elevate
- * page_count().
+ * refcount == 1 for present entries guarantees that the folio is mapped
+ * exactly once. For large folios this implies that exactly one
+ * PTE/PMD/... maps (a part of) this folio.
+ *
+ * Treat all non-present entries (where relying on the mapcount and
+ * refcount doesn't make sense) as "maybe shared, but not sure how
+ * often". We treat device private entries as being fake-present.
*
- * The page_mapcount() is called to get a snapshot of the mapcount.
- * Without holding the page lock this snapshot can be slightly wrong as
- * we cannot always read the mapcount atomically. It is not safe to
- * call page_mapcount() even with PTL held if the page is not mapped,
- * especially for migration entries. Treat regular migration entries
- * as mapcount == 1.
+ * Note that it would not be safe to read the mapcount especially for
+ * pages referenced by migration entries, even with the PTL held.
*/
- if ((page_count(page) == 1) || migration) {
- smaps_page_accumulate(mss, page, size, size << PSS_SHIFT, dirty,
- locked, true);
+ if (folio_ref_count(folio) == 1 || !present) {
+ smaps_page_accumulate(mss, folio, size, size << PSS_SHIFT,
+ dirty, locked, present);
return;
}
+ /*
+ * We obtain a snapshot of the mapcount. Without holding the folio lock
+ * this snapshot can be slightly wrong as we cannot always read the
+ * mapcount atomically.
+ */
for (i = 0; i < nr; i++, page++) {
- int mapcount = page_mapcount(page);
+ int mapcount = folio_precise_page_mapcount(folio, page);
unsigned long pss = PAGE_SIZE << PSS_SHIFT;
if (mapcount >= 2)
pss /= mapcount;
- smaps_page_accumulate(mss, page, PAGE_SIZE, pss, dirty, locked,
- mapcount < 2);
+ smaps_page_accumulate(mss, folio, PAGE_SIZE, pss,
+ dirty, locked, mapcount < 2);
}
}
@@ -526,13 +796,14 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
struct vm_area_struct *vma = walk->vma;
bool locked = !!(vma->vm_flags & VM_LOCKED);
struct page *page = NULL;
- bool migration = false, young = false, dirty = false;
+ bool present = false, young = false, dirty = false;
pte_t ptent = ptep_get(pte);
if (pte_present(ptent)) {
page = vm_normal_page(vma, addr, ptent);
young = pte_young(ptent);
dirty = pte_dirty(ptent);
+ present = true;
} else if (is_swap_pte(ptent)) {
swp_entry_t swpent = pte_to_swp_entry(ptent);
@@ -550,8 +821,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT;
}
} else if (is_pfn_swap_entry(swpent)) {
- if (is_migration_entry(swpent))
- migration = true;
+ if (is_device_private_entry(swpent))
+ present = true;
page = pfn_swap_entry_to_page(swpent);
}
} else {
@@ -562,7 +833,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
if (!page)
return;
- smaps_account(mss, page, false, young, dirty, locked, migration);
+ smaps_account(mss, page, false, young, dirty, locked, present);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -573,31 +844,32 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
struct vm_area_struct *vma = walk->vma;
bool locked = !!(vma->vm_flags & VM_LOCKED);
struct page *page = NULL;
- bool migration = false;
+ bool present = false;
+ struct folio *folio;
if (pmd_present(*pmd)) {
page = vm_normal_page_pmd(vma, addr, *pmd);
+ present = true;
} else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) {
swp_entry_t entry = pmd_to_swp_entry(*pmd);
- if (is_migration_entry(entry)) {
- migration = true;
+ if (is_pfn_swap_entry(entry))
page = pfn_swap_entry_to_page(entry);
- }
}
if (IS_ERR_OR_NULL(page))
return;
- if (PageAnon(page))
+ folio = page_folio(page);
+ if (folio_test_anon(folio))
mss->anonymous_thp += HPAGE_PMD_SIZE;
- else if (PageSwapBacked(page))
+ else if (folio_test_swapbacked(folio))
mss->shmem_thp += HPAGE_PMD_SIZE;
- else if (is_zone_device_page(page))
+ else if (folio_is_zone_device(folio))
/* pass */;
else
mss->file_thp += HPAGE_PMD_SIZE;
smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd),
- locked, migration);
+ locked, present);
}
#else
static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
@@ -637,8 +909,15 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
{
/*
* Don't forget to update Documentation/ on changes.
+ *
+ * The length of the second argument of mnemonics[]
+ * needs to be 3 instead of previously set 2
+ * (i.e. from [BITS_PER_LONG][2] to [BITS_PER_LONG][3])
+ * to avoid spurious
+ * -Werror=unterminated-string-initialization warning
+ * with GCC 15
*/
- static const char mnemonics[BITS_PER_LONG][2] = {
+ static const char mnemonics[BITS_PER_LONG][3] = {
/*
* In case if we meet a flag we don't know about.
