[PATCH v9 0/8] powerpc: Free up RPAGE_RSV bits

@@ -49,6 +49,20 @@ static inline int hash__hugepd_ok(hugepd_t hpd)
 }
 #endif
 
+/*
+ * 4K PTE format is different from 64K PTE format. Saving the hash_slot is just
+ * a matter of returning the PTE bits that need to be modified. On 64K PTE,
+ * things are a little more involved and hence needs many more parameters to
+ * accomplish the same. However we want to abstract this out from the caller by
+ * keeping the prototype consistent across the two formats.
+ */
+static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte,
+			unsigned int subpg_index, unsigned long hidx)
+{
+	return (hidx << H_PAGE_F_GIX_SHIFT) &
+		(H_PAGE_F_SECOND | H_PAGE_F_GIX);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
 static inline char *get_hpte_slot_array(pmd_t *pmdp)

@@ -68,6 +68,8 @@ static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
 	return rpte;
 }
 
+#define HIDX_BITS(x, index)  (x << (index << 2))
+
 static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
 {
 	if ((pte_val(rpte.pte) & H_PAGE_COMBO))

@@ -75,6 +77,29 @@ static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
 	return (pte_val(rpte.pte) >> H_PAGE_F_GIX_SHIFT) & 0xf;
 }
 
+/*
+ * Commit the hidx and return PTE bits that needs to be modified. The caller is
+ * expected to modify the PTE bits accordingly and commit the PTE to memory.
+ */
+static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte,
+		unsigned int subpg_index, unsigned long hidx)
+{
+	unsigned long *hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
+
+	rpte.hidx &= ~HIDX_BITS(0xfUL, subpg_index);
+	*hidxp = rpte.hidx  | HIDX_BITS(hidx, subpg_index);
+
+	/*
+	 * Anyone reading PTE must ensure hidx bits are read after reading the
+	 * PTE by using the read-side barrier smp_rmb(). __real_pte() can be
+	 * used for that.
+	 */
+	smp_wmb();
+
+	/* No PTE bits to be modified, return 0x0UL */
+	return 0x0UL;
+}
+
 #define __rpte_to_pte(r)	((r).pte)
 extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index);
 /*

@@ -167,6 +167,9 @@ static inline int hash__pte_none(pte_t pte)
 	return (pte_val(pte) & ~H_PTE_NONE_MASK) == 0;
 }
 
+unsigned long pte_get_hash_gslot(unsigned long vpn, unsigned long shift,
+		int ssize, real_pte_t rpte, unsigned int subpg_index);
+
 /* This low level function performs the actual PTE insertion
  * Setting the PTE depends on the MMU type and other factors. It's
  * an horrible mess that I'm not going to try to clean up now but

@@ -1591,6 +1591,24 @@ static inline void tm_flush_hash_page(int local)
 }
 #endif
 
+/*
+ * Return the global hash slot, corresponding to the given PTE, which contains
+ * the HPTE.
+ */
+unsigned long pte_get_hash_gslot(unsigned long vpn, unsigned long shift,
+		int ssize, real_pte_t rpte, unsigned int subpg_index)
+{
+	unsigned long hash, gslot, hidx;
+
+	hash = hpt_hash(vpn, shift, ssize);
+	hidx = __rpte_to_hidx(rpte, subpg_index);
+	if (hidx & _PTEIDX_SECONDARY)
+		hash = ~hash;
+	gslot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+	gslot += hidx & _PTEIDX_GROUP_IX;
+	return gslot;
+}
+
 /* WARNING: This is called from hash_low_64.S, if you change this prototype,
  *          do not forget to update the assembly call site !
  */

@@ -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)

