Merge tag 'powerpc-4.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Highlights include:

   - Larger virtual address space on 64-bit server CPUs. By default we
     use a 128TB virtual address space, but a process can request access
     to the full 512TB by passing a hint to mmap().

   - Support for the new Power9 "XIVE" interrupt controller.

   - TLB flushing optimisations for the radix MMU on Power9.

   - Support for CAPI cards on Power9, using the "Coherent Accelerator
     Interface Architecture 2.0".

   - The ability to configure the mmap randomisation limits at build and
     runtime.

   - Several small fixes and cleanups to the kprobes code, as well as
     support for KPROBES_ON_FTRACE.

   - Major improvements to handling of system reset interrupts,
     correctly treating them as NMIs, giving them a dedicated stack and
     using a new hypervisor call to trigger them, all of which should
     aid debugging and robustness.

   - Many fixes and other minor enhancements.

  Thanks to: Alastair D'Silva, Alexey Kardashevskiy, Alistair Popple,
  Andrew Donnellan, Aneesh Kumar K.V, Anshuman Khandual, Anton
  Blanchard, Balbir Singh, Ben Hutchings, Benjamin Herrenschmidt,
  Bhupesh Sharma, Chris Packham, Christian Zigotzky, Christophe Leroy,
  Christophe Lombard, Daniel Axtens, David Gibson, Gautham R. Shenoy,
  Gavin Shan, Geert Uytterhoeven, Guilherme G. Piccoli, Hamish Martin,
  Hari Bathini, Kees Cook, Laurent Dufour, Madhavan Srinivasan, Mahesh J
  Salgaonkar, Mahesh Salgaonkar, Masami Hiramatsu, Matt Brown, Matthew
  R. Ochs, Michael Neuling, Naveen N. Rao, Nicholas Piggin, Oliver
  O'Halloran, Pan Xinhui, Paul Mackerras, Rashmica Gupta, Russell
  Currey, Sukadev Bhattiprolu, Thadeu Lima de Souza Cascardo, Tobin C.
  Harding, Tyrel Datwyler, Uma Krishnan, Vaibhav Jain, Vipin K Parashar,
  Yang Shi"

* tag 'powerpc-4.12-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (214 commits)
  powerpc/64s: Power9 has no LPCR[VRMASD] field so don't set it
  powerpc/powernv: Fix TCE kill on NVLink2
  powerpc/mm/radix: Drop support for CPUs without lockless tlbie
  powerpc/book3s/mce: Move add_taint() later in virtual mode
  powerpc/sysfs: Move #ifdef CONFIG_HOTPLUG_CPU out of the function body
  powerpc/smp: Document irq enable/disable after migrating IRQs
  powerpc/mpc52xx: Don't select user-visible RTAS_PROC
  powerpc/powernv: Document cxl dependency on special case in pnv_eeh_reset()
  powerpc/eeh: Clean up and document event handling functions
  powerpc/eeh: Avoid use after free in eeh_handle_special_event()
  cxl: Mask slice error interrupts after first occurrence
  cxl: Route eeh events to all drivers in cxl_pci_error_detected()
  cxl: Force context lock during EEH flow
  powerpc/64: Allow CONFIG_RELOCATABLE if COMPILE_TEST
  powerpc/xmon: Teach xmon oops about radix vectors
  powerpc/mm/hash: Fix off-by-one in comment about kernel contexts ids
  powerpc/pseries: Enable VFIO
  powerpc/powernv: Fix iommu table size calculation hook for small tables
  powerpc/powernv: Check kzalloc() return value in pnv_pci_table_alloc
  powerpc: Add arch/powerpc/tools directory
  ...

49 files changed, 997 insertions, 456 deletions

diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index f6c5264287e5..7330150bfe34 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -17,6 +17,8 @@
 #include <asm/checksum.h>
 #include <linux/uaccess.h>
 #include <asm/epapr_hcalls.h>
+#include <asm/dcr.h>
+#include <asm/mmu_context.h>
 
 #include <uapi/asm/ucontext.h>
 
@@ -120,6 +122,8 @@ extern s64 __ashrdi3(s64, int);
 extern int __cmpdi2(s64, s64);
 extern int __ucmpdi2(u64, u64);
 
+/* tracing */
 void _mcount(void);
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
 
 #endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index bc5fdfd22788..33a24fdd7958 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -55,6 +55,14 @@
 #define PPC_BITEXTRACT(bits, ppc_bit, dst_bit)			\
 	((((bits) >> PPC_BITLSHIFT(ppc_bit)) & 1) << (dst_bit))
 