*/
@@ -689,7 +968,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
[ilog2(VM_PKEY_BIT0)] = "",
[ilog2(VM_PKEY_BIT1)] = "",
[ilog2(VM_PKEY_BIT2)] = "",
+#if VM_PKEY_BIT3
[ilog2(VM_PKEY_BIT3)] = "",
+#endif
#if VM_PKEY_BIT4
[ilog2(VM_PKEY_BIT4)] = "",
#endif
@@ -700,6 +981,12 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
#ifdef CONFIG_X86_USER_SHADOW_STACK
[ilog2(VM_SHADOW_STACK)] = "ss",
#endif
+#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32)
+ [ilog2(VM_DROPPABLE)] = "dp",
+#endif
+#ifdef CONFIG_64BIT
+ [ilog2(VM_SEALED)] = "sl",
+#endif
};
size_t i;
@@ -707,11 +994,8 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
for (i = 0; i < BITS_PER_LONG; i++) {
if (!mnemonics[i][0])
continue;
- if (vma->vm_flags & (1UL << i)) {
- seq_putc(m, mnemonics[i][0]);
- seq_putc(m, mnemonics[i][1]);
- seq_putc(m, ' ');
- }
+ if (vma->vm_flags & (1UL << i))
+ seq_printf(m, "%s ", mnemonics[i]);
}
seq_putc(m, '\n');
}
@@ -723,23 +1007,32 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = walk->vma;
- struct page *page = NULL;
- pte_t ptent = ptep_get(pte);
+ struct folio *folio = NULL;
+ bool present = false;
+ spinlock_t *ptl;
+ pte_t ptent;
+ ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
+ ptent = huge_ptep_get(walk->mm, addr, pte);
if (pte_present(ptent)) {
- page = vm_normal_page(vma, addr, ptent);
+ folio = page_folio(pte_page(ptent));
+ present = true;
} else if (is_swap_pte(ptent)) {
swp_entry_t swpent = pte_to_swp_entry(ptent);
if (is_pfn_swap_entry(swpent))
- page = pfn_swap_entry_to_page(swpent);
+ folio = pfn_swap_entry_folio(swpent);
}
- if (page) {
- if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte))
+
+ if (folio) {
+ /* We treat non-present entries as "maybe shared". */
+ if (!present || folio_likely_mapped_shared(folio) ||
+ hugetlb_pmd_shared(pte))
mss->shared_hugetlb += huge_page_size(hstate_vma(vma));
else
mss->private_hugetlb += huge_page_size(hstate_vma(vma));
}
+ spin_unlock(ptl);
return 0;
}
#else
@@ -849,9 +1142,7 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss,
static int show_smap(struct seq_file *m, void *v)
{
struct vm_area_struct *vma = v;
- struct mem_size_stats mss;
-
- memset(&mss, 0, sizeof(mss));
+ struct mem_size_stats mss = {};
smap_gather_stats(vma, &mss, 0);
@@ -865,7 +1156,8 @@ static int show_smap(struct seq_file *m, void *v)
__show_smap(m, &mss, false);
seq_printf(m, "THPeligible: %8u\n",
- hugepage_vma_check(vma, vma->vm_flags, true, false, true));
+ !!thp_vma_allowable_orders(vma, vma->vm_flags,
+ TVA_SMAPS | TVA_ENFORCE_SYSFS, THP_ORDERS_ALL));
if (arch_pkeys_enabled())
seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma));
@@ -877,7 +1169,7 @@ static int show_smap(struct seq_file *m, void *v)
static int show_smaps_rollup(struct seq_file *m, void *v)
{
struct proc_maps_private *priv = m->private;
- struct mem_size_stats mss;
+ struct mem_size_stats mss = {};
struct mm_struct *mm = priv->mm;
struct vm_area_struct *vma;
unsigned long vma_start = 0, last_vma_end = 0;
@@ -893,8 +1185,6 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
goto out_put_task;
}
- memset(&mss, 0, sizeof(mss));
-
ret = mmap_read_lock_killable(mm);
if (ret)
goto out_put_mm;
@@ -1083,7 +1373,7 @@ struct clear_refs_private {
static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
{
- struct page *page;
+ struct folio *folio;
if (!pte_write(pte))
return false;
@@ -1091,10 +1381,10 @@ static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr,
return false;
if (likely(!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)))
return false;
- page = vm_normal_page(vma, addr, pte);
- if (!page)
+ folio = vm_normal_folio(vma, addr, pte);
+ if (!folio)
return false;
- return page_maybe_dma_pinned(page);
+ return folio_maybe_dma_pinned(folio);
}
static inline void clear_soft_dirty(struct vm_area_struct *vma,
@@ -1166,7 +1456,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
struct vm_area_struct *vma = walk->vma;
pte_t *pte, ptent;
spinlock_t *ptl;
- struct page *page;
+ struct folio *folio;
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
@@ -1178,12 +1468,12 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
if (!pmd_present(*pmd))
goto out;
- page = pmd_page(*pmd);
+ folio = pmd_folio(*pmd);
/* Clear accessed and referenced bits. */
pmdp_test_and_clear_young(vma, addr, pmd);
- test_and_clear_page_young(page);
- ClearPageReferenced(page);
+ folio_test_clear_young(folio);
+ folio_clear_referenced(folio);
out:
spin_unlock(ptl);
return 0;
@@ -1205,14 +1495,14 @@ out:
if (!pte_present(ptent))
continue;
- page = vm_normal_page(vma, addr, ptent);
- if (!page)
+ folio = vm_normal_folio(vma, addr, ptent);
+ if (!folio)
continue;
/* Clear accessed and referenced bits. */