@@ -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)
 {

@@ -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 */

@@ -15,34 +15,22 @@
 #include <linux/mm.h>
 #include <asm/machdep.h>
 #include <asm/mmu.h>
+
 /*
- * index from 0 - 15
+ * Return true, if the entry has a slot value which
+ * the software considers as invalid.
  */
-bool __rpte_sub_valid(real_pte_t rpte, unsigned long index)
+static inline bool hpte_soft_invalid(unsigned long hidx)
 {
-	unsigned long g_idx;
-	unsigned long ptev = pte_val(rpte.pte);
-
-	g_idx = (ptev & H_PAGE_COMBO_VALID) >> H_PAGE_F_GIX_SHIFT;
-	index = index >> 2;
-	if (g_idx & (0x1 << index))
-		return true;
-	else
-		return false;
+	return ((hidx & 0xfUL) == 0xfUL);
 }
+
 /*
  * index from 0 - 15
  */
-static unsigned long mark_subptegroup_valid(unsigned long ptev, unsigned long index)
+bool __rpte_sub_valid(real_pte_t rpte, unsigned long index)
 {
-	unsigned long g_idx;
-
-	if (!(ptev & H_PAGE_COMBO))
-		return ptev;
-	index = index >> 2;
-	g_idx = 0x1 << index;
-
-	return ptev | (g_idx << H_PAGE_F_GIX_SHIFT);
+	return !(hpte_soft_invalid(__rpte_to_hidx(rpte, index)));
 }
 
 int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,

@@ -50,12 +38,11 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		   int ssize, int subpg_prot)
 {
 	real_pte_t rpte;
-	unsigned long *hidxp;
 	unsigned long hpte_group;
 	unsigned int subpg_index;
-	unsigned long rflags, pa, hidx;
+	unsigned long rflags, pa;
 	unsigned long old_pte, new_pte, subpg_pte;
-	unsigned long vpn, hash, slot;
+	unsigned long vpn, hash, slot, gslot;
 	unsigned long shift = mmu_psize_defs[MMU_PAGE_4K].shift;
 
 	/*

@@ -126,18 +113,14 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	if (__rpte_sub_valid(rpte, subpg_index)) {
 		int ret;
 
-		hash = hpt_hash(vpn, shift, ssize);
-		hidx = __rpte_to_hidx(rpte, subpg_index);
-		if (hidx & _PTEIDX_SECONDARY)
-			hash = ~hash;
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += hidx & _PTEIDX_GROUP_IX;
-
-		ret = mmu_hash_ops.hpte_updatepp(slot, rflags, vpn,
+		gslot = pte_get_hash_gslot(vpn, shift, ssize, rpte,
+					   subpg_index);
+		ret = mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn,
 						 MMU_PAGE_4K, MMU_PAGE_4K,
 						 ssize, flags);
+
 		/*
-		 *if we failed because typically the HPTE wasn't really here
+		 * If we failed because typically the HPTE wasn't really here
 		 * we try an insertion.
 		 */
 		if (ret == -1)

@@ -148,6 +131,14 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	}
 
 htab_insert_hpte:
+
+	/*
+	 * Initialize all hidx entries to invalid value, the first time
+	 * the PTE is about to allocate a 4K HPTE.
+	 */
+	if (!(old_pte & H_PAGE_COMBO))
+		rpte.hidx = INVALID_RPTE_HIDX;
+
 	/*
 	 * handle H_PAGE_4K_PFN case
 	 */

@@ -172,15 +163,39 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	 * Primary is full, try the secondary
 	 */
 	if (unlikely(slot == -1)) {
+		bool soft_invalid;
+
 		hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
 		slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
 						rflags, HPTE_V_SECONDARY,
 						MMU_PAGE_4K, MMU_PAGE_4K,
 						ssize);
-		if (slot == -1) {
-			if (mftb() & 0x1)
+
+		soft_invalid = hpte_soft_invalid(slot);
+		if (unlikely(soft_invalid)) {
+			/*
+			 * We got a valid slot from a hardware point of view.
+			 * but we cannot use it, because we use this special
+			 * value; as defined by hpte_soft_invalid(), to track
+			 * invalid slots. We cannot use it. So invalidate it.
+			 */
+			gslot = slot & _PTEIDX_GROUP_IX;
+			mmu_hash_ops.hpte_invalidate(hpte_group + gslot, vpn,
+						     MMU_PAGE_4K, MMU_PAGE_4K,
+						     ssize, 0);
+		}
+
+		if (unlikely(slot == -1 || soft_invalid)) {
+			/*
+			 * For soft invalid slot, let's ensure that we release a
+			 * slot from the primary, with the hope that we will
+			 * acquire that slot next time we try. This will ensure
+			 * that we do not get the same soft-invalid slot.
+			 */
+			if (soft_invalid || (mftb() & 0x1))
 				hpte_group = ((hash & htab_hash_mask) *
 					      HPTES_PER_GROUP) & ~0x7UL;
+
 			mmu_hash_ops.hpte_remove(hpte_group);
 			/*
 			 * FIXME!! Should be try the group from which we removed ?

