[PATCH V2 00/10] Fixes for Radix support

[PATCH V2 00/10] Fixes for Radix support

[Aneesh Kumar K.V]

Hi Michael,

This series includes patches I had posted before. I collected them in a series
and marked the series V2. This address the review feedback I received from
last post.


Aneesh Kumar K.V (9):
  powerpc/mm/radix: Update to tlb functions ric argument
  powerpc/mm/radix: Flush page walk cache when freeing page table
  powerpc/mm/radix: Update LPCR HR bit as per ISA
  powerpc/mm: use _raw variant of page table accessors
  powerpc/mm: Compile out radix related functions if RADIX_MMU is
    disabled
  powerpc/hash: Use the correct ppp mask when updating hpte
  powerpc/mm: Clear top 16 bits of va only on older cpus
  powerpc/mm: Print formation regarding the the MMU mode
  powerpc/mm/hash: Update SDR1 size encoding as documented in ISA 3.0

Balbir Singh (1):
  Fix .long's in mm/tlb-radix.c to more meaningful

 arch/powerpc/include/asm/book3s/32/pgalloc.h       |  1 -
 arch/powerpc/include/asm/book3s/64/mmu-hash.h      |  1 +
 arch/powerpc/include/asm/book3s/64/mmu.h           |  5 ++
 arch/powerpc/include/asm/book3s/64/pgalloc.h       | 16 +++-
 arch/powerpc/include/asm/book3s/64/pgtable-4k.h    |  6 +-
 arch/powerpc/include/asm/book3s/64/pgtable-64k.h   |  6 +-
 arch/powerpc/include/asm/book3s/64/pgtable.h       | 99 +++++++++++++++-------
 .../powerpc/include/asm/book3s/64/tlbflush-radix.h |  3 +
 arch/powerpc/include/asm/book3s/64/tlbflush.h      | 15 +++-
 arch/powerpc/include/asm/book3s/pgalloc.h          |  5 --
 arch/powerpc/include/asm/mmu.h                     | 12 ++-
 arch/powerpc/include/asm/pgtable-be-types.h        | 15 ++++
 arch/powerpc/include/asm/ppc-opcode.h              | 14 +++
 arch/powerpc/include/asm/reg.h                     |  1 +
 arch/powerpc/mm/hash_native_64.c                   | 14 +--
 arch/powerpc/mm/hash_utils_64.c                    | 12 +--
 arch/powerpc/mm/pgtable-radix.c                    |  7 +-
 arch/powerpc/mm/tlb-radix.c                        | 94 +++++++++++++-------
 18 files changed, 236 insertions(+), 90 deletions(-)

-- 
2.7.4

[PATCH V2 01/10] Fix .long's in mm/tlb-radix.c to more meaningful

[Aneesh Kumar K.V]

From: Balbir Singh <bsingharora@gmail.com>

The .longs with the shifts are harder to read, use more
meaningful names for the opcodes. PPC_TLBIE_5 is introduced
for the 5 opcode variation of the instruction due to an existing
op-code for the 2 opcode variant

Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/ppc-opcode.h | 14 ++++++++++++++
 arch/powerpc/mm/tlb-radix.c           | 13 +++++--------
 2 files changed, 19 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 1d035c1cc889..c0e9ea44fee3 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -184,6 +184,7 @@
 #define PPC_INST_STSWX			0x7c00052a
 #define PPC_INST_STXVD2X		0x7c000798
 #define PPC_INST_TLBIE			0x7c000264
+#define PPC_INST_TLBIEL			0x7c000224
 #define PPC_INST_TLBILX			0x7c000024
 #define PPC_INST_WAIT			0x7c00007c
 #define PPC_INST_TLBIVAX		0x7c000624
@@ -257,6 +258,9 @@
 #define ___PPC_RB(b)	(((b) & 0x1f) << 11)
 #define ___PPC_RS(s)	(((s) & 0x1f) << 21)
 #define ___PPC_RT(t)	___PPC_RS(t)
+#define ___PPC_R(r)	(((r) & 0x1) << 16)
+#define ___PPC_PRS(prs)	(((prs) & 0x1) << 17)
+#define ___PPC_RIC(ric)	(((ric) & 0x3) << 18)
 #define __PPC_RA(a)	___PPC_RA(__REG_##a)
 #define __PPC_RA0(a)	___PPC_RA(__REGA0_##a)
 #define __PPC_RB(b)	___PPC_RB(__REG_##b)
@@ -321,6 +325,16 @@
 					__PPC_WC(w))
 #define PPC_TLBIE(lp,a) 	stringify_in_c(.long PPC_INST_TLBIE | \
 					       ___PPC_RB(a) | ___PPC_RS(lp))
+#define	PPC_TLBIE_5(rb,rs,ric,prs,r) \
+				stringify_in_c(.long PPC_INST_TLBIE | \
+					___PPC_RB(rb) | ___PPC_RS(rs) | \
+					___PPC_RIC(ric) | ___PPC_PRS(prs) | \
+					___PPC_R(r))
+#define	PPC_TLBIEL(rb,rs,ric,prs,r) \
+				stringify_in_c(.long PPC_INST_TLBIEL | \
+					___PPC_RB(rb) | ___PPC_RS(rs) | \
+					___PPC_RIC(ric) | ___PPC_PRS(prs) | \
+					___PPC_R(r))
 #define PPC_TLBSRX_DOT(a,b)	stringify_in_c(.long PPC_INST_TLBSRX_DOT | \
 					__PPC_RA0(a) | __PPC_RB(b))
 #define PPC_TLBIVAX(a,b)	stringify_in_c(.long PPC_INST_TLBIVAX | \
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 0fdaf93a3e09..e6b7487ad28f 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -12,6 +12,7 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/memblock.h>
+#include <asm/ppc-opcode.h>
 
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
@@ -30,8 +31,7 @@ static inline void __tlbiel_pid(unsigned long pid, int set)
 	ric = 2;  /* invalidate all the caches */
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
-		     "(%2 << 17) | (%3 << 18) | (%4 << 21)"
+	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("ptesync": : :"memory");
 }
@@ -60,8 +60,7 @@ static inline void _tlbie_pid(unsigned long pid)
 	ric = 2;  /* invalidate all the caches */
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
-		     "(%2 << 17) | (%3 << 18) | (%4 << 21)"
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
@@ -79,8 +78,7 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 	ric = 0;  /* no cluster flush yet */
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(".long 0x7c000224 | (%0 << 11) | (%1 << 16) |"
-		     "(%2 << 17) | (%3 << 18) | (%4 << 21)"
+	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("ptesync": : :"memory");
 }
@@ -98,8 +96,7 @@ static inline void _tlbie_va(unsigned long va, unsigned long pid,
 	ric = 0;  /* no cluster flush yet */
 
 	asm volatile("ptesync": : :"memory");
-	asm volatile(".long 0x7c000264 | (%0 << 11) | (%1 << 16) |"
-		     "(%2 << 17) | (%3 << 18) | (%4 << 21)"
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
-- 
2.7.4

[PATCH V2 02/10] powerpc/mm/radix: Update to tlb functions ric argument

[Aneesh Kumar K.V]

Radix invalidate control (RIC) is used to control which cache to flush
using tlb instructions. When doing a PID flush, we currently flush
everything including page walk cache. For address range flush, we flush
only the TLB. In the later patch, we add support for flushing only
page walk cache.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/mm/tlb-radix.c | 43 ++++++++++++++++++++++---------------------
 1 file changed, 22 insertions(+), 21 deletions(-)

diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index e6b7487ad28f..b33b7c77cfa3 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -19,16 +19,20 @@
 
 static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
-static inline void __tlbiel_pid(unsigned long pid, int set)
+#define RIC_FLUSH_TLB 0
+#define RIC_FLUSH_PWC 1
+#define RIC_FLUSH_ALL 2
+
+static inline void __tlbiel_pid(unsigned long pid, int set,
+				unsigned long ric)
 {
-	unsigned long rb,rs,ric,prs,r;
+	unsigned long rb,rs,prs,r;
 
 	rb = PPC_BIT(53); /* IS = 1 */
 	rb |= set << PPC_BITLSHIFT(51);
 	rs = ((unsigned long)pid) << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
-	ric = 2;  /* invalidate all the caches */
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
@@ -39,25 +43,24 @@ static inline void __tlbiel_pid(unsigned long pid, int set)
 /*
  * We use 128 set in radix mode and 256 set in hpt mode.
  */
-static inline void _tlbiel_pid(unsigned long pid)
+static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 {
 	int set;
 
 	for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
-		__tlbiel_pid(pid, set);
+		__tlbiel_pid(pid, set, ric);
 	}
 	return;
 }
 
-static inline void _tlbie_pid(unsigned long pid)
+static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 {
-	unsigned long rb,rs,ric,prs,r;
+	unsigned long rb,rs,prs,r;
 
 	rb = PPC_BIT(53); /* IS = 1 */
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
-	ric = 2;  /* invalidate all the caches */
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
@@ -66,16 +69,15 @@ static inline void _tlbie_pid(unsigned long pid)
 }
 
 static inline void _tlbiel_va(unsigned long va, unsigned long pid,
-			      unsigned long ap)
+			      unsigned long ap, unsigned long ric)
 {
-	unsigned long rb,rs,ric,prs,r;
+	unsigned long rb,rs,prs,r;
 
 	rb = va & ~(PPC_BITMASK(52, 63));
 	rb |= ap << PPC_BITLSHIFT(58);
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
-	ric = 0;  /* no cluster flush yet */
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
@@ -84,16 +86,15 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 }
 
 static inline void _tlbie_va(unsigned long va, unsigned long pid,
-			     unsigned long ap)
+			     unsigned long ap, unsigned long ric)
 {
-	unsigned long rb,rs,ric,prs,r;
+	unsigned long rb,rs,prs,r;
 
 	rb = va & ~(PPC_BITMASK(52, 63));
 	rb |= ap << PPC_BITLSHIFT(58);
 	rs = pid << PPC_BITLSHIFT(31);
 	prs = 1; /* process scoped */
 	r = 1;   /* raidx format */
-	ric = 0;  /* no cluster flush yet */
 
 	asm volatile("ptesync": : :"memory");
 	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
@@ -119,7 +120,7 @@ void radix__local_flush_tlb_mm(struct mm_struct *mm)
 	preempt_disable();
 	pid = mm->context.id;
 	if (pid != MMU_NO_CONTEXT)
-		_tlbiel_pid(pid);
+		_tlbiel_pid(pid, RIC_FLUSH_ALL);
 	preempt_enable();
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_mm);
@@ -132,7 +133,7 @@ void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 	preempt_disable();
 	pid = mm ? mm->context.id : 0;
 	if (pid != MMU_NO_CONTEXT)
-		_tlbiel_va(vmaddr, pid, ap);
+		_tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
 	preempt_enable();
 }
 
@@ -169,11 +170,11 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
 
 		if (lock_tlbie)
 			raw_spin_lock(&native_tlbie_lock);
-		_tlbie_pid(pid);
+		_tlbie_pid(pid, RIC_FLUSH_ALL);
 		if (lock_tlbie)
 			raw_spin_unlock(&native_tlbie_lock);
 	} else
-		_tlbiel_pid(pid);
+		_tlbiel_pid(pid, RIC_FLUSH_ALL);
 no_context:
 	preempt_enable();
 }
@@ -193,11 +194,11 @@ void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 
 		if (lock_tlbie)
 			raw_spin_lock(&native_tlbie_lock);
-		_tlbie_va(vmaddr, pid, ap);
+		_tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
 		if (lock_tlbie)
 			raw_spin_unlock(&native_tlbie_lock);
 	} else
-		_tlbiel_va(vmaddr, pid, ap);
+		_tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
 bail:
 	preempt_enable();
 }
@@ -221,7 +222,7 @@ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
 
 	if (lock_tlbie)
 		raw_spin_lock(&native_tlbie_lock);
-	_tlbie_pid(0);
+	_tlbie_pid(0, RIC_FLUSH_ALL);
 	if (lock_tlbie)
 		raw_spin_unlock(&native_tlbie_lock);
 }
-- 
2.7.4

[PATCH V2 03/10] powerpc/mm/radix: Flush page walk cache when freeing page table

[Aneesh Kumar K.V]

Even though a tlb_flush() does a flush with invalidate all cache,
we can end up doing an RCU page table free before calling tlb_flush().
That means we can have page walk cache entries even after we free the
page table pages. This can result in us doing wrong page table walk.

Avoid this by doing pwc flush on every page table free. We can't batch
the pwc flush, because the rcu call back function where we free the
page table pages doesn't have information of the mmu gather. Thus we
have to do a pwc on every page table page freed.

Note: I also removed the dummy tlb_flush_pgtable call functions for
hash 32.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/32/pgalloc.h       |  1 -
 arch/powerpc/include/asm/book3s/64/pgalloc.h       | 16 ++++++++-
 .../powerpc/include/asm/book3s/64/tlbflush-radix.h |  3 ++
 arch/powerpc/include/asm/book3s/64/tlbflush.h      | 15 ++++++++-
 arch/powerpc/include/asm/book3s/pgalloc.h          |  5 ---
 arch/powerpc/mm/tlb-radix.c                        | 38 ++++++++++++++++++++++
 6 files changed, 70 insertions(+), 8 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index a2350194fc76..8e21bb492dca 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -102,7 +102,6 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb,
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
-	tlb_flush_pgtable(tlb, address);
 	pgtable_page_dtor(table);
 	pgtable_free_tlb(tlb, page_address(table), 0);
 }
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 488279edb1f0..26eb2cb80c4e 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -110,6 +110,11 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
 static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
                                   unsigned long address)
 {
+	/*
+	 * By now all the pud entries should be none entries. So go
+	 * ahead and flush the page walk cache
+	 */
+	flush_tlb_pgtable(tlb, address);
         pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE);
 }
 
@@ -127,6 +132,11 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
                                   unsigned long address)
 {
+	/*
+	 * By now all the pud entries should be none entries. So go
+	 * ahead and flush the page walk cache
+	 */
+	flush_tlb_pgtable(tlb, address);
         return pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX);
 }
 
@@ -198,7 +208,11 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 				  unsigned long address)
 {
-	tlb_flush_pgtable(tlb, address);
+	/*
+	 * By now all the pud entries should be none entries. So go
+	 * ahead and flush the page walk cache
+	 */
+	flush_tlb_pgtable(tlb, address);
 	pgtable_free_tlb(tlb, table, 0);
 }
 