ptep_test_and_clear_young(vma, addr, pte);
- test_and_clear_page_young(page);
- ClearPageReferenced(page);
+ folio_test_clear_young(folio);
+ folio_clear_referenced(folio);
}
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
@@ -1251,14 +1541,13 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
struct task_struct *task;
- char buffer[PROC_NUMBUF];
+ char buffer[PROC_NUMBUF] = {};
struct mm_struct *mm;
struct vm_area_struct *vma;
enum clear_refs_types type;
int itype;
int rv;
- memset(buffer, 0, sizeof(buffer));
if (count > sizeof(buffer) - 1)
count = sizeof(buffer) - 1;
if (copy_from_user(buffer, buf, count))
@@ -1411,6 +1700,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
{
u64 frame = 0, flags = 0;
struct page *page = NULL;
+ struct folio *folio;
if (pte_present(pte)) {
if (pm->show_pfn)
@@ -1448,10 +1738,14 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
flags |= PM_UFFD_WP;
}
- if (page && !PageAnon(page))
- flags |= PM_FILE;
- if (page && (flags & PM_PRESENT) && page_mapcount(page) == 1)
- flags |= PM_MMAP_EXCLUSIVE;
+ if (page) {
+ folio = page_folio(page);
+ if (!folio_test_anon(folio))
+ flags |= PM_FILE;
+ if ((flags & PM_PRESENT) &&
+ folio_precise_page_mapcount(folio, page) == 1)
+ flags |= PM_MMAP_EXCLUSIVE;
+ }
if (vma->vm_flags & VM_SOFTDIRTY)
flags |= PM_SOFT_DIRTY;
@@ -1474,6 +1768,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
u64 flags = 0, frame = 0;
pmd_t pmd = *pmdp;
struct page *page = NULL;
+ struct folio *folio = NULL;
if (vma->vm_flags & VM_SOFTDIRTY)
flags |= PM_SOFT_DIRTY;
@@ -1512,15 +1807,18 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
}
#endif
- if (page && !PageAnon(page))
- flags |= PM_FILE;
+ if (page) {
+ folio = page_folio(page);
+ if (!folio_test_anon(folio))
+ flags |= PM_FILE;
+ }
for (; addr != end; addr += PAGE_SIZE, idx++) {
- unsigned long cur_flags = flags;
+ u64 cur_flags = flags;
pagemap_entry_t pme;
- if (page && (flags & PM_PRESENT) &&
- page_mapcount(page + idx) == 1)
+ if (folio && (flags & PM_PRESENT) &&
+ folio_precise_page_mapcount(folio, page + idx) == 1)
cur_flags |= PM_MMAP_EXCLUSIVE;
pme = make_pme(frame, cur_flags);
@@ -1578,14 +1876,15 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask,
if (vma->vm_flags & VM_SOFTDIRTY)
flags |= PM_SOFT_DIRTY;
- pte = huge_ptep_get(ptep);
+ pte = huge_ptep_get(walk->mm, addr, ptep);
if (pte_present(pte)) {
- struct page *page = pte_page(pte);
+ struct folio *folio = page_folio(pte_page(pte));
- if (!PageAnon(page))
+ if (!folio_test_anon(folio))
flags |= PM_FILE;
- if (page_mapcount(page) == 1)
+ if (!folio_likely_mapped_shared(folio) &&
+ !hugetlb_pmd_shared(ptep))
flags |= PM_MMAP_EXCLUSIVE;
if (huge_pte_uffd_wp(pte))
@@ -1765,11 +2064,776 @@ static int pagemap_release(struct inode *inode, struct file *file)
return 0;
}
+#define PM_SCAN_CATEGORIES (PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | \
+ PAGE_IS_FILE | PAGE_IS_PRESENT | \
+ PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | \
+ PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY)
+#define PM_SCAN_FLAGS (PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC)
+
+struct pagemap_scan_private {
+ struct pm_scan_arg arg;
+ unsigned long masks_of_interest, cur_vma_category;
+ struct page_region *vec_buf;
+ unsigned long vec_buf_len, vec_buf_index, found_pages;
+ struct page_region __user *vec_out;
+};
+
+static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
+ struct vm_area_struct *vma,
+ unsigned long addr, pte_t pte)
+{
+ unsigned long categories = 0;
+
+ if (pte_present(pte)) {
+ struct page *page;
+
+ categories |= PAGE_IS_PRESENT;
+ if (!pte_uffd_wp(pte))
+ categories |= PAGE_IS_WRITTEN;
+
+ if (p->masks_of_interest & PAGE_IS_FILE) {
+ page = vm_normal_page(vma, addr, pte);
+ if (page && !PageAnon(page))
+ categories |= PAGE_IS_FILE;
+ }
+
+ if (is_zero_pfn(pte_pfn(pte)))
+ categories |= PAGE_IS_PFNZERO;
+ if (pte_soft_dirty(pte))
+ categories |= PAGE_IS_SOFT_DIRTY;
+ } else if (is_swap_pte(pte)) {
+ swp_entry_t swp;
+
+ categories |= PAGE_IS_SWAPPED;
+ if (!pte_swp_uffd_wp_any(pte))
+ categories |= PAGE_IS_WRITTEN;
+
+ if (p->masks_of_interest & PAGE_IS_FILE) {
+ swp = pte_to_swp_entry(pte);
+ if (is_pfn_swap_entry(swp) &&
+ !folio_test_anon(pfn_swap_entry_folio(swp)))
+ categories |= PAGE_IS_FILE;
+ }
+ if (pte_swp_soft_dirty(pte))
+ categories |= PAGE_IS_SOFT_DIRTY;
+ }
+
+ return categories;
+}
+
+static void make_uffd_wp_pte(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *pte, pte_t ptent)
+{
+ if (pte_present(ptent)) {
+ pte_t old_pte;
+
+ old_pte = ptep_modify_prot_start(vma, addr, pte);
+ ptent = pte_mkuffd_wp(old_pte);
+ ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent);
+ } else if (is_swap_pte(ptent)) {