@@ -198,21 +213,10 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 				   MMU_PAGE_4K, MMU_PAGE_4K, old_pte);
 		return -1;
 	}
-	/*
-	 * Insert slot number & secondary bit in PTE second half,
-	 * clear H_PAGE_BUSY and set appropriate HPTE slot bit
-	 * Since we have H_PAGE_BUSY set on ptep, we can be sure
-	 * nobody is undating hidx.
-	 */
-	hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
-	rpte.hidx &= ~(0xfUL << (subpg_index << 2));
-	*hidxp = rpte.hidx  | (slot << (subpg_index << 2));
-	new_pte = mark_subptegroup_valid(new_pte, subpg_index);
-	new_pte |=  H_PAGE_HASHPTE;
-	/*
-	 * check __real_pte for details on matching smp_rmb()
-	 */
-	smp_wmb();
+
+	new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot);
+	new_pte |= H_PAGE_HASHPTE;
+
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;
 }

@@ -978,8 +978,9 @@ void __init hash__early_init_devtree(void)
 
 void __init hash__early_init_mmu(void)
 {
+#ifndef CONFIG_PPC_64K_PAGES
 	/*
-	 * We have code in __hash_page_64K() and elsewhere, which assumes it can
+	 * We have code in __hash_page_4K() and elsewhere, which assumes it can
 	 * do the following:
 	 *   new_pte |= (slot << H_PAGE_F_GIX_SHIFT) & (H_PAGE_F_SECOND | H_PAGE_F_GIX);
 	 *

@@ -990,6 +991,7 @@ void __init hash__early_init_mmu(void)
 	 * with a BUILD_BUG_ON().
 	 */
 	BUILD_BUG_ON(H_PAGE_F_SECOND != (1ul  << (H_PAGE_F_GIX_SHIFT + 3)));
+#endif /* CONFIG_PPC_64K_PAGES */
 
 	htab_init_page_sizes();
 

@@ -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 */

@@ -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);
 }
 
 /*

@@ -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

@@ -103,8 +103,8 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		 * On hash insert failure we use old pte value and we don't
 		 * want slot information there if we have a insert failure.
 		 */
-		old_pte &= ~(H_PAGE_HASHPTE | H_PAGE_F_GIX | H_PAGE_F_SECOND);
-		new_pte &= ~(H_PAGE_HASHPTE | H_PAGE_F_GIX | H_PAGE_F_SECOND);
+		old_pte &= ~H_PAGE_HASHPTE;
+		new_pte &= ~H_PAGE_HASHPTE;
 		goto htab_insert_hpte;
 	}
 	/*

@@ -225,6 +225,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 		    unsigned long vsid, pte_t *ptep, unsigned long trap,
 		    unsigned long flags, int ssize)
 {
+	real_pte_t rpte;
 	unsigned long hpte_group;
 	unsigned long rflags, pa;
 	unsigned long old_pte, new_pte;

@@ -261,6 +262,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 	} while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
 
 	rflags = htab_convert_pte_flags(new_pte);
+	rpte = __real_pte(__pte(old_pte), ptep);
 
 	if (cpu_has_feature(CPU_FTR_NOEXECUTE) &&
 	    !cpu_has_feature(CPU_FTR_COHERENT_ICACHE))

@@ -268,16 +270,13 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 
 	vpn  = hpt_vpn(ea, vsid, ssize);
 	if (unlikely(old_pte & H_PAGE_HASHPTE)) {
+		unsigned long gslot;
+
 		/*
 		 * There MIGHT be an HPTE for this pte
 		 */
-		hash = hpt_hash(vpn, shift, ssize);
-		if (old_pte & H_PAGE_F_SECOND)
-			hash = ~hash;
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
-
-		if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_64K,
+		gslot = pte_get_hash_gslot(vpn, shift, ssize, rpte, 0);
+		if (mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn, MMU_PAGE_64K,
 					       MMU_PAGE_64K, ssize,
 					       flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;

@@ -326,9 +325,9 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 					   MMU_PAGE_64K, MMU_PAGE_64K, old_pte);
 			return -1;
 		}
+
 		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE;
-		new_pte |= (slot << H_PAGE_F_GIX_SHIFT) &
-			(H_PAGE_F_SECOND | H_PAGE_F_GIX);
+		new_pte |= pte_set_hidx(ptep, rpte, 0, slot);
 	}
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;

