linux/mm/mlock.c
Colin Cross 9a10064f56 mm: add a field to store names for private anonymous memory
In many userspace applications, and especially in VM based applications
like Android uses heavily, there are multiple different allocators in
use.  At a minimum there is libc malloc and the stack, and in many cases
there are libc malloc, the stack, direct syscalls to mmap anonymous
memory, and multiple VM heaps (one for small objects, one for big
objects, etc.).  Each of these layers usually has its own tools to
inspect its usage; malloc by compiling a debug version, the VM through
heap inspection tools, and for direct syscalls there is usually no way
to track them.

On Android we heavily use a set of tools that use an extended version of
the logic covered in Documentation/vm/pagemap.txt to walk all pages
mapped in userspace and slice their usage by process, shared (COW) vs.
unique mappings, backing, etc.  This can account for real physical
memory usage even in cases like fork without exec (which Android uses
heavily to share as many private COW pages as possible between
processes), Kernel SamePage Merging, and clean zero pages.  It produces
a measurement of the pages that only exist in that process (USS, for
unique), and a measurement of the physical memory usage of that process
with the cost of shared pages being evenly split between processes that
share them (PSS).

If all anonymous memory is indistinguishable then figuring out the real
physical memory usage (PSS) of each heap requires either a pagemap
walking tool that can understand the heap debugging of every layer, or
for every layer's heap debugging tools to implement the pagemap walking
logic, in which case it is hard to get a consistent view of memory
across the whole system.

Tracking the information in userspace leads to all sorts of problems.
It either needs to be stored inside the process, which means every
process has to have an API to export its current heap information upon
request, or it has to be stored externally in a filesystem that somebody
needs to clean up on crashes.  It needs to be readable while the process
is still running, so it has to have some sort of synchronization with
every layer of userspace.  Efficiently tracking the ranges requires
reimplementing something like the kernel vma trees, and linking to it
from every layer of userspace.  It requires more memory, more syscalls,
more runtime cost, and more complexity to separately track regions that
the kernel is already tracking.

This patch adds a field to /proc/pid/maps and /proc/pid/smaps to show a
userspace-provided name for anonymous vmas.  The names of named
anonymous vmas are shown in /proc/pid/maps and /proc/pid/smaps as
[anon:<name>].

Userspace can set the name for a region of memory by calling

   prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, start, len, (unsigned long)name)

Setting the name to NULL clears it.  The name length limit is 80 bytes
including NUL-terminator and is checked to contain only printable ascii
characters (including space), except '[',']','\','$' and '`'.

Ascii strings are being used to have a descriptive identifiers for vmas,
which can be understood by the users reading /proc/pid/maps or
/proc/pid/smaps.  Names can be standardized for a given system and they
can include some variable parts such as the name of the allocator or a
library, tid of the thread using it, etc.

The name is stored in a pointer in the shared union in vm_area_struct
that points to a null terminated string.  Anonymous vmas with the same
name (equivalent strings) and are otherwise mergeable will be merged.
The name pointers are not shared between vmas even if they contain the
same name.  The name pointer is stored in a union with fields that are
only used on file-backed mappings, so it does not increase memory usage.

CONFIG_ANON_VMA_NAME kernel configuration is introduced to enable this
feature.  It keeps the feature disabled by default to prevent any
additional memory overhead and to avoid confusing procfs parsers on
systems which are not ready to support named anonymous vmas.

The patch is based on the original patch developed by Colin Cross, more
specifically on its latest version [1] posted upstream by Sumit Semwal.
It used a userspace pointer to store vma names.  In that design, name
pointers could be shared between vmas.  However during the last
upstreaming attempt, Kees Cook raised concerns [2] about this approach
and suggested to copy the name into kernel memory space, perform
validity checks [3] and store as a string referenced from
vm_area_struct.

One big concern is about fork() performance which would need to strdup
anonymous vma names.  Dave Hansen suggested experimenting with
worst-case scenario of forking a process with 64k vmas having longest
possible names [4].  I ran this experiment on an ARM64 Android device
and recorded a worst-case regression of almost 40% when forking such a
process.

This regression is addressed in the followup patch which replaces the
pointer to a name with a refcounted structure that allows sharing the
name pointer between vmas of the same name.  Instead of duplicating the
string during fork() or when splitting a vma it increments the refcount.

