linux/mm/mlock.c
KOSAKI Motohiro 8891d6da17 mm: remove lru_add_drain_all() from the munlock path
lockdep warns about following message at boot time on one of my test
machine.  Then, schedule_on_each_cpu() sholdn't be called when the task
have mmap_sem.

Actually, lru_add_drain_all() exist to prevent the unevictalble pages
stay on reclaimable lru list.  but currenct unevictable code can rescue
unevictable pages although it stay on reclaimable list.

So removing is better.

In addition, this patch add lru_add_drain_all() to sys_mlock() and
sys_mlockall().  it isn't must.  but it reduce the failure of moving to
unevictable list.  its failure can rescue in vmscan later.  but reducing
is better.

Note, if above rescuing happend, the Mlocked and the Unevictable field
mismatching happend in /proc/meminfo.  but it doesn't cause any real
trouble.

=======================================================
[ INFO: possible circular locking dependency detected ]
2.6.28-rc2-mm1 #2
-------------------------------------------------------
lvm/1103 is trying to acquire lock:
 (&cpu_hotplug.lock){--..}, at: [<c0130789>] get_online_cpus+0x29/0x50

but task is already holding lock:
 (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #3 (&mm->mmap_sem){----}:
       [<c0153da2>] check_noncircular+0x82/0x110
       [<c0185e6a>] might_fault+0x4a/0xa0
       [<c0156161>] validate_chain+0xb11/0x1070
       [<c0185e6a>] might_fault+0x4a/0xa0
       [<c0156923>] __lock_acquire+0x263/0xa10
       [<c015714c>] lock_acquire+0x7c/0xb0			(*) grab mmap_sem
       [<c0185e6a>] might_fault+0x4a/0xa0
       [<c0185e9b>] might_fault+0x7b/0xa0
       [<c0185e6a>] might_fault+0x4a/0xa0
       [<c0294dd0>] copy_to_user+0x30/0x60
       [<c01ae3ec>] filldir+0x7c/0xd0
       [<c01e3a6a>] sysfs_readdir+0x11a/0x1f0			(*) grab sysfs_mutex
       [<c01ae370>] filldir+0x0/0xd0
       [<c01ae370>] filldir+0x0/0xd0
       [<c01ae4c6>] vfs_readdir+0x86/0xa0			(*) grab i_mutex
       [<c01ae75b>] sys_getdents+0x6b/0xc0
       [<c010355a>] syscall_call+0x7/0xb
       [<ffffffff>] 0xffffffff

-> #2 (sysfs_mutex){--..}:
       [<c0153da2>] check_noncircular+0x82/0x110
       [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0
       [<c0156161>] validate_chain+0xb11/0x1070
       [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0
       [<c0156923>] __lock_acquire+0x263/0xa10
       [<c015714c>] lock_acquire+0x7c/0xb0			(*) grab sysfs_mutex
       [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0
       [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0
       [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0
       [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0
       [<c01e3d2c>] sysfs_addrm_start+0x2c/0xc0
       [<c01e422f>] create_dir+0x3f/0x90
       [<c01e42a9>] sysfs_create_dir+0x29/0x50
       [<c04faaf5>] _spin_unlock+0x25/0x40
       [<c028f21d>] kobject_add_internal+0xcd/0x1a0
       [<c028f37a>] kobject_set_name_vargs+0x3a/0x50
       [<c028f41d>] kobject_init_and_add+0x2d/0x40
       [<c019d4d2>] sysfs_slab_add+0xd2/0x180
       [<c019d580>] sysfs_add_func+0x0/0x70
       [<c019d5dc>] sysfs_add_func+0x5c/0x70			(*) grab slub_lock
       [<c01400f2>] run_workqueue+0x172/0x200
       [<c014008f>] run_workqueue+0x10f/0x200
       [<c0140bd0>] worker_thread+0x0/0xf0
       [<c0140c6c>] worker_thread+0x9c/0xf0
       [<c0143c80>] autoremove_wake_function+0x0/0x50
       [<c0140bd0>] worker_thread+0x0/0xf0
       [<c0143972>] kthread+0x42/0x70
       [<c0143930>] kthread+0x0/0x70
       [<c01042db>] kernel_thread_helper+0x7/0x1c
       [<ffffffff>] 0xffffffff