+#define PPC_BITLSHIFT32(be)	(32 - 1 - (be))
+#define PPC_BIT32(bit)		(1UL << PPC_BITLSHIFT32(bit))
+#define PPC_BITMASK32(bs, be)	((PPC_BIT32(bs) - PPC_BIT32(be))|PPC_BIT32(bs))
+
+#define PPC_BITLSHIFT8(be)	(8 - 1 - (be))
+#define PPC_BIT8(bit)		(1UL << PPC_BITLSHIFT8(bit))
+#define PPC_BITMASK8(bs, be)	((PPC_BIT8(bs) - PPC_BIT8(be))|PPC_BIT8(bs))
+
 #include <asm/barrier.h>
 
 /* Macro for generating the ***_bits() functions */
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 0c4e470571ca..b4b5e6b671ca 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -8,7 +8,7 @@
 #define H_PTE_INDEX_SIZE  9
 #define H_PMD_INDEX_SIZE  7
 #define H_PUD_INDEX_SIZE  9
-#define H_PGD_INDEX_SIZE  9
+#define H_PGD_INDEX_SIZE  12
 
 #ifndef __ASSEMBLY__
 #define H_PTE_TABLE_SIZE	(sizeof(pte_t) << H_PTE_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index f3dd21efa2ea..214219dff87c 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -4,10 +4,14 @@
 #define H_PTE_INDEX_SIZE  8
 #define H_PMD_INDEX_SIZE  5
 #define H_PUD_INDEX_SIZE  5
-#define H_PGD_INDEX_SIZE  12
+#define H_PGD_INDEX_SIZE  15
 
-#define H_PAGE_COMBO	0x00001000 /* this is a combo 4k page */
-#define H_PAGE_4K_PFN	0x00002000 /* PFN is for a single 4k page */
+/*
+ * 64k aligned address free up few of the lower bits of RPN for us
+ * We steal that here. For more deatils look at pte_pfn/pfn_pte()
+ */
+#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 */
 /*
  * We need to differentiate between explicit huge page and THP huge
  * page, since THP huge page also need to track real subpage details
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index f7b721bbf918..4e957b027fe0 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -6,19 +6,13 @@
  * Common bits between 4K and 64K pages in a linux-style PTE.
  * Additional bits may be defined in pgtable-hash64-*.h
  *
- * Note: We only support user read/write permissions. Supervisor always
- * have full read/write to pages above PAGE_OFFSET (pages below that
- * always use the user access permissions).
- *
- * We could create separate kernel read-only if we used the 3 PP bits
- * combinations that newer processors provide but we currently don't.
  */
-#define H_PAGE_BUSY		0x00800 /* software: PTE & hash are busy */
 #define H_PTE_NONE_MASK		_PAGE_HPTEFLAGS
-#define H_PAGE_F_GIX_SHIFT	57
-#define H_PAGE_F_GIX		(7ul << 57)	/* HPTE index within HPTEG */
-#define H_PAGE_F_SECOND		(1ul << 60)	/* HPTE is in 2ndary HPTEG */
-#define H_PAGE_HASHPTE		(1ul << 61)	/* PTE has associated HPTE */
+#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 */
 
 #ifdef CONFIG_PPC_64K_PAGES
 #include <asm/book3s/64/hash-64k.h>
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index c62f14d0bec1..6666cd366596 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -46,7 +46,7 @@ static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 	 */
 	VM_WARN_ON(page_shift == mmu_psize_defs[MMU_PAGE_1G].shift);
 	if (page_shift == mmu_psize_defs[MMU_PAGE_2M].shift)
-		return __pte(pte_val(entry) | _PAGE_LARGE);
+		return __pte(pte_val(entry) | R_PAGE_LARGE);
 	else
 		return entry;
 }
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 52d8d1e4b772..6981a52b3887 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -39,6 +39,7 @@
 
 /* Bits in the SLB VSID word */
 #define SLB_VSID_SHIFT		12
+#define SLB_VSID_SHIFT_256M	SLB_VSID_SHIFT
 #define SLB_VSID_SHIFT_1T	24
 #define SLB_VSID_SSIZE_SHIFT	62
 #define SLB_VSID_B		ASM_CONST(0xc000000000000000)
@@ -408,7 +409,7 @@ static inline unsigned long hpt_vpn(unsigned long ea,
 static inline unsigned long hpt_hash(unsigned long vpn,
 				     unsigned int shift, int ssize)
 {
-	int mask;
+	unsigned long mask;
 	unsigned long hash, vsid;
 
