2005-04-16 18:20:36 -04:00
|
|
|
/*
|
|
|
|
* linux/mm/mlock.c
|
|
|
|
*
|
|
|
|
* (C) Copyright 1995 Linus Torvalds
|
|
|
|
* (C) Copyright 2002 Christoph Hellwig
|
|
|
|
*/
|
|
|
|
|
2006-01-11 15:17:46 -05:00
|
|
|
#include <linux/capability.h>
|
2005-04-16 18:20:36 -04:00
|
|
|
#include <linux/mman.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/mempolicy.h>
|
|
|
|
#include <linux/syscalls.h>
|
Detach sched.h from mm.h
First thing mm.h does is including sched.h solely for can_do_mlock() inline
function which has "current" dereference inside. By dealing with can_do_mlock()
mm.h can be detached from sched.h which is good. See below, why.
This patch
a) removes unconditional inclusion of sched.h from mm.h
b) makes can_do_mlock() normal function in mm/mlock.c
c) exports can_do_mlock() to not break compilation
d) adds sched.h inclusions back to files that were getting it indirectly.
e) adds less bloated headers to some files (asm/signal.h, jiffies.h) that were
getting them indirectly
Net result is:
a) mm.h users would get less code to open, read, preprocess, parse, ... if
they don't need sched.h
b) sched.h stops being dependency for significant number of files:
on x86_64 allmodconfig touching sched.h results in recompile of 4083 files,
after patch it's only 3744 (-8.3%).
Cross-compile tested on
all arm defconfigs, all mips defconfigs, all powerpc defconfigs,
alpha alpha-up
arm
i386 i386-up i386-defconfig i386-allnoconfig
ia64 ia64-up
m68k
mips
parisc parisc-up
powerpc powerpc-up
s390 s390-up
sparc sparc-up
sparc64 sparc64-up
um-x86_64
x86_64 x86_64-up x86_64-defconfig x86_64-allnoconfig
as well as my two usual configs.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-20 17:22:52 -04:00
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/module.h>
|
2005-04-16 18:20:36 -04:00
|
|
|
|
Detach sched.h from mm.h
First thing mm.h does is including sched.h solely for can_do_mlock() inline
function which has "current" dereference inside. By dealing with can_do_mlock()
mm.h can be detached from sched.h which is good. See below, why.
This patch
a) removes unconditional inclusion of sched.h from mm.h
b) makes can_do_mlock() normal function in mm/mlock.c
c) exports can_do_mlock() to not break compilation
d) adds sched.h inclusions back to files that were getting it indirectly.
e) adds less bloated headers to some files (asm/signal.h, jiffies.h) that were
getting them indirectly
Net result is:
a) mm.h users would get less code to open, read, preprocess, parse, ... if
they don't need sched.h
b) sched.h stops being dependency for significant number of files:
on x86_64 allmodconfig touching sched.h results in recompile of 4083 files,
after patch it's only 3744 (-8.3%).
Cross-compile tested on
all arm defconfigs, all mips defconfigs, all powerpc defconfigs,
alpha alpha-up
arm
i386 i386-up i386-defconfig i386-allnoconfig
ia64 ia64-up
m68k
mips
parisc parisc-up
powerpc powerpc-up
s390 s390-up
sparc sparc-up
sparc64 sparc64-up
um-x86_64
x86_64 x86_64-up x86_64-defconfig x86_64-allnoconfig
as well as my two usual configs.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-20 17:22:52 -04:00
|
|
|
int can_do_mlock(void)
|
|
|
|
{
|
|
|
|
if (capable(CAP_IPC_LOCK))
|
|
|
|
return 1;
|
|
|
|
if (current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur != 0)
|
|
|
|
return 1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(can_do_mlock);
|
2005-04-16 18:20:36 -04:00
|
|
|
|
|
|
|
static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
|
|
|
|
unsigned long start, unsigned long end, unsigned int newflags)
|
|
|
|
{
|
|
|
|
struct mm_struct * mm = vma->vm_mm;
|
|
|
|
pgoff_t pgoff;
|
|
|
|
int pages;
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
if (newflags == vma->vm_flags) {
|
|
|
|
*prev = vma;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
|
|
|
|
*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
|
|
|
|
vma->vm_file, pgoff, vma_policy(vma));
|
|
|
|
if (*prev) {
|
|
|
|
vma = *prev;
|
|
|
|
goto success;
|
|
|
|
}
|
|
|
|
|
|
|
|
*prev = vma;
|
|
|
|
|
|
|
|
if (start != vma->vm_start) {
|
|
|
|
ret = split_vma(mm, vma, start, 1);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (end != vma->vm_end) {
|
|
|
|
ret = split_vma(mm, vma, end, 0);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
success:
|
|
|
|
/*
|
|
|
|
* vm_flags is protected by the mmap_sem held in write mode.