@@ -23,6 +23,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 		     pte_t *ptep, unsigned long trap, unsigned long flags,
 		     int ssize, unsigned int shift, unsigned int mmu_psize)
 {
+	real_pte_t rpte;
 	unsigned long vpn;
 	unsigned long old_pte, new_pte;
 	unsigned long rflags, pa, sz;

@@ -62,6 +63,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	} while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
 
 	rflags = htab_convert_pte_flags(new_pte);
+	rpte = __real_pte(__pte(old_pte), ptep);
 
 	sz = ((1UL) << shift);
 	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))

@@ -72,15 +74,10 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	/* Check if pte already has an hpte (case 2) */
 	if (unlikely(old_pte & H_PAGE_HASHPTE)) {
 		/* There MIGHT be an HPTE for this pte */
-		unsigned long hash, slot;
+		unsigned long gslot;
 
-		hash = hpt_hash(vpn, shift, ssize);
-		if (old_pte & H_PAGE_F_SECOND)
-			hash = ~hash;
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
-
-		if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, mmu_psize,
+		gslot = pte_get_hash_gslot(vpn, shift, ssize, rpte, 0);
+		if (mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn, mmu_psize,
 					       mmu_psize, ssize, flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}

@@ -107,8 +104,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 			return -1;
 		}
 
-		new_pte |= (slot << H_PAGE_F_GIX_SHIFT) &
-			(H_PAGE_F_SECOND | H_PAGE_F_GIX);
+		new_pte |= pte_set_hidx(ptep, rpte, 0, slot);
 	}
 
 	/*

@@ -63,13 +63,21 @@ static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
 	return rpte;
 }
 
+/*
+ * shift the hidx representation by one-modulo-0xf; i.e hidx 0 is respresented
+ * as 1, 1 as 2,... , and 0xf as 0.  This convention lets us represent a
+ * invalid hidx 0xf with a 0x0 bit value. PTEs are anyway zero'd when
+ * allocated. We dont have to zero them gain; thus save on the initialization.
+ */
+#define HIDX_UNSHIFT_BY_ONE(x) ((x + 0xfUL) & 0xfUL) /* shift backward by one */
+#define HIDX_SHIFT_BY_ONE(x) ((x + 0x1UL) & 0xfUL)   /* shift forward by one */
 #define HIDX_BITS(x, index)  (x << (index << 2))
 #define BITS_TO_HIDX(x, index)  ((x >> (index << 2)) & 0xfUL)
-#define INVALID_RPTE_HIDX  ~(0x0UL)
+#define INVALID_RPTE_HIDX  0x0UL
 
 static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
 {
-	return BITS_TO_HIDX(rpte.hidx, index);
+	return HIDX_UNSHIFT_BY_ONE(BITS_TO_HIDX(rpte.hidx, index));
 }
 
 /*

@@ -82,7 +90,7 @@ static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte,
 	unsigned long *hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
 
 	rpte.hidx &= ~HIDX_BITS(0xfUL, subpg_index);
-	*hidxp = rpte.hidx  | HIDX_BITS(hidx, subpg_index);
+	*hidxp = rpte.hidx  | HIDX_BITS(HIDX_SHIFT_BY_ONE(hidx), subpg_index);
 
 	/*
 	 * Anyone reading PTE must ensure hidx bits are read after reading the

@@ -17,10 +17,11 @@
 #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_F_GIX_SHIFT	53
+#define H_PAGE_F_SECOND	_RPAGE_RPN44	/* HPTE is in 2ndary HPTEG */
+#define H_PAGE_F_GIX	(_RPAGE_RPN43 | _RPAGE_RPN42 | _RPAGE_RPN41)
 #define H_PAGE_BUSY	_RPAGE_RSV1     /* software: PTE & hash are busy */
+#define H_PAGE_HASHPTE	_RPAGE_RSV2     /* software: PTE & hash are busy */
 
 /* PTE flags to conserve for HPTE identification */
 #define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | \

@@ -14,6 +14,7 @@
 #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_RPN44     /* software: PTE & hash are busy */
+#define H_PAGE_HASHPTE	_RPAGE_RPN43	/* PTE has associated HPTE */
 