 	/* VPN_SHIFT can be atmost 12 */
@@ -491,13 +492,14 @@ extern void slb_set_size(u16 size);
  * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated
  * from mmu context id and effective segment id of the address.
  *
- * For user processes max context id is limited to ((1ul << 19) - 5)
- * for kernel space, we use the top 4 context ids to map address as below
+ * For user processes max context id is limited to MAX_USER_CONTEXT.
+
+ * For kernel space, we use context ids 1-4 to map addresses as below:
  * NOTE: each context only support 64TB now.
- * 0x7fffc -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
- * 0x7fffd -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
- * 0x7fffe -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
- * 0x7ffff -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
+ * 0x00001 -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
+ * 0x00002 -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
+ * 0x00003 -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
+ * 0x00004 -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
  *
  * The proto-VSIDs are then scrambled into real VSIDs with the
  * multiplicative hash:
@@ -511,20 +513,28 @@ extern void slb_set_size(u16 size);
  * robust scattering in the hash table (at least based on some initial
  * results).
  *
- * We also consider VSID 0 special. We use VSID 0 for slb entries mapping
- * bad address. This enables us to consolidate bad address handling in
- * hash_page.
+ * We use VSID 0 to indicate an invalid VSID. The means we can't use context id
+ * 0, because a context id of 0 and an EA of 0 gives a proto-VSID of 0, which
+ * will produce a VSID of 0.
  *
  * We also need to avoid the last segment of the last context, because that
  * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
- * because of the modulo operation in vsid scramble. But the vmemmap
- * (which is what uses region 0xf) will never be close to 64TB in size
- * (it's 56 bytes per page of system memory).
+ * because of the modulo operation in vsid scramble.
  */
 
+/*
+ * Max Va bits we support as of now is 68 bits. We want 19 bit
+ * context ID.
+ * Restrictions:
+ * GPU has restrictions of not able to access beyond 128TB
+ * (47 bit effective address). We also cannot do more than 20bit PID.
+ * For p4 and p5 which can only do 65 bit VA, we restrict our CONTEXT_BITS
+ * to 16 bits (ie, we can only have 2^16 pids at the same time).
+ */
+#define VA_BITS			68
 #define CONTEXT_BITS		19
-#define ESID_BITS		18
-#define ESID_BITS_1T		6
+#define ESID_BITS		(VA_BITS - (SID_SHIFT + CONTEXT_BITS))
+#define ESID_BITS_1T		(VA_BITS - (SID_SHIFT_1T + CONTEXT_BITS))
 
 #define ESID_BITS_MASK		((1 << ESID_BITS) - 1)
 #define ESID_BITS_1T_MASK	((1 << ESID_BITS_1T) - 1)
@@ -532,63 +542,70 @@ extern void slb_set_size(u16 size);
 /*
  * 256MB segment
  * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments
- * available for user + kernel mapping. The top 4 contexts are used for
- * kernel mapping. Each segment contains 2^28 bytes. Each
- * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts
- * (19 == 37 + 28 - 46).
+ * available for user + kernel mapping. VSID 0 is reserved as invalid, contexts
+ * 1-4 are used for kernel mapping. Each segment contains 2^28 bytes. Each
+ * context maps 2^49 bytes (512TB).
+ *
+ * We also need to avoid the last segment of the last context, because that
+ * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
+ * because of the modulo operation in vsid scramble.
+ */
+#define MAX_USER_CONTEXT	((ASM_CONST(1) << CONTEXT_BITS) - 2)
+#define MIN_USER_CONTEXT	(5)
+
+/* Would be nice to use KERNEL_REGION_ID here */
+#define KERNEL_REGION_CONTEXT_OFFSET	(0xc - 1)
+
+/*
+ * For platforms that support on 65bit VA we limit the context bits
  */
-#define MAX_USER_CONTEXT	((ASM_CONST(1) << CONTEXT_BITS) - 5)
+#define MAX_USER_CONTEXT_65BIT_VA ((ASM_CONST(1) << (65 - (SID_SHIFT + ESID_BITS))) - 2)
 
