* [PATCH -V8 07/11] arch/powerpc: Make some of the PGTABLE_RANGE dependency explicit
From: Aneesh Kumar K.V @ 2012-09-06 15:29 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1346945351-7672-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
slice array size and slice mask size depend on PGTABLE_RANGE. We
can't directly include pgtable.h in these header because there is
a circular dependency. So add compile time check for these values.
Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/mmu-hash64.h | 13 ++++++++-----
arch/powerpc/include/asm/page_64.h | 16 ++++++++++++----
arch/powerpc/include/asm/pgtable-ppc64.h | 8 ++++++++
3 files changed, 28 insertions(+), 9 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 7cbd541..cbd7edb 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -416,6 +416,13 @@ extern void slb_set_size(u16 size);
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 */
+#if 0 /* We can't directly include pgtable.h hence this hack */
+#define SLICE_ARRAY_SIZE (PGTABLE_RANGE >> 41)
+#else
+/* Right now we only support 64TB */
+#define SLICE_ARRAY_SIZE 32
+#endif
#ifndef __ASSEMBLY__
@@ -460,11 +467,7 @@ typedef struct {
#ifdef CONFIG_PPC_MM_SLICES
u64 low_slices_psize; /* SLB page size encodings */
- /*
- * Right now we support 64TB and 4 bits for each
- * 1TB slice we need 32 bytes for 64TB.
- */
- unsigned char high_slices_psize[32]; /* 4 bits per slice for now */
+ unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
#else
u16 sllp; /* SLB page size encoding */
#endif
diff --git a/arch/powerpc/include/asm/page_64.h b/arch/powerpc/include/asm/page_64.h
index 6c9bef4..b55beb4 100644
--- a/arch/powerpc/include/asm/page_64.h
+++ b/arch/powerpc/include/asm/page_64.h
@@ -78,14 +78,22 @@ extern u64 ppc64_pft_size;
#define GET_LOW_SLICE_INDEX(addr) ((addr) >> SLICE_LOW_SHIFT)
#define GET_HIGH_SLICE_INDEX(addr) ((addr) >> SLICE_HIGH_SHIFT)
+/* 1 bit per slice and we have one slice per 1TB */
+#if 0 /* We can't directly include pgtable.h hence this hack */
+#define SLICE_MASK_SIZE (PGTABLE_RANGE >> 43)
+#else
+/*
+ * Right now we support only 64TB.
+ * IF we change this we will have to change the type
+ * of high_slices
+ */
+#define SLICE_MASK_SIZE 8
+#endif
+
#ifndef __ASSEMBLY__
struct slice_mask {
u16 low_slices;
- /*
- * This should be derived out of PGTABLE_RANGE. For the current
- * max 64TB, u64 should be ok.
- */
u64 high_slices;
};
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 8af1cf2..dea953f 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -32,6 +32,14 @@
#endif
#endif
+#if (PGTABLE_RANGE >> 41) > SLICE_ARRAY_SIZE
+#error PGTABLE_RANGE exceeds SLICE_ARRAY_SIZE
+#endif
+
+#if (PGTABLE_RANGE >> 43) > SLICE_MASK_SIZE
+#error PGTABLE_RANGE exceeds slice_mask high_slices size
+#endif
+
/*
* Define the address range of the kernel non-linear virtual area
*/
--
1.7.10
^ permalink raw reply related
* [PATCH -V8 11/11] arch/powerpc: Update VSID allocation documentation
From: Aneesh Kumar K.V @ 2012-09-06 15:29 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1346945351-7672-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
This update the proto-VSID and VSID scramble related information
to be more generic by using names instead of current values.
Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/mmu-hash64.h | 40 ++++++++++++++-------------------
arch/powerpc/mm/mmu_context_hash64.c | 8 ++++---
2 files changed, 22 insertions(+), 26 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index de9cfed..428f23e 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -324,51 +324,45 @@ extern void slb_set_size(u16 size);
#endif /* __ASSEMBLY__ */
/*
- * VSID allocation
+ * VSID allocation (256MB segment)
*
- * We first generate a 36-bit "proto-VSID". For kernel addresses this
- * is equal to the ESID, for user addresses it is:
- * (context << 15) | (esid & 0x7fff)
+ * We first generate a 38-bit "proto-VSID". For kernel addresses this
+ * is equal to the ESID | 1 << 37, for user addresses it is:
+ * (context << USER_ESID_BITS) | (esid & ((1U << USER_ESID_BITS) - 1)
*
- * The two forms are distinguishable because the top bit is 0 for user
- * addresses, whereas the top two bits are 1 for kernel addresses.
- * Proto-VSIDs with the top two bits equal to 0b10 are reserved for
- * now.
+ * This splits the proto-VSID into the below range
+ * 0 - (2^(CONTEXT_BITS + USER_ESID_BITS) - 1) : User proto-VSID range
+ * 2^(CONTEXT_BITS + USER_ESID_BITS) - 2^(VSID_BITS) : Kernel proto-VSID range
+ *
+ * We also have CONTEXT_BITS + USER_ESID_BITS = VSID_BITS - 1
+ * That is, we assign half of the space to user processes and half
+ * to the kernel.
*
* The proto-VSIDs are then scrambled into real VSIDs with the
* multiplicative hash:
*
* VSID = (proto-VSID * VSID_MULTIPLIER) % VSID_MODULUS
- * where VSID_MULTIPLIER = 268435399 = 0xFFFFFC7
- * VSID_MODULUS = 2^36-1 = 0xFFFFFFFFF
*
- * This scramble is only well defined for proto-VSIDs below
- * 0xFFFFFFFFF, so both proto-VSID and actual VSID 0xFFFFFFFFF are
- * reserved. VSID_MULTIPLIER is prime, so in particular it is
+ * VSID_MULTIPLIER is prime, so in particular it is
* co-prime to VSID_MODULUS, making this a 1:1 scrambling function.
* Because the modulus is 2^n-1 we can compute it efficiently without
* a divide or extra multiply (see below).
*
* This scheme has several advantages over older methods:
*
- * - We have VSIDs allocated for every kernel address
+ * - We have VSIDs allocated for every kernel address
* (i.e. everything above 0xC000000000000000), except the very top
* segment, which simplifies several things.
*
- * - We allow for 16 significant bits of ESID and 19 bits of
- * context for user addresses. i.e. 16T (44 bits) of address space for
- * up to half a million contexts.
+ * - We allow for USER_ESID_BITS significant bits of ESID and
+ * CONTEXT_BITS bits of context for user addresses.
+ * i.e. 64T (46 bits) of address space for up to half a million contexts.
*
- * - The scramble function gives robust scattering in the hash
+ * - The scramble function gives robust scattering in the hash
* table (at least based on some initial results). The previous
* method was more susceptible to pathological cases giving excessive
* hash collisions.
*/
-/*
- * WARNING - If you change these you must make sure the asm
- * implementations in slb_allocate (slb_low.S), do_stab_bolted
- * (head.S) and ASM_VSID_SCRAMBLE (below) are changed accordingly.
- */
/*
* This should be computed such that protovosid * vsid_mulitplier
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index daa076c..40bc5b0 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -30,9 +30,11 @@ static DEFINE_SPINLOCK(mmu_context_lock);
static DEFINE_IDA(mmu_context_ida);
/*
- * The proto-VSID space has 2^35 - 1 segments available for user mappings.
- * Each segment contains 2^28 bytes. Each context maps 2^44 bytes,
- * so we can support 2^19-1 contexts (19 == 35 + 28 - 44).
+ * 256MB segment
+ * The proto-VSID space has 2^(CONTEX_BITS + USER_ESID_BITS) - 1 segments
+ * available for user mappings. 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).
*/
#define MAX_CONTEXT ((1UL << CONTEXT_BITS) - 1)
--
1.7.10
^ permalink raw reply related
* [PATCH -V8 10/11] arch/powerpc: Add 64TB support
From: Aneesh Kumar K.V @ 2012-09-06 15:29 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1346945351-7672-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Increase max addressable range to 64TB. This is not tested on
real hardware yet.
Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/mmu-hash64.h | 42 ++++++++++++++++++++------
arch/powerpc/include/asm/pgtable-ppc64-4k.h | 2 +-
arch/powerpc/include/asm/pgtable-ppc64-64k.h | 2 +-
arch/powerpc/include/asm/processor.h | 4 +--
arch/powerpc/include/asm/sparsemem.h | 4 +--
arch/powerpc/kernel/exceptions-64s.S | 4 ++-
arch/powerpc/mm/slb_low.S | 12 ++++++++
7 files changed, 54 insertions(+), 16 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index cbd7edb..de9cfed 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -370,17 +370,21 @@ extern void slb_set_size(u16 size);
* (head.S) and ASM_VSID_SCRAMBLE (below) are changed accordingly.
*/
-#define VSID_MULTIPLIER_256M ASM_CONST(200730139) /* 28-bit prime */
-#define VSID_BITS_256M 36
+/*
+ * This should be computed such that protovosid * vsid_mulitplier
+ * doesn't overflow 64 bits. It should also be co-prime to vsid_modulus
+ */
+#define VSID_MULTIPLIER_256M ASM_CONST(12538073) /* 24-bit prime */
+#define VSID_BITS_256M 38
#define VSID_MODULUS_256M ((1UL<<VSID_BITS_256M)-1)
#define VSID_MULTIPLIER_1T ASM_CONST(12538073) /* 24-bit prime */
-#define VSID_BITS_1T 24
+#define VSID_BITS_1T 26
#define VSID_MODULUS_1T ((1UL<<VSID_BITS_1T)-1)
#define CONTEXT_BITS 19
-#define USER_ESID_BITS 16
-#define USER_ESID_BITS_1T 4
+#define USER_ESID_BITS 18
+#define USER_ESID_BITS_1T 6
#define USER_VSID_RANGE (1UL << (USER_ESID_BITS + SID_SHIFT))
@@ -503,12 +507,32 @@ typedef struct {
})
#endif /* 1 */
-/* This is only valid for addresses >= PAGE_OFFSET */
+/*
+ * This is only valid for addresses >= PAGE_OFFSET
+ * The proto-VSID space is divided into two class
+ * User: 0 to 2^(CONTEXT_BITS + USER_ESID_BITS) -1
+ * kernel: 2^(CONTEXT_BITS + USER_ESID_BITS) to 2^(VSID_BITS) - 1
+ *
+ * With KERNEL_START at 0xc000000000000000, the proto vsid for
+ * the kernel ends up with 0xc00000000 (36 bits). With 64TB
+ * support we need to have kernel proto-VSID in the
+ * [2^37 to 2^38 - 1] range due to the increased USER_ESID_BITS.
+ */
static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
{
- if (ssize == MMU_SEGSIZE_256M)
- return vsid_scramble(ea >> SID_SHIFT, 256M);
- return vsid_scramble(ea >> SID_SHIFT_1T, 1T);
+ unsigned long proto_vsid;
+ /*
+ * We need to make sure proto_vsid for the kernel is
+ * >= 2^(CONTEXT_BITS + USER_ESID_BITS[_1T])
+ */
+ if (ssize == MMU_SEGSIZE_256M) {
+ proto_vsid = ea >> SID_SHIFT;
+ proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS));
+ return vsid_scramble(proto_vsid, 256M);
+ }
+ proto_vsid = ea >> SID_SHIFT_1T;
+ proto_vsid |= (1UL << (CONTEXT_BITS + USER_ESID_BITS_1T));
+ return vsid_scramble(proto_vsid, 1T);
}
/* Returns the segment size indicator for a user address */
diff --git a/arch/powerpc/include/asm/pgtable-ppc64-4k.h b/arch/powerpc/include/asm/pgtable-ppc64-4k.h
index 6eefdcf..b3eccf2 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64-4k.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64-4k.h
@@ -7,7 +7,7 @@
*/
#define PTE_INDEX_SIZE 9
#define PMD_INDEX_SIZE 7
-#define PUD_INDEX_SIZE 7
+#define PUD_INDEX_SIZE 9
#define PGD_INDEX_SIZE 9
#ifndef __ASSEMBLY__
diff --git a/arch/powerpc/include/asm/pgtable-ppc64-64k.h b/arch/powerpc/include/asm/pgtable-ppc64-64k.h
index 90533dd..be4e287 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64-64k.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64-64k.h
@@ -7,7 +7,7 @@
#define PTE_INDEX_SIZE 12
#define PMD_INDEX_SIZE 12
#define PUD_INDEX_SIZE 0
-#define PGD_INDEX_SIZE 4
+#define PGD_INDEX_SIZE 6
#ifndef __ASSEMBLY__
#define PTE_TABLE_SIZE (sizeof(real_pte_t) << PTE_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 53b6dfa..00bda2f 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -97,8 +97,8 @@ extern struct task_struct *last_task_used_spe;
#endif
#ifdef CONFIG_PPC64
-/* 64-bit user address space is 44-bits (16TB user VM) */
-#define TASK_SIZE_USER64 (0x0000100000000000UL)
+/* 64-bit user address space is 46-bits (64TB user VM) */
+#define TASK_SIZE_USER64 (0x0000400000000000UL)
/*
* 32-bit user address space is 4GB - 1 page
diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h
index 0c5fa31..f6fc0ee 100644
--- a/arch/powerpc/include/asm/sparsemem.h
+++ b/arch/powerpc/include/asm/sparsemem.h
@@ -10,8 +10,8 @@
*/
#define SECTION_SIZE_BITS 24
-#define MAX_PHYSADDR_BITS 44
-#define MAX_PHYSMEM_BITS 44
+#define MAX_PHYSADDR_BITS 46
+#define MAX_PHYSMEM_BITS 46
#endif /* CONFIG_SPARSEMEM */
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e894515..d980818 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -959,7 +959,9 @@ _GLOBAL(do_stab_bolted)
rldimi r10,r11,7,52 /* r10 = first ste of the group */
/* Calculate VSID */
- /* This is a kernel address, so protovsid = ESID */
+ /* This is a kernel address, so protovsid = ESID | 1 << 37 */
+ li r9,0x1
+ rldimi r11,r9,(CONTEXT_BITS + USER_ESID_BITS),0
ASM_VSID_SCRAMBLE(r11, r9, 256M)
rldic r9,r11,12,16 /* r9 = vsid << 12 */
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index f6a2625..1a16ca2 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -56,6 +56,12 @@ _GLOBAL(slb_allocate_realmode)
*/
_GLOBAL(slb_miss_kernel_load_linear)
li r11,0
+ li r9,0x1
+ /*
+ * for 1T we shift 12 bits more. slb_finish_load_1T will do
+ * the necessary adjustment
+ */
+ rldimi r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0
BEGIN_FTR_SECTION
b slb_finish_load
END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
@@ -85,6 +91,12 @@ _GLOBAL(slb_miss_kernel_load_vmemmap)
_GLOBAL(slb_miss_kernel_load_io)
li r11,0
6:
+ li r9,0x1
+ /*
+ * for 1T we shift 12 bits more. slb_finish_load_1T will do
+ * the necessary adjustment
+ */
+ rldimi r10,r9,(CONTEXT_BITS + USER_ESID_BITS),0
BEGIN_FTR_SECTION
b slb_finish_load
END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
--
1.7.10
^ permalink raw reply related
* [PATCH -V8 02/11] arch/powerpc: Use hpt_va to compute virtual address
From: Aneesh Kumar K.V @ 2012-09-06 15:29 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1346945351-7672-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Don't open code the same
Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/platforms/cell/beat_htab.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index 943c9d3..b83077e 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -259,7 +259,7 @@ static void beat_lpar_hpte_updateboltedpp(unsigned long newpp,
u64 dummy0, dummy1;
vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M);
- va = (vsid << 28) | (ea & 0x0fffffff);
+ va = hpt_va(ea, vsid, MMU_SEGSIZE_256M);
raw_spin_lock(&beat_htab_lock);
slot = beat_lpar_hpte_find(va, psize);
--
1.7.10
^ permalink raw reply related
* [PATCH -V8 08/11] arch/powerpc: Use the required number of VSID bits in slbmte
From: Aneesh Kumar K.V @ 2012-09-06 15:29 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1346945351-7672-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
ASM_VSID_SCRAMBLE can leave non-zero bits in the high 28 bits of the result
for 256MB segment (40 bits for 1T segment). Properly mask them before using
the values in slbmte
Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/mm/slb_low.S | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index e132dc6..3b75f19 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -223,7 +223,11 @@ _GLOBAL(slb_allocate_user)
*/
slb_finish_load:
ASM_VSID_SCRAMBLE(r10,r9,256M)
- rldimi r11,r10,SLB_VSID_SHIFT,16 /* combine VSID and flags */
+ /*
+ * bits above VSID_BITS_256M need to be ignored from r10
+ * also combine VSID and flags
+ */
+ rldimi r11,r10,SLB_VSID_SHIFT,(64 - (SLB_VSID_SHIFT + VSID_BITS_256M))
/* r3 = EA, r11 = VSID data */
/*
@@ -287,7 +291,11 @@ _GLOBAL(slb_compare_rr_to_size)
slb_finish_load_1T:
srdi r10,r10,40-28 /* get 1T ESID */
ASM_VSID_SCRAMBLE(r10,r9,1T)
- rldimi r11,r10,SLB_VSID_SHIFT_1T,16 /* combine VSID and flags */
+ /*
+ * bits above VSID_BITS_1T need to be ignored from r10
+ * also combine VSID and flags
+ */
+ rldimi r11,r10,SLB_VSID_SHIFT_1T,(64 - (SLB_VSID_SHIFT_1T + VSID_BITS_1T))
li r10,MMU_SEGSIZE_1T
rldimi r11,r10,SLB_VSID_SSIZE_SHIFT,0 /* insert segment size */
--
1.7.10
^ permalink raw reply related
* [PATCH -V8 05/11] arch/powerpc: Make KERN_VIRT_SIZE not dependend on PGTABLE_RANGE
From: Aneesh Kumar K.V @ 2012-09-06 15:29 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1346945351-7672-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
As we keep increasing PGTABLE_RANGE we need not increase the virual
map area for kernel.
Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/pgtable-ppc64.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index c420561..8af1cf2 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -41,7 +41,7 @@
#else
#define KERN_VIRT_START ASM_CONST(0xD000000000000000)
#endif
-#define KERN_VIRT_SIZE PGTABLE_RANGE
+#define KERN_VIRT_SIZE ASM_CONST(0x0000100000000000)
/*
* The vmalloc space starts at the beginning of that region, and
--
1.7.10
^ permalink raw reply related
* [PATCH -V8 04/11] arch/powerpc: Convert virtual address to vpn
From: Aneesh Kumar K.V @ 2012-09-06 15:29 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1346945351-7672-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
This patch convert different functions to take virtual page number
instead of virtual address. Virtual page number is virtual address
shifted right by VPN_SHIFT (12) bits. This enable us to have an
address range of upto 76 bits.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/kvm_book3s.h | 2 +-
arch/powerpc/include/asm/machdep.h | 6 +-
arch/powerpc/include/asm/mmu-hash64.h | 78 +++++++++++++++----
arch/powerpc/include/asm/pte-hash64-64k.h | 18 +++--
arch/powerpc/include/asm/tlbflush.h | 4 +-
arch/powerpc/kvm/book3s_32_mmu_host.c | 8 +-
arch/powerpc/kvm/book3s_64_mmu_host.c | 17 ++--
arch/powerpc/kvm/trace.h | 14 ++--
arch/powerpc/mm/hash_low_64.S | 97 ++++++++++++++---------
arch/powerpc/mm/hash_native_64.c | 121 +++++++++++++++++------------
arch/powerpc/mm/hash_utils_64.c | 30 +++----
arch/powerpc/mm/hugetlbpage-hash64.c | 15 ++--
arch/powerpc/mm/tlb_hash64.c | 11 +--
arch/powerpc/platforms/cell/beat_htab.c | 45 +++++------
arch/powerpc/platforms/ps3/htab.c | 22 +++---
arch/powerpc/platforms/pseries/lpar.c | 76 ++++++++----------
16 files changed, 324 insertions(+), 240 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index f0e0c6a..7aefdb3 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -59,7 +59,7 @@ struct hpte_cache {
struct hlist_node list_vpte;
struct hlist_node list_vpte_long;
struct rcu_head rcu_head;
- u64 host_va;
+ u64 host_vpn;
u64 pfn;
ulong slot;
struct kvmppc_pte pte;
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 42ce570..cd63f1a 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -34,19 +34,19 @@ struct machdep_calls {
char *name;
#ifdef CONFIG_PPC64
void (*hpte_invalidate)(unsigned long slot,
- unsigned long va,
+ unsigned long vpn,
int psize, int ssize,
int local);
long (*hpte_updatepp)(unsigned long slot,
unsigned long newpp,
- unsigned long va,
+ unsigned long vpn,
int psize, int ssize,
int local);
void (*hpte_updateboltedpp)(unsigned long newpp,
unsigned long ea,
int psize, int ssize);
long (*hpte_insert)(unsigned long hpte_group,
- unsigned long va,
+ unsigned long vpn,
unsigned long prpn,
unsigned long rflags,
unsigned long vflags,
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index 1c65a59..6aeb498 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -154,9 +154,25 @@ struct mmu_psize_def
#define MMU_SEGSIZE_256M 0
#define MMU_SEGSIZE_1T 1
+/*
+ * encode page number shift.
+ * in order to fit the 78 bit va in a 64 bit variable we shift the va by
+ * 12 bits. This enable us to address upto 76 bit va.
+ * For hpt hash from a va we can ignore the page size bits of va and for
+ * hpte encoding we ignore up to 23 bits of va. So ignoring lower 12 bits ensure
+ * we work in all cases including 4k page size.
+ */
+#define VPN_SHIFT 12
#ifndef __ASSEMBLY__
+static inline int segment_shift(int ssize)
+{
+ if (ssize == MMU_SEGSIZE_256M)
+ return SID_SHIFT;
+ return SID_SHIFT_1T;
+}
+
/*
* The current system page and segment sizes
*/
@@ -180,18 +196,39 @@ extern unsigned long tce_alloc_start, tce_alloc_end;
extern int mmu_ci_restrictions;
/*
+ * This computes the AVPN and B fields of the first dword of a HPTE,
+ * for use when we want to match an existing PTE. The bottom 7 bits
+ * of the returned value are zero.
+ */
+static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize,
+ int ssize)
+{
+ unsigned long v;
+ /*
+ * The AVA field omits the low-order 23 bits of the 78 bits VA.
+ * These bits are not needed in the PTE, because the
+ * low-order b of these bits are part of the byte offset
+ * into the virtual page and, if b < 23, the high-order
+ * 23-b of these bits are always used in selecting the
+ * PTEGs to be searched
+ */
+ v = (vpn >> (23 - VPN_SHIFT)) & ~(mmu_psize_defs[psize].avpnm);
+ v <<= HPTE_V_AVPN_SHIFT;
+ v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
+ return v;
+}
+
+/*
* This function sets the AVPN and L fields of the HPTE appropriately
* for the page size
*/
-static inline unsigned long hpte_encode_v(unsigned long va, int psize,
- int ssize)
+static inline unsigned long hpte_encode_v(unsigned long vpn,
+ int psize, int ssize)
{
unsigned long v;
- v = (va >> 23) & ~(mmu_psize_defs[psize].avpnm);
- v <<= HPTE_V_AVPN_SHIFT;
+ v = hpte_encode_avpn(vpn, psize, ssize);
if (psize != MMU_PAGE_4K)
v |= HPTE_V_LARGE;
- v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
return v;
}
@@ -216,30 +253,37 @@ static inline unsigned long hpte_encode_r(unsigned long pa, int psize)
}
/*
- * Build a VA given VSID, EA and segment size
+ * Build a VPN_SHIFT bit shifted va given VSID, EA and segment size.
*/
-static inline unsigned long hpt_va(unsigned long ea, unsigned long vsid,
- int ssize)
+static inline unsigned long hpt_vpn(unsigned long ea,
+ unsigned long vsid, int ssize)
{
- if (ssize == MMU_SEGSIZE_256M)
- return (vsid << 28) | (ea & 0xfffffffUL);
- return (vsid << 40) | (ea & 0xffffffffffUL);
+ unsigned long mask;
+ int s_shift = segment_shift(ssize);
+
+ mask = (1ul << (s_shift - VPN_SHIFT)) - 1;
+ return (vsid << (s_shift - VPN_SHIFT)) | ((ea >> VPN_SHIFT) & mask);
}
/*
* This hashes a virtual address
*/
-
-static inline unsigned long hpt_hash(unsigned long va, unsigned int shift,
- int ssize)
+static inline unsigned long hpt_hash(unsigned long vpn,
+ unsigned int shift, int ssize)
{
+ int mask;
unsigned long hash, vsid;
+ /* VPN_SHIFT can be atmost 12 */
if (ssize == MMU_SEGSIZE_256M) {
- hash = (va >> 28) ^ ((va & 0x0fffffffUL) >> shift);
+ mask = (1ul << (SID_SHIFT - VPN_SHIFT)) - 1;
+ hash = (vpn >> (SID_SHIFT - VPN_SHIFT)) ^
+ ((vpn & mask) >> (shift - VPN_SHIFT));
} else {
- vsid = va >> 40;
- hash = vsid ^ (vsid << 25) ^ ((va & 0xffffffffffUL) >> shift);
+ mask = (1ul << (SID_SHIFT_1T - VPN_SHIFT)) - 1;
+ vsid = vpn >> (SID_SHIFT_1T - VPN_SHIFT);
+ hash = vsid ^ (vsid << 25) ^
+ ((vpn & mask) >> (shift - VPN_SHIFT)) ;
}
return hash & 0x7fffffffffUL;
}
diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h
index 59247e8..eedf427 100644
--- a/arch/powerpc/include/asm/pte-hash64-64k.h
+++ b/arch/powerpc/include/asm/pte-hash64-64k.h
@@ -58,14 +58,16 @@
/* Trick: we set __end to va + 64k, which happens works for
* a 16M page as well as we want only one iteration
*/
-#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift) \
- do { \
- unsigned long __end = va + PAGE_SIZE; \
- unsigned __split = (psize == MMU_PAGE_4K || \
- psize == MMU_PAGE_64K_AP); \
- shift = mmu_psize_defs[psize].shift; \
- for (index = 0; va < __end; index++, va += (1L << shift)) { \
- if (!__split || __rpte_sub_valid(rpte, index)) do { \
+#define pte_iterate_hashed_subpages(rpte, psize, vpn, index, shift) \
+ do { \
+ unsigned long __end = vpn + (1UL << (PAGE_SHIFT - VPN_SHIFT)); \
+ unsigned __split = (psize == MMU_PAGE_4K || \
+ psize == MMU_PAGE_64K_AP); \
+ shift = mmu_psize_defs[psize].shift; \
+ for (index = 0; vpn < __end; index++, \
+ vpn += (1L << (shift - VPN_SHIFT))) { \
+ if (!__split || __rpte_sub_valid(rpte, index)) \
+ do {
#define pte_iterate_hashed_end() } while(0); } } while(0)
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index 81143fc..fc02d1d 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -95,7 +95,7 @@ struct ppc64_tlb_batch {
unsigned long index;
struct mm_struct *mm;
real_pte_t pte[PPC64_TLB_BATCH_NR];
- unsigned long vaddr[PPC64_TLB_BATCH_NR];
+ unsigned long vpn[PPC64_TLB_BATCH_NR];
unsigned int psize;
int ssize;
};
@@ -127,7 +127,7 @@ static inline void arch_leave_lazy_mmu_mode(void)
#define arch_flush_lazy_mmu_mode() do {} while (0)
-extern void flush_hash_page(unsigned long va, real_pte_t pte, int psize,
+extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize,
int ssize, int local);
extern void flush_hash_range(unsigned long number, int local);
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 837f13e..00aa612 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -141,7 +141,7 @@ extern char etext[];
int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
{
pfn_t hpaddr;
- u64 va;
+ u64 vpn;
u64 vsid;
struct kvmppc_sid_map *map;
volatile u32 *pteg;
@@ -173,7 +173,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
BUG_ON(!map);
vsid = map->host_vsid;
- va = (vsid << SID_SHIFT) | (eaddr & ~ESID_MASK);
+ vpn = (vsid << (SID_SHIFT - VPN_SHIFT)) | ((eaddr & ~ESID_MASK) >> VPN_SHIFT)
next_pteg:
if (rr == 16) {
@@ -244,11 +244,11 @@ next_pteg:
dprintk_mmu("KVM: %c%c Map 0x%llx: [%lx] 0x%llx (0x%llx) -> %lx\n",
orig_pte->may_write ? 'w' : '-',
orig_pte->may_execute ? 'x' : '-',
- orig_pte->eaddr, (ulong)pteg, va,
+ orig_pte->eaddr, (ulong)pteg, vpn,
orig_pte->vpage, hpaddr);
pte->slot = (ulong)&pteg[rr];
- pte->host_va = va;
+ pte->host_vpn = vpn;
pte->pte = *orig_pte;
pte->pfn = hpaddr >> PAGE_SHIFT;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 0688b6b..4d72f9e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -33,7 +33,7 @@
void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
{
- ppc_md.hpte_invalidate(pte->slot, pte->host_va,
+ ppc_md.hpte_invalidate(pte->slot, pte->host_vpn,
MMU_PAGE_4K, MMU_SEGSIZE_256M,
false);
}
@@ -80,8 +80,9 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
{
+ unsigned long vpn;
pfn_t hpaddr;
- ulong hash, hpteg, va;
+ ulong hash, hpteg;
u64 vsid;
int ret;
int rflags = 0x192;
@@ -117,7 +118,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
}
vsid = map->host_vsid;
- va = hpt_va(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M);
+ vpn = hpt_vpn(orig_pte->eaddr, vsid, MMU_SEGSIZE_256M);
if (!orig_pte->may_write)
rflags |= HPTE_R_PP;
@@ -129,7 +130,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
else
kvmppc_mmu_flush_icache(hpaddr >> PAGE_SHIFT);
- hash = hpt_hash(va, PTE_SIZE, MMU_SEGSIZE_256M);
+ hash = hpt_hash(vpn, PTE_SIZE, MMU_SEGSIZE_256M);
map_again:
hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
@@ -141,7 +142,8 @@ map_again:
goto out;
}
- ret = ppc_md.hpte_insert(hpteg, va, hpaddr, rflags, vflags, MMU_PAGE_4K, MMU_SEGSIZE_256M);
+ ret = ppc_md.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags,
+ MMU_PAGE_4K, MMU_SEGSIZE_256M);
if (ret < 0) {
/* If we couldn't map a primary PTE, try a secondary */
@@ -152,7 +154,8 @@ map_again:
} else {
struct hpte_cache *pte = kvmppc_mmu_hpte_cache_next(vcpu);
- trace_kvm_book3s_64_mmu_map(rflags, hpteg, va, hpaddr, orig_pte);
+ trace_kvm_book3s_64_mmu_map(rflags, hpteg,
+ vpn, hpaddr, orig_pte);
/* The ppc_md code may give us a secondary entry even though we
asked for a primary. Fix up. */
@@ -162,7 +165,7 @@ map_again:
}
pte->slot = hpteg + (ret & 7);
- pte->host_va = va;
+ pte->host_vpn = vpn;
pte->pte = *orig_pte;
pte->pfn = hpaddr >> PAGE_SHIFT;
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index 877186b..ddb6a21 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -189,7 +189,7 @@ TRACE_EVENT(kvm_book3s_mmu_map,
TP_ARGS(pte),
TP_STRUCT__entry(
- __field( u64, host_va )
+ __field( u64, host_vpn )
__field( u64, pfn )
__field( ulong, eaddr )
__field( u64, vpage )
@@ -198,7 +198,7 @@ TRACE_EVENT(kvm_book3s_mmu_map,
),
TP_fast_assign(
- __entry->host_va = pte->host_va;
+ __entry->host_vpn = pte->host_vpn;
__entry->pfn = pte->pfn;
__entry->eaddr = pte->pte.eaddr;
__entry->vpage = pte->pte.vpage;
@@ -208,8 +208,8 @@ TRACE_EVENT(kvm_book3s_mmu_map,
(pte->pte.may_execute ? 0x1 : 0);
),
- TP_printk("Map: hva=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
- __entry->host_va, __entry->pfn, __entry->eaddr,
+ TP_printk("Map: hvpn=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
+ __entry->host_vpn, __entry->pfn, __entry->eaddr,
__entry->vpage, __entry->raddr, __entry->flags)
);
@@ -218,7 +218,7 @@ TRACE_EVENT(kvm_book3s_mmu_invalidate,
TP_ARGS(pte),
TP_STRUCT__entry(
- __field( u64, host_va )
+ __field( u64, host_vpn )
__field( u64, pfn )
__field( ulong, eaddr )
__field( u64, vpage )
@@ -227,7 +227,7 @@ TRACE_EVENT(kvm_book3s_mmu_invalidate,
),
TP_fast_assign(
- __entry->host_va = pte->host_va;
+ __entry->host_vpn = pte->host_vpn;
__entry->pfn = pte->pfn;
__entry->eaddr = pte->pte.eaddr;
__entry->vpage = pte->pte.vpage;
@@ -238,7 +238,7 @@ TRACE_EVENT(kvm_book3s_mmu_invalidate,
),
TP_printk("Flush: hva=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
- __entry->host_va, __entry->pfn, __entry->eaddr,
+ __entry->host_vpn, __entry->pfn, __entry->eaddr,
__entry->vpage, __entry->raddr, __entry->flags)
);
diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S
index 602aeb0..5658508 100644
--- a/arch/powerpc/mm/hash_low_64.S
+++ b/arch/powerpc/mm/hash_low_64.S
@@ -63,7 +63,7 @@ _GLOBAL(__hash_page_4K)
/* Save non-volatile registers.
