aboutsummaryrefslogtreecommitdiffstats
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/array.c66
-rw-r--r--fs/proc/base.c31
-rw-r--r--fs/proc/inode.c19
-rw-r--r--fs/proc/internal.h2
-rw-r--r--fs/proc/proc_sysctl.c24
-rw-r--r--fs/proc/root.c2
-rw-r--r--fs/proc/task_mmu.c47
7 files changed, 104 insertions, 87 deletions
diff --git a/fs/proc/array.c b/fs/proc/array.c
index ff08a8957552..34a47fb0c57f 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -477,13 +477,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
int permitted;
struct mm_struct *mm;
unsigned long long start_time;
- unsigned long cmin_flt = 0, cmaj_flt = 0;
- unsigned long min_flt = 0, maj_flt = 0;
- u64 cutime, cstime, utime, stime;
- u64 cgtime, gtime;
+ unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt;
+ u64 cutime, cstime, cgtime, utime, stime, gtime;
unsigned long rsslim = 0;
unsigned long flags;
int exit_code = task->exit_code;
+ struct signal_struct *sig = task->signal;
+ unsigned int seq = 1;
state = *get_task_state(task);
vsize = eip = esp = 0;
@@ -511,12 +511,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
sigemptyset(&sigign);
sigemptyset(&sigcatch);
- cutime = cstime = utime = stime = 0;
- cgtime = gtime = 0;
if (lock_task_sighand(task, &flags)) {
- struct signal_struct *sig = task->signal;
-
if (sig->tty) {
struct pid *pgrp = tty_get_pgrp(sig->tty);
tty_pgrp = pid_nr_ns(pgrp, ns);
@@ -527,28 +523,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
num_threads = get_nr_threads(task);
collect_sigign_sigcatch(task, &sigign, &sigcatch);
- cmin_flt = sig->cmin_flt;
- cmaj_flt = sig->cmaj_flt;
- cutime = sig->cutime;
- cstime = sig->cstime;
- cgtime = sig->cgtime;
rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur);
- /* add up live thread stats at the group level */
if (whole) {
- struct task_struct *t;
-
- __for_each_thread(sig, t) {
- min_flt += t->min_flt;
- maj_flt += t->maj_flt;
- gtime += task_gtime(t);
- }
-
- min_flt += sig->min_flt;
- maj_flt += sig->maj_flt;
- thread_group_cputime_adjusted(task, &utime, &stime);
- gtime += sig->gtime;
-
if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED))
exit_code = sig->group_exit_code;
}
@@ -562,10 +539,41 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
if (permitted && (!whole || num_threads < 2))
wchan = !task_is_running(task);
- if (!whole) {
+
+ do {
+ seq++; /* 2 on the 1st/lockless path, otherwise odd */
+ flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
+
+ cmin_flt = sig->cmin_flt;
+ cmaj_flt = sig->cmaj_flt;
+ cutime = sig->cutime;
+ cstime = sig->cstime;
+ cgtime = sig->cgtime;
+
+ if (whole) {
+ struct task_struct *t;
+
+ min_flt = sig->min_flt;
+ maj_flt = sig->maj_flt;
+ gtime = sig->gtime;
+
+ rcu_read_lock();
+ __for_each_thread(sig, t) {
+ min_flt += t->min_flt;
+ maj_flt += t->maj_flt;
+ gtime += task_gtime(t);
+ }
+ rcu_read_unlock();
+ }
+ } while (need_seqretry(&sig->stats_lock, seq));
+ done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
+
+ if (whole) {
+ thread_group_cputime_adjusted(task, &utime, &stime);
+ } else {
+ task_cputime_adjusted(task, &utime, &stime);
min_flt = task->min_flt;
maj_flt = task->maj_flt;
- task_cputime_adjusted(task, &utime, &stime);
gtime = task_gtime(task);
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index dd31e3b6bf77..18550c071d71 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -97,6 +97,7 @@
#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"
@@ -146,10 +147,10 @@ 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 .
