diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 5a716bdcba05bb78d1b9ee852469d019a68cce37..0949811761e6ce7a9a1a46773399aa8fe4966b26 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2591,6 +2591,13 @@ int gmap_mark_unmergeable(void)
int ret;
VMA_ITERATOR(vmi, mm, 0);
+ /*
+ * Make sure to disable KSM (if enabled for the whole process or
+ * individual VMAs). Note that nothing currently hinders user space
+ * from re-enabling it.
+ */
+ clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
+
for_each_vma(vmi, vma) {
/* Copy vm_flags to avoid partial modifications in ksm_madvise */
vm_flags = vma->vm_flags;
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index d9e701326a88258574bd43be33d710533957a60d..4647b0c70c120a453b89932b8cc003a3ad0e01a2 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -18,13 +18,26 @@
#ifdef CONFIG_KSM
int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
unsigned long end, int advice, unsigned long *vm_flags);
+
+void ksm_add_vma(struct vm_area_struct *vma);
+int ksm_enable_merge_any(struct mm_struct *mm);
+
int __ksm_enter(struct mm_struct *mm);
void __ksm_exit(struct mm_struct *mm);
static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
- if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
- return __ksm_enter(mm);
+ int ret;
+
+ if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) {
+ ret = __ksm_enter(mm);
+ if (ret)
+ return ret;
+ }
+
+ if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags))
+ set_bit(MMF_VM_MERGE_ANY, &mm->flags);
+
return 0;
}
@@ -57,6 +70,10 @@ void collect_procs_ksm(struct page *page, struct list_head *to_kill,
#endif
#else /* !CONFIG_KSM */
+static inline void ksm_add_vma(struct vm_area_struct *vma)
+{
+}
+
static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
return 0;
diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h
index 0e17ae7fbfd357aced9b38f9e4ab780b4cfb743d..0ee96ea7a0e90870a35b8f82fef4b125d04c18d0 100644
--- a/include/linux/sched/coredump.h
+++ b/include/linux/sched/coredump.h
@@ -90,4 +90,5 @@ static inline int get_dumpable(struct mm_struct *mm)
#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK)
+#define MMF_VM_MERGE_ANY 29
#endif /* _LINUX_SCHED_COREDUMP_H */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index b99c0be72577c09f430358669cf38bff829ad2fb..f23d9a16507f6f46b19179d176e5e409ee94d395 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -292,4 +292,6 @@ struct prctl_mm_map {
#define PR_GET_AUXV 0x41555856
+#define PR_SET_MEMORY_MERGE 67
+#define PR_GET_MEMORY_MERGE 68
#endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index 26c1399e06543f54811ffc8fd86f3df091dbf6d3..72cdb16e26366b17308b698abb7e91dcc12eb67d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -15,6 +15,7 @@
#include <linux/highuid.h>
#include <linux/fs.h>
#include <linux/kmod.h>
+#include <linux/ksm.h>
#include <linux/perf_event.h>
#include <linux/resource.h>
#include <linux/kernel.h>
@@ -2687,6 +2688,32 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
case PR_SET_VMA:
error = prctl_set_vma(arg2, arg3, arg4, arg5);
break;
+#ifdef CONFIG_KSM
+ case PR_SET_MEMORY_MERGE:
+ if (arg3 || arg4 || arg5)
+ return -EINVAL;
+ if (mmap_write_lock_killable(me->mm))
+ return -EINTR;
+
+ if (arg2) {
+ error = ksm_enable_merge_any(me->mm);
+ } else {
+ /*
+ * TODO: we might want disable KSM on all VMAs and
+ * trigger unsharing to completely disable KSM.
