From 9420dc65ff9e6b67c032286efde823aeb8684670 Mon Sep 17 00:00:00 2001 From: Jesper Juhl Date: Mon, 30 Jul 2007 08:18:25 +1000 Subject: [POWERPC] Clean out a bunch of duplicate includes This removes several duplicate includes from arch/powerpc/. Signed-off-by: Jesper Juhl Acked-by: Benjamin Herrenschmidt Signed-off-by: Paul Mackerras --- arch/powerpc/mm/hash_utils_64.c | 1 - arch/powerpc/mm/hugetlbpage.c | 3 --- arch/powerpc/mm/init_32.c | 1 - arch/powerpc/mm/mem.c | 1 - 4 files changed, 6 deletions(-) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index a47151e806ca..c74af42eb9c1 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -49,7 +49,6 @@ #include #include #include -#include #include #include diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 4835f73af304..ba5f12a60467 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -22,11 +22,8 @@ #include #include #include -#include #include -#include - #define NUM_LOW_AREAS (0x100000000UL >> SID_SHIFT) #define NUM_HIGH_AREAS (PGTABLE_RANGE >> HTLB_AREA_SHIFT) diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index e1f5ded851f6..d65995ae8273 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -41,7 +41,6 @@ #include #include #include -#include #include #include diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index f0e7eedb1ba3..32dcfc9b0082 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -42,7 +42,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From 9dfe5c53d0fcc08e9efc1e13bb6702fac74f4a12 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 15 Aug 2007 16:33:55 +1000 Subject: [POWERPC] Fix non HUGETLB_PAGE build warning arch/powerpc/mm/mmu_context_64.c: In function 'init_new_context': arch/powerpc/mm/mmu_context_64.c:31: warning: unused variable 'new_context' Signed-off-by: Stephen Rothwell Signed-off-by: Paul Mackerras --- arch/powerpc/mm/mmu_context_64.c | 5 ++--- arch/powerpc/mm/slice.c | 1 + 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/mmu_context_64.c b/arch/powerpc/mm/mmu_context_64.c index 7a78cdc0515a..901ea765f146 100644 --- a/arch/powerpc/mm/mmu_context_64.c +++ b/arch/powerpc/mm/mmu_context_64.c @@ -28,7 +28,6 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { int index; int err; - int new_context = (mm->context.id == 0); again: if (!idr_pre_get(&mmu_context_idr, GFP_KERNEL)) @@ -50,19 +49,19 @@ again: return -ENOMEM; } - mm->context.id = index; #ifdef CONFIG_PPC_MM_SLICES /* The old code would re-promote on fork, we don't do that * when using slices as it could cause problem promoting slices * that have been forced down to 4K */ - if (new_context) + if (mm->context.id == 0) slice_set_user_psize(mm, mmu_virtual_psize); #else mm->context.user_psize = mmu_virtual_psize; mm->context.sllp = SLB_VSID_USER | mmu_psize_defs[mmu_virtual_psize].sllp; #endif + mm->context.id = index; return 0; } diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c index d5fd3909d13a..319826ef1645 100644 --- a/arch/powerpc/mm/slice.c +++ b/arch/powerpc/mm/slice.c @@ -551,6 +551,7 @@ EXPORT_SYMBOL_GPL(get_slice_psize); * * This is also called in init_new_context() to change back the user * psize from whatever the parent context had it set to + * N.B. This may be called before mm->context.id has been set. * * This function will only change the content of the {low,high)_slice_psize * masks, it will not flush SLBs as this shall be handled lazily by the -- cgit v1.2.3 From e8ff0646e5df850ff084be9c97a2e69fff5697b4 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 15 Aug 2007 16:51:18 +1000 Subject: [POWERPC] Tidy up CONFIG_PPC_MM_SLICES code This removes some of the #ifdefs from .c files. Signed-off-by: Stephen Rothwell Signed-off-by: Paul Mackerras --- arch/powerpc/mm/hash_utils_64.c | 6 ------ arch/powerpc/mm/mmu_context_64.c | 8 +------- include/asm-powerpc/page_64.h | 7 +++++++ 3 files changed, 8 insertions(+), 13 deletions(-) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index c74af42eb9c1..d525f2eba313 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -601,13 +601,7 @@ static void demote_segment_4k(struct mm_struct *mm, unsigned long addr) { if (mm->context.user_psize == MMU_PAGE_4K) return; -#ifdef CONFIG_PPC_MM_SLICES slice_set_user_psize(mm, MMU_PAGE_4K); -#else /* CONFIG_PPC_MM_SLICES */ - mm->context.user_psize = MMU_PAGE_4K; - mm->context.sllp = SLB_VSID_USER | mmu_psize_defs[MMU_PAGE_4K].sllp; -#endif /* CONFIG_PPC_MM_SLICES */ - #ifdef CONFIG_SPU_BASE spu_flush_all_slbs(mm); #endif diff --git a/arch/powerpc/mm/mmu_context_64.c b/arch/powerpc/mm/mmu_context_64.c index 901ea765f146..1db38ba1f544 100644 --- a/arch/powerpc/mm/mmu_context_64.c +++ b/arch/powerpc/mm/mmu_context_64.c @@ -49,18 +49,12 @@ again: return -ENOMEM; } -#ifdef CONFIG_PPC_MM_SLICES /* The old code would re-promote on fork, we don't do that * when using slices as it could cause problem promoting slices * that have been forced down to 4K */ - if (mm->context.id == 0) + if (slice_mm_new_context(mm)) slice_set_user_psize(mm, mmu_virtual_psize); -#else - mm->context.user_psize = mmu_virtual_psize; - mm->context.sllp = SLB_VSID_USER | - mmu_psize_defs[mmu_virtual_psize].sllp; -#endif mm->context.id = index; return 0; diff --git a/include/asm-powerpc/page_64.h b/include/asm-powerpc/page_64.h index 3448a3d4bc64..4ceb1132c480 100644 --- a/include/asm-powerpc/page_64.h +++ b/include/asm-powerpc/page_64.h @@ -121,6 +121,7 @@ extern unsigned int get_slice_psize(struct mm_struct *mm, extern void slice_init_context(struct mm_struct *mm, unsigned int psize); extern void slice_set_user_psize(struct mm_struct *mm, unsigned int psize); +#define slice_mm_new_context(mm) ((mm)->context.id == 0) #define ARCH_HAS_HUGEPAGE_ONLY_RANGE extern int is_hugepage_only_range(struct mm_struct *m, @@ -130,6 +131,12 @@ extern int is_hugepage_only_range(struct mm_struct *m, #endif /* __ASSEMBLY__ */ #else #define slice_init() +#define slice_set_user_psize(mm, psize) \ +do { \ + (mm)->context.user_psize = (psize); \ + (mm)->context.sllp = SLB_VSID_USER | mmu_psize_defs[(psize)].sllp; \ +} while (0) +#define slice_mm_new_context(mm) 1 #endif /* CONFIG_PPC_MM_SLICES */ #ifdef CONFIG_HUGETLB_PAGE -- cgit v1.2.3 From 15f6527e8e63e793f8ab1ddce4ed3c487ebd0d42 Mon Sep 17 00:00:00 2001 From: Josh Boyer Date: Mon, 20 Aug 2007 07:27:07 -0500 Subject: [POWERPC] Rename 4xx paths to 40x 4xx is a bit of a misnomer for certain things, as they really apply to PowerPC 40x only. Rename some of the files to clean this up. Signed-off-by: Josh Boyer Acked-by: David Gibson --- arch/powerpc/Makefile | 2 +- arch/powerpc/kernel/Makefile | 2 +- arch/powerpc/kernel/head_40x.S | 1021 +++++++++++++++++++++++++++++++++++ arch/powerpc/kernel/head_4xx.S | 1021 ----------------------------------- arch/powerpc/mm/40x_mmu.c | 135 +++++ arch/powerpc/mm/4xx_mmu.c | 135 ----- arch/powerpc/mm/Makefile | 2 +- arch/powerpc/platforms/40x/Kconfig | 208 +++++++ arch/powerpc/platforms/40x/Makefile | 1 + arch/powerpc/platforms/4xx/Kconfig | 208 ------- arch/powerpc/platforms/4xx/Makefile | 1 - 11 files changed, 1368 insertions(+), 1368 deletions(-) create mode 100644 arch/powerpc/kernel/head_40x.S delete mode 100644 arch/powerpc/kernel/head_4xx.S create mode 100644 arch/powerpc/mm/40x_mmu.c delete mode 100644 arch/powerpc/mm/4xx_mmu.c create mode 100644 arch/powerpc/platforms/40x/Kconfig create mode 100644 arch/powerpc/platforms/40x/Makefile delete mode 100644 arch/powerpc/platforms/4xx/Kconfig delete mode 100644 arch/powerpc/platforms/4xx/Makefile (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 6c1e36c33faa..8e59c0c405ad 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -123,7 +123,7 @@ CFLAGS += $(cpu-as-y) head-y := arch/powerpc/kernel/head_32.o head-$(CONFIG_PPC64) := arch/powerpc/kernel/head_64.o head-$(CONFIG_8xx) := arch/powerpc/kernel/head_8xx.o -head-$(CONFIG_4xx) := arch/powerpc/kernel/head_4xx.o +head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o head-$(CONFIG_44x) := arch/powerpc/kernel/head_44x.o head-$(CONFIG_FSL_BOOKE) := arch/powerpc/kernel/head_fsl_booke.o diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index b0cb2e662c25..a4850dd8764f 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -46,7 +46,7 @@ ifeq ($(CONFIG_PPC_MERGE),y) extra-$(CONFIG_PPC_STD_MMU) := head_32.o extra-$(CONFIG_PPC64) := head_64.o -extra-$(CONFIG_40x) := head_4xx.o +extra-$(CONFIG_40x) := head_40x.o extra-$(CONFIG_44x) := head_44x.o extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o extra-$(CONFIG_8xx) := head_8xx.o diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S new file mode 100644 index 000000000000..adc7f8097cd4 --- /dev/null +++ b/arch/powerpc/kernel/head_40x.S @@ -0,0 +1,1021 @@ +/* + * Copyright (c) 1995-1996 Gary Thomas + * Initial PowerPC version. + * Copyright (c) 1996 Cort Dougan + * Rewritten for PReP + * Copyright (c) 1996 Paul Mackerras + * Low-level exception handers, MMU support, and rewrite. + * Copyright (c) 1997 Dan Malek + * PowerPC 8xx modifications. + * Copyright (c) 1998-1999 TiVo, Inc. + * PowerPC 403GCX modifications. + * Copyright (c) 1999 Grant Erickson + * PowerPC 403GCX/405GP modifications. + * Copyright 2000 MontaVista Software Inc. + * PPC405 modifications + * PowerPC 403GCX/405GP modifications. + * Author: MontaVista Software, Inc. + * frank_rowand@mvista.com or source@mvista.com + * debbie_chu@mvista.com + * + * + * Module name: head_4xx.S + * + * Description: + * Kernel execution entry point code. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* As with the other PowerPC ports, it is expected that when code + * execution begins here, the following registers contain valid, yet + * optional, information: + * + * r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.) + * r4 - Starting address of the init RAM disk + * r5 - Ending address of the init RAM disk + * r6 - Start of kernel command line string (e.g. "mem=96m") + * r7 - End of kernel command line string + * + * This is all going to change RSN when we add bi_recs....... -- Dan + */ + .text +_GLOBAL(_stext) +_GLOBAL(_start) + + /* Save parameters we are passed. + */ + mr r31,r3 + mr r30,r4 + mr r29,r5 + mr r28,r6 + mr r27,r7 + + /* We have to turn on the MMU right away so we get cache modes + * set correctly. + */ + bl initial_mmu + +/* We now have the lower 16 Meg mapped into TLB entries, and the caches + * ready to work. + */ +turn_on_mmu: + lis r0,MSR_KERNEL@h + ori r0,r0,MSR_KERNEL@l + mtspr SPRN_SRR1,r0 + lis r0,start_here@h + ori r0,r0,start_here@l + mtspr SPRN_SRR0,r0 + SYNC + rfi /* enables MMU */ + b . /* prevent prefetch past rfi */ + +/* + * This area is used for temporarily saving registers during the + * critical exception prolog. + */ + . = 0xc0 +crit_save: +_GLOBAL(crit_r10) + .space 4 +_GLOBAL(crit_r11) + .space 4 + +/* + * Exception vector entry code. This code runs with address translation + * turned off (i.e. using physical addresses). We assume SPRG3 has the + * physical address of the current task thread_struct. + * Note that we have to have decremented r1 before we write to any fields + * of the exception frame, since a critical interrupt could occur at any + * time, and it will write to the area immediately below the current r1. + */ +#define NORMAL_EXCEPTION_PROLOG \ + mtspr SPRN_SPRG0,r10; /* save two registers to work with */\ + mtspr SPRN_SPRG1,r11; \ + mtspr SPRN_SPRG2,r1; \ + mfcr r10; /* save CR in r10 for now */\ + mfspr r11,SPRN_SRR1; /* check whether user or kernel */\ + andi. r11,r11,MSR_PR; \ + beq 1f; \ + mfspr r1,SPRN_SPRG3; /* if from user, start at top of */\ + lwz r1,THREAD_INFO-THREAD(r1); /* this thread's kernel stack */\ + addi r1,r1,THREAD_SIZE; \ +1: subi r1,r1,INT_FRAME_SIZE; /* Allocate an exception frame */\ + tophys(r11,r1); \ + stw r10,_CCR(r11); /* save various registers */\ + stw r12,GPR12(r11); \ + stw r9,GPR9(r11); \ + mfspr r10,SPRN_SPRG0; \ + stw r10,GPR10(r11); \ + mfspr r12,SPRN_SPRG1; \ + stw r12,GPR11(r11); \ + mflr r10; \ + stw r10,_LINK(r11); \ + mfspr r10,SPRN_SPRG2; \ + mfspr r12,SPRN_SRR0; \ + stw r10,GPR1(r11); \ + mfspr r9,SPRN_SRR1; \ + stw r10,0(r11); \ + rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\ + stw r0,GPR0(r11); \ + SAVE_4GPRS(3, r11); \ + SAVE_2GPRS(7, r11) + +/* + * Exception prolog for critical exceptions. This is a little different + * from the normal exception prolog above since a critical exception + * can potentially occur at any point during normal exception processing. + * Thus we cannot use the same SPRG registers as the normal prolog above. + * Instead we use a couple of words of memory at low physical addresses. + * This is OK since we don't support SMP on these processors. + */ +#define CRITICAL_EXCEPTION_PROLOG \ + stw r10,crit_r10@l(0); /* save two registers to work with */\ + stw r11,crit_r11@l(0); \ + mfcr r10; /* save CR in r10 for now */\ + mfspr r11,SPRN_SRR3; /* check whether user or kernel */\ + andi. r11,r11,MSR_PR; \ + lis r11,critical_stack_top@h; \ + ori r11,r11,critical_stack_top@l; \ + beq 1f; \ + /* COMING FROM USER MODE */ \ + mfspr r11,SPRN_SPRG3; /* if from user, start at top of */\ + lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\ + addi r11,r11,THREAD_SIZE; \ +1: subi r11,r11,INT_FRAME_SIZE; /* Allocate an exception frame */\ + tophys(r11,r11); \ + stw r10,_CCR(r11); /* save various registers */\ + stw r12,GPR12(r11); \ + stw r9,GPR9(r11); \ + mflr r10; \ + stw r10,_LINK(r11); \ + mfspr r12,SPRN_DEAR; /* save DEAR and ESR in the frame */\ + stw r12,_DEAR(r11); /* since they may have had stuff */\ + mfspr r9,SPRN_ESR; /* in them at the point where the */\ + stw r9,_ESR(r11); /* exception was taken */\ + mfspr r12,SPRN_SRR2; \ + stw r1,GPR1(r11); \ + mfspr r9,SPRN_SRR3; \ + stw r1,0(r11); \ + tovirt(r1,r11); \ + rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\ + stw r0,GPR0(r11); \ + SAVE_4GPRS(3, r11); \ + SAVE_2GPRS(7, r11) + + /* + * State at this point: + * r9 saved in stack frame, now saved SRR3 & ~MSR_WE + * r10 saved in crit_r10 and in stack frame, trashed + * r11 saved in crit_r11 and in stack frame, + * now phys stack/exception frame pointer + * r12 saved in stack frame, now saved SRR2 + * CR saved in stack frame, CR0.EQ = !SRR3.PR + * LR, DEAR, ESR in stack frame + * r1 saved in stack frame, now virt stack/excframe pointer + * r0, r3-r8 saved in stack frame + */ + +/* + * Exception vectors. + */ +#define START_EXCEPTION(n, label) \ + . = n; \ +label: + +#define EXCEPTION(n, label, hdlr, xfer) \ + START_EXCEPTION(n, label); \ + NORMAL_EXCEPTION_PROLOG; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + xfer(n, hdlr) + +#define CRITICAL_EXCEPTION(n, label, hdlr) \ + START_EXCEPTION(n, label); \ + CRITICAL_EXCEPTION_PROLOG; \ + addi r3,r1,STACK_FRAME_OVERHEAD; \ + EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \ + NOCOPY, crit_transfer_to_handler, \ + ret_from_crit_exc) + +#define EXC_XFER_TEMPLATE(hdlr, trap, msr, copyee, tfer, ret) \ + li r10,trap; \ + stw r10,_TRAP(r11); \ + lis r10,msr@h; \ + ori r10,r10,msr@l; \ + copyee(r10, r9); \ + bl tfer; \ + .long hdlr; \ + .long ret + +#define COPY_EE(d, s) rlwimi d,s,0,16,16 +#define NOCOPY(d, s) + +#define EXC_XFER_STD(n, hdlr) \ + EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, NOCOPY, transfer_to_handler_full, \ + ret_from_except_full) + +#define EXC_XFER_LITE(n, hdlr) \ + EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, NOCOPY, transfer_to_handler, \ + ret_from_except) + +#define EXC_XFER_EE(n, hdlr) \ + EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, COPY_EE, transfer_to_handler_full, \ + ret_from_except_full) + +#define EXC_XFER_EE_LITE(n, hdlr) \ + EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, COPY_EE, transfer_to_handler, \ + ret_from_except) + + +/* + * 0x0100 - Critical Interrupt Exception + */ + CRITICAL_EXCEPTION(0x0100, CriticalInterrupt, unknown_exception) + +/* + * 0x0200 - Machine Check Exception + */ + CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception) + +/* + * 0x0300 - Data Storage Exception + * This happens for just a few reasons. U0 set (but we don't do that), + * or zone protection fault (user violation, write to protected page). + * If this is just an update of modified status, we do that quickly + * and exit. Otherwise, we call heavywight functions to do the work. + */ + START_EXCEPTION(0x0300, DataStorage) + mtspr SPRN_SPRG0, r10 /* Save some working registers */ + mtspr SPRN_SPRG1, r11 +#ifdef CONFIG_403GCX + stw r12, 0(r0) + stw r9, 4(r0) + mfcr r11 + mfspr r12, SPRN_PID + stw r11, 8(r0) + stw r12, 12(r0) +#else + mtspr SPRN_SPRG4, r12 + mtspr SPRN_SPRG5, r9 + mfcr r11 + mfspr r12, SPRN_PID + mtspr SPRN_SPRG7, r11 + mtspr SPRN_SPRG6, r12 +#endif + + /* First, check if it was a zone fault (which means a user + * tried to access a kernel or read-protected page - always + * a SEGV). All other faults here must be stores, so no + * need to check ESR_DST as well. */ + mfspr r10, SPRN_ESR + andis. r10, r10, ESR_DIZ@h + bne 2f + + mfspr r10, SPRN_DEAR /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11, TASK_SIZE@h + cmplw r10, r11 + blt+ 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + li r9, 0 + mtspr SPRN_PID, r9 /* TLB will have 0 TID */ + b 4f + + /* Get the PGD for the current thread. + */ +3: + mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) +4: + tophys(r11, r11) + rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */ + lwz r11, 0(r11) /* Get L1 entry */ + rlwinm. r12, r11, 0, 0, 19 /* Extract L2 (pte) base address */ + beq 2f /* Bail if no table */ + + rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */ + lwz r11, 0(r12) /* Get Linux PTE */ + + andi. r9, r11, _PAGE_RW /* Is it writeable? */ + beq 2f /* Bail if not */ + + /* Update 'changed'. + */ + ori r11, r11, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE + stw r11, 0(r12) /* Update Linux page table */ + + /* Most of the Linux PTE is ready to load into the TLB LO. + * We set ZSEL, where only the LS-bit determines user access. + * We set execute, because we don't have the granularity to + * properly set this at the page level (Linux problem). + * If shared is set, we cause a zero PID->TID load. + * Many of these bits are software only. Bits we don't set + * here we (properly should) assume have the appropriate value. + */ + li r12, 0x0ce2 + andc r11, r11, r12 /* Make sure 20, 21 are zero */ + + /* find the TLB index that caused the fault. It has to be here. + */ + tlbsx r9, 0, r10 + + tlbwe r11, r9, TLB_DATA /* Load TLB LO */ + + /* Done...restore registers and get out of here. + */ +#ifdef CONFIG_403GCX + lwz r12, 12(r0) + lwz r11, 8(r0) + mtspr SPRN_PID, r12 + mtcr r11 + lwz r9, 4(r0) + lwz r12, 0(r0) +#else + mfspr r12, SPRN_SPRG6 + mfspr r11, SPRN_SPRG7 + mtspr SPRN_PID, r12 + mtcr r11 + mfspr r9, SPRN_SPRG5 + mfspr r12, SPRN_SPRG4 +#endif + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + PPC405_ERR77_SYNC + rfi /* Should sync shadow TLBs */ + b . /* prevent prefetch past rfi */ + +2: + /* The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ +#ifdef CONFIG_403GCX + lwz r12, 12(r0) + lwz r11, 8(r0) + mtspr SPRN_PID, r12 + mtcr r11 + lwz r9, 4(r0) + lwz r12, 0(r0) +#else + mfspr r12, SPRN_SPRG6 + mfspr r11, SPRN_SPRG7 + mtspr SPRN_PID, r12 + mtcr r11 + mfspr r9, SPRN_SPRG5 + mfspr r12, SPRN_SPRG4 +#endif + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + b DataAccess + +/* + * 0x0400 - Instruction Storage Exception + * This is caused by a fetch from non-execute or guarded pages. + */ + START_EXCEPTION(0x0400, InstructionAccess) + NORMAL_EXCEPTION_PROLOG + mr r4,r12 /* Pass SRR0 as arg2 */ + li r5,0 /* Pass zero as arg3 */ + EXC_XFER_EE_LITE(0x400, handle_page_fault) + +/* 0x0500 - External Interrupt Exception */ + EXCEPTION(0x0500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE) + +/* 0x0600 - Alignment Exception */ + START_EXCEPTION(0x0600, Alignment) + NORMAL_EXCEPTION_PROLOG + mfspr r4,SPRN_DEAR /* Grab the DEAR and save it */ + stw r4,_DEAR(r11) + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_EE(0x600, alignment_exception) + +/* 0x0700 - Program Exception */ + START_EXCEPTION(0x0700, ProgramCheck) + NORMAL_EXCEPTION_PROLOG + mfspr r4,SPRN_ESR /* Grab the ESR and save it */ + stw r4,_ESR(r11) + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_STD(0x700, program_check_exception) + + EXCEPTION(0x0800, Trap_08, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x0900, Trap_09, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x0A00, Trap_0A, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x0B00, Trap_0B, unknown_exception, EXC_XFER_EE) + +/* 0x0C00 - System Call Exception */ + START_EXCEPTION(0x0C00, SystemCall) + NORMAL_EXCEPTION_PROLOG + EXC_XFER_EE_LITE(0xc00, DoSyscall) + + EXCEPTION(0x0D00, Trap_0D, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x0E00, Trap_0E, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x0F00, Trap_0F, unknown_exception, EXC_XFER_EE) + +/* 0x1000 - Programmable Interval Timer (PIT) Exception */ + START_EXCEPTION(0x1000, Decrementer) + NORMAL_EXCEPTION_PROLOG + lis r0,TSR_PIS@h + mtspr SPRN_TSR,r0 /* Clear the PIT exception */ + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_LITE(0x1000, timer_interrupt) + +#if 0 +/* NOTE: + * FIT and WDT handlers are not implemented yet. + */ + +/* 0x1010 - Fixed Interval Timer (FIT) Exception +*/ + STND_EXCEPTION(0x1010, FITException, unknown_exception) + +/* 0x1020 - Watchdog Timer (WDT) Exception +*/ +#ifdef CONFIG_BOOKE_WDT + CRITICAL_EXCEPTION(0x1020, WDTException, WatchdogException) +#else + CRITICAL_EXCEPTION(0x1020, WDTException, unknown_exception) +#endif +#endif + +/* 0x1100 - Data TLB Miss Exception + * As the name implies, translation is not in the MMU, so search the + * page tables and fix it. The only purpose of this function is to + * load TLB entries from the page table if they exist. + */ + START_EXCEPTION(0x1100, DTLBMiss) + mtspr SPRN_SPRG0, r10 /* Save some working registers */ + mtspr SPRN_SPRG1, r11 +#ifdef CONFIG_403GCX + stw r12, 0(r0) + stw r9, 4(r0) + mfcr r11 + mfspr r12, SPRN_PID + stw r11, 8(r0) + stw r12, 12(r0) +#else + mtspr SPRN_SPRG4, r12 + mtspr SPRN_SPRG5, r9 + mfcr r11 + mfspr r12, SPRN_PID + mtspr SPRN_SPRG7, r11 + mtspr SPRN_SPRG6, r12 +#endif + mfspr r10, SPRN_DEAR /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11, TASK_SIZE@h + cmplw r10, r11 + blt+ 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + li r9, 0 + mtspr SPRN_PID, r9 /* TLB will have 0 TID */ + b 4f + + /* Get the PGD for the current thread. + */ +3: + mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) +4: + tophys(r11, r11) + rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */ + lwz r12, 0(r11) /* Get L1 entry */ + andi. r9, r12, _PMD_PRESENT /* Check if it points to a PTE page */ + beq 2f /* Bail if no table */ + + rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */ + lwz r11, 0(r12) /* Get Linux PTE */ + andi. r9, r11, _PAGE_PRESENT + beq 5f + + ori r11, r11, _PAGE_ACCESSED + stw r11, 0(r12) + + /* Create TLB tag. This is the faulting address plus a static + * set of bits. These are size, valid, E, U0. + */ + li r12, 0x00c0 + rlwimi r10, r12, 0, 20, 31 + + b finish_tlb_load + +2: /* Check for possible large-page pmd entry */ + rlwinm. r9, r12, 2, 22, 24 + beq 5f + + /* Create TLB tag. This is the faulting address, plus a static + * set of bits (valid, E, U0) plus the size from the PMD. + */ + ori r9, r9, 0x40 + rlwimi r10, r9, 0, 20, 31 + mr r11, r12 + + b finish_tlb_load + +5: + /* The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ +#ifdef CONFIG_403GCX + lwz r12, 12(r0) + lwz r11, 8(r0) + mtspr SPRN_PID, r12 + mtcr r11 + lwz r9, 4(r0) + lwz r12, 0(r0) +#else + mfspr r12, SPRN_SPRG6 + mfspr r11, SPRN_SPRG7 + mtspr SPRN_PID, r12 + mtcr r11 + mfspr r9, SPRN_SPRG5 + mfspr r12, SPRN_SPRG4 +#endif + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + b DataAccess + +/* 0x1200 - Instruction TLB Miss Exception + * Nearly the same as above, except we get our information from different + * registers and bailout to a different point. + */ + START_EXCEPTION(0x1200, ITLBMiss) + mtspr SPRN_SPRG0, r10 /* Save some working registers */ + mtspr SPRN_SPRG1, r11 +#ifdef CONFIG_403GCX + stw r12, 0(r0) + stw r9, 4(r0) + mfcr r11 + mfspr r12, SPRN_PID + stw r11, 8(r0) + stw r12, 12(r0) +#else + mtspr SPRN_SPRG4, r12 + mtspr SPRN_SPRG5, r9 + mfcr r11 + mfspr r12, SPRN_PID + mtspr SPRN_SPRG7, r11 + mtspr SPRN_SPRG6, r12 +#endif + mfspr r10, SPRN_SRR0 /* Get faulting address */ + + /* If we are faulting a kernel address, we have to use the + * kernel page tables. + */ + lis r11, TASK_SIZE@h + cmplw r10, r11 + blt+ 3f + lis r11, swapper_pg_dir@h + ori r11, r11, swapper_pg_dir@l + li r9, 0 + mtspr SPRN_PID, r9 /* TLB will have 0 TID */ + b 4f + + /* Get the PGD for the current thread. + */ +3: + mfspr r11,SPRN_SPRG3 + lwz r11,PGDIR(r11) +4: + tophys(r11, r11) + rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */ + lwz r12, 0(r11) /* Get L1 entry */ + andi. r9, r12, _PMD_PRESENT /* Check if it points to a PTE page */ + beq 2f /* Bail if no table */ + + rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */ + lwz r11, 0(r12) /* Get Linux PTE */ + andi. r9, r11, _PAGE_PRESENT + beq 5f + + ori r11, r11, _PAGE_ACCESSED + stw r11, 0(r12) + + /* Create TLB tag. This is the faulting address plus a static + * set of bits. These are size, valid, E, U0. + */ + li r12, 0x00c0 + rlwimi r10, r12, 0, 20, 31 + + b finish_tlb_load + +2: /* Check for possible large-page pmd entry */ + rlwinm. r9, r12, 2, 22, 24 + beq 5f + + /* Create TLB tag. This is the faulting address, plus a static + * set of bits (valid, E, U0) plus the size from the PMD. + */ + ori r9, r9, 0x40 + rlwimi r10, r9, 0, 20, 31 + mr r11, r12 + + b finish_tlb_load + +5: + /* The bailout. Restore registers to pre-exception conditions + * and call the heavyweights to help us out. + */ +#ifdef CONFIG_403GCX + lwz r12, 12(r0) + lwz r11, 8(r0) + mtspr SPRN_PID, r12 + mtcr r11 + lwz r9, 4(r0) + lwz r12, 0(r0) +#else + mfspr r12, SPRN_SPRG6 + mfspr r11, SPRN_SPRG7 + mtspr SPRN_PID, r12 + mtcr r11 + mfspr r9, SPRN_SPRG5 + mfspr r12, SPRN_SPRG4 +#endif + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + b InstructionAccess + + EXCEPTION(0x1300, Trap_13, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1400, Trap_14, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_EE) +#ifdef CONFIG_IBM405_ERR51 + /* 405GP errata 51 */ + START_EXCEPTION(0x1700, Trap_17) + b DTLBMiss +#else + EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_EE) +#endif + EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1A00, Trap_1A, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1B00, Trap_1B, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1C00, Trap_1C, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1D00, Trap_1D, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1E00, Trap_1E, unknown_exception, EXC_XFER_EE) + EXCEPTION(0x1F00, Trap_1F, unknown_exception, EXC_XFER_EE) + +/* Check for a single step debug exception while in an exception + * handler before state has been saved. This is to catch the case + * where an instruction that we are trying to single step causes + * an exception (eg ITLB/DTLB miss) and thus the first instruction of + * the exception handler generates a single step debug exception. + * + * If we get a debug trap on the first instruction of an exception handler, + * we reset the MSR_DE in the _exception handler's_ MSR (the debug trap is + * a critical exception, so we are using SPRN_CSRR1 to manipulate the MSR). + * The exception handler was handling a non-critical interrupt, so it will + * save (and later restore) the MSR via SPRN_SRR1, which will still have + * the MSR_DE bit set. + */ + /* 0x2000 - Debug Exception */ + START_EXCEPTION(0x2000, DebugTrap) + CRITICAL_EXCEPTION_PROLOG + + /* + * If this is a single step or branch-taken exception in an + * exception entry sequence, it was probably meant to apply to + * the code where the exception occurred (since exception entry + * doesn't turn off DE automatically). We simulate the effect + * of turning off DE on entry to an exception handler by turning + * off DE in the SRR3 value and clearing the debug status. + */ + mfspr r10,SPRN_DBSR /* check single-step/branch taken */ + andis. r10,r10,DBSR_IC@h + beq+ 2f + + andi. r10,r9,MSR_IR|MSR_PR /* check supervisor + MMU off */ + beq 1f /* branch and fix it up */ + + mfspr r10,SPRN_SRR2 /* Faulting instruction address */ + cmplwi r10,0x2100 + bgt+ 2f /* address above exception vectors */ + + /* here it looks like we got an inappropriate debug exception. */ +1: rlwinm r9,r9,0,~MSR_DE /* clear DE in the SRR3 value */ + lis r10,DBSR_IC@h /* clear the IC event */ + mtspr SPRN_DBSR,r10 + /* restore state and get out */ + lwz r10,_CCR(r11) + lwz r0,GPR0(r11) + lwz r1,GPR1(r11) + mtcrf 0x80,r10 + mtspr SPRN_SRR2,r12 + mtspr SPRN_SRR3,r9 + lwz r9,GPR9(r11) + lwz r12,GPR12(r11) + lwz r10,crit_r10@l(0) + lwz r11,crit_r11@l(0) + PPC405_ERR77_SYNC + rfci + b . + + /* continue normal handling for a critical exception... */ +2: mfspr r4,SPRN_DBSR + addi r3,r1,STACK_FRAME_OVERHEAD + EXC_XFER_TEMPLATE(DebugException, 0x2002, \ + (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \ + NOCOPY, crit_transfer_to_handler, ret_from_crit_exc) + +/* + * The other Data TLB exceptions bail out to this point + * if they can't resolve the lightweight TLB fault. + */ +DataAccess: + NORMAL_EXCEPTION_PROLOG + mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */ + stw r5,_ESR(r11) + mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */ + EXC_XFER_EE_LITE(0x300, handle_page_fault) + +/* Other PowerPC processors, namely those derived from the 6xx-series + * have vectors from 0x2100 through 0x2F00 defined, but marked as reserved. + * However, for the 4xx-series processors these are neither defined nor + * reserved. + */ + + /* Damn, I came up one instruction too many to fit into the + * exception space :-). Both the instruction and data TLB + * miss get to this point to load the TLB. + * r10 - TLB_TAG value + * r11 - Linux PTE + * r12, r9 - avilable to use + * PID - loaded with proper value when we get here + * Upon exit, we reload everything and RFI. + * Actually, it will fit now, but oh well.....a common place + * to load the TLB. + */ +tlb_4xx_index: + .long 0 +finish_tlb_load: + /* load the next available TLB index. + */ + lwz r9, tlb_4xx_index@l(0) + addi r9, r9, 1 + andi. r9, r9, (PPC4XX_TLB_SIZE-1) + stw r9, tlb_4xx_index@l(0) + +6: + /* + * Clear out the software-only bits in the PTE to generate the + * TLB_DATA value. These are the bottom 2 bits of the RPM, the + * top 3 bits of the zone field, and M. + */ + li r12, 0x0ce2 + andc r11, r11, r12 + + tlbwe r11, r9, TLB_DATA /* Load TLB LO */ + tlbwe r10, r9, TLB_TAG /* Load TLB HI */ + + /* Done...restore registers and get out of here. + */ +#ifdef CONFIG_403GCX + lwz r12, 12(r0) + lwz r11, 8(r0) + mtspr SPRN_PID, r12 + mtcr r11 + lwz r9, 4(r0) + lwz r12, 0(r0) +#else + mfspr r12, SPRN_SPRG6 + mfspr r11, SPRN_SPRG7 + mtspr SPRN_PID, r12 + mtcr r11 + mfspr r9, SPRN_SPRG5 + mfspr r12, SPRN_SPRG4 +#endif + mfspr r11, SPRN_SPRG1 + mfspr r10, SPRN_SPRG0 + PPC405_ERR77_SYNC + rfi /* Should sync shadow TLBs */ + b . /* prevent prefetch past rfi */ + +/* extern void giveup_fpu(struct task_struct *prev) + * + * The PowerPC 4xx family of processors do not have an FPU, so this just + * returns. + */ +_GLOBAL(giveup_fpu) + blr + +/* This is where the main kernel code starts. + */ +start_here: + + /* ptr to current */ + lis r2,init_task@h + ori r2,r2,init_task@l + + /* ptr to phys current thread */ + tophys(r4,r2) + addi r4,r4,THREAD /* init task's THREAD */ + mtspr SPRN_SPRG3,r4 + + /* stack */ + lis r1,init_thread_union@ha + addi r1,r1,init_thread_union@l + li r0,0 + stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1) + + bl early_init /* We have to do this with MMU on */ + +/* + * Decide what sort of machine this is and initialize the MMU. + */ + mr r3,r31 + mr r4,r30 + mr r5,r29 + mr r6,r28 + mr r7,r27 + bl machine_init + bl MMU_init + +/* Go back to running unmapped so we can load up new values + * and change to using our exception vectors. + * On the 4xx, all we have to do is invalidate the TLB to clear + * the old 16M byte TLB mappings. + */ + lis r4,2f@h + ori r4,r4,2f@l + tophys(r4,r4) + lis r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@h + ori r3,r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@l + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r3 + rfi + b . /* prevent prefetch past rfi */ + +/* Load up the kernel context */ +2: + sync /* Flush to memory before changing TLB */ + tlbia + isync /* Flush shadow TLBs */ + + /* set up the PTE pointers for the Abatron bdiGDB. + */ + lis r6, swapper_pg_dir@h + ori r6, r6, swapper_pg_dir@l + lis r5, abatron_pteptrs@h + ori r5, r5, abatron_pteptrs@l + stw r5, 0xf0(r0) /* Must match your Abatron config file */ + tophys(r5,r5) + stw r6, 0(r5) + +/* Now turn on the MMU for real! */ + lis r4,MSR_KERNEL@h + ori r4,r4,MSR_KERNEL@l + lis r3,start_kernel@h + ori r3,r3,start_kernel@l + mtspr SPRN_SRR0,r3 + mtspr SPRN_SRR1,r4 + rfi /* enable MMU and jump to start_kernel */ + b . /* prevent prefetch past rfi */ + +/* Set up the initial MMU state so we can do the first level of + * kernel initialization. This maps the first 16 MBytes of memory 1:1 + * virtual to physical and more importantly sets the cache mode. + */ +initial_mmu: + tlbia /* Invalidate all TLB entries */ + isync + + /* We should still be executing code at physical address 0x0000xxxx + * at this point. However, start_here is at virtual address + * 0xC000xxxx. So, set up a TLB mapping to cover this once + * translation is enabled. + */ + + lis r3,KERNELBASE@h /* Load the kernel virtual address */ + ori r3,r3,KERNELBASE@l + tophys(r4,r3) /* Load the kernel physical address */ + + iccci r0,r3 /* Invalidate the i-cache before use */ + + /* Load the kernel PID. + */ + li r0,0 + mtspr SPRN_PID,r0 + sync + + /* Configure and load two entries into TLB slots 62 and 63. + * In case we are pinning TLBs, these are reserved in by the + * other TLB functions. If not reserving, then it doesn't + * matter where they are loaded. + */ + clrrwi r4,r4,10 /* Mask off the real page number */ + ori r4,r4,(TLB_WR | TLB_EX) /* Set the write and execute bits */ + + clrrwi r3,r3,10 /* Mask off the effective page number */ + ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_16M)) + + li r0,63 /* TLB slot 63 */ + + tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */ + tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */ + +#if defined(CONFIG_SERIAL_TEXT_DEBUG) && defined(SERIAL_DEBUG_IO_BASE) + + /* Load a TLB entry for the UART, so that ppc4xx_progress() can use + * the UARTs nice and early. We use a 4k real==virtual mapping. */ + + lis r3,SERIAL_DEBUG_IO_BASE@h + ori r3,r3,SERIAL_DEBUG_IO_BASE@l + mr r4,r3 + clrrwi r4,r4,12 + ori r4,r4,(TLB_WR|TLB_I|TLB_M|TLB_G) + + clrrwi r3,r3,12 + ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_4K)) + + li r0,0 /* TLB slot 0 */ + tlbwe r4,r0,TLB_DATA + tlbwe r3,r0,TLB_TAG +#endif /* CONFIG_SERIAL_DEBUG_TEXT && SERIAL_DEBUG_IO_BASE */ + + isync + + /* Establish the exception vector base + */ + lis r4,KERNELBASE@h /* EVPR only uses the high 16-bits */ + tophys(r0,r4) /* Use the physical address */ + mtspr SPRN_EVPR,r0 + + blr + +_GLOBAL(abort) + mfspr r13,SPRN_DBCR0 + oris r13,r13,DBCR0_RST_SYSTEM@h + mtspr SPRN_DBCR0,r13 + +_GLOBAL(set_context) + +#ifdef CONFIG_BDI_SWITCH + /* Context switch the PTE pointer for the Abatron BDI2000. + * The PGDIR is the second parameter. + */ + lis r5, KERNELBASE@h + lwz r5, 0xf0(r5) + stw r4, 0x4(r5) +#endif + sync + mtspr SPRN_PID,r3 + isync /* Need an isync to flush shadow */ + /* TLBs after changing PID */ + blr + +/* We put a few things here that have to be page-aligned. This stuff + * goes at the beginning of the data segment, which is page-aligned. + */ + .data + .align 12 + .globl sdata +sdata: + .globl empty_zero_page +empty_zero_page: + .space 4096 + .globl swapper_pg_dir +swapper_pg_dir: + .space 4096 + + +/* Stack for handling critical exceptions from kernel mode */ + .section .bss + .align 12 +exception_stack_bottom: + .space 4096 +critical_stack_top: + .globl exception_stack_top +exception_stack_top: + +/* This space gets a copy of optional info passed to us by the bootstrap + * which is used to pass parameters into the kernel like root=/dev/sda1, etc. + */ + .globl cmd_line +cmd_line: + .space 512 + +/* Room for two PTE pointers, usually the kernel and current user pointers + * to their respective root page table. + */ +abatron_pteptrs: + .space 8 diff --git a/arch/powerpc/kernel/head_4xx.S b/arch/powerpc/kernel/head_4xx.S deleted file mode 100644 index adc7f8097cd4..000000000000 --- a/arch/powerpc/kernel/head_4xx.S +++ /dev/null @@ -1,1021 +0,0 @@ -/* - * Copyright (c) 1995-1996 Gary Thomas - * Initial PowerPC version. - * Copyright (c) 1996 Cort Dougan - * Rewritten for PReP - * Copyright (c) 1996 Paul Mackerras - * Low-level exception handers, MMU support, and rewrite. - * Copyright (c) 1997 Dan Malek - * PowerPC 8xx modifications. - * Copyright (c) 1998-1999 TiVo, Inc. - * PowerPC 403GCX modifications. - * Copyright (c) 1999 Grant Erickson - * PowerPC 403GCX/405GP modifications. - * Copyright 2000 MontaVista Software Inc. - * PPC405 modifications - * PowerPC 403GCX/405GP modifications. - * Author: MontaVista Software, Inc. - * frank_rowand@mvista.com or source@mvista.com - * debbie_chu@mvista.com - * - * - * Module name: head_4xx.S - * - * Description: - * Kernel execution entry point code. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* As with the other PowerPC ports, it is expected that when code - * execution begins here, the following registers contain valid, yet - * optional, information: - * - * r3 - Board info structure pointer (DRAM, frequency, MAC address, etc.) - * r4 - Starting address of the init RAM disk - * r5 - Ending address of the init RAM disk - * r6 - Start of kernel command line string (e.g. "mem=96m") - * r7 - End of kernel command line string - * - * This is all going to change RSN when we add bi_recs....... -- Dan - */ - .text -_GLOBAL(_stext) -_GLOBAL(_start) - - /* Save parameters we are passed. - */ - mr r31,r3 - mr r30,r4 - mr r29,r5 - mr r28,r6 - mr r27,r7 - - /* We have to turn on the MMU right away so we get cache modes - * set correctly. - */ - bl initial_mmu - -/* We now have the lower 16 Meg mapped into TLB entries, and the caches - * ready to work. - */ -turn_on_mmu: - lis r0,MSR_KERNEL@h - ori r0,r0,MSR_KERNEL@l - mtspr SPRN_SRR1,r0 - lis r0,start_here@h - ori r0,r0,start_here@l - mtspr SPRN_SRR0,r0 - SYNC - rfi /* enables MMU */ - b . /* prevent prefetch past rfi */ - -/* - * This area is used for temporarily saving registers during the - * critical exception prolog. - */ - . = 0xc0 -crit_save: -_GLOBAL(crit_r10) - .space 4 -_GLOBAL(crit_r11) - .space 4 - -/* - * Exception vector entry code. This code runs with address translation - * turned off (i.e. using physical addresses). We assume SPRG3 has the - * physical address of the current task thread_struct. - * Note that we have to have decremented r1 before we write to any fields - * of the exception frame, since a critical interrupt could occur at any - * time, and it will write to the area immediately below the current r1. - */ -#define NORMAL_EXCEPTION_PROLOG \ - mtspr SPRN_SPRG0,r10; /* save two registers to work with */\ - mtspr SPRN_SPRG1,r11; \ - mtspr SPRN_SPRG2,r1; \ - mfcr r10; /* save CR in r10 for now */\ - mfspr r11,SPRN_SRR1; /* check whether user or kernel */\ - andi. r11,r11,MSR_PR; \ - beq 1f; \ - mfspr r1,SPRN_SPRG3; /* if from user, start at top of */\ - lwz r1,THREAD_INFO-THREAD(r1); /* this thread's kernel stack */\ - addi r1,r1,THREAD_SIZE; \ -1: subi r1,r1,INT_FRAME_SIZE; /* Allocate an exception frame */\ - tophys(r11,r1); \ - stw r10,_CCR(r11); /* save various registers */\ - stw r12,GPR12(r11); \ - stw r9,GPR9(r11); \ - mfspr r10,SPRN_SPRG0; \ - stw r10,GPR10(r11); \ - mfspr r12,SPRN_SPRG1; \ - stw r12,GPR11(r11); \ - mflr r10; \ - stw r10,_LINK(r11); \ - mfspr r10,SPRN_SPRG2; \ - mfspr r12,SPRN_SRR0; \ - stw r10,GPR1(r11); \ - mfspr r9,SPRN_SRR1; \ - stw r10,0(r11); \ - rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\ - stw r0,GPR0(r11); \ - SAVE_4GPRS(3, r11); \ - SAVE_2GPRS(7, r11) - -/* - * Exception prolog for critical exceptions. This is a little different - * from the normal exception prolog above since a critical exception - * can potentially occur at any point during normal exception processing. - * Thus we cannot use the same SPRG registers as the normal prolog above. - * Instead we use a couple of words of memory at low physical addresses. - * This is OK since we don't support SMP on these processors. - */ -#define CRITICAL_EXCEPTION_PROLOG \ - stw r10,crit_r10@l(0); /* save two registers to work with */\ - stw r11,crit_r11@l(0); \ - mfcr r10; /* save CR in r10 for now */\ - mfspr r11,SPRN_SRR3; /* check whether user or kernel */\ - andi. r11,r11,MSR_PR; \ - lis r11,critical_stack_top@h; \ - ori r11,r11,critical_stack_top@l; \ - beq 1f; \ - /* COMING FROM USER MODE */ \ - mfspr r11,SPRN_SPRG3; /* if from user, start at top of */\ - lwz r11,THREAD_INFO-THREAD(r11); /* this thread's kernel stack */\ - addi r11,r11,THREAD_SIZE; \ -1: subi r11,r11,INT_FRAME_SIZE; /* Allocate an exception frame */\ - tophys(r11,r11); \ - stw r10,_CCR(r11); /* save various registers */\ - stw r12,GPR12(r11); \ - stw r9,GPR9(r11); \ - mflr r10; \ - stw r10,_LINK(r11); \ - mfspr r12,SPRN_DEAR; /* save DEAR and ESR in the frame */\ - stw r12,_DEAR(r11); /* since they may have had stuff */\ - mfspr r9,SPRN_ESR; /* in them at the point where the */\ - stw r9,_ESR(r11); /* exception was taken */\ - mfspr r12,SPRN_SRR2; \ - stw r1,GPR1(r11); \ - mfspr r9,SPRN_SRR3; \ - stw r1,0(r11); \ - tovirt(r1,r11); \ - rlwinm r9,r9,0,14,12; /* clear MSR_WE (necessary?) */\ - stw r0,GPR0(r11); \ - SAVE_4GPRS(3, r11); \ - SAVE_2GPRS(7, r11) - - /* - * State at this point: - * r9 saved in stack frame, now saved SRR3 & ~MSR_WE - * r10 saved in crit_r10 and in stack frame, trashed - * r11 saved in crit_r11 and in stack frame, - * now phys stack/exception frame pointer - * r12 saved in stack frame, now saved SRR2 - * CR saved in stack frame, CR0.EQ = !SRR3.PR - * LR, DEAR, ESR in stack frame - * r1 saved in stack frame, now virt stack/excframe pointer - * r0, r3-r8 saved in stack frame - */ - -/* - * Exception vectors. - */ -#define START_EXCEPTION(n, label) \ - . = n; \ -label: - -#define EXCEPTION(n, label, hdlr, xfer) \ - START_EXCEPTION(n, label); \ - NORMAL_EXCEPTION_PROLOG; \ - addi r3,r1,STACK_FRAME_OVERHEAD; \ - xfer(n, hdlr) - -#define CRITICAL_EXCEPTION(n, label, hdlr) \ - START_EXCEPTION(n, label); \ - CRITICAL_EXCEPTION_PROLOG; \ - addi r3,r1,STACK_FRAME_OVERHEAD; \ - EXC_XFER_TEMPLATE(hdlr, n+2, (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \ - NOCOPY, crit_transfer_to_handler, \ - ret_from_crit_exc) - -#define EXC_XFER_TEMPLATE(hdlr, trap, msr, copyee, tfer, ret) \ - li r10,trap; \ - stw r10,_TRAP(r11); \ - lis r10,msr@h; \ - ori r10,r10,msr@l; \ - copyee(r10, r9); \ - bl tfer; \ - .long hdlr; \ - .long ret - -#define COPY_EE(d, s) rlwimi d,s,0,16,16 -#define NOCOPY(d, s) - -#define EXC_XFER_STD(n, hdlr) \ - EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, NOCOPY, transfer_to_handler_full, \ - ret_from_except_full) - -#define EXC_XFER_LITE(n, hdlr) \ - EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, NOCOPY, transfer_to_handler, \ - ret_from_except) - -#define EXC_XFER_EE(n, hdlr) \ - EXC_XFER_TEMPLATE(hdlr, n, MSR_KERNEL, COPY_EE, transfer_to_handler_full, \ - ret_from_except_full) - -#define EXC_XFER_EE_LITE(n, hdlr) \ - EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, COPY_EE, transfer_to_handler, \ - ret_from_except) - - -/* - * 0x0100 - Critical Interrupt Exception - */ - CRITICAL_EXCEPTION(0x0100, CriticalInterrupt, unknown_exception) - -/* - * 0x0200 - Machine Check Exception - */ - CRITICAL_EXCEPTION(0x0200, MachineCheck, machine_check_exception) - -/* - * 0x0300 - Data Storage Exception - * This happens for just a few reasons. U0 set (but we don't do that), - * or zone protection fault (user violation, write to protected page). - * If this is just an update of modified status, we do that quickly - * and exit. Otherwise, we call heavywight functions to do the work. - */ - START_EXCEPTION(0x0300, DataStorage) - mtspr SPRN_SPRG0, r10 /* Save some working registers */ - mtspr SPRN_SPRG1, r11 -#ifdef CONFIG_403GCX - stw r12, 0(r0) - stw r9, 4(r0) - mfcr r11 - mfspr r12, SPRN_PID - stw r11, 8(r0) - stw r12, 12(r0) -#else - mtspr SPRN_SPRG4, r12 - mtspr SPRN_SPRG5, r9 - mfcr r11 - mfspr r12, SPRN_PID - mtspr SPRN_SPRG7, r11 - mtspr SPRN_SPRG6, r12 -#endif - - /* First, check if it was a zone fault (which means a user - * tried to access a kernel or read-protected page - always - * a SEGV). All other faults here must be stores, so no - * need to check ESR_DST as well. */ - mfspr r10, SPRN_ESR - andis. r10, r10, ESR_DIZ@h - bne 2f - - mfspr r10, SPRN_DEAR /* Get faulting address */ - - /* If we are faulting a kernel address, we have to use the - * kernel page tables. - */ - lis r11, TASK_SIZE@h - cmplw r10, r11 - blt+ 3f - lis r11, swapper_pg_dir@h - ori r11, r11, swapper_pg_dir@l - li r9, 0 - mtspr SPRN_PID, r9 /* TLB will have 0 TID */ - b 4f - - /* Get the PGD for the current thread. - */ -3: - mfspr r11,SPRN_SPRG3 - lwz r11,PGDIR(r11) -4: - tophys(r11, r11) - rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */ - lwz r11, 0(r11) /* Get L1 entry */ - rlwinm. r12, r11, 0, 0, 19 /* Extract L2 (pte) base address */ - beq 2f /* Bail if no table */ - - rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */ - lwz r11, 0(r12) /* Get Linux PTE */ - - andi. r9, r11, _PAGE_RW /* Is it writeable? */ - beq 2f /* Bail if not */ - - /* Update 'changed'. - */ - ori r11, r11, _PAGE_DIRTY|_PAGE_ACCESSED|_PAGE_HWWRITE - stw r11, 0(r12) /* Update Linux page table */ - - /* Most of the Linux PTE is ready to load into the TLB LO. - * We set ZSEL, where only the LS-bit determines user access. - * We set execute, because we don't have the granularity to - * properly set this at the page level (Linux problem). - * If shared is set, we cause a zero PID->TID load. - * Many of these bits are software only. Bits we don't set - * here we (properly should) assume have the appropriate value. - */ - li r12, 0x0ce2 - andc r11, r11, r12 /* Make sure 20, 21 are zero */ - - /* find the TLB index that caused the fault. It has to be here. - */ - tlbsx r9, 0, r10 - - tlbwe r11, r9, TLB_DATA /* Load TLB LO */ - - /* Done...restore registers and get out of here. - */ -#ifdef CONFIG_403GCX - lwz r12, 12(r0) - lwz r11, 8(r0) - mtspr SPRN_PID, r12 - mtcr r11 - lwz r9, 4(r0) - lwz r12, 0(r0) -#else - mfspr r12, SPRN_SPRG6 - mfspr r11, SPRN_SPRG7 - mtspr SPRN_PID, r12 - mtcr r11 - mfspr r9, SPRN_SPRG5 - mfspr r12, SPRN_SPRG4 -#endif - mfspr r11, SPRN_SPRG1 - mfspr r10, SPRN_SPRG0 - PPC405_ERR77_SYNC - rfi /* Should sync shadow TLBs */ - b . /* prevent prefetch past rfi */ - -2: - /* The bailout. Restore registers to pre-exception conditions - * and call the heavyweights to help us out. - */ -#ifdef CONFIG_403GCX - lwz r12, 12(r0) - lwz r11, 8(r0) - mtspr SPRN_PID, r12 - mtcr r11 - lwz r9, 4(r0) - lwz r12, 0(r0) -#else - mfspr r12, SPRN_SPRG6 - mfspr r11, SPRN_SPRG7 - mtspr SPRN_PID, r12 - mtcr r11 - mfspr r9, SPRN_SPRG5 - mfspr r12, SPRN_SPRG4 -#endif - mfspr r11, SPRN_SPRG1 - mfspr r10, SPRN_SPRG0 - b DataAccess - -/* - * 0x0400 - Instruction Storage Exception - * This is caused by a fetch from non-execute or guarded pages. - */ - START_EXCEPTION(0x0400, InstructionAccess) - NORMAL_EXCEPTION_PROLOG - mr r4,r12 /* Pass SRR0 as arg2 */ - li r5,0 /* Pass zero as arg3 */ - EXC_XFER_EE_LITE(0x400, handle_page_fault) - -/* 0x0500 - External Interrupt Exception */ - EXCEPTION(0x0500, HardwareInterrupt, do_IRQ, EXC_XFER_LITE) - -/* 0x0600 - Alignment Exception */ - START_EXCEPTION(0x0600, Alignment) - NORMAL_EXCEPTION_PROLOG - mfspr r4,SPRN_DEAR /* Grab the DEAR and save it */ - stw r4,_DEAR(r11) - addi r3,r1,STACK_FRAME_OVERHEAD - EXC_XFER_EE(0x600, alignment_exception) - -/* 0x0700 - Program Exception */ - START_EXCEPTION(0x0700, ProgramCheck) - NORMAL_EXCEPTION_PROLOG - mfspr r4,SPRN_ESR /* Grab the ESR and save it */ - stw r4,_ESR(r11) - addi r3,r1,STACK_FRAME_OVERHEAD - EXC_XFER_STD(0x700, program_check_exception) - - EXCEPTION(0x0800, Trap_08, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x0900, Trap_09, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x0A00, Trap_0A, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x0B00, Trap_0B, unknown_exception, EXC_XFER_EE) - -/* 0x0C00 - System Call Exception */ - START_EXCEPTION(0x0C00, SystemCall) - NORMAL_EXCEPTION_PROLOG - EXC_XFER_EE_LITE(0xc00, DoSyscall) - - EXCEPTION(0x0D00, Trap_0D, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x0E00, Trap_0E, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x0F00, Trap_0F, unknown_exception, EXC_XFER_EE) - -/* 0x1000 - Programmable Interval Timer (PIT) Exception */ - START_EXCEPTION(0x1000, Decrementer) - NORMAL_EXCEPTION_PROLOG - lis r0,TSR_PIS@h - mtspr SPRN_TSR,r0 /* Clear the PIT exception */ - addi r3,r1,STACK_FRAME_OVERHEAD - EXC_XFER_LITE(0x1000, timer_interrupt) - -#if 0 -/* NOTE: - * FIT and WDT handlers are not implemented yet. - */ - -/* 0x1010 - Fixed Interval Timer (FIT) Exception -*/ - STND_EXCEPTION(0x1010, FITException, unknown_exception) - -/* 0x1020 - Watchdog Timer (WDT) Exception -*/ -#ifdef CONFIG_BOOKE_WDT - CRITICAL_EXCEPTION(0x1020, WDTException, WatchdogException) -#else - CRITICAL_EXCEPTION(0x1020, WDTException, unknown_exception) -#endif -#endif - -/* 0x1100 - Data TLB Miss Exception - * As the name implies, translation is not in the MMU, so search the - * page tables and fix it. The only purpose of this function is to - * load TLB entries from the page table if they exist. - */ - START_EXCEPTION(0x1100, DTLBMiss) - mtspr SPRN_SPRG0, r10 /* Save some working registers */ - mtspr SPRN_SPRG1, r11 -#ifdef CONFIG_403GCX - stw r12, 0(r0) - stw r9, 4(r0) - mfcr r11 - mfspr r12, SPRN_PID - stw r11, 8(r0) - stw r12, 12(r0) -#else - mtspr SPRN_SPRG4, r12 - mtspr SPRN_SPRG5, r9 - mfcr r11 - mfspr r12, SPRN_PID - mtspr SPRN_SPRG7, r11 - mtspr SPRN_SPRG6, r12 -#endif - mfspr r10, SPRN_DEAR /* Get faulting address */ - - /* If we are faulting a kernel address, we have to use the - * kernel page tables. - */ - lis r11, TASK_SIZE@h - cmplw r10, r11 - blt+ 3f - lis r11, swapper_pg_dir@h - ori r11, r11, swapper_pg_dir@l - li r9, 0 - mtspr SPRN_PID, r9 /* TLB will have 0 TID */ - b 4f - - /* Get the PGD for the current thread. - */ -3: - mfspr r11,SPRN_SPRG3 - lwz r11,PGDIR(r11) -4: - tophys(r11, r11) - rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */ - lwz r12, 0(r11) /* Get L1 entry */ - andi. r9, r12, _PMD_PRESENT /* Check if it points to a PTE page */ - beq 2f /* Bail if no table */ - - rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */ - lwz r11, 0(r12) /* Get Linux PTE */ - andi. r9, r11, _PAGE_PRESENT - beq 5f - - ori r11, r11, _PAGE_ACCESSED - stw r11, 0(r12) - - /* Create TLB tag. This is the faulting address plus a static - * set of bits. These are size, valid, E, U0. - */ - li r12, 0x00c0 - rlwimi r10, r12, 0, 20, 31 - - b finish_tlb_load - -2: /* Check for possible large-page pmd entry */ - rlwinm. r9, r12, 2, 22, 24 - beq 5f - - /* Create TLB tag. This is the faulting address, plus a static - * set of bits (valid, E, U0) plus the size from the PMD. - */ - ori r9, r9, 0x40 - rlwimi r10, r9, 0, 