[PATCH] ppc64: support 64k pages
Adds a new CONFIG_PPC_64K_PAGES which, when enabled, changes the kernel
base page size to 64K. The resulting kernel still boots on any
hardware. On current machines with 4K pages support only, the kernel
will maintain 16 "subpages" for each 64K page transparently.
Note that while real 64K capable HW has been tested, the current patch
will not enable it yet as such hardware is not released yet, and I'm
still verifying with the firmware architects the proper to get the
information from the newer hypervisors.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S
index a3a03da..3e18241 100644
--- a/arch/powerpc/mm/slb_low.S
+++ b/arch/powerpc/mm/slb_low.S
@@ -18,25 +18,161 @@
#include <linux/config.h>
#include <asm/processor.h>
-#include <asm/page.h>
-#include <asm/mmu.h>
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
#include <asm/cputable.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/pgtable.h>
-/* void slb_allocate(unsigned long ea);
+/* void slb_allocate_realmode(unsigned long ea);
*
* Create an SLB entry for the given EA (user or kernel).
* r3 = faulting address, r13 = PACA
* r9, r10, r11 are clobbered by this function
* No other registers are examined or changed.
*/
-_GLOBAL(slb_allocate)
- /*
- * First find a slot, round robin. Previously we tried to find
- * a free slot first but that took too long. Unfortunately we
- * dont have any LRU information to help us choose a slot.
+_GLOBAL(slb_allocate_realmode)
+ /* r3 = faulting address */
+
+ srdi r9,r3,60 /* get region */
+ srdi r10,r3,28 /* get esid */
+ cmpldi cr7,r9,0xc /* cmp KERNELBASE for later use */
+
+ /* r3 = address, r10 = esid, cr7 = <>KERNELBASE */
+ 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 of the vmalloc/ioremap
+ * kernel space
+ */
+ bne cr7,1f
+
+ /* Linear mapping encoding bits, the "li" instruction below will
+ * be patched by the kernel at boot
*/
+_GLOBAL(slb_miss_kernel_load_linear)
+ li r11,0
+ b slb_finish_load
+
+1: /* vmalloc/ioremap mapping encoding bits, the "li" instruction below
+ * will be patched by the kernel at boot
+ */
+_GLOBAL(slb_miss_kernel_load_virtual)
+ li r11,0
+ b slb_finish_load
+
+
+0: /* user address: proto-VSID = context << 15 | ESID. First check
+ * if the address is within the boundaries of the user region
+ */
+ srdi. r9,r10,USER_ESID_BITS
+ bne- 8f /* invalid ea bits set */
+
+ /* Figure out if the segment contains huge pages */
+#ifdef CONFIG_HUGETLB_PAGE
+BEGIN_FTR_SECTION
+ b 1f
+END_FTR_SECTION_IFCLR(CPU_FTR_16M_PAGE)
+ lhz r9,PACAHIGHHTLBAREAS(r13)
+ srdi r11,r10,(HTLB_AREA_SHIFT-SID_SHIFT)
+ srd r9,r9,r11
+ lhz r11,PACALOWHTLBAREAS(r13)
+ srd r11,r11,r10
+ or. r9,r9,r11
+ beq 1f
+_GLOBAL(slb_miss_user_load_huge)
+ li r11,0
+ b 2f
+1:
+#endif /* CONFIG_HUGETLB_PAGE */
+
+_GLOBAL(slb_miss_user_load_normal)
+ li r11,0
+
+2:
+ ld r9,PACACONTEXTID(r13)
+ rldimi r10,r9,USER_ESID_BITS,0
+ b slb_finish_load
+
+8: /* invalid EA */
+ li r10,0 /* BAD_VSID */
+ li r11,SLB_VSID_USER /* flags don't much matter */
+ b slb_finish_load
+
+#ifdef __DISABLED__
+
+/* void slb_allocate_user(unsigned long ea);
+ *
+ * Create an SLB entry for the given EA (user or kernel).
+ * r3 = faulting address, r13 = PACA
+ * r9, r10, r11 are clobbered by this function
+ * No other registers are examined or changed.
+ *
+ * It is called with translation enabled in order to be able to walk the
+ * page tables. This is not currently used.
