powerpc/mm: Don't track subpage valid bit in pte_t

This free up 11 bits in pte_t. In the later patch we also change
the pte_t format so that we can start supporting migration pte
at pmd level. We now track 4k subpage valid bit as below

If we have _PAGE_COMBO set, we override the _PAGE_F_GIX_SHIFT
and _PAGE_F_SECOND. Together we have 4 bits, each of them
used to indicate whether any of the 4 4k subpage in that group
is valid. ie,

[ group 1 bit ]   [ group 2 bit ]  ..... [ group 4 ]
[ subpage 1 - 4]  [ subpage 5- 8]  ..... [ subpage 13 - 16]

We still track each 4k subpage slot number and secondary hash
information in the second half of pgtable_t. Removing the subpage
tracking have some significant overhead on aim9 and ebizzy benchmark and
to support THP with 4K subpage, we do need a pgtable_t of 4096 bytes.

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

1 files changed, 32 insertions, 2 deletions

diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c
index 9ffeae2cbb57..f1b86ba63430 100644
--- a/arch/powerpc/mm/hash64_64k.c
+++ b/arch/powerpc/mm/hash64_64k.c
@@ -15,6 +15,35 @@
 #include <linux/mm.h>
 #include <asm/machdep.h>
 #include <asm/mmu.h>
+/*
+ * index from 0 - 15
+ */
+bool __rpte_sub_valid(real_pte_t rpte, unsigned long index)
+{
+	unsigned long g_idx;
+	unsigned long ptev = pte_val(rpte.pte);
+
+	g_idx = (ptev & _PAGE_COMBO_VALID) >> _PAGE_F_GIX_SHIFT;
+	index = index >> 2;
+	if (g_idx & (0x1 << index))
+		return true;
+	else
+		return false;
+}
+/*
+ * index from 0 - 15
+ */
+static unsigned long mark_subptegroup_valid(unsigned long ptev, unsigned long index)
+{
+	unsigned long g_idx;
+
+	if (!(ptev & _PAGE_COMBO))
+		return ptev;
+	index = index >> 2;
+	g_idx = 0x1 << index;
+
+	return ptev | (g_idx << _PAGE_F_GIX_SHIFT);
+}
 
 int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		   pte_t *ptep, unsigned long trap, unsigned long flags,
@@ -102,7 +131,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	 */
 	if (!(old_pte & _PAGE_COMBO)) {
 		flush_hash_page(vpn, rpte, MMU_PAGE_64K, ssize, flags);
-		old_pte &= ~_PAGE_HPTE_SUB;
+		old_pte &= ~_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND;
 		goto htab_insert_hpte;
 	}
 	/*
@@ -192,7 +221,8 @@ repeat:
 	/* __real_pte use pte_val() any idea why ? FIXME!! */
 	rpte.hidx &= ~(0xfUL << (subpg_index << 2));
 	*hidxp = rpte.hidx  | (slot << (subpg_index << 2));
-	new_pte |= (_PAGE_HPTE_SUB0 >> subpg_index);
+	new_pte = mark_subptegroup_valid(new_pte, subpg_index);
+	new_pte |=  _PAGE_HASHPTE;
 	/*
 	 * check __real_pte for details on matching smp_rmb()
 	 */