* r31 will hold "old PTE"
* r30 is "new PTE"
- * r29 is "va"
+ * r29 is vpn
* r28 is a hash value
* r27 is hashtab mask (maybe dynamic patched instead ?)
*/
@@ -111,10 +111,10 @@ BEGIN_FTR_SECTION
cmpdi r9,0 /* check segment size */
bne 3f
END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
- /* Calc va and put it in r29 */
- rldicr r29,r5,28,63-28
- rldicl r3,r3,0,36
- or r29,r3,r29
+ /* Calc vpn and put it in r29 */
+ sldi r29,r5,SID_SHIFT - VPN_SHIFT
+ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
+ or r29,r28,r29
/* Calculate hash value for primary slot and store it in r28 */
rldicl r5,r5,0,25 /* vsid & 0x0000007fffffffff */
@@ -122,14 +122,19 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
xor r28,r5,r0
b 4f
-3: /* Calc VA and hash in r29 and r28 for 1T segment */
- sldi r29,r5,40 /* vsid << 40 */
- clrldi r3,r3,24 /* ea & 0xffffffffff */
+3: /* Calc vpn and put it in r29 */
+ sldi r29,r5,SID_SHIFT_1T - VPN_SHIFT
+ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT)
+ or r29,r28,r29
+
+ /*
+ * calculate hash value for primary slot and
+ * store it in r28 for 1T segment
+ */
rldic r28,r5,25,25 /* (vsid << 25) & 0x7fffffffff */
clrldi r5,r5,40 /* vsid & 0xffffff */
rldicl r0,r3,64-12,36 /* (ea >> 12) & 0xfffffff */
xor r28,r28,r5
- or r29,r3,r29 /* VA */
xor r28,r28,r0 /* hash */
/* Convert linux PTE bits into HW equivalents */
@@ -185,7 +190,7 @@ htab_insert_pte:
/* Call ppc_md.hpte_insert */
ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve va */
+ mr r4,r29 /* Retrieve vpn */
li r7,0 /* !bolted, !secondary */
li r8,MMU_PAGE_4K /* page size */
ld r9,STK_PARAM(R9)(r1) /* segment size */
@@ -208,7 +213,7 @@ _GLOBAL(htab_call_hpte_insert1)
/* Call ppc_md.hpte_insert */
ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve va */
+ mr r4,r29 /* Retrieve vpn */
li r7,HPTE_V_SECONDARY /* !bolted, secondary */
li r8,MMU_PAGE_4K /* page size */
ld r9,STK_PARAM(R9)(r1) /* segment size */
@@ -278,7 +283,7 @@ htab_modify_pte:
add r3,r0,r3 /* add slot idx */
/* Call ppc_md.hpte_updatepp */
- mr r5,r29 /* va */
+ mr r5,r29 /* vpn */
li r6,MMU_PAGE_4K /* page size */
ld r7,STK_PARAM(R9)(r1) /* segment size */
ld r8,STK_PARAM(R8)(r1) /* get "local" param */
@@ -339,7 +344,7 @@ _GLOBAL(__hash_page_4K)
/* Save non-volatile registers.
* r31 will hold "old PTE"
* r30 is "new PTE"
- * r29 is "va"
+ * r29 is vpn
* r28 is a hash value
* r27 is hashtab mask (maybe dynamic patched instead ?)
* r26 is the hidx mask
@@ -394,10 +399,14 @@ BEGIN_FTR_SECTION
cmpdi r9,0 /* check segment size */
bne 3f
END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
- /* Calc va and put it in r29 */
- rldicr r29,r5,28,63-28 /* r29 = (vsid << 28) */
- rldicl r3,r3,0,36 /* r3 = (ea & 0x0fffffff) */
- or r29,r3,r29 /* r29 = va */
+ /* Calc vpn and put it in r29 */
+ sldi r29,r5,SID_SHIFT - VPN_SHIFT
+ /*
+ * clrldi r3,r3,64 - SID_SHIFT --> ea & 0xfffffff
+ * srdi r28,r3,VPN_SHIFT
+ */
+ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
+ or r29,r28,r29
/* Calculate hash value for primary slot and store it in r28 */
rldicl r5,r5,0,25 /* vsid & 0x0000007fffffffff */
@@ -405,14 +414,23 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
xor r28,r5,r0
b 4f
-3: /* Calc VA and hash in r29 and r28 for 1T segment */
- sldi r29,r5,40 /* vsid << 40 */
- clrldi r3,r3,24 /* ea & 0xffffffffff */
+3: /* Calc vpn and put it in r29 */
+ sldi r29,r5,SID_SHIFT_1T - VPN_SHIFT
+ /*
+ * clrldi r3,r3,64 - SID_SHIFT_1T --> ea & 0xffffffffff
+ * srdi r28,r3,VPN_SHIFT
+ */
+ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT)
+ or r29,r28,r29
+
+ /*
+ * Calculate hash value for primary slot and
+ * store it in r28 for 1T segment
+ */
rldic r28,r5,25,25 /* (vsid << 25) & 0x7fffffffff */
clrldi r5,r5,40 /* vsid & 0xffffff */
rldicl r0,r3,64-12,36 /* (ea >> 12) & 0xfffffff */
xor r28,r28,r5
- or r29,r3,r29 /* VA */
xor r28,r28,r0 /* hash */
/* Convert linux PTE bits into HW equivalents */
@@ -488,7 +506,7 @@ htab_special_pfn:
/* Call ppc_md.hpte_insert */
ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve va */
+ mr r4,r29 /* Retrieve vpn */
li r7,0 /* !bolted, !secondary */
li r8,MMU_PAGE_4K /* page size */
ld r9,STK_PARAM(R9)(r1) /* segment size */
@@ -515,7 +533,7 @@ _GLOBAL(htab_call_hpte_insert1)
/* Call ppc_md.hpte_insert */
ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve va */
+ mr r4,r29 /* Retrieve vpn */
li r7,HPTE_V_SECONDARY /* !bolted, secondary */
li r8,MMU_PAGE_4K /* page size */
ld r9,STK_PARAM(R9)(r1) /* segment size */
@@ -547,7 +565,7 @@ _GLOBAL(htab_call_hpte_remove)
* useless now that the segment has been switched to 4k pages.
*/
htab_inval_old_hpte:
- mr r3,r29 /* virtual addr */
+ mr r3,r29 /* vpn */
mr r4,r31 /* PTE.pte */
li r5,0 /* PTE.hidx */
li r6,MMU_PAGE_64K /* psize */
@@ -620,7 +638,7 @@ htab_modify_pte:
add r3,r0,r3 /* add slot idx */
/* Call ppc_md.hpte_updatepp */
- mr r5,r29 /* va */
+ mr r5,r29 /* vpn */
li r6,MMU_PAGE_4K /* page size */
ld r7,STK_PARAM(R9)(r1) /* segment size */
ld r8,STK_PARAM(R8)(r1) /* get "local" param */
@@ -676,7 +694,7 @@ _GLOBAL(__hash_page_64K)
/* Save non-volatile registers.
* r31 will hold "old PTE"
* r30 is "new PTE"
- * r29 is "va"
+ * r29 is vpn
* r28 is a hash value
* r27 is hashtab mask (maybe dynamic patched instead ?)
*/
@@ -729,10 +747,10 @@ BEGIN_FTR_SECTION
cmpdi r9,0 /* check segment size */
bne 3f
END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
- /* Calc va and put it in r29 */
- rldicr r29,r5,28,63-28
- rldicl r3,r3,0,36
- or r29,r3,r29
+ /* Calc vpn and put it in r29 */
+ sldi r29,r5,SID_SHIFT - VPN_SHIFT
+ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT - VPN_SHIFT)
+ or r29,r28,r29
/* Calculate hash value for primary slot and store it in r28 */
rldicl r5,r5,0,25 /* vsid & 0x0000007fffffffff */
@@ -740,14 +758,19 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_1T_SEGMENT)
xor r28,r5,r0
b 4f
-3: /* Calc VA and hash in r29 and r28 for 1T segment */
- sldi r29,r5,40 /* vsid << 40 */
- clrldi r3,r3,24 /* ea & 0xffffffffff */
+3: /* Calc vpn and put it in r29 */
+ sldi r29,r5,SID_SHIFT_1T - VPN_SHIFT
+ rldicl r28,r3,64 - VPN_SHIFT,64 - (SID_SHIFT_1T - VPN_SHIFT)
+ or r29,r28,r29
+
+ /*
+ * calculate hash value for primary slot and
+ * store it in r28 for 1T segment
+ */
rldic r28,r5,25,25 /* (vsid << 25) & 0x7fffffffff */
clrldi r5,r5,40 /* vsid & 0xffffff */
rldicl r0,r3,64-16,40 /* (ea >> 16) & 0xffffff */
xor r28,r28,r5
- or r29,r3,r29 /* VA */
xor r28,r28,r0 /* hash */
/* Convert linux PTE bits into HW equivalents */
@@ -806,7 +829,7 @@ ht64_insert_pte:
/* Call ppc_md.hpte_insert */
ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve va */
+ mr r4,r29 /* Retrieve vpn */
li r7,0 /* !bolted, !secondary */
li r8,MMU_PAGE_64K
ld r9,STK_PARAM(R9)(r1) /* segment size */
@@ -829,7 +852,7 @@ _GLOBAL(ht64_call_hpte_insert1)
/* Call ppc_md.hpte_insert */
ld r6,STK_PARAM(R4)(r1) /* Retrieve new pp bits */
- mr r4,r29 /* Retrieve va */
+ mr r4,r29 /* Retrieve vpn */
li r7,HPTE_V_SECONDARY /* !bolted, secondary */
li r8,MMU_PAGE_64K
ld r9,STK_PARAM(R9)(r1) /* segment size */
@@ -899,7 +922,7 @@ ht64_modify_pte:
add r3,r0,r3 /* add slot idx */
/* Call ppc_md.hpte_updatepp */
- mr r5,r29 /* va */
+ mr r5,r29 /* vpn */
li r6,MMU_PAGE_64K
ld r7,STK_PARAM(R9)(r1) /* segment size */
ld r8,STK_PARAM(R8)(r1) /* get "local" param */
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 660b8bb..36b212b 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -39,22 +39,35 @@
DEFINE_RAW_SPINLOCK(native_tlbie_lock);
-static inline void __tlbie(unsigned long va, int psize, int ssize)
+static inline void __tlbie(unsigned long vpn, int psize, int ssize)
{
+ unsigned long va;
unsigned int penc;
- /* clear top 16 bits, non SLS segment */
+ /*
+ * We need 14 to 65 bits of va for a tlibe of 4K page
+ * With vpn we ignore the lower VPN_SHIFT bits already.
+ * And top two bits are already ignored because we can
+ * only accomadate 76 bits in a 64 bit vpn with a VPN_SHIFT
+ * of 12.
+ */
+ va = vpn << VPN_SHIFT;
+ /*
+ * clear top 16 bits of 64bit va, non SLS segment
+ * Older versions of the architecture (2.02 and earler) require the
+ * masking of the top 16 bits.
+ */
va &= ~(0xffffULL << 48);
switch (psize) {
case MMU_PAGE_4K:
- va &= ~0xffful;
va |= ssize << 8;
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);
va |= penc << 12;
@@ -67,21 +80,28 @@ static inline void __tlbie(unsigned long va, int psize, int ssize)
}
}
-static inline void __tlbiel(unsigned long va, int psize, int ssize)
+static inline void __tlbiel(unsigned long vpn, int psize, int ssize)
{
+ unsigned long va;
unsigned int penc;
- /* clear top 16 bits, non SLS segment */
+ /* VPN_SHIFT can be atmost 12 */
+ va = vpn << VPN_SHIFT;
+ /*
+ * clear top 16 bits of 64 bit va, non SLS segment
+ * Older versions of the architecture (2.02 and earler) require the
+ * masking of the top 16 bits.
+ */
va &= ~(0xffffULL << 48);
switch (psize) {
case MMU_PAGE_4K:
- va &= ~0xffful;
va |= ssize << 8;
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);
va |= penc << 12;
@@ -94,7 +114,7 @@ static inline void __tlbiel(unsigned long va, int psize, int ssize)
}
-static inline void tlbie(unsigned long va, int psize, int ssize, int local)
+static inline void tlbie(unsigned long vpn, int psize, 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);
@@ -105,10 +125,10 @@ static inline void tlbie(unsigned long va, int psize, int ssize, int local)
raw_spin_lock(&native_tlbie_lock);
asm volatile("ptesync": : :"memory");
if (use_local) {
- __tlbiel(va, psize, ssize);
+ __tlbiel(vpn, psize, ssize);
asm volatile("ptesync": : :"memory");
} else {
- __tlbie(va, psize, ssize);
+ __tlbie(vpn, psize, ssize);
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
if (lock_tlbie && !use_local)
@@ -134,7 +154,7 @@ static inline void native_unlock_hpte(struct hash_pte *hptep)
clear_bit_unlock(HPTE_LOCK_BIT, word);
}
-static long native_hpte_insert(unsigned long hpte_group, unsigned long va,
+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)
{
@@ -143,9 +163,9 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long va,
int i;
if (!(vflags & HPTE_V_BOLTED)) {
- DBG_LOW(" insert(group=%lx, va=%016lx, pa=%016lx,"
+ DBG_LOW(" insert(group=%lx, vpn=%016lx, pa=%016lx,"
" rflags=%lx, vflags=%lx, psize=%d)\n",
- hpte_group, va, pa, rflags, vflags, psize);
+ hpte_group, vpn, pa, rflags, vflags, psize);
}
for (i = 0; i < HPTES_PER_GROUP; i++) {
@@ -163,7 +183,7 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long va,
if (i == HPTES_PER_GROUP)
return -1;
- hpte_v = hpte_encode_v(va, psize, ssize) | vflags | HPTE_V_VALID;
+ hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID;
hpte_r = hpte_encode_r(pa, psize) | rflags;
if (!(vflags & HPTE_V_BOLTED)) {
@@ -225,17 +245,17 @@ static long native_hpte_remove(unsigned long hpte_group)
}
static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
- unsigned long va, int psize, int ssize,
+ unsigned long vpn, int psize, int ssize,
int local)
{
struct hash_pte *hptep = htab_address + slot;
unsigned long hpte_v, want_v;
int ret = 0;
- want_v = hpte_encode_v(va, psize, ssize);
+ want_v = hpte_encode_v(vpn, psize, ssize);
- DBG_LOW(" update(va=%016lx, avpnv=%016lx, hash=%016lx, newpp=%x)",
- va, want_v & HPTE_V_AVPN, slot, newpp);
+ DBG_LOW(" update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)",
+ vpn, want_v & HPTE_V_AVPN, slot, newpp);
native_lock_hpte(hptep);
@@ -254,12 +274,12 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
native_unlock_hpte(hptep);
/* Ensure it is out of the tlb too. */
- tlbie(va, psize, ssize, local);
+ tlbie(vpn, psize, ssize, local);
return ret;
}
-static long native_hpte_find(unsigned long va, int psize, int ssize)
+static long native_hpte_find(unsigned long vpn, int psize, int ssize)
{
struct hash_pte *hptep;
unsigned long hash;
@@ -267,8 +287,8 @@ static long native_hpte_find(unsigned long va, int psize, int ssize)
long slot;
unsigned long want_v, hpte_v;
- hash = hpt_hash(va, mmu_psize_defs[psize].shift, ssize);
- want_v = hpte_encode_v(va, psize, ssize);
+ hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize);
+ want_v = hpte_encode_v(vpn, psize, ssize);
/* Bolted mappings are only ever in the primary group */
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
@@ -295,14 +315,15 @@ static long native_hpte_find(unsigned long va, int psize, int ssize)
static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
int psize, int ssize)
{
- unsigned long vsid, va;
+ unsigned long vpn;
+ unsigned long vsid;
long slot;
struct hash_pte *hptep;
vsid = get_kernel_vsid(ea, ssize);
- va = hpt_va(ea, vsid, ssize);
+ vpn = hpt_vpn(ea, vsid, ssize);
- slot = native_hpte_find(va, psize, ssize);
+ slot = native_hpte_find(vpn, psize, ssize);
if (slot == -1)
panic("could not find page to bolt\n");
hptep = htab_address + slot;
@@ -312,10 +333,10 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
(newpp & (HPTE_R_PP | HPTE_R_N));
/* Ensure it is out of the tlb too. */
- tlbie(va, psize, ssize, 0);
+ tlbie(vpn, psize, ssize, 0);
}
-static void native_hpte_invalidate(unsigned long slot, unsigned long va,
+static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
int psize, int ssize, int local)
{
struct hash_pte *hptep = htab_address + slot;
@@ -325,9 +346,9 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long va,
local_irq_save(flags);
- DBG_LOW(" invalidate(va=%016lx, hash: %x)\n", va, slot);
+ DBG_LOW(" invalidate(vpn=%016lx, hash: %lx)\n", vpn, slot);
- want_v = hpte_encode_v(va, psize, ssize);
+ want_v = hpte_encode_v(vpn, psize, ssize);
native_lock_hpte(hptep);
hpte_v = hptep->v;
@@ -339,7 +360,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long va,
hptep->v = 0;
/* Invalidate the TLB */
- tlbie(va, psize, ssize, local);
+ tlbie(vpn, psize, ssize, local);
local_irq_restore(flags);
}
@@ -349,7 +370,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long va,
#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 *va)
+ int *psize, int *ssize, unsigned long *vpn)
{
unsigned long avpn, pteg, vpi;
unsigned long hpte_r = hpte->r;
@@ -399,7 +420,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
vpi = (vsid ^ pteg) & htab_hash_mask;
seg_off |= vpi << shift;
}
- *va = vsid << SID_SHIFT | seg_off;
+ *vpn = vsid << (SID_SHIFT - VPN_SHIFT) | seg_off >> VPN_SHIFT;
case MMU_SEGSIZE_1T:
/* We only have 40 - 23 bits of seg_off in avpn */
seg_off = (avpn & 0x1ffff) << 23;
@@ -408,9 +429,9 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
vpi = (vsid ^ (vsid << 25) ^ pteg) & htab_hash_mask;
seg_off |= vpi << shift;
}
- *va = vsid << SID_SHIFT_1T | seg_off;
+ *vpn = vsid << (SID_SHIFT_1T - VPN_SHIFT) | seg_off >> VPN_SHIFT;
default:
- *va = size = 0;
+ *vpn = size = 0;
}
*psize = size;
}
@@ -425,9 +446,10 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
*/
static void native_hpte_clear(void)
{
+ unsigned long vpn = 0;
unsigned long slot, slots, flags;
struct hash_pte *hptep = htab_address;
- unsigned long hpte_v, va;
+ unsigned long hpte_v;
unsigned long pteg_count;
int psize, ssize;
@@ -455,9 +477,9 @@ static void native_hpte_clear(void)
* already hold the native_tlbie_lock.
*/
if (hpte_v & HPTE_V_VALID) {
- hpte_decode(hptep, slot, &psize, &ssize, &va);
+ hpte_decode(hptep, slot, &psize, &ssize, &vpn);
hptep->v = 0;
- __tlbie(va, psize, ssize);
+ __tlbie(vpn, psize, ssize);
}
}
@@ -472,7 +494,8 @@ static void native_hpte_clear(void)
*/
static void native_flush_hash_range(unsigned long number, int local)
{
- unsigned long va, hash, index, hidx, shift, slot;
+ unsigned long vpn;
+ unsigned long hash, index, hidx, shift, slot;
struct hash_pte *hptep;
unsigned long hpte_v;
unsigned long want_v;
@@ -486,18 +509,18 @@ static void native_flush_hash_range(unsigned long number, int local)
local_irq_save(flags);
for (i = 0; i < number; i++) {
- va = batch->vaddr[i];
+ vpn = batch->vpn[i];
pte = batch->pte[i];
- pte_iterate_hashed_subpages(pte, psize, va, index, shift) {
- hash = hpt_hash(va, shift, ssize);
+ pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
+ hash = hpt_hash(vpn, shift, ssize);
hidx = __rpte_to_hidx(pte, index);
if (hidx & _PTEIDX_SECONDARY)
hash = ~hash;
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += hidx & _PTEIDX_GROUP_IX;
hptep = htab_address + slot;
- want_v = hpte_encode_v(va, psize, ssize);
+ want_v = hpte_encode_v(vpn, psize, ssize);
native_lock_hpte(hptep);
hpte_v = hptep->v;
if (!HPTE_V_COMPARE(hpte_v, want_v) ||
@@ -512,12 +535,12 @@ static void native_flush_hash_range(unsigned long number, int local)
mmu_psize_defs[psize].tlbiel && local) {
asm volatile("ptesync":::"memory");
for (i = 0; i < number; i++) {
- va = batch->vaddr[i];
+ vpn = batch->vpn[i];
pte = batch->pte[i];
- pte_iterate_hashed_subpages(pte, psize, va, index,
- shift) {
- __tlbiel(va, psize, ssize);
+ pte_iterate_hashed_subpages(pte, psize,
+ vpn, index, shift) {
+ __tlbiel(vpn, psize, ssize);
} pte_iterate_hashed_end();
}
asm volatile("ptesync":::"memory");
@@ -529,12 +552,12 @@ static void native_flush_hash_range(unsigned long number, int local)
asm volatile("ptesync":::"memory");
for (i = 0; i < number; i++) {
- va = batch->vaddr[i];
+ vpn = batch->vpn[i];
pte = batch->pte[i];
- pte_iterate_hashed_subpages(pte, psize, va, index,
- shift) {
- __tlbie(va, psize, ssize);
+ pte_iterate_hashed_subpages(pte, psize,
+ vpn, index, shift) {
+ __tlbie(vpn, psize, ssize);
} pte_iterate_hashed_end();
}
asm volatile("eieio; tlbsync; ptesync":::"memory");
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 377e5cb..74c5479 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -192,18 +192,18 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
vaddr += step, paddr += step) {
unsigned long hash, hpteg;
unsigned long vsid = get_kernel_vsid(vaddr, ssize);
- unsigned long va = hpt_va(vaddr, vsid, ssize);
+ unsigned long vpn = hpt_vpn(vaddr, vsid, ssize);
unsigned long tprot = prot;
/* Make kernel text executable */
if (overlaps_kernel_text(vaddr, vaddr + step))
tprot &= ~HPTE_R_N;
- hash = hpt_hash(va, shift, ssize);
+ hash = hpt_hash(vpn, shift, ssize);
hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
BUG_ON(!ppc_md.hpte_insert);
- ret = ppc_md.hpte_insert(hpteg, va, paddr, tprot,
+ ret = ppc_md.hpte_insert(hpteg, vpn, paddr, tprot,
HPTE_V_BOLTED, psize, ssize);
if (ret < 0)
@@ -1153,21 +1153,21 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
/* WARNING: This is called from hash_low_64.S, if you change this prototype,
* do not forget to update the assembly call site !
