summaryrefslogtreecommitdiff
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/base.c58
-rw-r--r--fs/proc/generic.c5
-rw-r--r--fs/proc/inode.c4
-rw-r--r--fs/proc/meminfo.c2
-rw-r--r--fs/proc/proc_net.c4
-rw-r--r--fs/proc/proc_sysctl.c48
-rw-r--r--fs/proc/root.c2
-rw-r--r--fs/proc/stat.c41
-rw-r--r--fs/proc/task_mmu.c85
-rw-r--r--fs/proc/vmcore.c1
10 files changed, 181 insertions, 69 deletions
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 91fb655a5cbf..851ba3dcdc29 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1107,21 +1107,13 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
goto err_sighand;
}
- if (oom_adjust != task->signal->oom_adj) {
- if (oom_adjust == OOM_DISABLE)
- atomic_inc(&task->mm->oom_disable_count);
- if (task->signal->oom_adj == OOM_DISABLE)
- atomic_dec(&task->mm->oom_disable_count);
- }
-
/*
* Warn that /proc/pid/oom_adj is deprecated, see
* Documentation/feature-removal-schedule.txt.
*/
- printk_once(KERN_WARNING "%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));
+ printk_once(KERN_WARNING "%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_adj = oom_adjust;
/*
* Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum
@@ -1216,12 +1208,6 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf,
goto err_sighand;
}
- if (oom_score_adj != task->signal->oom_score_adj) {
- if (oom_score_adj == OOM_SCORE_ADJ_MIN)
- atomic_inc(&task->mm->oom_disable_count);
- if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
- atomic_dec(&task->mm->oom_disable_count);
- }
task->signal->oom_score_adj = oom_score_adj;
if (has_capability_noaudit(current, CAP_SYS_RESOURCE))
task->signal->oom_score_adj_min = oom_score_adj;
@@ -1920,6 +1906,14 @@ static int proc_fd_info(struct inode *inode, struct path *path, char *info)
spin_lock(&files->file_lock);
file = fcheck_files(files, fd);
if (file) {
+ unsigned int f_flags;
+ struct fdtable *fdt;
+
+ fdt = files_fdtable(files);
+ f_flags = file->f_flags & ~O_CLOEXEC;
+ if (FD_ISSET(fd, fdt->close_on_exec))
+ f_flags |= O_CLOEXEC;
+
if (path) {
*path = file->f_path;
path_get(&file->f_path);
@@ -1929,7 +1923,7 @@ static int proc_fd_info(struct inode *inode, struct path *path, char *info)
"pos:\t%lli\n"
"flags:\t0%o\n",
(long long) file->f_pos,
- file->f_flags);
+ f_flags);
spin_unlock(&files->file_lock);
put_files_struct(files);
return 0;
@@ -2254,7 +2248,7 @@ static struct dentry *proc_pident_instantiate(struct inode *dir,
ei = PROC_I(inode);
inode->i_mode = p->mode;
if (S_ISDIR(inode->i_mode))
- inode->i_nlink = 2; /* Use getattr to fix if necessary */
+ set_nlink(inode, 2); /* Use getattr to fix if necessary */
if (p->iop)
inode->i_op = p->iop;
if (p->fop)
@@ -2648,7 +2642,7 @@ static struct dentry *proc_base_instantiate(struct inode *dir,
inode->i_mode = p->mode;
if (S_ISDIR(inode->i_mode))
- inode->i_nlink = 2;
+ set_nlink(inode, 2);
if (S_ISLNK(inode->i_mode))
inode->i_size = 64;
if (p->iop)
@@ -2707,9 +2701,16 @@ static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
{
struct task_io_accounting acct = task->ioac;
unsigned long flags;
+ int result;
- if (!ptrace_may_access(task, PTRACE_MODE_READ))
- return -EACCES;
+ result = mutex_lock_killable(&task->signal->cred_guard_mutex);
+ if (result)
+ return result;
+
+ if (!ptrace_may_access(task, PTRACE_MODE_READ)) {
+ result = -EACCES;
+ goto out_unlock;
+ }
if (whole && lock_task_sighand(task, &flags)) {
struct task_struct *t = task;
@@ -2720,7 +2721,7 @@ static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
unlock_task_sighand(task, &flags);
}
- return sprintf(buffer,
+ result = sprintf(buffer,
"rchar: %llu\n"
"wchar: %llu\n"
"syscr: %llu\n"
@@ -2735,6 +2736,9 @@ static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
(unsigned long long)acct.read_bytes,
(unsigned long long)acct.write_bytes,
(unsigned long long)acct.cancelled_write_bytes);
+out_unlock:
+ mutex_unlock(&task->signal->cred_guard_mutex);
+ return result;
}
static int proc_tid_io_accounting(struct task_struct *task, char *buffer)
@@ -2977,8 +2981,8 @@ static struct dentry *proc_pid_instantiate(struct inode *dir,
