aboutsummaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2022-03-24 18:14:12 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-03-24 19:06:51 -0700
commit9457056ac426e5ed0671356509c8dcce69f8dee0 (patch)
tree5237b52dad5a524729a81ddebd2990136e9ec372 /mm
parentmm: fix race between MADV_FREE reclaim and blkdev direct IO read (diff)
downloadlinux-dev-9457056ac426e5ed0671356509c8dcce69f8dee0.tar.xz
linux-dev-9457056ac426e5ed0671356509c8dcce69f8dee0.zip
mm: madvise: MADV_DONTNEED_LOCKED
MADV_DONTNEED historically rejects mlocked ranges, but with MLOCK_ONFAULT and MCL_ONFAULT allowing to mlock without populating, there are valid use cases for depopulating locked ranges as well. Users mlock memory to protect secrets. There are allocators for secure buffers that want in-use memory generally mlocked, but cleared and invalidated memory to give up the physical pages. This could be done with explicit munlock -> mlock calls on free -> alloc of course, but that adds two unnecessary syscalls, heavy mmap_sem write locks, vma splits and re-merges - only to get rid of the backing pages. Users also mlockall(MCL_ONFAULT) to suppress sustained paging, but are okay with on-demand initial population. It seems valid to selectively free some memory during the lifetime of such a process, without having to mess with its overall policy. Why add a separate flag? Isn't this a pretty niche usecase? - MADV_DONTNEED has been bailing on locked vmas forever. It's at least conceivable that someone, somewhere is relying on mlock to protect data from perhaps broader invalidation calls. Changing this behavior now could lead to quiet data corruption. - It also clarifies expectations around MADV_FREE and maybe MADV_REMOVE. It avoids the situation where one quietly behaves different than the others. MADV_FREE_LOCKED can be added later. - The combination of mlock() and madvise() in the first place is probably niche. But where it happens, I'd say that dropping pages from a locked region once they don't contain secrets or won't page anymore is much saner than relying on mlock to protect memory from speculative or errant invalidation calls. It's just that we can't change the default behavior because of the two previous points. Given that, an explicit new flag seems to make the most sense. [hannes@cmpxchg.org: fix mips build] Link: https://lkml.kernel.org/r/20220304171912.305060-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Nadav Amit <nadav.amit@gmail.com> Cc: David Hildenbrand <david@redhat.com> Cc: Dr. David Alan Gilbert <dgilbert@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/madvise.c24
1 files changed, 14 insertions, 10 deletions
diff --git a/mm/madvise.c b/mm/madvise.c
index 2e6213664c52..b41858ee937b 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -52,6 +52,7 @@ static int madvise_need_mmap_write(int behavior)
case MADV_REMOVE:
case MADV_WILLNEED:
case MADV_DONTNEED:
+ case MADV_DONTNEED_LOCKED:
case MADV_COLD:
case MADV_PAGEOUT:
case MADV_FREE:
@@ -502,14 +503,9 @@ static void madvise_cold_page_range(struct mmu_gather *tlb,
tlb_end_vma(tlb, vma);
}
-static inline bool can_madv_lru_non_huge_vma(struct vm_area_struct *vma)
-{
- return !(vma->vm_flags & (VM_LOCKED|VM_PFNMAP));
-}
-
static inline bool can_madv_lru_vma(struct vm_area_struct *vma)
{
- return can_madv_lru_non_huge_vma(vma) && !is_vm_hugetlb_page(vma);
+ return !(vma->vm_flags & (VM_LOCKED|VM_PFNMAP|VM_HUGETLB));
}
static long madvise_cold(struct vm_area_struct *vma,
@@ -787,10 +783,16 @@ static bool madvise_dontneed_free_valid_vma(struct vm_area_struct *vma,
unsigned long *end,
int behavior)
{
- if (!is_vm_hugetlb_page(vma))
- return can_madv_lru_non_huge_vma(vma);
+ if (!is_vm_hugetlb_page(vma)) {
+ unsigned int forbidden = VM_PFNMAP;
+
+ if (behavior != MADV_DONTNEED_LOCKED)
+ forbidden |= VM_LOCKED;
+
+ return !(vma->vm_flags & forbidden);
+ }
- if (behavior != MADV_DONTNEED)
+ if (behavior != MADV_DONTNEED && behavior != MADV_DONTNEED_LOCKED)
return false;
if (start & ~huge_page_mask(hstate_vma(vma)))
return false;
@@ -854,7 +856,7 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
VM_WARN_ON(start >= end);
}
- if (behavior == MADV_DONTNEED)
+ if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED)
return madvise_dontneed_single_vma(vma, start, end);
else if (behavior == MADV_FREE)
return madvise_free_single_vma(vma, start, end);
@@ -993,6 +995,7 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
return madvise_pageout(vma, prev, start, end);
case MADV_FREE:
case MADV_DONTNEED:
+ case MADV_DONTNEED_LOCKED:
return madvise_dontneed_free(vma, prev, start, end, behavior);
case MADV_POPULATE_READ:
case MADV_POPULATE_WRITE:
@@ -1123,6 +1126,7 @@ madvise_behavior_valid(int behavior)
case MADV_REMOVE:
case MADV_WILLNEED:
case MADV_DONTNEED:
+ case MADV_DONTNEED_LOCKED:
case MADV_FREE:
case MADV_COLD:
case MADV_PAGEOUT: