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>

1 files changed, 4 insertions, 13 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 41e2a2d4b2a6..6040b74d02a2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3489,7 +3489,7 @@ static int create_huge_pmd(struct vm_fault *vmf)
         if (vma_is_anonymous(vmf->vma))
                 return do_huge_pmd_anonymous_page(vmf);
         if (vmf->vma->vm_ops->huge_fault)
-                return vmf->vma->vm_ops->huge_fault(vmf);
+                return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
         return VM_FAULT_FALLBACK;
 }
 
@@ -3498,7 +3498,7 @@ static int wp_huge_pmd(struct vm_fault *vmf, pmd_t orig_pmd)
         if (vma_is_anonymous(vmf->vma))
                 return do_huge_pmd_wp_page(vmf, orig_pmd);
         if (vmf->vma->vm_ops->huge_fault)
-                return vmf->vma->vm_ops->huge_fault(vmf);
+                return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PMD);
 
         /* COW handled on pte level: split pmd */
         VM_BUG_ON_VMA(vmf->vma->vm_flags & VM_SHARED, vmf->vma);
@@ -3519,7 +3519,7 @@ static int create_huge_pud(struct vm_fault *vmf)
         if (vma_is_anonymous(vmf->vma))
                 return VM_FAULT_FALLBACK;
         if (vmf->vma->vm_ops->huge_fault)
-                return vmf->vma->vm_ops->huge_fault(vmf);
+                return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
         return VM_FAULT_FALLBACK;
 }
@@ -3531,7 +3531,7 @@ static int wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
         if (vma_is_anonymous(vmf->vma))
                 return VM_FAULT_FALLBACK;
         if (vmf->vma->vm_ops->huge_fault)
-                return vmf->vma->vm_ops->huge_fault(vmf);
+                return vmf->vma->vm_ops->huge_fault(vmf, PE_SIZE_PUD);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
         return VM_FAULT_FALLBACK;
 }
@@ -3659,7 +3659,6 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
         if (!vmf.pud)
                 return VM_FAULT_OOM;
         if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) {
-                vmf.flags |= FAULT_FLAG_SIZE_PUD;
                 ret = create_huge_pud(&vmf);
                 if (!(ret & VM_FAULT_FALLBACK))
                         return ret;
@@ -3670,8 +3669,6 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
                 if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
                         unsigned int dirty = flags & FAULT_FLAG_WRITE;
 
-                        vmf.flags |= FAULT_FLAG_SIZE_PUD;
-
                         /* NUMA case for anonymous PUDs would go here */
 
                         if (dirty && !pud_write(orig_pud)) {
@@ -3689,18 +3686,14 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
         if (!vmf.pmd)
                 return VM_FAULT_OOM;
         if (pmd_none(*vmf.pmd) && transparent_hugepage_enabled(vma)) {
-                vmf.flags |= FAULT_FLAG_SIZE_PMD;
                 ret = create_huge_pmd(&vmf);
                 if (!(ret & VM_FAULT_FALLBACK))
                         return ret;
-                /* fall through path, remove PMD flag */
-                vmf.flags &= ~FAULT_FLAG_SIZE_PMD;
         } else {
                 pmd_t orig_pmd = *vmf.pmd;
 
                 barrier();
                 if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
-                        vmf.flags |= FAULT_FLAG_SIZE_PMD;
                         if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
                                 return do_huge_pmd_numa_page(&vmf, orig_pmd);
 
@@ -3709,8 +3702,6 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
                                 ret = wp_huge_pmd(&vmf, orig_pmd);
                                 if (!(ret & VM_FAULT_FALLBACK))
                                         return ret;
-                                /* fall through path, remove PUD flag */
-                                vmf.flags &= ~FAULT_FLAG_SIZE_PUD;
                         } else {
                                 huge_pmd_set_accessed(&vmf, orig_pmd);
                                 return 0;