+ ptent = pte_swp_mkuffd_wp(ptent);
+ set_pte_at(vma->vm_mm, addr, pte, ptent);
+ } else {
+ set_pte_at(vma->vm_mm, addr, pte,
+ make_pte_marker(PTE_MARKER_UFFD_WP));
+ }
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
+ struct vm_area_struct *vma,
+ unsigned long addr, pmd_t pmd)
+{
+ unsigned long categories = PAGE_IS_HUGE;
+
+ if (pmd_present(pmd)) {
+ struct page *page;
+
+ categories |= PAGE_IS_PRESENT;
+ if (!pmd_uffd_wp(pmd))
+ categories |= PAGE_IS_WRITTEN;
+
+ if (p->masks_of_interest & PAGE_IS_FILE) {
+ page = vm_normal_page_pmd(vma, addr, pmd);
+ if (page && !PageAnon(page))
+ categories |= PAGE_IS_FILE;
+ }
+
+ if (is_huge_zero_pmd(pmd))
+ categories |= PAGE_IS_PFNZERO;
+ if (pmd_soft_dirty(pmd))
+ categories |= PAGE_IS_SOFT_DIRTY;
+ } else if (is_swap_pmd(pmd)) {
+ swp_entry_t swp;
+
+ categories |= PAGE_IS_SWAPPED;
+ if (!pmd_swp_uffd_wp(pmd))
+ categories |= PAGE_IS_WRITTEN;
+ if (pmd_swp_soft_dirty(pmd))
+ categories |= PAGE_IS_SOFT_DIRTY;
+
+ if (p->masks_of_interest & PAGE_IS_FILE) {
+ swp = pmd_to_swp_entry(pmd);
+ if (is_pfn_swap_entry(swp) &&
+ !folio_test_anon(pfn_swap_entry_folio(swp)))
+ categories |= PAGE_IS_FILE;
+ }
+ }
+
+ return categories;
+}
+
+static void make_uffd_wp_pmd(struct vm_area_struct *vma,
+ unsigned long addr, pmd_t *pmdp)
+{
+ pmd_t old, pmd = *pmdp;
+
+ if (pmd_present(pmd)) {
+ old = pmdp_invalidate_ad(vma, addr, pmdp);
+ pmd = pmd_mkuffd_wp(old);
+ set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
+ } else if (is_migration_entry(pmd_to_swp_entry(pmd))) {
+ pmd = pmd_swp_mkuffd_wp(pmd);
+ set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
+ }
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#ifdef CONFIG_HUGETLB_PAGE
+static unsigned long pagemap_hugetlb_category(pte_t pte)
+{
+ unsigned long categories = PAGE_IS_HUGE;
+
+ /*
+ * According to pagemap_hugetlb_range(), file-backed HugeTLB
+ * page cannot be swapped. So PAGE_IS_FILE is not checked for
+ * swapped pages.
+ */
+ if (pte_present(pte)) {
+ categories |= PAGE_IS_PRESENT;
+ if (!huge_pte_uffd_wp(pte))
+ categories |= PAGE_IS_WRITTEN;
+ if (!PageAnon(pte_page(pte)))
+ categories |= PAGE_IS_FILE;
+ if (is_zero_pfn(pte_pfn(pte)))
+ categories |= PAGE_IS_PFNZERO;
+ if (pte_soft_dirty(pte))
+ categories |= PAGE_IS_SOFT_DIRTY;
+ } else if (is_swap_pte(pte)) {
+ categories |= PAGE_IS_SWAPPED;
+ if (!pte_swp_uffd_wp_any(pte))
+ categories |= PAGE_IS_WRITTEN;
+ if (pte_swp_soft_dirty(pte))
+ categories |= PAGE_IS_SOFT_DIRTY;
+ }
+
+ return categories;
+}
+
+static void make_uffd_wp_huge_pte(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t ptent)
+{
+ unsigned long psize;
+
+ if (is_hugetlb_entry_hwpoisoned(ptent) || is_pte_marker(ptent))
+ return;
+
+ psize = huge_page_size(hstate_vma(vma));
+
+ if (is_hugetlb_entry_migration(ptent))
+ set_huge_pte_at(vma->vm_mm, addr, ptep,
+ pte_swp_mkuffd_wp(ptent), psize);
+ else if (!huge_pte_none(ptent))
+ huge_ptep_modify_prot_commit(vma, addr, ptep, ptent,
+ huge_pte_mkuffd_wp(ptent));
+ else
+ set_huge_pte_at(vma->vm_mm, addr, ptep,
+ make_pte_marker(PTE_MARKER_UFFD_WP), psize);
+}
+#endif /* CONFIG_HUGETLB_PAGE */
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
+static void pagemap_scan_backout_range(struct pagemap_scan_private *p,
+ unsigned long addr, unsigned long end)
+{
+ struct page_region *cur_buf = &p->vec_buf[p->vec_buf_index];
+
+ if (cur_buf->start != addr)
+ cur_buf->end = addr;
+ else
+ cur_buf->start = cur_buf->end = 0;
+
+ p->found_pages -= (end - addr) / PAGE_SIZE;
+}
+#endif
+
+static bool pagemap_scan_is_interesting_page(unsigned long categories,
+ const struct pagemap_scan_private *p)
+{
+ categories ^= p->arg.category_inverted;
+ if ((categories & p->arg.category_mask) != p->arg.category_mask)
+ return false;
+ if (p->arg.category_anyof_mask && !(categories & p->arg.category_anyof_mask))
+ return false;
+
+ return true;
+}
+
+static bool pagemap_scan_is_interesting_vma(unsigned long categories,
+ const struct pagemap_scan_private *p)
+{
+ unsigned long required = p->arg.category_mask & PAGE_IS_WPALLOWED;
+
+ categories ^= p->arg.category_inverted;
+ if ((categories & required) != required)
+ return false;
+
+ return true;
+}
+
+static int pagemap_scan_test_walk(unsigned long start, unsigned long end,
+ struct mm_walk *walk)
+{
+ struct pagemap_scan_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+ unsigned long vma_category = 0;
+ bool wp_allowed = userfaultfd_wp_async(vma) &&
+ userfaultfd_wp_use_markers(vma);
+
+ if (!wp_allowed) {
+ /* User requested explicit failure over wp-async capability */
+ if (p->arg.flags & PM_SCAN_CHECK_WPASYNC)
+ return -EPERM;
+ /*
+ * User requires wr-protect, and allows silently skipping
+ * unsupported vmas.