20, 31 - mr r11, r12 - - b finish_tlb_load - -5: - /* The bailout. Restore registers to pre-exception conditions - * and call the heavyweights to help us out. - */ -#ifdef CONFIG_403GCX - lwz r12, 12(r0) - lwz r11, 8(r0) - mtspr SPRN_PID, r12 - mtcr r11 - lwz r9, 4(r0) - lwz r12, 0(r0) -#else - mfspr r12, SPRN_SPRG6 - mfspr r11, SPRN_SPRG7 - mtspr SPRN_PID, r12 - mtcr r11 - mfspr r9, SPRN_SPRG5 - mfspr r12, SPRN_SPRG4 -#endif - mfspr r11, SPRN_SPRG1 - mfspr r10, SPRN_SPRG0 - b DataAccess - -/* 0x1200 - Instruction TLB Miss Exception - * Nearly the same as above, except we get our information from different - * registers and bailout to a different point. - */ - START_EXCEPTION(0x1200, ITLBMiss) - mtspr SPRN_SPRG0, r10 /* Save some working registers */ - mtspr SPRN_SPRG1, r11 -#ifdef CONFIG_403GCX - stw r12, 0(r0) - stw r9, 4(r0) - mfcr r11 - mfspr r12, SPRN_PID - stw r11, 8(r0) - stw r12, 12(r0) -#else - mtspr SPRN_SPRG4, r12 - mtspr SPRN_SPRG5, r9 - mfcr r11 - mfspr r12, SPRN_PID - mtspr SPRN_SPRG7, r11 - mtspr SPRN_SPRG6, r12 -#endif - mfspr r10, SPRN_SRR0 /* Get faulting address */ - - /* If we are faulting a kernel address, we have to use the - * kernel page tables. - */ - lis r11, TASK_SIZE@h - cmplw r10, r11 - blt+ 3f - lis r11, swapper_pg_dir@h - ori r11, r11, swapper_pg_dir@l - li r9, 0 - mtspr SPRN_PID, r9 /* TLB will have 0 TID */ - b 4f - - /* Get the PGD for the current thread. - */ -3: - mfspr r11,SPRN_SPRG3 - lwz r11,PGDIR(r11) -4: - tophys(r11, r11) - rlwimi r11, r10, 12, 20, 29 /* Create L1 (pgdir/pmd) address */ - lwz r12, 0(r11) /* Get L1 entry */ - andi. r9, r12, _PMD_PRESENT /* Check if it points to a PTE page */ - beq 2f /* Bail if no table */ - - rlwimi r12, r10, 22, 20, 29 /* Compute PTE address */ - lwz r11, 0(r12) /* Get Linux PTE */ - andi. r9, r11, _PAGE_PRESENT - beq 5f - - ori r11, r11, _PAGE_ACCESSED - stw r11, 0(r12) - - /* Create TLB tag. This is the faulting address plus a static - * set of bits. These are size, valid, E, U0. - */ - li r12, 0x00c0 - rlwimi r10, r12, 0, 20, 31 - - b finish_tlb_load - -2: /* Check for possible large-page pmd entry */ - rlwinm. r9, r12, 2, 22, 24 - beq 5f - - /* Create TLB tag. This is the faulting address, plus a static - * set of bits (valid, E, U0) plus the size from the PMD. - */ - ori r9, r9, 0x40 - rlwimi r10, r9, 0, 20, 31 - mr r11, r12 - - b finish_tlb_load - -5: - /* The bailout. Restore registers to pre-exception conditions - * and call the heavyweights to help us out. - */ -#ifdef CONFIG_403GCX - lwz r12, 12(r0) - lwz r11, 8(r0) - mtspr SPRN_PID, r12 - mtcr r11 - lwz r9, 4(r0) - lwz r12, 0(r0) -#else - mfspr r12, SPRN_SPRG6 - mfspr r11, SPRN_SPRG7 - mtspr SPRN_PID, r12 - mtcr r11 - mfspr r9, SPRN_SPRG5 - mfspr r12, SPRN_SPRG4 -#endif - mfspr r11, SPRN_SPRG1 - mfspr r10, SPRN_SPRG0 - b InstructionAccess - - EXCEPTION(0x1300, Trap_13, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x1400, Trap_14, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x1600, Trap_16, unknown_exception, EXC_XFER_EE) -#ifdef CONFIG_IBM405_ERR51 - /* 405GP errata 51 */ - START_EXCEPTION(0x1700, Trap_17) - b DTLBMiss -#else - EXCEPTION(0x1700, Trap_17, unknown_exception, EXC_XFER_EE) -#endif - EXCEPTION(0x1800, Trap_18, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x1900, Trap_19, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x1A00, Trap_1A, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x1B00, Trap_1B, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x1C00, Trap_1C, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x1D00, Trap_1D, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x1E00, Trap_1E, unknown_exception, EXC_XFER_EE) - EXCEPTION(0x1F00, Trap_1F, unknown_exception, EXC_XFER_EE) - -/* Check for a single step debug exception while in an exception - * handler before state has been saved. This is to catch the case - * where an instruction that we are trying to single step causes - * an exception (eg ITLB/DTLB miss) and thus the first instruction of - * the exception handler generates a single step debug exception. - * - * If we get a debug trap on the first instruction of an exception handler, - * we reset the MSR_DE in the _exception handler's_ MSR (the debug trap is - * a critical exception, so we are using SPRN_CSRR1 to manipulate the MSR). - * The exception handler was handling a non-critical interrupt, so it will - * save (and later restore) the MSR via SPRN_SRR1, which will still have - * the MSR_DE bit set. - */ - /* 0x2000 - Debug Exception */ - START_EXCEPTION(0x2000, DebugTrap) - CRITICAL_EXCEPTION_PROLOG - - /* - * If this is a single step or branch-taken exception in an - * exception entry sequence, it was probably meant to apply to - * the code where the exception occurred (since exception entry - * doesn't turn off DE automatically). We simulate the effect - * of turning off DE on entry to an exception handler by turning - * off DE in the SRR3 value and clearing the debug status. - */ - mfspr r10,SPRN_DBSR /* check single-step/branch taken */ - andis. r10,r10,DBSR_IC@h - beq+ 2f - - andi. r10,r9,MSR_IR|MSR_PR /* check supervisor + MMU off */ - beq 1f /* branch and fix it up */ - - mfspr r10,SPRN_SRR2 /* Faulting instruction address */ - cmplwi r10,0x2100 - bgt+ 2f /* address above exception vectors */ - - /* here it looks like we got an inappropriate debug exception. */ -1: rlwinm r9,r9,0,~MSR_DE /* clear DE in the SRR3 value */ - lis r10,DBSR_IC@h /* clear the IC event */ - mtspr SPRN_DBSR,r10 - /* restore state and get out */ - lwz r10,_CCR(r11) - lwz r0,GPR0(r11) - lwz r1,GPR1(r11) - mtcrf 0x80,r10 - mtspr SPRN_SRR2,r12 - mtspr SPRN_SRR3,r9 - lwz r9,GPR9(r11) - lwz r12,GPR12(r11) - lwz r10,crit_r10@l(0) - lwz r11,crit_r11@l(0) - PPC405_ERR77_SYNC - rfci - b . - - /* continue normal handling for a critical exception... */ -2: mfspr r4,SPRN_DBSR - addi r3,r1,STACK_FRAME_OVERHEAD - EXC_XFER_TEMPLATE(DebugException, 0x2002, \ - (MSR_KERNEL & ~(MSR_ME|MSR_DE|MSR_CE)), \ - NOCOPY, crit_transfer_to_handler, ret_from_crit_exc) - -/* - * The other Data TLB exceptions bail out to this point - * if they can't resolve the lightweight TLB fault. - */ -DataAccess: - NORMAL_EXCEPTION_PROLOG - mfspr r5,SPRN_ESR /* Grab the ESR, save it, pass arg3 */ - stw r5,_ESR(r11) - mfspr r4,SPRN_DEAR /* Grab the DEAR, save it, pass arg2 */ - EXC_XFER_EE_LITE(0x300, handle_page_fault) - -/* Other PowerPC processors, namely those derived from the 6xx-series - * have vectors from 0x2100 through 0x2F00 defined, but marked as reserved. - * However, for the 4xx-series processors these are neither defined nor - * reserved. - */ - - /* Damn, I came up one instruction too many to fit into the - * exception space :-). Both the instruction and data TLB - * miss get to this point to load the TLB. - * r10 - TLB_TAG value - * r11 - Linux PTE - * r12, r9 - avilable to use - * PID - loaded with proper value when we get here - * Upon exit, we reload everything and RFI. - * Actually, it will fit now, but oh well.....a common place - * to load the TLB. - */ -tlb_4xx_index: - .long 0 -finish_tlb_load: - /* load the next available TLB index. - */ - lwz r9, tlb_4xx_index@l(0) - addi r9, r9, 1 - andi. r9, r9, (PPC4XX_TLB_SIZE-1) - stw r9, tlb_4xx_index@l(0) - -6: - /* - * Clear out the software-only bits in the PTE to generate the - * TLB_DATA value. These are the bottom 2 bits of the RPM, the - * top 3 bits of the zone field, and M. - */ - li r12, 0x0ce2 - andc r11, r11, r12 - - tlbwe r11, r9, TLB_DATA /* Load TLB LO */ - tlbwe r10, r9, TLB_TAG /* Load TLB HI */ - - /* Done...restore registers and get out of here. - */ -#ifdef CONFIG_403GCX - lwz r12, 12(r0) - lwz r11, 8(r0) - mtspr SPRN_PID, r12 - mtcr r11 - lwz r9, 4(r0) - lwz r12, 0(r0) -#else - mfspr r12, SPRN_SPRG6 - mfspr r11, SPRN_SPRG7 - mtspr SPRN_PID, r12 - mtcr r11 - mfspr r9, SPRN_SPRG5 - mfspr r12, SPRN_SPRG4 -#endif - mfspr r11, SPRN_SPRG1 - mfspr r10, SPRN_SPRG0 - PPC405_ERR77_SYNC - rfi /* Should sync shadow TLBs */ - b . /* prevent prefetch past rfi */ - -/* extern void giveup_fpu(struct task_struct *prev) - * - * The PowerPC 4xx family of processors do not have an FPU, so this just - * returns. - */ -_GLOBAL(giveup_fpu) - blr - -/* This is where the main kernel code starts. - */ -start_here: - - /* ptr to current */ - lis r2,init_task@h - ori r2,r2,init_task@l - - /* ptr to phys current thread */ - tophys(r4,r2) - addi r4,r4,THREAD /* init task's THREAD */ - mtspr SPRN_SPRG3,r4 - - /* stack */ - lis r1,init_thread_union@ha - addi r1,r1,init_thread_union@l - li r0,0 - stwu r0,THREAD_SIZE-STACK_FRAME_OVERHEAD(r1) - - bl early_init /* We have to do this with MMU on */ - -/* - * Decide what sort of machine this is and initialize the MMU. - */ - mr r3,r31 - mr r4,r30 - mr r5,r29 - mr r6,r28 - mr r7,r27 - bl machine_init - bl MMU_init - -/* Go back to running unmapped so we can load up new values - * and change to using our exception vectors. - * On the 4xx, all we have to do is invalidate the TLB to clear - * the old 16M byte TLB mappings. - */ - lis r4,2f@h - ori r4,r4,2f@l - tophys(r4,r4) - lis r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@h - ori r3,r3,(MSR_KERNEL & ~(MSR_IR|MSR_DR))@l - mtspr SPRN_SRR0,r4 - mtspr SPRN_SRR1,r3 - rfi - b . /* prevent prefetch past rfi */ - -/* Load up the kernel context */ -2: - sync /* Flush to memory before changing TLB */ - tlbia - isync /* Flush shadow TLBs */ - - /* set up the PTE pointers for the Abatron bdiGDB. - */ - lis r6, swapper_pg_dir@h - ori r6, r6, swapper_pg_dir@l - lis r5, abatron_pteptrs@h - ori r5, r5, abatron_pteptrs@l - stw r5, 0xf0(r0) /* Must match your Abatron config file */ - tophys(r5,r5) - stw r6, 0(r5) - -/* Now turn on the MMU for real! */ - lis r4,MSR_KERNEL@h - ori r4,r4,MSR_KERNEL@l - lis r3,start_kernel@h - ori r3,r3,start_kernel@l - mtspr SPRN_SRR0,r3 - mtspr SPRN_SRR1,r4 - rfi /* enable MMU and jump to start_kernel */ - b . /* prevent prefetch past rfi */ - -/* Set up the initial MMU state so we can do the first level of - * kernel initialization. This maps the first 16 MBytes of memory 1:1 - * virtual to physical and more importantly sets the cache mode. - */ -initial_mmu: - tlbia /* Invalidate all TLB entries */ - isync - - /* We should still be executing code at physical address 0x0000xxxx - * at this point. However, start_here is at virtual address - * 0xC000xxxx. So, set up a TLB mapping to cover this once - * translation is enabled. - */ - - lis r3,KERNELBASE@h /* Load the kernel virtual address */ - ori r3,r3,KERNELBASE@l - tophys(r4,r3) /* Load the kernel physical address */ - - iccci r0,r3 /* Invalidate the i-cache before use */ - - /* Load the kernel PID. - */ - li r0,0 - mtspr SPRN_PID,r0 - sync - - /* Configure and load two entries into TLB slots 62 and 63. - * In case we are pinning TLBs, these are reserved in by the - * other TLB functions. If not reserving, then it doesn't - * matter where they are loaded. - */ - clrrwi r4,r4,10 /* Mask off the real page number */ - ori r4,r4,(TLB_WR | TLB_EX) /* Set the write and execute bits */ - - clrrwi r3,r3,10 /* Mask off the effective page number */ - ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_16M)) - - li r0,63 /* TLB slot 63 */ - - tlbwe r4,r0,TLB_DATA /* Load the data portion of the entry */ - tlbwe r3,r0,TLB_TAG /* Load the tag portion of the entry */ - -#if defined(CONFIG_SERIAL_TEXT_DEBUG) && defined(SERIAL_DEBUG_IO_BASE) - - /* Load a TLB entry for the UART, so that ppc4xx_progress() can use - * the UARTs nice and early. We use a 4k real==virtual mapping. */ - - lis r3,SERIAL_DEBUG_IO_BASE@h - ori r3,r3,SERIAL_DEBUG_IO_BASE@l - mr r4,r3 - clrrwi r4,r4,12 - ori r4,r4,(TLB_WR|TLB_I|TLB_M|TLB_G) - - clrrwi r3,r3,12 - ori r3,r3,(TLB_VALID | TLB_PAGESZ(PAGESZ_4K)) - - li r0,0 /* TLB slot 0 */ - tlbwe r4,r0,TLB_DATA - tlbwe r3,r0,TLB_TAG -#endif /* CONFIG_SERIAL_DEBUG_TEXT && SERIAL_DEBUG_IO_BASE */ - - isync - - /* Establish the exception vector base - */ - lis r4,KERNELBASE@h /* EVPR only uses the high 16-bits */ - tophys(r0,r4) /* Use the physical address */ - mtspr SPRN_EVPR,r0 - - blr - -_GLOBAL(abort) - mfspr r13,SPRN_DBCR0 - oris r13,r13,DBCR0_RST_SYSTEM@h - mtspr SPRN_DBCR0,r13 - -_GLOBAL(set_context) - -#ifdef CONFIG_BDI_SWITCH - /* Context switch the PTE pointer for the Abatron BDI2000. - * The PGDIR is the second parameter. - */ - lis r5, KERNELBASE@h - lwz r5, 0xf0(r5) - stw r4, 0x4(r5) -#endif - sync - mtspr SPRN_PID,r3 - isync /* Need an isync to flush shadow */ - /* TLBs after changing PID */ - blr - -/* We put a few things here that have to be page-aligned. This stuff - * goes at the beginning of the data segment, which is page-aligned. - */ - .data - .align 12 - .globl sdata -sdata: - .globl empty_zero_page -empty_zero_page: - .space 4096 - .globl swapper_pg_dir -swapper_pg_dir: - .space 4096 - - -/* Stack for handling critical exceptions from kernel mode */ - .section .bss - .align 12 -exception_stack_bottom: - .space 4096 -critical_stack_top: - .globl exception_stack_top -exception_stack_top: - -/* This space gets a copy of optional info passed to us by the bootstrap - * which is used to pass parameters into the kernel like root=/dev/sda1, etc. - */ - .globl cmd_line -cmd_line: - .space 512 - -/* Room for two PTE pointers, usually the kernel and current user pointers - * to their respective root page table. - */ -abatron_pteptrs: - .space 8 diff --git a/arch/powerpc/mm/40x_mmu.c b/arch/powerpc/mm/40x_mmu.c new file mode 100644 index 000000000000..7ff2609b64d1 --- /dev/null +++ b/arch/powerpc/mm/40x_mmu.c @@ -0,0 +1,135 @@ +/* + * This file contains the routines for initializing the MMU + * on the 4xx series of chips. + * -- paulus + * + * Derived from arch/ppc/mm/init.c: + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au) + * and Cort Dougan (PReP) (cort@cs.nmt.edu) + * Copyright (C) 1996 Paul Mackerras + * + * Derived from "arch/i386/mm/init.c" + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "mmu_decl.h" + +extern int __map_without_ltlbs; +/* + * MMU_init_hw does the chip-specific initialization of the MMU hardware. + */ +void __init MMU_init_hw(void) +{ + /* + * The Zone Protection Register (ZPR) defines how protection will + * be applied to every page which is a member of a given zone. At + * present, we utilize only two of the 4xx's zones. + * The zone index bits (of ZSEL) in the PTE are used for software + * indicators, except the LSB. For user access, zone 1 is used, + * for kernel access, zone 0 is used. We set all but zone 1 + * to zero, allowing only kernel access as indicated in the PTE. + * For zone 1, we set a 01 binary (a value of 10 will not work) + * to allow user access as indicated in the PTE. This also allows + * kernel access as indicated in the PTE. + */ + + mtspr(SPRN_ZPR, 0x10000000); + + flush_instruction_cache(); + + /* + * Set up the real-mode cache parameters for the exception vector + * handlers (which are run in real-mode). + */ + + mtspr(SPRN_DCWR, 0x00000000); /* All caching is write-back */ + + /* + * Cache instruction and data space where the exception + * vectors and the kernel live in real-mode. + */ + + mtspr(SPRN_DCCR, 0xF0000000); /* 512 MB of data space at 0x0. */ + mtspr(SPRN_ICCR, 0xF0000000); /* 512 MB of instr. space at 0x0. */ +} + +#define LARGE_PAGE_SIZE_16M (1<<24) +#define LARGE_PAGE_SIZE_4M (1<<22) + +unsigned long __init mmu_mapin_ram(void) +{ + unsigned long v, s; + phys_addr_t p; + + v = KERNELBASE; + p = PPC_MEMSTART; + s = 0; + + if (__map_without_ltlbs) { + return s; + } + + while (s <= (total_lowmem - LARGE_PAGE_SIZE_16M)) { + pmd_t *pmdp; + unsigned long val = p | _PMD_SIZE_16M | _PAGE_HWEXEC | _PAGE_HWWRITE; + + pmdp = pmd_offset(pgd_offset_k(v), v); + pmd_val(*pmdp++) = val; + pmd_val(*pmdp++) = val; + pmd_val(*pmdp++) = val; + pmd_val(*pmdp++) = val; + + v += LARGE_PAGE_SIZE_16M; + p += LARGE_PAGE_SIZE_16M; + s += LARGE_PAGE_SIZE_16M; + } + + while (s <= (total_lowmem - LARGE_PAGE_SIZE_4M)) { + pmd_t *pmdp; + unsigned long val = p | _PMD_SIZE_4M | _PAGE_HWEXEC | _PAGE_HWWRITE; + + pmdp = pmd_offset(pgd_offset_k(v), v); + pmd_val(*pmdp) = val; + + v += LARGE_PAGE_SIZE_4M; + p += LARGE_PAGE_SIZE_4M; + s += LARGE_PAGE_SIZE_4M; + } + + return s; +} diff --git a/arch/powerpc/mm/4xx_mmu.c b/arch/powerpc/mm/4xx_mmu.c deleted file mode 100644 index 7ff2609b64d1..000000000000 --- a/arch/powerpc/mm/4xx_mmu.c +++ /dev/null @@ -1,135 +0,0 @@ -/* - * This file contains the routines for initializing the MMU - * on the 4xx series of chips. - * -- paulus - * - * Derived from arch/ppc/mm/init.c: - * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) - * - * Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au) - * and Cort Dougan (PReP) (cort@cs.nmt.edu) - * Copyright (C) 1996 Paul Mackerras - * - * Derived from "arch/i386/mm/init.c" - * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include "mmu_decl.h" - -extern int __map_without_ltlbs; -/* - * MMU_init_hw does the chip-specific initialization of the MMU hardware. - */ -void __init MMU_init_hw(void) -{ - /* - * The Zone Protection Register (ZPR) defines how protection will - * be applied to every page which is a member of a given zone. At - * present, we utilize only two of the 4xx's zones. - * The zone index bits (of