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index 13ef38828dfe..3fa94fcac628 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -18,16 +18,19 @@ extern void radix__local_flush_tlb_mm(struct mm_struct *mm);
 extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 extern void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 				    unsigned long ap, int nid);
+extern void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 extern void radix__tlb_flush(struct mmu_gather *tlb);
 #ifdef CONFIG_SMP
 extern void radix__flush_tlb_mm(struct mm_struct *mm);
 extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 extern void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 			      unsigned long ap, int nid);
+extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 #else
 #define radix__flush_tlb_mm(mm)		radix__local_flush_tlb_mm(mm)
 #define radix__flush_tlb_page(vma,addr)	radix__local_flush_tlb_page(vma,addr)
 #define radix___flush_tlb_page(mm,addr,p,i)	radix___local_flush_tlb_page(mm,addr,p,i)
+#define radix__flush_tlb_pwc(tlb, addr)	radix__local_flush_tlb_pwc(tlb, addr)
 #endif
 
 #endif
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h
index d98424ae356c..541cf809e38e 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h
@@ -72,5 +72,18 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 #define flush_tlb_mm(mm)		local_flush_tlb_mm(mm)
 #define flush_tlb_page(vma, addr)	local_flush_tlb_page(vma, addr)
 #endif /* CONFIG_SMP */
-
+/*
+ * flush the page walk cache for the address
+ */
+static inline void flush_tlb_pgtable(struct mmu_gather *tlb, unsigned long address)
+{
+	/*
+	 * flush the page table walk cache on freeing page table. We already
+	 * have marked the upper/higher level page table entry none by now.
+	 * So it is safe to flush PWC here.
+	 */
+	if (!radix_enabled())
+		return;
+	radix__flush_tlb_pwc(tlb, address);
+}
 #endif /*  _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H */
diff --git a/arch/powerpc/include/asm/book3s/pgalloc.h b/arch/powerpc/include/asm/book3s/pgalloc.h
index 54f591e9572e..c0a69ae92256 100644
--- a/arch/powerpc/include/asm/book3s/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/pgalloc.h
@@ -4,11 +4,6 @@
 #include <linux/mm.h>
 
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
-				     unsigned long address)
-{
-
-}
 
 #ifdef CONFIG_PPC64
 #include <asm/book3s/64/pgalloc.h>
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index b33b7c77cfa3..0c0593f201e3 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -125,6 +125,19 @@ void radix__local_flush_tlb_mm(struct mm_struct *mm)
 }
 EXPORT_SYMBOL(radix__local_flush_tlb_mm);
 
+void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+{
+	unsigned long pid;
+	struct mm_struct *mm = tlb->mm;
+
+	preempt_disable();
+	pid = mm->context.id;
+	if (pid != MMU_NO_CONTEXT)
+		_tlbiel_pid(pid, RIC_FLUSH_PWC);
+	preempt_enable();
+}
+EXPORT_SYMBOL(radix__local_flush_tlb_pwc);
+
 void radix___local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 			    unsigned long ap, int nid)
 {
@@ -180,6 +193,31 @@ no_context:
 }
 EXPORT_SYMBOL(radix__flush_tlb_mm);
 
+void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
+{
+	unsigned long pid;
+	struct mm_struct *mm = tlb->mm;
+
+	preempt_disable();
+	pid = mm->context.id;
+	if (unlikely(pid == MMU_NO_CONTEXT))
+		goto no_context;
+
+	if (!mm_is_core_local(mm)) {
+		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+
+		if (lock_tlbie)
+			raw_spin_lock(&native_tlbie_lock);
+		_tlbie_pid(pid, RIC_FLUSH_PWC);
+		if (lock_tlbie)
+			raw_spin_unlock(&native_tlbie_lock);
+	} else
+		_tlbiel_pid(pid, RIC_FLUSH_PWC);
+no_context:
+	preempt_enable();
+}
+EXPORT_SYMBOL(radix__flush_tlb_pwc);
+
 void radix___flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
 		       unsigned long ap, int nid)
 {
-- 
2.7.4

[PATCH V2 04/10] powerpc/mm/radix: Update LPCR HR bit as per ISA

[Aneesh Kumar K.V]

PowerISA 3.0 requires the MMU mode (radix vs. hash) of the hypervisor
to be mirrored in the LPCR register, in addition to the partition table.
This is done to avoid fetching from the table when deciding, among other
things, how to perform transitions to HV mode on some interrupts.
So let's set it up appropriately

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/reg.h  | 1 +
 arch/powerpc/mm/pgtable-radix.c | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index a0948f40bc7b..466816ede138 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -348,6 +348,7 @@
 #define   LPCR_RMI     0x00000002      /* real mode is cache inhibit */
 #define   LPCR_HDICE   0x00000001      /* Hyp Decr enable (HV,PR,EE) */
 #define   LPCR_UPRT    0x00400000      /* Use Process Table (ISA 3) */
+#define	  LPCR_HR      0x00100000
 #ifndef SPRN_LPID
 #define SPRN_LPID	0x13F	/* Logical Partition Identifier */
 #endif
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index c939e6e57a9e..73aa402047ef 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -340,7 +340,7 @@ void __init radix__early_init_mmu(void)
 	radix_init_page_sizes();
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 		lpcr = mfspr(SPRN_LPCR);
-		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
+		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 		radix_init_partition_table();
 	}
 
@@ -355,7 +355,7 @@ void radix__early_init_mmu_secondary(void)
 	 */
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 		lpcr = mfspr(SPRN_LPCR);
-		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT);
+		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 
 		mtspr(SPRN_PTCR,
 		      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
-- 
2.7.4

[PATCH V2 05/10] powerpc/mm: use _raw variant of page table accessors

[Aneesh Kumar K.V]

This switch few of the page table accessor to use the __raw variant
and does the cpu to big endian conversion of constants. This helps in
generating better code.

For ex: a pgd_none(pgd) check with and without fix is listed below

Without fix:
------------
   2240:	20 00 61 eb 	ld      r27,32(r1)
/* PGD level */
typedef struct { __be64 pgd; } pgd_t;
static inline unsigned long pgd_val(pgd_t x)
{
	return be64_to_cpu(x.pgd);

    2244:	22 00 66 78 	rldicl  r6,r3,32,32
    2248:	3e 40 7d 54 	rotlwi  r29,r3,8
    224c:	0e c0 7d 50 	rlwimi  r29,r3,24,0,7
    2250:	3e 40 c5 54 	rotlwi  r5,r6,8
    2254:	2e c4 7d 50 	rlwimi  r29,r3,24,16,23
    2258:	0e c0 c5 50 	rlwimi  r5,r6,24,0,7
    225c:	2e c4 c5 50 	rlwimi  r5,r6,24,16,23
    2260:	c6 07 bd 7b 	rldicr  r29,r29,32,31
    2264:	78 2b bd 7f 	or      r29,r29,r5
		if (pgd_none(pgd))
    2268:	00 00 bd 2f 	cmpdi   cr7,r29,0
    226c:	54 03 9e 41 	beq     cr7,25c0 <__get_user_pages_fast+0x500>

With fix:
---------
    2370:	20 00 61 eb 	ld      r27,32(r1)
		if (pgd_none(pgd))
    2374:	00 00 bd 2f 	cmpdi   cr7,r29,0
    2378:	a8 03 9e 41 	beq     cr7,2720 <__get_user_pages_fast+0x530>
			break;
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/pgtable-4k.h  |  6 +-
 arch/powerpc/include/asm/book3s/64/pgtable-64k.h |  6 +-
 arch/powerpc/include/asm/book3s/64/pgtable.h     | 99 +++++++++++++++++-------
 arch/powerpc/include/asm/pgtable-be-types.h      | 15 ++++
 4 files changed, 91 insertions(+), 35 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
index 71e9abced493..9db83b4e017d 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
@@ -11,7 +11,7 @@ static inline int pmd_huge(pmd_t pmd)
 	 * leaf pte for huge page
 	 */
 	if (radix_enabled())
-		return !!(pmd_val(pmd) & _PAGE_PTE);
+		return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
 	return 0;
 }
 