+ */
+ if (p->arg.flags & PM_SCAN_WP_MATCHING)
+ return 1;
+ /*
+ * Then the request doesn't involve wr-protects at all,
+ * fall through to the rest checks, and allow vma walk.
+ */
+ }
+
+ if (vma->vm_flags & VM_PFNMAP)
+ return 1;
+
+ if (wp_allowed)
+ vma_category |= PAGE_IS_WPALLOWED;
+
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ vma_category |= PAGE_IS_SOFT_DIRTY;
+
+ if (!pagemap_scan_is_interesting_vma(vma_category, p))
+ return 1;
+
+ p->cur_vma_category = vma_category;
+
+ return 0;
+}
+
+static bool pagemap_scan_push_range(unsigned long categories,
+ struct pagemap_scan_private *p,
+ unsigned long addr, unsigned long end)
+{
+ struct page_region *cur_buf = &p->vec_buf[p->vec_buf_index];
+
+ /*
+ * When there is no output buffer provided at all, the sentinel values
+ * won't match here. There is no other way for `cur_buf->end` to be
+ * non-zero other than it being non-empty.
+ */
+ if (addr == cur_buf->end && categories == cur_buf->categories) {
+ cur_buf->end = end;
+ return true;
+ }
+
+ if (cur_buf->end) {
+ if (p->vec_buf_index >= p->vec_buf_len - 1)
+ return false;
+
+ cur_buf = &p->vec_buf[++p->vec_buf_index];
+ }
+
+ cur_buf->start = addr;
+ cur_buf->end = end;
+ cur_buf->categories = categories;
+
+ return true;
+}
+
+static int pagemap_scan_output(unsigned long categories,
+ struct pagemap_scan_private *p,
+ unsigned long addr, unsigned long *end)
+{
+ unsigned long n_pages, total_pages;
+ int ret = 0;
+
+ if (!p->vec_buf)
+ return 0;
+
+ categories &= p->arg.return_mask;
+
+ n_pages = (*end - addr) / PAGE_SIZE;
+ if (check_add_overflow(p->found_pages, n_pages, &total_pages) ||
+ total_pages > p->arg.max_pages) {
+ size_t n_too_much = total_pages - p->arg.max_pages;
+ *end -= n_too_much * PAGE_SIZE;
+ n_pages -= n_too_much;
+ ret = -ENOSPC;
+ }
+
+ if (!pagemap_scan_push_range(categories, p, addr, *end)) {
+ *end = addr;
+ n_pages = 0;
+ ret = -ENOSPC;
+ }
+
+ p->found_pages += n_pages;
+ if (ret)
+ p->arg.walk_end = *end;
+
+ return ret;
+}
+
+static int pagemap_scan_thp_entry(pmd_t *pmd, unsigned long start,
+ unsigned long end, struct mm_walk *walk)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ struct pagemap_scan_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+ unsigned long categories;
+ spinlock_t *ptl;
+ int ret = 0;
+
+ ptl = pmd_trans_huge_lock(pmd, vma);
+ if (!ptl)
+ return -ENOENT;
+
+ categories = p->cur_vma_category |
+ pagemap_thp_category(p, vma, start, *pmd);
+
+ if (!pagemap_scan_is_interesting_page(categories, p))
+ goto out_unlock;
+
+ ret = pagemap_scan_output(categories, p, start, &end);
+ if (start == end)
+ goto out_unlock;
+
+ if (~p->arg.flags & PM_SCAN_WP_MATCHING)
+ goto out_unlock;
+ if (~categories & PAGE_IS_WRITTEN)
+ goto out_unlock;
+
+ /*
+ * Break huge page into small pages if the WP operation
+ * needs to be performed on a portion of the huge page.