[1] https://lore.kernel.org/linux-mm/20200901161459.11772-4-sumit.semwal@linaro.org/
[2] https://lore.kernel.org/linux-mm/202009031031.D32EF57ED@keescook/
[3] https://lore.kernel.org/linux-mm/202009031022.3834F692@keescook/
[4] https://lore.kernel.org/linux-mm/5d0358ab-8c47-2f5f-8e43-23b89d6a8e95@intel.com/

Changes for prctl(2) manual page (in the options section):

PR_SET_VMA
	Sets an attribute specified in arg2 for virtual memory areas
	starting from the address specified in arg3 and spanning the
	size specified	in arg4. arg5 specifies the value of the attribute
	to be set. Note that assigning an attribute to a virtual memory
	area might prevent it from being merged with adjacent virtual
	memory areas due to the difference in that attribute's value.

	Currently, arg2 must be one of:

	PR_SET_VMA_ANON_NAME
		Set a name for anonymous virtual memory areas. arg5 should
		be a pointer to a null-terminated string containing the
		name. The name length including null byte cannot exceed
		80 bytes. If arg5 is NULL, the name of the appropriate
		anonymous virtual memory areas will be reset. The name
		can contain only printable ascii characters (including
                space), except '[',']','\','$' and '`'.

                This feature is available only if the kernel is built with
                the CONFIG_ANON_VMA_NAME option enabled.

[surenb@google.com: docs: proc.rst: /proc/PID/maps: fix malformed table]
  Link: https://lkml.kernel.org/r/20211123185928.2513763-1-surenb@google.com
[surenb: rebased over v5.15-rc6, replaced userpointer with a kernel copy,
 added input sanitization and CONFIG_ANON_VMA_NAME config. The bulk of the
 work here was done by Colin Cross, therefore, with his permission, keeping
 him as the author]

Link: https://lkml.kernel.org/r/20211019215511.3771969-2-surenb@google.com
Signed-off-by: Colin Cross <ccross@google.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jan Glauber <jan.glauber@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Landley <rob@landley.net>
Cc: "Serge E. Hallyn" <serge.hallyn@ubuntu.com>
Cc: Shaohua Li <shli@fusionio.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-01-15 16:30:27 +02:00

