[RFCv1,2/6] pagewalk: Add a page table walker for init_mm page table

Commit Message

Pasha Tatashin Nov. 16, 2024, 5:59 p.m. UTC

Page Detective will use it to walk the kernel page table. Make this
function accessible from modules, and also while here make
walk_page_range() accessible from modules, so Page Detective could
use it to walk user page tables.

Signed-off-by: Pasha Tatashin <[e-mail]>
---
 include/linux/pagewalk.h |  2 ++
 mm/pagewalk.c            | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+)

Patch

diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
index f5eb5a32aeed..ff25374470f0 100644
--- a/include/linux/pagewalk.h
+++ b/include/linux/pagewalk.h
@@ -124,6 +124,8 @@  int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
 int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end, const struct mm_walk_ops *ops,
 			void *private);
+int walk_page_range_kernel(unsigned long start, unsigned long end,
+			   const struct mm_walk_ops *ops, void *private);
 int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
 		void *private);
 int walk_page_mapping(struct address_space *mapping, pgoff_t first_index,
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 5f9f01532e67..050790aeb15f 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -478,6 +478,7 @@  int walk_page_range(struct mm_struct *mm, unsigned long start,
 	} while (start = next, start < end);
 	return err;
 }
+EXPORT_SYMBOL_GPL(walk_page_range);
 
 /**
  * walk_page_range_novma - walk a range of pagetables not backed by a vma
@@ -541,6 +542,37 @@  int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
 	return walk_pgd_range(start, end, &walk);
 }
 
+/**
+ * walk_page_range_kernel - walk a range of pagetables of kernel/init_mm
+ * @start:	start address of the virtual address range
+ * @end:	end address of the virtual address range
+ * @ops:	operation to call during the walk
+ * @private:	private data for callbacks' usage
+ *
+ * Similar to walk_page_range_novma() but specifically walks init_mm.pgd table.
+ *
+ * Note: This function takes two looks: get_online_mems(), and mmap_read, this
+ * is to prevent kernel page tables from being freed while walking.
+ */
+int walk_page_range_kernel(unsigned long start, unsigned long end,
+			   const struct mm_walk_ops *ops, void *private)
+{
+		get_online_mems();
+		if (mmap_read_lock_killable(&init_mm)) {
+			put_online_mems();
+			return -EAGAIN;
+		}
+
+		walk_page_range_novma(&init_mm, start, end, ops,
+				      init_mm.pgd, private);
+
+		mmap_read_unlock(&init_mm);
+		put_online_mems();
+
+		return 0;
+}
+EXPORT_SYMBOL_GPL(walk_page_range_kernel);
+
 int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end, const struct mm_walk_ops *ops,
 			void *private)