[patch] do_no_pfn handler

[Jes Sorensen <jes@sgi.com>]

Linus,

Attached is a repost of the do_no_pfn handler patch. This version
includes all the changes that were suggested after my previous posting
(the order of checking ->nopage before ->nopfn and Nick's suggestion
to check for others refaulting the same).  The patch is needed for the
MSPEC driver and Bjorn and Carsten have expressed strong interest in
using this interface for other things as well.

You mentioned earlier that you preferred an alternative approach, do
you still feel that given the additional interest from other Bjorn and
Carsten? If this is still the case, I'd love to get some guidance as
to what that should be.

I had hoped to get this in before 2.6.17, dunno if that is too late or
would you prefer to see it in -mm first?

Thanks,
Jes

Implement do_no_pfn() for handling mapping of memory without a struct
page backing it. This avoids creating fake page table entries for
regions which are not backed by real memory.

Signed-off-by: Jes Sorensen <jes@sgi.com>

---
 include/linux/mm.h |    1 
 mm/memory.c        |   63 ++++++++++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 59 insertions(+), 5 deletions(-)

Index: linux-2.6/include/linux/mm.h
===================================================================
--- linux-2.6.orig/include/linux/mm.h
+++ linux-2.6/include/linux/mm.h
@@ -199,6 +199,7 @@
 	void (*open)(struct vm_area_struct * area);
 	void (*close)(struct vm_area_struct * area);
 	struct page * (*nopage)(struct vm_area_struct * area, unsigned long address, int *type);
+	long (*nopfn)(struct vm_area_struct * area, unsigned long address, int *type);
 	int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock);
 #ifdef CONFIG_NUMA
 	int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);
Index: linux-2.6/mm/memory.c
===================================================================
--- linux-2.6.orig/mm/memory.c
+++ linux-2.6/mm/memory.c
@@ -2146,6 +2146,53 @@
 }
 
 /*
+ * do_no_pfn() tries to create a new page mapping for a page without
+ * a struct_page backing it
+ *
+ * As this is called only for pages that do not currently exist, we
+ * do not need to flush old virtual caches or the TLB.
+ *
+ * We enter with non-exclusive mmap_sem (to exclude vma changes,
+ * but allow concurrent faults), and pte mapped but not yet locked.
+ * We return with mmap_sem still held, but pte unmapped and unlocked.
+ *
+ * It is expected that the ->nopfn handler always returns the same pfn
+ * for a given virtual mapping.
+ */
+static int do_no_pfn(struct mm_struct *mm, struct vm_area_struct *vma,
+		     unsigned long address, pte_t *page_table, pmd_t *pmd,
+		     int write_access)
+{
+	spinlock_t *ptl;
+	pte_t entry;
+	long pfn;
+	int ret = VM_FAULT_MINOR;
+
+	pte_unmap(page_table);
+	BUG_ON(!(vma->vm_flags & VM_PFNMAP));
+
+	pfn = vma->vm_ops->nopfn(vma, address & PAGE_MASK, &ret);
+	if (pfn == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (pfn == -EFAULT)
+		return VM_FAULT_SIGBUS;
+	if (pfn < 0)
+		return VM_FAULT_SIGBUS;
+
+	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
+
+	/* Only go through if we didn't race with anybody else... */
+	if (pte_none(*page_table)) {
+		entry = pfn_pte(pfn, vma->vm_page_prot);
+		if (write_access)
+			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		set_pte_at(mm, address, page_table, entry);
+	}
+	pte_unmap_unlock(page_table, ptl);
+	return ret;
+}
+
+/*
  * Fault of a previously existing named mapping. Repopulate the pte
  * from the encoded file_pte if possible. This enables swappable
  * nonlinear vmas.
@@ -2207,11 +2254,17 @@
 	old_entry = entry = *pte;
 	if (!pte_present(entry)) {
 		if (pte_none(entry)) {
-			if (!vma->vm_ops || !vma->vm_ops->nopage)
-				return do_anonymous_page(mm, vma, address,
-					pte, pmd, write_access);
-			return do_no_page(mm, vma, address,
-					pte, pmd, write_access);
+			if (vma->vm_ops) {
+				if (vma->vm_ops->nopage)
+					return do_no_page(mm, vma, address,
+							  pte, pmd,
+							  write_access);
+				if (vma->vm_ops->nopfn)
+					return do_no_pfn(mm, vma, address, pte,
+							 pmd, write_access);
+			}
+			return do_anonymous_page(mm, vma, address,
+						 pte, pmd, write_access);
 		}
 		if (pte_file(entry))
 			return do_file_page(mm, vma, address,
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/