@@ -21,7 +21,7 @@ static inline int pud_huge(pud_t pud)
 	 * leaf pte for huge page
 	 */
 	if (radix_enabled())
-		return !!(pud_val(pud) & _PAGE_PTE);
+		return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
 	return 0;
 }
 
@@ -31,7 +31,7 @@ static inline int pgd_huge(pgd_t pgd)
 	 * leaf pte for huge page
 	 */
 	if (radix_enabled())
-		return !!(pgd_val(pgd) & _PAGE_PTE);
+		return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE));
 	return 0;
 }
 #define pgd_huge pgd_huge
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
index cb2d0a5fa3f8..0d2845b44763 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
@@ -15,7 +15,7 @@ static inline int pmd_huge(pmd_t pmd)
 	/*
 	 * leaf pte for huge page
 	 */
-	return !!(pmd_val(pmd) & _PAGE_PTE);
+	return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
 }
 
 static inline int pud_huge(pud_t pud)
@@ -23,7 +23,7 @@ static inline int pud_huge(pud_t pud)
 	/*
 	 * leaf pte for huge page
 	 */
-	return !!(pud_val(pud) & _PAGE_PTE);
+	return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
 }
 
 static inline int pgd_huge(pgd_t pgd)
@@ -31,7 +31,7 @@ static inline int pgd_huge(pgd_t pgd)
 	/*
 	 * leaf pte for huge page
 	 */
-	return !!(pgd_val(pgd) & _PAGE_PTE);
+	return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PTE));
 }
 #define pgd_huge pgd_huge
 
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 88a5ecaa157b..d3ab97e3c744 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -317,7 +317,7 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
 {
 	unsigned long old;
 
-	if ((pte_val(*ptep) & (_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
+	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
 		return 0;
 	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
 	return (old & _PAGE_ACCESSED) != 0;
@@ -335,8 +335,7 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pte_t *ptep)
 {
-
-	if ((pte_val(*ptep) & _PAGE_WRITE) == 0)
+	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
 		return;
 
 	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
@@ -345,7 +344,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	if ((pte_val(*ptep) & _PAGE_WRITE) == 0)
+	if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
 		return;
 
 	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
@@ -364,17 +363,35 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
 {
 	pte_update(mm, addr, ptep, ~0UL, 0, 0);
 }
-static inline int pte_write(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_WRITE);}
-static inline int pte_dirty(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_DIRTY); }
-static inline int pte_young(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_ACCESSED); }
-static inline int pte_special(pte_t pte)	{ return !!(pte_val(pte) & _PAGE_SPECIAL); }
+
+static inline int pte_write(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
+}
+
+static inline int pte_dirty(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DIRTY));
+}
+
+static inline int pte_young(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_ACCESSED));
+}
+
+static inline int pte_special(pte_t pte)
+{
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SPECIAL));
+}
+
 static inline pgprot_t pte_pgprot(pte_t pte)	{ return __pgprot(pte_val(pte) & PAGE_PROT_BITS); }
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline bool pte_soft_dirty(pte_t pte)
 {
-	return !!(pte_val(pte) & _PAGE_SOFT_DIRTY);
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SOFT_DIRTY));
 }
+
 static inline pte_t pte_mksoft_dirty(pte_t pte)
 {
 	return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY);
@@ -394,14 +411,14 @@ static inline pte_t pte_clear_soft_dirty(pte_t pte)
  */
 static inline int pte_protnone(pte_t pte)
 {
-	return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PRIVILEGED)) ==
-		(_PAGE_PRESENT | _PAGE_PRIVILEGED);
+	return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED)) ==
+		cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED);
 }
 #endif /* CONFIG_NUMA_BALANCING */
 
 static inline int pte_present(pte_t pte)
 {
-	return !!(pte_val(pte) & _PAGE_PRESENT);
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT));
 }
 /*
  * Conversion functions: convert a page and protection to a page entry,
@@ -473,7 +490,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 
 static inline bool pte_user(pte_t pte)
 {
-	return !(pte_val(pte) & _PAGE_PRIVILEGED);
+	return !(pte_raw(pte) & cpu_to_be64(_PAGE_PRIVILEGED));
 }
 
 /* Encode and de-code a swap entry */
@@ -516,10 +533,12 @@ static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
 {
 	return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY);
 }
+
 static inline bool pte_swp_soft_dirty(pte_t pte)
 {
-	return !!(pte_val(pte) & _PAGE_SWP_SOFT_DIRTY);
+	return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SWP_SOFT_DIRTY));
 }
+
 static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
 {
 	return __pte(pte_val(pte) & ~_PAGE_SWP_SOFT_DIRTY);
@@ -625,8 +644,16 @@ static inline void pmd_clear(pmd_t *pmdp)
 	*pmdp = __pmd(0);
 }
 
-#define pmd_none(pmd)		(!pmd_val(pmd))
-#define	pmd_present(pmd)	(!pmd_none(pmd))
+static inline int pmd_none(pmd_t pmd)
+{
+	return !pmd_raw(pmd);
+}
+
+static inline int pmd_present(pmd_t pmd)
+{
+
+	return !pmd_none(pmd);
+}
 
 static inline int pmd_bad(pmd_t pmd)
 {
@@ -645,19 +672,26 @@ static inline void pud_clear(pud_t *pudp)
 	*pudp = __pud(0);
 }
 
-#define pud_none(pud)		(!pud_val(pud))
-#define pud_present(pud)	(pud_val(pud) != 0)
+static inline int pud_none(pud_t pud)
+{
+	return !pud_raw(pud);
+}
+
+static inline int pud_present(pud_t pud)
+{
+	return !pud_none(pud);
+}
 
 extern struct page *pud_page(pud_t pud);
 extern struct page *pmd_page(pmd_t pmd);
 static inline pte_t pud_pte(pud_t pud)
 {
-	return __pte(pud_val(pud));
+	return __pte_raw(pud_raw(pud));
 }
 
 static inline pud_t pte_pud(pte_t pte)
 {
-	return __pud(pte_val(pte));
+	return __pud_raw(pte_raw(pte));
 }
 #define pud_write(pud)		pte_write(pud_pte(pud))
 
@@ -680,17 +714,24 @@ static inline void pgd_clear(pgd_t *pgdp)
 	*pgdp = __pgd(0);
 }
 
-#define pgd_none(pgd)		(!pgd_val(pgd))
-#define pgd_present(pgd)	(!pgd_none(pgd))
+static inline int pgd_none(pgd_t pgd)
+{
+	return !pgd_raw(pgd);
+}
+
+static inline int pgd_present(pgd_t pgd)
+{
+	return !pgd_none(pgd);
+}
 
 static inline pte_t pgd_pte(pgd_t pgd)
 {
-	return __pte(pgd_val(pgd));
+	return __pte_raw(pgd_raw(pgd));
 }
 
 static inline pgd_t pte_pgd(pte_t pte)
 {
-	return __pgd(pte_val(pte));
+	return __pgd_raw(pte_raw(pte));
 }
 
 static inline int pgd_bad(pgd_t pgd)
@@ -782,12 +823,12 @@ struct page *realmode_pfn_to_page(unsigned long pfn);
 
 static inline pte_t pmd_pte(pmd_t pmd)
 {
-	return __pte(pmd_val(pmd));
+	return __pte_raw(pmd_raw(pmd));
 }
 
 static inline pmd_t pte_pmd(pte_t pte)
 {
-	return __pmd(pte_val(pte));
+	return __pmd_raw(pte_raw(pte));
 }
 
 static inline pte_t *pmdp_ptep(pmd_t *pmd)
@@ -848,7 +889,7 @@ pmd_hugepage_update(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp,
 
 static inline int pmd_large(pmd_t pmd)
 {
-	return !!(pmd_val(pmd) & _PAGE_PTE);
+	return !!(pmd_raw(pmd) & cpu_to_be64(_PAGE_PTE));
 }
 
 static inline pmd_t pmd_mknotpresent(pmd_t pmd)
@@ -864,7 +905,7 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
 {
 	unsigned long old;
 
