powerpc/mm/hash: Use context ids 1-4 for the kernel

Currently we use the top 4 context ids (0x7fffc-0x7ffff) for the kernel.
Kernel VSIDs are built using these top context values and effective the
segement ID. In subsequent patches we want to increase the max effective
address to 512TB. We will achieve that by increasing the effective
segment IDs there by increasing virtual address range.

We will be switching to a 68bit virtual address in the following patch.
But platforms like Power4 and Power5 only support a 65 bit virtual
address. We will handle that by limiting the context bits to 16 instead
of 19 on those platforms. That means the max context id will have a
different value on different platforms.

So that we don't have to deal with the kernel context ids changing
between different platforms, move the kernel context ids down to use
context ids 1-4.

We can't use segment 0 of context-id 0, because that maps to VSID 0,
which we want to keep as invalid, so we avoid context-id 0 entirely.
Similarly we can't use the last segment of the maximum context, so we
avoid it too.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[mpe: Switch from 0-3 to 1-4 so VSID=0 remains invalid]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 52d8d1e4b772e27bc333786a49d61d943d2d01df..a5ab6f5b8a7f81bc35a2dd209d9b607d50e68407 100644 (file)
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -491,13 +491,14 @@ extern void slb_set_size(u16 size);
  * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated
  * from mmu context id and effective segment id of the address.
  *
- * For user processes max context id is limited to ((1ul << 19) - 5)
- * for kernel space, we use the top 4 context ids to map address as below
+ * For user processes max context id is limited to MAX_USER_CONTEXT.
+
+ * For kernel space, we use context ids 1-5 to map address as below:
  * NOTE: each context only support 64TB now.
- * 0x7fffc -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
- * 0x7fffd -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
- * 0x7fffe -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
- * 0x7ffff -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
+ * 0x00001 -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
+ * 0x00002 -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
+ * 0x00003 -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
+ * 0x00004 -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
  *
  * The proto-VSIDs are then scrambled into real VSIDs with the
  * multiplicative hash:
@@ -511,15 +512,13 @@ extern void slb_set_size(u16 size);
  * robust scattering in the hash table (at least based on some initial
  * results).
  *
- * We also consider VSID 0 special. We use VSID 0 for slb entries mapping
- * bad address. This enables us to consolidate bad address handling in
- * hash_page.
+ * We use VSID 0 to indicate an invalid VSID. The means we can't use context id
+ * 0, because a context id of 0 and an EA of 0 gives a proto-VSID of 0, which
+ * will produce a VSID of 0.
  *
  * We also need to avoid the last segment of the last context, because that
  * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
- * because of the modulo operation in vsid scramble. But the vmemmap
- * (which is what uses region 0xf) will never be close to 64TB in size
- * (it's 56 bytes per page of system memory).
+ * because of the modulo operation in vsid scramble.
  */
 
 #define CONTEXT_BITS           19
@@ -532,12 +531,19 @@ extern void slb_set_size(u16 size);
 /*
  * 256MB segment
  * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments
- * available for user + kernel mapping. The top 4 contexts are used for
- * kernel mapping. Each segment contains 2^28 bytes. Each
- * context maps 2^46 bytes (64TB) so we can support 2^19-1 contexts
- * (19 == 37 + 28 - 46).
+ * available for user + kernel mapping. VSID 0 is reserved as invalid, contexts
+ * 1-4 are used for kernel mapping. Each segment contains 2^28 bytes. Each
+ * context maps 2^46 bytes (64TB).
+ *
+ * We also need to avoid the last segment of the last context, because that
+ * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
+ * because of the modulo operation in vsid scramble.
  */
-#define MAX_USER_CONTEXT       ((ASM_CONST(1) << CONTEXT_BITS) - 5)
+#define MAX_USER_CONTEXT       ((ASM_CONST(1) << CONTEXT_BITS) - 2)
+#define MIN_USER_CONTEXT       (5)
+
+/* Would be nice to use KERNEL_REGION_ID here */
+#define KERNEL_REGION_CONTEXT_OFFSET   (0xc - 1)
 