 /*
  * This should be computed such that protovosid * vsid_mulitplier
- * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus
+ * doesn't overflow 64 bits. The vsid_mutliplier should also be
+ * co-prime to vsid_modulus. We also need to make sure that number
+ * of bits in multiplied result (dividend) is less than twice the number of
+ * protovsid bits for our modulus optmization to work.
+ *
+ * The below table shows the current values used.
+ * |-------+------------+----------------------+------------+-------------------|
+ * |       | Prime Bits | proto VSID_BITS_65VA | Total Bits | 2* prot VSID_BITS |
+ * |-------+------------+----------------------+------------+-------------------|
+ * | 1T    |         24 |                   25 |         49 |                50 |
+ * |-------+------------+----------------------+------------+-------------------|
+ * | 256MB |         24 |                   37 |         61 |                74 |
+ * |-------+------------+----------------------+------------+-------------------|
+ *
+ * |-------+------------+----------------------+------------+--------------------|
+ * |       | Prime Bits | proto VSID_BITS_68VA | Total Bits | 2* proto VSID_BITS |
+ * |-------+------------+----------------------+------------+--------------------|
+ * | 1T    |         24 |                   28 |         52 |                 56 |
+ * |-------+------------+----------------------+------------+--------------------|
+ * | 256MB |         24 |                   40 |         64 |                 80 |
+ * |-------+------------+----------------------+------------+--------------------|
+ *
  */
 #define VSID_MULTIPLIER_256M	ASM_CONST(12538073)	/* 24-bit prime */
-#define VSID_BITS_256M		(CONTEXT_BITS + ESID_BITS)
-#define VSID_MODULUS_256M	((1UL<<VSID_BITS_256M)-1)
+#define VSID_BITS_256M		(VA_BITS - SID_SHIFT)
+#define VSID_BITS_65_256M	(65 - SID_SHIFT)
+/*
+ * Modular multiplicative inverse of VSID_MULTIPLIER under modulo VSID_MODULUS
+ */
+#define VSID_MULINV_256M	ASM_CONST(665548017062)
 
 #define VSID_MULTIPLIER_1T	ASM_CONST(12538073)	/* 24-bit prime */
-#define VSID_BITS_1T		(CONTEXT_BITS + ESID_BITS_1T)
-#define VSID_MODULUS_1T		((1UL<<VSID_BITS_1T)-1)
-
+#define VSID_BITS_1T		(VA_BITS - SID_SHIFT_1T)
+#define VSID_BITS_65_1T		(65 - SID_SHIFT_1T)
+#define VSID_MULINV_1T		ASM_CONST(209034062)
 
+/* 1TB VSID reserved for VRMA */
+#define VRMA_VSID	0x1ffffffUL
 #define USER_VSID_RANGE	(1UL << (ESID_BITS + SID_SHIFT))
 
-/*
- * This macro generates asm code to compute the VSID scramble
- * function.  Used in slb_allocate() and do_stab_bolted.  The function
- * computed is: (protovsid*VSID_MULTIPLIER) % VSID_MODULUS
- *
- *	rt = register containing the proto-VSID and into which the
- *		VSID will be stored
- *	rx = scratch register (clobbered)
- *
- * 	- rt and rx must be different registers
- * 	- The answer will end up in the low VSID_BITS bits of rt.  The higher
- * 	  bits may contain other garbage, so you may need to mask the
- * 	  result.
- */
-#define ASM_VSID_SCRAMBLE(rt, rx, size)					\
-	lis	rx,VSID_MULTIPLIER_##size@h;				\
-	ori	rx,rx,VSID_MULTIPLIER_##size@l;				\
-	mulld	rt,rt,rx;		/* rt = rt * MULTIPLIER */	\
-									\
-	srdi	rx,rt,VSID_BITS_##size;					\
-	clrldi	rt,rt,(64-VSID_BITS_##size);				\
-	add	rt,rt,rx;		/* add high and low bits */	\
-	/* NOTE: explanation based on VSID_BITS_##size = 36		\
-	 * Now, r3 == VSID (mod 2^36-1), and lies between 0 and		\
-	 * 2^36-1+2^28-1.  That in particular means that if r3 >=	\
-	 * 2^36-1, then r3+1 has the 2^36 bit set.  So, if r3+1 has	\
-	 * the bit clear, r3 already has the answer we want, if it	\
-	 * doesn't, the answer is the low 36 bits of r3+1.  So in all	\
-	 * cases the answer is the low 36 bits of (r3 + ((r3+1) >> 36))*/\
-	addi	rx,rt,1;						\
-	srdi	rx,rx,VSID_BITS_##size;	/* extract 2^VSID_BITS bit */	\
-	add	rt,rt,rx
-
 /* 4 bits per slice and we have one slice per 1TB */
-#define SLICE_ARRAY_SIZE  (H_PGTABLE_RANGE >> 41)
+#define SLICE_ARRAY_SIZE	(H_PGTABLE_RANGE >> 41)
+#define TASK_SLICE_ARRAY_SZ(x)	((x)->context.addr_limit >> 41)
 