-> #1 (slub_lock){----}:
       [<c0153d2d>] check_noncircular+0xd/0x110
       [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0
       [<c0156161>] validate_chain+0xb11/0x1070
       [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0
       [<c015433d>] mark_lock+0x35d/0xd00
       [<c0156923>] __lock_acquire+0x263/0xa10
       [<c015714c>] lock_acquire+0x7c/0xb0
       [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0
       [<c04f93a3>] down_read+0x43/0x80
       [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0		(*) grab slub_lock
       [<c04f650f>] slab_cpuup_callback+0x11f/0x1d0
       [<c04fd9ac>] notifier_call_chain+0x3c/0x70
       [<c04f5454>] _cpu_up+0x84/0x110
       [<c04f552b>] cpu_up+0x4b/0x70				(*) grab cpu_hotplug.lock
       [<c06d1530>] kernel_init+0x0/0x170
       [<c06d15e5>] kernel_init+0xb5/0x170
       [<c06d1530>] kernel_init+0x0/0x170
       [<c01042db>] kernel_thread_helper+0x7/0x1c
       [<ffffffff>] 0xffffffff

-> #0 (&cpu_hotplug.lock){--..}:
       [<c0155bff>] validate_chain+0x5af/0x1070
       [<c040f7e0>] dev_status+0x0/0x50
       [<c0156923>] __lock_acquire+0x263/0xa10
       [<c015714c>] lock_acquire+0x7c/0xb0
       [<c0130789>] get_online_cpus+0x29/0x50
       [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0
       [<c0130789>] get_online_cpus+0x29/0x50
       [<c0130789>] get_online_cpus+0x29/0x50
       [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10
       [<c0130789>] get_online_cpus+0x29/0x50			(*) grab cpu_hotplug.lock
       [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0
       [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0
       [<c0156945>] __lock_acquire+0x285/0xa10
       [<c0188f09>] vma_merge+0xa9/0x1d0
       [<c0187450>] mlock_fixup+0x180/0x200
       [<c0187548>] do_mlockall+0x78/0x90			(*) grab mmap_sem
       [<c01878e1>] sys_mlockall+0x81/0xb0
       [<c010355a>] syscall_call+0x7/0xb
       [<ffffffff>] 0xffffffff

other info that might help us debug this:

1 lock held by lvm/1103:
 #0:  (&mm->mmap_sem){----}, at: [<c01878ae>] sys_mlockall+0x4e/0xb0

stack backtrace:
Pid: 1103, comm: lvm Not tainted 2.6.28-rc2-mm1 #2
Call Trace:
 [<c01555fc>] print_circular_bug_tail+0x7c/0xd0
 [<c0155bff>] validate_chain+0x5af/0x1070
 [<c040f7e0>] dev_status+0x0/0x50
 [<c0156923>] __lock_acquire+0x263/0xa10
 [<c015714c>] lock_acquire+0x7c/0xb0
 [<c0130789>] get_online_cpus+0x29/0x50
 [<c04f8b55>] mutex_lock_nested+0xa5/0x2f0
 [<c0130789>] get_online_cpus+0x29/0x50
 [<c0130789>] get_online_cpus+0x29/0x50
 [<c017bc30>] lru_add_drain_per_cpu+0x0/0x10
 [<c0130789>] get_online_cpus+0x29/0x50
 [<c0140cf2>] schedule_on_each_cpu+0x32/0xe0
 [<c0187095>] __mlock_vma_pages_range+0x85/0x2c0
 [<c0156945>] __lock_acquire+0x285/0xa10
 [<c0188f09>] vma_merge+0xa9/0x1d0
 [<c0187450>] mlock_fixup+0x180/0x200
 [<c0187548>] do_mlockall+0x78/0x90
 [<c01878e1>] sys_mlockall+0x81/0xb0
 [<c010355a>] syscall_call+0x7/0xb

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Tested-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-12 17:17:16 -08:00

