summaryrefslogtreecommitdiffstats
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/Makefile1
-rw-r--r--fs/proc/base.c192
-rw-r--r--fs/proc/inode.c15
-rw-r--r--fs/proc/internal.h3
-rw-r--r--fs/proc/meminfo.c23
-rw-r--r--fs/proc/proc_sysctl.c2
-rw-r--r--fs/proc/root.c61
-rw-r--r--fs/proc/stat.c10
-rw-r--r--fs/proc/task_mmu.c10
9 files changed, 147 insertions, 170 deletions
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index 7151ea428041..12c6922c913c 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -4,6 +4,7 @@
obj-y += proc.o
+CFLAGS_task_mmu.o += $(call cc-option,-Wno-override-init,)
proc-y := nommu.o task_nommu.o
proc-$(CONFIG_MMU) := task_mmu.o
diff --git a/fs/proc/base.c b/fs/proc/base.c
index a11eb7196ec8..54e270262979 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -579,11 +579,8 @@ static int proc_oom_score(struct seq_file *m, struct pid_namespace *ns,
unsigned long totalpages = totalram_pages + total_swap_pages;
unsigned long points = 0;
- read_lock(&tasklist_lock);
- if (pid_alive(task))
- points = oom_badness(task, NULL, NULL, totalpages) *
- 1000 / totalpages;
- read_unlock(&tasklist_lock);
+ points = oom_badness(task, NULL, NULL, totalpages) *
+ 1000 / totalpages;
seq_printf(m, "%lu\n", points);
return 0;
@@ -1024,23 +1021,107 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
char buffer[PROC_NUMBUF];
int oom_adj = OOM_ADJUST_MIN;
size_t len;
- unsigned long flags;
if (!task)
return -ESRCH;
- if (lock_task_sighand(task, &flags)) {
- if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
- oom_adj = OOM_ADJUST_MAX;
- else
- oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
- OOM_SCORE_ADJ_MAX;
- unlock_task_sighand(task, &flags);
- }
+ if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX)
+ oom_adj = OOM_ADJUST_MAX;
+ else
+ oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) /
+ OOM_SCORE_ADJ_MAX;
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj);
return simple_read_from_buffer(buf, count, ppos, buffer, len);
}
+static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
+{
+ static DEFINE_MUTEX(oom_adj_mutex);
+ struct mm_struct *mm = NULL;
+ struct task_struct *task;
+ int err = 0;
+
+ task = get_proc_task(file_inode(file));
+ if (!task)
+ return -ESRCH;
+
+ mutex_lock(&oom_adj_mutex);
+ if (legacy) {
+ if (oom_adj < task->signal->oom_score_adj &&
+ !capable(CAP_SYS_RESOURCE)) {
+ err = -EACCES;
+ goto err_unlock;
+ }
+ /*
+ * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
+ * /proc/pid/oom_score_adj instead.
+ */
+ pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
+ current->comm, task_pid_nr(current), task_pid_nr(task),
+ task_pid_nr(task));
+ } else {
+ if ((short)oom_adj < task->signal->oom_score_adj_min &&
+ !capable(CAP_SYS_RESOURCE)) {
+ err = -EACCES;
+ goto err_unlock;
+ }
+ }
+
+ /*
+ * Make sure we will check other processes sharing the mm if this is
+ * not vfrok which wants its own oom_score_adj.
+ * pin the mm so it doesn't go away and get reused after task_unlock
+ */
+ if (!task->vfork_done) {
+ struct task_struct *p = find_lock_task_mm(task);
+
+ if (p) {
+ if (atomic_read(&p->mm->mm_users) > 1) {
+ mm = p->mm;
+ atomic_inc(&mm->mm_count);
+ }
+ task_unlock(p);
+ }
+ }
+
+ task->signal->oom_score_adj = oom_adj;
+ if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
+ task->signal->oom_score_adj_min = (short)oom_adj;
+ trace_oom_score_adj_update(task);
+
+ if (mm) {
+ struct task_struct *p;
+
+ rcu_read_lock();
+ for_each_process(p) {
+ if (same_thread_group(task, p))
+ continue;
+
+ /* do not touch kernel threads or the global init */
+ if (p->flags & PF_KTHREAD || is_global_init(p))
+ continue;
+
+ task_lock(p);
+ if (!p->vfork_done && process_shares_mm(p, mm)) {
+ pr_info("updating oom_score_adj for %d (%s) from %d to %d because it shares mm with %d (%s). Report if this is unexpected.\n",
+ task_pid_nr(p), p->comm,
+ p->signal->oom_score_adj, oom_adj,
+ task_pid_nr(task), task->comm);
+ p->signal->oom_score_adj = oom_adj;
+ if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
+ p->signal->oom_score_adj_min = (short)oom_adj;
+ }
+ task_unlock(p);
+ }
+ rcu_read_unlock();
+ mmdrop(mm);
+ }
+err_unlock:
+ mutex_unlock(&oom_adj_mutex);
+ put_task_struct(task);
+ return err;
+}
+
/*
* /proc/pid/oom_adj exists solely for backwards compatibility with previous
* kernels. The effective policy is defined by oom_score_adj, which has a
@@ -1054,10 +1135,8 @@ static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count,
static ssize_t oom_adj_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
- struct task_struct *task;
char buffer[PROC_NUMBUF];
int oom_adj;
- unsigned long flags;
int err;
memset(buffer, 0, sizeof(buffer));
@@ -1077,23 +1156,6 @@ static ssize_t oom_adj_write(struct file *file, const char __user *buf,
goto out;
}
- task = get_proc_task(file_inode(file));
- if (!task) {
- err = -ESRCH;
- goto out;
- }
-
- task_lock(task);
- if (!task->mm) {
- err = -EINVAL;
- goto err_task_lock;
- }
-
- if (!lock_task_sighand(task, &flags)) {
- err = -ESRCH;
- goto err_task_lock;
- }
-
/*
* Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
* value is always attainable.