 #ifndef __ASSEMBLY__
 
@@ -634,7 +651,7 @@ static inline void subpage_prot_init_new_context(struct mm_struct *mm) { }
 #define vsid_scramble(protovsid, size) \
 	((((protovsid) * VSID_MULTIPLIER_##size) % VSID_MODULUS_##size))
 
-#else /* 1 */
+/* simplified form avoiding mod operation */
 #define vsid_scramble(protovsid, size) \
 	({								 \
 		unsigned long x;					 \
@@ -642,6 +659,21 @@ static inline void subpage_prot_init_new_context(struct mm_struct *mm) { }
 		x = (x >> VSID_BITS_##size) + (x & VSID_MODULUS_##size); \
 		(x + ((x+1) >> VSID_BITS_##size)) & VSID_MODULUS_##size; \
 	})
+
+#else /* 1 */
+static inline unsigned long vsid_scramble(unsigned long protovsid,
+				  unsigned long vsid_multiplier, int vsid_bits)
+{
+	unsigned long vsid;
+	unsigned long vsid_modulus = ((1UL << vsid_bits) - 1);
+	/*
+	 * We have same multipler for both 256 and 1T segements now
+	 */
+	vsid = protovsid * vsid_multiplier;
+	vsid = (vsid >> vsid_bits) + (vsid & vsid_modulus);
+	return (vsid + ((vsid + 1) >> vsid_bits)) & vsid_modulus;
+}
+
 #endif /* 1 */
 
 /* Returns the segment size indicator for a user address */
@@ -656,36 +688,56 @@ static inline int user_segment_size(unsigned long addr)
 static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
 				     int ssize)
 {
+	unsigned long va_bits = VA_BITS;
+	unsigned long vsid_bits;
+	unsigned long protovsid;
+
 	/*
 	 * Bad address. We return VSID 0 for that
 	 */
 	if ((ea & ~REGION_MASK) >= H_PGTABLE_RANGE)
 		return 0;
 
-	if (ssize == MMU_SEGSIZE_256M)
-		return vsid_scramble((context << ESID_BITS)
-				     | ((ea >> SID_SHIFT) & ESID_BITS_MASK), 256M);
-	return vsid_scramble((context << ESID_BITS_1T)
-			     | ((ea >> SID_SHIFT_1T) & ESID_BITS_1T_MASK), 1T);
+	if (!mmu_has_feature(MMU_FTR_68_BIT_VA))
+		va_bits = 65;
+
+	if (ssize == MMU_SEGSIZE_256M) {
+		vsid_bits = va_bits - SID_SHIFT;
+		protovsid = (context << ESID_BITS) |
+			((ea >> SID_SHIFT) & ESID_BITS_MASK);
+		return vsid_scramble(protovsid, VSID_MULTIPLIER_256M, vsid_bits);
+	}
+	/* 1T segment */
+	vsid_bits = va_bits - SID_SHIFT_1T;
+	protovsid = (context << ESID_BITS_1T) |
+		((ea >> SID_SHIFT_1T) & ESID_BITS_1T_MASK);
+	return vsid_scramble(protovsid, VSID_MULTIPLIER_1T, vsid_bits);
 }
 
 /*
  * This is only valid for addresses >= PAGE_OFFSET
- *
- * For kernel space, we use the top 4 context ids to map address as below
- * 0x7fffc -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
- * 0x7fffd -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
- * 0x7fffe -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
- * 0x7ffff -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
  */
 static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
 {
 	unsigned long context;
 
+	if (!is_kernel_addr(ea))
+		return 0;
+
 	/*
-	 * kernel take the top 4 context from the available range
+	 * For kernel space, we use context ids 1-4 to map the address space as
+	 * below:
+	 *
+	 * 0x00001 -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
+	 * 0x00002 -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
+	 * 0x00003 -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
+	 * 0x00004 -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
+	 *
+	 * So we can compute the context from the region (top nibble) by
+	 * subtracting 11, or 0xc - 1.
 	 */
-	context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1;
+	context = (ea >> 60) - KERNEL_REGION_CONTEXT_OFFSET;
+
 	return get_vsid(context, ea, ssize);
 }
 
diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 805d4105e9bb..77529a3e3811 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -65,6 +65,8 @@ extern struct patb_entry *partition_tb;
  * MAX_USER_CONTEXT * 16 bytes of space.
  */
 #define PRTB_SIZE_SHIFT	(CONTEXT_BITS + 4)
+#define PRTB_ENTRIES	(1ul << CONTEXT_BITS)
+
 /*
  * Power9 currently only support 64K partition table size.
  */
@@ -73,13 +75,20 @@ extern struct patb_entry *partition_tb;
 typedef unsigned long mm_context_id_t;
 struct spinlock;
 
