powerpc/mm/radix: Update pte fragment count from 16 to 256 on radix

With split PTL (page table lock) config, we allocate the level
4 (leaf) page table using pte fragment framework instead of slab cache
like other levels. This was done to enable us to have split page table
lock at the level 4 of the page table. We use page->plt backing the
all the level 4 pte fragment for the lock.

Currently with Radix, we use only 16 fragments out of the allocated
page. In radix each fragment is 256 bytes which means we use only 4k
out of the allocated 64K page wasting 60k of the allocated memory.
This was done earlier to keep it closer to hash.

This patch update the pte fragment count to 256, thereby using the
full 64K page and reducing the memory usage. Performance tests shows
really low impact even with THP disabled. With THP disabled we will be
contenting further less on level 4 ptl and hence the impact should be
further low.

  256 threads:
    without patch (10 runs of ./ebizzy  -m -n 1000 -s 131072 -S 100)
      median = 15678.5
      stdev = 42.1209

    with patch:
      median = 15354
      stdev = 194.743

This is with THP disabled. With THP enabled the impact of the patch
will be less.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

4 files changed, 17 insertions, 12 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index eb39313..cc82745 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -38,15 +38,13 @@
 /* PTE flags to conserve for HPTE identification */
 #define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | H_PAGE_COMBO)
 /*
- * we support 16 fragments per PTE page of 64K size.
- */
-#define H_PTE_FRAG_NR	16
-/*
  * We use a 2K PTE page fragment and another 2K for storing
  * real_pte_t hash index
+ * 8 bytes per each pte entry and another 8 bytes for storing
+ * slot details.
  */
-#define H_PTE_FRAG_SIZE_SHIFT  12
-#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT)
+#define H_PTE_FRAG_SIZE_SHIFT  (H_PTE_INDEX_SIZE + 3 + 1)
+#define H_PTE_FRAG_NR	(PAGE_SIZE >> H_PTE_FRAG_SIZE_SHIFT)
 
 #ifndef __ASSEMBLY__
 #include <asm/errno.h>
diff --git a/arch/powerpc/include/asm/book3s/64/radix-4k.h b/arch/powerpc/include/asm/book3s/64/radix-4k.h
index a61aa9c..ca366ec 100644
--- a/arch/powerpc/include/asm/book3s/64/radix-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/radix-4k.h
@@ -9,5 +9,10 @@
 #define RADIX_PMD_INDEX_SIZE  9  /* 1G huge page */
 #define RADIX_PUD_INDEX_SIZE	 9
 #define RADIX_PGD_INDEX_SIZE  13
+/*
+ * One fragment per per page
+ */
+#define RADIX_PTE_FRAG_SIZE_SHIFT  (RADIX_PTE_INDEX_SIZE + 3)
+#define RADIX_PTE_FRAG_NR	(PAGE_SIZE >> RADIX_PTE_FRAG_SIZE_SHIFT)
 
 #endif /* _ASM_POWERPC_PGTABLE_RADIX_4K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/radix-64k.h b/arch/powerpc/include/asm/book3s/64/radix-64k.h
index c7e71ba..8300824 100644
--- a/arch/powerpc/include/asm/book3s/64/radix-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/radix-64k.h
@@ -10,4 +10,10 @@
 #define RADIX_PUD_INDEX_SIZE	 9
 #define RADIX_PGD_INDEX_SIZE  13
 
+/*
+ * We use a 256 byte PTE page fragment in radix
+ * 8 bytes per each PTE entry.
+ */
+#define RADIX_PTE_FRAG_SIZE_SHIFT  (RADIX_PTE_INDEX_SIZE + 3)
+#define RADIX_PTE_FRAG_NR	(PAGE_SIZE >> RADIX_PTE_FRAG_SIZE_SHIFT)
 #endif /* _ASM_POWERPC_PGTABLE_RADIX_64K_H */
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 7095384..f1891e2 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -638,12 +638,8 @@ void __init radix__early_init_mmu(void)
 #ifdef CONFIG_PCI
 	pci_io_base = ISA_IO_BASE;
 #endif
-
-	/*
-	 * For now radix also use the same frag size
-	 */
-	__pte_frag_nr = H_PTE_FRAG_NR;
-	__pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT;
+	__pte_frag_nr = RADIX_PTE_FRAG_NR;
+	__pte_frag_size_shift = RADIX_PTE_FRAG_SIZE_SHIFT;
 
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 		radix_init_native();