@@ -1103,27 +1165,7 @@ static ssize_t oom_adj_write(struct file *file, const char __user *buf,
else
oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE;
- if (oom_adj < task->signal->oom_score_adj &&
- !capable(CAP_SYS_RESOURCE)) {
- err = -EACCES;
- goto err_sighand;
- }
-
- /*
- * /proc/pid/oom_adj is provided for legacy purposes, ask users to use
- * /proc/pid/oom_score_adj instead.
- */
- pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n",
- current->comm, task_pid_nr(current), task_pid_nr(task),
- task_pid_nr(task));
-
- task->signal->oom_score_adj = oom_adj;
- trace_oom_score_adj_update(task);
-err_sighand:
- unlock_task_sighand(task, &flags);
-err_task_lock:
- task_unlock(task);
- put_task_struct(task);
+ err = __set_oom_adj(file, oom_adj, true);
out:
return err < 0 ? err : count;
}
@@ -1140,15 +1182,11 @@ static ssize_t oom_score_adj_read(struct file *file, char __user *buf,
struct task_struct *task = get_proc_task(file_inode(file));
char buffer[PROC_NUMBUF];
short oom_score_adj = OOM_SCORE_ADJ_MIN;
- unsigned long flags;
size_t len;
if (!task)
return -ESRCH;
- if (lock_task_sighand(task, &flags)) {
- oom_score_adj = task->signal->oom_score_adj;
- unlock_task_sighand(task, &flags);
- }
+ oom_score_adj = task->signal->oom_score_adj;
put_task_struct(task);
len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj);
return simple_read_from_buffer(buf, count, ppos, buffer, len);
@@ -1157,9 +1195,7 @@ 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)
{
- struct task_struct *task;
char buffer[PROC_NUMBUF];
- unsigned long flags;
int oom_score_adj;
int err;
@@ -1180,39 +1216,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
goto out;
}
- task = get_proc_task(file_inode(file));
- if (!task) {
- err = -ESRCH;
- goto out;
- }
-
- task_lock(task);
- if (!task->mm) {
- err = -EINVAL;
- goto err_task_lock;
- }
-
- if (!lock_task_sighand(task, &flags)) {
- err = -ESRCH;
- goto err_task_lock;
- }
-
- if ((short)oom_score_adj < task->signal->oom_score_adj_min &&
- !capable(CAP_SYS_RESOURCE)) {
- err = -EACCES;
- goto err_sighand;
- }
-
- task->signal->oom_score_adj = (short)oom_score_adj;
- if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
- task->signal->oom_score_adj_min = (short)oom_score_adj;
- trace_oom_score_adj_update(task);
-
-err_sighand:
- unlock_task_sighand(task, &flags);
-err_task_lock:
- task_unlock(task);
- put_task_struct(task);
+ err = __set_oom_adj(file, oom_score_adj, false);
out:
return err < 0 ? err : count;
}
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 42305ddcbaa0..c1b72388e571 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -457,17 +457,30 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
return inode;
}
-int proc_fill_super(struct super_block *s)
+int proc_fill_super(struct super_block *s, void *data, int silent)
{
+ struct pid_namespace *ns = get_pid_ns(s->s_fs_info);
struct inode *root_inode;
int ret;
+ if (!proc_parse_options(data, ns))
+ return -EINVAL;
+
+ /* User space would break if executables or devices appear on proc */
+ s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
s->s_flags |= MS_NODIRATIME | MS_NOSUID | MS_NOEXEC;
s->s_blocksize = 1024;
s->s_blocksize_bits = 10;
s->s_magic = PROC_SUPER_MAGIC;
s->s_op = &proc_sops;
s->s_time_gran = 1;
+
+ /*
+ * procfs isn't actually a stacking filesystem; however, there is
+ * too much magic going on inside it to permit stacking things on
+ * top of it
+ */
+ s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
pde_get(&proc_root);
root_inode = proc_get_inode(s, &proc_root);
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index aa2781095bd1..7931c558c192 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -212,7 +212,7 @@ extern const struct inode_operations proc_pid_link_inode_operations;
extern void proc_init_inodecache(void);
extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
-extern int proc_fill_super(struct super_block *);