670 lines
17 KiB
C

/*
* linux/mm/mlock.c
*
* (C) Copyright 1995 Linus Torvalds
* (C) Copyright 2002 Christoph Hellwig
*/
#include <linux/capability.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>
#include "internal.h"
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);
#ifdef CONFIG_UNEVICTABLE_LRU
/*
* Mlocked pages are marked with PageMlocked() flag for efficient testing
* in vmscan and, possibly, the fault path; and to support semi-accurate
* statistics.
*
* An mlocked page [PageMlocked(page)] is unevictable. As such, it will
* be placed on the LRU "unevictable" list, rather than the [in]active lists.
* The unevictable list is an LRU sibling list to the [in]active lists.
* PageUnevictable is set to indicate the unevictable state.
*
* When lazy mlocking via vmscan, it is important to ensure that the
* vma's VM_LOCKED status is not concurrently being modified, otherwise we
* may have mlocked a page that is being munlocked. So lazy mlock must take
* the mmap_sem for read, and verify that the vma really is locked
* (see mm/rmap.c).
*/
/*
* LRU accounting for clear_page_mlock()
*/
void __clear_page_mlock(struct page *page)
{
VM_BUG_ON(!PageLocked(page));
if (!page->mapping) { /* truncated ? */
return;
}
dec_zone_page_state(page, NR_MLOCK);
count_vm_event(UNEVICTABLE_PGCLEARED);
if (!isolate_lru_page(page)) {
putback_lru_page(page);
} else {
/*
* We lost the race. the page already moved to evictable list.
*/
if (PageUnevictable(page))
count_vm_event(UNEVICTABLE_PGSTRANDED);
}
}
/*
* Mark page as mlocked if not already.
* If page on LRU, isolate and putback to move to unevictable list.
*/
void mlock_vma_page(struct page *page)
{
BUG_ON(!PageLocked(page));
if (!TestSetPageMlocked(page)) {
inc_zone_page_state(page, NR_MLOCK);
count_vm_event(UNEVICTABLE_PGMLOCKED);
if (!isolate_lru_page(page))
putback_lru_page(page);
}
}
/*
* called from munlock()/munmap() path with page supposedly on the LRU.
*
* Note: unlike mlock_vma_page(), we can't just clear the PageMlocked
* [in try_to_munlock()] and then attempt to isolate the page. We must
* isolate the page to keep others from messing with its unevictable
* and mlocked state while trying to munlock. However, we pre-clear the
* mlocked state anyway as we might lose the isolation race and we might
* not get another chance to clear PageMlocked. If we successfully
* isolate the page and try_to_munlock() detects other VM_LOCKED vmas
* mapping the page, it will restore the PageMlocked state, unless the page
* is mapped in a non-linear vma. So, we go ahead and SetPageMlocked(),
* perhaps redundantly.
* If we lose the isolation race, and the page is mapped by other VM_LOCKED
* vmas, we'll detect this in vmscan--via try_to_munlock() or try_to_unmap()
* either of which will restore the PageMlocked state by calling
* mlock_vma_page() above, if it can grab the vma's mmap sem.
*/
static void munlock_vma_page(struct page *page)
{
BUG_ON(!PageLocked(page));
if (TestClearPageMlocked(page)) {
dec_zone_page_state(page, NR_MLOCK);
if (!isolate_lru_page(page)) {
int ret = try_to_munlock(page);
/*
* did try_to_unlock() succeed or punt?
*/
if (ret == SWAP_SUCCESS || ret == SWAP_AGAIN)
count_vm_event(UNEVICTABLE_PGMUNLOCKED);
putback_lru_page(page);
} else {
/*
* We lost the race. let try_to_unmap() deal
* with it. At least we get the page state and
* mlock stats right. However, page is still on
* the noreclaim list. We'll fix that up when
* the page is eventually freed or we scan the
* noreclaim list.
*/
if (PageUnevictable(page))
count_vm_event(UNEVICTABLE_PGSTRANDED);
else
count_vm_event(UNEVICTABLE_PGMUNLOCKED);
}
}
}
/**
* __mlock_vma_pages_range() - mlock/munlock a range of pages in the vma.
* @vma: target vma
* @start: start address
* @end: end address
* @mlock: 0 indicate munlock, otherwise mlock.
*
* If @mlock == 0, unlock an mlocked range;
* else mlock the range of pages. This takes care of making the pages present ,
* too.
*
* return 0 on success, negative error code on error.
*
* vma->vm_mm->mmap_sem must be held for at least read.
*/
static long __mlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
int mlock)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long addr = start;