+ */
+ if (end != start + HPAGE_SIZE) {
+ spin_unlock(ptl);
+ split_huge_pmd(vma, pmd, start);
+ pagemap_scan_backout_range(p, start, end);
+ /* Report as if there was no THP */
+ return -ENOENT;
+ }
+
+ make_uffd_wp_pmd(vma, start, pmd);
+ flush_tlb_range(vma, start, end);
+out_unlock:
+ spin_unlock(ptl);
+ return ret;
+#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
+ return -ENOENT;
+#endif
+}
+
+static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start,
+ unsigned long end, struct mm_walk *walk)
+{
+ struct pagemap_scan_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+ unsigned long addr, flush_end = 0;
+ pte_t *pte, *start_pte;
+ spinlock_t *ptl;
+ int ret;
+
+ arch_enter_lazy_mmu_mode();
+
+ ret = pagemap_scan_thp_entry(pmd, start, end, walk);
+ if (ret != -ENOENT) {
+ arch_leave_lazy_mmu_mode();
+ return ret;
+ }
+
+ ret = 0;
+ start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl);
+ if (!pte) {
+ arch_leave_lazy_mmu_mode();
+ walk->action = ACTION_AGAIN;
+ return 0;
+ }
+
+ if ((p->arg.flags & PM_SCAN_WP_MATCHING) && !p->vec_out) {
+ /* Fast path for performing exclusive WP */
+ for (addr = start; addr != end; pte++, addr += PAGE_SIZE) {
+ pte_t ptent = ptep_get(pte);
+
+ if ((pte_present(ptent) && pte_uffd_wp(ptent)) ||
+ pte_swp_uffd_wp_any(ptent))
+ continue;
+ make_uffd_wp_pte(vma, addr, pte, ptent);
+ if (!flush_end)
+ start = addr;
+ flush_end = addr + PAGE_SIZE;
+ }
+ goto flush_and_return;
+ }
+
+ if (!p->arg.category_anyof_mask && !p->arg.category_inverted &&
+ p->arg.category_mask == PAGE_IS_WRITTEN &&
+ p->arg.return_mask == PAGE_IS_WRITTEN) {
+ for (addr = start; addr < end; pte++, addr += PAGE_SIZE) {
+ unsigned long next = addr + PAGE_SIZE;
+ pte_t ptent = ptep_get(pte);
+
+ if ((pte_present(ptent) && pte_uffd_wp(ptent)) ||
+ pte_swp_uffd_wp_any(ptent))
+ continue;
+ ret = pagemap_scan_output(p->cur_vma_category | PAGE_IS_WRITTEN,
+ p, addr, &next);
+ if (next == addr)
+ break;
+ if (~p->arg.flags & PM_SCAN_WP_MATCHING)
+ continue;
+ make_uffd_wp_pte(vma, addr, pte, ptent);
+ if (!flush_end)
+ start = addr;
+ flush_end = next;
+ }
+ goto flush_and_return;
+ }
+
+ for (addr = start; addr != end; pte++, addr += PAGE_SIZE) {
+ pte_t ptent = ptep_get(pte);
+ unsigned long categories = p->cur_vma_category |
+ pagemap_page_category(p, vma, addr, ptent);
+ unsigned long next = addr + PAGE_SIZE;
+
+ if (!pagemap_scan_is_interesting_page(categories, p))
+ continue;
+
+ ret = pagemap_scan_output(categories, p, addr, &next);
+ if (next == addr)
+ break;
+
+ if (~p->arg.flags & PM_SCAN_WP_MATCHING)
+ continue;
+ if (~categories & PAGE_IS_WRITTEN)
+ continue;
+
+ make_uffd_wp_pte(vma, addr, pte, ptent);
+ if (!flush_end)
+ start = addr;
+ flush_end = next;
+ }
+
+flush_and_return:
+ if (flush_end)
+ flush_tlb_range(vma, start, addr);
+
+ pte_unmap_unlock(start_pte, ptl);
+ arch_leave_lazy_mmu_mode();
+
+ cond_resched();
+ return ret;
+}
+
+#ifdef CONFIG_HUGETLB_PAGE
+static int pagemap_scan_hugetlb_entry(pte_t *ptep, unsigned long hmask,
+ unsigned long start, unsigned long end,
+ struct mm_walk *walk)
+{
+ struct pagemap_scan_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+ unsigned long categories;
+ spinlock_t *ptl;
+ int ret = 0;
+ pte_t pte;
+
+ if (~p->arg.flags & PM_SCAN_WP_MATCHING) {
+ /* Go the short route when not write-protecting pages. */
+
+ pte = huge_ptep_get(walk->mm, start, ptep);
+ categories = p->cur_vma_category | pagemap_hugetlb_category(pte);
+
+ if (!pagemap_scan_is_interesting_page(categories, p))
+ return 0;
+
+ return pagemap_scan_output(categories, p, start, &end);
+ }
+
+ i_mmap_lock_write(vma->vm_file->f_mapping);
+ ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, ptep);
+
+ pte = huge_ptep_get(walk->mm, start, ptep);
+ categories = p->cur_vma_category | pagemap_hugetlb_category(pte);
+
+ if (!pagemap_scan_is_interesting_page(categories, p))
+ goto out_unlock;
+
+ ret = pagemap_scan_output(categories, p, start, &end);
+ if (start == end)
+ goto out_unlock;
+
+ if (~categories & PAGE_IS_WRITTEN)
+ goto out_unlock;
+
+ if (end != start + HPAGE_SIZE) {
+ /* Partial HugeTLB page WP isn't possible. */
+ pagemap_scan_backout_range(p, start, end);
+ p->arg.walk_end = start;
+ ret = 0;
+ goto out_unlock;
+ }
+
+ make_uffd_wp_huge_pte(vma, start, ptep, pte);
+ flush_hugetlb_tlb_range(vma, start, end);
+
+out_unlock:
+ spin_unlock(ptl);
+ i_mmap_unlock_write(vma->vm_file->f_mapping);
+
+ return ret;
+}
+#else
+#define pagemap_scan_hugetlb_entry NULL
+#endif
+
+static int pagemap_scan_pte_hole(unsigned long addr, unsigned long end,
