Patchwork [-V7,01/10] powerpc/THP: Double the PMD table size for THP

login
register
mail settings
Submitter Aneesh Kumar K.V
Date April 28, 2013, 7:51 p.m.
Message ID <1367178711-8232-2-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
Download mbox | patch
Permalink /patch/240295/
State Superseded
Headers show

Comments

Aneesh Kumar K.V - April 28, 2013, 7:51 p.m.
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>

THP code does PTE page allocation along with large page request and deposit them
for later use. This is to ensure that we won't have any failures when we split
hugepages to regular pages.

On powerpc we want to use the deposited PTE page for storing hash pte slot and
secondary bit information for the HPTEs. We use the second half
of the pmd table to save the deposted PTE page.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/pgalloc-64.h    | 6 +++---
 arch/powerpc/include/asm/pgtable-ppc64.h | 6 +++++-
 arch/powerpc/mm/init_64.c                | 9 ++++++---
 3 files changed, 14 insertions(+), 7 deletions(-)
David Gibson - May 3, 2013, 3:21 a.m.
On Mon, Apr 29, 2013 at 01:21:42AM +0530, Aneesh Kumar K.V wrote:
> From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
> 
> THP code does PTE page allocation along with large page request and deposit them
> for later use. This is to ensure that we won't have any failures when we split
> hugepages to regular pages.
> 
> On powerpc we want to use the deposited PTE page for storing hash pte slot and
> secondary bit information for the HPTEs. We use the second half
> of the pmd table to save the deposted PTE page.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

So far so good.

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>

Patch

diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 91acb12..c756463 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -221,17 +221,17 @@  static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
+	return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
 				GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
+	kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd);
 }
 
 #define __pmd_free_tlb(tlb, pmd, addr)		      \
-	pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
+	pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX)
 #ifndef CONFIG_PPC_64K_PAGES
 #define __pud_free_tlb(tlb, pud, addr)		      \
 	pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index e3d55f6f..ab84332 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -20,7 +20,11 @@ 
                 	    PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
 #define PGTABLE_RANGE (ASM_CONST(1) << PGTABLE_EADDR_SIZE)
 
-
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define PMD_CACHE_INDEX	(PMD_INDEX_SIZE + 1)
+#else
+#define PMD_CACHE_INDEX	PMD_INDEX_SIZE
+#endif
 /*
  * Define the address range of the kernel non-linear virtual area
  */
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index a56de85..97f741d 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -88,7 +88,11 @@  static void pgd_ctor(void *addr)
 
 static void pmd_ctor(void *addr)
 {
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	memset(addr, 0, PMD_TABLE_SIZE * 2);
+#else
 	memset(addr, 0, PMD_TABLE_SIZE);
+#endif
 }
 
 struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
@@ -137,10 +141,9 @@  void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
 void pgtable_cache_init(void)
 {
 	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
-	pgtable_cache_add(PMD_INDEX_SIZE, pmd_ctor);
-	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_INDEX_SIZE))
+	pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
+	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_CACHE_INDEX))
 		panic("Couldn't allocate pgtable caches");
-
 	/* In all current configs, when the PUD index exists it's the
 	 * same size as either the pgd or pmd index.  Verify that the
 	 * initialization above has also created a PUD cache.  This