struct page *pages[16]; /* 16 gives a reasonable batch */
int nr_pages = (end - start) / PAGE_SIZE;
int ret;
int gup_flags = 0;
VM_BUG_ON(start & ~PAGE_MASK);
VM_BUG_ON(end & ~PAGE_MASK);
VM_BUG_ON(start < vma->vm_start);
VM_BUG_ON(end > vma->vm_end);
VM_BUG_ON((!rwsem_is_locked(&mm->mmap_sem)) &&
(atomic_read(&mm->mm_users) != 0));
/*
* mlock: don't page populate if page has PROT_NONE permission.
* munlock: the pages always do munlock althrough
* its has PROT_NONE permission.
*/
if (!mlock)
gup_flags |= GUP_FLAGS_IGNORE_VMA_PERMISSIONS;
if (vma->vm_flags & VM_WRITE)
gup_flags |= GUP_FLAGS_WRITE;
while (nr_pages > 0) {
int i;
cond_resched();
/*
* get_user_pages makes pages present if we are
* setting mlock. and this extra reference count will
* disable migration of this page. However, page may
* still be truncated out from under us.
*/
ret = __get_user_pages(current, mm, addr,
min_t(int, nr_pages, ARRAY_SIZE(pages)),
gup_flags, pages, NULL);
/*
* This can happen for, e.g., VM_NONLINEAR regions before
* a page has been allocated and mapped at a given offset,
* or for addresses that map beyond end of a file.
* We'll mlock the the pages if/when they get faulted in.
*/
if (ret < 0)
break;
if (ret == 0) {
/*
* We know the vma is there, so the only time
* we cannot get a single page should be an
* error (ret < 0) case.
*/
WARN_ON(1);
break;
}
lru_add_drain(); /* push cached pages to LRU */
for (i = 0; i < ret; i++) {
struct page *page = pages[i];
lock_page(page);
/*
* Because we lock page here and migration is blocked
* by the elevated reference, we need only check for
* page truncation (file-cache only).
*/
if (page->mapping) {
if (mlock)
mlock_vma_page(page);
else
munlock_vma_page(page);
}
unlock_page(page);
put_page(page); /* ref from get_user_pages() */
/*
* here we assume that get_user_pages() has given us
* a list of virtually contiguous pages.
*/
addr += PAGE_SIZE; /* for next get_user_pages() */
nr_pages--;
}
ret = 0;
}
return ret; /* count entire vma as locked_vm */
}
/*
* convert get_user_pages() return value to posix mlock() error
*/
static int __mlock_posix_error_return(long retval)
{
if (retval == -EFAULT)
retval = -ENOMEM;
else if (retval == -ENOMEM)
retval = -EAGAIN;
return retval;
}
#else /* CONFIG_UNEVICTABLE_LRU */
/*
* Just make pages present if VM_LOCKED. No-op if unlocking.
*/
static long __mlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
int mlock)
{
if (mlock && (vma->vm_flags & VM_LOCKED))
return make_pages_present(start, end);
return 0;
}
static inline int __mlock_posix_error_return(long retval)
{
return 0;
}
#endif /* CONFIG_UNEVICTABLE_LRU */
/**
* mlock_vma_pages_range() - mlock pages in specified vma range.
* @vma - the vma containing the specfied address range
* @start - starting address in @vma to mlock
* @end - end address [+1] in @vma to mlock
*
* For mmap()/mremap()/expansion of mlocked vma.
*
* return 0 on success for "normal" vmas.
*
* return number of pages [> 0] to be removed from locked_vm on success
* of "special" vmas.
*
* return negative error if vma spanning @start-@range disappears while
* mmap semaphore is dropped. Unlikely?
*/
long mlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
int nr_pages = (end - start) / PAGE_SIZE;
BUG_ON(!(vma->vm_flags & VM_LOCKED));
/*
* filter unlockable vmas
*/
if (vma->vm_flags & (VM_IO | VM_PFNMAP))
goto no_mlock;
if (!((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
is_vm_hugetlb_page(vma) ||
vma == get_gate_vma(current))) {
long error;
downgrade_write(&mm->mmap_sem);
error = __mlock_vma_pages_range(vma, start, end, 1);
up_read(&mm->mmap_sem);
/* vma can change or disappear */
down_write(&mm->mmap_sem);
vma = find_vma(mm, start);
/* non-NULL vma must contain @start, but need to check @end */
if (!vma || end > vma->vm_end)
return -ENOMEM;
return 0; /* hide other errors from mmap(), et al */
}
/*
* User mapped kernel pages or huge pages:
* make these pages present to populate the ptes, but
* fall thru' to reset VM_LOCKED--no need to unlock, and
* return nr_pages so these don't get counted against task's
* locked limit. huge pages are already counted against
* locked vm limit.
*/
make_pages_present(start, end);
no_mlock:
vma->vm_flags &= ~VM_LOCKED; /* and don't come back! */
return nr_pages; /* error or pages NOT mlocked */
}
/*
* munlock_vma_pages_range() - munlock all pages in the vma range.'
* @vma - vma containing range to be munlock()ed.
* @start - start address in @vma of the range
* @end - end of range in @vma.
*
* For mremap(), munmap() and exit().
*
* Called with @vma VM_LOCKED.
*
* Returns with VM_LOCKED cleared. Callers must be prepared to
* deal with this.
*
* We don't save and restore VM_LOCKED here because pages are
* still on lru. In unmap path, pages might be scanned by reclaim
* and re-mlocked by try_to_{munlock|unmap} before we unmap and
* free them. This will result in freeing mlocked pages.
*/
void munlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
vma->vm_flags &= ~VM_LOCKED;
__mlock_vma_pages_range(vma, start, end, 0);
}
/*
* mlock_fixup - handle mlock[all]/munlock[all] requests.
*
* Filters out "special" vmas -- VM_LOCKED never gets set for these, and
* munlock is a no-op. However, for some special vmas, we go ahead and
* populate the ptes via make_pages_present().
*
* For vmas that pass the filters, merge/split as appropriate.
*/
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 nr_pages;
int ret = 0;
int lock = newflags & VM_LOCKED;
if (newflags == vma->vm_flags ||
(vma->vm_flags & (VM_IO | VM_PFNMAP)))
goto out; /* don't set VM_LOCKED, don't count */
if ((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
is_vm_hugetlb_page(vma) ||
vma == get_gate_vma(current)) {
if (lock)
make_pages_present(start, end);
goto out; /* don't set VM_LOCKED, don't count */
}
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;
}
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:
/*
* Keep track of amount of locked VM.
*/
nr_pages = (end - start) >> PAGE_SHIFT;
if (!lock)
nr_pages = -nr_pages;
mm->locked_vm += nr_pages;
/*
* 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, __mlock_vma_pages_range will bring it back.
*/
vma->vm_flags = newflags;
if (lock) {
/*
* mmap_sem is currently held for write. Downgrade the write
* lock to a read lock so that other faults, mmap scans, ...
* while we fault in all pages.
*/
downgrade_write(&mm->mmap_sem);
ret = __mlock_vma_pages_range(vma, start, end, 1);
/*
* Need to reacquire mmap sem in write mode, as our callers
* expect this. We have no support for atomically upgrading
* a sem to write, so we need to check for ranges while sem
* is unlocked.
*/
up_read(&mm->mmap_sem);
/* vma can change or disappear */
down_write(&mm->mmap_sem);
*prev = find_vma(mm, start);
/* non-NULL *prev must contain @start, but need to check @end */
if (!(*prev) || end > (*prev)->vm_end)
ret = -ENOMEM;
else if (ret > 0) {
mm->locked_vm -= ret;
ret = 0;
} else
ret = __mlock_posix_error_return(ret); /* translate if needed */
} else {
/*
* TODO: for unlocking, pages will already be resident, so
* we don't need to wait for allocations/reclaim/pagein, ...
* However, unlocking a very large region can still take a
* while. Should we downgrade the semaphore for both lock
* AND unlock ?
*/
__mlock_vma_pages_range(vma, start, end, 0);
}
out:
*prev = vma;
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;
lru_add_drain_all(); /* flush pagevec */
down_write(&current->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(&current->mm->mmap_sem);
return error;
}
asmlinkage long sys_munlock(unsigned long start, size_t len)
{
int ret;
down_write(&current->mm->mmap_sem);
len = PAGE_ALIGN(len + (start & ~PAGE_MASK));
start &= PAGE_MASK;
ret = do_mlock(start, len, 0);
up_write(&current->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;
lru_add_drain_all(); /* flush pagevec */
down_write(&current->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(&current->mm->mmap_sem);
out:
return ret;
}
asmlinkage long sys_munlockall(void)
{
int ret;
down_write(&current->mm->mmap_sem);
ret = do_mlockall(0);
up_write(&current->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;
if (lock_limit == RLIM_INFINITY)
allowed = 1;
lock_limit >>= PAGE_SHIFT;
spin_lock(&shmlock_user_lock);
if (!allowed &&
locked + user->locked_shm > lock_limit && !capable(CAP_IPC_LOCK))
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);
}