[patch 090/100] x86, PAT: Remove page granularity tracking for vm_insert_pfn maps

[Chris Wright]

-stable review patch.  If anyone has any objections, please let us know.
---------------------

From: Venkatesh Pallipadi <venkatesh.pallipadi@xxxxxxxxx>

upstream commit: 4b065046273afa01ec8e3de7da407e8d3599251d

This change resolves the problem of too many single page entries
in pat_memtype_list and "freeing invalid memtype" errors with i915,
reported here:

  http://marc.info/?l=linux-kernel&m=123845244713183&w=2

Remove page level granularity track and untrack of vm_insert_pfn.
memtype tracking at page granularity does not scale and cleaner
approach would be for the driver to request a type for a bigger
IO address range or PCI io memory range for that device, either at
mmap time or driver init time and just use that type during
vm_insert_pfn.

This patch just removes the track/untrack of vm_insert_pfn. That
means we will be in same state as 2.6.28, with respect to these APIs.

Newer APIs for the drivers to request a memtype for a bigger region
is coming soon.

[ Impact: fix Xorg startup warnings and hangs ]

Reported-by: Arkadiusz Miskiewicz <a.miskiewicz@xxxxxxxxx>
Tested-by: Arkadiusz Miskiewicz <a.miskiewicz@xxxxxxxxx>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@xxxxxxxxx>
Signed-off-by: Suresh Siddha <suresh.b.siddha@xxxxxxxxx>
Cc: Jesse Barnes <jbarnes@xxxxxxxxxxxxxxxx>
LKML-Reference: <20090408223716.GC3493@xxxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Chris Wright <chrisw@xxxxxxxxxxxx>
---
 arch/x86/mm/pat.c |   98 ++++++++++--------------------------------------------
 1 file changed, 19 insertions(+), 79 deletions(-)

--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -713,29 +713,28 @@ static void free_pfn_range(u64 paddr, un
  *
  * If the vma has a linear pfn mapping for the entire range, we get the prot
  * from pte and reserve the entire vma range with single reserve_pfn_range call.
- * Otherwise, we reserve the entire vma range, my ging through the PTEs page
- * by page to get physical address and protection.
  */
 int track_pfn_vma_copy(struct vm_area_struct *vma)
 {
-	int retval = 0;
-	unsigned long i, j;
 	resource_size_t paddr;
 	unsigned long prot;
-	unsigned long vma_start = vma->vm_start;
-	unsigned long vma_end = vma->vm_end;
-	unsigned long vma_size = vma_end - vma_start;
+	unsigned long vma_size = vma->vm_end - vma->vm_start;
 	pgprot_t pgprot;
 
 	if (!pat_enabled)
 		return 0;
 
+	/*
+	 * For now, only handle remap_pfn_range() vmas where
+	 * is_linear_pfn_mapping() == TRUE. Handling of
+	 * vm_insert_pfn() is TBD.
+	 */
 	if (is_linear_pfn_mapping(vma)) {
 		/*
 		 * reserve the whole chunk covered by vma. We need the
 		 * starting address and protection from pte.
 		 */
-		if (follow_phys(vma, vma_start, 0, &prot, &paddr)) {
+		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
 			WARN_ON_ONCE(1);
 			return -EINVAL;
 		}
@@ -743,28 +742,7 @@ int track_pfn_vma_copy(struct vm_area_st
 		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
 	}
 
-	/* reserve entire vma page by page, using pfn and prot from pte */
-	for (i = 0; i < vma_size; i += PAGE_SIZE) {
-		if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
-			continue;
-
-		pgprot = __pgprot(prot);
-		retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1);
-		if (retval)
-			goto cleanup_ret;
-	}
 	return 0;
-
-cleanup_ret:
-	/* Reserve error: Cleanup partial reservation and return error */
-	for (j = 0; j < i; j += PAGE_SIZE) {
-		if (follow_phys(vma, vma_start + j, 0, &prot, &paddr))
-			continue;
-
-		free_pfn_range(paddr, PAGE_SIZE);
-	}
-
-	return retval;
 }
 
 /*
@@ -774,50 +752,28 @@ cleanup_ret:
  * prot is passed in as a parameter for the new mapping. If the vma has a
  * linear pfn mapping for the entire range reserve the entire vma range with
  * single reserve_pfn_range call.
- * Otherwise, we look t the pfn and size and reserve only the specified range
- * page by page.
- *
- * 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,
 			unsigned long pfn, unsigned long size)
 {
-	int retval = 0;
-	unsigned long i, j;
-	resource_size_t base_paddr;
 	resource_size_t paddr;
-	unsigned long vma_start = vma->vm_start;
-	unsigned long vma_end = vma->vm_end;
-	unsigned long vma_size = vma_end - vma_start;
+	unsigned long vma_size = vma->vm_end - vma->vm_start;
 
 	if (!pat_enabled)
 		return 0;
 
+	/*
+	 * For now, only handle remap_pfn_range() vmas where
+	 * is_linear_pfn_mapping() == TRUE. Handling of
+	 * vm_insert_pfn() is TBD.
+	 */
 	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, 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, 0);
-		if (retval)
-			goto cleanup_ret;
-	}
 	return 0;
-
-cleanup_ret:
-	/* Reserve error: Cleanup partial reservation and return error */
-	for (j = 0; j < i; j += PAGE_SIZE) {
-		paddr = base_paddr + j;
-		free_pfn_range(paddr, PAGE_SIZE);
-	}
-
-	return retval;
 }
 
 /*
@@ -828,39 +784,23 @@ cleanup_ret:
 void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
 			unsigned long size)
 {
-	unsigned long i;
 	resource_size_t paddr;
-	unsigned long prot;
-	unsigned long vma_start = vma->vm_start;
-	unsigned long vma_end = vma->vm_end;
-	unsigned long vma_size = vma_end - vma_start;
+	unsigned long vma_size = vma->vm_end - vma->vm_start;
 
 	if (!pat_enabled)
 		return;
 
+	/*
+	 * For now, only handle remap_pfn_range() vmas where
+	 * is_linear_pfn_mapping() == TRUE. Handling of
+	 * vm_insert_pfn() is TBD.
+	 */
 	if (is_linear_pfn_mapping(vma)) {
 		/* free the whole chunk starting from vm_pgoff */
 		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
 		free_pfn_range(paddr, vma_size);
 		return;
 	}
-
-	if (size != 0 && size != vma_size) {
-		/* free page by page, using pfn and size */
-		paddr = (resource_size_t)pfn << PAGE_SHIFT;
-		for (i = 0; i < size; i += PAGE_SIZE) {
-			paddr = paddr + i;
-			free_pfn_range(paddr, PAGE_SIZE);
-		}
-	} else {
-		/* free entire vma, page by page, using the pfn from pte */
-		for (i = 0; i < vma_size; i += PAGE_SIZE) {
-			if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
-				continue;
-
-			free_pfn_range(paddr, PAGE_SIZE);
-		}
-	}
 }
 
 pgprot_t pgprot_writecombine(pgprot_t prot)

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/