inode->i_fop = &proc_tgid_base_operations;
inode->i_flags|=S_IMMUTABLE;
- inode->i_nlink = 2 + pid_entry_count_dirs(tgid_base_stuff,
- ARRAY_SIZE(tgid_base_stuff));
+ set_nlink(inode, 2 + pid_entry_count_dirs(tgid_base_stuff,
+ ARRAY_SIZE(tgid_base_stuff)));
d_set_d_op(dentry, &pid_dentry_operations);
@@ -3229,8 +3233,8 @@ static struct dentry *proc_task_instantiate(struct inode *dir,
inode->i_fop = &proc_tid_base_operations;
inode->i_flags|=S_IMMUTABLE;
- inode->i_nlink = 2 + pid_entry_count_dirs(tid_base_stuff,
- ARRAY_SIZE(tid_base_stuff));
+ set_nlink(inode, 2 + pid_entry_count_dirs(tid_base_stuff,
+ ARRAY_SIZE(tid_base_stuff)));
d_set_d_op(dentry, &pid_dentry_operations);
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index f1637f17c37c..10090d9c7ad5 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -283,7 +283,7 @@ static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct inode *inode = dentry->d_inode;
struct proc_dir_entry *de = PROC_I(inode)->pde;
if (de && de->nlink)
- inode->i_nlink = de->nlink;
+ set_nlink(inode, de->nlink);
generic_fillattr(inode, stat);
return 0;
@@ -620,8 +620,7 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
if (!ent) goto out;
memset(ent, 0, sizeof(struct proc_dir_entry));
- memcpy(((char *) ent) + sizeof(struct proc_dir_entry), fn, len + 1);
- ent->name = ((char *) ent) + sizeof(*ent);
+ memcpy(ent->name, fn, len + 1);
ent->namelen = len;
ent->mode = mode;
ent->nlink = nlink;
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 74b48cfa1bb2..7737c5468a40 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -319,7 +319,7 @@ static int proc_reg_open(struct inode *inode, struct file *file)
if (!pde->proc_fops) {
spin_unlock(&pde->pde_unload_lock);
kfree(pdeo);
- return -EINVAL;
+ return -ENOENT;
}
pde->pde_users++;
open = pde->proc_fops->open;
@@ -445,7 +445,7 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
if (de->size)
inode->i_size = de->size;
if (de->nlink)
- inode->i_nlink = de->nlink;
+ set_nlink(inode, de->nlink);
if (de->proc_iops)
inode->i_op = de->proc_iops;
if (de->proc_fops) {
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index ed257d141568..586174168e2a 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -10,7 +10,7 @@
#include <linux/seq_file.h>
#include <linux/swap.h>
#include <linux/vmstat.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include "internal.h"
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 9020ac15baaa..f738024ccc8e 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -197,15 +197,15 @@ static __net_init int proc_net_ns_init(struct net *net)
int err;
err = -ENOMEM;
- netd = kzalloc(sizeof(*netd), GFP_KERNEL);
+ netd = kzalloc(sizeof(*netd) + 4, GFP_KERNEL);
if (!netd)
goto out;
netd->data = net;
netd->nlink = 2;
- netd->name = "net";
netd->namelen = 3;
netd->parent = &proc_root;
+ memcpy(netd->name, "net", 4);
err = -EEXIST;
net_statd = proc_net_mkdir(net, "stat", netd);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 1a77dbef226f..a6b62173d4c3 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -3,6 +3,7 @@
*/
#include <linux/init.h>
#include <linux/sysctl.h>
+#include <linux/poll.h>
#include <linux/proc_fs.h>
#include <linux/security.h>
#include <linux/namei.h>
@@ -14,6 +15,15 @@ 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;
+void proc_sys_poll_notify(struct ctl_table_poll *poll)
+{
+ if (!poll)
+ return;
+
+ atomic_inc(&poll->event);
+ wake_up_interruptible(&poll->wait);
+}
+
static struct inode *proc_sys_make_inode(struct super_block *sb,
struct ctl_table_header *head, struct ctl_table *table)
{
@@ -39,7 +49,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
inode->i_fop = &proc_sys_file_operations;
} else {
inode->i_mode |= S_IFDIR;
- inode->i_nlink = 0;
+ clear_nlink(inode);
inode->i_op = &proc_sys_dir_operations;
inode->i_fop = &proc_sys_dir_file_operations;
}
@@ -176,6 +186,39 @@ static ssize_t proc_sys_write(struct file *filp, const char __user *buf,
return proc_sys_call_handler(filp, (void __user *)buf, count, ppos, 1);
}
+static int proc_sys_open(struct inode *inode, struct file *filp)
+{
+ struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+
+ if (table->poll)
+ filp->private_data = proc_sys_poll_event(table->poll);
+
+ return 0;
+}
+
+static unsigned int proc_sys_poll(struct file *filp, poll_table *wait)
+{
+ struct inode *inode = filp->f_path.dentry->d_inode;
+ struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+ unsigned long event = (unsigned long)filp->private_data;
+ unsigned int ret = DEFAULT_POLLMASK;
+
+ if (!table->proc_handler)
+ goto out;
+
+ if (!table->poll)
+ goto out;
+
+ poll_wait(filp, &table->poll->wait, wait);
+
+ if (event != atomic_read(&table->poll->event)) {
+ filp->private_data = proc_sys_poll_event(table->poll);
+ ret = POLLIN | POLLRDNORM | POLLERR | POLLPRI;
+ }
+
+out:
+ return ret;
+}
static int proc_sys_fill_cache(struct file *filp, void *dirent,
filldir_t filldir,
@@ -364,12 +407,15 @@ static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct
}
static const struct file_operations proc_sys_file_operations = {
+ .open = proc_sys_open,
+ .poll = proc_sys_poll,
.read = proc_sys_read,
.write = proc_sys_write,
.llseek = default_llseek,
};
static const struct file_operations proc_sys_dir_file_operations = {
+ .read = generic_read_dir,
.readdir = proc_sys_readdir,
.llseek = generic_file_llseek,
};
diff --git a/fs/proc/root.c b/fs/proc/root.c
index d6c3b416529b..9a8a2b77b874 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -186,13 +186,13 @@ static const struct inode_operations proc_root_inode_operations = {
struct proc_dir_entry proc_root = {
.low_ino = PROC_ROOT_INO,
.namelen = 5,
- .name = "/proc",
.mode = S_IFDIR | S_IRUGO | S_IXUGO,
.nlink = 2,
.count = ATOMIC_INIT(1),
.proc_iops = &proc_root_inode_operations,
.proc_fops = &proc_root_operations,
.parent = &proc_root,
+ .name = "/proc",
};
int pid_ns_prepare_proc(struct pid_namespace *ns)
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 9758b654a1bc..42b274da92c3 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -10,6 +10,7 @@
#include <linux/time.h>
#include <linux/irqnr.h>
#include <asm/cputime.h>
+#include <linux/tick.h>
#ifndef arch_irq_stat_cpu
#define arch_irq_stat_cpu(cpu) 0
@@ -21,6 +22,35 @@
#define arch_idle_time(cpu) 0
#endif
+static cputime64_t get_idle_time(int cpu)
+{
+ u64 idle_time = get_cpu_idle_time_us(cpu, NULL);
+ cputime64_t idle;
+
+ if (idle_time == -1ULL) {
+ /* !NO_HZ so we can rely on cpustat.idle */
+ idle = kstat_cpu(cpu).cpustat.idle;
+ idle = cputime64_add(idle, arch_idle_time(cpu));
+ } else
+ idle = usecs_to_cputime(idle_time);
+
+ return idle;
+}
+
+static cputime64_t get_iowait_time(int cpu)
+{
+ u64 iowait_time = get_cpu_iowait_time_us(cpu, NULL);
+ cputime64_t iowait;
+
+ if (iowait_time == -1ULL)
+ /* !NO_HZ so we can rely on cpustat.iowait */
+ iowait = kstat_cpu(cpu).cpustat.iowait;
+ else
+ iowait = usecs_to_cputime(iowait_time);
+
+ return iowait;
+}
+
static int show_stat(struct seq_file *p, void *v)
{
int i, j;
@@ -42,9 +72,8 @@ static int show_stat(struct seq_file *p, void *v)
user = cputime64_add(user, kstat_cpu(i).cpustat.user);
nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice);
system = cputime64_add(system, kstat_cpu(i).cpustat.system);
- idle = cputime64_add(idle, kstat_cpu(i).cpustat.idle);
- idle = cputime64_add(idle, arch_idle_time(i));
- iowait = cputime64_add(iowait, kstat_cpu(i).cpustat.iowait);
+ idle = cputime64_add(idle, get_idle_time(i));
+ iowait = cputime64_add(iowait, get_iowait_time(i));
irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq);
softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
@@ -76,14 +105,12 @@ static int show_stat(struct seq_file *p, void *v)
(unsigned long long)cputime64_to_clock_t(guest),
(unsigned long long)cputime64_to_clock_t(guest_nice));
for_each_online_cpu(i) {
-
/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
user = kstat_cpu(i).cpustat.user;
nice = kstat_cpu(i).cpustat.nice;
system = kstat_cpu(i).cpustat.system;
- idle = kstat_cpu(i).cpustat.idle;
- idle = cputime64_add(idle, arch_idle_time(i));
- iowait = kstat_cpu(i).cpustat.iowait;
+ idle = get_idle_time(i);
+ iowait = get_iowait_time(i);
