powerpc: Decode the pte-lp-encoding bits correctly.

We look at both the segment base page size and actual page size and store
the pte-lp-encodings in an array per base page size.

We also update all relevant functions to take actual page size argument
so that we can use the correct PTE LP encoding in HPTE. This should also
get the basic Multiple Page Size per Segment (MPSS) support. This is needed
to enable THP on ppc64.

[Fixed PR KVM build --BenH]

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

1 files changed, 98 insertions, 37 deletions

diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 9d8983a..14e3fe8 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -39,7 +39,7 @@
 
 DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
-static inline void __tlbie(unsigned long vpn, int psize, int ssize)
+static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 {
 	unsigned long va;
 	unsigned int penc;
@@ -68,7 +68,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int ssize)
 		break;
 	default:
 		/* We need 14 to 14 + i bits of va */
-		penc = mmu_psize_defs[psize].penc;
+		penc = mmu_psize_defs[psize].penc[apsize];
 		va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
 		va |= penc << 12;
 		va |= ssize << 8;
@@ -80,7 +80,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int ssize)
 	}
 }
 
-static inline void __tlbiel(unsigned long vpn, int psize, int ssize)
+static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 {
 	unsigned long va;
 	unsigned int penc;
@@ -102,7 +102,7 @@ static inline void __tlbiel(unsigned long vpn, int psize, int ssize)
 		break;
 	default:
 		/* We need 14 to 14 + i bits of va */
-		penc = mmu_psize_defs[psize].penc;
+		penc = mmu_psize_defs[psize].penc[apsize];
 		va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
 		va |= penc << 12;
 		va |= ssize << 8;
@@ -114,7 +114,8 @@ static inline void __tlbiel(unsigned long vpn, int psize, int ssize)
 
 }
 
-static inline void tlbie(unsigned long vpn, int psize, int ssize, int local)
+static inline void tlbie(unsigned long vpn, int psize, int apsize,
+			 int ssize, int local)
 {
 	unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL);
 	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
@@ -125,10 +126,10 @@ static inline void tlbie(unsigned long vpn, int psize, int ssize, int local)
 		raw_spin_lock(&native_tlbie_lock);
 	asm volatile("ptesync": : :"memory");
 	if (use_local) {
-		__tlbiel(vpn, psize, ssize);
+		__tlbiel(vpn, psize, apsize, ssize);
 		asm volatile("ptesync": : :"memory");
 	} else {
-		__tlbie(vpn, psize, ssize);
+		__tlbie(vpn, psize, apsize, ssize);
 		asm volatile("eieio; tlbsync; ptesync": : :"memory");
 	}
 	if (lock_tlbie && !use_local)
@@ -156,7 +157,7 @@ static inline void native_unlock_hpte(struct hash_pte *hptep)
 
 static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 			unsigned long pa, unsigned long rflags,
-			unsigned long vflags, int psize, int ssize)
+			unsigned long vflags, int psize, int apsize, int ssize)
 {
 	struct hash_pte *hptep = htab_address + hpte_group;
 	unsigned long hpte_v, hpte_r;
@@ -183,8 +184,8 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 	if (i == HPTES_PER_GROUP)
 		return -1;
 
-	hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID;
-	hpte_r = hpte_encode_r(pa, psize) | rflags;
+	hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
+	hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
 
 	if (!(vflags & HPTE_V_BOLTED)) {
 		DBG_LOW(" i=%x hpte_v=%016lx, hpte_r=%016lx\n",
@@ -244,6 +245,45 @@ static long native_hpte_remove(unsigned long hpte_group)
 	return i;
 }
 