+ */
+_GLOBAL(slb_allocate_user)
+ /* r3 = faulting address */
+ srdi r10,r3,28 /* get esid */
+
+ crset 4*cr7+lt /* set "user" flag for later */
+
+ /* check if we fit in the range covered by the pagetables*/
+ srdi. r9,r3,PGTABLE_EADDR_SIZE
+ crnot 4*cr0+eq,4*cr0+eq
+ beqlr
+
+ /* now we need to get to the page tables in order to get the page
+ * size encoding from the PMD. In the future, we'll be able to deal
+ * with 1T segments too by getting the encoding from the PGD instead
+ */
+ ld r9,PACAPGDIR(r13)
+ cmpldi cr0,r9,0
+ beqlr
+ rlwinm r11,r10,8,25,28
+ ldx r9,r9,r11 /* get pgd_t */
+ cmpldi cr0,r9,0
+ beqlr
+ rlwinm r11,r10,3,17,28
+ ldx r9,r9,r11 /* get pmd_t */
+ cmpldi cr0,r9,0
+ beqlr
+
+ /* build vsid flags */
+ andi. r11,r9,SLB_VSID_LLP
+ ori r11,r11,SLB_VSID_USER
+
+ /* get context to calculate proto-VSID */
+ ld r9,PACACONTEXTID(r13)
+ rldimi r10,r9,USER_ESID_BITS,0
+
+ /* fall through slb_finish_load */
+
+#endif /* __DISABLED__ */
+
+
+/*
+ * Finish loading of an SLB entry and return
+ *
+ * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9, cr7 = <>KERNELBASE
+ */
+slb_finish_load:
+ ASM_VSID_SCRAMBLE(r10,r9)
+ rldimi r11,r10,SLB_VSID_SHIFT,16 /* combine VSID and flags */
+
+ /* r3 = EA, r11 = VSID data */
+ /*
+ * Find a slot, round robin. Previously we tried to find a
+ * free slot first but that took too long. Unfortunately we
+ * dont have any LRU information to help us choose a slot.
+ */
#ifdef CONFIG_PPC_ISERIES
/*
* On iSeries, the "bolted" stack segment can be cast out on
@@ -45,9 +181,9 @@
*/
ld r9,PACAKSAVE(r13)
clrrdi r9,r9,28
- clrrdi r11,r3,28
+ clrrdi r3,r3,28
li r10,SLB_NUM_BOLTED-1 /* Stack goes in last bolted slot */
- cmpld r9,r11
+ cmpld r9,r3
beq 3f
#endif /* CONFIG_PPC_ISERIES */
@@ -61,63 +197,12 @@
4:
std r10,PACASTABRR(r13)
+
3:
- /* r3 = faulting address, r10 = entry */
+ rldimi r3,r10,0,36 /* r3= EA[0:35] | entry */
+ oris r10,r3,SLB_ESID_V@h /* r3 |= SLB_ESID_V */
- srdi r9,r3,60 /* get region */
- srdi r3,r3,28 /* get esid */
- cmpldi cr7,r9,0xc /* cmp KERNELBASE for later use */
-
- rldimi r10,r3,28,0 /* r10= ESID<<28 | entry */
- oris r10,r10,SLB_ESID_V@h /* r10 |= SLB_ESID_V */
-
- /* r3 = esid, r10 = esid_data, cr7 = <>KERNELBASE */
-
- 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. */
- li r11,SLB_VSID_KERNEL
-BEGIN_FTR_SECTION
- bne cr7,9f
- li r11,(SLB_VSID_KERNEL|SLB_VSID_L)
-END_FTR_SECTION_IFSET(CPU_FTR_16M_PAGE)
- b 9f
-
-0: /* user address: proto-VSID = context<<15 | ESID */
- srdi. r9,r3,USER_ESID_BITS
- bne- 8f /* invalid ea bits set */
-
-#ifdef CONFIG_HUGETLB_PAGE
-BEGIN_FTR_SECTION
- lhz r9,PACAHIGHHTLBAREAS(r13)
- srdi r11,r3,(HTLB_AREA_SHIFT-SID_SHIFT)
- srd r9,r9,r11
- lhz r11,PACALOWHTLBAREAS(r13)
- srd r11,r11,r3
- or r9,r9,r11
-END_FTR_SECTION_IFSET(CPU_FTR_16M_PAGE)
-#endif /* CONFIG_HUGETLB_PAGE */
-
- li r11,SLB_VSID_USER
-
-#ifdef CONFIG_HUGETLB_PAGE
-BEGIN_FTR_SECTION
- rldimi r11,r9,8,55 /* shift masked bit into SLB_VSID_L */
-END_FTR_SECTION_IFSET(CPU_FTR_16M_PAGE)
-#endif /* CONFIG_HUGETLB_PAGE */
-
- ld r9,PACACONTEXTID(r13)
- rldimi r3,r9,USER_ESID_BITS,0
-
-9: /* r3 = protovsid, r11 = flags, r10 = esid_data, cr7 = <>KERNELBASE */
- ASM_VSID_SCRAMBLE(r3,r9)
-
- rldimi r11,r3,SLB_VSID_SHIFT,16 /* combine VSID and flags */
+ /* r3 = ESID data, r11 = VSID data */
/*
* No need for an isync before or after this slbmte. The exception
@@ -125,7 +210,9 @@
*/
slbmte r11,r10
- bgelr cr7 /* we're done for kernel addresses */
+ /* we're done for kernel addresses */
+ crclr 4*cr0+eq /* set result to "success" */
+ bgelr cr7
/* Update the slb cache */
lhz r3,PACASLBCACHEPTR(r13) /* offset = paca->slb_cache_ptr */
@@ -143,9 +230,6 @@
li r3,SLB_CACHE_ENTRIES+1
2:
sth r3,PACASLBCACHEPTR(r13) /* paca->slb_cache_ptr = offset */
+ crclr 4*cr0+eq /* set result to "success" */
blr
-8: /* invalid EA */
- li r3,0 /* BAD_VSID */
- li r11,SLB_VSID_USER /* flags don't much matter */
- b 9b