Skip to contentSkip to conversation

mm: Define pte_index as macro for x86

PATCH In review Arjun Roy 3 participants 4 messages Feb 28, 2020

Subsystems (3)
lore
Share & tools
lore

Arjun Roy

author
#0 lore raw

PATCH v3 1/2 mm: Define pte_index as macro for x86

From: Arjun Roy <[email protected]>

pte_index() is either defined as a macro (e.g. sparc64) or as an inlined function (e.g. x86). vm_insert_pages() depends on pte_index but it is not defined on all platforms (e.g. m68k).

To fix compilation of vm_insert_pages() on architectures not providing pte_index(), we perform the following fix:

0. For platforms where it is meaningful, and defined as a macro, no change is needed.
1. For platforms where it is meaningful and defined as an inlined function, and we want to use it with vm_insert_pages(), we define a degenerate macro of the form: #define pte_index pte_index
2. vm_insert_pages() checks for the existence of a pte_index macro definition. If found, it implements a batched insert. If not found, it devolves to calling vm_insert_page() in a loop.

This patch implements step 1 for x86.

v3 of this patch fixes a compilation warning for an unused method. v2 of this patch moved a macro definition to a more readable location.

---
 arch/x86/include/asm/pgtable.h | 3 +++
 1 file changed, 3 insertions(+)
arch/x86/include/asm/pgtable.h +3 -0
index 7e118660bbd9..d9925b10e326 100644
@@ -828,7 +828,10 @@ static inline unsigned long pmd_index(unsigned long address)
  *
  * this function returns the index of the entry in the pte page which would
  * control the given virtual address
+ *
+ * Also define macro so we can test if pte_index is defined for arch.
  */
+#define pte_index pte_index
 static inline unsigned long pte_index(unsigned long address)
 {
 	return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
Signature · 1 line
2.25.1.481.gfbce0eb801-goog
author
#1 lore raw

PATCH v3 2/2 mm: vm_insert_pages() checks if pte_index defined.

From: Arjun Roy <[email protected]>

pte_index() is either defined as a macro (e.g. sparc64) or as an inlined function (e.g. x86). vm_insert_pages() depends on pte_index but it is not defined on all platforms (e.g. m68k).

To fix compilation of vm_insert_pages() on architectures not providing pte_index(), we perform the following fix:

0. For platforms where it is meaningful, and defined as a macro, no change is needed.
1. For platforms where it is meaningful and defined as an inlined function, and we want to use it with vm_insert_pages(), we define a degenerate macro of the form: #define pte_index pte_index
2. vm_insert_pages() checks for the existence of a pte_index macro definition. If found, it implements a batched insert. If not found, it devolves to calling vm_insert_page() in a loop.

This patch implements step 2.

v3 of this patch fixes a compilation warning for an unused method. v2 of this patch moved a macro definition to a more readable location.

---
 mm/memory.c | 41 ++++++++++++++++++++++++++++-------------
 1 file changed, 28 insertions(+), 13 deletions(-)
mm/memory.c +28 -13
index d6f834f7d145..47b28fcc73c2 100644
@@ -1460,18 +1460,6 @@ static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte,
 	return 0;
 }
 
-static int insert_page_in_batch_locked(struct mm_struct *mm, pmd_t *pmd,
-			unsigned long addr, struct page *page, pgprot_t prot)
-{
-	int err;
-
-	if (!page_count(page))
-		return -EINVAL;
-	err = validate_page_before_insert(page);
-	return err ? err : insert_page_into_pte_locked(
-		mm, pte_offset_map(pmd, addr), addr, page, prot);
-}
-
 /*
  * This is the old fallback for page remapping.
  *
@@ -1500,8 +1488,21 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
 	return retval;
 }
 
+#ifdef pte_index
+static int insert_page_in_batch_locked(struct mm_struct *mm, pmd_t *pmd,
+			unsigned long addr, struct page *page, pgprot_t prot)
+{
+	int err;
+
+	if (!page_count(page))
+		return -EINVAL;
+	err = validate_page_before_insert(page);
+	return err ? err : insert_page_into_pte_locked(
+		mm, pte_offset_map(pmd, addr), addr, page, prot);
+}
+
 /* insert_pages() amortizes the cost of spinlock operations
- * when inserting pages in a loop.
+ * when inserting pages in a loop. Arch *must* define pte_index.
  */
 static int insert_pages(struct vm_area_struct *vma, unsigned long addr,
 			struct page **pages, unsigned long *num, pgprot_t prot)
@@ -1556,6 +1557,7 @@ static int insert_pages(struct vm_area_struct *vma, unsigned long addr,
 	*num = remaining_pages_total;
 	return ret;
 }
+#endif  /* ifdef pte_index */
 