+extern int proc_fill_super(struct super_block *, void *data, int flags);
extern void proc_entry_rundown(struct proc_dir_entry *);
/*
@@ -268,6 +268,7 @@ static inline void proc_tty_init(void) {}
* root.c
*/
extern struct proc_dir_entry proc_root;
+extern int proc_parse_options(char *options, struct pid_namespace *pid);
extern void proc_self_init(void);
extern int proc_remount(struct super_block *, int *, char *);
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 83720460c5bc..09e18fdf61e5 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -40,7 +40,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
si_swapinfo(&i);
committed = percpu_counter_read_positive(&vm_committed_as);
- cached = global_page_state(NR_FILE_PAGES) -
+ cached = global_node_page_state(NR_FILE_PAGES) -
total_swapcache_pages() - i.bufferram;
if (cached < 0)
cached = 0;
@@ -105,6 +105,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
"AnonHugePages: %8lu kB\n"
+ "ShmemHugePages: %8lu kB\n"
+ "ShmemPmdMapped: %8lu kB\n"
#endif
#ifdef CONFIG_CMA
"CmaTotal: %8lu kB\n"
@@ -136,23 +138,23 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
#endif
K(i.totalswap),
K(i.freeswap),
- K(global_page_state(NR_FILE_DIRTY)),
- K(global_page_state(NR_WRITEBACK)),
- K(global_page_state(NR_ANON_PAGES)),
- K(global_page_state(NR_FILE_MAPPED)),
+ K(global_node_page_state(NR_FILE_DIRTY)),
+ K(global_node_page_state(NR_WRITEBACK)),
+ K(global_node_page_state(NR_ANON_MAPPED)),
+ K(global_node_page_state(NR_FILE_MAPPED)),
K(i.sharedram),
K(global_page_state(NR_SLAB_RECLAIMABLE) +
global_page_state(NR_SLAB_UNRECLAIMABLE)),
K(global_page_state(NR_SLAB_RECLAIMABLE)),
K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
- global_page_state(NR_KERNEL_STACK) * THREAD_SIZE / 1024,
+ global_page_state(NR_KERNEL_STACK_KB),
K(global_page_state(NR_PAGETABLE)),
#ifdef CONFIG_QUICKLIST
K(quicklist_total_size()),
#endif
- K(global_page_state(NR_UNSTABLE_NFS)),
+ K(global_node_page_state(NR_UNSTABLE_NFS)),
K(global_page_state(NR_BOUNCE)),
- K(global_page_state(NR_WRITEBACK_TEMP)),
+ K(global_node_page_state(NR_WRITEBACK_TEMP)),
K(vm_commit_limit()),
K(committed),
(unsigned long)VMALLOC_TOTAL >> 10,
@@ -162,8 +164,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
, atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- , K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
- HPAGE_PMD_NR)
+ , K(global_node_page_state(NR_ANON_THPS) * HPAGE_PMD_NR)
+ , K(global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR)
+ , K(global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR)
#endif
#ifdef CONFIG_CMA
, K(totalcma_pages)
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 04f69ea4b8c7..ffbb513c06c6 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -623,7 +623,7 @@ static bool proc_sys_fill_cache(struct file *file,
qname.name = table->procname;
qname.len = strlen(table->procname);
- qname.hash = full_name_hash(qname.name, qname.len);
+ qname.hash = full_name_hash(dir, qname.name, qname.len);
child = d_lookup(dir, &qname);
if (!child) {
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 06702783bf40..8d3e484055a6 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -23,21 +23,6 @@
#include "internal.h"
-static int proc_test_super(struct super_block *sb, void *data)
-{
- return sb->s_fs_info == data;
-}
-
-static int proc_set_super(struct super_block *sb, void *data)
-{
- int err = set_anon_super(sb, NULL);
- if (!err) {
- struct pid_namespace *ns = (struct pid_namespace *)data;
- sb->s_fs_info = get_pid_ns(ns);
- }
- return err;
-}
-
enum {
Opt_gid, Opt_hidepid, Opt_err,
};
@@ -48,7 +33,7 @@ static const match_table_t tokens = {
{Opt_err, NULL},
};
-static int proc_parse_options(char *options, struct pid_namespace *pid)
+int proc_parse_options(char *options, struct pid_namespace *pid)
{
char *p;
substring_t args[MAX_OPT_ARGS];
@@ -100,52 +85,16 @@ int proc_remount(struct super_block *sb, int *flags, char *data)
