x86: PAT: hooks in generic vm code to help archs to track pfnmap regions - v3

Impact: Introduces new hooks, which are currently null.

Introduce generic hooks in remap_pfn_range and vm_insert_pfn and
corresponding copy and free routines with reserve and free tracking.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/include/linux/mm.h b/include/linux/mm.h
index a25024ff9c11966010e3ff647a555a09f1f2e7d6..87ecb40e11a0f2d5294edbe16ea43db79cf08ba0 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -155,6 +155,12 @@ static inline int is_pfn_mapping(struct vm_area_struct *vma)
        return (vma->vm_flags & VM_PFNMAP);
 }
 
+extern int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+                               unsigned long pfn, unsigned long size);
+extern int track_pfn_vma_copy(struct vm_area_struct *vma);
+extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
+                               unsigned long size);
+
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's
  * ->fault function. The vma's ->fault is responsible for returning a bitmask

diff --git a/mm/memory.c b/mm/memory.c
index 8ca6bbf34ad6ac2be0596441e1e57ccebb9c555f..1e8f0d347c0e3943be549c0dfce465555b84e876 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -99,6 +99,50 @@ int randomize_va_space __read_mostly =
                                        2;
 #endif
 
+#ifndef track_pfn_vma_new
+/*
+ * Interface that can be used by architecture code to keep track of
+ * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
+ *
+ * track_pfn_vma_new is called when a _new_ pfn mapping is being established
+ * for physical range indicated by pfn and size.
+ */
+int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+                       unsigned long pfn, unsigned long size)
+{
+       return 0;
+}
+#endif
+
+#ifndef track_pfn_vma_copy
+/*
+ * Interface that can be used by architecture code to keep track of
+ * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
+ *
+ * track_pfn_vma_copy is called when vma that is covering the pfnmap gets
+ * copied through copy_page_range().
+ */
+int track_pfn_vma_copy(struct vm_area_struct *vma)
+{
+       return 0;
+}
+#endif
+
+#ifndef untrack_pfn_vma
+/*
+ * Interface that can be used by architecture code to keep track of
+ * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
+ *
+ * untrack_pfn_vma is called while unmapping a pfnmap for a region.
+ * untrack can be called for a specific region indicated by pfn and size or
+ * can be for the entire vma (in which case size can be zero).
+ */
+void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
+                       unsigned long size)
+{
+}
+#endif
+
 static int __init disable_randmaps(char *s)
 {
        randomize_va_space = 0;
@@ -669,6 +713,16 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
        if (is_vm_hugetlb_page(vma))
                return copy_hugetlb_page_range(dst_mm, src_mm, vma);
 
+       if (is_pfn_mapping(vma)) {
+               /*
+                * We do not free on error cases below as remove_vma
+                * gets called on error from higher level routine
+                */
+               ret = track_pfn_vma_copy(vma);
+               if (ret)
+                       return ret;
+       }
+
        /*
         * We need to invalidate the secondary MMU mappings only when
         * there could be a permission downgrade on the ptes of the
@@ -915,6 +969,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
                if (vma->vm_flags & VM_ACCOUNT)
                        *nr_accounted += (end - start) >> PAGE_SHIFT;
 
+               if (is_pfn_mapping(vma))
+                       untrack_pfn_vma(vma, 0, 0);
+
                while (start != end) {
                        if (!tlb_start_valid) {
                                tlb_start = start;
@@ -1473,6 +1530,7 @@ out:
 int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
                        unsigned long pfn)
 {
+       int ret;
        /*
         * Technically, architectures with pte_special can avoid all these
         * restrictions (same for remap_pfn_range).  However we would like
@@ -1487,7 +1545,15 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 
        if (addr < vma->vm_start || addr >= vma->vm_end)
                return -EFAULT;
-       return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+       if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE))
+               return -EINVAL;
+
+       ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+
+       if (ret)
+               untrack_pfn_vma(vma, pfn, PAGE_SIZE);
+
+       return ret;
 }
 EXPORT_SYMBOL(vm_insert_pfn);
 
@@ -1625,6 +1691,10 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 
        vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
 
+       err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size));
+       if (err)
+               return -EINVAL;
+
        BUG_ON(addr >= end);
        pfn -= addr >> PAGE_SHIFT;
        pgd = pgd_offset(mm, addr);
@@ -1636,6 +1706,10 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
                if (err)
                        break;
        } while (pgd++, addr = next, addr != end);
+
+       if (err)
+               untrack_pfn_vma(vma, pfn, PAGE_ALIGN(size));
+
        return err;
 }
 EXPORT_SYMBOL(remap_pfn_range);