857 lines
22 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* 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/sched/user.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
#include <linux/export.h>
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
#include <linux/secretmem.h>
#include "internal.h"
bool can_do_mlock(void)
{
if (rlimit(RLIMIT_MEMLOCK) != 0)
return true;
if (capable(CAP_IPC_LOCK))
return true;
return false;
}
EXPORT_SYMBOL(can_do_mlock);
/*
* 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_lock 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)
{
int nr_pages;
if (!TestClearPageMlocked(page))
return;
nr_pages = thp_nr_pages(page);
mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages);
/*
* The previous TestClearPageMlocked() corresponds to the smp_mb()
* in __pagevec_lru_add_fn().
*
* See __pagevec_lru_add_fn for more explanation.
*/
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_events(UNEVICTABLE_PGSTRANDED, nr_pages);
}
}
/*
* 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)
{
/* Serialize with page migration */
BUG_ON(!PageLocked(page));
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page);
if (!TestSetPageMlocked(page)) {
int nr_pages = thp_nr_pages(page);
mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages);
count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
if (!isolate_lru_page(page))
putback_lru_page(page);
}
}
/*
* Finish munlock after successful page isolation
*
* Page must be locked. This is a wrapper for page_mlock()
* and putback_lru_page() with munlock accounting.
*/
static void __munlock_isolated_page(struct page *page)
{
/*
* Optimization: if the page was mapped just once, that's our mapping
* and we don't need to check all the other vmas.
*/
if (page_mapcount(page) > 1)
page_mlock(page);
/* Did try_to_unlock() succeed or punt? */
if (!PageMlocked(page))
count_vm_events(UNEVICTABLE_PGMUNLOCKED, thp_nr_pages(page));
putback_lru_page(page);
}
/*
* Accounting for page isolation fail during munlock
*
* Performs accounting when page isolation fails in munlock. There is nothing
* else to do because it means some other task has already removed the page
* from the LRU. putback_lru_page() will take care of removing the page from
* the unevictable list, if necessary. vmscan [page_referenced()] will move
* the page back to the unevictable list if some other vma has it mlocked.
*/
static void __munlock_isolation_failed(struct page *page)
{
int nr_pages = thp_nr_pages(page);
if (PageUnevictable(page))
__count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages);
else
__count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages);
}
/**
* munlock_vma_page - munlock a vma page
* @page: page to be unlocked, either a normal page or THP page head
*
* returns the size of the page as a page mask (0 for normal page,
* HPAGE_PMD_NR - 1 for THP head page)
*
* called from munlock()/munmap() path with page supposedly on the LRU.
* When we munlock a page, because the vma where we found the page is being
* munlock()ed or munmap()ed, we want to check whether other vmas hold the
* page locked so that we can leave it on the unevictable lru list and not
* bother vmscan with it. However, to walk the page's rmap list in
* page_mlock() we must isolate the page from the LRU. If some other
* task has removed the page from the LRU, we won't be able to do that.
* So we clear the PageMlocked as we might not get another chance. If we
* can't isolate the page, we leave it for putback_lru_page() and vmscan
* [page_referenced()/try_to_unmap()] to deal with.
*/
unsigned int munlock_vma_page(struct page *page)
{
int nr_pages;
/* For page_mlock() and to serialize with page migration */
BUG_ON(!PageLocked(page));
VM_BUG_ON_PAGE(PageTail(page), page);
if (!TestClearPageMlocked(page)) {
/* Potentially, PTE-mapped THP: do not skip the rest PTEs */
return 0;
}
nr_pages = thp_nr_pages(page);
mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
if (!isolate_lru_page(page))
__munlock_isolated_page(page);
else
__munlock_isolation_failed(page);
return nr_pages - 1;
}
/*
* 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;
}
/*
* Prepare page for fast batched LRU putback via putback_lru_evictable_pagevec()
*
* The fast path is available only for evictable pages with single mapping.
* Then we can bypass the per-cpu pvec and get better performance.
* when mapcount > 1 we need page_mlock() which can fail.
* when !page_evictable(), we need the full redo logic of putback_lru_page to
* avoid leaving evictable page in unevictable list.
*
