path: root/fs/proc/task_mmu.c

#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/huge_mm.h>
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/highmem.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mmu_notifier.h>

#include <asm/elf.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include "internal.h"

void task_mem(struct seq_file *m, struct mm_struct *mm)
{
	unsigned long data, text, lib, swap;
	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;

	/*
	 * Note: to minimize their overhead, mm maintains hiwater_vm and
	 * hiwater_rss only when about to *lower* total_vm or rss.  Any
	 * collector of these hiwater stats must therefore get total_vm
	 * and rss too, which will usually be the higher.  Barriers? not
	 * worth the effort, such snapshots can always be inconsistent.
	 */
	hiwater_vm = total_vm = mm->total_vm;
	if (hiwater_vm < mm->hiwater_vm)
		hiwater_vm = mm->hiwater_vm;
	hiwater_rss = total_rss = get_mm_rss(mm);
	if (hiwater_rss < mm->hiwater_rss)
		hiwater_rss = mm->hiwater_rss;

	data = mm->total_vm - mm->shared_vm - mm->stack_vm;
	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
	swap = get_mm_counter(mm, MM_SWAPENTS);
	seq_printf(m,
		"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"
		"VmStk:\t%8lu kB\n"
		"VmExe:\t%8lu kB\n"
		"VmLib:\t%8lu kB\n"
		"VmPTE:\t%8lu kB\n"
		"VmSwap:\t%8lu kB\n",
		hiwater_vm << (PAGE_SHIFT-10),
		total_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),
		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
		(PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10,
		swap << (PAGE_SHIFT-10));
}

unsigned long task_vsize(struct mm_struct *mm)
{
	return PAGE_SIZE * mm->total_vm;
}

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);
	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
								>> PAGE_SHIFT;
	*data = mm->total_vm - mm->shared_vm;
	*resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
	return mm->total_vm;
}

static void pad_len_spaces(struct seq_file *m, int len)
{
	len = 25 + sizeof(void*) * 6 - len;
	if (len < 1)
		len = 1;
	seq_printf(m, "%*c", len, ' ');
}

#ifdef CONFIG_NUMA
/*
 * These functions are for numa_maps but called in generic **maps seq_file
 * ->start(), ->stop() ops.
 *
 * numa_maps scans all vmas under mmap_sem and checks their mempolicy.
 * Each mempolicy object is controlled by reference counting. The problem here
 * is how to avoid accessing dead mempolicy object.
 *
 * Because we're holding mmap_sem while reading seq_file, it's safe to access
 * each vma's mempolicy, no vma objects will never drop refs to mempolicy.
 *
 * A task's mempolicy (task->mempolicy) has different behavior. task->mempolicy
 * is set and replaced under mmap_sem but unrefed and cleared under task_lock().
 * So, without task_lock(), we cannot trust get_vma_policy() because we cannot
 * gurantee the task never exits under us. But taking task_lock() around
 * get_vma_plicy() causes lock order problem.
 *
 * To access task->mempolicy without lock, we hold a reference count of an
 * object pointed by task->mempolicy and remember it. This will guarantee
 * that task->mempolicy points to an alive object or NULL in numa_maps accesses.
 */
static void hold_task_mempolicy(struct proc_maps_private *priv)
{
	struct task_struct *task = priv->task;

	task_lock(task);
	priv->task_mempolicy = task->mempolicy;
	mpol_get(priv->task_mempolicy);
	task_unlock(task);
}
static void release_task_mempolicy(struct proc_maps_private *priv)
{
	mpol_put(priv->task_mempolicy);
}
#else
static void hold_task_mempolicy(struct proc_maps_private *priv)
{
}
static void release_task_mempolicy(struct proc_maps_private *priv)
{
}
#endif

static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
{
	if (vma && vma != priv->tail_vma) {
		struct mm_struct *mm = vma->vm_mm;
		release_task_mempolicy(priv);
		up_read(&mm->mmap_sem);
		mmput(mm);
	}
}

static void *m_start(struct seq_file *m, loff_t *pos)
{
	struct proc_maps_private *priv = m->private;
	unsigned long last_addr = m->version;
	struct mm_struct *mm;
	struct vm_area_struct *vma, *tail_vma = NULL;
	loff_t l = *pos;

	/* Clear the per syscall fields in priv */
	priv->task = NULL;
	priv->tail_vma = NULL;

	/*
	 * We remember last_addr rather than next_addr to hit with
	 * mmap_cache most of the time. We have zero last_addr at
	 * the beginning and also after lseek. We will have -1 last_addr
	 * after the end of the vmas.
	 */

	if (last_addr == -1UL)
		return NULL;

	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
	if (!priv->task)
		return ERR_PTR(-ESRCH);

	mm = mm_access(priv->task, PTRACE_MODE_READ);
	if (!mm || IS_ERR(mm))
		return mm;
	down_read(&mm->mmap_sem);

	tail_vma = get_gate_vma(priv->task->mm);
	priv->tail_vma = tail_vma;
	hold_task_mempolicy(priv);
	/* Start with last addr hint */
	vma = find_vma(mm, last_addr);
	if (last_addr && vma) {
		vma = vma->vm_next;
		goto out;
	}

	/*
	 * Check the vma index is within the range and do
	 * sequential scan until m_index.
	 */
	vma = NULL;
	if ((unsigned long)l < mm->map_count) {
		vma = mm->mmap;
		while (l-- && vma)
			vma = vma->vm_next;
		goto out;
	}

	if (l != mm->map_count)
		tail_vma = NULL; /* After gate vma */

out:
	if (vma)
		return vma;

	release_task_mempolicy(priv);
	/* End of vmas has been reached */
	m->version = (tail_vma != NULL)? 0: -1UL;
	up_read(&mm->mmap_sem);
	mmput(mm);
	return tail_vma;
}

static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct proc_maps_private *priv = m->private;
	struct vm_area_struct *vma = v;
	struct vm_area_struct *tail_vma = priv->tail_vma;

	(*pos)++;
	if (vma && (vma != tail_vma) && vma->vm_next)
		return vma->vm_next;
	vma_stop(priv, vma);
	return (vma != tail_vma)? tail_vma: NULL;
}

static void m_stop(struct seq_file *m, void *v)
{
	struct proc_maps_private *priv = m->private;
	struct vm_area_struct *vma = v;

	if (!IS_ERR(vma))
		vma_stop(priv, vma);
	if (priv->task)
		put_task_struct(priv->task);
}

static int do_maps_open(struct inode *inode, struct file *file,
			const struct seq_operations *ops)
{
	struct proc_maps_private *priv;
	int ret = -ENOMEM;
	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
	if (priv) {
		priv->pid = proc_pid(inode);
		ret = seq_open(file, ops);
		if (!ret) {
			struct seq_file *m = file->private_data;
			m->private = priv;
		} else {
			kfree(priv);
		}
	}
	return ret;
}

static void
show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
{
	struct mm_struct *mm = vma->vm_mm;
	struct file *file = vma->vm_file;
	struct proc_maps_private *priv = m->private;
	struct task_struct *task = priv->task;
	vm_flags_t flags = vma->vm_flags;
	unsigned long ino = 0;
	unsigned long long pgoff = 0;
	unsigned long start, end;
	dev_t dev = 0;
	int len;
	const char *name = NULL;

	if (file) {
		struct inode *inode = file_inode(vma->vm_file);
		dev = inode->i_sb->s_dev;
		ino = inode->i_ino;
		pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
	}

	/* We don't show the stack guard page in /proc/maps */
	start = vma->vm_start;
	if (stack_guard_page_start(vma, start))
		start += PAGE_SIZE;
	end = vma->vm_end;
	if (stack_guard_page_end(vma, end))
		end -= PAGE_SIZE;

	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
			start,
			end,
			flags & VM_READ ? 'r' : '-',
			flags & VM_WRITE ? 'w' : '-',
			flags & VM_EXEC ? 'x' : '-'