ZSEL) in the PTE are used for software - * indicators, except the LSB. For user access, zone 1 is used, - * for kernel access, zone 0 is used. We set all but zone 1 - * to zero, allowing only kernel access as indicated in the PTE. - * For zone 1, we set a 01 binary (a value of 10 will not work) - * to allow user access as indicated in the PTE. This also allows - * kernel access as indicated in the PTE. - */ - - mtspr(SPRN_ZPR, 0x10000000); - - flush_instruction_cache(); - - /* - * Set up the real-mode cache parameters for the exception vector - * handlers (which are run in real-mode). - */ - - mtspr(SPRN_DCWR, 0x00000000); /* All caching is write-back */ - - /* - * Cache instruction and data space where the exception - * vectors and the kernel live in real-mode. - */ - - mtspr(SPRN_DCCR, 0xF0000000); /* 512 MB of data space at 0x0. */ - mtspr(SPRN_ICCR, 0xF0000000); /* 512 MB of instr. space at 0x0. */ -} - -#define LARGE_PAGE_SIZE_16M (1<<24) -#define LARGE_PAGE_SIZE_4M (1<<22) - -unsigned long __init mmu_mapin_ram(void) -{ - unsigned long v, s; - phys_addr_t p; - - v = KERNELBASE; - p = PPC_MEMSTART; - s = 0; - - if (__map_without_ltlbs) { - return s; - } - - while (s <= (total_lowmem - LARGE_PAGE_SIZE_16M)) { - pmd_t *pmdp; - unsigned long val = p | _PMD_SIZE_16M | _PAGE_HWEXEC | _PAGE_HWWRITE; - - pmdp = pmd_offset(pgd_offset_k(v), v); - pmd_val(*pmdp++) = val; - pmd_val(*pmdp++) = val; - pmd_val(*pmdp++) = val; - pmd_val(*pmdp++) = val; - - v += LARGE_PAGE_SIZE_16M; - p += LARGE_PAGE_SIZE_16M; - s += LARGE_PAGE_SIZE_16M; - } - - while (s <= (total_lowmem - LARGE_PAGE_SIZE_4M)) { - pmd_t *pmdp; - unsigned long val = p | _PMD_SIZE_4M | _PAGE_HWEXEC | _PAGE_HWWRITE; - - pmdp = pmd_offset(pgd_offset_k(v), v); - pmd_val(*pmdp) = val; - - v += LARGE_PAGE_SIZE_4M; - p += LARGE_PAGE_SIZE_4M; - s += LARGE_PAGE_SIZE_4M; - } - - return s; -} diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 7e4d27ad3dee..bf20fa688809 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_PPC64) += init_64.o pgtable_64.o mmu_context_64.o \ hash_utils_64.o hash_low_64.o tlb_64.o \ slb_low.o slb.o stab.o mmap.o $(hash-y) obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o tlb_32.o -obj-$(CONFIG_40x) += 4xx_mmu.o +obj-$(CONFIG_40x) += 40x_mmu.o obj-$(CONFIG_44x) += 44x_mmu.o obj-$(CONFIG_FSL_BOOKE) += fsl_booke_mmu.o obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig new file mode 100644 index 000000000000..ded357c17414 --- /dev/null +++ b/arch/powerpc/platforms/40x/Kconfig @@ -0,0 +1,208 @@ +config 4xx + bool + depends on 40x || 44x + default y + +config BOOKE + bool + depends on 44x + default y + +menu "AMCC 40x options" + depends on 40x + +#config BUBINGA +# bool "Bubinga" +# depends on 40x +# default n +# select 405EP +# help +# This option enables support for the IBM 405EP evaluation board. + +#config CPCI405 +# bool "CPCI405" +# depends on 40x +# default n +# select 405GP +# help +# This option enables support for the CPCI405 board. + +#config EP405 +# bool "EP405/EP405PC" +# depends on 40x +# default n +# select 405GP +# help +# This option enables support for the EP405/EP405PC boards. + +#config EP405PC +# bool "EP405PC Support" +# depends on EP405 +# default y +# help +# This option enables support for the extra features of the EP405PC board. + +#config REDWOOD_5 +# bool "Redwood-5" +# depends on 40x +# default n +# select STB03xxx +# help +# This option enables support for the IBM STB04 evaluation board. + +#config REDWOOD_6 +# bool "Redwood-6" +# depends on 40x +# default n +# select STB03xxx +# help +# This option enables support for the IBM STBx25xx evaluation board. + +#config SYCAMORE +# bool "Sycamore" +# depends on 40x +# default n +# select 405GPR +# help +# This option enables support for the IBM PPC405GPr evaluation board. + +#config WALNUT +# bool "Walnut" +# depends on 40x +# default y +# select 405GP +# help +# This option enables support for the IBM PPC405GP evaluation board. + +#config XILINX_ML300 +# bool "Xilinx-ML300" +# depends on 40x +# default y +# select VIRTEX_II_PRO +# help +# This option enables support for the Xilinx ML300 evaluation board. + +endmenu + +# 40x specific CPU modules, selected based on the board above. +config NP405H + bool + #depends on ASH + +# OAK doesn't exist but wanted to keep this around for any future 403GCX boards +config 403GCX + bool + #depends on OAK + select IBM405_ERR51 + +config 405GP + bool + select IBM405_ERR77 + select IBM405_ERR51 + +config 405EP + bool + +config 405GPR + bool + +config VIRTEX_II_PRO + bool + select IBM405_ERR77 + select IBM405_ERR51 + +config STB03xxx + bool + select IBM405_ERR77 + select IBM405_ERR51 + +# 40x errata/workaround config symbols, selected by the CPU models above + +# All 405-based cores up until the 405GPR and 405EP have this errata. +config IBM405_ERR77 + bool + +# All 40x-based cores, up until the 405GPR and 405EP have this errata. +config IBM405_ERR51 + bool + +menu "AMCC 44x options" + depends on 44x + +#config BAMBOO +# bool "Bamboo" +# depends on 44x +# default n +# select 440EP +# help +# This option enables support for the IBM PPC440EP evaluation board. + +config EBONY + bool "Ebony" + depends on 44x + default y + select 440GP + help + This option enables support for the IBM PPC440GP evaluation board. + +#config LUAN +# bool "Luan" +# depends on 44x +# default n +# select 440SP +# help +# This option enables support for the IBM PPC440SP evaluation board. + +#config OCOTEA +# bool "Ocotea" +# depends on 44x +# default n +# select 440GX +# help +# This option enables support for the IBM PPC440GX evaluation board. + +endmenu + +# 44x specific CPU modules, selected based on the board above. +config 440EP + bool + select PPC_FPU + select IBM440EP_ERR42 + +config 440GP + bool + select IBM_NEW_EMAC_ZMII + +config 440GX + bool + +config 440SP + bool + +config 440A + bool + depends on 440GX + default y + +# 44x errata/workaround config symbols, selected by the CPU models above +config IBM440EP_ERR42 + bool + +#config XILINX_OCP +# bool +# depends on XILINX_ML300 +# default y + +#config BIOS_FIXUP +# bool +# depends on BUBINGA || EP405 || SYCAMORE || WALNUT +# default y + +#config PPC4xx_DMA +# bool "PPC4xx DMA controller support" +# depends on 4xx + +#config PPC4xx_EDMA +# bool +# depends on !STB03xxx && PPC4xx_DMA +# default y diff --git a/arch/powerpc/platforms/40x/Makefile b/arch/powerpc/platforms/40x/Makefile new file mode 100644 index 000000000000..79ff6b1e887c --- /dev/null +++ b/arch/powerpc/platforms/40x/Makefile @@ -0,0 +1 @@ +# empty makefile so make clean works \ No newline at end of file diff --git a/arch/powerpc/platforms/4xx/Kconfig b/arch/powerpc/platforms/4xx/Kconfig deleted file mode 100644 index ded357c17414..000000000000 --- a/arch/powerpc/platforms/4xx/Kconfig +++ /dev/null @@ -1,208 +0,0 @@ -config 4xx - bool - depends on 40x || 44x - default y - -config BOOKE - bool - depends on 44x - default y - -menu "AMCC 40x options" - depends on 40x - -#config BUBINGA -# bool "Bubinga" -# depends on 40x -# default n -# select 405EP -# help -# This option enables support for the IBM 405EP evaluation board. - -#config CPCI405 -# bool "CPCI405" -# depends on 40x -# default n -# select 405GP -# help -# This option enables support for the CPCI405 board. - -#config EP405 -# bool "EP405/EP405PC" -# depends on 40x -# default n -# select 405GP -# help -# This option enables support for the EP405/EP405PC boards. - -#config EP405PC -# bool "EP405PC Support" -# depends on EP405 -# default y -# help -# This option enables support for the extra features of the EP405PC board. - -#config REDWOOD_5 -# bool "Redwood-5" -# depends on 40x -# default n -# select STB03xxx -# help -# This option enables support for the IBM STB04 evaluation board. - -#config REDWOOD_6 -# bool "Redwood-6" -# depends on 40x -# default n -# select STB03xxx -# help -# This option enables support for the IBM STBx25xx evaluation board. - -#config SYCAMORE -# bool "Sycamore" -# depends on 40x -# default n -# select 405GPR -# help -# This option enables support for the IBM PPC405GPr evaluation board. - -#config WALNUT -# bool "Walnut" -# depends on 40x -# default y -# select 405GP -# help -# This option enables support for the IBM PPC405GP evaluation board. - -#config XILINX_ML300 -# bool "Xilinx-ML300" -# depends on 40x -# default y -# select VIRTEX_II_PRO -# help -# This option enables support for the Xilinx ML300 evaluation board. - -endmenu - -# 40x specific CPU modules, selected based on the board above. -config NP405H - bool - #depends on ASH - -# OAK doesn't exist but wanted to keep this around for any future 403GCX boards -config 403GCX - bool - #depends on OAK - select IBM405_ERR51 - -config 405GP - bool - select IBM405_ERR77 - select IBM405_ERR51 - -config 405EP - bool - -config 405GPR - bool - -config VIRTEX_II_PRO - bool - select IBM405_ERR77 - select IBM405_ERR51 - -config STB03xxx - bool - select IBM405_ERR77 - select IBM405_ERR51 - -# 40x errata/workaround config symbols, selected by the CPU models above - -# All 405-based cores up until the 405GPR and 405EP have this errata. -config IBM405_ERR77 - bool - -# All 40x-based cores, up until the 405GPR and 405EP have this errata. -config IBM405_ERR51 - bool - -menu "AMCC 44x options" - depends on 44x - -#config BAMBOO -# bool "Bamboo" -# depends on 44x -# default n -# select 440EP -# help -# This option enables support for the IBM PPC440EP evaluation board. - -config EBONY - bool "Ebony" - depends on 44x - default y - select 440GP - help - This option enables support for the IBM PPC440GP evaluation board. - -#config LUAN -# bool "Luan" -# depends on 44x -# default n -# select 440SP -# help -# This option enables support for the IBM PPC440SP evaluation board. - -#config OCOTEA -# bool "Ocotea" -# depends on 44x -# default n -# select 440GX -# help -# This option enables support for the IBM PPC440GX evaluation board. - -endmenu - -# 44x specific CPU modules, selected based on the board above. -config 440EP - bool - select PPC_FPU - select IBM440EP_ERR42 - -config 440GP - bool - select IBM_NEW_EMAC_ZMII - -config 440GX - bool - -config 440SP - bool - -config 440A - bool - depends on 440GX - default y - -# 44x errata/workaround config symbols, selected by the CPU models above -config IBM440EP_ERR42 - bool - -#config XILINX_OCP -# bool -# depends on XILINX_ML300 -# default y - -#config BIOS_FIXUP -# bool -# depends on BUBINGA || EP405 || SYCAMORE || WALNUT -# default y - -#config PPC4xx_DMA -# bool "PPC4xx DMA controller support" -# depends on 4xx - -#config PPC4xx_EDMA -# bool -# depends on !STB03xxx && PPC4xx_DMA -# default y diff --git a/arch/powerpc/platforms/4xx/Makefile b/arch/powerpc/platforms/4xx/Makefile deleted file mode 100644 index 79ff6b1e887c..000000000000 --- a/arch/powerpc/platforms/4xx/Makefile +++ /dev/null @@ -1 +0,0 @@ -# empty makefile so make clean works \ No newline at end of file -- cgit v1.2.3 From 4d922c8dc332f4c7bc156fa832187661d4899cee Mon Sep 17 00:00:00 2001 From: Josh Boyer Date: Mon, 20 Aug 2007 07:28:48 -0500 Subject: [POWERPC] 40x MMU Add MMU definitions for 40x platforms. Also fixes two warnings in 40x_mmu.c. Signed-off-by: Josh Boyer Acked-by: David Gibson --- arch/powerpc/kernel/head_40x.S | 2 +- arch/powerpc/mm/40x_mmu.c | 4 +-- include/asm-powerpc/mmu-40x.h | 65 ++++++++++++++++++++++++++++++++++++++++++ include/asm-powerpc/mmu.h | 3 ++ 4 files changed, 71 insertions(+), 3 deletions(-) create mode 100644 include/asm-powerpc/mmu-40x.h (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index adc7f8097cd4..fe8afb60290e 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -772,7 +772,7 @@ finish_tlb_load: */ lwz r9, tlb_4xx_index@l(0) addi r9, r9, 1 - andi. r9, r9, (PPC4XX_TLB_SIZE-1) + andi. r9, r9, (PPC40X_TLB_SIZE-1) stw r9, tlb_4xx_index@l(0) 6: diff --git a/arch/powerpc/mm/40x_mmu.c b/arch/powerpc/mm/40x_mmu.c index 7ff2609b64d1..e067df836be2 100644 --- a/arch/powerpc/mm/40x_mmu.c +++ b/arch/powerpc/mm/40x_mmu.c @@ -108,7 +108,7 @@ unsigned long __init mmu_mapin_ram(void) pmd_t *pmdp; unsigned long val = p | _PMD_SIZE_16M | _PAGE_HWEXEC | _PAGE_HWWRITE; - pmdp = pmd_offset(pgd_offset_k(v), v); + pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v); pmd_val(*pmdp++) = val; pmd_val(*pmdp++) = val; pmd_val(*pmdp++) = val; @@ -123,7 +123,7 @@ unsigned long __init mmu_mapin_ram(void) pmd_t *pmdp; unsigned long val = p | _PMD_SIZE_4M | _PAGE_HWEXEC | _PAGE_HWWRITE; - pmdp = pmd_offset(pgd_offset_k(v), v); + pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v); pmd_val(*pmdp) = val; v += LARGE_PAGE_SIZE_4M; diff --git a/include/asm-powerpc/mmu-40x.h b/include/asm-powerpc/mmu-40x.h new file mode 100644 index 000000000000..7d37f77043ac --- /dev/null +++ b/include/asm-powerpc/mmu-40x.h @@ -0,0 +1,65 @@ +#ifndef _ASM_POWERPC_MMU_40X_H_ +#define _ASM_POWERPC_MMU_40X_H_ + +/* + * PPC40x support + */ + +#define PPC40X_TLB_SIZE 64 + +/* + * TLB entries are defined by a "high" tag portion and a "low" data + * portion. On all architectures, the data portion is 32-bits. + * + * TLB entries are managed entirely under software control by reading, + * writing, and searchoing using the 4xx-specific tlbre, tlbwr, and tlbsx + * instructions. + */ + +#define TLB_LO 1 +#define TLB_HI 0 + +#define TLB_DATA TLB_LO +#define TLB_TAG TLB_HI + +/* Tag portion */ + +#define TLB_EPN_MASK 0xFFFFFC00 /* Effective Page Number */ +#define TLB_PAGESZ_MASK 0x00000380 +#define TLB_PAGESZ(x) (((x) & 0x7) << 7) +#define PAGESZ_1K 0 +#define PAGESZ_4K 1 +#define PAGESZ_16K 2 +#define PAGESZ_64K 3 +#define PAGESZ_256K 4 +#define PAGESZ_1M 5 +#define PAGESZ_4M 6 +#define PAGESZ_16M 7 +#define TLB_VALID 0x00000040 /* Entry is valid */ + +/* Data portion */ + +#define TLB_RPN_MASK 0xFFFFFC00 /* Real Page Number */ +#define TLB_PERM_MASK 0x00000300 +#define TLB_EX 0x00000200 /* Instruction execution allowed */ +#define TLB_WR 0x00000100 /* Writes permitted */ +#define TLB_ZSEL_MASK 0x000000F0 +#define TLB_ZSEL(x) (((x) & 0xF) << 4) +#define TLB_ATTR_MASK 0x0000000F +#define TLB_W 0x00000008 /* Caching is write-through */ +#define TLB_I 0x00000004 /* Caching is inhibited */ +#define TLB_M 0x00000002 /* Memory is coherent */ +#define TLB_G 0x00000001 /* Memory is guarded from prefetch */ + +#ifndef __ASSEMBLY__ + +typedef unsigned long phys_addr_t; + +typedef struct { + unsigned long id; + unsigned long vdso_base; +} mm_context_t; + +#endif /* !__ASSEMBLY__ */ + +#endif /* _ASM_POWERPC_MMU_40X_H_ */ diff --git a/include/asm-powerpc/mmu.h b/include/asm-powerpc/mmu.h index d44d211e7588..4c0e1b4f975c 100644 --- a/include/asm-powerpc/mmu.h +++ b/include/asm-powerpc/mmu.h @@ -8,6 +8,9 @@ #elif defined(CONFIG_PPC_STD_MMU) /* 32-bit classic hash table MMU */ # include +#elif defined(CONFIG_40x) +/* 40x-style software loaded TLB */ +# include #elif defined(CONFIG_44x) /* 44x-style software loaded TLB */ # include -- cgit v1.2.3 From a302cb9d95978505b18c12be0cd1e41556564f68 Mon Sep 17 00:00:00 2001 From: Olof Johansson Date: Fri, 31 Aug 2007 13:58:51 +1000 Subject: [POWERPC] Export new __io{re,un}map_at() symbols Export new __io{re,un}map_at() symbols so modules can use them. Signed-off-by: Olof Johansson Signed-off-by: Paul Mackerras --- arch/powerpc/mm/pgtable_64.