-	if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
+	if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_ACCESSED | H_PAGE_HASHPTE)) == 0)
 		return 0;
 	old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0);
 	return ((old & _PAGE_ACCESSED) != 0);
@@ -875,7 +916,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 				      pmd_t *pmdp)
 {
 
-	if ((pmd_val(*pmdp) & _PAGE_WRITE) == 0)
+	if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_WRITE)) == 0)
 		return;
 
 	pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
diff --git a/arch/powerpc/include/asm/pgtable-be-types.h b/arch/powerpc/include/asm/pgtable-be-types.h
index e2bf208605b1..49c0a5a80efa 100644
--- a/arch/powerpc/include/asm/pgtable-be-types.h
+++ b/arch/powerpc/include/asm/pgtable-be-types.h
@@ -6,6 +6,7 @@
 /* PTE level */
 typedef struct { __be64 pte; } pte_t;
 #define __pte(x)	((pte_t) { cpu_to_be64(x) })
+#define __pte_raw(x)	((pte_t) { (x) })
 static inline unsigned long pte_val(pte_t x)
 {
 	return be64_to_cpu(x.pte);
@@ -20,6 +21,7 @@ static inline __be64 pte_raw(pte_t x)
 #ifdef CONFIG_PPC64
 typedef struct { __be64 pmd; } pmd_t;
 #define __pmd(x)	((pmd_t) { cpu_to_be64(x) })
+#define __pmd_raw(x)	((pmd_t) { (x) })
 static inline unsigned long pmd_val(pmd_t x)
 {
 	return be64_to_cpu(x.pmd);
@@ -37,21 +39,34 @@ static inline __be64 pmd_raw(pmd_t x)
 #if defined(CONFIG_PPC_BOOK3S_64) || !defined(CONFIG_PPC_64K_PAGES)
 typedef struct { __be64 pud; } pud_t;
 #define __pud(x)	((pud_t) { cpu_to_be64(x) })
+#define __pud_raw(x)	((pud_t) { (x) })
 static inline unsigned long pud_val(pud_t x)
 {
 	return be64_to_cpu(x.pud);
 }
+
+static inline __be64 pud_raw(pud_t x)
+{
+	return x.pud;
+}
+
 #endif /* CONFIG_PPC_BOOK3S_64 || !CONFIG_PPC_64K_PAGES */
 #endif /* CONFIG_PPC64 */
 
 /* PGD level */
 typedef struct { __be64 pgd; } pgd_t;
 #define __pgd(x)	((pgd_t) { cpu_to_be64(x) })
+#define __pgd_raw(x)	((pgd_t) { (x) })
 static inline unsigned long pgd_val(pgd_t x)
 {
 	return be64_to_cpu(x.pgd);
 }
 
+static inline __be64 pgd_raw(pgd_t x)
+{
+	return x.pgd;
+}
+
 /* Page protection bits */
 typedef struct { unsigned long pgprot; } pgprot_t;
 #define pgprot_val(x)	((x).pgprot)
-- 
2.7.4

[PATCH V2 06/10] powerpc/mm: Compile out radix related functions if RADIX_MMU is disabled

[Aneesh Kumar K.V]

Currently we depend on mmu_has_feature to evalute to zero based on
MMU_FTRS_POSSIBLE mask. In a later patch, we want to update
radix_enabled() to runtime update the conditional operation to a jump
instruction. This implies we cannot depend on MMU_FTRS_POSSIBLE mask.
Instead define radix_enabled to return 0 if RADIX_MMU is not enabled.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/mmu.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h
index 5854263d4d6e..d4eda6420523 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu.h
@@ -23,7 +23,12 @@ struct mmu_psize_def {
 };
 extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
 
+#ifdef CONFIG_PPC_RADIX_MMU
 #define radix_enabled() mmu_has_feature(MMU_FTR_RADIX)
+#else
+#define radix_enabled() (0)
+#endif
+
 
 #endif /* __ASSEMBLY__ */
 
-- 
2.7.4

[PATCH V2 07/10] powerpc/hash: Use the correct ppp mask when updating hpte

[Aneesh Kumar K.V]

With commit: e58e87adc8bf9 ("powerpc/mm: Update _PAGE_KERNEL_RO") we
now use all the three PPP bits. The top bit is now used to have a
PPP value of 0b110 which will be mapped to kernel read only. When
updating the hpte entry use right mask such that we update the
63rd bit (top 'P' bit) too.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1 +
 arch/powerpc/mm/hash_native_64.c              | 8 ++++----
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 290157e8d5b2..74839f24f412 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -88,6 +88,7 @@
 #define HPTE_R_RPN_SHIFT	12
 #define HPTE_R_RPN		ASM_CONST(0x0ffffffffffff000)
 #define HPTE_R_PP		ASM_CONST(0x0000000000000003)
+#define HPTE_R_PPP		ASM_CONST(0x8000000000000003)
 #define HPTE_R_N		ASM_CONST(0x0000000000000004)
 #define HPTE_R_G		ASM_CONST(0x0000000000000008)
 #define HPTE_R_M		ASM_CONST(0x0000000000000010)
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index d873f6507f72..e37916cbc18d 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -316,8 +316,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 			DBG_LOW(" -> hit\n");
 			/* Update the HPTE */
 			hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
-						~(HPTE_R_PP | HPTE_R_N)) |
-					       (newpp & (HPTE_R_PP | HPTE_R_N |
+						~(HPTE_R_PPP | HPTE_R_N)) |
+					       (newpp & (HPTE_R_PPP | HPTE_R_N |
 							 HPTE_R_C)));
 		}
 		native_unlock_hpte(hptep);
@@ -385,8 +385,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 
 	/* Update the HPTE */
 	hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
-			~(HPTE_R_PP | HPTE_R_N)) |
-		(newpp & (HPTE_R_PP | HPTE_R_N)));
+				~(HPTE_R_PPP | HPTE_R_N)) |
+			       (newpp & (HPTE_R_PPP | HPTE_R_N)));
 	/*
 	 * Ensure it is out of the tlb too. Bolted entries base and
 	 * actual page size will be same.
-- 
2.7.4

[PATCH V2 08/10] powerpc/mm: Clear top 16 bits of va only on older cpus

[Aneesh Kumar K.V]

As per ISA, we need to do this only for architecture version 2.02 and
earlier. This continued to work even for 2.07. But let's not do this for
anything after 2.02

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/mmu.h   | 12 +++++++++---
 arch/powerpc/mm/hash_native_64.c |  6 ++++--
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index e53ebebff474..616575fcbcc7 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -24,6 +24,11 @@
 /*
  * This is individual features
  */
+/*
+ * We need to clear top 16bits of va (from the remaining 64 bits )in
+ * tlbie* instructions
+ */
+#define MMU_FTR_TLBIE_CROP_VA		ASM_CONST(0x00008000)
 
 /* Enable use of high BAT registers */
 #define MMU_FTR_USE_HIGH_BATS		ASM_CONST(0x00010000)
@@ -96,8 +101,9 @@
 /* MMU feature bit sets for various CPUs */
 #define MMU_FTRS_DEFAULT_HPTE_ARCH_V2	\
 	MMU_FTR_HPTE_TABLE | MMU_FTR_PPCAS_ARCH_V2
-#define MMU_FTRS_POWER4		MMU_FTRS_DEFAULT_HPTE_ARCH_V2
-#define MMU_FTRS_PPC970		MMU_FTRS_POWER4
+#define MMU_FTRS_POWER4		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
+				MMU_FTR_TLBIE_CROP_VA
+#define MMU_FTRS_PPC970		MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA
 #define MMU_FTRS_POWER5		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
 #define MMU_FTRS_POWER6		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
 #define MMU_FTRS_POWER7		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
@@ -124,7 +130,7 @@ enum {
 		MMU_FTR_USE_TLBRSRV | MMU_FTR_USE_PAIRED_MAS |
 		MMU_FTR_NO_SLBIE_B | MMU_FTR_16M_PAGE | MMU_FTR_TLBIEL |
 		MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE |
-		MMU_FTR_1T_SEGMENT |
+		MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA |
 #ifdef CONFIG_PPC_RADIX_MMU
 		MMU_FTR_RADIX |
 #endif
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index e37916cbc18d..4c6b68ef571c 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -64,7 +64,8 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 	 * Older versions of the architecture (2.02 and earler) require the
 	 * masking of the top 16 bits.
 	 */
-	va &= ~(0xffffULL << 48);
+	if (mmu_has_feature(MMU_FTR_TLBIE_CROP_VA))
+		va &= ~(0xffffULL << 48);
 
 	switch (psize) {
 	case MMU_PAGE_4K:
@@ -113,7 +114,8 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 	 * Older versions of the architecture (2.02 and earler) require the
 	 * masking of the top 16 bits.
 	 */
-	va &= ~(0xffffULL << 48);
+	if (mmu_has_feature(MMU_FTR_TLBIE_CROP_VA))
+		va &= ~(0xffffULL << 48);
 
 	switch (psize) {
 	case MMU_PAGE_4K:
-- 
2.7.4

[PATCH V2 09/10] powerpc/mm: Print formation regarding the the MMU mode

[Aneesh Kumar K.V]

This helps in easily identifying the MMU mode with which the kernel
is operating.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/mm/hash_utils_64.c | 3 ++-
 arch/powerpc/mm/pgtable-radix.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index b2740c67e172..bf9b0b80bbfc 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -720,7 +720,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table,
 	 * For now UPRT is 0 for us.
 	 */
 	partition_tb->patb1 = 0;
-	DBG("Partition table %p\n", partition_tb);
+	pr_info("Partition table %p\n", partition_tb);
 	/*
 	 * update partition table control register,
 	 * 64 K size.
@@ -924,6 +924,7 @@ void __init hash__early_init_mmu(void)
 	 */
 	htab_initialize();
 
+	pr_info("Initializing hash mmu with SLB\n");
 	/* Initialize SLB management */
 	slb_initialize();
 }
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 73aa402047ef..d6598cd1c3e6 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -185,7 +185,8 @@ static void __init radix_init_partition_table(void)
 	partition_tb = early_alloc_pgtable(1UL << PATB_SIZE_SHIFT);
 	partition_tb->patb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) |
 					  RADIX_PGD_INDEX_SIZE | PATB_HR);
-	printk("Partition table %p\n", partition_tb);
+	pr_info("Initializing Radix MMU\n");
+	pr_info("Partition table %p\n", partition_tb);
 
 	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 	/*
-- 
2.7.4

[PATCH V2 10/10] powerpc/mm/hash: Update SDR1 size encoding as documented in ISA 3.0

[Aneesh Kumar K.V]

ISA 3.0 document hash table size in bytes = 2^(HTABSIZE + 18)

No functionality change by this patch.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/mm/hash_utils_64.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index bf9b0b80bbfc..7cce2f6169fa 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -695,10 +695,9 @@ int remove_section_mapping(unsigned long start, unsigned long end)
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 static void __init hash_init_partition_table(phys_addr_t hash_table,
-					     unsigned long pteg_count)
+					     unsigned long htab_size)
 {
 	unsigned long ps_field;
-	unsigned long htab_size;
 	unsigned long patb_size = 1UL << PATB_SIZE_SHIFT;
 
 	/*
@@ -706,7 +705,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table,
 	 * We can ignore that for lpid 0
 	 */
 	ps_field = 0;
-	htab_size =  __ilog2(pteg_count) - 11;
+	htab_size =  __ilog2(htab_size) - 18;
 
 	BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 24), "Partition table size too large.");
 	partition_tb = __va(memblock_alloc_base(patb_size, patb_size,
@@ -792,7 +791,7 @@ static void __init htab_initialize(void)
 		htab_address = __va(table);
 
 		/* htab absolute addr + encoded htabsize */
-		_SDR1 = table + __ilog2(pteg_count) - 11;
+		_SDR1 = table + __ilog2(htab_size_bytes) - 18;
 
 		/* Initialize the HPT with no entries */
 		memset((void *)table, 0, htab_size_bytes);
@@ -801,7 +800,7 @@ static void __init htab_initialize(void)
 			/* Set SDR1 */
 			mtspr(SPRN_SDR1, _SDR1);
 		else
-			hash_init_partition_table(table, pteg_count);
+			hash_init_partition_table(table, htab_size_bytes);
 	}
 
 	prot = pgprot_val(PAGE_KERNEL);
-- 
2.7.4

Re: [PATCH V2 08/10] powerpc/mm: Clear top 16 bits of va only on older cpus

[Aneesh Kumar K.V]

"Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> writes:

> As per ISA, we need to do this only for architecture version 2.02 and
> earlier. This continued to work even for 2.07. But let's not do this for
> anything after 2.02
>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
> ---
>  arch/powerpc/include/asm/mmu.h   | 12 +++++++++---
>  arch/powerpc/mm/hash_native_64.c |  6 ++++--
>  2 files changed, 13 insertions(+), 5 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
> index e53ebebff474..616575fcbcc7 100644
> --- a/arch/powerpc/include/asm/mmu.h
> +++ b/arch/powerpc/include/asm/mmu.h
> @@ -24,6 +24,11 @@
>  /*
>   * This is individual features
>   */
> +/*
> + * We need to clear top 16bits of va (from the remaining 64 bits )in
> + * tlbie* instructions
> + */
> +#define MMU_FTR_TLBIE_CROP_VA		ASM_CONST(0x00008000)
>
>  /* Enable use of high BAT registers */
>  #define MMU_FTR_USE_HIGH_BATS		ASM_CONST(0x00010000)
> @@ -96,8 +101,9 @@
>  /* MMU feature bit sets for various CPUs */
>  #define MMU_FTRS_DEFAULT_HPTE_ARCH_V2	\
>  	MMU_FTR_HPTE_TABLE | MMU_FTR_PPCAS_ARCH_V2
> -#define MMU_FTRS_POWER4		MMU_FTRS_DEFAULT_HPTE_ARCH_V2
> -#define MMU_FTRS_PPC970		MMU_FTRS_POWER4
> +#define MMU_FTRS_POWER4		MMU_FTRS_DEFAULT_HPTE_ARCH_V2 | \
> +				MMU_FTR_TLBIE_CROP_VA
> +#define MMU_FTRS_PPC970		MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA
>  #define MMU_FTRS_POWER5		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
>  #define MMU_FTRS_POWER6		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE
>  #define MMU_FTRS_POWER7		MMU_FTRS_POWER4 | MMU_FTR_LOCKLESS_TLBIE


Updated patch below. MMU_FTRS_POWER4 is inherited by others, hence don't
update that.