|
|
|
|
* It's okay if try_to_unmap_one unmaps a page just after we
|
|
|
|
* set VM_LOCKED, make_pages_present below will bring it back.
|
|
|
|
*/
|
|
|
|
vma->vm_flags = newflags;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Keep track of amount of locked VM.
|
|
|
|
*/
|
|
|
|
pages = (end - start) >> PAGE_SHIFT;
|
|
|
|
if (newflags & VM_LOCKED) {
|
|
|
|
pages = -pages;
|
|
|
|
if (!(newflags & VM_IO))
|
|
|
|
ret = make_pages_present(start, end);
|
|
|
|
}
|
|
|
|
|
2006-12-06 23:32:25 -05:00
|
|
|
mm->locked_vm -= pages;
|
2005-04-16 18:20:36 -04:00
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int do_mlock(unsigned long start, size_t len, int on)
|
|
|
|
{
|
|
|
|
unsigned long nstart, end, tmp;
|
|
|
|
struct vm_area_struct * vma, * prev;
|
|
|
|
int error;
|
|
|
|
|
|
|
|
len = PAGE_ALIGN(len);
|
|
|
|
end = start + len;
|
|
|
|
if (end < start)
|
|
|
|
return -EINVAL;
|
|
|
|
if (end == start)
|
|
|
|
return 0;
|
|
|
|
vma = find_vma_prev(current->mm, start, &prev);
|
|
|
|
if (!vma || vma->vm_start > start)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
if (start > vma->vm_start)
|
|
|
|
prev = vma;
|
|
|
|
|
|
|
|
for (nstart = start ; ; ) {
|
|
|
|
unsigned int newflags;
|
|
|
|
|
|
|
|
/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
|
|
|
|
|
|
|
|
newflags = vma->vm_flags | VM_LOCKED;
|
|
|
|
if (!on)
|
|
|
|
newflags &= ~VM_LOCKED;
|
|
|
|
|
|
|
|
tmp = vma->vm_end;
|
|
|
|
if (tmp > end)
|
|
|
|
tmp = end;
|
|
|
|
error = mlock_fixup(vma, &prev, nstart, tmp, newflags);
|
|
|
|
if (error)
|
|
|
|
break;
|
|
|
|
nstart = tmp;
|
|
|
|
if (nstart < prev->vm_end)
|
|
|
|
nstart = prev->vm_end;
|
|
|
|
if (nstart >= end)
|
|
|
|
break;
|
|
|
|
|
|
|
|
vma = prev->vm_next;
|
|
|
|
if (!vma || vma->vm_start != nstart) {
|
|
|
|
error = -ENOMEM;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage long sys_mlock(unsigned long start, size_t len)
|
|
|
|
{
|
|
|
|
unsigned long locked;
|
|
|
|
unsigned long lock_limit;
|
|
|
|
int error = -ENOMEM;
|
|
|
|
|
|
|
|
if (!can_do_mlock())
|
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
down_write(¤t->mm->mmap_sem);
|
|
|
|
len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
|
|
|
|
start &= PAGE_MASK;
|
|
|
|
|
|
|
|
locked = len >> PAGE_SHIFT;
|
|
|
|
locked += current->mm->locked_vm;
|
|
|
|
|
|
|
|
lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
|
|
|
|
lock_limit >>= PAGE_SHIFT;
|
|
|
|
|
|
|
|
/* check against resource limits */
|
|
|
|
if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
|
|
|
|
error = do_mlock(start, len, 1);
|
|
|
|
up_write(¤t->mm->mmap_sem);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage long sys_munlock(unsigned long start, size_t len)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
down_write(¤t->mm->mmap_sem);
|
|
|
|
len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
|
|
|
|
start &= PAGE_MASK;
|
|
|
|
ret = do_mlock(start, len, 0);
|
|
|
|
