diff mbox series

[23/35] kvm, x86: introduce VM_DMEM

Message ID 3c8fc6f37abe66c13348c9af2eacee04d4dfaa72.1602093760.git.yuleixzhang@tencent.com (mailing list archive)
State New, archived
Headers show
Series Enhance memory utilization with DMEMFS | expand

Commit Message

yulei zhang Oct. 8, 2020, 7:54 a.m. UTC
From: Yulei Zhang <yuleixzhang@tencent.com>

Currently dmemfs do not support memory readonly, so change_protection()
will be disabled for dmemfs vma. Since vma->vm_flags could be changed to
new flag in mprotect_fixup(), so we introduce a new vma flag VM_DMEM and
check this flag in mprotect_fixup() to avoid changing vma->vm_flags.

We also check it in vma_to_resize() to disable mremap() for dmemfs vma.

Signed-off-by: Chen Zhuo <sagazchen@tencent.com>
Signed-off-by: Yulei Zhang <yuleixzhang@tencent.com>
---
 fs/dmemfs/inode.c  | 2 +-
 include/linux/mm.h | 7 +++++++
 mm/mprotect.c      | 5 ++++-
 mm/mremap.c        | 3 +++
 4 files changed, 15 insertions(+), 2 deletions(-)
diff mbox series

Patch

diff --git a/fs/dmemfs/inode.c b/fs/dmemfs/inode.c
index e37498c00497..b3e394f33b42 100644
--- a/fs/dmemfs/inode.c
+++ b/fs/dmemfs/inode.c
@@ -510,7 +510,7 @@  int dmemfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
-	vma->vm_flags |= VM_PFNMAP;
+	vma->vm_flags |= VM_PFNMAP | VM_DMEM | VM_IO;
 
 	file_accessed(file);
 	vma->vm_ops = &dmemfs_vm_ops;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ca6e6a81576b..7b1e574d2387 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -309,6 +309,8 @@  extern unsigned int kobjsize(const void *objp);
 #define VM_HIGH_ARCH_4	BIT(VM_HIGH_ARCH_BIT_4)
 #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
 
+#define VM_DMEM		BIT(38)		/* Dmem page VM */
+
 #ifdef CONFIG_ARCH_HAS_PKEYS
 # define VM_PKEY_SHIFT	VM_HIGH_ARCH_BIT_0
 # define VM_PKEY_BIT0	VM_HIGH_ARCH_0	/* A protection key is a 4-bit value */
@@ -656,6 +658,11 @@  static inline bool vma_is_accessible(struct vm_area_struct *vma)
 	return vma->vm_flags & VM_ACCESS_FLAGS;
 }
 
+static inline bool vma_is_dmem(struct vm_area_struct *vma)
+{
+	return !!(vma->vm_flags & VM_DMEM);
+}
+
 #ifdef CONFIG_SHMEM
 /*
  * The vma_is_shmem is not inline because it is used only by slow
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ce8b8a5eacbb..36f885cbbb30 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -236,7 +236,7 @@  static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		 * for all the checks.
 		 */
 		if (!is_swap_pmd(*pmd) && !pmd_devmap(*pmd) &&
-		     pmd_none_or_clear_bad_unless_trans_huge(pmd))
+		     pmd_none_or_clear_bad_unless_trans_huge(pmd) && !pmd_special(*pmd))
 			goto next;
 
 		/* invoke the mmu notifier if the pmd is populated */
@@ -412,6 +412,9 @@  mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 		return 0;
 	}
 
+	if (vma_is_dmem(vma))
+		return -EINVAL;
+
 	/*
 	 * Do PROT_NONE PFN permission checks here when we can still
 	 * bail out without undoing a lot of state. This is a rather
diff --git a/mm/mremap.c b/mm/mremap.c
index 138abbae4f75..598e68174e24 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -482,6 +482,9 @@  static struct vm_area_struct *vma_to_resize(unsigned long addr,
 	if (!vma || vma->vm_start > addr)
 		return ERR_PTR(-EFAULT);
 
+	if (vma_is_dmem(vma))
+		return ERR_PTR(-EINVAL);
+
 	/*
 	 * !old_len is a special case where an attempt is made to 'duplicate'
 	 * a mapping.  This makes no sense for private mappings as it will