 /*
  * We need to differentiate between explicit huge page and THP huge

@@ -9,7 +9,6 @@
  *
  */
 #define H_PTE_NONE_MASK		_PAGE_HPTEFLAGS
-#define H_PAGE_HASHPTE		_RPAGE_RPN43	/* PTE has associated HPTE */
 
 #ifdef CONFIG_PPC_64K_PAGES
 #include <asm/book3s/64/hash-64k.h>

@@ -20,6 +20,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		   pte_t *ptep, unsigned long trap, unsigned long flags,
 		   int ssize, int subpg_prot)
 {
+	real_pte_t rpte;
 	unsigned long hpte_group;
 	unsigned long rflags, pa;
 	unsigned long old_pte, new_pte;

@@ -54,6 +55,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	 * need to add in 0x1 if it's a read-only user page
 	 */
 	rflags = htab_convert_pte_flags(new_pte);
+	rpte = __real_pte(__pte(old_pte), ptep);
 
 	if (cpu_has_feature(CPU_FTR_NOEXECUTE) &&
 	    !cpu_has_feature(CPU_FTR_COHERENT_ICACHE))

@@ -64,13 +66,10 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		/*
 		 * There MIGHT be an HPTE for this pte
 		 */
-		hash = hpt_hash(vpn, shift, ssize);
-		if (old_pte & H_PAGE_F_SECOND)
-			hash = ~hash;
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += (old_pte & H_PAGE_F_GIX) >> H_PAGE_F_GIX_SHIFT;
+		unsigned long gslot = pte_get_hash_gslot(vpn, shift, ssize,
+							 rpte, 0);
 
-		if (mmu_hash_ops.hpte_updatepp(slot, rflags, vpn, MMU_PAGE_4K,
+		if (mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn, MMU_PAGE_4K,
 					       MMU_PAGE_4K, ssize, flags) == -1)
 			old_pte &= ~_PAGE_HPTEFLAGS;
 	}

@@ -118,8 +117,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 			return -1;
 		}
 		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE;
-		new_pte |= (slot << H_PAGE_F_GIX_SHIFT) &
-			(H_PAGE_F_SECOND | H_PAGE_F_GIX);
+		new_pte |= pte_set_hidx(ptep, rpte, 0, slot);
 	}
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;

@@ -1617,23 +1617,18 @@ unsigned long pte_get_hash_gslot(unsigned long vpn, unsigned long shift,
 void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
 		     unsigned long flags)
 {
-	unsigned long hash, index, shift, hidx, slot;
+	unsigned long index, shift, gslot;
 	int local = flags & HPTE_LOCAL_UPDATE;
 
 	DBG_LOW("flush_hash_page(vpn=%016lx)\n", vpn);
 	pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
-		hash = hpt_hash(vpn, shift, ssize);
-		hidx = __rpte_to_hidx(pte, index);
-		if (hidx & _PTEIDX_SECONDARY)
-			hash = ~hash;
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += hidx & _PTEIDX_GROUP_IX;
-		DBG_LOW(" sub %ld: hash=%lx, hidx=%lx\n", index, slot, hidx);
+		gslot = pte_get_hash_gslot(vpn, shift, ssize, pte, index);
+		DBG_LOW(" sub %ld: gslot=%lx\n", index, gslot);
 		/*
 		 * We use same base page size and actual psize, because we don't
 		 * use these functions for hugepage
 		 */
-		mmu_hash_ops.hpte_invalidate(slot, vpn, psize, psize,
+		mmu_hash_ops.hpte_invalidate(gslot, vpn, psize, psize,
 					     ssize, local);
 	} pte_iterate_hashed_end();
 

@@ -213,7 +213,7 @@ struct flag_info {
 		.val	= H_PAGE_4K_PFN,
 		.set	= "4K_pfn",
 	}, {
-#endif
+#else /* CONFIG_PPC_64K_PAGES */
 		.mask	= H_PAGE_F_GIX,
 		.val	= H_PAGE_F_GIX,
 		.set	= "f_gix",

@@ -224,6 +224,7 @@ struct flag_info {
 		.val	= H_PAGE_F_SECOND,
 		.set	= "f_second",
 	}, {
+#endif /* CONFIG_PPC_64K_PAGES */
 #endif
 		.mask	= _PAGE_SPECIAL,
 		.val	= _PAGE_SPECIAL,