The vDSO getrandom() implementation works with a buffer allocated with a
new system call that has certain requirements:
- It shouldn't be written to core dumps.
* Easy: VM_DONTDUMP.
- It should be zeroed on fork.
* Easy: VM_WIPEONFORK.
- It shouldn't be written to swap.
* Uh-oh: mlock is rlimited.
* Uh-oh: mlock isn't inherited by forks.
It turns out that the vDSO getrandom() function has three really nice
characteristics that we can exploit to solve this problem:
1) Due to being wiped during fork(), the vDSO code is already robust to
having the contents of the pages it reads zeroed out midway through
the function's execution.
2) In the absolute worst case of whatever contingency we're coding for,
we have the option to fallback to the getrandom() syscall, and
everything is fine.
3) The buffers the function uses are only ever useful for a maximum of
60 seconds -- a sort of cache, rather than a long term allocation.
These characteristics mean that we can introduce VM_DROPPABLE, which
has the following semantics:
a) It never is written out to swap.
b) Under memory pressure, mm can just drop the pages (so that they're
zero when read back again).
c) It is inherited by fork.
d) It doesn't count against the mlock budget, since nothing is locked.
This is fairly simple to implement, with the one snag that we have to
use 64-bit VM_* flags, but this shouldn't be a problem, since the only
consumers will probably be 64-bit anyway.
This way, allocations used by vDSO getrandom() can use:
VM_DROPPABLE | VM_DONTDUMP | VM_WIPEONFORK | VM_NORESERVE
And there will be no problem with using memory when not in use, not
wiping on fork(), coredumps, or writing out to swap.
When this functionality is exposed via vgetrandom_alloc() later in this
series, a userspace selftest is added that verifies this is working as
intended.
Cc: linux-mm@xxxxxxxxx
Signed-off-by: Jason A. Donenfeld <Jason@xxxxxxxxx>
---
fs/proc/task_mmu.c | 3 +++
include/linux/mm.h | 8 ++++++++
include/trace/events/mmflags.h | 7 +++++++
mm/Kconfig | 3 +++
mm/mprotect.c | 2 +-
mm/rmap.c | 16 +++++++++++++---
6 files changed, 35 insertions(+), 4 deletions(-)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 71e5039d940d..b3bd8432f869 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -709,6 +709,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
#endif
#ifdef CONFIG_64BIT
[ilog2(VM_SEALED)] = "sl",
+#endif
+#ifdef CONFIG_NEED_VM_DROPPABLE
+ [ilog2(VM_DROPPABLE)] = "dp",
#endif
};
size_t i;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index eb7c96d24ac0..92454a0272ce 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -321,12 +321,14 @@ extern unsigned int kobjsize(const void *objp);
#define VM_HIGH_ARCH_BIT_3 35 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_4 36 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_BIT_5 37 /* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_BIT_6 38 /* bit only usable on 64-bit architectures */
#define VM_HIGH_ARCH_0 BIT(VM_HIGH_ARCH_BIT_0)
#define VM_HIGH_ARCH_1 BIT(VM_HIGH_ARCH_BIT_1)
#define VM_HIGH_ARCH_2 BIT(VM_HIGH_ARCH_BIT_2)
#define VM_HIGH_ARCH_3 BIT(VM_HIGH_ARCH_BIT_3)
#define VM_HIGH_ARCH_4 BIT(VM_HIGH_ARCH_BIT_4)
#define VM_HIGH_ARCH_5 BIT(VM_HIGH_ARCH_BIT_5)
+#define VM_HIGH_ARCH_6 BIT(VM_HIGH_ARCH_BIT_6)
#endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
#ifdef CONFIG_ARCH_HAS_PKEYS
@@ -357,6 +359,12 @@ extern unsigned int kobjsize(const void *objp);
# define VM_SHADOW_STACK VM_NONE
#endif
+#ifdef CONFIG_NEED_VM_DROPPABLE
+# define VM_DROPPABLE VM_HIGH_ARCH_6
+#else
+# define VM_DROPPABLE VM_NONE
+#endif
+
#if defined(CONFIG_X86)
# define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */
#elif defined(CONFIG_PPC)
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index e46d6e82765e..fab7848df50a 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -165,6 +165,12 @@ IF_HAVE_PG_ARCH_X(arch_3)
# define IF_HAVE_UFFD_MINOR(flag, name)
#endif
+#ifdef CONFIG_NEED_VM_DROPPABLE
+# define IF_HAVE_VM_DROPPABLE(flag, name) {flag, name},
+#else
+# define IF_HAVE_VM_DROPPABLE(flag, name)
+#endif
+
#define __def_vmaflag_names \
{VM_READ, "read" }, \
{VM_WRITE, "write" }, \
@@ -197,6 +203,7 @@ IF_HAVE_VM_SOFTDIRTY(VM_SOFTDIRTY, "softdirty" ) \
{VM_MIXEDMAP, "mixedmap" }, \
{VM_HUGEPAGE, "hugepage" }, \
{VM_NOHUGEPAGE, "nohugepage" }, \
+IF_HAVE_VM_DROPPABLE(VM_DROPPABLE, "droppable" ) \
{VM_MERGEABLE, "mergeable" } \
#define show_vma_flags(flags) \
diff --git a/mm/Kconfig b/mm/Kconfig
index b4cb45255a54..6cd65ea4b3ad 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1056,6 +1056,9 @@ config ARCH_USES_HIGH_VMA_FLAGS
bool
config ARCH_HAS_PKEYS
bool
+config NEED_VM_DROPPABLE
+ select ARCH_USES_HIGH_VMA_FLAGS
+ bool
config ARCH_USES_PG_ARCH_X
bool
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 8c6cd8825273..57b8dad9adcc 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -623,7 +623,7 @@ mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb,
may_expand_vm(mm, oldflags, nrpages))
return -ENOMEM;
if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
- VM_SHARED|VM_NORESERVE))) {
+ VM_SHARED|VM_NORESERVE|VM_DROPPABLE))) {
charged = nrpages;
if (security_vm_enough_memory_mm(mm, charged))
return -ENOMEM;
diff --git a/mm/rmap.c b/mm/rmap.c
index e8fc5ecb59b2..56d7535d5cf6 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1397,7 +1397,10 @@ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio);
VM_BUG_ON_VMA(address < vma->vm_start ||
address + (nr << PAGE_SHIFT) > vma->vm_end, vma);
- __folio_set_swapbacked(folio);
+ /* VM_DROPPABLE mappings don't swap; instead they're just dropped when
+ * under memory pressure. */
+ if (!(vma->vm_flags & VM_DROPPABLE))
+ __folio_set_swapbacked(folio);
__folio_set_anon(folio, vma, address, true);
if (likely(!folio_test_large(folio))) {
@@ -1841,7 +1844,11 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
* plus the rmap(s) (dropped by discard:).
*/
if (ref_count == 1 + map_count &&
- !folio_test_dirty(folio)) {
+ (!folio_test_dirty(folio) ||
+ /* Unlike MADV_FREE mappings, VM_DROPPABLE
+ * ones can be dropped even if they've
+ * been dirtied. */
+ (vma->vm_flags & VM_DROPPABLE))) {
dec_mm_counter(mm, MM_ANONPAGES);
goto discard;
}
@@ -1851,7 +1858,10 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
* discarded. Remap the page to page table.
*/
set_pte_at(mm, address, pvmw.pte, pteval);
- folio_set_swapbacked(folio);
+ /* Unlike MADV_FREE mappings, VM_DROPPABLE ones
+ * never get swap backed on failure to drop. */
+ if (!(vma->vm_flags & VM_DROPPABLE))
+ folio_set_swapbacked(folio);
ret = false;
page_vma_mapped_walk_done(&pvmw);
break;
--
2.45.2