*/
-void flush_hash_page(unsigned long va, real_pte_t pte, int psize, int ssize,
+void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
int local)
{
unsigned long hash, index, shift, hidx, slot;
- DBG_LOW("flush_hash_page(va=%016lx)\n", va);
- pte_iterate_hashed_subpages(pte, psize, va, index, shift) {
- hash = hpt_hash(va, shift, ssize);
+ DBG_LOW("flush_hash_page(vpn=%016lx)\n", vpn);
+ pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
+ hash = hpt_hash(vpn, shift, ssize);
hidx = __rpte_to_hidx(pte, index);
if (hidx & _PTEIDX_SECONDARY)
hash = ~hash;
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += hidx & _PTEIDX_GROUP_IX;
DBG_LOW(" sub %ld: hash=%lx, hidx=%lx\n", index, slot, hidx);
- ppc_md.hpte_invalidate(slot, va, psize, ssize, local);
+ ppc_md.hpte_invalidate(slot, vpn, psize, ssize, local);
} pte_iterate_hashed_end();
}
@@ -1181,7 +1181,7 @@ void flush_hash_range(unsigned long number, int local)
&__get_cpu_var(ppc64_tlb_batch);
for (i = 0; i < number; i++)
- flush_hash_page(batch->vaddr[i], batch->pte[i],
+ flush_hash_page(batch->vpn[i], batch->pte[i],
batch->psize, batch->ssize, local);
}
}
@@ -1208,14 +1208,14 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
{
unsigned long hash, hpteg;
unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
- unsigned long va = hpt_va(vaddr, vsid, mmu_kernel_ssize);
+ unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
unsigned long mode = htab_convert_pte_flags(PAGE_KERNEL);
int ret;
- hash = hpt_hash(va, PAGE_SHIFT, mmu_kernel_ssize);
+ hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
- ret = ppc_md.hpte_insert(hpteg, va, __pa(vaddr),
+ ret = ppc_md.hpte_insert(hpteg, vpn, __pa(vaddr),
mode, HPTE_V_BOLTED,
mmu_linear_psize, mmu_kernel_ssize);
BUG_ON (ret < 0);
@@ -1229,9 +1229,9 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
{
unsigned long hash, hidx, slot;
unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
- unsigned long va = hpt_va(vaddr, vsid, mmu_kernel_ssize);
+ unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
- hash = hpt_hash(va, PAGE_SHIFT, mmu_kernel_ssize);
+ hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
spin_lock(&linear_map_hash_lock);
BUG_ON(!(linear_map_hash_slots[lmi] & 0x80));
hidx = linear_map_hash_slots[lmi] & 0x7f;
@@ -1241,7 +1241,7 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
hash = ~hash;
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += hidx & _PTEIDX_GROUP_IX;
- ppc_md.hpte_invalidate(slot, va, mmu_linear_psize, mmu_kernel_ssize, 0);
+ ppc_md.hpte_invalidate(slot, vpn, mmu_linear_psize, mmu_kernel_ssize, 0);
}
void kernel_map_pages(struct page *page, int numpages, int enable)
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index cc5c273..cecad34 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -18,14 +18,15 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
pte_t *ptep, unsigned long trap, int local, int ssize,
unsigned int shift, unsigned int mmu_psize)
{
+ unsigned long vpn;
unsigned long old_pte, new_pte;
- unsigned long va, rflags, pa, sz;
+ unsigned long rflags, pa, sz;
long slot;
BUG_ON(shift != mmu_psize_defs[mmu_psize].shift);
/* Search the Linux page table for a match with va */
- va = hpt_va(ea, vsid, ssize);
+ vpn = hpt_vpn(ea, vsid, ssize);
/* At this point, we have a pte (old_pte) which can be used to build
* or update an HPTE. There are 2 cases:
@@ -69,19 +70,19 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
/* There MIGHT be an HPTE for this pte */
unsigned long hash, slot;
- hash = hpt_hash(va, shift, ssize);
+ hash = hpt_hash(vpn, shift, ssize);
if (old_pte & _PAGE_F_SECOND)
hash = ~hash;
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += (old_pte & _PAGE_F_GIX) >> 12;
- if (ppc_md.hpte_updatepp(slot, rflags, va, mmu_psize,
+ if (ppc_md.hpte_updatepp(slot, rflags, vpn, mmu_psize,
ssize, local) == -1)
old_pte &= ~_PAGE_HPTEFLAGS;
}
if (likely(!(old_pte & _PAGE_HASHPTE))) {
- unsigned long hash = hpt_hash(va, shift, ssize);
+ unsigned long hash = hpt_hash(vpn, shift, ssize);
unsigned long hpte_group;
pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT;
@@ -101,14 +102,14 @@ repeat:
_PAGE_COHERENT | _PAGE_GUARDED));
/* Insert into the hash table, primary slot */
- slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, 0,
+ slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
mmu_psize, ssize);
/* Primary is full, try the secondary */
if (unlikely(slot == -1)) {
hpte_group = ((~hash & htab_hash_mask) *
HPTES_PER_GROUP) & ~0x7UL;
- slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags,
+ slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags,
HPTE_V_SECONDARY,
mmu_psize, ssize);
if (slot == -1) {
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 31f1820..ae758b3 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -42,8 +42,9 @@ DEFINE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch);
void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long pte, int huge)
{
+ unsigned long vpn;
struct ppc64_tlb_batch *batch = &get_cpu_var(ppc64_tlb_batch);
- unsigned long vsid, vaddr;
+ unsigned long vsid;
unsigned int psize;
int ssize;
real_pte_t rpte;
@@ -86,7 +87,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
ssize = mmu_kernel_ssize;
}
- vaddr = hpt_va(addr, vsid, ssize);
+ vpn = hpt_vpn(addr, vsid, ssize);
rpte = __real_pte(__pte(pte), ptep);
/*
@@ -96,7 +97,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
* and decide to use local invalidates instead...
*/
if (!batch->active) {
- flush_hash_page(vaddr, rpte, psize, ssize, 0);
+ flush_hash_page(vpn, rpte, psize, ssize, 0);
put_cpu_var(ppc64_tlb_batch);
return;
}
@@ -122,7 +123,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
batch->ssize = ssize;
}
batch->pte[i] = rpte;
- batch->vaddr[i] = vaddr;
+ batch->vpn[i] = vpn;
batch->index = ++i;
if (i >= PPC64_TLB_BATCH_NR)
__flush_tlb_pending(batch);
@@ -146,7 +147,7 @@ void __flush_tlb_pending(struct ppc64_tlb_batch *batch)
if (cpumask_equal(mm_cpumask(batch->mm), tmp))
local = 1;
if (i == 1)
- flush_hash_page(batch->vaddr[0], batch->pte[0],
+ flush_hash_page(batch->vpn[0], batch->pte[0],
batch->psize, batch->ssize, local);
else
flush_hash_range(i, local);
diff --git a/arch/powerpc/platforms/cell/beat_htab.c b/arch/powerpc/platforms/cell/beat_htab.c
index b83077e..0f6f839 100644
--- a/arch/powerpc/platforms/cell/beat_htab.c
+++ b/arch/powerpc/platforms/cell/beat_htab.c
@@ -88,7 +88,7 @@ static inline unsigned int beat_read_mask(unsigned hpte_group)
}
static long beat_lpar_hpte_insert(unsigned long hpte_group,
- unsigned long va, unsigned long pa,
+ unsigned long vpn, unsigned long pa,
unsigned long rflags, unsigned long vflags,
int psize, int ssize)
{
@@ -103,7 +103,7 @@ static long beat_lpar_hpte_insert(unsigned long hpte_group,
"rflags=%lx, vflags=%lx, psize=%d)\n",
hpte_group, va, pa, rflags, vflags, psize);
- hpte_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M) |
+ hpte_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M) |
vflags | HPTE_V_VALID;
hpte_r = hpte_encode_r(pa, psize) | rflags;
@@ -184,14 +184,14 @@ static void beat_lpar_hptab_clear(void)
*/
static long beat_lpar_hpte_updatepp(unsigned long slot,
unsigned long newpp,
- unsigned long va,
+ unsigned long vpn,
int psize, int ssize, int local)
{
unsigned long lpar_rc;
u64 dummy0, dummy1;
unsigned long want_v;
- want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M);
+ want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
DBG_LOW(" update: "
"avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ",
@@ -220,15 +220,15 @@ static long beat_lpar_hpte_updatepp(unsigned long slot,
return 0;
}
-static long beat_lpar_hpte_find(unsigned long va, int psize)
+static long beat_lpar_hpte_find(unsigned long vpn, int psize)
{
unsigned long hash;
unsigned long i, j;
long slot;
unsigned long want_v, hpte_v;
- hash = hpt_hash(va, mmu_psize_defs[psize].shift, MMU_SEGSIZE_256M);
- want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M);
+ hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, MMU_SEGSIZE_256M);
+ want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
for (j = 0; j < 2; j++) {
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
@@ -255,14 +255,15 @@ static void beat_lpar_hpte_updateboltedpp(unsigned long newpp,
unsigned long ea,
int psize, int ssize)
{
- unsigned long lpar_rc, slot, vsid, va;
+ unsigned long vpn;
+ unsigned long lpar_rc, slot, vsid;
u64 dummy0, dummy1;
vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M);
- va = hpt_va(ea, vsid, MMU_SEGSIZE_256M);
+ vpn = hpt_vpn(ea, vsid, MMU_SEGSIZE_256M);
raw_spin_lock(&beat_htab_lock);
- slot = beat_lpar_hpte_find(va, psize);
+ slot = beat_lpar_hpte_find(vpn, psize);
BUG_ON(slot == -1);
lpar_rc = beat_write_htab_entry(0, slot, 0, newpp, 0, 7,
@@ -272,7 +273,7 @@ static void beat_lpar_hpte_updateboltedpp(unsigned long newpp,
BUG_ON(lpar_rc != 0);
}
-static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
+static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
int psize, int ssize, int local)
{
unsigned long want_v;
@@ -282,7 +283,7 @@ static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
DBG_LOW(" inval : slot=%lx, va=%016lx, psize: %d, local: %d\n",
slot, va, psize, local);
- want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M);
+ want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
raw_spin_lock_irqsave(&beat_htab_lock, flags);
dummy1 = beat_lpar_hpte_getword0(slot);
@@ -311,7 +312,7 @@ void __init hpte_init_beat(void)
}
static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
- unsigned long va, unsigned long pa,
+ unsigned long vpn, unsigned long pa,
unsigned long rflags, unsigned long vflags,
int psize, int ssize)
{
@@ -322,11 +323,11 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
return -1;
if (!(vflags & HPTE_V_BOLTED))
- DBG_LOW("hpte_insert(group=%lx, va=%016lx, pa=%016lx, "
+ DBG_LOW("hpte_insert(group=%lx, vpn=%016lx, pa=%016lx, "
"rflags=%lx, vflags=%lx, psize=%d)\n",
- hpte_group, va, pa, rflags, vflags, psize);
+ hpte_group, vpn, pa, rflags, vflags, psize);
- hpte_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M) |
+ hpte_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M) |
vflags | HPTE_V_VALID;
hpte_r = hpte_encode_r(pa, psize) | rflags;
@@ -364,14 +365,14 @@ static long beat_lpar_hpte_insert_v3(unsigned long hpte_group,
*/
static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
unsigned long newpp,
- unsigned long va,
+ unsigned long vpn,
int psize, int ssize, int local)
{
unsigned long lpar_rc;
unsigned long want_v;
unsigned long pss;
- want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M);
+ want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc;
DBG_LOW(" update: "
@@ -392,16 +393,16 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot,
return 0;
}
-static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long va,
+static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long vpn,
int psize, int ssize, int local)
{
unsigned long want_v;
unsigned long lpar_rc;
unsigned long pss;
- DBG_LOW(" inval : slot=%lx, va=%016lx, psize: %d, local: %d\n",
- slot, va, psize, local);
- want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M);
+ DBG_LOW(" inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n",
+ slot, vpn, psize, local);
+ want_v = hpte_encode_v(vpn, psize, MMU_SEGSIZE_256M);
pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc;
lpar_rc = beat_invalidate_htab_entry3(0, slot, want_v, pss);
diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c
index 3124cf7..d00d7b0 100644
--- a/arch/powerpc/platforms/ps3/htab.c
+++ b/arch/powerpc/platforms/ps3/htab.c
@@ -43,7 +43,7 @@ enum ps3_lpar_vas_id {
static DEFINE_SPINLOCK(ps3_htab_lock);
-static long ps3_hpte_insert(unsigned long hpte_group, unsigned long va,
+static long ps3_hpte_insert(unsigned long hpte_group, unsigned long vpn,
unsigned long pa, unsigned long rflags, unsigned long vflags,
int psize, int ssize)
{
@@ -61,7 +61,7 @@ static long ps3_hpte_insert(unsigned long hpte_group, unsigned long va,
*/
vflags &= ~HPTE_V_SECONDARY;
- hpte_v = hpte_encode_v(va, psize, ssize) | vflags | HPTE_V_VALID;
+ hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID;
hpte_r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize) | rflags;
spin_lock_irqsave(&ps3_htab_lock, flags);
@@ -75,8 +75,8 @@ static long ps3_hpte_insert(unsigned long hpte_group, unsigned long va,
if (result) {
/* all entries bolted !*/
- pr_info("%s:result=%d va=%lx pa=%lx ix=%lx v=%llx r=%llx\n",
- __func__, result, va, pa, hpte_group, hpte_v, hpte_r);
+ pr_info("%s:result=%d vpn=%lx pa=%lx ix=%lx v=%llx r=%llx\n",
+ __func__, result, vpn, pa, hpte_group, hpte_v, hpte_r);
BUG();
}
@@ -107,7 +107,7 @@ static long ps3_hpte_remove(unsigned long hpte_group)
}
static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
- unsigned long va, int psize, int ssize, int local)
+ unsigned long vpn, int psize, int ssize, int local)
{
int result;
u64 hpte_v, want_v, hpte_rs;
@@ -115,7 +115,7 @@ static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
unsigned long flags;
long ret;
- want_v = hpte_encode_v(va, psize, ssize);
+ want_v = hpte_encode_v(vpn, psize, ssize);
spin_lock_irqsave(&ps3_htab_lock, flags);
@@ -125,8 +125,8 @@ static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp,
&hpte_rs);
if (result) {
- pr_info("%s: res=%d read va=%lx slot=%lx psize=%d\n",
- __func__, result, va, slot, psize);
+ pr_info("%s: res=%d read vpn=%lx slot=%lx psize=%d\n",
+ __func__, result, vpn, slot, psize);
BUG();
}
@@ -159,7 +159,7 @@ static void ps3_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
panic("ps3_hpte_updateboltedpp() not implemented");
}
-static void ps3_hpte_invalidate(unsigned long slot, unsigned long va,
+static void ps3_hpte_invalidate(unsigned long slot, unsigned long vpn,
int psize, int ssize, int local)
{
unsigned long flags;
@@ -170,8 +170,8 @@ static void ps3_hpte_invalidate(unsigned long slot, unsigned long va,
result = lv1_write_htab_entry(PS3_LPAR_VAS_ID_CURRENT, slot, 0, 0);
if (result) {
- pr_info("%s: res=%d va=%lx slot=%lx psize=%d\n",
- __func__, result, va, slot, psize);
+ pr_info("%s: res=%d vpn=%lx slot=%lx psize=%d\n",
+ __func__, result, vpn, slot, psize);
BUG();
}
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 5f3ef87..8308b25 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -108,9 +108,9 @@ void vpa_init(int cpu)
}
static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
- unsigned long va, unsigned long pa,
- unsigned long rflags, unsigned long vflags,
- int psize, int ssize)
+ unsigned long vpn, unsigned long pa,
+ unsigned long rflags, unsigned long vflags,
+ int psize, int ssize)
{
unsigned long lpar_rc;
unsigned long flags;
@@ -118,11 +118,11 @@ static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
unsigned long hpte_v, hpte_r;
if (!(vflags & HPTE_V_BOLTED))
- pr_devel("hpte_insert(group=%lx, va=%016lx, pa=%016lx, "
- "rflags=%lx, vflags=%lx, psize=%d)\n",
- hpte_group, va, pa, rflags, vflags, psize);
+ pr_devel("hpte_insert(group=%lx, vpn=%016lx, "
+ "pa=%016lx, rflags=%lx, vflags=%lx, psize=%d)\n",
+ hpte_group, vpn, pa, rflags, vflags, psize);
- hpte_v = hpte_encode_v(va, psize, ssize) | vflags | HPTE_V_VALID;
+ hpte_v = hpte_encode_v(vpn, psize, ssize) | vflags | HPTE_V_VALID;
hpte_r = hpte_encode_r(pa, psize) | rflags;
if (!(vflags & HPTE_V_BOLTED))
@@ -227,22 +227,6 @@ static void pSeries_lpar_hptab_clear(void)
}
/*
- * This computes the AVPN and B fields of the first dword of a HPTE,
- * for use when we want to match an existing PTE. The bottom 7 bits
- * of the returned value are zero.
- */
-static inline unsigned long hpte_encode_avpn(unsigned long va, int psize,
- int ssize)
-{
- unsigned long v;
-
- v = (va >> 23) & ~(mmu_psize_defs[psize].avpnm);
- v <<= HPTE_V_AVPN_SHIFT;
- v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
- return v;
-}
-
-/*
* NOTE: for updatepp ops we are fortunate that the linux "newpp" bits and
* the low 3 bits of flags happen to line up. So no transform is needed.
* We can probably optimize here and assume the high bits of newpp are
@@ -250,14 +234,14 @@ static inline unsigned long hpte_encode_avpn(unsigned long va, int psize,
*/
static long pSeries_lpar_hpte_updatepp(unsigned long slot,
unsigned long newpp,
- unsigned long va,
+ unsigned long vpn,
int psize, int ssize, int local)
{
unsigned long lpar_rc;
unsigned long flags = (newpp & 7) | H_AVPN;
unsigned long want_v;
- want_v = hpte_encode_avpn(va, psize, ssize);
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
pr_devel(" update: avpnv=%016lx, hash=%016lx, f=%lx, psize: %d ...",
want_v, slot, flags, psize);
@@ -295,15 +279,15 @@ static unsigned long pSeries_lpar_hpte_getword0(unsigned long slot)
return dword0;
}
-static long pSeries_lpar_hpte_find(unsigned long va, int psize, int ssize)
+static long pSeries_lpar_hpte_find(unsigned long vpn, int psize, int ssize)
{
unsigned long hash;
unsigned long i;
long slot;
unsigned long want_v, hpte_v;
- hash = hpt_hash(va, mmu_psize_defs[psize].shift, ssize);
- want_v = hpte_encode_avpn(va, psize, ssize);
+ hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize);
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
/* Bolted entries are always in the primary group */
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
@@ -323,12 +307,13 @@ static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
unsigned long ea,
int psize, int ssize)
{
- unsigned long lpar_rc, slot, vsid, va, flags;
+ unsigned long vpn;
+ unsigned long lpar_rc, slot, vsid, flags;
vsid = get_kernel_vsid(ea, ssize);
- va = hpt_va(ea, vsid, ssize);
+ vpn = hpt_vpn(ea, vsid, ssize);
- slot = pSeries_lpar_hpte_find(va, psize, ssize);
+ slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
BUG_ON(slot == -1);
flags = newpp & 7;
@@ -337,17 +322,17 @@ static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
BUG_ON(lpar_rc != H_SUCCESS);
}
-static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
+static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
int psize, int ssize, int local)
{
unsigned long want_v;
unsigned long lpar_rc;
unsigned long dummy1, dummy2;
- pr_devel(" inval : slot=%lx, va=%016lx, psize: %d, local: %d\n",
- slot, va, psize, local);
+ pr_devel(" inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n",
+ slot, vpn, psize, local);
- want_v = hpte_encode_avpn(va, psize, ssize);
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
lpar_rc = plpar_pte_remove(H_AVPN, slot, want_v, &dummy1, &dummy2);
if (lpar_rc == H_NOT_FOUND)
return;
@@ -358,15 +343,16 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va,
static void pSeries_lpar_hpte_removebolted(unsigned long ea,
int psize, int ssize)
{
- unsigned long slot, vsid, va;
+ unsigned long vpn;
+ unsigned long slot, vsid;
vsid = get_kernel_vsid(ea, ssize);
- va = hpt_va(ea, vsid, ssize);
+ vpn = hpt_vpn(ea, vsid, ssize);
- slot = pSeries_lpar_hpte_find(va, psize, ssize);
+ slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
BUG_ON(slot == -1);
- pSeries_lpar_hpte_invalidate(slot, va, psize, ssize, 0);
+ pSeries_lpar_hpte_invalidate(slot, vpn, psize, ssize, 0);
}
/* Flag bits for H_BULK_REMOVE */
@@ -382,12 +368,12 @@ static void pSeries_lpar_hpte_removebolted(unsigned long ea,
*/
static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
{
+ unsigned long vpn;
unsigned long i, pix, rc;
unsigned long flags = 0;
struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch);
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
unsigned long param[9];
- unsigned long va;
unsigned long hash, index, shift, hidx, slot;
real_pte_t pte;
int psize, ssize;
@@ -399,21 +385,21 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
ssize = batch->ssize;
pix = 0;
for (i = 0; i < number; i++) {
- va = batch->vaddr[i];
+ vpn = batch->vpn[i];
pte = batch->pte[i];
- pte_iterate_hashed_subpages(pte, psize, va, index, shift) {
- hash = hpt_hash(va, shift, ssize);
+ pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
+ hash = hpt_hash(vpn, shift, ssize);
hidx = __rpte_to_hidx(pte, index);
if (hidx & _PTEIDX_SECONDARY)
hash = ~hash;
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
slot += hidx & _PTEIDX_GROUP_IX;
if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
- pSeries_lpar_hpte_invalidate(slot, va, psize,
+ pSeries_lpar_hpte_invalidate(slot, vpn, psize,
ssize, local);
} else {
param[pix] = HBR_REQUEST | HBR_AVPN | slot;
- param[pix+1] = hpte_encode_avpn(va, psize,
+ param[pix+1] = hpte_encode_avpn(vpn, psize,
ssize);
pix += 2;
if (pix == 8) {
--
1.7.10
^ permalink raw reply related
* [PATCH -V8 03/11] arch/powerpc: Simplify hpte_decode
From: Aneesh Kumar K.V @ 2012-09-06 15:29 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1346945351-7672-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
This patch simplify hpte_decode for easy switching of virtual address to
virtual page number in the later patch
Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/mm/hash_native_64.c | 49 ++++++++++++++++++++++----------------
1 file changed, 28 insertions(+), 21 deletions(-)
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 90039bc..660b8bb 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -351,9 +351,10 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long va,
static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
int *psize, int *ssize, unsigned long *va)
{
+ unsigned long avpn, pteg, vpi;
unsigned long hpte_r = hpte->r;
unsigned long hpte_v = hpte->v;
- unsigned long avpn;
+ unsigned long vsid, seg_off;
int i, size, shift, penc;
if (!(hpte_v & HPTE_V_LARGE))
@@ -380,32 +381,38 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
}
/* 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;
- avpn = (HPTE_V_AVPN_VAL(hpte_v) & ~mmu_psize_defs[size].avpnm) << 23;
-
- if (shift < 23) {
- unsigned long vpi, vsid, pteg;
- pteg = slot / HPTES_PER_GROUP;
- if (hpte_v & HPTE_V_SECONDARY)
- pteg = ~pteg;
- switch (hpte_v >> HPTE_V_SSIZE_SHIFT) {
- case MMU_SEGSIZE_256M:
- vpi = ((avpn >> 28) ^ pteg) & htab_hash_mask;
- break;
- case MMU_SEGSIZE_1T:
- vsid = avpn >> 40;
+ avpn = (HPTE_V_AVPN_VAL(hpte_v) & ~mmu_psize_defs[size].avpnm);
+ pteg = slot / HPTES_PER_GROUP;
+ if (hpte_v & HPTE_V_SECONDARY)
+ pteg = ~pteg;
+
+ switch (*ssize) {
+ case MMU_SEGSIZE_256M:
+ /* We only have 28 - 23 bits of seg_off in avpn */
+ seg_off = (avpn & 0x1f) << 23;
+ vsid = avpn >> 5;
+ /* We can find more bits from the pteg value */
+ if (shift < 23) {
+ vpi = (vsid ^ pteg) & htab_hash_mask;
+ seg_off |= vpi << shift;
+ }
+ *va = vsid << SID_SHIFT | seg_off;
+ case MMU_SEGSIZE_1T:
+ /* We only have 40 - 23 bits of seg_off in avpn */
+ seg_off = (avpn & 0x1ffff) << 23;
+ vsid = avpn >> 17;
+ if (shift < 23) {
vpi = (vsid ^ (vsid << 25) ^ pteg) & htab_hash_mask;
- break;
- default:
- avpn = vpi = size = 0;
+ seg_off |= vpi << shift;
}
- avpn |= (vpi << mmu_psize_defs[size].shift);
+ *va = vsid << SID_SHIFT_1T | seg_off;
+ default:
+ *va = size = 0;
}
-
- *va = avpn;
*psize = size;
- *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
}
/*
--
1.7.10
^ permalink raw reply related
* [PATCH -V8 0/11] arch/powerpc: Add 64TB support to ppc64
From: Aneesh Kumar K.V @ 2012-09-06 15:29 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev
Hi,
This patchset include patches for supporting 64TB with ppc64. I haven't booted
this on hardware with 64TB memory yet. But they boot fine on real hardware with
less memory. Changes extend VSID bits to 38 bits for a 256MB segment
and 26 bits for 1TB segments.
Changes from V7:
* Address review feedback
Changes from V6:
* rebase to latest upstream (5b716ac728bcc01b1f2a7ed6e437196602237c27)
Changes from v5:
* Address review feedback
Changes from v4:
* Drop patch "arch/powerpc: properly offset the context bits for 1T segemnts"
based on review feedback
* split CONTEXT_BITS related changes from patch 12
* Add a new doc update patch
Changes from v3:
* Address review comments.
* Added new patch to ensure proto-VSID isolation between kernel and user space
Changes from V2:
* Fix few FIXMEs in the patchset. I have added them as separate patch for
easier review. That should help us to drop those changes if we don't agree.
Changes from V1:
* Drop the usage of structure (struct virt_addr) to carry virtual address.
We now represent virtual address via vpn which is virtual address shifted
right 12 bits.
Thanks,
-aneesh
^ permalink raw reply
* [PATCH -V8 01/11] arch/powerpc: Replace open coded CONTEXT_BITS value
From: Aneesh Kumar K.V @ 2012-09-06 15:29 UTC (permalink / raw)
To: benh, paulus; +Cc: linuxppc-dev, Aneesh Kumar K.V
In-Reply-To: <1346945351-7672-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com>
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
To clarify the meaning for future readers, replace the open coded
19 with CONTEXT_BITS
Reviewed-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
arch/powerpc/mm/mmu_context_hash64.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/mm/mmu_context_hash64.c b/arch/powerpc/mm/mmu_context_hash64.c
index 40677aa..daa076c 100644
--- a/arch/powerpc/mm/mmu_context_hash64.c
+++ b/arch/powerpc/mm/mmu_context_hash64.c
@@ -34,7 +34,7 @@ static DEFINE_IDA(mmu_context_ida);
* Each segment contains 2^28 bytes. Each context maps 2^44 bytes,
* so we can support 2^19-1 contexts (19 == 35 + 28 - 44).
*/
-#define MAX_CONTEXT ((1UL << 19) - 1)
+#define MAX_CONTEXT ((1UL << CONTEXT_BITS) - 1)
int __init_new_context(void)
{
--
1.7.10
^ permalink raw reply related
* Re: [PATCH] usb: gadget: fsl_udc_core: remove mapped flag
From: Felipe Balbi @ 2012-09-06 14:32 UTC (permalink / raw)
To: Enrico Scholz
Cc: Li Yang-R58472, Chen Peter-B29397, linux-usb@vger.kernel.org,
balbi@ti.com, gregkh@linuxfoundation.org,
linuxppc-dev@lists.ozlabs.org
In-Reply-To: <lya9x31atf.fsf@ensc-virt.intern.sigma-chemnitz.de>
[-- Attachment #1: Type: text/plain, Size: 406 bytes --]
On Thu, Sep 06, 2012 at 04:32:28PM +0200, Enrico Scholz wrote:
> Chen Peter-B29397 <B29397@freescale.com> writes:
>
> > If the class driver has already mapped this address, the req->req.dma is not
> > DMA_ADDR_INVALID either, in this case, the dma_sync_single_for_cpu is
> > enough.
>
> ok; forget the patch then.
fair enough, when can I get generic map/unmap conversion patch ?
--
balbi
[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply
* Re: [PATCH] usb: gadget: fsl_udc_core: remove mapped flag
From: Enrico Scholz @ 2012-09-06 14:32 UTC (permalink / raw)
To: Chen Peter-B29397
Cc: gregkh@linuxfoundation.org, linux-usb@vger.kernel.org,
linuxppc-dev@lists.ozlabs.org, Li Yang-R58472, balbi@ti.com
In-Reply-To: <F281D0F91ED19E4D8E63A7504E8A649803C67DB9@039-SN2MPN1-023.039d.mgd.msft.net>
Chen Peter-B29397 <B29397@freescale.com> writes:
> If the class driver has already mapped this address, the req->req.dma is not
> DMA_ADDR_INVALID either, in this case, the dma_sync_single_for_cpu is
> enough.
ok; forget the patch then.
Thanks
Enrico
^ permalink raw reply
* Re: [PATCH] usb: gadget: fsl_udc_core: do not immediatly prime STATUS for IN xfer
From: Felipe Balbi @ 2012-09-06 14:27 UTC (permalink / raw)
To: Enrico Scholz
Cc: Li Yang-R58472, Chen Peter-B29397, linux-usb@vger.kernel.org,
balbi, gregkh@linuxfoundation.org, linuxppc-dev@lists.ozlabs.org
In-Reply-To: <lyehmf1b27.fsf@ensc-virt.intern.sigma-chemnitz.de>
[-- Attachment #1: Type: text/plain, Size: 1730 bytes --]
Hi,
On Thu, Sep 06, 2012 at 04:27:12PM +0200, Enrico Scholz wrote:
> Felipe Balbi <balbi@ti.com> writes:
>
> >> > Because the fsl_udc_core driver shares one 'status_req' object for the
> >> > complete ep0 control transfer, it is not possible to prime the final
> >> > STATUS phase immediately after the IN transaction. E.g. ch9getstatus()
> >> > executed:
> >> >
> >> > | req = udc->status_req;
> >> > | ...
> >> > | list_add_tail(&req->queue, &ep->queue);
> >> > | if (ep0_prime_status(udc, EP_DIR_OUT))
> >> > | ....
> >> > | struct fsl_req *req = udc->status_req;
> >> > | list_add_tail(&req->queue, &ep->queue);
> >> >
> >> > which corrupts the ep->queue list by inserting 'status_req' twice. This
> >> > causes a kernel oops e.g. when 'lsusb -v' is executed on the host.
> >> >
> >> > Patch delays the final 'ep0_prime_status(udc, EP_DIR_OUT))' by moving it
> >> > into the ep0 completion handler.
> >> >
> >> Enrico, thanks for pointing this problem.
> >>
> >> As "prime STATUS phase immediately after the IN transaction" is followed
> >> USB 2.0 spec, to fix this problem, it is better to add data_req for ep0.
> >> In fact, it is already at FSL i.mx internal code, just still not mainlined.
> >
> > so, do I get an Acked-by to this patch ? Does it need to go on v3.6-rc
> > or can it wait until v3.7 merge window ?
