aboutsummaryrefslogtreecommitdiff
path: root/fs/userfaultfd.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/userfaultfd.c')
-rw-r--r--fs/userfaultfd.c84
1 files changed, 68 insertions, 16 deletions
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 44d1ee429eb0..4e800bb7d2ab 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -32,7 +32,22 @@
#include <linux/swapops.h>
#include <linux/miscdevice.h>
-int sysctl_unprivileged_userfaultfd __read_mostly;
+static int sysctl_unprivileged_userfaultfd __read_mostly;
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table vm_userfaultfd_table[] = {
+ {
+ .procname = "unprivileged_userfaultfd",
+ .data = &sysctl_unprivileged_userfaultfd,
+ .maxlen = sizeof(sysctl_unprivileged_userfaultfd),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+ { }
+};
+#endif
static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly;
@@ -108,6 +123,21 @@ static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx)
return ctx->features & UFFD_FEATURE_INITIALIZED;
}
+/*
+ * Whether WP_UNPOPULATED is enabled on the uffd context. It is only
+ * meaningful when userfaultfd_wp()==true on the vma and when it's
+ * anonymous.
+ */
+bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma)
+{
+ struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
+
+ if (!ctx)
+ return false;
+
+ return ctx->features & UFFD_FEATURE_WP_UNPOPULATED;
+}
+
static void userfaultfd_set_vm_flags(struct vm_area_struct *vma,
vm_flags_t flags)
{
@@ -1302,6 +1332,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
bool basic_ioctls;
unsigned long start, end, vma_end;
struct vma_iterator vmi;
+ pgoff_t pgoff;
user_uffdio_register = (struct uffdio_register __user *) arg;
@@ -1429,6 +1460,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
vma_iter_set(&vmi, start);
prev = vma_prev(&vmi);
+ if (vma->vm_start < start)
+ prev = vma;
ret = 0;
for_each_vma_range(vmi, vma, end) {
@@ -1452,8 +1485,9 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
vma_end = min(end, vma->vm_end);
new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags;
+ pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags,
- vma->anon_vma, vma->vm_file, vma->vm_pgoff,
+ vma->anon_vma, vma->vm_file, pgoff,
vma_policy(vma),
((struct vm_userfaultfd_ctx){ ctx }),
anon_vma_name(vma));
@@ -1533,6 +1567,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
unsigned long start, end, vma_end;
const void __user *buf = (void __user *)arg;
struct vma_iterator vmi;
+ pgoff_t pgoff;
ret = -EFAULT;
if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
@@ -1595,6 +1630,9 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
vma_iter_set(&vmi, start);
prev = vma_prev(&vmi);
+ if (vma->vm_start < start)
+ prev = vma;
+
ret = 0;
for_each_vma_range(vmi, vma, end) {
cond_resched();
@@ -1629,11 +1667,12 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
/* Reset ptes for the whole vma range if wr-protected */
if (userfaultfd_wp(vma))
- uffd_wp_range(mm, vma, start, vma_end - start, false);
+ uffd_wp_range(vma, start, vma_end - start, false);
new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
+ pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
prev = vma_merge(&vmi, mm, prev, start, vma_end, new_flags,
- vma->anon_vma, vma->vm_file, vma->vm_pgoff,
+ vma->anon_vma, vma->vm_file, pgoff,
vma_policy(vma),
NULL_VM_UFFD_CTX, anon_vma_name(vma));
if (prev) {
@@ -1714,6 +1753,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
struct uffdio_copy uffdio_copy;
struct uffdio_copy __user *user_uffdio_copy;
struct userfaultfd_wake_range range;
+ uffd_flags_t flags = 0;
user_uffdio_copy = (struct uffdio_copy __user *) arg;
@@ -1740,10 +1780,12 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
goto out;
if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP))
goto out;
+ if (uffdio_copy.mode & UFFDIO_COPY_MODE_WP)
+ flags |= MFILL_ATOMIC_WP;
if (mmget_not_zero(ctx->mm)) {
- ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
- uffdio_copy.len, &ctx->mmap_changing,
- uffdio_copy.mode);
+ ret = mfill_atomic_copy(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
+ uffdio_copy.len, &ctx->mmap_changing,
+ flags);
mmput(ctx->mm);
} else {
return -ESRCH;
@@ -1793,9 +1835,9 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
goto out;
if (mmget_not_zero(ctx->mm)) {
- ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start,
- uffdio_zeropage.range.len,
- &ctx->mmap_changing);
+ ret = mfill_atomic_zeropage(ctx->mm, uffdio_zeropage.range.start,
+ uffdio_zeropage.range.len,
+ &ctx->mmap_changing);
mmput(ctx->mm);
} else {
return -ESRCH;
@@ -1875,6 +1917,7 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
struct uffdio_continue uffdio_continue;
struct uffdio_continue __user *user_uffdio_continue;
struct userfaultfd_wake_range range;
+ uffd_flags_t flags = 0;
user_uffdio_continue = (struct uffdio_continue __user *)arg;
@@ -1899,13 +1942,16 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
uffdio_continue.range.start) {
goto out;
}
- if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE)
+ if (uffdio_continue.mode & ~(UFFDIO_CONTINUE_MODE_DONTWAKE |
+ UFFDIO_CONTINUE_MODE_WP))
goto out;
+ if (uffdio_continue.mode & UFFDIO_CONTINUE_MODE_WP)
+ flags |= MFILL_ATOMIC_WP;
if (mmget_not_zero(ctx->mm)) {
- ret = mcopy_continue(ctx->mm, uffdio_continue.range.start,
- uffdio_continue.range.len,
- &ctx->mmap_changing);
+ ret = mfill_atomic_continue(ctx->mm, uffdio_continue.range.start,
+ uffdio_continue.range.len,
+ &ctx->mmap_changing, flags);
mmput(ctx->mm);
} else {
return -ESRCH;
@@ -1955,8 +2001,10 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
ret = -EFAULT;
if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api)))
goto out;
- /* Ignore unsupported features (userspace built against newer kernel) */
- features = uffdio_api.features & UFFD_API_FEATURES;
+ features = uffdio_api.features;
+ ret = -EINVAL;
+ if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES))
+ goto err_out;
ret = -EPERM;
if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE))
goto err_out;
@@ -1971,6 +2019,7 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
#endif
#ifndef CONFIG_PTE_MARKER_UFFD_WP
uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
+ uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED;
#endif
uffdio_api.ioctls = UFFD_API_IOCTLS;
ret = -EFAULT;
@@ -2178,6 +2227,9 @@ static int __init userfaultfd_init(void)
0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC,
init_once_userfaultfd_ctx);
+#ifdef CONFIG_SYSCTL
+ register_sysctl_init("vm", vm_userfaultfd_table);
+#endif
return 0;
}
__initcall(userfaultfd_init);