irq = kstat_cpu(i).cpustat.irq;
softirq = kstat_cpu(i).cpustat.softirq;
steal = kstat_cpu(i).cpustat.steal;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 25b6a887adb9..e418c5abdb0e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -44,6 +44,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
"VmPeak:\t%8lu kB\n"
"VmSize:\t%8lu kB\n"
"VmLck:\t%8lu kB\n"
+ "VmPin:\t%8lu kB\n"
"VmHWM:\t%8lu kB\n"
"VmRSS:\t%8lu kB\n"
"VmData:\t%8lu kB\n"
@@ -55,6 +56,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
hiwater_vm << (PAGE_SHIFT-10),
(total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
mm->locked_vm << (PAGE_SHIFT-10),
+ mm->pinned_vm << (PAGE_SHIFT-10),
hiwater_rss << (PAGE_SHIFT-10),
total_rss << (PAGE_SHIFT-10),
data << (PAGE_SHIFT-10),
@@ -877,30 +879,54 @@ struct numa_maps_private {
struct numa_maps md;
};
-static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty)
+static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty,
+ unsigned long nr_pages)
{
int count = page_mapcount(page);
- md->pages++;
+ md->pages += nr_pages;
if (pte_dirty || PageDirty(page))
- md->dirty++;
+ md->dirty += nr_pages;
if (PageSwapCache(page))
- md->swapcache++;
+ md->swapcache += nr_pages;
if (PageActive(page) || PageUnevictable(page))
- md->active++;
+ md->active += nr_pages;
if (PageWriteback(page))
- md->writeback++;
+ md->writeback += nr_pages;
if (PageAnon(page))
- md->anon++;
+ md->anon += nr_pages;
if (count > md->mapcount_max)
md->mapcount_max = count;
- md->node[page_to_nid(page)]++;
+ md->node[page_to_nid(page)] += nr_pages;
+}
+
+static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ struct page *page;
+ int nid;
+
+ if (!pte_present(pte))
+ return NULL;
+
+ page = vm_normal_page(vma, addr, pte);
+ if (!page)
+ return NULL;
+
+ if (PageReserved(page))
+ return NULL;
+
+ nid = page_to_nid(page);
+ if (!node_isset(nid, node_states[N_HIGH_MEMORY]))
+ return NULL;
+
+ return page;
}
static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
@@ -912,26 +938,32 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
pte_t *pte;
md = walk->private;
- orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
- do {
- struct page *page;
- int nid;
+ spin_lock(&walk->mm->page_table_lock);
+ if (pmd_trans_huge(*pmd)) {
+ if (pmd_trans_splitting(*pmd)) {
+ spin_unlock(&walk->mm->page_table_lock);
+ wait_split_huge_page(md->vma->anon_vma, pmd);
+ } else {
+ pte_t huge_pte = *(pte_t *)pmd;
+ struct page *page;
- if (!pte_present(*pte))
- continue;
+ page = can_gather_numa_stats(huge_pte, md->vma, addr);
+ if (page)
+ gather_stats(page, md, pte_dirty(huge_pte),
+ HPAGE_PMD_SIZE/PAGE_SIZE);
+ spin_unlock(&walk->mm->page_table_lock);
+ return 0;
+ }
+ } else {
+ spin_unlock(&walk->mm->page_table_lock);
+ }
- page = vm_normal_page(md->vma, addr, *pte);
+ orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+ do {
+ struct page *page = can_gather_numa_stats(*pte, md->vma, addr);
if (!page)
continue;
-
- if (PageReserved(page))
- continue;
-
- nid = page_to_nid(page);
- if (!node_isset(nid, node_states[N_HIGH_MEMORY]))
- continue;
-
- gather_stats(page, md, pte_dirty(*pte));
+ gather_stats(page, md, pte_dirty(*pte), 1);
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_unmap_unlock(orig_pte, ptl);
@@ -952,7 +984,7 @@ static int gather_hugetbl_stats(pte_t *pte, unsigned long hmask,
return 0;
md = walk->private;
- gather_stats(page, md, pte_dirty(*pte));
+ gather_stats(page, md, pte_dirty(*pte), 1);
return 0;
}
@@ -1009,6 +1041,9 @@ static int show_numa_map(struct seq_file *m, void *v)
seq_printf(m, " stack");
}
+ if (is_vm_hugetlb_page(vma))
+ seq_printf(m, " huge");
+
walk_page_range(vma->vm_start, vma->vm_end, &walk);
if (!md->pages)
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index cd99bf557650..b0f450a2bb7c 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -12,6 +12,7 @@
#include <linux/user.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
+#include <linux/export.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/bootmem.h>
generated by cgit (git 2.34.1) at 2025-05-20 17:12:16 +0000