>
> Without this (or the mentioned data_req patch), I can crash a g_multi
> gadget by executing 'lsusb -v' as root on the host. Should not be
> exploitable (only a BUG_ON() is triggered) but issue should be fixed
> asap.
cool, so I'll apply to my fixes branch as soon as I get Acked-by or
Tested-by from someone.
cheers
--
balbi
[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply
* Re: [PATCH] usb: gadget: fsl_udc_core: do not immediatly prime STATUS for IN xfer
From: Enrico Scholz @ 2012-09-06 14:27 UTC (permalink / raw)
To: balbi
Cc: Chen Peter-B29397, linux-usb@vger.kernel.org,
linuxppc-dev@lists.ozlabs.org, Li Yang-R58472,
gregkh@linuxfoundation.org
In-Reply-To: <20120906131708.GJ29202@arwen.pp.htv.fi>
Felipe Balbi <balbi@ti.com> writes:
>> > Because the fsl_udc_core driver shares one 'status_req' object for the
>> > complete ep0 control transfer, it is not possible to prime the final
>> > STATUS phase immediately after the IN transaction. E.g. ch9getstatus()
>> > executed:
>> >
>> > | req = udc->status_req;
>> > | ...
>> > | list_add_tail(&req->queue, &ep->queue);
>> > | if (ep0_prime_status(udc, EP_DIR_OUT))
>> > | ....
>> > | struct fsl_req *req = udc->status_req;
>> > | list_add_tail(&req->queue, &ep->queue);
>> >
>> > which corrupts the ep->queue list by inserting 'status_req' twice. This
>> > causes a kernel oops e.g. when 'lsusb -v' is executed on the host.
>> >
>> > Patch delays the final 'ep0_prime_status(udc, EP_DIR_OUT))' by moving it
>> > into the ep0 completion handler.
>> >
>> Enrico, thanks for pointing this problem.
>>
>> As "prime STATUS phase immediately after the IN transaction" is followed
>> USB 2.0 spec, to fix this problem, it is better to add data_req for ep0.
>> In fact, it is already at FSL i.mx internal code, just still not mainlined.
>
> so, do I get an Acked-by to this patch ? Does it need to go on v3.6-rc
> or can it wait until v3.7 merge window ?
Without this (or the mentioned data_req patch), I can crash a g_multi
gadget by executing 'lsusb -v' as root on the host. Should not be
exploitable (only a BUG_ON() is triggered) but issue should be fixed
asap.
Enrico
^ permalink raw reply
* Re: [PATCH] usb: gadget: fsl_udc_core: do not immediatly prime STATUS for IN xfer
From: Felipe Balbi @ 2012-09-06 13:17 UTC (permalink / raw)
To: Chen Peter-B29397
Cc: Li Yang-R58472, Enrico Scholz, linux-usb@vger.kernel.org,
balbi@ti.com, gregkh@linuxfoundation.org,
linuxppc-dev@lists.ozlabs.org
In-Reply-To: <F281D0F91ED19E4D8E63A7504E8A649803C67DA2@039-SN2MPN1-023.039d.mgd.msft.net>
[-- Attachment #1: Type: text/plain, Size: 1278 bytes --]
On Wed, Sep 05, 2012 at 02:10:39AM +0000, Chen Peter-B29397 wrote:
>
> >
> > Because the fsl_udc_core driver shares one 'status_req' object for the
> > complete ep0 control transfer, it is not possible to prime the final
> > STATUS phase immediately after the IN transaction. E.g. ch9getstatus()
> > executed:
> >
> > | req = udc->status_req;
> > | ...
> > | list_add_tail(&req->queue, &ep->queue);
> > | if (ep0_prime_status(udc, EP_DIR_OUT))
> > | ....
> > | struct fsl_req *req = udc->status_req;
> > | list_add_tail(&req->queue, &ep->queue);
> >
> > which corrupts the ep->queue list by inserting 'status_req' twice. This
> > causes a kernel oops e.g. when 'lsusb -v' is executed on the host.
> >
> > Patch delays the final 'ep0_prime_status(udc, EP_DIR_OUT))' by moving it
> > into the ep0 completion handler.
> >
> Enrico, thanks for pointing this problem.
>
> As "prime STATUS phase immediately after the IN transaction" is followed
> USB 2.0 spec, to fix this problem, it is better to add data_req for ep0.
> In fact, it is already at FSL i.mx internal code, just still not mainlined.
so, do I get an Acked-by to this patch ? Does it need to go on v3.6-rc
or can it wait until v3.7 merge window ?
--
balbi
[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply
* [PATCH] powerpc64: restore VDSO information on critical exception
From: Mihai Caraman @ 2012-09-06 12:49 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Mihai Caraman, kvm, kvm-ppc
Critical exception on 64-bit booke uses user-visible SPRG3 as scratch.
Restore VDSO information in SPRG3 on exception prolog.
Use a common sprg3 field in PACA for all powerpc64 architectures.
Signed-off-by: Mihai Caraman <mihai.caraman@freescale.com>
---
arch/powerpc/include/asm/kvm_book3s_asm.h | 1 -
arch/powerpc/include/asm/paca.h | 1 +
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/kernel/exceptions-64e.S | 4 +++-
arch/powerpc/kernel/vdso.c | 4 +---
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 +-
6 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index bfcd00c..88609b2 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -74,7 +74,6 @@ struct kvmppc_host_state {
ulong vmhandler;
ulong scratch0;
ulong scratch1;
- ulong sprg3;
u8 in_guest;
u8 restore_hid5;
u8 napping;
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index daf813f..7796519 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -136,6 +136,7 @@ struct paca_struct {
u8 io_sync; /* writel() needs spin_unlock sync */
u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */
u8 nap_state_lost; /* NV GPR values lost in power7_idle */
+ u64 sprg3; /* Saved user-visible sprg */
#ifdef CONFIG_PPC_POWERNV
/* Pointer to OPAL machine check event structure set by the
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 85b05c4..72f2616 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -205,6 +205,7 @@ int main(void)
DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost));
+ DEFINE(PACA_SPRG3, offsetof(struct paca_struct, sprg3));
#endif /* CONFIG_PPC64 */
/* RTAS */
@@ -533,7 +534,6 @@ int main(void)
HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
- HSTATE_FIELD(HSTATE_SPRG3, sprg3);
HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
HSTATE_FIELD(HSTATE_RESTORE_HID5, restore_hid5);
HSTATE_FIELD(HSTATE_NAPPING, napping);
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 7476b0a..87a82fb 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -110,7 +110,9 @@
#define PROLOG_STORE_RESTORE_SCRATCH_CRIT \
mfspr r10,SPRN_SPRG_CRIT_SCRATCH; /* get r13 */ \
- std r10,PACA_EXCRIT+EX_R13(r13)
+ std r10,PACA_EXCRIT+EX_R13(r13); \
+ ld r11,PACA_SPRG3(r13); \
+ mtspr SPRN_SPRG_CRIT_SCRATCH,r11;
/* Variants of the "addition" argument for the prolog
*/
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index b67db22..1b2076f 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -723,9 +723,7 @@ int __cpuinit vdso_getcpu_init(void)
val = (cpu & 0xfff) | ((node & 0xffff) << 16);
mtspr(SPRN_SPRG3, val);
-#ifdef CONFIG_KVM_BOOK3S_HANDLER
- get_paca()->kvm_hstate.sprg3 = val;
-#endif
+ get_paca()->sprg3 = val;
put_cpu();
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 5a84c8d..39a21bf 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1065,7 +1065,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
mtspr SPRN_DABRX,r6
/* Restore SPRG3 */
- ld r3,HSTATE_SPRG3(r13)
+ ld r3,PACA_SPRG3(r13)
mtspr SPRN_SPRG3,r3
/*
--
1.7.4.1
^ permalink raw reply related
* RE: [PATCH] [v2] sata_fsl: add workaround for data length mismatch on freescale V2 controller
From: Xie Shaohui-B21989 @ 2012-09-06 11:57 UTC (permalink / raw)
To: Sergei Shtylyov
Cc: linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org,
linux-ide@vger.kernel.org, David.Laight@ACULAB.COM,
Bhartiya Anju-B07263, jgarzik@pobox.com
In-Reply-To: <504888F8.5060907@mvista.com>
> >
> > hstatus =3D ioread32(hcr_base + HSTATUS);
> >
> > sata_fsl_scr_read(&ap->link, SCR_ERROR, &SError);
> >
> > + /* Read command completed register */
> > + done_mask =3D ioread32(hcr_base + CC);
> > +
> > + /* Workaround for data length mismatch errata */
> > + if (unlikely(hstatus & INT_ON_DATA_LENGTH_MISMATCH)) {
> > + for (tag =3D 0; tag < ATA_MAX_QUEUE; tag++) {
> > + qc =3D ata_qc_from_tag(ap, tag);
> > + if (qc && ata_is_atapi(qc->tf.protocol)) {
> > + u32 Hcontrol;
>=20
> No uppercase in variable names please.=20
[S.H] OK.
Besides, you have 'hstatus'
> variable already and that would be inconsistent.
[S.H] Yes, but I ignored fatal error and device error, so this won't be an =
issue.
>=20
> > +#define HCONTROL_CLEAR_ERROR (1 << 27)
> > + /* Set HControl[27] to clear error registers */
> > + Hcontrol =3D ioread32(hcr_base + HCONTROL);
> > + iowrite32(Hcontrol | HCONTROL_CLEAR_ERROR,
> > + hcr_base + HCONTROL);
> > +
> > + /* Clear HControl[27] */
> > + iowrite32(Hcontrol & (~HCONTROL_CLEAR_ERROR),
>=20
> Parens not needed around ~HCONTROL_CLEAR_ERROR.
[S.H] OK.
Best Regards,=20
Shaohui Xie
^ permalink raw reply
* Re: [PATCH] [v2] sata_fsl: add workaround for data length mismatch on freescale V2 controller
From: Sergei Shtylyov @ 2012-09-06 11:28 UTC (permalink / raw)
To: Shaohui Xie
Cc: linuxppc-dev, linux-kernel, linux-ide, David.Laight,
Anju Bhartiya, jgarzik
In-Reply-To: <1346905686-27912-1-git-send-email-Shaohui.Xie@freescale.com>
Hello.
On 06-09-2012 8:28, Shaohui Xie wrote:
> The freescale V2 SATA controller checks if the received data length matches
> the programmed length 'ttl', if not, it assumes that this is an error.
> In ATAPI, the 'ttl' is based on max allocation length and not the actual
> data transfer length, controller will raise 'DLM' (Data length Mismatch)
> error bit in Hstatus register. Along with 'DLM', DE (Device error) and
> FE (fatal Error) bits are also set in Hstatus register, 'E' (Internal Error)
> bit is set in Serror register and CE (Command Error) and DE (Device error)
> registers have the corresponding bit set. In this condition, we need to
> clear errors in following way: in the service routine, based on 'DLM' flag,
> HCONTROL[27] operation clears Hstatus, CE and DE registers, clear Serror
> register.
> Signed-off-by: Shaohui Xie <Shaohui.Xie@freescale.com>
> Signed-off-by: Anju Bhartiya <Anju.Bhartiya@freescale.com>
> ---
> changes for V2:
> 1. remove the using of quirk;
> 2. wrap errata codes in condition;
> drivers/ata/sata_fsl.c | 40 +++++++++++++++++++++++++++++++++++-----
> 1 files changed, 35 insertions(+), 5 deletions(-)
> diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
> index d6577b9..6b7b73e 100644
> --- a/drivers/ata/sata_fsl.c
> +++ b/drivers/ata/sata_fsl.c
[...]
> @@ -1180,26 +1181,55 @@ static void sata_fsl_host_intr(struct ata_port *ap)
> void __iomem *hcr_base = host_priv->hcr_base;
> u32 hstatus, done_mask = 0;
> struct ata_queued_cmd *qc;
> - u32 SError;
> + u32 SError, tag;
> + u32 status_mask = INT_ON_ERROR;
>
> hstatus = ioread32(hcr_base + HSTATUS);
>
> sata_fsl_scr_read(&ap->link, SCR_ERROR, &SError);
>
> + /* Read command completed register */
> + done_mask = ioread32(hcr_base + CC);
> +
> + /* Workaround for data length mismatch errata */
> + if (unlikely(hstatus & INT_ON_DATA_LENGTH_MISMATCH)) {
> + for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
> + qc = ata_qc_from_tag(ap, tag);
> + if (qc && ata_is_atapi(qc->tf.protocol)) {
> + u32 Hcontrol;
No uppercase in variable names please. Besides, you have 'hstatus'
variable already and that would be inconsistent.
> +#define HCONTROL_CLEAR_ERROR (1 << 27)
> + /* Set HControl[27] to clear error registers */
> + Hcontrol = ioread32(hcr_base + HCONTROL);
> + iowrite32(Hcontrol | HCONTROL_CLEAR_ERROR,
> + hcr_base + HCONTROL);
> +
> + /* Clear HControl[27] */
> + iowrite32(Hcontrol & (~HCONTROL_CLEAR_ERROR),
Parens not needed around ~HCONTROL_CLEAR_ERROR.
> + hcr_base + HCONTROL);
MBR, Sergei
^ permalink raw reply
* Re: [PATCH v2] powerpc: fix personality handling in ppc64_personality()
From: Jiri Kosina @ 2012-09-06 8:46 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: Paul Mackerras, Andreas Schwab, linuxppc-dev, linux-kernel
In-Reply-To: <1346879598.19098.4.camel@pasglop>
On Thu, 6 Sep 2012, Benjamin Herrenschmidt wrote:
> > actually commit 7256a5d2da56 seems to contain the correct PER_LINUX
> > handling, so seems like you picked the right one :)
> >
>
> Odd, they looked different around the use of PER_MASK when I looked but
The original patch had
personality &= ~PER_LINUX | PER_LINUX32;
Which is bogus, exactly because ~PER_LINUX is -1.
I then used
personality = (personality & ~PER_MASK) | PER_LINUX32;
which is correct and perhaps a little bit more descriptive, and that is
what you have merged, so all is fine.
> I was tired & jet lagged, so I might have just had a brain fail...
Probably just missed that the first patch used PER_LINUX and the second
one PER_MASK, or whatever.
Anyway, thanks.