 /*
  * This should be computed such that protovosid * vsid_mulitplier
@@ -671,21 +677,25 @@ static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
 
 /*
  * This is only valid for addresses >= PAGE_OFFSET
- *
- * For kernel space, we use the top 4 context ids to map address as below
- * 0x7fffc -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
- * 0x7fffd -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
- * 0x7fffe -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
- * 0x7ffff -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
  */
 static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
 {
        unsigned long context;
 
        /*
-        * kernel take the top 4 context from the available range
+        * For kernel space, we use context ids 1-4 to map the address space as
+        * below:
+        *
+        * 0x00001 -  [ 0xc000000000000000 - 0xc0003fffffffffff ]
+        * 0x00002 -  [ 0xd000000000000000 - 0xd0003fffffffffff ]
+        * 0x00003 -  [ 0xe000000000000000 - 0xe0003fffffffffff ]
+        * 0x00004 -  [ 0xf000000000000000 - 0xf0003fffffffffff ]
+        *
+        * So we can compute the context from the region (top nibble) by
+        * subtracting 11, or 0xc - 1.
         */
-       context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1;
+       context = (ea >> 60) - KERNEL_REGION_CONTEXT_OFFSET;
+
        return get_vsid(context, ea, ssize);
 }
 

diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index e5da551edde33f98699bd0bfe37009b4e94c27ec..a10e972221c40bf801535899a294580114d18771 100644 (file)
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -59,7 +59,7 @@ again:
 
 int hash__alloc_context_id(void)
 {
-       return alloc_context_id(1, MAX_USER_CONTEXT);
+       return alloc_context_id(MIN_USER_CONTEXT, MAX_USER_CONTEXT);
 }
 EXPORT_SYMBOL_GPL(hash__alloc_context_id);
 

diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index a85e06ea6c2040a84f702b3c41b761808377552e..ba1f8696c3388ecce9ee7b6085cc171e0d88b1d5 100644 (file)
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -45,13 +45,6 @@ _GLOBAL(slb_allocate_realmode)
        /* r3 = address, r10 = esid, cr7 = <> PAGE_OFFSET */
        blt     cr7,0f                  /* user or kernel? */
 
-       /* kernel address: proto-VSID = ESID */
-       /* WARNING - MAGIC: we don't use the VSID 0xfffffffff, but
-        * this code will generate the protoVSID 0xfffffffff for the
-        * top segment.  That's ok, the scramble below will translate
-        * it to VSID 0, which is reserved as a bad VSID - one which
-        * will never have any pages in it.  */
-
        /* Check if hitting the linear mapping or some other kernel space
        */
        bne     cr7,1f
@@ -63,12 +56,10 @@ _GLOBAL(slb_allocate_realmode)
 slb_miss_kernel_load_linear:
        li      r11,0
        /*
-        * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
+        * context = (ea >> 60) - (0xc - 1)
         * r9 = region id.
         */
-       addis   r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha
-       addi    r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l
-
+       subi    r9,r9,KERNEL_REGION_CONTEXT_OFFSET
 
 BEGIN_FTR_SECTION
        b       .Lslb_finish_load
@@ -77,9 +68,9 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
 
 1:
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-       /* Check virtual memmap region. To be patches at kernel boot */
        cmpldi  cr0,r9,0xf
        bne     1f
+/* Check virtual memmap region. To be patched at kernel boot */
 .globl slb_miss_kernel_load_vmemmap
 slb_miss_kernel_load_vmemmap:
        li      r11,0
@@ -102,11 +93,10 @@ slb_miss_kernel_load_io:
        li      r11,0
 6:
        /*
-        * context = (MAX_USER_CONTEXT) + ((ea >> 60) - 0xc) + 1
+        * context = (ea >> 60) - (0xc - 1)
         * r9 = region id.
         */
-       addis   r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@ha
-       addi    r9,r9,(MAX_USER_CONTEXT - 0xc + 1)@l
+       subi    r9,r9,KERNEL_REGION_CONTEXT_OFFSET
 
 BEGIN_FTR_SECTION
        b       .Lslb_finish_load