mm: replace FAULT_FLAG_SIZE with parameter to huge_fault

Since the introduction of FAULT_FLAG_SIZE to the vm_fault flag, it has
been somewhat painful with getting the flags set and removed at the
correct locations.  More than one kernel oops was introduced due to
difficulties of getting the placement correctly.

Remove the flag values and introduce an input parameter to huge_fault
that indicates the size of the page entry.  This makes the code easier
to trace and should avoid the issues we see with the fault flags where
removal of the flag was necessary in the fallback paths.

Link: http://lkml.kernel.org/r/148615748258.43180.1690152053774975329.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 10 insertions, 7 deletions

diff --git a/include/linux/dax.h b/include/linux/dax.h
index cf9af225962b..d8a3dc042e1c 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -38,7 +38,8 @@ static inline void *dax_radix_locked_entry(sector_t sector, unsigned long flags)
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops);
-int dax_iomap_fault(struct vm_fault *vmf, const struct iomap_ops *ops);
+int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+		    const struct iomap_ops *ops);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index d8b75d7d6a9e..c65aa43b5712 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -285,11 +285,6 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_REMOTE	0x80	/* faulting for non current tsk/mm */
 #define FAULT_FLAG_INSTRUCTION  0x100	/* The fault was during an instruction fetch */
 
-#define FAULT_FLAG_SIZE_MASK	0x7000	/* Support up to 8-level page tables */
-#define FAULT_FLAG_SIZE_PTE	0x0000	/* First level (eg 4k) */
-#define FAULT_FLAG_SIZE_PMD	0x1000	/* Second level (eg 2MB) */
-#define FAULT_FLAG_SIZE_PUD	0x2000	/* Third level (eg 1GB) */
-
 #define FAULT_FLAG_TRACE \
 	{ FAULT_FLAG_WRITE,		"WRITE" }, \
 	{ FAULT_FLAG_MKWRITE,		"MKWRITE" }, \
@@ -349,6 +344,13 @@ struct vm_fault {
 					 */
 };
 
+/* page entry size for vm->huge_fault() */
+enum page_entry_size {
+	PE_SIZE_PTE = 0,
+	PE_SIZE_PMD,
+	PE_SIZE_PUD,
+};
+
 /*
  * These are the virtual MM functions - opening of an area, closing and
  * unmapping it (needed to keep files on disk up-to-date etc), pointer
@@ -359,7 +361,7 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	int (*mremap)(struct vm_area_struct * area);
 	int (*fault)(struct vm_fault *vmf);
-	int (*huge_fault)(struct vm_fault *vmf);
+	int (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size);
 	void (*map_pages)(struct vm_fault *vmf,
 			pgoff_t start_pgoff, pgoff_t end_pgoff);