* In case of success, @page is added to @pvec and @pgrescued is incremented
* in case that the page was previously unevictable. @page is also unlocked.
*/
static bool __putback_lru_fast_prepare(struct page *page, struct pagevec *pvec,
int *pgrescued)
{
VM_BUG_ON_PAGE(PageLRU(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
if (page_mapcount(page) <= 1 && page_evictable(page)) {
pagevec_add(pvec, page);
if (TestClearPageUnevictable(page))
(*pgrescued)++;
unlock_page(page);
return true;
}
return false;
}
/*
* Putback multiple evictable pages to the LRU
*
* Batched putback of evictable pages that bypasses the per-cpu pvec. Some of
* the pages might have meanwhile become unevictable but that is OK.
*/
static void __putback_lru_fast(struct pagevec *pvec, int pgrescued)
{
count_vm_events(UNEVICTABLE_PGMUNLOCKED, pagevec_count(pvec));
/*
*__pagevec_lru_add() calls release_pages() so we don't call
* put_page() explicitly
*/
__pagevec_lru_add(pvec);
count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
}
/*
* Munlock a batch of pages from the same zone
*
* The work is split to two main phases. First phase clears the Mlocked flag
* and attempts to isolate the pages, all under a single zone lru lock.
* The second phase finishes the munlock only for pages where isolation
* succeeded.
*
* Note that the pagevec may be modified during the process.
*/
static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
{
int i;
int nr = pagevec_count(pvec);
int delta_munlocked = -nr;
struct pagevec pvec_putback;
struct lruvec *lruvec = NULL;
int pgrescued = 0;
pagevec_init(&pvec_putback);
/* Phase 1: page isolation */
for (i = 0; i < nr; i++) {
struct page *page = pvec->pages[i];
struct folio *folio = page_folio(page);
if (TestClearPageMlocked(page)) {
/*
* We already have pin from follow_page_mask()
* so we can spare the get_page() here.
*/
if (TestClearPageLRU(page)) {
lruvec = folio_lruvec_relock_irq(folio, lruvec);
del_page_from_lru_list(page, lruvec);
continue;
} else
__munlock_isolation_failed(page);
} else {
delta_munlocked++;
}
/*
* We won't be munlocking this page in the next phase
* but we still need to release the follow_page_mask()
* pin. We cannot do it under lru_lock however. If it's
* the last pin, __page_cache_release() would deadlock.
*/
pagevec_add(&pvec_putback, pvec->pages[i]);
pvec->pages[i] = NULL;
}
if (lruvec) {
__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
unlock_page_lruvec_irq(lruvec);
} else if (delta_munlocked) {
mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
}
/* Now we can release pins of pages that we are not munlocking */
pagevec_release(&pvec_putback);
/* Phase 2: page munlock */
for (i = 0; i < nr; i++) {
struct page *page = pvec->pages[i];
if (page) {
lock_page(page);
if (!__putback_lru_fast_prepare(page, &pvec_putback,
&pgrescued)) {
/*
* Slow path. We don't want to lose the last
* pin before unlock_page()
*/
get_page(page); /* for putback_lru_page() */
__munlock_isolated_page(page);
unlock_page(page);
put_page(page); /* from follow_page_mask() */
}
}
}
/*
* Phase 3: page putback for pages that qualified for the fast path
* This will also call put_page() to return pin from follow_page_mask()
*/
if (pagevec_count(&pvec_putback))
__putback_lru_fast(&pvec_putback, pgrescued);
}
/*
* Fill up pagevec for __munlock_pagevec using pte walk
*
* The function expects that the struct page corresponding to @start address is
* a non-TPH page already pinned and in the @pvec, and that it belongs to @zone.
*
* The rest of @pvec is filled by subsequent pages within the same pmd and same
* zone, as long as the pte's are present and vm_normal_page() succeeds. These
* pages also get pinned.
*
* Returns the address of the next page that should be scanned. This equals
* @start + PAGE_SIZE when no page could be added by the pte walk.
*/
static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
struct vm_area_struct *vma, struct zone *zone,
unsigned long start, unsigned long end)
{
pte_t *pte;
spinlock_t *ptl;
/*
* Initialize pte walk starting at the already pinned page where we
* are sure that there is a pte, as it was pinned under the same
* mmap_lock write op.
*/
pte = get_locked_pte(vma->vm_mm, start, &ptl);
/* Make sure we do not cross the page table boundary */
end = pgd_addr_end(start, end);
end = p4d_addr_end(start, end);
end = pud_addr_end(start, end);
end = pmd_addr_end(start, end);
/* The page next to the pinned page is the first we will try to get */
start += PAGE_SIZE;
while (start < end) {
struct page *page = NULL;
pte++;
if (pte_present(*pte))
page = vm_normal_page(vma, start, *pte);
/*