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 3dfd10db931a..60fd52cd270f 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -228,5 +228,7 @@ void iounmap(volatile void __iomem *token) EXPORT_SYMBOL(ioremap); EXPORT_SYMBOL(ioremap_flags); EXPORT_SYMBOL(__ioremap); +EXPORT_SYMBOL(__ioremap_at); EXPORT_SYMBOL(iounmap); EXPORT_SYMBOL(__iounmap); +EXPORT_SYMBOL(__iounmap_at); -- cgit v1.2.3 From 00efee7d5d0d7888aafbf0d2de76943ee8aca47a Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Fri, 24 Aug 2007 16:58:37 +1000 Subject: [POWERPC] Remove barriers from the SLB shadow buffer update After talking to an IBM POWER hypervisor (PHYP) design and development guy, there seems to be no need for memory barriers when updating the SLB shadow buffer provided we only update it from the current CPU, which we do. Also, these guys see no need in the future for these barriers. Signed-off-by: Michael Neuling Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/entry_64.S | 8 ++++---- arch/powerpc/mm/slb.c | 6 ++---- 2 files changed, 6 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 952eba6701f4..fbbd3f6f0064 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -385,15 +385,15 @@ BEGIN_FTR_SECTION oris r0,r6,(SLB_ESID_V)@h ori r0,r0,(SLB_NUM_BOLTED-1)@l - /* Update the last bolted SLB */ + /* Update the last bolted SLB. No write barriers are needed + * here, provided we only update the current CPU's SLB shadow + * buffer. + */ ld r9,PACA_SLBSHADOWPTR(r13) li r12,0 std r12,SLBSHADOW_STACKESID(r9) /* Clear ESID */ - eieio std r7,SLBSHADOW_STACKVSID(r9) /* Save VSID */ - eieio std r0,SLBSHADOW_STACKESID(r9) /* Save ESID */ - eieio slbie r6 slbie r6 /* Workaround POWER5 < DD2.1 issue */ diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c index ff1811ac6c81..4bee1cfa9dea 100644 --- a/arch/powerpc/mm/slb.c +++ b/arch/powerpc/mm/slb.c @@ -59,14 +59,12 @@ static inline void slb_shadow_update(unsigned long ea, { /* * Clear the ESID first so the entry is not valid while we are - * updating it. + * updating it. No write barriers are needed here, provided + * we only update the current CPU's SLB shadow buffer. */ get_slb_shadow()->save_area[entry].esid = 0; - smp_wmb(); get_slb_shadow()->save_area[entry].vsid = mk_vsid_data(ea, flags); - smp_wmb(); get_slb_shadow()->save_area[entry].esid = mk_esid_data(ea, entry); - smp_wmb(); } static inline void slb_shadow_clear(unsigned long entry) -- cgit v1.2.3 From 2578bfae84a78bd46fdbc0d2f9d39e9fbc9c8a3f Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Fri, 21 Sep 2007 10:16:20 +1000 Subject: [POWERPC] Create and use CONFIG_WORD_SIZE Linus made this suggestion for the x86 merge and this starts the process for powerpc. We assume that CONFIG_PPC64 implies CONFIG_PPC_MERGE and CONFIG_PPC_STD_MMU_32 implies CONFIG_PPC_STD_MMU. Signed-off-by: Stephen Rothwell Signed-off-by: Paul Mackerras --- arch/powerpc/Kconfig | 5 +++++ arch/powerpc/Makefile | 21 ++++++++++++--------- arch/powerpc/kernel/Makefile | 30 +++++++++++++----------------- arch/powerpc/lib/Makefile | 7 ++++--- arch/powerpc/mm/Makefile | 13 ++++++++----- arch/ppc/Kconfig | 4 ++++ 6 files changed, 46 insertions(+), 34 deletions(-) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 26126d27d756..45e86c751f11 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -14,6 +14,11 @@ config 64BIT bool default y if PPC64 +config WORD_SIZE + int + default 64 if PPC64 + default 32 if !PPC64 + config PPC_MERGE def_bool y diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 87aff5372d6e..71632b20b81d 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -39,7 +39,6 @@ KBUILD_DEFCONFIG := $(shell uname -m)_defconfig ifeq ($(CONFIG_PPC64),y) OLDARCH := ppc64 -SZ := 64 new_nm := $(shell if $(NM) --help 2>&1 | grep -- '--synthetic' > /dev/null; then echo y; else echo n; fi) @@ -49,16 +48,21 @@ endif else OLDARCH := ppc -SZ := 32 +endif + +# It seems there are times we use this Makefile without +# including the config file, but this replicates the old behaviour +ifeq ($(CONFIG_WORD_SIZE),) +CONFIG_WORD_SIZE := 32 endif UTS_MACHINE := $(OLDARCH) ifeq ($(HAS_BIARCH),y) -override AS += -a$(SZ) -override LD += -m elf$(SZ)ppc -override CC += -m$(SZ) -override AR := GNUTARGET=elf$(SZ)-powerpc $(AR) +override AS += -a$(CONFIG_WORD_SIZE) +override LD += -m elf$(CONFIG_WORD_SIZE)ppc +override CC += -m$(CONFIG_WORD_SIZE) +override AR := GNUTARGET=elf$(CONFIG_WORD_SIZE)-powerpc $(AR) endif LDFLAGS_vmlinux := -Bstatic @@ -72,7 +76,7 @@ AFLAGS += $(AFLAGS-y) CFLAGS += -msoft-float -pipe $(CFLAGS-y) CPP = $(CC) -E $(CFLAGS) -CHECKFLAGS += -m$(SZ) -D__powerpc__ -D__powerpc$(SZ)__ +CHECKFLAGS += -m$(CONFIG_WORD_SIZE) -D__powerpc__ -D__powerpc$(CONFIG_WORD_SIZE)__ ifeq ($(CONFIG_PPC64),y) GCC_BROKEN_VEC := $(shell if [ $(call cc-version) -lt 0400 ] ; then echo "y"; fi) @@ -120,8 +124,7 @@ cpu-as-$(CONFIG_E200) += -Wa,-me200 AFLAGS += $(cpu-as-y) CFLAGS += $(cpu-as-y) -head-y := arch/powerpc/kernel/head_32.o -head-$(CONFIG_PPC64) := arch/powerpc/kernel/head_64.o +head-y := arch/powerpc/kernel/head_$(CONFIG_WORD_SIZE).o head-$(CONFIG_8xx) := arch/powerpc/kernel/head_8xx.o head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o head-$(CONFIG_44x) := arch/powerpc/kernel/head_44x.o diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index b37165effb65..fb33a7e71941 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -38,10 +38,10 @@ obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_6xx) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o obj-$(CONFIG_TAU) += tau_6xx.o -obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o -obj32-$(CONFIG_HIBERNATION) += swsusp_32.o -obj64-$(CONFIG_HIBERNATION) += swsusp_64.o swsusp_asm64.o -obj32-$(CONFIG_MODULES) += module_32.o +obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o \ + swsusp_$(CONFIG_WORD_SIZE).o +obj64-$(CONFIG_HIBERNATION) += swsusp_asm64.o +obj-$(CONFIG_MODULES) += module_$(CONFIG_WORD_SIZE).o ifeq ($(CONFIG_PPC_MERGE),y) @@ -54,9 +54,10 @@ extra-$(CONFIG_8xx) := head_8xx.o extra-y += vmlinux.lds obj-y += time.o prom.o traps.o setup-common.o \ - udbg.o misc.o io.o -obj-$(CONFIG_PPC32) += entry_32.o setup_32.o misc_32.o -obj-$(CONFIG_PPC64) += misc_64.o dma_64.o iommu.o + udbg.o misc.o io.o \ + misc_$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_PPC32) += entry_32.o setup_32.o +obj-$(CONFIG_PPC64) += dma_64.o iommu.o obj-$(CONFIG_PPC_MULTIPLATFORM) += prom_init.o obj-$(CONFIG_MODULES) += ppc_ksyms.o obj-$(CONFIG_BOOTX_TEXT) += btext.o @@ -64,16 +65,12 @@ obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o -module-$(CONFIG_PPC64) += module_64.o -obj-$(CONFIG_MODULES) += $(module-y) - -pci64-$(CONFIG_PPC64) += pci_64.o pci_dn.o isa-bridge.o -pci32-$(CONFIG_PPC32) := pci_32.o -obj-$(CONFIG_PCI) += $(pci64-y) $(pci32-y) pci-common.o +pci64-$(CONFIG_PPC64) += pci_dn.o isa-bridge.o +obj-$(CONFIG_PCI) += pci_$(CONFIG_WORD_SIZE).o $(pci64-y) \ + pci-common.o obj-$(CONFIG_PCI_MSI) += msi.o -kexec-$(CONFIG_PPC64) := machine_kexec_64.o -kexec-$(CONFIG_PPC32) := machine_kexec_32.o -obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o $(kexec-y) +obj-$(CONFIG_KEXEC) += machine_kexec.o crash.o \ + machine_kexec_$(CONFIG_WORD_SIZE).o obj-$(CONFIG_AUDIT) += audit.o obj64-$(CONFIG_AUDIT) += compat_audit.o @@ -87,7 +84,6 @@ smpobj-$(CONFIG_SMP) += smp.o endif -obj-$(CONFIG_PPC32) += $(obj32-y) obj-$(CONFIG_PPC64) += $(obj64-y) extra-$(CONFIG_PPC_FPU) += fpu.o diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 23bbb1ea7f9f..65d492e316a6 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -7,11 +7,12 @@ EXTRA_CFLAGS += -mno-minimal-toc endif ifeq ($(CONFIG_PPC_MERGE),y) -obj-y := string.o alloc.o -obj-$(CONFIG_PPC32) += div64.o copy_32.o checksum_32.o +obj-y := string.o alloc.o \ + checksum_$(CONFIG_WORD_SIZE).o +obj-$(CONFIG_PPC32) += div64.o copy_32.o endif -obj-$(CONFIG_PPC64) += checksum_64.o copypage_64.o copyuser_64.o \ +obj-$(CONFIG_PPC64) += copypage_64.o copyuser_64.o \ memcpy_64.o usercopy_64.o mem_64.o string.o obj-$(CONFIG_QUICC_ENGINE) += rheap.o obj-$(CONFIG_XMON) += sstep.o diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index bf20fa688809..20629ae95c50 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -6,13 +6,16 @@ ifeq ($(CONFIG_PPC64),y) EXTRA_CFLAGS += -mno-minimal-toc endif -obj-y := fault.o mem.o lmb.o -obj-$(CONFIG_PPC32) += init_32.o pgtable_32.o mmu_context_32.o +obj-y := fault.o mem.o lmb.o \ + init_$(CONFIG_WORD_SIZE).o \ + pgtable_$(CONFIG_WORD_SIZE).o \ + mmu_context_$(CONFIG_WORD_SIZE).o hash-$(CONFIG_PPC_NATIVE) := hash_native_64.o -obj-$(CONFIG_PPC64) += init_64.o pgtable_64.o mmu_context_64.o \ - hash_utils_64.o hash_low_64.o tlb_64.o \ +obj-$(CONFIG_PPC64) += hash_utils_64.o \ slb_low.o slb.o stab.o mmap.o $(hash-y) -obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o tlb_32.o +obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o +obj-$(CONFIG_PPC_STD_MMU) += hash_low_$(CONFIG_WORD_SIZE).o \ + tlb_$(CONFIG_WORD_SIZE).o obj-$(CONFIG_40x) += 40x_mmu.o obj-$(CONFIG_44x) += 44x_mmu.o obj-$(CONFIG_FSL_BOOKE) += fsl_booke_mmu.o diff --git a/arch/ppc/Kconfig b/arch/ppc/Kconfig index c1b34eb383cf..c2087f645ad3 100644 --- a/arch/ppc/Kconfig +++ b/arch/ppc/Kconfig @@ -4,6 +4,10 @@ mainmenu "Linux/PowerPC Kernel Configuration" +config WORD_SIZE + int + default 32 + config MMU bool default y -- cgit v1.2.3 From df174e3be88d4352bfcfe20d11adc671d2961c79 Mon Sep 17 00:00:00 2001 From: Ed Swarthout Date: Fri, 21 Sep 2007 12:53:02 +1000 Subject: [POWERPC] Add memory regions to the kcore list for 32-bit machines The entries are only 32-bit, so restrict the virtual address to stay below 0xffff_ffff. With KERNELBASE set to 0xc000_0000, this in effect restricts access to the first 1GB of real memory. Make setup_kcore conditional on CONFIG_PROC_KCORE for both 32/64. Signed-off-by: Ed Swarthout Signed-off-by: Paul Mackerras --- arch/powerpc/mm/init_32.c | 37 +++++++++++++++++++++++++++++++++++++ arch/powerpc/mm/init_64.c | 2 ++ 2 files changed, 39 insertions(+) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index d65995ae8273..27c234fb5118 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -255,3 +255,40 @@ void free_initrd_mem(unsigned long start, unsigned long end) } } #endif + +#ifdef CONFIG_PROC_KCORE +static struct kcore_list kcore_vmem; + +static int __init setup_kcore(void) +{ + int i; + + for (i = 0; i < lmb.memory.cnt; i++) { + unsigned long base; + unsigned long size; + struct kcore_list *kcore_mem; + + base = lmb.memory.region[i].base; + size = lmb.memory.region[i].size; + + kcore_mem = kmalloc(sizeof(struct kcore_list), GFP_ATOMIC); + if (!kcore_mem) + panic("%s: kmalloc failed\n", __FUNCTION__); + + /* must stay under 32 bits */ + if ( 0xfffffffful - (unsigned long)__va(base) < size) { + size = 0xfffffffful - (unsigned long)(__va(base)); + printk(KERN_DEBUG "setup_kcore: restrict size=%lx\n", + size); + } + + kclist_add(kcore_mem, __va(base), size); + } + + kclist_add(&kcore_vmem, (void *)VMALLOC_START, + VMALLOC_END-VMALLOC_START); + + return 0; +} +module_init(setup_kcore); +#endif diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 9f27bb56a61d..fa90f6561b9f 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -113,6 +113,7 @@ void free_initrd_mem(unsigned long start, unsigned long end) } #endif +#ifdef CONFIG_PROC_KCORE static struct kcore_list kcore_vmem; static int __init setup_kcore(void) @@ -139,6 +140,7 @@ static int __init setup_kcore(void) return 0; } module_init(setup_kcore); +#endif static void zero_ctor(void *addr, struct kmem_cache *cache, unsigned long flags) { -- cgit v1.2.3 From 544cdabe642e5508e784de709530a74d0775d070 Mon Sep 17 00:00:00 2001 From: John Traill Date: Tue, 17 Jul 2007 05:17:23 +0400 Subject: [POWERPC] 8xx: Set initial memory limit. The 8xx can only support a max of 8M during early boot (it seems a lot of 8xx boards only have 8M so the bug was never triggered), but the early allocator isn't aware of this. The following change makes it able to run with larger memory. Signed-off-by: John Traill Signed-off-by: Vitaly Bordug Signed-off-by: Scott Wood Signed-off-by: Kumar Gala --- arch/powerpc/mm/init_32.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 27c234fb5118..977cb1ee5e72 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -132,6 +132,9 @@ void __init MMU_init(void) /* 601 can only access 16MB at the moment */ if (PVR_VER(mfspr(SPRN_PVR)) == 1) __initial_memory_limit = 0x01000000; + /* 8xx can only access 8MB at the moment */ + if (PVR_VER(mfspr(SPRN_PVR)) == 0x50) + __initial_memory_limit = 0x00800000; /* parse args from command line */ MMU_setup(); -- cgit v1.2.3 From 873553b3d6b3b19f187a5630300ece20bbf74afd Mon Sep 17 00:00:00 2001 From: Dale Farnsworth Date: Wed, 3 Oct 2007 12:01:40 -0700 Subject: [POWERPC] 85xx: Failure with odd memory sizes and CONFIG_HIGHMEM The CONFIG_FSL_BOOKE mmu setup code fails when CONFIG_HIGHMEM=y and the 3 fixed TLB entries cannot exactly map the lowmem size. Each TLB entry can map 4MB, 16MB, 64MB or 256MB, so the failure is observed when the kernel lowmem size is not equal to the sum of up to 3 of those values. Normally, memory is sized in nice numbers, but I observed this problem while testing a crash dump kernel. The failure can also be observed by artificially reducing the kernel's main memory via the mem= kernel command line parameter. This commit fixes the problem by setting __initial_memory_limit in adjust_total_lowmem(). Signed-off-by: Dale Farnsworth Signed-off-by: Kumar Gala --- arch/powerpc/mm/fsl_booke_mmu.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/mm/fsl_booke_mmu.c b/arch/powerpc/mm/fsl_booke_mmu.c index afab247d472f..17139daeaff4 100644 --- a/arch/powerpc/mm/fsl_booke_mmu.c +++ b/arch/powerpc/mm/fsl_booke_mmu.c @@ -59,6 +59,7 @@ unsigned int num_tlbcam_entries; static unsigned long __cam0, __cam1, __cam2; extern unsigned long total_lowmem; extern unsigned long __max_low_memory; +extern unsigned long __initial_memory_limit; #define MAX_LOW_MEM CONFIG_LOWMEM_SIZE #define NUM_TLBCAMS (16) @@ -232,4 +233,5 @@ adjust_total_lowmem(void) __cam0 >> 20, __cam1 >> 20, __cam2 >> 20, (total_lowmem - __cam0 - __cam1 - __cam2) >> 20); __max_low_memory = max_low_mem = __cam0 + __cam1 + __cam2; + __initial_memory_limit = __max_low_memory; } -- cgit v1.2.3 From 1189be6508d45183013ddb82b18f4934193de274 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Thu, 11 Oct 2007 20:37:10 +1000 Subject: [POWERPC] Use 1TB segments This makes the kernel use 1TB segments for all kernel mappings and for user addresses of 1TB and above, on machines which support them (currently POWER5+, POWER6 and PA6T). We detect that the machine supports 1TB segments by looking at the ibm,processor-segment-sizes property in the device tree. We don't currently use 1TB segments for user addresses < 1T, since that would effectively prevent 32-bit processes from using huge pages unless we also had a way to revert to using 256MB segments. That would be possible but would involve extra complications (such as keeping track of which segment size was used when HPTEs were inserted) and is not addressed here. Parts of this patch were originally written by Ben Herrenschmidt. Signed-off-by: Paul Mackerras --- arch/powerpc/kernel/entry_64.S | 14 ++- arch/powerpc/kernel/head_64.S | 2 +- arch/powerpc/kernel/process.c | 9 +- arch/powerpc/mm/hash_low_64.S | 73 +++++++++++++-- arch/powerpc/mm/hash_native_64.c | 92 +++++++++---------- arch/powerpc/mm/hash_utils_64.c | 114 ++++++++++++++++------- arch/powerpc/mm/hugetlbpage.c | 13 +-- arch/powerpc/mm/pgtable_64.c | 4 +- arch/powerpc/mm/slb.c | 67 ++++++++------ arch/powerpc/mm/slb_low.S | 37 +++++++- arch/powerpc/mm/stab.c | 6 +- arch/powerpc/mm/tlb_64.c | 20 +++-- arch/powerpc/platforms/cell/spu_base.c | 6 +- arch/powerpc/platforms/cell/spufs/switch.c | 2 +- arch/powerpc/platforms/celleb/htab.c | 34 +++---- arch/powerpc/platforms/iseries/htab.c | 13 +-- arch/powerpc/platforms/ps3/htab.c | 14 +-- arch/powerpc/platforms/pseries/lpar.c | 89 +++++++++--------- include/asm-powerpc/cputable.h | 3 +- include/asm-powerpc/machdep.h | 8 +- include/asm-powerpc/mmu-hash64.h | 140 ++++++++++++++++++++--------- include/asm-powerpc/page_64.h | 8 +- include/asm-powerpc/tlbflush.h | 3 +- 23 files changed, 513 insertions(+), 258 deletions(-) (limited to 'arch/powerpc/mm') diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index fbbd3f6f0064..0ec134034899 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -372,9 +372,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) std r6,PACACURRENT(r13) /* Set new 'current' */ ld r8,KSP(r4) /* new stack pointer */ +BEGIN_FTR_SECTION + b 2f +END_FTR_SECTION_IFCLR(CPU_FTR_SLB) BEGIN_FTR_SECTION clrrdi r6,r8,28 /* get its ESID */ clrrdi r9,r1,28 /* get current sp ESID */ +END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT) +BEGIN_FTR_SECTION + clrrdi r6,r8,40 /* get its 1T ESID */ + clrrdi r9,r1,40 /* get current sp 1T ESID */ +END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) clrldi. r0,r6,2 /* is new ESID c00000000? */ cmpd cr1,r6,r9 /* or is new ESID the same as current ESID? */ cror eq,4*cr1+eq,eq @@ -384,6 +392,11 @@ BEGIN_FTR_SECTION ld r7,KSP_VSID(r4) /* Get new stack's VSID */ oris r0,r6,(SLB_ESID_V)@h ori r0,r0,(SLB_NUM_BOLTED-1)@l +BEGIN_FTR_SECTION + li r9,MMU_SEGSIZE_1T /* insert B field */ + oris r6,r6,(MMU_SEGSIZE_1T << SLBIE_SSIZE_SHIFT)@h + rldimi r7,r9,SLB_VSID_SSIZE_SHIFT,0 +END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) /* Update the last bolted SLB. No write barriers are needed * here, provided we only update the current CPU's SLB shadow @@ -401,7 +414,6 @@ BEGIN_FTR_SECTION isync 2: -END_FTR_SECTION_IFSET(CPU_FTR_SLB) clrrdi r7,r8,THREAD_SHIFT /* base of new stack */ /* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE because we don't need to leave the 288-byte ABI gap at the diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 22ac245bd59a..97c5857faf00 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -935,7 +935,7 @@ _GLOBAL(do_stab_bolted) /* Calculate VSID */ /* This is a kernel address, so protovsid = ESID */ - ASM_VSID_SCRAMBLE(r11, r9) + ASM_VSID_SCRAMBLE(r11, r9, 256M) rldic r9,r11,12,16 /* r9 = vsid << 12 */ /* Search the primary group for a free entry */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 15998b57767c..7949c203cb89 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -564,10 +564,15 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long usp, #ifdef CONFIG_PPC64 if (cpu_has_feature(CPU_FTR_SLB)) { - unsigned long sp_vsid = get_kernel_vsid(sp); + unsigned long sp_vsid; unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp; - sp_vsid <<= SLB_VSID_SHIFT; + if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) + sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T) + << SLB_VSID_SHIFT_1T; + else + sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_256M) + << SLB_VSID_SHIFT; sp_vsid |= SLB_VSID_KERNEL | llp; p->thread.ksp_vsid = sp_vsid; } diff --git a/arch/powerpc/mm/hash_low_64.S b/arch/powerpc/mm/hash_low_64.S index 35eabfb50723..ad253b959030 100644 --- a/arch/powerpc/mm/hash_low_64.S +++ b/arch/powerpc/mm/hash_low_64.S @@ -54,7 +54,7 @@ /* * _hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, - * pte_t *ptep, unsigned long trap, int local) + * pte_t *ptep, unsigned long trap, int local, int ssize) * * Adds a 4K page to the hash table in a segment of 4K pages only */ @@ -66,6 +66,7 @@ _GLOBAL(__hash_page_4K) /* Save all params that we need after a function call */ std r6,STK_PARM(r6)(r1) std r8,STK_PARM(r8)(r1) + std r9,STK_PARM(r9)(r1) /* Add _PAGE_PRESENT to access */ ori r4,r4,_PAGE_PRESENT @@ -117,6 +118,10 @@ _GLOBAL(__hash_page_4K) * r4 (access) is re-useable, we use it for the new HPTE flags */ +BEGIN_FTR_SECTION + cmpdi r9,0 /* check segment size */ + bne 3f +END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) /* Calc va and put it in r29 */ rldicr r29,r5,28,63-28 rldicl r3,r3,0,36 @@ -126,9 +131,20 @@ _GLOBAL(__hash_page_4K) rldicl r5,r5,0,25 /* vsid & 0x0000007fffffffff */ rldicl r0,r3,64-12,48 /* (ea >> 12) & 0xffff */ 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 */ + 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 */ - andi. r3,r30,0x1fe /* Get basic set of flags */ +4: andi. r3,r30,0x1fe /* Get basic set of flags */ xori r3,r3,HPTE_R_N /* _PAGE_EXEC -> NOEXEC */ rlwinm r0,r30,32-9+1,30,30 /* _PAGE_RW -> _PAGE_USER (r0) */ rlwinm r4,r30,32-7+1,30,30 /* _PAGE_DIRTY -> _PAGE_USER (r4) */ @@ -183,6 +199,7 @@ htab_insert_pte: mr r4,r29 /* Retreive va */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_4K /* page size */ + ld r9,STK_PARM(r9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert1) bl . /* Patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -205,6 +222,7 @@ _GLOBAL(htab_call_hpte_insert1) mr r4,r29 /* Retreive va */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_4K /* page size */ + ld r9,STK_PARM(r9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert2) bl . /* Patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -273,7 +291,8 @@ htab_modify_pte: /* Call ppc_md.hpte_updatepp */ mr r5,r29 /* va */ li r6,MMU_PAGE_4K /* page size */ - ld r7,STK_PARM(r8)(r1) /* get "local" param */ + ld r7,STK_PARM(r9)(r1) /* segment size */ + ld r8,STK_PARM(r8)(r1) /* get "local" param */ _GLOBAL(htab_call_hpte_updatepp) bl . /* Patched by htab_finish_init() */ @@ -325,6 +344,7 @@ _GLOBAL(__hash_page_4K) /* Save all params that we need after a function call */ std r6,STK_PARM(r6)(r1) std r8,STK_PARM(r8)(r1) + std r9,STK_PARM(r9)(r1) /* Add _PAGE_PRESENT to access */ ori r4,r4,_PAGE_PRESENT @@ -383,18 +403,33 @@ _GLOBAL(__hash_page_4K) /* Load the hidx index */ rldicl r25,r3,64-12,60 +BEGIN_FTR_SECTION + cmpdi r9,0 /* check segment size */ + bne 3f +END_FTR_SECTION_IFSET(CPU_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 + or r29,r3,r29 /* r29 = va */ /* Calculate hash value for primary slot and store it in r28 */ rldicl r5,r5,0,25 /* vsid & 0x0000007fffffffff */ rldicl r0,r3,64-12,48 /* (ea >> 12) & 0xffff */ 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 */ + 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 */ - andi. r3,r30,0x1fe /* Get basic set of flags */ +4: andi. r3,r30,0x1fe /* Get basic set of flags */ xori r3,r3,HPTE_R_N /* _PAGE_EXEC -> NOEXEC */ rlwinm r0,r30,32-9+1,30,30 /* _PAGE_RW -> _PAGE_USER (r0) */ rlwinm r4,r30,32-7+1,30,30 /* _PAGE_DIRTY -> _PAGE_USER (r4) */ @@ -462,6 +497,7 @@ htab_special_pfn: mr r4,r29 /* Retreive va */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_4K /* page size */ + ld r9,STK_PARM(r9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert1) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -488,6 +524,7 @@ _GLOBAL(htab_call_hpte_insert1) mr r4,r29 /* Retreive va */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_4K /* page size */ + ld r9,STK_PARM(r9)(r1) /* segment size */ _GLOBAL(htab_call_hpte_insert2) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -586,7 +623,8 @@ htab_modify_pte: /* Call ppc_md.hpte_updatepp */ mr r5,r29 /* va */ li r6,MMU_PAGE_4K /* page size */ - ld r7,STK_PARM(r8)(r1) /* get "local" param */ + ld r7,STK_PARM(r9)(r1) /* segment size */ + ld r8,STK_PARM(r8)(r1) /* get "local" param */ _GLOBAL(htab_call_hpte_updatepp) bl . /* patched by htab_finish_init() */ @@ -634,6 +672,7 @@ _GLOBAL(__hash_page_64K) /* Save all params that we need after a function call */ std r6,STK_PARM(r6)(r1) std r8,STK_PARM(r8)(r1) + std r9,STK_PARM(r9)(r1) /* Add _PAGE_PRESENT to access */ ori r4,r4,_PAGE_PRESENT @@ -690,6 +729,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE) * r4 (access) is re-useable, we use it for the new HPTE flags */ +BEGIN_FTR_SECTION + cmpdi r9,0 /* check segment size */ + bne 3f +END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) /* Calc va and put it in r29 */ rldicr r29,r5,28,63-28 rldicl r3,r3,0,36 @@ -699,9 +742,20 @@ END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE) rldicl r5,r5,0,25 /* vsid & 0x0000007fffffffff */ rldicl r0,r3,64-16,52 /* (ea >> 16) & 0xfff */ 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 */ + 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 */ - andi. r3,r30,0x1fe /* Get basic set of flags */ +4: andi. r3,r30,0x1fe /* Get basic set of flags */ xori r3,r3,HPTE_R_N /* _PAGE_EXEC -> NOEXEC */ rlwinm r0,r30,32-9+1,30,30 /* _PAGE_RW -> _PAGE_USER (r0) */ rlwinm r4,r30,32-7+1,30,30 /* _PAGE_DIRTY -> _PAGE_USER (r4) */ @@ -756,6 +810,7 @@ ht64_insert_pte: mr r4,r29 /* Retreive va */ li r7,0 /* !bolted, !secondary */ li r8,MMU_PAGE_64K + ld r9,STK_PARM(r9)(r1) /* segment size */ _GLOBAL(ht64_call_hpte_insert1) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -778,6 +833,7 @@ _GLOBAL(ht64_call_hpte_insert1) mr r4,r29 /* Retreive va */ li r7,HPTE_V_SECONDARY /* !bolted, secondary */ li r8,MMU_PAGE_64K + ld r9,STK_PARM(r9)(r1) /* segment size */ _GLOBAL(ht64_call_hpte_insert2) bl . /* patched by htab_finish_init() */ cmpdi 0,r3,0 @@ -846,7 +902,8 @@ ht64_modify_pte: /* Call ppc_md.hpte_updatepp */ mr r5,r29 /* va */ li r6,MMU_PAGE_64K - ld r7,STK_PARM(r8)(r1) /* get "local" param */ + ld r7,STK_PARM(r9)(r1) /* segment size */ + ld r8,STK_PARM(r8)(r1) /* get "local" param */ _GLOBAL(ht64_call_hpte_updatepp) bl . /* patched by htab_finish_init() */ diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c index 6ba9b47e55af..34e5c0b219b9 100644 --- a/arch/powerpc/mm/hash_native_64.c +++ b/arch/powerpc/mm/hash_native_64.c @@ -38,7 +38,7 @@ static DEFINE_SPINLOCK(native_tlbie_lock); -static inline void __tlbie(unsigned long va, unsigned int psize) +static inline void __tlbie(unsigned long va, int psize, int ssize) { unsigned int penc; @@ -48,18 +48,20 @@ static inline void __tlbie(unsigned long va, unsigned int psize) switch (psize) { case MMU_PAGE_4K: va &= ~0xffful; + va |= ssize << 8; asm volatile("tlbie %0,0" : : "r" (va) : "memory"); break; default: penc = mmu_psize_defs[psize].penc; va &= ~((1ul << mmu_psize_defs[psize].shift) - 1); va |= penc << 12; + va |= ssize << 8; asm volatile("tlbie %0,1" : : "r" (va) : "memory"); break; } } -static inline void __tlbiel(unsigned long va, unsigned int psize) +static inline void __tlbiel(unsigned long va, int psize, int ssize) { unsigned int penc; @@ -69,6 +71,7 @@ static inline void __tlbiel(unsigned long va, unsigned int psize) switch (psize) { case MMU_PAGE_4K: va &= ~0xffful; + va |= ssize << 8; asm volatile(".long 0x7c000224 | (%0 << 11) | (0 << 21)" : : "r"(va) : "memory"); break; @@ -76,6 +79,7 @@ static inline void __tlbiel(unsigned long va, unsigned int psize) penc = mmu_psize_defs[psize].penc; va &= ~((1ul << mmu_psize_defs[psize].shift) - 1); va |= penc << 12; + va |= ssize << 8; asm volatile(".long 0x7c000224 | (%0 << 11) | (1 << 21)" : : "r"(va) : "memory"); break; @@ -83,7 +87,7 @@ static inline void __tlbiel(unsigned long va, unsigned int psize) } -static inline void tlbie(unsigned long va, int psize, int local) +static inline void tlbie(unsigned long va, int psize, int ssize, int local) { unsigned int use_local = local && cpu_has_feature(CPU_FTR_TLBIEL); int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE); @@ -94,10 +98,10 @@ static inline void tlbie(unsigned long va, int psize, int local) spin_lock(&native_tlbie_lock); asm volatile("ptesync": : :"memory"); if (use_local) { - __tlbiel(va, psize); + __tlbiel(va, psize, ssize); asm volatile("ptesync": : :"memory"); } else { - __tlbie(va, psize); + __tlbie(va, psize, ssize); asm volatile("eieio; tlbsync; ptesync": : :"memory"); } if (lock_tlbie && !use_local) @@ -126,7 +130,7 @@ static inline void native_unlock_hpte(struct hash_pte *hptep) static long native_hpte_insert(unsigned long hpte_group, unsigned long va, unsigned long pa, unsigned long rflags, - unsigned long vflags, int psize) + unsigned long vflags, int psize, int ssize) { struct hash_pte *hptep = htab_address + hpte_group; unsigned long hpte_v, hpte_r; @@ -153,7 +157,7 @@ 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) | vflags | HPTE_V_VALID; + hpte_v = hpte_encode_v(va, psize, ssize) | vflags | HPTE_V_VALID; hpte_r = hpte_encode_r(pa, psize) | rflags; if (!(vflags & HPTE_V_BOLTED)) { @@ -215,13 +219,14 @@ 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 local) + unsigned long va, 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); + want_v = hpte_encode_v(va, psize, ssize); DBG_LOW(" update(va=%016lx, avpnv=%016lx, hash=%016lx, newpp=%x)", va, want_v & HPTE_V_AVPN, slot, newpp); @@ -243,39 +248,32 @@ 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, local); + tlbie(va, psize, ssize, local); return ret; } -static long native_hpte_find(unsigned long va, int psize) +static long native_hpte_find(unsigned long va, int psize, int ssize) { struct hash_pte *hptep; unsigned long hash; - unsigned long i, j; + unsigned long i; long slot; unsigned long want_v, hpte_v; - hash = hpt_hash(va, mmu_psize_defs[psize].shift); - want_v = hpte_encode_v(va, psize); + hash = hpt_hash(va, mmu_psize_defs[psize].shift, ssize); + want_v = hpte_encode_v(va, psize, ssize); - for (j = 0; j < 2; j++) { - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; - for (i = 0; i < HPTES_PER_GROUP; i++) { - hptep = htab_address + slot; - hpte_v = hptep->v; + /* Bolted mappings are only ever in the primary group */ + slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; + for (i = 0; i < HPTES_PER_GROUP; i++) { + hptep = htab_address + slot; + hpte_v = hptep->v; - if (HPTE_V_COMPARE(hpte_v, want_v) - && (hpte_v & HPTE_V_VALID) - && ( !!(hpte_v & HPTE_V_SECONDARY) == j)) { - /* HPTE matches */ - if (j) - slot = -slot; - return slot; - } - ++slot; - } - hash = ~hash; + if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) + /* HPTE matches */ + return slot; + ++slot; } return -1; @@ -289,16 +287,16 @@ static long native_hpte_find(unsigned long va, int psize) * No need to lock here because we should be the only user. */ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, - int psize) + int psize, int ssize) { unsigned long vsid, va; long slot; struct hash_pte *hptep; - vsid = get_kernel_vsid(ea); - va = (vsid << 28) | (ea & 0x0fffffff); + vsid = get_kernel_vsid(ea, ssize); + va = hpt_va(ea, vsid, ssize); - slot = native_hpte_find(va, psize); + slot = native_hpte_find(va, psize, ssize); if (slot == -1) panic("could not find page to bolt\n"); hptep = htab_address + slot; @@ -308,11 +306,11 @@ 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, 0); + tlbie(va, psize, ssize, 0); } static void native_hpte_invalidate(unsigned long slot, unsigned long va, - int psize, int local) + int psize, int ssize, int local) { struct hash_pte *hptep = htab_address + slot; unsigned long hpte_v; @@ -323,7 +321,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long va, DBG_LOW(" invalidate(va=%016lx, hash: %x)\n", va, slot); - want_v = hpte_encode_v(va, psize); + want_v = hpte_encode_v(va, psize, ssize); native_lock_hpte(hptep); hpte_v = hptep->v; @@ -335,7 +333,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long va, hptep->v = 0; /* Invalidate the TLB */ - tlbie(va, psize, local); + tlbie(va, psize, ssize, local); local_irq_restore(flags); } @@ -345,7 +343,7 @@ 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, unsigned long *va) + int *psize, int *ssize, unsigned long *va) { unsigned long hpte_r = hpte->r; unsigned long hpte_v = hpte->v; @@ -401,6 +399,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot, *va = avpn; *psize = size; + *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT; } /* @@ -417,7 +416,7 @@ static void native_hpte_clear(void) struct hash_pte *hptep = htab_address; unsigned long hpte_v, va; unsigned long pteg_count; - int psize; + int psize, ssize; pteg_count = htab_hash_mask + 1; @@ -443,9 +442,9 @@ static void native_hpte_clear(void) * already hold the native_tlbie_lock. */ if (hpte_v & HPTE_V_VALID) { - hpte_decode(hptep, slot, &psize, &va); + hpte_decode(hptep, slot, &psize, &ssize, &va); hptep->v = 0; - __tlbie(va, psize); + __tlbie(va, psize, ssize); } } @@ -468,6 +467,7 @@ static void native_flush_hash_range(unsigned long number, int local) real_pte_t pte; struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch); unsigned long psize = batch->psize; + int ssize = batch->ssize; int i; local_irq_save(flags); @@ -477,14 +477,14 @@ static void native_flush_hash_range(unsigned long number, int local) pte = batch->pte[i]; pte_iterate_hashed_subpages(pte, psize, va, index, shift) { - hash = hpt_hash(va, shift); + hash = hpt_hash(va, 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); + want_v = hpte_encode_v(va, psize, ssize); native_lock_hpte(hptep); hpte_v = hptep->v; if (!HPTE_V_COMPARE(hpte_v, want_v) || @@ -504,7 +504,7 @@ static void native_flush_hash_range(unsigned long number, int local) pte_iterate_hashed_subpages(pte, psize, va, index, shift) { - __tlbiel(va, psize); + __tlbiel(va, psize, ssize); } pte_iterate_hashed_end(); } asm volatile("ptesync":::"memory"); @@ -521,7 +521,7 @@ static void native_flush_hash_range(unsigned long number, int local) pte_iterate_hashed_subpages(pte, psize, va, index, shift) { - __tlbie(va, psize); + __tlbie(va, 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 d525f2eba313..611ad084b7e7 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -93,6 +93,8 @@ int mmu_linear_psize = MMU_PAGE_4K; int mmu_virtual_psize = MMU_PAGE_4K; int mmu_vmalloc_psize = MMU_PAGE_4K; int mmu_io_psize = MMU_PAGE_4K; +int mmu_kernel_ssize = MMU_SEGSIZE_256M; +int mmu_highuser_ssize = MMU_SEGSIZE_256M; #ifdef CONFIG_HUGETLB_PAGE int mmu_huge_psize = MMU_PAGE_16M; unsigned int HPAGE_SHIFT; @@ -145,7 +147,8 @@ struct mmu_psize_def mmu_psize_defaults_gp[] = { int htab_bolt_mapping(unsigned long vstart, unsigned long vend, - unsigned long pstart, unsigned long mode, int psize) + unsigned long pstart, unsigned long mode, + int psize, int ssize) { unsigned long vaddr, paddr; unsigned int step, shift; @@ -158,8 +161,8 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, for (vaddr = vstart, paddr = pstart; vaddr < vend; vaddr += step, paddr += step) { unsigned long hash, hpteg; - unsigned long vsid = get_kernel_vsid(vaddr); - unsigned long va = (vsid << 28) | (vaddr & 0x0fffffff); + unsigned long vsid = get_kernel_vsid(vaddr, ssize); + unsigned long va = hpt_va(vaddr, vsid, ssize); tmp_mode = mode; @@ -167,14 +170,14 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, if (!in_kernel_text(vaddr)) tmp_mode = mode | HPTE_R_N; - hash = hpt_hash(va, shift); + hash = hpt_hash(va, shift, ssize); hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); DBG("htab_bolt_mapping: calling %p\n", ppc_md.hpte_insert); BUG_ON(!ppc_md.hpte_insert); ret = ppc_md.hpte_insert(hpteg, va, paddr, - tmp_mode, HPTE_V_BOLTED, psize); + tmp_mode, HPTE_V_BOLTED, psize, ssize); if (ret < 0) break; @@ -186,6 +189,37 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, return ret < 0 ? ret : 0; } +static int __init htab_dt_scan_seg_sizes(unsigned long node, + const char *uname, int depth, + void *data) +{ + char *type = of_get_flat_dt_prop(node, "device_type", NULL); + u32 *prop; + unsigned long size = 0; + + /* We are scanning "cpu" nodes only */ + if (type == NULL || strcmp(type, "cpu") != 0) + return 0; + + prop = (u32 *)of_get_flat_dt_prop(node, "ibm,processor-segment-sizes", + &size); + if (prop == NULL) + return 0; + for (; size >= 4; size -= 4, ++prop) { + if (prop[0] == 40) { + DBG("1T segment support detected\n"); + cur_cpu_spec->cpu_features |= CPU_FTR_1T_SEGMENT; + } + return 1; + } + return 0; +} + +static void __init htab_init_seg_sizes(void) +{ + of_scan_flat_dt(htab_dt_scan_seg_sizes, NULL); +} + static int __init htab_dt_scan_page_sizes(unsigned long node, const char *uname, int depth, void *data) @@ -265,7 +299,6 @@ static int __init htab_dt_scan_page_sizes(unsigned long node, return 0; } - static void __init htab_init_page_sizes(void) { int rc; @@ -398,7 +431,7 @@ void create_section_mapping(unsigned long start, unsigned long end) { BUG_ON(htab_bolt_mapping(start, end, __pa(start), _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX, - mmu_linear_psize)); + mmu_linear_psize, mmu_kernel_ssize)); } #endif /* CONFIG_MEMORY_HOTPLUG */ @@ -449,9 +482,18 @@ void __init htab_initialize(void) DBG(" -> htab_initialize()\n"); + /* Initialize segment sizes */ + htab_init_seg_sizes(); + /* Initialize page sizes */ htab_init_page_sizes(); + if (cpu_has_feature(CPU_FTR_1T_SEGMENT)) { + mmu_kernel_ssize = MMU_SEGSIZE_1T; + mmu_highuser_ssize = MMU_SEGSIZE_1T; + printk(KERN_INFO "Using 1TB segments\n"); + } + /* * Calculate the required size of the htab. We want the number of * PTEGs to equal one half the number of real pages. @@ -523,18 +565,20 @@ void __init htab_initialize(void) if (base != dart_tablebase) BUG_ON(htab_bolt_mapping(base, dart_tablebase, __pa(base), mode_rw, - mmu_linear_psize)); + mmu_linear_psize, + mmu_kernel_ssize)); if ((base + size) > dart_table_end) BUG_ON(htab_bolt_mapping(dart_tablebase+16*MB, base + size, __pa(dart_table_end), mode_rw, - mmu_linear_psize)); + mmu_linear_psize, + mmu_kernel_ssize)); continue; } #endif /* CONFIG_U3_DART */ BUG_ON(htab_bolt_mapping(base, base + size, __pa(base), - mode_rw, mmu_linear_psize)); + mode_rw, mmu_linear_psize, mmu_kernel_ssize)); } /* @@ -553,7 +597,7 @@ void __init htab_initialize(void) BUG_ON(htab_bolt_mapping(tce_alloc_start, tce_alloc_end, __pa(tce_alloc_start), mode_rw, - mmu_linear_psize)); + mmu_linear_psize, mmu_kernel_ssize)); } htab_finish_init(); @@ -621,7 +665,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) pte_t *ptep; cpumask_t tmp; int rc, user_region = 0, local = 0; - int psize; + int psize, ssize; DBG_LOW("hash_page(ea=%016lx, access=%lx, trap=%lx\n", ea, access, trap); @@ -640,20 +684,22 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) DBG_LOW(" user region with no mm !