@@ -1877,8 +1878,6 @@ 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,
@@ -2726,7 +2725,7 @@ 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);
@@ -2784,7 +2783,7 @@ 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);
@@ -2833,27 +2832,27 @@ 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),
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index b33e490e3fd9..05350f3c2812 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);
@@ -38,17 +37,8 @@ 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) {
@@ -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));
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 9a8f32f21ff5..a71ac5379584 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -92,7 +92,7 @@ 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 {
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 8064ea76f80b..37cde0efee57 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -44,7 +44,7 @@ static struct ctl_table sysctl_mount_point[] = {
*/
struct ctl_table_header *register_sysctl_mount_point(const char *path)
{
- return register_sysctl_sz(path, sysctl_mount_point, 0);
+ return register_sysctl(path, sysctl_mount_point);
}
EXPORT_SYMBOL(register_sysctl_mount_point);
@@ -71,7 +71,6 @@ 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 = {
@@ -233,7 +232,8 @@ static int insert_header(struct ctl_dir *dir, struct ctl_table_header *header)
return -EROFS;
/* Am I creating a permanently empty directory? */
- if (sysctl_is_perm_empty_ctl_table(header->ctl_table)) {
+ if (header->ctl_table_size > 0 &&
+ sysctl_is_perm_empty_ctl_table(header->ctl_table)) {
if (!RB_EMPTY_ROOT(&dir->root))
return -EINVAL;
sysctl_set_perm_empty_ctl_header(dir_h);
@@ -534,13 +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:
@@ -698,13 +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)) {
@@ -1213,6 +1203,10 @@ static bool get_links(struct ctl_dir *dir,
struct ctl_table_header *tmp_head;
struct ctl_table *entry, *link;
+ if (header->ctl_table_size == 0 ||
+ sysctl_is_perm_empty_ctl_table(header->ctl_table))
+ return true;
+
/* Are there links available for every entry in table? */
list_for_each_table_entry(entry, header) {
const char *procname = entry->procname;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index b55dbc70287b..06a297a27ba3 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -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/task_mmu.c b/fs/proc/task_mmu.c
index 435b61054b5b..3f78ebbb795f 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -273,7 +273,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
const char *name = NULL;
if (file) {
- struct inode *inode = file_inode(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;
@@ -865,7 +866,8 @@ 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, true, false,
+ true, THP_ORDERS_ALL));
if (arch_pkeys_enabled())
seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma));
@@ -1761,7 +1763,7 @@ static int pagemap_release(struct inode *inode, struct file *file)
#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_HUGE | PAGE_IS_SOFT_DIRTY)
#define PM_SCAN_FLAGS (PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC)
struct pagemap_scan_private {
@@ -1793,6 +1795,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
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;
@@ -1806,6 +1810,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
!PageAnon(pfn_swap_entry_to_page(swp)))
categories |= PAGE_IS_FILE;
}
+ if (pte_swp_soft_dirty(pte))
+ categories |= PAGE_IS_SOFT_DIRTY;
}
return categories;
@@ -1853,12 +1859,16 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
if (is_zero_pfn(pmd_pfn(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);
@@ -1905,10 +1915,14 @@ static unsigned long pagemap_hugetlb_category(pte_t 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;
@@ -2007,6 +2021,9 @@ static int pagemap_scan_test_walk(unsigned long start, unsigned long end,
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;
@@ -2415,7 +2432,6 @@ static long pagemap_scan_flush_buffer(struct pagemap_scan_private *p)
static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
{
- struct mmu_notifier_range range;
struct pagemap_scan_private p = {0};
unsigned long walk_start;
size_t n_ranges_out = 0;
@@ -2431,15 +2447,9 @@ static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
if (ret)
return ret;
- /* 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, p.arg.start, p.arg.end);
- mmu_notifier_invalidate_range_start(&range);
- }
-
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)) {
@@ -2450,8 +2460,20 @@ static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
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);
@@ -2477,9 +2499,6 @@ static long do_pagemap_scan(struct mm_struct *mm, unsigned long uarg)
if (pagemap_scan_writeback_args(&p.arg, uarg))
ret = -EFAULT;
- if (p.arg.flags & PM_SCAN_WP_MATCHING)
- mmu_notifier_invalidate_range_end(&range);
-
kfree(p.vec_buf);
return ret;
}
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-06-24 07:01:26 +0000