+static inline int hpte_actual_psize(struct hash_pte *hptep, int psize)
+{
+	int i, shift;
+	unsigned int mask;
+	/* Look at the 8 bit LP value */
+	unsigned int lp = (hptep->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
+
+	if (!(hptep->v & HPTE_V_VALID))
+		return -1;
+
+	/* First check if it is large page */
+	if (!(hptep->v & HPTE_V_LARGE))
+		return MMU_PAGE_4K;
+
+	/* start from 1 ignoring MMU_PAGE_4K */
+	for (i = 1; i < MMU_PAGE_COUNT; i++) {
+
+		/* invalid penc */
+		if (mmu_psize_defs[psize].penc[i] == -1)
+			continue;
+		/*
+		 * encoding bits per actual page size
+		 *        PTE LP     actual page size
+		 *    rrrr rrrz		>=8KB
+		 *    rrrr rrzz		>=16KB
+		 *    rrrr rzzz		>=32KB
+		 *    rrrr zzzz		>=64KB
+		 * .......
+		 */
+		shift = mmu_psize_defs[i].shift - LP_SHIFT;
+		if (shift > LP_BITS)
+			shift = LP_BITS;
+		mask = (1 << shift) - 1;
+		if ((lp & mask) == mmu_psize_defs[psize].penc[i])
+			return i;
+	}
+	return -1;
+}
+
 static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 				 unsigned long vpn, int psize, int ssize,
 				 int local)
@@ -251,6 +291,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v, want_v;
 	int ret = 0;
+	int actual_psize;
 
 	want_v = hpte_encode_avpn(vpn, psize, ssize);
 
@@ -260,9 +301,13 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	native_lock_hpte(hptep);
 
 	hpte_v = hptep->v;
-
+	actual_psize = hpte_actual_psize(hptep, psize);
+	if (actual_psize < 0) {
+		native_unlock_hpte(hptep);
+		return -1;
+	}
 	/* Even if we miss, we need to invalidate the TLB */
-	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) {
+	if (!HPTE_V_COMPARE(hpte_v, want_v)) {
 		DBG_LOW(" -> miss\n");
 		ret = -1;
 	} else {
@@ -274,7 +319,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	native_unlock_hpte(hptep);
 
 	/* Ensure it is out of the tlb too. */
-	tlbie(vpn, psize, ssize, local);
+	tlbie(vpn, psize, actual_psize, ssize, local);
 
 	return ret;
 }
@@ -315,6 +360,7 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)
 static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 				       int psize, int ssize)
 {
+	int actual_psize;
 	unsigned long vpn;
 	unsigned long vsid;
 	long slot;
@@ -327,13 +373,16 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	if (slot == -1)
 		panic("could not find page to bolt\n");
 	hptep = htab_address + slot;
+	actual_psize = hpte_actual_psize(hptep, psize);
+	if (actual_psize < 0)
+		return;
 
 	/* Update the HPTE */
 	hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
 		(newpp & (HPTE_R_PP | HPTE_R_N));
 
 	/* Ensure it is out of the tlb too. */
-	tlbie(vpn, psize, ssize, 0);
+	tlbie(vpn, psize, actual_psize, ssize, 0);
 }
 
 static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
@@ -343,6 +392,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	unsigned long hpte_v;
 	unsigned long want_v;
 	unsigned long flags;
+	int actual_psize;
 
 	local_irq_save(flags);
 
@@ -352,35 +402,38 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	native_lock_hpte(hptep);
 	hpte_v = hptep->v;
 
+	actual_psize = hpte_actual_psize(hptep, psize);
+	if (actual_psize < 0) {
+		native_unlock_hpte(hptep);
+		local_irq_restore(flags);
+		return;
+	}
 	/* Even if we miss, we need to invalidate the TLB */
-	if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
+	if (!HPTE_V_COMPARE(hpte_v, want_v))
 		native_unlock_hpte(hptep);
 	else
 		/* Invalidate the hpte. NOTE: this also unlocks it */
 		hptep->v = 0;
 
