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/array.c1
-rw-r--r--fs/proc/base.c24
-rw-r--r--fs/proc/inode.c2
-rw-r--r--fs/proc/meminfo.c1
-rw-r--r--fs/proc/nommu.c1
-rw-r--r--fs/proc/proc_sysctl.c149
-rw-r--r--fs/proc/root.c10
-rw-r--r--fs/proc/self.c2
-rw-r--r--fs/proc/task_mmu.c34
-rw-r--r--fs/proc/task_nommu.c18
-rw-r--r--fs/proc/thread_self.c2
-rw-r--r--fs/proc/vmcore.c1
13 files changed, 197 insertions, 50 deletions
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index 971a42f6357d..c930001056f9 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -66,7 +66,7 @@ config PROC_SYSCTL
depends on PROC_FS
select SYSCTL
default y
- ---help---
+ help
The sysctl interface provides a means of dynamically changing
certain kernel parameters and variables on the fly without requiring
a recompile of the kernel or reboot of the system. The primary
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 713ffac59bbb..55ecbeb3a721 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -92,7 +92,6 @@
#include <linux/user_namespace.h>
#include <linux/fs_struct.h>
-#include <asm/pgtable.h>
#include <asm/processor.h>
#include "internal.h"
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 066d9c0f4664..d86c0afc8a85 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2112,11 +2112,11 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
goto out;
if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) {
- status = down_read_killable(&mm->mmap_sem);
+ status = mmap_read_lock_killable(mm);
if (!status) {
exact_vma_exists = !!find_exact_vma(mm, vm_start,
vm_end);
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
}
}
@@ -2163,7 +2163,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path)
if (rc)
goto out_mmput;
- rc = down_read_killable(&mm->mmap_sem);
+ rc = mmap_read_lock_killable(mm);
if (rc)
goto out_mmput;
@@ -2174,7 +2174,7 @@ static int map_files_get_link(struct dentry *dentry, struct path *path)
path_get(path);
rc = 0;
}
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
out_mmput:
mmput(mm);
@@ -2264,7 +2264,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
goto out_put_task;
result = ERR_PTR(-EINTR);
- if (down_read_killable(&mm->mmap_sem))
+ if (mmap_read_lock_killable(mm))
goto out_put_mm;
result = ERR_PTR(-ENOENT);
@@ -2277,7 +2277,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
(void *)(unsigned long)vma->vm_file->f_mode);
out_no_vma:
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
out_put_mm:
mmput(mm);
out_put_task:
@@ -2322,7 +2322,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
if (!mm)
goto out_put_task;
- ret = down_read_killable(&mm->mmap_sem);
+ ret = mmap_read_lock_killable(mm);
if (ret) {
mmput(mm);
goto out_put_task;
@@ -2333,11 +2333,11 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
/*
* We need two passes here:
*
- * 1) Collect vmas of mapped files with mmap_sem taken
- * 2) Release mmap_sem and instantiate entries
+ * 1) Collect vmas of mapped files with mmap_lock taken
+ * 2) Release mmap_lock and instantiate entries
*
* otherwise we get lockdep complained, since filldir()
- * routine might require mmap_sem taken in might_fault().
+ * routine might require mmap_lock taken in might_fault().
*/
for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) {
@@ -2349,7 +2349,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
p = genradix_ptr_alloc(&fa, nr_files++, GFP_KERNEL);
if (!p) {
ret = -ENOMEM;
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
mmput(mm);
goto out_put_task;
}
@@ -2358,7 +2358,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
p->end = vma->vm_end;
p->mode = vma->vm_file->f_mode;
}
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
mmput(mm);
for (i = 0; i < nr_files; i++) {
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index f40c2532c057..28d6105e908e 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -617,7 +617,7 @@ const struct inode_operations proc_link_inode_operations = {
struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
{
- struct inode *inode = new_inode_pseudo(sb);
+ struct inode *inode = new_inode(sb);
if (inode) {
inode->i_ino = de->low_ino;
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index ecc63ce01be7..e9a6841fc25b 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -17,7 +17,6 @@
#include <linux/cma.h>
#endif
#include <asm/page.h>
-#include <asm/pgtable.h>
#include "internal.h"
void __attribute__((weak)) arch_report_meminfo(struct seq_file *m)
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index 14c2badb8fd9..13452b32e2bd 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -22,7 +22,6 @@
#include <linux/hugetlb.h>
#include <linux/vmalloc.h>
#include <linux/uaccess.h>
-#include <asm/pgtable.h>
#include <asm/tlb.h>
#include <asm/div64.h>
#include "internal.h"
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index df2143e05c57..42c5128c7d1c 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -14,6 +14,7 @@
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/bpf-cgroup.h>
+#include <linux/mount.h>
#include "internal.h"
static const struct dentry_operations proc_sys_dentry_operations;
@@ -564,6 +565,10 @@ static ssize_t proc_sys_call_handler(struct file *filp, void __user *ubuf,
if (!table->proc_handler)
goto out;
+ /* don't even try if the size is too large */
+ if (count > KMALLOC_MAX_SIZE)
+ return -ENOMEM;
+
if (write) {
kbuf = memdup_user_nul(ubuf, count);
if (IS_ERR(kbuf)) {
@@ -1703,3 +1708,147 @@ int __init proc_sys_init(void)
return sysctl_init();
}
+
+struct sysctl_alias {
+ const char *kernel_param;
+ const char *sysctl_param;
+};
+
+/*
+ * Historically some settings had both sysctl and a command line parameter.
