VM, x86, PAT: Change is_linear_pfn_mapping to not use vm_pgoff

Impact: fix false positive PAT warnings - also fix VirtalBox hang

Use of vma->vm_pgoff to identify the pfnmaps that are fully
mapped at mmap time is broken. vm_pgoff is set by generic mmap
code even for cases where drivers are setting up the mappings
at the fault time.

The problem was originally reported here:

 http://marc.info/?l=linux-kernel&m=123383810628583&w=2

Change is_linear_pfn_mapping logic to overload VM_INSERTPAGE
flag along with VM_PFNMAP to mean full PFNMAP setup at mmap
time.

Problem also tracked at:

 http://bugzilla.kernel.org/show_bug.cgi?id=12800

Reported-by: Thomas Hellstrom <thellstrom@vmware.com>
Tested-by: Frans Pop <elendil@planet.nl>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha>@intel.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: "ebiederm@xmission.com" <ebiederm@xmission.com>
Cc: <stable@kernel.org> # only for 2.6.29.1, not .28
LKML-Reference: <20090313004527.GA7176@linux-os.sc.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index e0ab173b6974ba4e7f150adf480fd6e603a5c20c..21bc1f787ae2cd75e50bc2a58a9ff1f9b5f8ed3b 100644 (file)
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -641,10 +641,11 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
        is_ram = pat_pagerange_is_ram(paddr, paddr + size);
 
        /*
-        * reserve_pfn_range() doesn't support RAM pages.
+        * reserve_pfn_range() doesn't support RAM pages. Maintain the current
+        * behavior with RAM pages by returning success.
         */
        if (is_ram != 0)
-               return -EINVAL;
+               return 0;
 
        ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
        if (ret)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 065cdf8c09fb50fcce6ff67bcae848ac555c6b7a..3daa05feed9f7521983e6de482e11910947bb7c3 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -98,7 +98,7 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_HUGETLB     0x00400000      /* Huge TLB Page VM */
 #define VM_NONLINEAR   0x00800000      /* Is non-linear (remap_file_pages) */
 #define VM_MAPPED_COPY 0x01000000      /* T if mapped copy of data (nommu mmap) */
-#define VM_INSERTPAGE  0x02000000      /* The vma has had "vm_insert_page()" done on it */
+#define VM_INSERTPAGE  0x02000000      /* The vma has had "vm_insert_page()" done on it. Refer note in VM_PFNMAP_AT_MMAP below */
 #define VM_ALWAYSDUMP  0x04000000      /* Always include in core dumps */
 
 #define VM_CAN_NONLINEAR 0x08000000    /* Has ->fault & does nonlinear pages */
@@ -126,6 +126,17 @@ extern unsigned int kobjsize(const void *objp);
  */
 #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP)
 
+/*
+ * pfnmap vmas that are fully mapped at mmap time (not mapped on fault).
+ * Used by x86 PAT to identify such PFNMAP mappings and optimize their handling.
+ * Note VM_INSERTPAGE flag is overloaded here. i.e,
+ * VM_INSERTPAGE && !VM_PFNMAP implies
+ *     The vma has had "vm_insert_page()" done on it
+ * VM_INSERTPAGE && VM_PFNMAP implies
+ *     The vma is PFNMAP with full mapping at mmap time
+ */
+#define VM_PFNMAP_AT_MMAP (VM_INSERTPAGE | VM_PFNMAP)
+
 /*
  * mapping from the currently active vm_flags protection bits (the
  * low four bits) to a page protection mask..
@@ -145,7 +156,7 @@ extern pgprot_t protection_map[16];
  */
 static inline int is_linear_pfn_mapping(struct vm_area_struct *vma)
 {
-       return ((vma->vm_flags & VM_PFNMAP) && vma->vm_pgoff);
+       return ((vma->vm_flags & VM_PFNMAP_AT_MMAP) == VM_PFNMAP_AT_MMAP);
 }
 
 static inline int is_pfn_mapping(struct vm_area_struct *vma)

diff --git a/mm/memory.c b/mm/memory.c
index baa999e87cd21d2f9e67c8e3b1093bb6831513fb..d7df5babcba9332e1ea50e6a8683b56c91bdc225 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1665,9 +1665,10 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
         * behaviour that some programs depend on. We mark the "original"
         * un-COW'ed pages by matching them up with "vma->vm_pgoff".
         */
-       if (addr == vma->vm_start && end == vma->vm_end)
+       if (addr == vma->vm_start && end == vma->vm_end) {
                vma->vm_pgoff = pfn;
-       else if (is_cow_mapping(vma->vm_flags))
+               vma->vm_flags |= VM_PFNMAP_AT_MMAP;
+       } else if (is_cow_mapping(vma->vm_flags))
                return -EINVAL;
 
        vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
@@ -1679,6 +1680,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
                 * needed from higher level routine calling unmap_vmas
                 */
                vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP);
+               vma->vm_flags &= ~VM_PFNMAP_AT_MMAP;
                return -EINVAL;
        }