Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc update from Benjamin Herrenschmidt:
 "The main highlights this time around are:

   - A pile of addition POWER8 bits and nits, such as updated
     performance counter support (Michael Ellerman), new branch history
     buffer support (Anshuman Khandual), base support for the new PCI
     host bridge when not using the hypervisor (Gavin Shan) and other
     random related bits and fixes from various contributors.

   - Some rework of our page table format by Aneesh Kumar which fixes a
     thing or two and paves the way for THP support.  THP itself will
     not make it this time around however.

   - More Freescale updates, including Altivec support on the new e6500
     cores, new PCI controller support, and a pile of new boards support
     and updates.

   - The usual batch of trivial cleanups & fixes"

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (156 commits)
  powerpc: Fix build error for book3e
  powerpc: Context switch the new EBB SPRs
  powerpc: Turn on the EBB H/FSCR bits
  powerpc: Replace CPU_FTR_BCTAR with CPU_FTR_ARCH_207S
  powerpc: Setup BHRB instructions facility in HFSCR for POWER8
  powerpc: Fix interrupt range check on debug exception
  powerpc: Update tlbie/tlbiel as per ISA doc
  powerpc: Print page size info during boot
  powerpc: print both base and actual page size on hash failure
  powerpc: Fix hpte_decode to use the correct decoding for page sizes
  powerpc: Decode the pte-lp-encoding bits correctly.
  powerpc: Use encode avpn where we need only avpn values
  powerpc: Reduce PTE table memory wastage
  powerpc: Move the pte free routines from common header
  powerpc: Reduce the PTE_INDEX_SIZE
  powerpc: Switch 16GB and 16MB explicit hugepages to a different page table format
  powerpc: New hugepage directory format
  powerpc: Don't truncate pgd_index wrongly
  powerpc: Don't hard code the size of pte page
  powerpc: Save DAR and DSISR in pt_regs on MCE
  ...

1 files changed, 129 insertions, 49 deletions

diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index ffc1e00..6a2aead 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;
@@ -61,17 +61,31 @@ static inline void __tlbie(unsigned long vpn, int psize, int ssize)
 
 	switch (psize) {
 	case MMU_PAGE_4K:
+		/* clear out bits after (52) [0....52.....63] */
+		va &= ~((1ul << (64 - 52)) - 1);
 		va |= ssize << 8;
+		va |= mmu_psize_defs[apsize].sllp << 6;
 		asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
 			     : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
 			     : "memory");
 		break;
 	default:
 		/* We need 14 to 14 + i bits of va */
-		penc = mmu_psize_defs[psize].penc;
-		va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
+		penc = mmu_psize_defs[psize].penc[apsize];
+		va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1);
 		va |= penc << 12;
 		va |= ssize << 8;
+		/* Add AVAL part */
+		if (psize != apsize) {
+			/*
+			 * MPSS, 64K base page size and 16MB parge page size
+			 * We don't need all the bits, but rest of the bits
+			 * must be ignored by the processor.
+			 * vpn cover upto 65 bits of va. (0...65) and we need
+			 * 58..64 bits of va.
+			 */
+			va |= (vpn & 0xfe);
+		}
 		va |= 1; /* L */
 		asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2)
 			     : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
@@ -80,7 +94,7 @@ 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;
@@ -96,16 +110,30 @@ static inline void __tlbiel(unsigned long vpn, int psize, int ssize)
 