 	/* Invalidate the TLB */
-	tlbie(vpn, psize, ssize, local);
+	tlbie(vpn, psize, actual_psize, ssize, local);
 
 	local_irq_restore(flags);
 }
 
-#define LP_SHIFT	12
-#define LP_BITS		8
-#define LP_MASK(i)	((0xFF >> (i)) << LP_SHIFT)
-
 static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
-			int *psize, int *ssize, unsigned long *vpn)
+			int *psize, int *apsize, int *ssize, unsigned long *vpn)
 {
 	unsigned long avpn, pteg, vpi;
 	unsigned long hpte_r = hpte->r;
 	unsigned long hpte_v = hpte->v;
 	unsigned long vsid, seg_off;
-	int i, size, shift, penc;
+	int i, size, a_size, shift, penc;
 
-	if (!(hpte_v & HPTE_V_LARGE))
-		size = MMU_PAGE_4K;
-	else {
+	if (!(hpte_v & HPTE_V_LARGE)) {
+		size   = MMU_PAGE_4K;
+		a_size = MMU_PAGE_4K;
+	} else {
 		for (i = 0; i < LP_BITS; i++) {
 			if ((hpte_r & LP_MASK(i+1)) == LP_MASK(i+1))
 				break;
@@ -388,19 +441,26 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 		penc = LP_MASK(i+1) >> LP_SHIFT;
 		for (size = 0; size < MMU_PAGE_COUNT; size++) {
 
-			/* 4K pages are not represented by LP */
-			if (size == MMU_PAGE_4K)
-				continue;
-
 			/* valid entries have a shift value */
 			if (!mmu_psize_defs[size].shift)
 				continue;
+			for (a_size = 0; a_size < MMU_PAGE_COUNT; a_size++) {
 
-			if (penc == mmu_psize_defs[size].penc)
-				break;
+				/* 4K pages are not represented by LP */
+				if (a_size == MMU_PAGE_4K)
+					continue;
+
+				/* valid entries have a shift value */
+				if (!mmu_psize_defs[a_size].shift)
+					continue;
+
+				if (penc == mmu_psize_defs[size].penc[a_size])
+					goto out;
+			}
 		}
 	}
 
+out:
 	/* This works for all page sizes, and for 256M and 1T segments */
 	*ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
 	shift = mmu_psize_defs[size].shift;
@@ -433,7 +493,8 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 	default:
 		*vpn = size = 0;
 	}
-	*psize = size;
+	*psize  = size;
+	*apsize = a_size;
 }
 
 /*
@@ -451,7 +512,7 @@ static void native_hpte_clear(void)
 	struct hash_pte *hptep = htab_address;
 	unsigned long hpte_v;
 	unsigned long pteg_count;
-	int psize, ssize;
+	int psize, apsize, ssize;
 
 	pteg_count = htab_hash_mask + 1;
 
@@ -477,9 +538,9 @@ static void native_hpte_clear(void)
 		 * already hold the native_tlbie_lock.
 		 */
 		if (hpte_v & HPTE_V_VALID) {
-			hpte_decode(hptep, slot, &psize, &ssize, &vpn);
+			hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn);
 			hptep->v = 0;
-			__tlbie(vpn, psize, ssize);
+			__tlbie(vpn, psize, apsize, ssize);
 		}
 	}
 
@@ -540,7 +601,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 
 			pte_iterate_hashed_subpages(pte, psize,
 						    vpn, index, shift) {
-				__tlbiel(vpn, psize, ssize);
+				__tlbiel(vpn, psize, psize, ssize);
 			} pte_iterate_hashed_end();
 		}
 		asm volatile("ptesync":::"memory");
@@ -557,7 +618,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 
 			pte_iterate_hashed_subpages(pte, psize,
 						    vpn, index, shift) {
-				__tlbie(vpn, psize, ssize);
+				__tlbie(vpn, psize, psize, ssize);
 			} pte_iterate_hashed_end();
 		}
 		asm volatile("eieio; tlbsync; ptesync":::"memory");