Re: [git pull] x86 fixes

["Pallipadi, Venkatesh" <venkatesh.pallipadi@intel.com>]

On Mon, Jan 12, 2009 at 11:01:57AM -0800, Torsten Kaiser wrote:
> On Mon, Jan 12, 2009 at 7:17 PM, Pallipadi, Venkatesh
> <venkatesh.pallipadi@intel.com> wrote:
> >
> > I don't seem to be able to reproduce this failure on my test systems..
> > What distribution are you using here? Can you send me the kernel config that you used.
> 
> I'm using Gentoo, the compiler is:
> gcc (Gentoo 4.3.2-r2 p1.5, pie-10.1.5) 4.3.2
> 
> The system has 2x 2218 Opterons with 4GB of RAM, so it a NUMA system
> with 2 nodes.
> What might be important is, that I switched to the new TREE_RCU:
> # CONFIG_CLASSIC_RCU is not set
> CONFIG_TREE_RCU=y
> # CONFIG_PREEMPT_RCU is not set
> # CONFIG_RCU_TRACE is not set
> CONFIG_RCU_FANOUT=4
> # CONFIG_RCU_FANOUT_EXACT is not set
> # CONFIG_TREE_RCU_TRACE is not set
> # CONFIG_PREEMPT_RCU_TRACE is not set
> 
> Rest of the .config is attached. I used the same .config for the
> vanilla 2.6.29-rc1 that worked apart from the DRM trouble that was
> also reported by others and the version patched with these fixes.
> 

I will try with this config. Meanwhile can you try the single patch below
over 2.6.29-rc1 and see whether you still see the failure. This patch
is fixing the DRM issue that you had seen and does not include other fixes
cleaups that were in the patch series. If you still see the failure, can yo
usend me the full boot log from the crash.

Thanks,
Venki

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>

---
 arch/x86/mm/pat.c |   50 ++++++++++++++++++++++++++++++++++----------------
 mm/memory.c       |   15 +++++++++++----
 2 files changed, 45 insertions(+), 20 deletions(-)

Index: linux-2.6/arch/x86/mm/pat.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/pat.c	2009-01-12 10:45:03.000000000 -0800
+++ linux-2.6/arch/x86/mm/pat.c	2009-01-12 11:06:43.000000000 -0800
@@ -601,12 +601,13 @@ void unmap_devmem(unsigned long pfn, uns
  * Reserved non RAM regions only and after successful reserve_memtype,
  * this func also keeps identity mapping (if any) in sync with this new prot.
  */
-static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t vma_prot)
+static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
+				int strict_prot)
 {
 	int is_ram = 0;
 	int id_sz, ret;
 	unsigned long flags;
-	unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
+	unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
 
 	is_ram = pagerange_is_ram(paddr, paddr + size);
 
@@ -625,15 +626,29 @@ static int reserve_pfn_range(u64 paddr, 
 		return ret;
 
 	if (flags != want_flags) {
-		free_memtype(paddr, paddr + size);
-		printk(KERN_ERR
-		"%s:%d map pfn expected mapping type %s for %Lx-%Lx, got %s\n",
-			current->comm, current->pid,
-			cattr_name(want_flags),
-			(unsigned long long)paddr,
-			(unsigned long long)(paddr + size),
-			cattr_name(flags));
-		return -EINVAL;
+		if (strict_prot ||
+		    (want_flags == _PAGE_CACHE_UC_MINUS &&
+		     flags == _PAGE_CACHE_WB) ||
+		    (want_flags == _PAGE_CACHE_WC &&
+		     flags == _PAGE_CACHE_WB)) {
+			free_memtype(paddr, paddr + size);
+			printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
+				" for %Lx-%Lx, got %s\n",
+				current->comm, current->pid,
+				cattr_name(want_flags),
+				(unsigned long long)paddr,
+				(unsigned long long)(paddr + size),
+				cattr_name(flags));
+			return -EINVAL;
+		}
+		/*
+		 * We allow returning different type than the one requested in
+		 * non strict case.
+		 */
+		*vma_prot = __pgprot((pgprot_val(*vma_prot) &
+				      (~_PAGE_CACHE_MASK)) |
+				     flags);
+
 	}
 
 	/* Need to keep identity mapping in sync */
@@ -689,6 +704,7 @@ int track_pfn_vma_copy(struct vm_area_st
 	unsigned long vma_start = vma->vm_start;
 	unsigned long vma_end = vma->vm_end;
 	unsigned long vma_size = vma_end - vma_start;
+	pgprot_t pgprot;
 
 	if (!pat_enabled)
 		return 0;
@@ -702,7 +718,8 @@ int track_pfn_vma_copy(struct vm_area_st
 			WARN_ON_ONCE(1);
 			return -EINVAL;
 		}
-		return reserve_pfn_range(paddr, vma_size, __pgprot(prot));
+		pgprot = __pgprot(prot);
+		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
 	}
 
 	/* reserve entire vma page by page, using pfn and prot from pte */
@@ -710,7 +727,8 @@ int track_pfn_vma_copy(struct vm_area_st
 		if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
 			continue;
 
-		retval = reserve_pfn_range(paddr, PAGE_SIZE, __pgprot(prot));
+		pgprot = __pgprot(prot);
+		retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1);
 		if (retval)
 			goto cleanup_ret;
 	}
@@ -741,7 +759,7 @@ cleanup_ret:
  * Note that this function can be called with caller trying to map only a
  * subrange/page inside the vma.
  */
-int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
 			unsigned long pfn, unsigned long size)
 {
 	int retval = 0;
@@ -758,14 +776,14 @@ int track_pfn_vma_new(struct vm_area_str
 	if (is_linear_pfn_mapping(vma)) {
 		/* reserve the whole chunk starting from vm_pgoff */
 		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
-		return reserve_pfn_range(paddr, vma_size, prot);
+		return reserve_pfn_range(paddr, vma_size, prot, 0);
 	}
 
 	/* reserve page by page using pfn and size */
 	base_paddr = (resource_size_t)pfn << PAGE_SHIFT;
 	for (i = 0; i < size; i += PAGE_SIZE) {
 		paddr = base_paddr + i;
-		retval = reserve_pfn_range(paddr, PAGE_SIZE, prot);
+		retval = reserve_pfn_range(paddr, PAGE_SIZE, prot, 0);
 		if (retval)
 			goto cleanup_ret;
 	}
Index: linux-2.6/mm/memory.c
===================================================================
--- linux-2.6.orig/mm/memory.c	2009-01-12 10:45:03.000000000 -0800
+++ linux-2.6/mm/memory.c	2009-01-12 10:59:30.000000000 -0800
@@ -1511,6 +1511,7 @@ int vm_insert_pfn(struct vm_area_struct 
 			unsigned long pfn)
 {
 	int ret;
+	pgprot_t pgprot = vma->vm_page_prot;
 	/*
 	 * Technically, architectures with pte_special can avoid all these
 	 * restrictions (same for remap_pfn_range).  However we would like
@@ -1525,10 +1526,10 @@ int vm_insert_pfn(struct vm_area_struct 
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
-	if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE))
+	if (track_pfn_vma_new(vma, &pgprot, pfn, PAGE_SIZE))
 		return -EINVAL;
 
-	ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+	ret = insert_pfn(vma, addr, pfn, pgprot);
 
 	if (ret)
 		untrack_pfn_vma(vma, pfn, PAGE_SIZE);
@@ -1671,9 +1672,15 @@ int remap_pfn_range(struct vm_area_struc
 
 	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
 
-	err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size));
-	if (err)
+	err = track_pfn_vma_new(vma, &prot, pfn, PAGE_ALIGN(size));
+	if (err) {
+		/*
+		 * To indicate that track_pfn related cleanup is not
+		 * needed from higher level routine calling unmap_vmas
+		 */
+		vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP);
 		return -EINVAL;
+	}
 
 	BUG_ON(addr >= end);
 	pfn -= addr >> PAGE_SHIFT;