+ int depth, struct mm_walk *walk)
+{
+ struct pagemap_scan_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+ int ret, err;
+
+ if (!vma || !pagemap_scan_is_interesting_page(p->cur_vma_category, p))
+ return 0;
+
+ ret = pagemap_scan_output(p->cur_vma_category, p, addr, &end);
+ if (addr == end)
+ return ret;
+
+ if (~p->arg.flags & PM_SCAN_WP_MATCHING)
+ return ret;
+
+ err = uffd_wp_range(vma, addr, end - addr, true);
+ if (err < 0)
+ ret = err;
+
+ return ret;
+}
+
+static const struct mm_walk_ops pagemap_scan_ops = {
+ .test_walk = pagemap_scan_test_walk,
+ .pmd_entry = pagemap_scan_pmd_entry,
+ .pte_hole = pagemap_scan_pte_hole,
+ .hugetlb_entry = pagemap_scan_hugetlb_entry,
+};
+
+static int pagemap_scan_get_args(struct pm_scan_arg *arg,
+ unsigned long uarg)
+{
+ if (copy_from_user(arg, (void __user *)uarg, sizeof(*arg)))
+ return -EFAULT;
+
+ if (arg->size != sizeof(struct pm_scan_arg))
+ return -EINVAL;
+
+ /* Validate requested features */
+ if (arg->flags & ~PM_SCAN_FLAGS)
+ return -EINVAL;
+ if ((arg->category_inverted | arg->category_mask |
+ arg->category_anyof_mask | arg->return_mask) & ~PM_SCAN_CATEGORIES)
+ return -EINVAL;
+
+ arg->start = untagged_addr((unsigned long)arg->start);
+ arg->end = untagged_addr((unsigned long)arg->end);
+ arg->vec = untagged_addr((unsigned long)arg->vec);
+
+ /* Validate memory pointers */
+ if (!IS_ALIGNED(arg->start, PAGE_SIZE))
+ return -EINVAL;
+ if (!access_ok((void __user *)(long)arg->start, arg->end - arg->start))
+ return -EFAULT;
+ if (!arg->vec && arg->vec_len)
+ return -EINVAL;
+ if (UINT_MAX == SIZE_MAX && arg->vec_len > SIZE_MAX)
+ return -EINVAL;
+ if (arg->vec && !access_ok((void __user *)(long)arg->vec,
+ size_mul(arg->vec_len, sizeof(struct page_region))))
+ return -EFAULT;
+
+ /* Fixup default values */
+ arg->end = ALIGN(arg->end, PAGE_SIZE);
+ arg->walk_end = 0;
+ if (!arg->max_pages)
+ arg->max_pages = ULONG_MAX;
+
+ return 0;
+}
+
+static int pagemap_scan_writeback_args(struct pm_scan_arg *arg,
+ unsigned long uargl)
+{
+ struct pm_scan_arg __user *uarg = (void __user *)uargl;
+
+ if (copy_to_user(&uarg->walk_end, &arg->walk_end, sizeof(arg->walk_end)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int pagemap_scan_init_bounce_buffer(struct pagemap_scan_private *p)
+{
+ if (!p->arg.vec_len)
+ return 0;
+
+ p->vec_buf_len = min_t(size_t, PAGEMAP_WALK_SIZE >> PAGE_SHIFT,
+ p->arg.vec_len);
+ p->vec_buf = kmalloc_array(p->vec_buf_len, sizeof(*p->vec_buf),
+ GFP_KERNEL);
+ if (!p->vec_buf)
+ return -ENOMEM;
+
+ p->vec_buf->start = p->vec_buf->end = 0;
+ p->vec_out = (struct page_region __user *)(long)p->arg.vec;
+
+ return 0;
+}
+
+static long pagemap_scan_flush_buffer(struct pagemap_scan_private *p)
+{
+ const struct page_region *buf = p->vec_buf;
+ long n = p->vec_buf_index;
+
+ if (!p->vec_buf)
+ return 0;
+
+ if (buf[n].end != buf[n].start)
+ n++;
+
+ if (!n)
+ return 0;
+
+ if (copy_to_user(p->vec_out, buf, n * sizeof(*buf)))
+ return -EFAULT;
+
+ p->arg.vec_len -= n;
+ p->vec_out += n;
+
+ p->vec_buf_index = 0;
+ p->vec_buf_len = min_t(size_t, p->vec_buf_len, p->arg.vec_len);
+ p->vec_buf->start = p->vec_buf->end = 0;
+
+ return n;
+}
+
+static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
+{
+ struct pagemap_scan_private p = {0};
+ unsigned long walk_start;
+ size_t n_ranges_out = 0;
+ int ret;
+
+ ret = pagemap_scan_get_args(&p.arg, uarg);
+ if (ret)
+ return ret;
+
+ p.masks_of_interest = p.arg.category_mask | p.arg.category_anyof_mask |
+ p.arg.return_mask;
+ ret = pagemap_scan_init_bounce_buffer(&p);
+ if (ret)
+ return ret;
+
+ for (walk_start = p.arg.start; walk_start < p.arg.end;
+ walk_start = p.arg.walk_end) {
+ struct mmu_notifier_range range;
+ long n_out;
+
+ if (fatal_signal_pending(current)) {
+ ret = -EINTR;
+ break;
+ }
+
+ ret = mmap_read_lock_killable(mm);
+ if (ret)
+ break;
+
+ /* Protection change for the range is going to happen. */
+ if (p.arg.flags & PM_SCAN_WP_MATCHING) {
+ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0,
+ mm, walk_start, p.arg.end);
+ mmu_notifier_invalidate_range_start(&range);
+ }
+
+ ret = walk_page_range(mm, walk_start, p.arg.end,
+ &pagemap_scan_ops, &p);
+
+ if (p.arg.flags & PM_SCAN_WP_MATCHING)
+ mmu_notifier_invalidate_range_end(&range);
+
+ mmap_read_unlock(mm);
+
+ n_out = pagemap_scan_flush_buffer(&p);
+ if (n_out < 0)
+ ret = n_out;
+ else
+ n_ranges_out += n_out;
+
+ if (ret != -ENOSPC)
+ break;
+
+ if (p.arg.vec_len == 0 || p.found_pages == p.arg.max_pages)
+ break;
+ }
+
+ /* ENOSPC signifies early stop (buffer full) from the walk. */