+/* Maximum possible number of NPUs in a system. */
+#define NV_MAX_NPUS 8
+
 typedef struct {
 	mm_context_id_t id;
 	u16 user_psize;		/* page size index */
 
+	/* NPU NMMU context */
+	struct npu_context *npu_context;
+
 #ifdef CONFIG_PPC_MM_SLICES
 	u64 low_slices_psize;	/* SLB page size encodings */
 	unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
+	unsigned long addr_limit;
 #else
 	u16 sllp;		/* SLB page size encoding */
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 8f4d41936e5a..85bc9875c3be 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -13,6 +13,7 @@
 #define _PAGE_BIT_SWAP_TYPE	0
 
 #define _PAGE_RO		0
+#define _PAGE_SHARED		0
 
 #define _PAGE_EXEC		0x00001 /* execute permission */
 #define _PAGE_WRITE		0x00002 /* write access allowed */
@@ -37,21 +38,47 @@
 #define _RPAGE_RSV3		0x0400000000000000UL
 #define _RPAGE_RSV4		0x0200000000000000UL
 
-#ifdef CONFIG_MEM_SOFT_DIRTY
-#define _PAGE_SOFT_DIRTY	_RPAGE_SW3 /* software: software dirty tracking */
-#else
-#define _PAGE_SOFT_DIRTY	0x00000
-#endif
-#define _PAGE_SPECIAL		_RPAGE_SW2 /* software: special page */
+#define _PAGE_PTE		0x4000000000000000UL	/* distinguishes PTEs from pointers */
+#define _PAGE_PRESENT		0x8000000000000000UL	/* pte contains a translation */
 
 /*
- * For P9 DD1 only, we need to track whether the pte's huge.
+ * Top and bottom bits of RPN which can be used by hash
+ * translation mode, because we expect them to be zero
+ * otherwise.
  */
-#define _PAGE_LARGE	_RPAGE_RSV1
+#define _RPAGE_RPN0		0x01000
+#define _RPAGE_RPN1		0x02000
+#define _RPAGE_RPN44		0x0100000000000000UL
+#define _RPAGE_RPN43		0x0080000000000000UL
+#define _RPAGE_RPN42		0x0040000000000000UL
+#define _RPAGE_RPN41		0x0020000000000000UL
+
+/* Max physical address bit as per radix table */
+#define _RPAGE_PA_MAX		57
 
+/*
+ * Max physical address bit we will use for now.
+ *
+ * This is mostly a hardware limitation and for now Power9 has
+ * a 51 bit limit.
+ *
+ * This is different from the number of physical bit required to address
+ * the last byte of memory. That is defined by MAX_PHYSMEM_BITS.
+ * MAX_PHYSMEM_BITS is a linux limitation imposed by the maximum
+ * number of sections we can support (SECTIONS_SHIFT).
+ *
+ * This is different from Radix page table limitation above and
+ * should always be less than that. The limit is done such that
+ * we can overload the bits between _RPAGE_PA_MAX and _PAGE_PA_MAX
+ * for hash linux page table specific bits.
+ *
+ * In order to be compatible with future hardware generations we keep
+ * some offsets and limit this for now to 53
+ */
+#define _PAGE_PA_MAX		53
 
-#define _PAGE_PTE		(1ul << 62)	/* distinguishes PTEs from pointers */
-#define _PAGE_PRESENT		(1ul << 63)	/* pte contains a translation */
+#define _PAGE_SOFT_DIRTY	_RPAGE_SW3 /* software: software dirty tracking */
+#define _PAGE_SPECIAL		_RPAGE_SW2 /* software: special page */
 /*
  * Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE
  * Instead of fixing all of them, add an alternate define which
@@ -59,10 +86,11 @@
  */
 #define _PAGE_NO_CACHE		_PAGE_TOLERANT
 /*
- * We support 57 bit real address in pte. Clear everything above 57, and
- * every thing below PAGE_SHIFT;
+ * We support _RPAGE_PA_MAX bit real address in pte. On the linux side
+ * we are limited by _PAGE_P