fs/proc/task_mmu: implement IOCTL to get and optionally clear info about PTEs

The PAGEMAP_SCAN IOCTL on the pagemap file can be used to get or optionally
clear the info about page table entries. The following operations are
supported in this IOCTL:
- Scan the address range and get the memory ranges matching the provided
  criteria. This is performed when the output buffer is specified.
- Write-protect the pages. The PM_SCAN_WP_MATCHING is used to write-protect
  the pages of interest. The PM_SCAN_CHECK_WPASYNC aborts the operation if
  non-Async Write Protected pages are found. The ``PM_SCAN_WP_MATCHING``
  can be used with or without PM_SCAN_CHECK_WPASYNC.
- Both of those operations can be combined into one atomic operation where
  we can get and write protect the pages as well.

Following flags about pages are currently supported:
- PAGE_IS_WPALLOWED - Page has async-write-protection enabled
- PAGE_IS_WRITTEN - Page has been written to from the time it was write protected
- PAGE_IS_FILE - Page is file backed
- PAGE_IS_PRESENT - Page is present in the memory
- PAGE_IS_SWAPPED - Page is in swapped
- PAGE_IS_PFNZERO - Page has zero PFN
- PAGE_IS_HUGE - Page is THP or Hugetlb backed

This IOCTL can be extended to get information about more PTE bits. The
entire address range passed by user [start, end) is scanned until either
the user provided buffer is full or max_pages have been found.

[akpm@linux-foundation.org: update it for "mm: hugetlb: add huge page size param to set_huge_pte_at()"]
[akpm@linux-foundation.org: fix CONFIG_HUGETLB_PAGE=n warning]
[arnd@arndb.de: hide unused pagemap_scan_backout_range() function]
  Link: https://lkml.kernel.org/r/20230927060257.2975412-1-arnd@kernel.org
[sfr@canb.auug.org.au: fix "fs/proc/task_mmu: hide unused pagemap_scan_backout_range() function"]
  Link: https://lkml.kernel.org/r/20230928092223.0625c6bf@canb.auug.org.au
Link: https://lkml.kernel.org/r/20230821141518.870589-3-usama.anjum@collabora.com
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Reviewed-by: Andrei Vagin <avagin@gmail.com>
Reviewed-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Cc: Alex Sierra <alex.sierra@amd.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Miroslaw <emmir@google.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nadav Amit <namit@vmware.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yun Zhou <yun.zhou@windriver.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/hugetlb.h

@@ -280,6 +280,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long cp_flags);
 
 bool is_hugetlb_entry_migration(pte_t pte);
+bool is_hugetlb_entry_hwpoisoned(pte_t pte);
 void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);
 
 #else /* !CONFIG_HUGETLB_PAGE */

include/linux/userfaultfd_k.h

@@ -221,6 +221,13 @@ static inline vm_fault_t handle_userfault(struct vm_fault *vmf,
 	return VM_FAULT_SIGBUS;
 }
 
+static inline long uffd_wp_range(struct vm_area_struct *vma,
+				 unsigned long start, unsigned long len,
+				 bool enable_wp)
+{
+	return false;
+}
+
 static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
 					struct vm_userfaultfd_ctx vm_ctx)
 {

include/uapi/linux/fs.h

@@ -305,4 +305,63 @@ typedef int __bitwise __kernel_rwf_t;
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
 			 RWF_APPEND)
 
+/* Pagemap ioctl */
+#define PAGEMAP_SCAN	_IOWR('f', 16, struct pm_scan_arg)
+
+/* Bitmasks provided in pm_scan_args masks and reported in page_region.categories. */
+#define PAGE_IS_WPALLOWED	(1 << 0)
+#define PAGE_IS_WRITTEN		(1 << 1)
+#define PAGE_IS_FILE		(1 << 2)
+#define PAGE_IS_PRESENT		(1 << 3)
+#define PAGE_IS_SWAPPED		(1 << 4)
+#define PAGE_IS_PFNZERO		(1 << 5)
+#define PAGE_IS_HUGE		(1 << 6)
+
+/*
+ * struct page_region - Page region with flags
+ * @start:	Start of the region
+ * @end:	End of the region (exclusive)
+ * @categories:	PAGE_IS_* category bitmask for the region
+ */
+struct page_region {
+	__u64 start;
+	__u64 end;
+	__u64 categories;
+};
+
+/* Flags for PAGEMAP_SCAN ioctl */
+#define PM_SCAN_WP_MATCHING	(1 << 0)	/* Write protect the pages matched. */
+#define PM_SCAN_CHECK_WPASYNC	(1 << 1)	/* Abort the scan when a non-WP-enabled page is found. */
+
+/*
+ * struct pm_scan_arg - Pagemap ioctl argument
+ * @size:		Size of the structure
+ * @flags:		Flags for the IOCTL
+ * @start:		Starting address of the region
+ * @end:		Ending address of the region
+ * @walk_end		Address where the scan stopped (written by kernel).
+ *			walk_end == end (address tags cleared) informs that the scan completed on entire range.
+ * @vec:		Address of page_region struct array for output
+ * @vec_len:		Length of the page_region struct array
+ * @max_pages:		Optional limit for number of returned pages (0 = disabled)
+ * @category_inverted:	PAGE_IS_* categories which values match if 0 instead of 1
+ * @category_mask:	Skip pages for which any category doesn't match
+ * @category_anyof_mask: Skip pages for which no category matches
+ * @return_mask:	PAGE_IS_* categories that are to be reported in `page_region`s returned
+ */
+struct pm_scan_arg {
+	__u64 size;
+	__u64 flags;
+	__u64 start;
+	__u64 end;
+	__u64 walk_end;
+	__u64 vec;
+	__u64 vec_len;
+	__u64 max_pages;
+	__u64 category_inverted;
+	__u64 category_mask;
+	__u64 category_anyof_mask;
+	__u64 return_mask;
+};
+
 #endif /* _UAPI_LINUX_FS_H */

mm/hugetlb.c

@@ -5044,7 +5044,7 @@ bool is_hugetlb_entry_migration(pte_t pte)
 		return false;
 }
 
-static bool is_hugetlb_entry_hwpoisoned(pte_t pte)
+bool is_hugetlb_entry_hwpoisoned(pte_t pte)
 {
 	swp_entry_t swp;
 
@@ -6266,7 +6266,8 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		}
 
 		entry = huge_pte_clear_uffd_wp(entry);
-		set_huge_pte_at(mm, haddr, ptep, entry);
+		set_huge_pte_at(mm, haddr, ptep, entry,
+				huge_page_size(hstate_vma(vma)));
 		/* Fallthrough to CoW */
 	}