+ if (!ret || ret == -ENOSPC)
+ ret = n_ranges_out;
+
+ /* The walk_end isn't set when ret is zero */
+ if (!p.arg.walk_end)
+ p.arg.walk_end = p.arg.end;
+ if (pagemap_scan_writeback_args(&p.arg, uarg))
+ ret = -EFAULT;
+
+ kfree(p.vec_buf);
+ return ret;
+}
+
+static long do_pagemap_cmd(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ struct mm_struct *mm = file->private_data;
+
+ switch (cmd) {
+ case PAGEMAP_SCAN:
+ return do_pagemap_scan(mm, arg);
+
+ default:
+ return -EINVAL;
+ }
+}
+
const struct file_operations proc_pagemap_operations = {
.llseek = mem_lseek, /* borrow this */
.read = pagemap_read,
.open = pagemap_open,
.release = pagemap_release,
+ .unlocked_ioctl = do_pagemap_cmd,
+ .compat_ioctl = do_pagemap_cmd,
};
#endif /* CONFIG_PROC_PAGE_MONITOR */
@@ -1794,28 +2858,29 @@ struct numa_maps_private {
static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty,
unsigned long nr_pages)
{
- int count = page_mapcount(page);
+ struct folio *folio = page_folio(page);
+ int count = folio_precise_page_mapcount(folio, page);
md->pages += nr_pages;
- if (pte_dirty || PageDirty(page))
+ if (pte_dirty || folio_test_dirty(folio))
md->dirty += nr_pages;
- if (PageSwapCache(page))
+ if (folio_test_swapcache(folio))
md->swapcache += nr_pages;
- if (PageActive(page) || PageUnevictable(page))
+ if (folio_test_active(folio) || folio_test_unevictable(folio))
md->active += nr_pages;
- if (PageWriteback(page))
+ if (folio_test_writeback(folio))
md->writeback += nr_pages;
- if (PageAnon(page))
+ if (folio_test_anon(folio))
md->anon += nr_pages;
if (count > md->mapcount_max)
md->mapcount_max = count;
- md->node[page_to_nid(page)] += nr_pages;
+ md->node[folio_nid(folio)] += nr_pages;
}
static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
@@ -1910,7 +2975,7 @@ 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);
+ pte_t huge_pte = huge_ptep_get(walk->mm, addr, pte);
struct numa_maps *md;
struct page *page;
@@ -1949,8 +3014,9 @@ static int show_numa_map(struct seq_file *m, void *v)
struct numa_maps *md = &numa_priv->md;
struct file *file = vma->vm_file;
struct mm_struct *mm = vma->vm_mm;
- struct mempolicy *pol;
char buffer[64];
+ struct mempolicy *pol;
+ pgoff_t ilx;
int nid;
if (!mm)
@@ -1959,7 +3025,7 @@ static int show_numa_map(struct seq_file *m, void *v)
/* Ensure we start with an empty set of numa_maps statistics. */
memset(md, 0, sizeof(*md));
- pol = __get_vma_policy(vma, vma->vm_start);
+ pol = __get_vma_policy(vma, vma->vm_start, &ilx);
if (pol) {
mpol_to_str(buffer, sizeof(buffer), pol);
mpol_cond_put(pol);
@@ -1971,7 +3037,7 @@ static int show_numa_map(struct seq_file *m, void *v)
if (file) {
seq_puts(m, " file=");
- seq_file_path(m, file, "\n\t= ");
+ seq_path(m, file_user_path(file), "\n\t= ");
} else if (vma_is_initial_heap(vma)) {
seq_puts(m, " heap");
} else if (vma_is_initial_stack(vma)) {
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 7cebd397cc26..bce674533000 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -157,7 +157,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
if (file) {
seq_pad(m, ' ');
- seq_file_path(m, file, "");
+ seq_path(m, file_user_path(file), "");
} else if (mm && vma_is_initial_stack(vma)) {
seq_pad(m, ' ');
seq_puts(m, "[stack]");
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
index 63ac1f93289f..0e5050d6ab64 100644
--- a/fs/proc/thread_self.c
+++ b/fs/proc/thread_self.c
@@ -46,7 +46,7 @@ int proc_setup_thread_self(struct super_block *s)
struct inode *inode = new_inode(s);
if (inode) {
inode->i_ino = thread_self_inum;
- inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode);
+ simple_inode_init_ts(inode);
inode->i_mode = S_IFLNK | S_IRWXUGO;
inode->i_uid = GLOBAL_ROOT_UID;
inode->i_gid = GLOBAL_ROOT_GID;
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 8319bcbe3ee3..387a7a176ad8 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -404,6 +404,8 @@ static ssize_t __read_vmcore(struct iov_iter *iter, loff_t *fpos)
if (!iov_iter_count(iter))
return acc;
}
+
+ cond_resched();
}
return acc;
@@ -1373,9 +1375,8 @@ static void vmcoredd_write_header(void *buf, struct vmcoredd_data *data,
vdd_hdr->n_descsz = size + sizeof(vdd_hdr->dump_name);
vdd_hdr->n_type = NT_VMCOREDD;
- strncpy((char *)vdd_hdr->name, VMCOREDD_NOTE_NAME,
- sizeof(vdd_hdr->name));
- memcpy(vdd_hdr->dump_name, data->dump_name, sizeof(vdd_hdr->dump_name));
+ strscpy_pad(vdd_hdr->name, VMCOREDD_NOTE_NAME);
+ strscpy_pad(vdd_hdr->dump_name, data->dump_name);
}
/**
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-29 17:40:40 +0300