>From 4ed66fd24dc4f976969cc34aca8df2ddbc69fe61 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Sat, 4 Jun 2016 19:58:26 +0530
Subject: [PATCH] powerpc/mm: Clear top 16 bits of va only on older cpus

As per ISA, we need to do this only for architecture version 2.02 and
earlier. This continued to work even for 2.07. But let's not do this for
anything after 2.02

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 arch/powerpc/include/asm/mmu.h   |  7 ++++++-
 arch/powerpc/kernel/cputable.c   | 14 +++++++-------
 arch/powerpc/mm/hash_native_64.c |  6 ++++--
 3 files changed, 17 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index e53ebebff474..fa314b1d667e 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -24,6 +24,11 @@
 /*
  * This is individual features
  */
+/*
+ * We need to clear top 16bits of va (from the remaining 64 bits )in
+ * tlbie* instructions
+ */
+#define MMU_FTR_TLBIE_CROP_VA		ASM_CONST(0x00008000)
 
 /* Enable use of high BAT registers */
 #define MMU_FTR_USE_HIGH_BATS		ASM_CONST(0x00010000)
@@ -124,7 +129,7 @@ enum {
 		MMU_FTR_USE_TLBRSRV | MMU_FTR_USE_PAIRED_MAS |
 		MMU_FTR_NO_SLBIE_B | MMU_FTR_16M_PAGE | MMU_FTR_TLBIEL |
 		MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE |
-		MMU_FTR_1T_SEGMENT |
+		MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA |
 #ifdef CONFIG_PPC_RADIX_MMU
 		MMU_FTR_RADIX |
 #endif
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index eeeacf6235a3..d8a0f7ca74e1 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -137,7 +137,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER4 (gp)",
 		.cpu_features		= CPU_FTRS_POWER4,
 		.cpu_user_features	= COMMON_USER_POWER4,
-		.mmu_features		= MMU_FTRS_POWER4,
+		.mmu_features		= MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -152,7 +152,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER4+ (gq)",
 		.cpu_features		= CPU_FTRS_POWER4,
 		.cpu_user_features	= COMMON_USER_POWER4,
-		.mmu_features		= MMU_FTRS_POWER4,
+		.mmu_features		= MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -168,7 +168,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
-		.mmu_features		= MMU_FTRS_PPC970,
+		.mmu_features		= MMU_FTRS_PPC970 | MMU_FTR_TLBIE_CROP_VA,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -186,7 +186,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
-		.mmu_features		= MMU_FTRS_PPC970,
+		.mmu_features		= MMU_FTRS_PPC970 | MMU_FTR_TLBIE_CROP_VA,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -204,7 +204,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
-		.mmu_features		= MMU_FTRS_PPC970,
+		.mmu_features		= MMU_FTRS_PPC970 | MMU_FTR_TLBIE_CROP_VA,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -222,7 +222,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
-		.mmu_features		= MMU_FTRS_PPC970,
+		.mmu_features		= MMU_FTRS_PPC970 | MMU_FTR_TLBIE_CROP_VA,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
@@ -240,7 +240,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_features		= CPU_FTRS_PPC970,
 		.cpu_user_features	= COMMON_USER_POWER4 |
 			PPC_FEATURE_HAS_ALTIVEC_COMP,
-		.mmu_features		= MMU_FTRS_PPC970,
+		.mmu_features		= MMU_FTRS_PPC970 | MMU_FTR_TLBIE_CROP_VA,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.num_pmcs		= 8,
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 80dd344726f3..4c6d4c736ba4 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -64,7 +64,8 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 	 * Older versions of the architecture (2.02 and earler) require the
 	 * masking of the top 16 bits.
 	 */
-	va &= ~(0xffffULL << 48);
+	if (mmu_has_feature(MMU_FTR_TLBIE_CROP_VA))
+		va &= ~(0xffffULL << 48);
 
 	switch (psize) {
 	case MMU_PAGE_4K:
@@ -113,7 +114,8 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 	 * Older versions of the architecture (2.02 and earler) require the
 	 * masking of the top 16 bits.
 	 */
-	va &= ~(0xffffULL << 48);
+	if (mmu_has_feature(MMU_FTR_TLBIE_CROP_VA))
+		va &= ~(0xffffULL << 48);
 
 	switch (psize) {
 	case MMU_PAGE_4K:
-- 
2.7.4

Re: [V2, 08/10] powerpc/mm: Clear top 16 bits of va only on older cpus

[Michael Ellerman]

On Thu, 2016-09-06 at 06:19:15 UTC, "Aneesh Kumar K.V" wrote:
> Updated patch below. MMU_FTRS_POWER4 is inherited by others, hence don't
> update that.
> 
> >From 4ed66fd24dc4f976969cc34aca8df2ddbc69fe61 Mon Sep 17 00:00:00 2001
> From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
> Date: Sat, 4 Jun 2016 19:58:26 +0530
> Subject: [PATCH] powerpc/mm: Clear top 16 bits of va only on older cpus
> 
> As per ISA, we need to do this only for architecture version 2.02 and
> earlier. This continued to work even for 2.07. But let's not do this for
> anything after 2.02

What are the practical effects of this?

> diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
> index e53ebebff474..fa314b1d667e 100644
> --- a/arch/powerpc/include/asm/mmu.h
> +++ b/arch/powerpc/include/asm/mmu.h
> @@ -24,6 +24,11 @@
>  /*
>   * This is individual features
>   */
> +/*
> + * We need to clear top 16bits of va (from the remaining 64 bits )in
> + * tlbie* instructions
> + */
> +#define MMU_FTR_TLBIE_CROP_VA		ASM_CONST(0x00008000)
>  
>  /* Enable use of high BAT registers */
>  #define MMU_FTR_USE_HIGH_BATS		ASM_CONST(0x00010000)
> @@ -124,7 +129,7 @@ enum {
>  		MMU_FTR_USE_TLBRSRV | MMU_FTR_USE_PAIRED_MAS |
>  		MMU_FTR_NO_SLBIE_B | MMU_FTR_16M_PAGE | MMU_FTR_TLBIEL |
>  		MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE |
> -		MMU_FTR_1T_SEGMENT |
> +		MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA |
>  #ifdef CONFIG_PPC_RADIX_MMU
>  		MMU_FTR_RADIX |
>  #endif
> diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
> index eeeacf6235a3..d8a0f7ca74e1 100644
> --- a/arch/powerpc/kernel/cputable.c
> +++ b/arch/powerpc/kernel/cputable.c
> @@ -137,7 +137,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
>  		.cpu_name		= "POWER4 (gp)",
>  		.cpu_features		= CPU_FTRS_POWER4,
>  		.cpu_user_features	= COMMON_USER_POWER4,
> -		.mmu_features		= MMU_FTRS_POWER4,
> +		.mmu_features		= MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA,
>  		.icache_bsize		= 128,
>  		.dcache_bsize		= 128,
>  		.num_pmcs		= 8,
> @@ -152,7 +152,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
>  		.cpu_name		= "POWER4+ (gq)",
>  		.cpu_features		= CPU_FTRS_POWER4,
>  		.cpu_user_features	= COMMON_USER_POWER4,
> -		.mmu_features		= MMU_FTRS_POWER4,
> +		.mmu_features		= MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA,
>  		.icache_bsize		= 128,
>  		.dcache_bsize		= 128,
>  		.num_pmcs		= 8,
> @@ -168,7 +168,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
>  		.cpu_features		= CPU_FTRS_PPC970,
>  		.cpu_user_features	= COMMON_USER_POWER4 |
>  			PPC_FEATURE_HAS_ALTIVEC_COMP,
> -		.mmu_features		= MMU_FTRS_PPC970,
> +		.mmu_features		= MMU_FTRS_PPC970 | MMU_FTR_TLBIE_CROP_VA,