+ * With the generic sysctl. parameter support, we can handle them at a single
+ * place and only keep the historical name for compatibility. This is not meant
+ * to add brand new aliases. When adding existing aliases, consider whether
+ * the possibly different moment of changing the value (e.g. from early_param
+ * to the moment do_sysctl_args() is called) is an issue for the specific
+ * parameter.
+ */
+static const struct sysctl_alias sysctl_aliases[] = {
+ {"hardlockup_all_cpu_backtrace", "kernel.hardlockup_all_cpu_backtrace" },
+ {"hung_task_panic", "kernel.hung_task_panic" },
+ {"numa_zonelist_order", "vm.numa_zonelist_order" },
+ {"softlockup_all_cpu_backtrace", "kernel.softlockup_all_cpu_backtrace" },
+ {"softlockup_panic", "kernel.softlockup_panic" },
+ { }
+};
+
+static const char *sysctl_find_alias(char *param)
+{
+ const struct sysctl_alias *alias;
+
+ for (alias = &sysctl_aliases[0]; alias->kernel_param != NULL; alias++) {
+ if (strcmp(alias->kernel_param, param) == 0)
+ return alias->sysctl_param;
+ }
+
+ return NULL;
+}
+
+/* Set sysctl value passed on kernel command line. */
+static int process_sysctl_arg(char *param, char *val,
+ const char *unused, void *arg)
+{
+ char *path;
+ struct vfsmount **proc_mnt = arg;
+ struct file_system_type *proc_fs_type;
+ struct file *file;
+ int len;
+ int err;
+ loff_t pos = 0;
+ ssize_t wret;
+
+ if (strncmp(param, "sysctl", sizeof("sysctl") - 1) == 0) {
+ param += sizeof("sysctl") - 1;
+
+ if (param[0] != '/' && param[0] != '.')
+ return 0;
+
+ param++;
+ } else {
+ param = (char *) sysctl_find_alias(param);
+ if (!param)
+ return 0;
+ }
+
+ /*
+ * To set sysctl options, we use a temporary mount of proc, look up the
+ * respective sys/ file and write to it. To avoid mounting it when no
+ * options were given, we mount it only when the first sysctl option is
+ * found. Why not a persistent mount? There are problems with a
+ * persistent mount of proc in that it forces userspace not to use any
+ * proc mount options.
+ */
+ if (!*proc_mnt) {
+ proc_fs_type = get_fs_type("proc");
+ if (!proc_fs_type) {
+ pr_err("Failed to find procfs to set sysctl from command line\n");
+ return 0;
+ }
+ *proc_mnt = kern_mount(proc_fs_type);
+ put_filesystem(proc_fs_type);
+ if (IS_ERR(*proc_mnt)) {
+ pr_err("Failed to mount procfs to set sysctl from command line\n");
+ return 0;
+ }
+ }
+
+ path = kasprintf(GFP_KERNEL, "sys/%s", param);
+ if (!path)
+ panic("%s: Failed to allocate path for %s\n", __func__, param);
+ strreplace(path, '.', '/');
+
+ file = file_open_root((*proc_mnt)->mnt_root, *proc_mnt, path, O_WRONLY, 0);
+ if (IS_ERR(file)) {
+ err = PTR_ERR(file);
+ if (err == -ENOENT)
+ pr_err("Failed to set sysctl parameter '%s=%s': parameter not found\n",
+ param, val);
+ else if (err == -EACCES)
+ pr_err("Failed to set sysctl parameter '%s=%s': permission denied (read-only?)\n",
+ param, val);
+ else
+ pr_err("Error %pe opening proc file to set sysctl parameter '%s=%s'\n",
+ file, param, val);
+ goto out;
+ }
+ len = strlen(val);
+ wret = kernel_write(file, val, len, &pos);
+ if (wret < 0) {
+ err = wret;
+ if (err == -EINVAL)
+ pr_err("Failed to set sysctl parameter '%s=%s': invalid value\n",
+ param, val);
+ else
+ pr_err("Error %pe writing to proc file to set sysctl parameter '%s=%s'\n",
+ ERR_PTR(err), param, val);
+ } else if (wret != len) {
+ pr_err("Wrote only %zd bytes of %d writing to proc file %s to set sysctl parameter '%s=%s\n",
+ wret, len, path, param, val);
+ }
+
+ err = filp_close(file, NULL);
+ if (err)
+ pr_err("Error %pe closing proc file to set sysctl parameter '%s=%s\n",
+ ERR_PTR(err), param, val);
+out:
+ kfree(path);
+ return 0;
+}
+
+void do_sysctl_args(void)
+{
+ char *command_line;