--
Jiri Kosina
SUSE Labs
^ permalink raw reply
* Re: [RFC v9 PATCH 20/21] memory-hotplug: clear hwpoisoned flag when onlining pages
From: Wen Congyang @ 2012-09-06 8:41 UTC (permalink / raw)
To: andywu106建国
Cc: linux-s390, linux-ia64, len.brown, linux-acpi, linux-sh, x86,
linux-kernel, cmetcalf, linux-mm, isimatu.yasuaki, paulus,
minchan.kim, kosaki.motohiro, rientjes, sparclinux, cl,
linuxppc-dev, akpm, liuj97
In-Reply-To: <CA+quRcZtQCmFa4=1fq1iainQROy3NgtAXjLFF9cixs6KVXoMDA@mail.gmail.com>
At 09/06/2012 03:27 PM, andywu106=E5=BB=BA=E5=9B=BD Wrote:
> 2012/9/5 <wency@cn.fujitsu.com>
>>
>> From: Wen Congyang <wency@cn.fujitsu.com>
>>
>> hwpoisoned may set when we offline a page by the sysfs interface
>> /sys/devices/system/memory/soft=5Foffline=5Fpage or
>> /sys/devices/system/memory/hard=5Foffline=5Fpage. If we don't clear
>> this flag when onlining pages, this page can't be freed, and will
>> not in free list. So we can't offline these pages again. So we
>> should clear this flag when onlining pages.
>>
>> CC: David Rientjes <rientjes@google.com>
>> CC: Jiang Liu <liuj97@gmail.com>
>> CC: Len Brown <len.brown@intel.com>
>> CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
>> CC: Paul Mackerras <paulus@samba.org>
>> CC: Christoph Lameter <cl@linux.com>
>> Cc: Minchan Kim <minchan.kim@gmail.com>
>> CC: Andrew Morton <akpm@linux-foundation.org>
>> CC: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
>> CC: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
>> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
>> ---
>> mm/memory=5Fhotplug.c | 5 +++++
>> 1 files changed, 5 insertions(+), 0 deletions(-)
>>
>> diff --git a/mm/memory=5Fhotplug.c b/mm/memory=5Fhotplug.c
>> index 270c249..140c080 100644
>> --- a/mm/memory=5Fhotplug.c
>> +++ b/mm/memory=5Fhotplug.c
>> @@ -661,6 +661,11 @@ EXPORT=5FSYMBOL=5FGPL(=5F=5Fonline=5Fpage=5Fincreme=
nt=5Fcounters);
>>
>> void =5F=5Fonline=5Fpage=5Ffree(struct page *page)
>> {
>> +#ifdef CONFIG=5FMEMORY=5FFAILURE
>> + /* The page may be marked HWPoisoned by soft/hard offline page */
>> + ClearPageHWPoison(page);
>=20
> Hi Congyang,
> I think you should decrease mce=5Fbad=5Fpages counter her
> atomic=5Flong=5Fsub(1, &mce=5Fbad=5Fpages);
Yes, thanks for pointing it out.
Thanks
Wen Congyang
>=20
>>
>> +#endif
>> +
>> ClearPageReserved(page);
>> init=5Fpage=5Fcount(page);
>> =5F=5Ffree=5Fpage(page);
>> --
>> 1.7.1
>>
>> --
>> To unsubscribe, send a message with 'unsubscribe linux-mm' in
>> the body to majordomo@kvack.org. For more info on Linux MM,
>> see: http://www.linux-mm.org/ .
>> Don't email: <a href=3Dmailto:"dont@kvack.org"> email@kvack.org </a>
>=20
=
^ permalink raw reply
* Re: linux-next: build failure after merge of the final tree (powerpc tree related)
From: Ananth N Mavinakayanahalli @ 2012-09-06 8:20 UTC (permalink / raw)
To: Stephen Rothwell; +Cc: linux-next, Paul Mackerras, linuxppc-dev, linux-kernel
In-Reply-To: <20120906171153.c80e87ea8db3dd3f4ac87cf5@canb.auug.org.au>
On Thu, Sep 06, 2012 at 05:11:53PM +1000, Stephen Rothwell wrote:
> Hi all,
>
> After merging the final tree, today's linux-next build (powerpc allyesconfig)
> failed like this:
>
> In file included from drivers/atm/fore200e.c:70:0:
> drivers/atm/fore200e.h:263:3: error: redefinition of typedef 'opcode_t' with different type
> arch/powerpc/include/asm/probes.h:25:13: note: previous declaration of 'opcode_t' was here
>
> Caused by commit 7118e7e648e0 ("powerpc: Consolidate {k,u}probe
> definitions") from the powerpc tree.
>
> I have reverted that commit (and the two following:
> 41ab5266c362 "powerpc: Add trap_nr to thread_struct"
> 8b7b80b9ebb4 "powerpc: Uprobes port to powerpc")
> for today.
Hi Stephen,
I have just posted a patch [1] to fix the issue.
Ananth
[1] https://lists.ozlabs.org/pipermail/linuxppc-dev/2012-September/100813.html
^ permalink raw reply
* [PATCH] Rename opcode_t in probes.h to ppc_opcode_t
From: Ananth N Mavinakayanahalli @ 2012-09-06 8:17 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Stephen Rothwell
Cc: linuxppc-dev, Meelis Roos, Fengguang Wu, kernel-janitors,
David S. Miller
In-Reply-To: <1346900172.19098.17.camel@pasglop>
On Thu, Sep 06, 2012 at 12:56:12PM +1000, Benjamin Herrenschmidt wrote:
> On Thu, 2012-09-06 at 10:19 +0800, Fengguang Wu wrote:
> > Hi Ananth,
> >
> > FYI, kernel build failed on
> >
> > tree: git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc.git next
> > head: 8b64a9dfb091f1eca8b7e58da82f1e7d1d5fe0ad
> > commit: 8b7b80b9ebb46dd88fbb94e918297295cf312b59 [24/29] powerpc: Uprobes port to powerpc
> > config: powerpc-allmodconfig (attached as .config)
> >
> > All related error/warning messages:
> >
> > In file included from drivers/atm/fore200e.c:70:0:
> > drivers/atm/fore200e.h:263:3: error: redefinition of typedef 'opcode_t' with different type
> > arch/powerpc/include/asm/probes.h:25:13: note: previous declaration of 'opcode_t' was here
>
> This is a bit more annoying. Ananth, do we need that to be called
> opcode_t for generic reasons or can we make it ppc_opcode_t ? If it has
> to remain, I suppose we can try to change that ATM driver to use a
> different type name...
We can make it ppc_opcode_t. Attached is the patch that fixes this.
Regards,
Ananth
---
From: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
tree: git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc.git next
head: 8b64a9dfb091f1eca8b7e58da82f1e7d1d5fe0ad
commit: 8b7b80b9ebb46dd88fbb94e918297295cf312b59 [24/29] powerpc: Uprobes port to powerpc
config: powerpc-allmodconfig (attached as .config)
All related error/warning messages:
In file included from drivers/atm/fore200e.c:70:0:
drivers/atm/fore200e.h:263:3: error: redefinition of typedef 'opcode_t' with different type
arch/powerpc/include/asm/probes.h:25:13: note: previous declaration of 'opcode_t' was here
Fix the namespace clash by making opcode_t in probes.h to ppc_opcode_t.
Signed-off-by: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
---
Index: linux-tip-22aug/arch/powerpc/include/asm/probes.h
===================================================================
--- linux-tip-22aug.orig/arch/powerpc/include/asm/probes.h 2012-09-04 20:00:19.747069793 +0530
+++ linux-tip-22aug/arch/powerpc/include/asm/probes.h 2012-09-04 20:42:08.147286718 +0530
@@ -22,7 +22,7 @@
*/
#include <linux/types.h>
-typedef u32 opcode_t;
+typedef u32 ppc_opcode_t;
#define BREAKPOINT_INSTRUCTION 0x7fe00008 /* trap */
/* Trap definitions per ISA */
Index: linux-tip-22aug/arch/powerpc/include/asm/uprobes.h
===================================================================
--- linux-tip-22aug.orig/arch/powerpc/include/asm/uprobes.h 2012-09-04 20:01:30.617071747 +0530
+++ linux-tip-22aug/arch/powerpc/include/asm/uprobes.h 2012-09-04 20:42:26.657287349 +0530
@@ -25,7 +25,7 @@
#include <linux/notifier.h>
#include <asm/probes.h>
-typedef opcode_t uprobe_opcode_t;
+typedef ppc_opcode_t uprobe_opcode_t;
#define MAX_UINSN_BYTES 4
#define UPROBE_XOL_SLOT_BYTES (MAX_UINSN_BYTES)
Index: linux-tip-22aug/arch/powerpc/include/asm/kprobes.h
===================================================================
--- linux-tip-22aug.orig/arch/powerpc/include/asm/kprobes.h 2012-09-04 20:00:19.747069793 +0530
+++ linux-tip-22aug/arch/powerpc/include/asm/kprobes.h 2012-09-04 20:42:15.557286955 +0530
@@ -36,7 +36,7 @@
struct pt_regs;
struct kprobe;
-typedef opcode_t kprobe_opcode_t;
+typedef ppc_opcode_t kprobe_opcode_t;
#define MAX_INSN_SIZE 1
#ifdef CONFIG_PPC64
^ permalink raw reply
* Re: [RFC v9 PATCH 20/21] memory-hotplug: clear hwpoisoned flag when onlining pages
From: andywu106建国 @ 2012-09-06 7:27 UTC (permalink / raw)
To: wency
Cc: linux-s390, linux-ia64, len.brown, linux-acpi, linux-sh, x86,
linux-kernel, cmetcalf, linux-mm, isimatu.yasuaki, paulus,
minchan.kim, kosaki.motohiro, rientjes, sparclinux, cl,
linuxppc-dev, akpm, liuj97
In-Reply-To: <1346837155-534-21-git-send-email-wency@cn.fujitsu.com>
2012/9/5 <wency@cn.fujitsu.com>
>
> From: Wen Congyang <wency@cn.fujitsu.com>
>
> hwpoisoned may set when we offline a page by the sysfs interface
> /sys/devices/system/memory/soft_offline_page or
> /sys/devices/system/memory/hard_offline_page. If we don't clear
> this flag when onlining pages, this page can't be freed, and will
> not in free list. So we can't offline these pages again. So we
> should clear this flag when onlining pages.
>
> CC: David Rientjes <rientjes@google.com>
> CC: Jiang Liu <liuj97@gmail.com>
> CC: Len Brown <len.brown@intel.com>
> CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> CC: Paul Mackerras <paulus@samba.org>
> CC: Christoph Lameter <cl@linux.com>
> Cc: Minchan Kim <minchan.kim@gmail.com>
> CC: Andrew Morton <akpm@linux-foundation.org>
> CC: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
> CC: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
> Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
> ---
> mm/memory_hotplug.c | 5 +++++
> 1 files changed, 5 insertions(+), 0 deletions(-)
>
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index 270c249..140c080 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -661,6 +661,11 @@ EXPORT_SYMBOL_GPL(__online_page_increment_counters);
>
> void __online_page_free(struct page *page)
> {
> +#ifdef CONFIG_MEMORY_FAILURE
> + /* The page may be marked HWPoisoned by soft/hard offline page */
> + ClearPageHWPoison(page);
Hi Congyang,
I think you should decrease mce_bad_pages counter her
atomic_long_sub(1, &mce_bad_pages);
>
> +#endif
> +
> ClearPageReserved(page);
> init_page_count(page);
> __free_page(page);
> --
> 1.7.1
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* linux-next: build failure after merge of the final tree (powerpc tree related)
From: Stephen Rothwell @ 2012-09-06 7:11 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, linuxppc-dev
Cc: linux-next, linux-kernel
[-- Attachment #1: Type: text/plain, Size: 698 bytes --]
Hi all,
After merging the final tree, today's linux-next build (powerpc allyesconfig)
failed like this:
In file included from drivers/atm/fore200e.c:70:0:
drivers/atm/fore200e.h:263:3: error: redefinition of typedef 'opcode_t' with different type
arch/powerpc/include/asm/probes.h:25:13: note: previous declaration of 'opcode_t' was here
Caused by commit 7118e7e648e0 ("powerpc: Consolidate {k,u}probe
definitions") from the powerpc tree.
I have reverted that commit (and the two following:
41ab5266c362 "powerpc: Add trap_nr to thread_struct"
8b7b80b9ebb4 "powerpc: Uprobes port to powerpc")
for today.
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply
* Re: [RFC PATCH V6 10/19] memory-hotplug: add memory_block_release
From: wujianguo @ 2012-09-06 7:06 UTC (permalink / raw)
To: wency
Cc: linux-s390, linux-ia64, linux-acpi, len.brown, linux-sh,
linux-kernel, cmetcalf, linux-mm, isimatu.yasuaki, paulus,
minchan.kim, kosaki.motohiro, rientjes, cl, linuxppc-dev, akpm,
liuj97
In-Reply-To: <1343980161-14254-11-git-send-email-wency@cn.fujitsu.com>
On 2012-8-3 15:49, wency@cn.fujitsu.com wrote:
> From: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
>
> When calling remove_memory_block(), the function shows following message at
> device_release().
>
> Device 'memory528' does not have a release() function, it is broken and must
> be fixed.
>
I found this warning too when doing memory-hotplug,
why not send as a bug fix patch?
The same as [RFC PATCH V6 18/19] memory-hotplug: add node_device_release
> remove_memory_block() calls kfree(mem). I think it shouled be called from
> device_release(). So the patch implements memory_block_release()
>
> CC: David Rientjes <rientjes@google.com>
> CC: Jiang Liu <liuj97@gmail.com>
> CC: Len Brown <len.brown@intel.com>
> CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> CC: Paul Mackerras <paulus@samba.org>
> CC: Christoph Lameter <cl@linux.com>
> Cc: Minchan Kim <minchan.kim@gmail.com>
> CC: Andrew Morton <akpm@linux-foundation.org>
> CC: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
> CC: Wen Congyang <wency@cn.fujitsu.com>
> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
> ---
> drivers/base/memory.c | 11 ++++++++++-
> 1 files changed, 10 insertions(+), 1 deletions(-)
>
> diff --git a/drivers/base/memory.c b/drivers/base/memory.c
> index 038be73..1cd3ef3 100644
> --- a/drivers/base/memory.c
> +++ b/drivers/base/memory.c
> @@ -109,6 +109,15 @@ bool is_memblk_offline(unsigned long start, unsigned long size)
> }
> EXPORT_SYMBOL(is_memblk_offline);
>
> +#define to_memory_block(device) container_of(device, struct memory_block, dev)
> +
> +static void release_memory_block(struct device *dev)
> +{
> + struct memory_block *mem = to_memory_block(dev);
> +
> + kfree(mem);
> +}
> +
> /*
> * register_memory - Setup a sysfs device for a memory block
> */
> @@ -119,6 +128,7 @@ int register_memory(struct memory_block *memory)
>
> memory->dev.bus = &memory_subsys;
> memory->dev.id = memory->start_section_nr / sections_per_block;
> + memory->dev.release = release_memory_block;
>
> error = device_register(&memory->dev);
> return error;
> @@ -674,7 +684,6 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section,
> mem_remove_simple_file(mem, phys_device);
> mem_remove_simple_file(mem, removable);
> unregister_memory(mem);
> - kfree(mem);
> } else
> kobject_put(&mem->dev.kobj);
>
>
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox