linux_dsm_epyc7002/fs/proc/nommu.c
David Howells 8feae13110 NOMMU: Make VMAs per MM as for MMU-mode linux
Make VMAs per mm_struct as for MMU-mode linux.  This solves two problems:

 (1) In SYSV SHM where nattch for a segment does not reflect the number of
     shmat's (and forks) done.

 (2) In mmap() where the VMA's vm_mm is set to point to the parent mm by an
     exec'ing process when VM_EXECUTABLE is specified, regardless of the fact
     that a VMA might be shared and already have its vm_mm assigned to another
     process or a dead process.

A new struct (vm_region) is introduced to track a mapped region and to remember
the circumstances under which it may be shared and the vm_list_struct structure
is discarded as it's no longer required.

This patch makes the following additional changes:

 (1) Regions are now allocated with alloc_pages() rather than kmalloc() and
     with no recourse to __GFP_COMP, so the pages are not composite.  Instead,
     each page has a reference on it held by the region.  Anything else that is
     interested in such a page will have to get a reference on it to retain it.
     When the pages are released due to unmapping, each page is passed to
     put_page() and will be freed when the page usage count reaches zero.

 (2) Excess pages are trimmed after an allocation as the allocation must be
     made as a power-of-2 quantity of pages.

 (3) VMAs are added to the parent MM's R/B tree and mmap lists.  As an MM may
     end up with overlapping VMAs within the tree, the VMA struct address is
     appended to the sort key.

 (4) Non-anonymous VMAs are now added to the backing inode's prio list.

 (5) Holes may be punched in anonymous VMAs with munmap(), releasing parts of
     the backing region.  The VMA and region structs will be split if
     necessary.

 (6) sys_shmdt() only releases one attachment to a SYSV IPC shared memory
     segment instead of all the attachments at that addresss.  Multiple
     shmat()'s return the same address under NOMMU-mode instead of different
     virtual addresses as under MMU-mode.

 (7) Core dumping for ELF-FDPIC requires fewer exceptions for NOMMU-mode.

 (8) /proc/maps is now the global list of mapped regions, and may list bits
     that aren't actually mapped anywhere.

 (9) /proc/meminfo gains a line (tagged "MmapCopy") that indicates the amount
     of RAM currently allocated by mmap to hold mappable regions that can't be
     mapped directly.  These are copies of the backing device or file if not
     anonymous.

These changes make NOMMU mode more similar to MMU mode.  The downside is that
NOMMU mode requires some extra memory to track things over NOMMU without this
patch (VMAs are no longer shared, and there are now region structs).

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Mike Frysinger <vapier.adi@gmail.com>
Acked-by: Paul Mundt <lethal@linux-sh.org>
2009-01-08 12:04:47 +00:00

138 lines
3.3 KiB
C

/* nommu.c: mmu-less memory info files
*
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/mman.h>
#include <linux/proc_fs.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/seq_file.h>
#include <linux/hugetlb.h>
#include <linux/vmalloc.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/tlb.h>
#include <asm/div64.h>
#include "internal.h"
/*
* display a single region to a sequenced file
*/
static int nommu_region_show(struct seq_file *m, struct vm_region *region)
{
unsigned long ino = 0;
struct file *file;
dev_t dev = 0;
int flags, len;
flags = region->vm_flags;
file = region->vm_file;
if (file) {
struct inode *inode = region->vm_file->f_path.dentry->d_inode;
dev = inode->i_sb->s_dev;
ino = inode->i_ino;
}
seq_printf(m,
"%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
region->vm_start,
region->vm_end,
flags & VM_READ ? 'r' : '-',
flags & VM_WRITE ? 'w' : '-',
flags & VM_EXEC ? 'x' : '-',
flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p',
((loff_t)region->vm_pgoff) << PAGE_SHIFT,
MAJOR(dev), MINOR(dev), ino, &len);
if (file) {
len = 25 + sizeof(void *) * 6 - len;
if (len < 1)
len = 1;
seq_printf(m, "%*c", len, ' ');
seq_path(m, &file->f_path, "");
}
seq_putc(m, '\n');
return 0;
}
/*
* display a list of all the REGIONs the kernel knows about
* - nommu kernals have a single flat list
*/
static int nommu_region_list_show(struct seq_file *m, void *_p)
{
struct rb_node *p = _p;
return nommu_region_show(m, rb_entry(p, struct vm_region, vm_rb));
}
static void *nommu_region_list_start(struct seq_file *m, loff_t *_pos)
{
struct rb_node *p;
loff_t pos = *_pos;
down_read(&nommu_region_sem);
for (p = rb_first(&nommu_region_tree); p; p = rb_next(p))
if (pos-- == 0)
return p;
return NULL;
}
static void nommu_region_list_stop(struct seq_file *m, void *v)
{
up_read(&nommu_region_sem);
}
static void *nommu_region_list_next(struct seq_file *m, void *v, loff_t *pos)
{
(*pos)++;
return rb_next((struct rb_node *) v);
}
static struct seq_operations proc_nommu_region_list_seqop = {
.start = nommu_region_list_start,
.next = nommu_region_list_next,
.stop = nommu_region_list_stop,
.show = nommu_region_list_show
};
static int proc_nommu_region_list_open(struct inode *inode, struct file *file)
{
return seq_open(file, &proc_nommu_region_list_seqop);
}
static const struct file_operations proc_nommu_region_list_operations = {
.open = proc_nommu_region_list_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static int __init proc_nommu_init(void)
{
proc_create("maps", S_IRUGO, NULL, &proc_nommu_region_list_operations);
return 0;
}
module_init(proc_nommu_init);