From: Erik Jacobson <ejacobso@redhat.com>
Subject: [RHEL5 Patch] 2/2 BZ 221029 x86_64 big memory Intel S5000PAL systems freeze at startup
Date: Thu, 11 Jan 2007 20:16:35 -0500
Bugzilla: 221029
Message-Id: <20070112011635.GA14915@redhat.com>
Changelog: mm: handle mapping of memory without a struct page backing it


Patch Author: Jes Sorensen
Community Status: From the community
Original RH Kernel List Posting:
http://post-office.corp.redhat.com/archives/rhkernel-list/2006-October/msg00925.html

Git link:
http://kernel.org/git/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=f4b81804a2d1ab341a4613089dc31ecce0800ed8


This description is from Jes's original posting:


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.

This feature is used by the MSPEC driver and other users, where it is
highly undesirable to have a struct page sitting behind the page (for
instance if the page is accessed in cached mode via the struct page in
parallel to the the driver accessing it uncached, which can result in data
corruption on some architectures, such as ia64).

This version uses specific NOPFN_{SIGBUS,OOM} return values, rather than
expect all negative pfn values would be an error.  It also bugs on cow
mappings as this would not work with the VM.

Index: linux/include/linux/mm.h
===================================================================
--- linux.orig/include/linux/mm.h	2007-01-11 10:31:44.801835178 -0600
+++ linux/include/linux/mm.h	2007-01-11 10:33:30.698686510 -0600
@@ -201,6 +201,7 @@
 	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);
+	unsigned long (*nopfn)(struct vm_area_struct * area, unsigned long address);
 	int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock);
 
 	/* notification that a previously read-only page is about to become
@@ -629,6 +630,12 @@
 #define NOPAGE_OOM	((struct page *) (-1))
 
 /*
+ * Error return values for the *_nopfn functions
+ */
+#define NOPFN_SIGBUS	((unsigned long) -1)
+#define NOPFN_OOM	((unsigned long) -2)
+
+/*
  * Different kinds of faults, as returned by handle_mm_fault().
  * Used to decide whether a process gets delivered SIGBUS or
  * just gets major/minor fault counters bumped up.
Index: linux/mm/memory.c
===================================================================
--- linux.orig/mm/memory.c	2007-01-11 10:31:40.697337190 -0600
+++ linux/mm/memory.c	2007-01-11 10:33:30.706687481 -0600
@@ -2361,6 +2361,54 @@
 }
 
 /*
+ * 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.
+ *
+ * Mark this `noinline' to prevent it from bloating the main pagefault code.
+ */
+static noinline 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;
+	unsigned long pfn;
+	int ret = VM_FAULT_MINOR;
+
+	pte_unmap(page_table);
+	BUG_ON(!(vma->vm_flags & VM_PFNMAP));
+	BUG_ON(is_cow_mapping(vma->vm_flags));
+
+	pfn = vma->vm_ops->nopfn(vma, address & PAGE_MASK);
+	if (pfn == NOPFN_OOM)
+		return VM_FAULT_OOM;
+	if (pfn == NOPFN_SIGBUS)
+		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.
@@ -2422,11 +2470,17 @@
 	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 (unlikely(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,