+ struct vfsmount *proc_mnt = NULL;
+
+ command_line = kstrdup(saved_command_line, GFP_KERNEL);
+ if (!command_line)
+ panic("%s: Failed to allocate copy of command line\n", __func__);
+
+ parse_args("Setting sysctl args", command_line,
+ NULL, 0, -1, -1, &proc_mnt, process_sysctl_arg);
+
+ if (proc_mnt)
+ kern_unmount(proc_mnt);
+
+ kfree(command_line);
+}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index ffebed1999e5..5e444d4f9717 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -264,11 +264,13 @@ static void proc_kill_sb(struct super_block *sb)
{
struct proc_fs_info *fs_info = proc_sb_info(sb);
- if (fs_info->proc_self)
- dput(fs_info->proc_self);
+ if (!fs_info) {
+ kill_anon_super(sb);
+ return;
+ }
- if (fs_info->proc_thread_self)
- dput(fs_info->proc_thread_self);
+ dput(fs_info->proc_self);
+ dput(fs_info->proc_thread_self);
kill_anon_super(sb);
put_pid_ns(fs_info->pid_ns);
diff --git a/fs/proc/self.c b/fs/proc/self.c
index ca5158fa561c..72cd69bcaf4a 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -43,7 +43,7 @@ int proc_setup_self(struct super_block *s)
inode_lock(root_inode);
self = d_alloc_name(s->s_root, "self");
if (self) {
- struct inode *inode = new_inode_pseudo(s);
+ struct inode *inode = new_inode(s);
if (inode) {
inode->i_ino = self_inum;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 6ad407d5efe2..dbda4499a859 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -145,7 +145,7 @@ static void *m_start(struct seq_file *m, loff_t *ppos)
return NULL;
}
- if (down_read_killable(&mm->mmap_sem)) {
+ if (mmap_read_lock_killable(mm)) {
mmput(mm);
put_task_struct(priv->task);
priv->task = NULL;
@@ -188,7 +188,7 @@ static void m_stop(struct seq_file *m, void *v)
return;
release_task_mempolicy(priv);
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
mmput(mm);
put_task_struct(priv->task);
priv->task = NULL;
@@ -593,7 +593,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
if (pmd_trans_unstable(pmd))
goto out;
/*
- * The mmap_sem held all the way back in m_start() is what
+ * The mmap_lock held all the way back in m_start() is what
* keeps khugepaged out of here and from collapsing things
* in here.
*/
@@ -752,7 +752,7 @@ static void smap_gather_stats(struct vm_area_struct *vma,
}
}
#endif
- /* mmap_sem is held in m_start */
+ /* mmap_lock is held in m_start */
walk_page_vma(vma, &smaps_walk_ops, mss);
}
@@ -847,7 +847,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
memset(&mss, 0, sizeof(mss));
- ret = down_read_killable(&mm->mmap_sem);
+ ret = mmap_read_lock_killable(mm);
if (ret)
goto out_put_mm;
@@ -866,7 +866,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v)
__show_smap(m, &mss, true);
release_task_mempolicy(priv);
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
out_put_mm:
mmput(mm);
@@ -1140,7 +1140,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
};
if (type == CLEAR_REFS_MM_HIWATER_RSS) {
- if (down_write_killable(&mm->mmap_sem)) {
+ if (mmap_write_lock_killable(mm)) {
count = -EINTR;
goto out_mm;
}
@@ -1150,11 +1150,11 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
* resident set size to this mm's current rss value.
*/
reset_mm_hiwater_rss(mm);
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
goto out_mm;
}
- if (down_read_killable(&mm->mmap_sem)) {
+ if (mmap_read_lock_killable(mm)) {
count = -EINTR;
goto out_mm;
}
@@ -1163,8 +1163,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (!(vma->vm_flags & VM_SOFTDIRTY))
continue;
- up_read(&mm->mmap_sem);
- if (down_write_killable(&mm->mmap_sem)) {
+ mmap_read_unlock(mm);
+ if (mmap_write_lock_killable(mm)) {
count = -EINTR;
goto out_mm;
}
@@ -1183,14 +1183,14 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
* failed like if
* get_proc_task() fails?
*/
- up_write(&mm->mmap_sem);
+ mmap_write_unlock(mm);
goto out_mm;
}
for (vma = mm->mmap; vma; vma = vma->vm_next) {
vma->vm_flags &= ~VM_SOFTDIRTY;
vma_set_page_prot(vma);
}
- downgrade_write(&mm->mmap_sem);
+ mmap_write_downgrade(mm);
break;
}
@@ -1203,7 +1203,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
if (type == CLEAR_REFS_SOFT_DIRTY)
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb, 0, -1);
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
out_mm:
mmput(mm);
}
@@ -1564,11 +1564,11 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
/* overflow ? */
if (end < start_vaddr || end > end_vaddr)
end = end_vaddr;
- ret = down_read_killable(&mm->mmap_sem);
+ ret = mmap_read_lock_killable(mm);
if (ret)
goto out_free;
ret = walk_page_range(mm, start_vaddr, end, &pagemap_ops, &pm);
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
start_vaddr = end;
len = min(count, PM_ENTRY_BYTES * pm.pos);
@@ -1827,7 +1827,7 @@ static int show_numa_map(struct seq_file *m, void *v)
if (is_vm_hugetlb_page(vma))
seq_puts(m, " huge");
- /* mmap_sem is held by m_start */
+ /* mmap_lock is held by m_start */
walk_page_vma(vma, &show_numa_ops, md);
if (!md->pages)
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 7907e6419e57..a6d21fc0033c 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -25,7 +25,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
struct rb_node *p;
unsigned long bytes = 0, sbytes = 0, slack = 0, size;
- down_read(&mm->mmap_sem);
+ mmap_read_lock(mm);
for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
vma = rb_entry(p, struct vm_area_struct, vm_rb);
@@ -77,7 +77,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
"Shared:\t%8lu bytes\n",
bytes, slack, sbytes);
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
}
unsigned long task_vsize(struct mm_struct *mm)
@@ -86,12 +86,12 @@ unsigned long task_vsize(struct mm_struct *mm)
struct rb_node *p;
unsigned long vsize = 0;
- down_read(&mm->mmap_sem);
+ mmap_read_lock(mm);
for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
vma = rb_entry(p, struct vm_area_struct, vm_rb);
vsize += vma->vm_end - vma->vm_start;
}
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
return vsize;
}
@@ -104,7 +104,7 @@ unsigned long task_statm(struct mm_struct *mm,
struct rb_node *p;
unsigned long size = kobjsize(mm);
- down_read(&mm->mmap_sem);
+ mmap_read_lock(mm);
for (p = rb_first(&mm->mm_rb); p; p = rb_next(p)) {
vma = rb_entry(p, struct vm_area_struct, vm_rb);
size += kobjsize(vma);
@@ -119,7 +119,7 @@ unsigned long task_statm(struct mm_struct *mm,
>> PAGE_SHIFT;
*data = (PAGE_ALIGN(mm->start_stack) - (mm->start_data & PAGE_MASK))
>> PAGE_SHIFT;
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
size >>= PAGE_SHIFT;
size += *text + *data;
*resident = size;
@@ -211,7 +211,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
if (!mm || !mmget_not_zero(mm))
return NULL;
- if (down_read_killable(&mm->mmap_sem)) {
+ if (mmap_read_lock_killable(mm)) {
mmput(mm);
return ERR_PTR(-EINTR);
}
@@ -221,7 +221,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
if (n-- == 0)
return p;
- up_read(&mm->mmap_sem);
+ mmap_read_unlock(mm);
mmput(mm);
return NULL;
}
@@ -231,7 +231,7 @@ static void m_stop(struct seq_file *m, void *_vml)
struct proc_maps_private *priv = m->private;
if (!IS_ERR_OR_NULL(_vml)) {
- up_read(&priv->mm->mmap_sem);
+ mmap_read_unlock(priv->mm);
mmput(priv->mm);
}
if (priv->task) {
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
index ac284f409568..a553273fbd41 100644
--- a/fs/proc/thread_self.c
+++ b/fs/proc/thread_self.c
@@ -43,7 +43,7 @@ int proc_setup_thread_self(struct super_block *s)
inode_lock(root_inode);
thread_self = d_alloc_name(s->s_root, "thread-self");
if (thread_self) {
- struct inode *inode = new_inode_pseudo(s);
+ struct inode *inode = new_inode(s);
if (inode) {
inode->i_ino = thread_self_inum;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index c663202da8de..c3a345c28a93 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -27,7 +27,6 @@
#include <linux/pagemap.h>
#include <linux/uaccess.h>
#include <linux/mem_encrypt.h>
-#include <asm/pgtable.h>
#include <asm/io.h>
#include "internal.h"
generated by cgit v1.2.3 (git 2.0.4) at 2025-12-26 15:04:09 +0000