powerpc: Free up four 64K PTE bits in 4K backed HPTE pages

Rearrange 64K PTE bits to free up bits 3, 4, 5 and 6,
in the 4K backed HPTE pages.These bits continue to be used
for 64K backed HPTE pages in this patch, but will be freed
up in the next patch. The bit numbers are big-endian as
defined in the ISA3.0

The patch does the following change to the 4k HTPE backed
64K PTE's format.

H_PAGE_BUSY moves from bit 3 to bit 9 (B bit in the figure
		below)
V0 which occupied bit 4 is not used anymore.
V1 which occupied bit 5 is not used anymore.
V2 which occupied bit 6 is not used anymore.
V3 which occupied bit 7 is not used anymore.

Before the patch, the 4k backed 64k PTE format was as follows

 0 1 2 3 4  5  6  7  8 9 10...........................63
 : : : : :  :  :  :  : : :                            :
 v v v v v  v  v  v  v v v                            v

,-,-,-,-,--,--,--,--,-,-,-,-,-,------------------,-,-,-,
|x|x|x|B|V0|V1|V2|V3|x| | |x|x|................|x|x|x|x| <- primary pte
'_'_'_'_'__'__'__'__'_'_'_'_'_'________________'_'_'_'_'
|S|G|I|X|S |G |I |X |S|G|I|X|..................|S|G|I|X| <- secondary pte
'_'_'_'_'__'__'__'__'_'_'_'_'__________________'_'_'_'_'

After the patch, the 4k backed 64k PTE format is as follows

 0 1 2 3 4  5  6  7  8 9 10...........................63
 : : : : :  :  :  :  : : :                            :
 v v v v v  v  v  v  v v v                            v

,-,-,-,-,--,--,--,--,-,-,-,-,-,------------------,-,-,-,
|x|x|x| |  |  |  |  |x|B| |x|x|................|.|.|.|.| <- primary pte
'_'_'_'_'__'__'__'__'_'_'_'_'_'________________'_'_'_'_'
|S|G|I|X|S |G |I |X |S|G|I|X|..................|S|G|I|X| <- secondary pte
'_'_'_'_'__'__'__'__'_'_'_'_'__________________'_'_'_'_'

the four bits S,G,I,X (one quadruplet per 4k HPTE) that
cache the hash-bucket slot value, is initialized to
1,1,1,1 indicating -- an invalid slot. If a HPTE gets
cached in a 1111 slot(i.e 7th slot of secondary hash
bucket), it is released immediately. In other words,
even though 1111 is a valid slot value in the hash
bucket, we consider it invalid and release the slot and
the HPTE. This gives us the opportunity to determine
the validity of S,G,I,X bits based on its contents and
not on any of the bits V0,V1,V2 or V3 in the primary PTE

When we release a HPTE cached in the 1111 slot
we also release a legitimate slot in the primary
hash bucket and unmap its corresponding HPTE. This
is to ensure that we do get a HPTE cached in a slot
of the primary hash bucket, the next time we retry.

Though treating 1111 slot as invalid, reduces the
number of available slots in the hash bucket and may
have an effect on the performance, the probabilty of
hitting a 1111 slot is extermely low.

Compared to the current scheme, the above scheme
reduces the number of false hash table updates
significantly and has the added advantage of releasing
four valuable PTE bits for other purpose.

NOTE:even though bits 3, 4, 5, 6, 7 are not used when
the 64K PTE is backed by 4k HPTE, they continue to be
used if the PTE gets backed by 64k HPTE. The next
patch will decouple that aswell, and truely release the
bits.

This idea was jointly developed by Paul Mackerras,
Aneesh, Michael Ellermen and myself.

4K PTE format remains unchanged currently.

The patch does the following code changes
a) PTE flags are split between 64k and 4k header files.
b) __hash_page_4K() is reimplemented to reflect the
 above logic.

Acked-by: Balbir Singh <bsingharora@gmail.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

3 files changed, 5 insertions, 7 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 2975fc172d1a..e0130c34766e 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -17,6 +17,8 @@
 #define H_PUD_TABLE_SIZE	(sizeof(pud_t) << H_PUD_INDEX_SIZE)
 #define H_PGD_TABLE_SIZE	(sizeof(pgd_t) << H_PGD_INDEX_SIZE)
 
+#define H_PAGE_BUSY	_RPAGE_RSV1     /* software: PTE & hash are busy */
+
 /* PTE flags to conserve for HPTE identification */
 #define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | \
 			 H_PAGE_F_SECOND | H_PAGE_F_GIX)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index c1bd258b7303..c929e6437a60 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -13,18 +13,14 @@
  */
 #define H_PAGE_COMBO	_RPAGE_RPN0 /* this is a combo 4k page */
 #define H_PAGE_4K_PFN	_RPAGE_RPN1 /* PFN is for a single 4k page */
+#define H_PAGE_BUSY	_RPAGE_RPN42     /* software: PTE & hash are busy */
+
 /*
  * We need to differentiate between explicit huge page and THP huge
  * page, since THP huge page also need to track real subpage details
  */
 #define H_PAGE_THP_HUGE  H_PAGE_4K_PFN
 
-/*
- * Used to track subpage group valid if H_PAGE_COMBO is set
- * This overloads H_PAGE_F_GIX and H_PAGE_F_SECOND
- */
-#define H_PAGE_COMBO_VALID	(H_PAGE_F_GIX | H_PAGE_F_SECOND)
-
 /* PTE flags to conserve for HPTE identification */
 #define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_F_SECOND | \
 			 H_PAGE_F_GIX | H_PAGE_HASHPTE | H_PAGE_COMBO)
@@ -69,6 +65,7 @@ static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
 }
 
 #define HIDX_BITS(x, index)  (x << (index << 2))
+#define INVALID_RPTE_HIDX  ~(0x0UL)
 
 static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
 {
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 9099c1f3a54e..4e19a612a963 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -10,7 +10,6 @@
  */
 #define H_PTE_NONE_MASK		_PAGE_HPTEFLAGS
 #define H_PAGE_F_GIX_SHIFT	56
-#define H_PAGE_BUSY		_RPAGE_RSV1 /* software: PTE & hash are busy */
 #define H_PAGE_F_SECOND		_RPAGE_RSV2	/* HPTE is in 2ndary HPTEG */
 #define H_PAGE_F_GIX		(_RPAGE_RSV3 | _RPAGE_RSV4 | _RPAGE_RPN44)
 #define H_PAGE_HASHPTE		_RPAGE_RPN43	/* PTE has associated HPTE */