Please add it to MMU_FTRS_PPC970, rather than at every usage.

cheers

Re: [V2, 08/10] powerpc/mm: Clear top 16 bits of va only on older cpus

[Aneesh Kumar K.V]

Michael Ellerman <mpe@ellerman.id.au> writes:

> On Thu, 2016-09-06 at 06:19:15 UTC, "Aneesh Kumar K.V" wrote:
>> Updated patch below. MMU_FTRS_POWER4 is inherited by others, hence don't
>> update that.
>> 
>> >From 4ed66fd24dc4f976969cc34aca8df2ddbc69fe61 Mon Sep 17 00:00:00 2001
>> From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
>> Date: Sat, 4 Jun 2016 19:58:26 +0530
>> Subject: [PATCH] powerpc/mm: Clear top 16 bits of va only on older cpus
>> 
>> As per ISA, we need to do this only for architecture version 2.02 and
>> earlier. This continued to work even for 2.07. But let's not do this for
>> anything after 2.02
>
> What are the practical effects of this?


For ISA 3.0 we require these top bits to be not cleared. I have updated
the commit message to reflect that.

>
>> diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
>> index e53ebebff474..fa314b1d667e 100644
>> --- a/arch/powerpc/include/asm/mmu.h
>> +++ b/arch/powerpc/include/asm/mmu.h
>> @@ -24,6 +24,11 @@
>>  /*
>>   * This is individual features
>>   */
>> +/*
>> + * We need to clear top 16bits of va (from the remaining 64 bits )in
>> + * tlbie* instructions
>> + */
>> +#define MMU_FTR_TLBIE_CROP_VA		ASM_CONST(0x00008000)
>>  
>>  /* Enable use of high BAT registers */
>>  #define MMU_FTR_USE_HIGH_BATS		ASM_CONST(0x00010000)
>> @@ -124,7 +129,7 @@ enum {
>>  		MMU_FTR_USE_TLBRSRV | MMU_FTR_USE_PAIRED_MAS |
>>  		MMU_FTR_NO_SLBIE_B | MMU_FTR_16M_PAGE | MMU_FTR_TLBIEL |
>>  		MMU_FTR_LOCKLESS_TLBIE | MMU_FTR_CI_LARGE_PAGE |
>> -		MMU_FTR_1T_SEGMENT |
>> +		MMU_FTR_1T_SEGMENT | MMU_FTR_TLBIE_CROP_VA |
>>  #ifdef CONFIG_PPC_RADIX_MMU
>>  		MMU_FTR_RADIX |
>>  #endif
>> diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
>> index eeeacf6235a3..d8a0f7ca74e1 100644
>> --- a/arch/powerpc/kernel/cputable.c
>> +++ b/arch/powerpc/kernel/cputable.c
>> @@ -137,7 +137,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
>>  		.cpu_name		= "POWER4 (gp)",
>>  		.cpu_features		= CPU_FTRS_POWER4,
>>  		.cpu_user_features	= COMMON_USER_POWER4,
>> -		.mmu_features		= MMU_FTRS_POWER4,
>> +		.mmu_features		= MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA,
>>  		.icache_bsize		= 128,
>>  		.dcache_bsize		= 128,
>>  		.num_pmcs		= 8,
>> @@ -152,7 +152,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
>>  		.cpu_name		= "POWER4+ (gq)",
>>  		.cpu_features		= CPU_FTRS_POWER4,
>>  		.cpu_user_features	= COMMON_USER_POWER4,
>> -		.mmu_features		= MMU_FTRS_POWER4,
>> +		.mmu_features		= MMU_FTRS_POWER4 | MMU_FTR_TLBIE_CROP_VA,
>>  		.icache_bsize		= 128,
>>  		.dcache_bsize		= 128,
>>  		.num_pmcs		= 8,
>> @@ -168,7 +168,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
>>  		.cpu_features		= CPU_FTRS_PPC970,
>>  		.cpu_user_features	= COMMON_USER_POWER4 |
>>  			PPC_FEATURE_HAS_ALTIVEC_COMP,
>> -		.mmu_features		= MMU_FTRS_PPC970,
>> +		.mmu_features		= MMU_FTRS_PPC970 | MMU_FTR_TLBIE_CROP_VA,
>
> Please add it to MMU_FTRS_PPC970, rather than at every usage.
>

Done

-aneesh

Re: [V2, 02/10] powerpc/mm/radix: Update to tlb functions ric argument

[Michael Ellerman]

On Wed, 2016-08-06 at 14:25:50 UTC, "Aneesh Kumar K.V" wrote:
> Radix invalidate control (RIC) is used to control which cache to flush
> using tlb instructions. When doing a PID flush, we currently flush
> everything including page walk cache. For address range flush, we flush
> only the TLB. In the later patch, we add support for flushing only
> page walk cache.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

Applied to powerpc fixes, thanks.

https://git.kernel.org/powerpc/c/36194812a4063dd2a72070aec3

cheers

Re: [V2, 03/10] powerpc/mm/radix: Flush page walk cache when freeing page table

[Michael Ellerman]

On Wed, 2016-08-06 at 14:25:51 UTC, "Aneesh Kumar K.V" wrote:
> Even though a tlb_flush() does a flush with invalidate all cache,
> we can end up doing an RCU page table free before calling tlb_flush().
> That means we can have page walk cache entries even after we free the
> page table pages. This can result in us doing wrong page table walk.
> 
> Avoid this by doing pwc flush on every page table free. We can't batch
> the pwc flush, because the rcu call back function where we free the
> page table pages doesn't have information of the mmu gather. Thus we
> have to do a pwc on every page table page freed.
> 
> Note: I also removed the dummy tlb_flush_pgtable call functions for
> hash 32.
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

Applied to powerpc fixes, thanks.

https://git.kernel.org/powerpc/c/a145abf12c9f7d30d8c330c9d8

cheers

Re: [V2, 07/10] powerpc/hash: Use the correct ppp mask when updating hpte

[Michael Ellerman]

On Wed, 2016-08-06 at 14:25:55 UTC, "Aneesh Kumar K.V" wrote:
> With commit: e58e87adc8bf9 ("powerpc/mm: Update _PAGE_KERNEL_RO") we
> now use all the three PPP bits. The top bit is now used to have a
> PPP value of 0b110 which will be mapped to kernel read only. When
> updating the hpte entry use right mask such that we update the
> 63rd bit (top 'P' bit) too.
> 
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

Applied to powerpc fixes, thanks.

https://git.kernel.org/powerpc/c/8550e2fa34f077c8a87cf1ba24

cheers