+ */
+ clear_bit(MMF_VM_MERGE_ANY, &me->mm->flags);
+ error = 0;
+ }
+ mmap_write_unlock(me->mm);
+ break;
+ case PR_GET_MEMORY_MERGE:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+
+ error = !!test_bit(MMF_VM_MERGE_ANY, &me->mm->flags);
+ break;
+#endif
default:
error = -EINVAL;
break;
diff --git a/mm/ksm.c b/mm/ksm.c
index 37c63310bc4e431e9000c0e71ad64be4996a7a5f..35ac6c741572e96c5448ab1f0bc0967215bce6d9 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -515,6 +515,28 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr)
return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
}
+static bool vma_ksm_compatible(struct vm_area_struct *vma)
+{
+ if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE | VM_PFNMAP |
+ VM_IO | VM_DONTEXPAND | VM_HUGETLB |
+ VM_MIXEDMAP))
+ return false; /* just ignore the advice */
+
+ if (vma_is_dax(vma))
+ return false;
+
+#ifdef VM_SAO
+ if (vma->vm_flags & VM_SAO)
+ return false;
+#endif
+#ifdef VM_SPARC_ADI
+ if (vma->vm_flags & VM_SPARC_ADI)
+ return false;
+#endif
+
+ return true;
+}
+
static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm,
unsigned long addr)
{
@@ -1026,6 +1048,7 @@ static int unmerge_and_remove_all_rmap_items(void)
mm_slot_free(mm_slot_cache, mm_slot);
clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+ clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
mmdrop(mm);
} else
spin_unlock(&ksm_mmlist_lock);
@@ -2408,6 +2431,7 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page)
mm_slot_free(mm_slot_cache, mm_slot);
clear_bit(MMF_VM_MERGEABLE, &mm->flags);
+ clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
mmap_read_unlock(mm);
mmdrop(mm);
} else {
@@ -2485,6 +2509,66 @@ static int ksm_scan_thread(void *nothing)
return 0;
}
+static void __ksm_add_vma(struct vm_area_struct *vma)
+{
+ unsigned long vm_flags = vma->vm_flags;
+
+ if (vm_flags & VM_MERGEABLE)
+ return;
+
+ if (vma_ksm_compatible(vma))
+ vm_flags_set(vma, VM_MERGEABLE);
+}
+
+/**
+ * ksm_add_vma - Mark vma as mergeable if compatible
+ *
+ * @vma: Pointer to vma
+ */
+void ksm_add_vma(struct vm_area_struct *vma)
+{
+ struct mm_struct *mm = vma->vm_mm;
+
+ if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+ __ksm_add_vma(vma);
+}
+
+static void ksm_add_vmas(struct mm_struct *mm)
+{
+ struct vm_area_struct *vma;
+
+ VMA_ITERATOR(vmi, mm, 0);
+ for_each_vma(vmi, vma)
+ __ksm_add_vma(vma);
+}
+
+/**
+ * ksm_enable_merge_any - Add mm to mm ksm list and enable merging on all
+ * compatible VMA's
+ *
+ * @mm: Pointer to mm
+ *
+ * Returns 0 on success, otherwise error code
+ */
+int ksm_enable_merge_any(struct mm_struct *mm)
+{
+ int err;
+
+ if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+ return 0;
+
+ if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
+ err = __ksm_enter(mm);
+ if (err)
+ return err;
+ }
+
+ set_bit(MMF_VM_MERGE_ANY, &mm->flags);
+ ksm_add_vmas(mm);
+
+ return 0;
+}
+
int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
unsigned long end, int advice, unsigned long *vm_flags)
{
@@ -2493,25 +2577,10 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
switch (advice) {
case MADV_MERGEABLE:
- /*
- * Be somewhat over-protective for now!
- */
- if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE |
- VM_PFNMAP | VM_IO | VM_DONTEXPAND |
- VM_HUGETLB | VM_MIXEDMAP))
- return 0; /* just ignore the advice */
-
- if (vma_is_dax(vma))
+ if (vma->vm_flags & VM_MERGEABLE)
return 0;
-
-#ifdef VM_SAO
- if (*vm_flags & VM_SAO)
+ if (!vma_ksm_compatible(vma))
return 0;
-#endif
-#ifdef VM_SPARC_ADI
- if (*vm_flags & VM_SPARC_ADI)
- return 0;
-#endif
if (!test_bit(MMF_VM_MERGEABLE, &mm->flags)) {
err = __ksm_enter(mm);
@@ -2615,6 +2684,7 @@ void __ksm_exit(struct mm_struct *mm)
if (easy_to_free) {
mm_slot_free(mm_slot_cache, mm_slot);
+ clear_bit(MMF_VM_MERGE_ANY, &mm->flags);
clear_bit(MMF_VM_MERGEABLE, &mm->flags);
mmdrop(mm);
} else if (mm_slot) {
diff --git a/mm/mmap.c b/mm/mmap.c
index 790cc62c0038449befabfb8f657588c120061b50..51b6976fd5256addd71e1d1638d10c8b788bbc2f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -46,6 +46,7 @@
#include <linux/pkeys.h>
#include <linux/oom.h>
#include <linux/sched/mm.h>
+#include <linux/ksm.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
@@ -2729,6 +2730,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
if (file && vm_flags & VM_SHARED)
mapping_unmap_writable(file->f_mapping);
file = vma->vm_file;
+ ksm_add_vma(vma);
expanded:
perf_event_mmap(vma);
@@ -3001,6 +3003,7 @@ static int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
goto mas_store_fail;
mm->map_count++;
+ ksm_add_vma(vma);
out:
perf_event_mmap(vma);
mm->total_vm += len >> PAGE_SHIFT;