 /**
  * vm_insert_pages - insert multiple pages into user vma, batching the pmd lock.
@@ -1575,6 +1577,7 @@ static int insert_pages(struct vm_area_struct *vma, unsigned long addr,
 int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
 			struct page **pages, unsigned long *num)
 {
+#ifdef pte_index
 	const unsigned long end_addr = addr + (*num * PAGE_SIZE) - 1;
 
 	if (addr < vma->vm_start || end_addr >= vma->vm_end)
@@ -1586,6 +1589,18 @@ int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
 	}
 	/* Defer page refcount checking till we're about to map that page. */
 	return insert_pages(vma, addr, pages, num, vma->vm_page_prot);
+#else
+	unsigned long idx = 0, pgcount = *num;
+	int err;
+
+	for (; idx < pgcount; ++idx) {
+		err = vm_insert_page(vma, addr + (PAGE_SIZE * idx), pages[idx]);
+		if (err)
+			break;
+	}
+	*num = pgcount - idx;
+	return err;
+#endif  /* ifdef pte_index */
 }
 EXPORT_SYMBOL(vm_insert_pages);
 
Signature · 1 line
2.25.1.481.gfbce0eb801-goog
#2 lore raw

Re: [PATCH v3 mm 2/2] mm: vm_insert_pages() checks if pte_index defined.

Quoted 23 lines · Arjun Roy
mm/memory.c +1 -12
index d6f834f7d145..47b28fcc73c2 100644
+++ b/mm/memory.c
@@ -1460,18 +1460,6 @@ static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte,
 	return 0;
 }
 
-static int insert_page_in_batch_locked(struct mm_struct *mm, pmd_t *pmd,
-			unsigned long addr, struct page *page, pgprot_t prot)
-{
-	int err;
-
-	if (!page_count(page))
-		return -EINVAL;
-	err = validate_page_before_insert(page);
-	return err ? err : insert_page_into_pte_locked(
-		mm, pte_offset_map(pmd, addr), addr, page, prot);
-}
-
 /*
  * This is the old fallback for page remapping.
  *

mm/memory.c static int insert_page(struct vm_area_struct *vma, unsigned long addr, · line 1491

Quoted 4 lines
mm/memory.c +1 -0
@@ -1500,8 +1488,21 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
 	return retval;
 }
 
+#ifdef pte_index

It seems a bit weird like this, don't we usually do this kind of stuff with some CONFIG_ARCH_HAS_XX thing?

IMHO all arches should implement pte_index as the static inline, that has been the general direction lately.

Jason

#3 lore raw

Re: [PATCH v3 mm 2/2] mm: vm_insert_pages() checks if pte_index defined.

Quoted 28 lines · Jason Gunthorpe
Quoted 26 lines · Arjun Roy
mm/memory.c +1 -12
index d6f834f7d145..47b28fcc73c2 100644
+++ b/mm/memory.c
@@ -1460,18 +1460,6 @@ static int insert_page_into_pte_locked(struct mm_struct *mm, pte_t *pte,
      return 0;
 }
 
-static int insert_page_in_batch_locked(struct mm_struct *mm, pmd_t *pmd,
-                     unsigned long addr, struct page *page, pgprot_t prot)
-{
-     int err;
-
-     if (!page_count(page))
-             return -EINVAL;
-     err = validate_page_before_insert(page);
-     return err ? err : insert_page_into_pte_locked(
-             mm, pte_offset_map(pmd, addr), addr, page, prot);
-}
-
 /*
  * This is the old fallback for page remapping.
  *
@@ -1500,8 +1488,21 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
      return retval;
 }
 
Quoted 7 lines

mm/memory.c static int insert_page(struct vm_area_struct *vma, unsigned long addr, · line 1491

Quoted 1 line
mm/memory.c +1 -0
+#ifdef pte_index

It seems a bit weird like this, don't we usually do this kind of stuff with some CONFIG_ARCH_HAS_XX thing?

IMHO all arches should implement pte_index as the static inline, that has been the general direction lately.

Based on a comment from Stephen Rothwell, we found out that "static inline" functions are only used in tile and x86. That's why Arjun opted for this method to create a smaller patch-series to fix the build breakage.

Thanks,
Soheil

Quoted 1 line

Jason