* Break if page could not be obtained or the page's node+zone does not
* match
*/
if (!page || page_zone(page) != zone)
break;
/*
* Do not use pagevec for PTE-mapped THP,
* munlock_vma_pages_range() will handle them.
*/
if (PageTransCompound(page))
break;
get_page(page);
/*
* Increase the address that will be returned *before* the
* eventual break due to pvec becoming full by adding the page
*/
start += PAGE_SIZE;
if (pagevec_add(pvec, page) == 0)
break;
}
pte_unmap_unlock(pte, ptl);
return start;
}
/*
* 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 page_mlock/try_to_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_CLEAR_MASK;
while (start < end) {
struct page *page;
unsigned int page_mask = 0;
unsigned long page_increm;
struct pagevec pvec;
struct zone *zone;
pagevec_init(&pvec);
/*
* Although FOLL_DUMP is intended for get_dump_page(),
* it just so happens that its special treatment of the
* ZERO_PAGE (returning an error instead of doing get_page)
* suits munlock very well (and if somehow an abnormal page
* has sneaked into the range, we won't oops here: great).
*/
page = follow_page(vma, start, FOLL_GET | FOLL_DUMP);
if (page && !IS_ERR(page)) {
if (PageTransTail(page)) {
VM_BUG_ON_PAGE(PageMlocked(page), page);
put_page(page); /* follow_page_mask() */
} else if (PageTransHuge(page)) {
lock_page(page);
/*
* Any THP page found by follow_page_mask() may
* have gotten split before reaching
* munlock_vma_page(), so we need to compute
* the page_mask here instead.
*/
page_mask = munlock_vma_page(page);
unlock_page(page);
put_page(page); /* follow_page_mask() */
} else {
/*
* Non-huge pages are handled in batches via
* pagevec. The pin from follow_page_mask()
* prevents them from collapsing by THP.
*/
pagevec_add(&pvec, page);
zone = page_zone(page);
/*
* Try to fill the rest of pagevec using fast
* pte walk. This will also update start to
* the next page to process. Then munlock the
* pagevec.
*/
start = __munlock_pagevec_fill(&pvec, vma,
zone, start, end);
__munlock_pagevec(&pvec, zone);
goto next;
}
}
page_increm = 1 + page_mask;
start += page_increm * PAGE_SIZE;
next:
cond_resched();
}
}
/*
* 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.
*
* 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, vm_flags_t newflags)
{
struct mm_struct *mm = vma->vm_mm;
pgoff_t pgoff;
int nr_pages;
int ret = 0;
int lock = !!(newflags & VM_LOCKED);
vm_flags_t old_flags = vma->vm_flags;
if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) ||
vma_is_dax(vma) || vma_is_secretmem(vma))
/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
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),
vma->vm_userfaultfd_ctx, vma_anon_name(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;
else if (old_flags & VM_LOCKED)
nr_pages = 0;
mm->locked_vm += nr_pages;
/*
* vm_flags is protected by the mmap_lock held in write mode.
* It's okay if try_to_unmap_one unmaps a page just after we
* set VM_LOCKED, populate_vma_page_range will bring it back.
*/
if (lock)
vma->vm_flags = newflags;
else
munlock_vma_pages_range(vma, start, end);
out:
*prev = vma;
return ret;
}
static int apply_vma_lock_flags(unsigned long start, size_t len,
vm_flags_t flags)
{
unsigned long nstart, end, tmp;
struct vm_area_struct *vma, *prev;
int error;
VM_BUG_ON(offset_in_page(start));
VM_BUG_ON(len != PAGE_ALIGN(len));
end = start + len;
if (end < start)
return -EINVAL;
if (end == start)
return 0;
vma = find_vma(current->mm, start);
if (!vma || vma->vm_start > start)
return -ENOMEM;
prev = vma->vm_prev;
if (start > vma->vm_start)
prev = vma;
for (nstart = start ; ; ) {
vm_flags_t newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
newflags |= flags;
/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
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;
}
/*
* Go through vma areas and sum size of mlocked
* vma pages, as return value.
* Note deferred memory locking case(mlock2(,,MLOCK_ONFAULT)
* is also counted.
* Return value: previously mlocked page counts
*/
static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm,
unsigned long start, size_t len)
{
struct vm_area_struct *vma;
unsigned long count = 0;
if (mm == NULL)
mm = current->mm;
vma = find_vma(mm, start);
if (vma == NULL)
return 0;
for (; vma ; vma = vma->vm_next) {
if (start >= vma->vm_end)
continue;
if (start + len <= vma->vm_start)
break;
if (vma->vm_flags & VM_LOCKED) {
if (start > vma->vm_start)
count -= (start - vma->vm_start);
if (start + len < vma->vm_end) {
count += start + len - vma->vm_start;
break;
}
count += vma->vm_end - vma->vm_start;
}
}
return count >> PAGE_SHIFT;
}
static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags)
{
unsigned long locked;
unsigned long lock_limit;
int error = -ENOMEM;
start = untagged_addr(start);
if (!can_do_mlock())
return -EPERM;
len = PAGE_ALIGN(len + (offset_in_page(start)));
start &= PAGE_MASK;
lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
locked = len >> PAGE_SHIFT;
if (mmap_write_lock_killable(current->mm))
return -EINTR;
locked += current->mm->locked_vm;
if ((locked > lock_limit) && (!capable(CAP_IPC_LOCK))) {
/*
* It is possible that the regions requested intersect with
* previously mlocked areas, that part area in "mm->locked_vm"
* should not be counted to new mlock increment count. So check
* and adjust locked count if necessary.
*/
locked -= count_mm_mlocked_page_nr(current->mm,
start, len);
}
/* check against resource limits */
if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
error = apply_vma_lock_flags(start, len, flags);
mmap_write_unlock(current->mm);
if (error)
return error;
error = __mm_populate(start, len, 0);
if (error)
return __mlock_posix_error_return(error);
return 0;
}
SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
{
return do_mlock(start, len, VM_LOCKED);
}
SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
{
vm_flags_t vm_flags = VM_LOCKED;
if (flags & ~MLOCK_ONFAULT)
return -EINVAL;
if (flags & MLOCK_ONFAULT)
vm_flags |= VM_LOCKONFAULT;
return do_mlock(start, len, vm_flags);
}
SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
{
int ret;
start = untagged_addr(start);
len = PAGE_ALIGN(len + (offset_in_page(start)));
start &= PAGE_MASK;
if (mmap_write_lock_killable(current->mm))
return -EINTR;
ret = apply_vma_lock_flags(start, len, 0);
mmap_write_unlock(current->mm);
return ret;
}
/*
* Take the MCL_* flags passed into mlockall (or 0 if called from munlockall)
* and translate into the appropriate modifications to mm->def_flags and/or the
* flags for all current VMAs.
*
* There are a couple of subtleties with this. If mlockall() is called multiple
* times with different flags, the values do not necessarily stack. If mlockall
* is called once including the MCL_FUTURE flag and then a second time without
* it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags.
*/
static int apply_mlockall_flags(int flags)
{
struct vm_area_struct *vma, *prev = NULL;
vm_flags_t to_add = 0;
current->mm->def_flags &= VM_LOCKED_CLEAR_MASK;
if (flags & MCL_FUTURE) {
current->mm->def_flags |= VM_LOCKED;
if (flags & MCL_ONFAULT)
current->mm->def_flags |= VM_LOCKONFAULT;
if (!(flags & MCL_CURRENT))
goto out;
}
if (flags & MCL_CURRENT) {
to_add |= VM_LOCKED;
if (flags & MCL_ONFAULT)
to_add |= VM_LOCKONFAULT;
}
for (vma = current->mm->mmap; vma ; vma = prev->vm_next) {
vm_flags_t newflags;
newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
newflags |= to_add;
/* Ignore errors */
mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
cond_resched();
}
out:
return 0;
}
SYSCALL_DEFINE1(mlockall, int, flags)
{
unsigned long lock_limit;
int ret;
if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) ||
flags == MCL_ONFAULT)
return -EINVAL;
if (!can_do_mlock())
return -EPERM;
lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
if (mmap_write_lock_killable(current->mm))
return -EINTR;
ret = -ENOMEM;
if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
capable(CAP_IPC_LOCK))
ret = apply_mlockall_flags(flags);
mmap_write_unlock(current->mm);
if (!ret && (flags & MCL_CURRENT))
mm_populate(0, TASK_SIZE);
return ret;
}
SYSCALL_DEFINE0(munlockall)
{
int ret;
if (mmap_write_lock_killable(current->mm))
return -EINTR;
ret = apply_mlockall_flags(0);
mmap_write_unlock(current->mm);
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 ucounts *ucounts)
{
unsigned long lock_limit, locked;
long memlock;
int allowed = 0;
locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
lock_limit = rlimit(RLIMIT_MEMLOCK);
if (lock_limit == RLIM_INFINITY)
allowed = 1;
lock_limit >>= PAGE_SHIFT;
spin_lock(&shmlock_user_lock);
memlock = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked);
if (!allowed && (memlock == LONG_MAX || memlock > lock_limit) && !capable(CAP_IPC_LOCK)) {
dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked);
goto out;
}
if (!get_ucounts(ucounts)) {
dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked);
goto out;
}
allowed = 1;
out:
spin_unlock(&shmlock_user_lock);
return allowed;
}
void user_shm_unlock(size_t size, struct ucounts *ucounts)
{
spin_lock(&shmlock_user_lock);
dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, (size + PAGE_SIZE - 1) >> PAGE_SHIFT);
spin_unlock(&shmlock_user_lock);
put_ucounts(ucounts);
}