static struct dentry *proc_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
- int err;
- struct super_block *sb;
struct pid_namespace *ns;
- char *options;
if (flags & MS_KERNMOUNT) {
- ns = (struct pid_namespace *)data;
- options = NULL;
+ ns = data;
+ data = NULL;
} else {
ns = task_active_pid_ns(current);
- options = data;
-
- /* Does the mounter have privilege over the pid namespace? */
- if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
- return ERR_PTR(-EPERM);
- }
-
- sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
- if (IS_ERR(sb))
- return ERR_CAST(sb);
-
- /*
- * procfs isn't actually a stacking filesystem; however, there is
- * too much magic going on inside it to permit stacking things on
- * top of it
- */
- sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
-
- if (!proc_parse_options(options, ns)) {
- deactivate_locked_super(sb);
- return ERR_PTR(-EINVAL);
- }
-
- if (!sb->s_root) {
- err = proc_fill_super(sb);
- if (err) {
- deactivate_locked_super(sb);
- return ERR_PTR(err);
- }
-
- sb->s_flags |= MS_ACTIVE;
- /* User space would break if executables appear on proc */
- sb->s_iflags |= SB_I_NOEXEC;
}
- return dget(sb->s_root);
+ return mount_ns(fs_type, flags, data, ns, ns->user_ns, proc_fill_super);
}
static void proc_kill_sb(struct super_block *sb)
@@ -165,7 +114,7 @@ static struct file_system_type proc_fs_type = {
.name = "proc",
.mount = proc_mount,
.kill_sb = proc_kill_sb,
- .fs_flags = FS_USERNS_VISIBLE | FS_USERNS_MOUNT,
+ .fs_flags = FS_USERNS_MOUNT,
};
void __init proc_root_init(void)
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 510413eb25b8..7907e456ac4f 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -80,19 +80,17 @@ static u64 get_iowait_time(int cpu)
static int show_stat(struct seq_file *p, void *v)
{
int i, j;
- unsigned long jif;
u64 user, nice, system, idle, iowait, irq, softirq, steal;
u64 guest, guest_nice;
u64 sum = 0;
u64 sum_softirq = 0;
unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
- struct timespec boottime;
+ struct timespec64 boottime;
user = nice = system = idle = iowait =
irq = softirq = steal = 0;
guest = guest_nice = 0;
- getboottime(&boottime);
- jif = boottime.tv_sec;
+ getboottime64(&boottime);
for_each_possible_cpu(i) {
user += kcpustat_cpu(i).cpustat[CPUTIME_USER];
@@ -163,12 +161,12 @@ static int show_stat(struct seq_file *p, void *v)
seq_printf(p,
"\nctxt %llu\n"
- "btime %lu\n"
+ "btime %llu\n"
"processes %lu\n"
"procs_running %lu\n"
"procs_blocked %lu\n",
nr_context_switches(),
- (unsigned long)jif,
+ (unsigned long long)boottime.tv_sec,
total_forks,
nr_running(),
nr_iowait());
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4648c7f63ae2..187d84ef9de9 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -448,6 +448,7 @@ struct mem_size_stats {
unsigned long referenced;
unsigned long anonymous;
unsigned long anonymous_thp;
+ unsigned long shmem_thp;
unsigned long swap;
unsigned long shared_hugetlb;
unsigned long private_hugetlb;
@@ -576,7 +577,12 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
if (IS_ERR_OR_NULL(page))
return;
- mss->anonymous_thp += HPAGE_PMD_SIZE;
+ if (PageAnon(page))
+ mss->anonymous_thp += HPAGE_PMD_SIZE;
+ else if (PageSwapBacked(page))
+ mss->shmem_thp += HPAGE_PMD_SIZE;
+ else
+ VM_BUG_ON_PAGE(1, page);
smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
}
#else
@@ -770,6 +776,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
"Referenced: %8lu kB\n"
"Anonymous: %8lu kB\n"
"AnonHugePages: %8lu kB\n"
+ "ShmemPmdMapped: %8lu kB\n"
"Shared_Hugetlb: %8lu kB\n"
"Private_Hugetlb: %7lu kB\n"
"Swap: %8lu kB\n"
@@ -787,6 +794,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
mss.referenced >> 10,
mss.anonymous >> 10,
mss.anonymous_thp >> 10,
+ mss.shmem_thp >> 10,
mss.shared_hugetlb >> 10,
mss.private_hugetlb >> 10,
mss.swap >> 10,
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-13 00:01:04 +0000