 	switch (psize) {
 	case MMU_PAGE_4K:
+		/* clear out bits after(52) [0....52.....63] */
+		va &= ~((1ul << (64 - 52)) - 1);
 		va |= ssize << 8;
+		va |= mmu_psize_defs[apsize].sllp << 6;
 		asm volatile(".long 0x7c000224 | (%0 << 11) | (0 << 21)"
 			     : : "r"(va) : "memory");
 		break;
 	default:
 		/* We need 14 to 14 + i bits of va */
-		penc = mmu_psize_defs[psize].penc;
-		va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
+		penc = mmu_psize_defs[psize].penc[apsize];
+		va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1);
 		va |= penc << 12;
 		va |= ssize << 8;
+		/* Add AVAL part */
+		if (psize != apsize) {
+			/*
+			 * MPSS, 64K base page size and 16MB parge page size
+			 * We don't need all the bits, but rest of the bits
+			 * must be ignored by the processor.
+			 * vpn cover upto 65 bits of va. (0...65) and we need
+			 * 58..64 bits of va.
+			 */
+			va |= (vpn & 0xfe);
+		}
 		va |= 1; /* L */
 		asm volatile(".long 0x7c000224 | (%0 << 11) | (1 << 21)"
 			     : : "r"(va) : "memory");
@@ -114,7 +142,8 @@ 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 +154,10 @@ 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 +185,7 @@ 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 +212,8 @@ 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 +273,51 @@ static long native_hpte_remove(unsigned long hpte_group)
 	return i;
 }
 
+static inline int __hpte_actual_psize(unsigned int lp, int psize)
+{
+	int i, shift;
+	unsigned int mask;
+
+	/* 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 inline int hpte_actual_psize(struct hash_pte *hptep, int psize)
+{
+	/* 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;
+
+	return __hpte_actual_psize(lp, psize);
+}
+
 static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 				 unsigned long vpn, int psize, int ssize,
 				 int local)
@@ -251,8 +325,9 @@ 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_v(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, psize, ssize);
 
 	DBG_LOW("    update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)",
 		vpn, want_v & HPTE_V_AVPN, slot, newpp);
@@ -260,9 +335,13 @@ 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 +353,7 @@ 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;
 }
@@ -288,7 +367,7 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)
 	unsigned long want_v, hpte_v;
 
 	hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize);
-	want_v = hpte_encode_v(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, psize, ssize);
 
 	/* Bolted mappings are only ever in the primary group */
 	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
@@ -315,6 +394,7 @@ 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 +407,16 @@ 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,
@@ -343,64 +426,60 @@ 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);
 
 	DBG_LOW("    invalidate(vpn=%016lx, hash: %lx)\n", vpn, slot);
 
-	want_v = hpte_encode_v(vpn, psize, ssize);
+	want_v = hpte_encode_avpn(vpn, psize, ssize);
 	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 size, a_size, shift;
+	/* Look at the 8 bit LP value */
+	unsigned int lp = (hpte->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
 
-	if (!(hpte_v & HPTE_V_LARGE))
-		size = MMU_PAGE_4K;
-	else {
-		for (i = 0; i < LP_BITS; i++) {
-			if ((hpte_r & LP_MASK(i+1)) == LP_MASK(i+1))
-				break;
-		}
-		penc = LP_MASK(i+1) >> LP_SHIFT;
+	if (!(hpte_v & HPTE_V_LARGE)) {
+		size   = MMU_PAGE_4K;
+		a_size = MMU_PAGE_4K;
+	} else {
 		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;
 
-			if (penc == mmu_psize_defs[size].penc)
+			a_size = __hpte_actual_psize(lp, size);
+			if (a_size != -1)
 				break;
 		}
 	}
-
 	/* 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 +512,8 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 	default:
 		*vpn = size = 0;
 	}
-	*psize = size;
+	*psize  = size;
+	*apsize = a_size;
 }
 
 /*
@@ -451,7 +531,7 @@ 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 +557,9 @@ 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);
 		}
 	}
 
@@ -520,7 +600,7 @@ static void native_flush_hash_range(unsigned long number, int local)
 			slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
 			slot += hidx & _PTEIDX_GROUP_IX;
 			hptep = htab_address + slot;
-			want_v = hpte_encode_v(vpn, psize, ssize);
+			want_v = hpte_encode_avpn(vpn, psize, ssize);
 			native_lock_hpte(hptep);
 			hpte_v = hptep->v;
 			if (!HPTE_V_COMPARE(hpte_v, want_v) ||
@@ -540,7 +620,7 @@ 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 +637,7 @@ 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");