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

Rearrange 64K PTE bits to free up bits 3, 4, 5 and 6
in the 64K backed HPTE pages. This along with the earlier
patch will entirely free up the four bits from 64K PTE.
The bit numbers are big-endian as defined in the ISA3.0

This patch does the following change to 64K PTE backed
by 64K HPTE.

H_PAGE_F_SECOND (S) which occupied bit 4 moves to the
	second part of the pte to bit 60.
H_PAGE_F_GIX (G,I,X) which occupied bit 5, 6 and 7 also
	moves to the second part of the pte to bit 61,
 	62, 63, 64 respectively

since bit 7 is now freed up, we move H_PAGE_BUSY (B) from
bit 9 to bit 7.

The second part of the PTE will hold
(H_PAGE_F_SECOND|H_PAGE_F_GIX) at bit 60,61,62,63.
NOTE: None of the bits in the secondary PTE were not used
by 64k-HPTE backed PTE.

Before the patch, the 64K HPTE 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| |S |G |I |X |x|B| |x|x|................|x|x|x|x| <- primary pte
'_'_'_'_'__'__'__'__'_'_'_'_'_'________________'_'_'_'_'
| | | | |  |  |  |  | | | | |..................| | | | | <- secondary pte
'_'_'_'_'__'__'__'__'_'_'_'_'__________________'_'_'_'_'

After the patch, the 64k HPTE 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| |  |  |  |B |x| | |x|x|................|.|.|.|.| <- primary pte
'_'_'_'_'__'__'__'__'_'_'_'_'_'________________'_'_'_'_'
| | | | |  |  |  |  | | | | |..................|S|G|I|X| <- secondary pte
'_'_'_'_'__'__'__'__'_'_'_'_'__________________'_'_'_'_'

The above PTE changes is applicable to hugetlbpages aswell.

The patch does the following code changes:

a) moves the H_PAGE_F_SECOND and H_PAGE_F_GIX to 4k PTE
	header since it is no more needed b the 64k PTEs.
b) abstracts out __real_pte() and __rpte_to_hidx() so the
	caller need not know the bit location of the slot.
c) moves the slot bits to the secondary pte.

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, 17 insertions, 19 deletions

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index e0130c34766e..ed0d1cd98907 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -17,6 +17,9 @@
 #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_F_GIX_SHIFT	56
+#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_BUSY	_RPAGE_RSV1     /* software: PTE & hash are busy */
 
 /* PTE flags to conserve for HPTE identification */
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index c929e6437a60..73ed988e6da5 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -13,7 +13,7 @@
  */
 #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 */
+#define H_PAGE_BUSY	_RPAGE_RPN44     /* software: PTE & hash are busy */
 
 /*
  * We need to differentiate between explicit huge page and THP huge
@@ -22,8 +22,7 @@
 #define H_PAGE_THP_HUGE  H_PAGE_4K_PFN
 
 /* 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)
+#define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | H_PAGE_COMBO)
 /*
  * we support 16 fragments per PTE page of 64K size.
  */
@@ -51,27 +50,26 @@ static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
 	unsigned long *hidxp;
 
 	rpte.pte = pte;
-	rpte.hidx = 0;
-	if (pte_val(pte) & H_PAGE_COMBO) {
-		/*
-		 * Make sure we order the hidx load against the H_PAGE_COMBO
-		 * check. The store side ordering is done in __hash_page_4K
-		 */
-		smp_rmb();
-		hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
-		rpte.hidx = *hidxp;
-	}
+
+	/*
+	 * Ensure that we do not read the hidx before we read the PTE. Because
+	 * the writer side is expected to finish writing the hidx first followed
+	 * by the PTE, by using smp_wmb(). pte_set_hash_slot() ensures that.
+	 */
+	smp_rmb();
+
+	hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
+	rpte.hidx = *hidxp;
 	return rpte;
 }
 
 #define HIDX_BITS(x, index)  (x << (index << 2))
+#define BITS_TO_HIDX(x, index)  ((x >> (index << 2)) & 0xfUL)
 #define INVALID_RPTE_HIDX  ~(0x0UL)
 
 static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
 {
-	if ((pte_val(rpte.pte) & H_PAGE_COMBO))
-		return (rpte.hidx >> (index<<2)) & 0xf;
-	return (pte_val(rpte.pte) >> H_PAGE_F_GIX_SHIFT) & 0xf;
+	return BITS_TO_HIDX(rpte.hidx, index);
 }
 
 /*
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 4e19a612a963..e72474f13936 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -9,9 +9,6 @@
  *
  */
 #define H_PTE_NONE_MASK		_PAGE_HPTEFLAGS
-#define H_PAGE_F_GIX_SHIFT	56
-#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 */
 
 #ifdef CONFIG_PPC_64K_PAGES