up_write(¤t->mm->mmap_sem);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int do_mlockall(int flags)
|
|
|
|
{
|
|
|
|
struct vm_area_struct * vma, * prev = NULL;
|
|
|
|
unsigned int def_flags = 0;
|
|
|
|
|
|
|
|
if (flags & MCL_FUTURE)
|
|
|
|
def_flags = VM_LOCKED;
|
|
|
|
current->mm->def_flags = def_flags;
|
|
|
|
if (flags == MCL_FUTURE)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
|
|
|
|
unsigned int newflags;
|
|
|
|
|
|
|
|
newflags = vma->vm_flags | VM_LOCKED;
|
|
|
|
if (!(flags & MCL_CURRENT))
|
|
|
|
newflags &= ~VM_LOCKED;
|
|
|
|
|
|
|
|
/* Ignore errors */
|
|
|
|
mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
|
|
|
|
}
|
|
|
|
out:
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage long sys_mlockall(int flags)
|
|
|
|
{
|
|
|
|
unsigned long lock_limit;
|
|
|
|
int ret = -EINVAL;
|
|
|
|
|
|
|
|
if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE)))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
ret = -EPERM;
|
|
|
|
if (!can_do_mlock())
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
down_write(¤t->mm->mmap_sem);
|
|
|
|
|
|
|
|
lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
|
|
|
|
lock_limit >>= PAGE_SHIFT;
|
|
|
|
|
|
|
|
ret = -ENOMEM;
|
|
|
|
if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
|
|
|
|
capable(CAP_IPC_LOCK))
|
|
|
|
ret = do_mlockall(flags);
|
|
|
|
up_write(¤t->mm->mmap_sem);
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage long sys_munlockall(void)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
down_write(¤t->mm->mmap_sem);
|
|
|
|
ret = do_mlockall(0);
|
|
|
|
up_write(¤t->mm->mmap_sem);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Objects with different lifetime than processes (SHM_LOCK and SHM_HUGETLB
|
|
|
|
* shm segments) get accounted against the user_struct instead.
|
|
|
|
*/
|
|
|
|
static DEFINE_SPINLOCK(shmlock_user_lock);
|
|
|
|
|
|
|
|
int user_shm_lock(size_t size, struct user_struct *user)
|
|
|
|
{
|
|
|
|
unsigned long lock_limit, locked;
|
|
|
|
int allowed = 0;
|
|
|
|
|
|
|
|
locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
|
|
|
|
lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur;
|
2007-07-16 02:38:25 -04:00
|
|
|
if (lock_limit == RLIM_INFINITY)
|
|
|
|
allowed = 1;
|
2005-04-16 18:20:36 -04:00
|
|
|
lock_limit >>= PAGE_SHIFT;
|
|
|
|
spin_lock(&shmlock_user_lock);
|
2007-07-16 02:38:25 -04:00
|
|
|
if (!allowed &&
|
|
|
|
locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
|
2005-04-16 18:20:36 -04:00
|
|
|
goto out;
|
|
|
|
get_uid(user);
|
|
|
|
user->locked_shm += locked;
|
|
|
|
allowed = 1;
|
|
|
|
out:
|
|
|
|
spin_unlock(&shmlock_user_lock);
|
|
|
|
return allowed;
|
|
|
|
}
|
|
|
|
|
|
|
|
void user_shm_unlock(size_t size, struct user_struct *user)
|
|
|
|
{
|
|
|
|
spin_lock(&shmlock_user_lock);
|
|
|
|
user->locked_shm -= (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
|
|
|
|
spin_unlock(&shmlock_user_lock);
|
|
|
|
free_uid(user);
|
|
|
|
}
|