userfaultfd: teach vma_merge to merge across vma->vm_userfaultfd_ctx

vma->vm_userfaultfd_ctx is yet another vma parameter that vma_merge
must be aware about so that we can merge vmas back like they were
originally before arming the userfaultfd on some memory range.

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0f7cd30039eaddeaa46986feaf7420387357b03a..77a9d609523e890f64a0c5ba4de1f66a049b6ea5 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1835,7 +1835,7 @@ extern int vma_adjust(struct vm_area_struct *vma, unsigned long start,
 extern struct vm_area_struct *vma_merge(struct mm_struct *,
        struct vm_area_struct *prev, unsigned long addr, unsigned long end,
        unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t,
-       struct mempolicy *);
+       struct mempolicy *, struct vm_userfaultfd_ctx);
 extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *);
 extern int split_vma(struct mm_struct *,
        struct vm_area_struct *, unsigned long addr, int new_below);

diff --git a/mm/madvise.c b/mm/madvise.c
index 64bb8a22110c23b7989256b02c7d4851b89aab3f..911357973905938c3b1a4ccb3bc4e2a2c95abc1d 100644 (file)
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -103,7 +103,8 @@ static long madvise_behavior(struct vm_area_struct *vma,
 
        pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
        *prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma,
-                               vma->vm_file, pgoff, vma_policy(vma));
+                         vma->vm_file, pgoff, vma_policy(vma),
+                         vma->vm_userfaultfd_ctx);
        if (*prev) {
                vma = *prev;
                goto success;

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 99d4c1d0b8583dc453ef992582074ef015f1fb49..a7f1e0d1d6b8fed5d1e3d9bd1380c9cd9b1447e8 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -722,8 +722,8 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
                pgoff = vma->vm_pgoff +
                        ((vmstart - vma->vm_start) >> PAGE_SHIFT);
                prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
-                                 vma->anon_vma, vma->vm_file, pgoff,
-                                 new_pol);
+                                vma->anon_vma, vma->vm_file, pgoff,
+                                new_pol, vma->vm_userfaultfd_ctx);
                if (prev) {
                        vma = prev;
                        next = vma->vm_next;

diff --git a/mm/mlock.c b/mm/mlock.c
index 6fd2cf15e8687d32114f8e81516aed0a52997147..25936680064fd433d4cf693c88c3195bdab4bb98 100644 (file)
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -510,7 +510,8 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 
        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_file, pgoff, vma_policy(vma),
+                         vma->vm_userfaultfd_ctx);
        if (*prev) {
                vma = *prev;
                goto success;

diff --git a/mm/mmap.c b/mm/mmap.c
index f126923ce683c6969a9ce2498bcd481d90d39b8e..82db4fc0a9d34040bf7fa6750eddf7b508fb0e1a 100644 (file)
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -41,6 +41,7 @@
 #include <linux/notifier.h>
 #include <linux/memory.h>
 #include <linux/printk.h>
+#include <linux/userfaultfd_k.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -919,7 +920,8 @@ again:                      remove_next = 1 + (end > next->vm_end);
  * per-vma resources, so we don't attempt to merge those.
  */
 static inline int is_mergeable_vma(struct vm_area_struct *vma,
-                       struct file *file, unsigned long vm_flags)
+                               struct file *file, unsigned long vm_flags,
+                               struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
 {
        /*
         * VM_SOFTDIRTY should not prevent from VMA merging, if we
@@ -935,6 +937,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma,
                return 0;
        if (vma->vm_ops && vma->vm_ops->close)
                return 0;
+       if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx))
+               return 0;
        return 1;
 }
 
@@ -965,9 +969,11 @@ static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1,
  */
 static int
 can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
-       struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
+                    struct anon_vma *anon_vma, struct file *file,
+                    pgoff_t vm_pgoff,
+                    struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
 {
-       if (is_mergeable_vma(vma, file, vm_flags) &&
+       if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) &&
            is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
                if (vma->vm_pgoff == vm_pgoff)
                        return 1;
@@ -984,9 +990,11 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
  */
 static int
 can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
-       struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
+                   struct anon_vma *anon_vma, struct file *file,
+                   pgoff_t vm_pgoff,
+                   struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
 {
-       if (is_mergeable_vma(vma, file, vm_flags) &&
+       if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) &&
            is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
                pgoff_t vm_pglen;
                vm_pglen = vma_pages(vma);
@@ -1029,7 +1037,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
                        struct vm_area_struct *prev, unsigned long addr,
                        unsigned long end, unsigned long vm_flags,
                        struct anon_vma *anon_vma, struct file *file,
-                       pgoff_t pgoff, struct mempolicy *policy)
+                       pgoff_t pgoff, struct mempolicy *policy,
+                       struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
 {
        pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
        struct vm_area_struct *area, *next;
@@ -1056,14 +1065,17 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
        if (prev && prev->vm_end == addr &&
                        mpol_equal(vma_policy(prev), policy) &&
                        can_vma_merge_after(prev, vm_flags,
-                                               anon_vma, file, pgoff)) {
+                                           anon_vma, file, pgoff,
+                                           vm_userfaultfd_ctx)) {
                /*
                 * OK, it can.  Can we now merge in the successor as well?
                 */
                if (next && end == next->vm_start &&
                                mpol_equal(policy, vma_policy(next)) &&
                                can_vma_merge_before(next, vm_flags,
-                                       anon_vma, file, pgoff+pglen) &&
+                                                    anon_vma, file,
+                                                    pgoff+pglen,
+                                                    vm_userfaultfd_ctx) &&
                                is_mergeable_anon_vma(prev->anon_vma,
                                                      next->anon_vma, NULL)) {
                                                        /* cases 1, 6 */
@@ -1084,7 +1096,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
        if (next && end == next->vm_start &&
                        mpol_equal(policy, vma_policy(next)) &&
                        can_vma_merge_before(next, vm_flags,
-                                       anon_vma, file, pgoff+pglen)) {
+                                            anon_vma, file, pgoff+pglen,
+                                            vm_userfaultfd_ctx)) {
                if (prev && addr < prev->vm_end)        /* case 4 */
                        err = vma_adjust(prev, prev->vm_start,
                                addr, prev->vm_pgoff, NULL);
@@ -1570,8 +1583,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
        /*
         * Can we just expand an old mapping?
         */
-       vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff,
-                       NULL);
+       vma = vma_merge(mm, prev, addr, addr + len, vm_flags,
+                       NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX);
        if (vma)
                goto out;
 
@@ -2757,7 +2770,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len)
 
        /* Can we just expand an old private anonymous mapping? */
        vma = vma_merge(mm, prev, addr, addr + len, flags,
-                                       NULL, NULL, pgoff, NULL);
+                       NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX);
        if (vma)
                goto out;
 
@@ -2913,7 +2926,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
        if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent))
                return NULL;    /* should never get here */
        new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
-                       vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
+                           vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+                           vma->vm_userfaultfd_ctx);
        if (new_vma) {
                /*
                 * Source vma may have been merged into new_vma

diff --git a/mm/mprotect.c b/mm/mprotect.c
index e7d6f1171ecb6ec453e62edd88cc258b31cfe9f3..ef5be8eaab001792b469fac1bd5b43cb139d1b0b 100644 (file)
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -292,7 +292,8 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
         */
        pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
        *pprev = vma_merge(mm, *pprev, start, end, newflags,
-                       vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
+                          vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+                          vma->vm_userfaultfd_ctx);
        if (*pprev) {
                vma = *pprev;
                goto success;