\n"); return 1; } - vsid = get_vsid(mm->context.id, ea); #ifdef CONFIG_PPC_MM_SLICES psize = get_slice_psize(mm, ea); #else psize = mm->context.user_psize; #endif + ssize = user_segment_size(ea); + vsid = get_vsid(mm->context.id, ea, ssize); break; case VMALLOC_REGION_ID: mm = &init_mm; - vsid = get_kernel_vsid(ea); + vsid = get_kernel_vsid(ea, mmu_kernel_ssize); if (ea < VMALLOC_END) psize = mmu_vmalloc_psize; else psize = mmu_io_psize; + ssize = mmu_kernel_ssize; break; default: /* Not a valid range @@ -758,10 +804,10 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap) #ifdef CONFIG_PPC_HAS_HASH_64K if (psize == MMU_PAGE_64K) - rc = __hash_page_64K(ea, access, vsid, ptep, trap, local); + rc = __hash_page_64K(ea, access, vsid, ptep, trap, local, ssize); else #endif /* CONFIG_PPC_HAS_HASH_64K */ - rc = __hash_page_4K(ea, access, vsid, ptep, trap, local); + rc = __hash_page_4K(ea, access, vsid, ptep, trap, local, ssize); #ifndef CONFIG_PPC_64K_PAGES DBG_LOW(" o-pte: %016lx\n", pte_val(*ptep)); @@ -783,6 +829,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, cpumask_t mask; unsigned long flags; int local = 0; + int ssize; BUG_ON(REGION_ID(ea) != USER_REGION_ID); @@ -815,7 +862,8 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, #endif /* CONFIG_PPC_64K_PAGES */ /* Get VSID */ - vsid = get_vsid(mm->context.id, ea); + ssize = user_segment_size(ea); + vsid = get_vsid(mm->context.id, ea, ssize); /* Hash doesn't like irqs */ local_irq_save(flags); @@ -828,28 +876,29 @@ void hash_preload(struct mm_struct *mm, unsigned long ea, /* Hash it in */ #ifdef CONFIG_PPC_HAS_HASH_64K if (mm->context.user_psize == MMU_PAGE_64K) - __hash_page_64K(ea, access, vsid, ptep, trap, local); + __hash_page_64K(ea, access, vsid, ptep, trap, local, ssize); else #endif /* CONFIG_PPC_HAS_HASH_64K */ - __hash_page_4K(ea, access, vsid, ptep, trap, local); + __hash_page_4K(ea, access, vsid, ptep, trap, local, ssize); local_irq_restore(flags); } -void flush_hash_page(unsigned long va, real_pte_t pte, int psize, int local) +void flush_hash_page(unsigned long va, real_pte_t pte, int psize, int ssize, + int local) { unsigned long hash, index, shift, hidx, slot; DBG_LOW("flush_hash_page(va=%016x)\n", va); pte_iterate_hashed_subpages(pte, psize, va, index, shift) { - hash = hpt_hash(va, shift); + hash = hpt_hash(va, 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 %d: hash=%x, hidx=%x\n", index, slot, hidx); - ppc_md.hpte_invalidate(slot, va, psize, local); + ppc_md.hpte_invalidate(slot, va, psize, ssize, local); } pte_iterate_hashed_end(); } @@ -864,7 +913,7 @@ void flush_hash_range(unsigned long number, int local) for (i = 0; i < number; i++) flush_hash_page(batch->vaddr[i], batch->pte[i], - batch->psize, local); + batch->psize, batch->ssize, local); } } @@ -890,17 +939,19 @@ void low_hash_fault(struct pt_regs *regs, unsigned long address) #ifdef CONFIG_DEBUG_PAGEALLOC static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi) { - unsigned long hash, hpteg, vsid = get_kernel_vsid(vaddr); - unsigned long va = (vsid << 28) | (vaddr & 0x0fffffff); + 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 mode = _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX | HPTE_R_N; int ret; - hash = hpt_hash(va, PAGE_SHIFT); + hash = hpt_hash(va, PAGE_SHIFT, mmu_kernel_ssize); hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP); ret = ppc_md.hpte_insert(hpteg, va, __pa(vaddr), - mode, HPTE_V_BOLTED, mmu_linear_psize); + mode, HPTE_V_BOLTED, + mmu_linear_psize, mmu_kernel_ssize); BUG_ON (ret < 0); spin_lock(&linear_map_hash_lock); BUG_ON(linear_map_hash_slots[lmi] & 0x80); @@ -910,10 +961,11 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi) static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi) { - unsigned long hash, hidx, slot, vsid = get_kernel_vsid(vaddr); - unsigned long va = (vsid << 28) | (vaddr & 0x0fffffff); + 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); - hash = hpt_hash(va, PAGE_SHIFT); + hash = hpt_hash(va, 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; @@ -923,7 +975,7 @@ 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, 0); + ppc_md.hpte_invalidate(slot, va, 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.c b/arch/powerpc/mm/hugetlbpage.c index ba5f12a60467..08f0d9ff7712 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -403,11 +403,12 @@ int hash_huge_page(struct mm_struct *mm, unsigned long access, unsigned long va, rflags, pa; long slot; int err = 1; + int ssize = user_segment_size(ea); ptep = huge_pte_offset(mm, ea); /* Search the Linux page table for a match with va */ - va = (vsid << 28) | (ea & 0x0fffffff); + va = hpt_va(ea, vsid, ssize); /* * If no pte found or not present, send the problem up to @@ -458,19 +459,19 @@ int hash_huge_page(struct mm_struct *mm, unsigned long access, /* There MIGHT be an HPTE for this pte */ unsigned long hash, slot; - hash = hpt_hash(va, HPAGE_SHIFT); + hash = hpt_hash(va, HPAGE_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_huge_psize, - local) == -1) + ssize, local) == -1) old_pte &= ~_PAGE_HPTEFLAGS; } if (likely(!(old_pte & _PAGE_HASHPTE))) { - unsigned long hash = hpt_hash(va, HPAGE_SHIFT); + unsigned long hash = hpt_hash(va, HPAGE_SHIFT, ssize); unsigned long hpte_group; pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT; @@ -489,7 +490,7 @@ repeat: /* Insert into the hash table, primary slot */ slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, 0, - mmu_huge_psize); + mmu_huge_psize, ssize); /* Primary is full, try the secondary */ if (unlikely(slot == -1)) { @@ -497,7 +498,7 @@ repeat: HPTES_PER_GROUP) & ~0x7UL; slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, HPTE_V_SECONDARY, - mmu_huge_psize); + mmu_huge_psize, ssize); if (slot == -1) { if (mftb() & 0x1) hpte_group = ((hash & htab_hash_mask) * diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 60fd52cd270f..3ef0ad2f9ca0 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -87,8 +87,8 @@ static int map_io_page(unsigned long ea, unsigned long pa, int flags) * entry in the hardware page table. * */ - if (htab_bolt_mapping(ea, (unsigned long)ea + PAGE_SIZE, - pa, flags, mmu_io_psize)) { + if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags, + mmu_io_psize, mmu_kernel_ssize)) { printk(KERN_ERR "Failed to do bolted mapping IO " "memory at %016lx !\n", pa); return -ENOMEM; diff --git a/arch/powerpc/mm/slb.c b/arch/powerpc/mm/slb.c index 4bee1cfa9dea..6c164cec9d2c 100644 --- a/arch/powerpc/mm/slb.c +++ b/arch/powerpc/mm/slb.c @@ -43,17 +43,26 @@ static void slb_allocate(unsigned long ea) slb_allocate_realmode(ea); } -static inline unsigned long mk_esid_data(unsigned long ea, unsigned long slot) +static inline unsigned long mk_esid_data(unsigned long ea, int ssize, + unsigned long slot) { - return (ea & ESID_MASK) | SLB_ESID_V | slot; + unsigned long mask; + + mask = (ssize == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T; + return (ea & mask) | SLB_ESID_V | slot; } -static inline unsigned long mk_vsid_data(unsigned long ea, unsigned long flags) +#define slb_vsid_shift(ssize) \ + ((ssize) == MMU_SEGSIZE_256M? SLB_VSID_SHIFT: SLB_VSID_SHIFT_1T) + +static inline unsigned long mk_vsid_data(unsigned long ea, int ssize, + unsigned long flags) { - return (get_kernel_vsid(ea) << SLB_VSID_SHIFT) | flags; + return (get_kernel_vsid(ea, ssize) << slb_vsid_shift(ssize)) | flags | + ((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT); } -static inline void slb_shadow_update(unsigned long ea, +static inline void slb_shadow_update(unsigned long ea, int ssize, unsigned long flags, unsigned long entry) { @@ -63,8 +72,8 @@ static inline void slb_shadow_update(unsigned long ea, * we only update the current CPU's SLB shadow buffer. */ get_slb_shadow()->save_area[entry].esid = 0; - get_slb_shadow()->save_area[entry].vsid = mk_vsid_data(ea, flags); - get_slb_shadow()->save_area[entry].esid = mk_esid_data(ea, entry); + get_slb_shadow()->save_area[entry].vsid = mk_vsid_data(ea, ssize, flags); + get_slb_shadow()->save_area[entry].esid = mk_esid_data(ea, ssize, entry); } static inline void slb_shadow_clear(unsigned long entry) @@ -72,7 +81,8 @@ static inline void slb_shadow_clear(unsigned long entry) get_slb_shadow()->save_area[entry].esid = 0; } -static inline void create_shadowed_slbe(unsigned long ea, unsigned long flags, +static inline void create_shadowed_slbe(unsigned long ea, int ssize, + unsigned long flags, unsigned long entry) { /* @@ -80,11 +90,11 @@ static inline void create_shadowed_slbe(unsigned long ea, unsigned long flags, * we don't get a stale entry here if we get preempted by PHYP * between these two statements. */ - slb_shadow_update(ea, flags, entry); + slb_shadow_update(ea, ssize, flags, entry); asm volatile("slbmte %0,%1" : - : "r" (mk_vsid_data(ea, flags)), - "r" (mk_esid_data(ea, entry)) + : "r" (mk_vsid_data(ea, ssize, flags)), + "r" (mk_esid_data(ea, ssize, entry)) : "memory" ); } @@ -93,7 +103,7 @@ void slb_flush_and_rebolt(void) /* If you change this make sure you change SLB_NUM_BOLTED * appropriately too. */ unsigned long linear_llp, vmalloc_llp, lflags, vflags; - unsigned long ksp_esid_data; + unsigned long ksp_esid_data, ksp_vsid_data; WARN_ON(!irqs_disabled()); @@ -102,13 +112,15 @@ void slb_flush_and_rebolt(void) lflags = SLB_VSID_KERNEL | linear_llp; vflags = SLB_VSID_KERNEL | vmalloc_llp; - ksp_esid_data = mk_esid_data(get_paca()->kstack, 2); - if ((ksp_esid_data & ESID_MASK) == PAGE_OFFSET) { + ksp_esid_data = mk_esid_data(get_paca()->kstack, mmu_kernel_ssize, 2); + if ((ksp_esid_data & ~0xfffffffUL) <= PAGE_OFFSET) { ksp_esid_data &= ~SLB_ESID_V; + ksp_vsid_data = 0; slb_shadow_clear(2); } else { /* Update stack entry; others don't change */ - slb_shadow_update(get_paca()->kstack, lflags, 2); + slb_shadow_update(get_paca()->kstack, mmu_kernel_ssize, lflags, 2); + ksp_vsid_data = get_slb_shadow()->save_area[2].vsid; } /* We need to do this all in asm, so we're sure we don't touch @@ -120,9 +132,9 @@ void slb_flush_and_rebolt(void) /* Slot 2 - kernel stack */ "slbmte %2,%3\n" "isync" - :: "r"(mk_vsid_data(VMALLOC_START, vflags)), - "r"(mk_esid_data(VMALLOC_START, 1)), - "r"(mk_vsid_data(ksp_esid_data, lflags)), + :: "r"(mk_vsid_data(VMALLOC_START, mmu_kernel_ssize, vflags)), + "r"(mk_esid_data(VMALLOC_START, mmu_kernel_ssize, 1)), + "r"(ksp_vsid_data), "r"(ksp_esid_data) : "memory"); } @@ -132,7 +144,7 @@ void slb_vmalloc_update(void) unsigned long vflags; vflags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_vmalloc_psize].sllp; - slb_shadow_update(VMALLOC_START, vflags, 1); + slb_shadow_update(VMALLOC_START, mmu_kernel_ssize, vflags, 1); slb_flush_and_rebolt(); } @@ -140,7 +152,7 @@ void slb_vmalloc_update(void) void switch_slb(struct task_struct *tsk, struct mm_struct *mm) { unsigned long offset = get_paca()->slb_cache_ptr; - unsigned long esid_data = 0; + unsigned long slbie_data = 0; unsigned long pc = KSTK_EIP(tsk); unsigned long stack = KSTK_ESP(tsk); unsigned long unmapped_base; @@ -149,9 +161,12 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm) int i; asm volatile("isync" : : : "memory"); for (i = 0; i < offset; i++) { - esid_data = ((unsigned long)get_paca()->slb_cache[i] - << SID_SHIFT) | SLBIE_C; - asm volatile("slbie %0" : : "r" (esid_data)); + slbie_data = (unsigned long)get_paca()->slb_cache[i] + << SID_SHIFT; /* EA */ + slbie_data |= user_segment_size(slbie_data) + << SLBIE_SSIZE_SHIFT; + slbie_data |= SLBIE_C; /* C set for user addresses */ + asm volatile("slbie %0" : : "r" (slbie_data)); } asm volatile("isync" : : : "memory"); } else { @@ -160,7 +175,7 @@ void switch_slb(struct task_struct *tsk, struct mm_struct *mm) /* Workaround POWER5 < DD2.1 issue */ if (offset == 1 || offset > SLB_CACHE_ENTRIES) - asm volatile("slbie %0" : : "r" (esid_data)); + asm volatile("slbie %0" : : "r" (slbie_data)); get_paca()->slb_cache_ptr = 0; get_paca()->context = mm->context; @@ -243,9 +258,9 @@ void slb_initialize(void) asm volatile("isync":::"memory"); asm volatile("slbmte %0,%0"::"r" (0) : "memory"); asm volatile("isync; slbia; isync":::"memory"); - create_shadowed_slbe(PAGE_OFFSET, lflags, 0); + create_shadowed_slbe(PAGE_OFFSET, mmu_kernel_ssize, lflags, 0); - create_shadowed_slbe(VMALLOC_START, vflags, 1); + create_shadowed_slbe(VMALLOC_START, mmu_kernel_ssize, vflags, 1); /* We don't bolt the stack for the time being - we're in boot, * so the stack is in the bolted segment. By the time it goes diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index cd1a93d4948c..1328a81a84aa 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -57,7 +57,10 @@ _GLOBAL(slb_allocate_realmode) */ _GLOBAL(slb_miss_kernel_load_linear) li r11,0 +BEGIN_FTR_SECTION b slb_finish_load +END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT) + b slb_finish_load_1T 1: /* vmalloc/ioremap mapping encoding bits, the "li" instructions below * will be patched by the kernel at boot @@ -68,13 +71,16 @@ BEGIN_FTR_SECTION cmpldi r11,(VMALLOC_SIZE >> 28) - 1 bgt 5f lhz r11,PACAVMALLOCSLLP(r13) - b slb_finish_load + b 6f 5: END_FTR_SECTION_IFCLR(CPU_FTR_CI_LARGE_PAGE) _GLOBAL(slb_miss_kernel_load_io) li r11,0 +6: +BEGIN_FTR_SECTION b slb_finish_load - +END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT) + b slb_finish_load_1T 0: /* user address: proto-VSID = context << 15 | ESID. First check * if the address is within the boundaries of the user region @@ -122,7 +128,13 @@ _GLOBAL(slb_miss_kernel_load_io) #endif /* CONFIG_PPC_MM_SLICES */ ld r9,PACACONTEXTID(r13) +BEGIN_FTR_SECTION + cmpldi r10,0x1000 +END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) rldimi r10,r9,USER_ESID_BITS,0 +BEGIN_FTR_SECTION + bge slb_finish_load_1T +END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT) b slb_finish_load 8: /* invalid EA */ @@ -188,7 +200,7 @@ _GLOBAL(slb_allocate_user) * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9, cr7 = <> PAGE_OFFSET */ slb_finish_load: - ASM_VSID_SCRAMBLE(r10,r9) + ASM_VSID_SCRAMBLE(r10,r9,256M) rldimi r11,r10,SLB_VSID_SHIFT,16 /* combine VSID and flags */ /* r3 = EA, r11 = VSID data */ @@ -213,7 +225,7 @@ BEGIN_FW_FTR_SECTION END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES) #endif /* CONFIG_PPC_ISERIES */ - ld r10,PACASTABRR(r13) +7: ld r10,PACASTABRR(r13) addi r10,r10,1 /* use a cpu feature mask if we ever change our slb size */ cmpldi r10,SLB_NUM_ENTRIES @@ -259,3 +271,20 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_ISERIES) crclr 4*cr0+eq /* set result to "success" */ blr +/* + * Finish loading of a 1T SLB entry (for the kernel linear mapping) and return. + * We assume legacy iSeries will never have 1T segments. + * + * r3 = EA, r10 = proto-VSID, r11 = flags, clobbers r9 + */ +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 */ + li r10,MMU_SEGSIZE_1T + rldimi r11,r10,SLB_VSID_SSIZE_SHIFT,0 /* insert segment size */ + + /* r3 = EA, r11 = VSID data */ + clrrdi r3,r3,SID_SHIFT_1T /* clear out non-ESID bits */ + b 7b + diff --git a/arch/powerpc/mm/stab.c b/arch/powerpc/mm/stab.c index 28492bbdee8e..9e85bda76216 100644 --- a/arch/powerpc/mm/stab.c +++ b/arch/powerpc/mm/stab.c @@ -122,12 +122,12 @@ static int __ste_allocate(unsigned long ea, struct mm_struct *mm) /* Kernel or user address? */ if (is_kernel_addr(ea)) { - vsid = get_kernel_vsid(ea); + vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M); } else { if ((ea >= TASK_SIZE_USER64) || (! mm)) return 1; - vsid = get_vsid(mm->context.id, ea); + vsid = get_vsid(mm->context.id, ea, MMU_SEGSIZE_256M); } stab_entry = make_ste(get_paca()->stab_addr, GET_ESID(ea), vsid); @@ -261,7 +261,7 @@ void __init stabs_alloc(void) */ void stab_initialize(unsigned long stab) { - unsigned long vsid = get_kernel_vsid(PAGE_OFFSET); + unsigned long vsid = get_kernel_vsid(PAGE_OFFSET, MMU_SEGSIZE_256M); unsigned long stabreal; asm volatile("isync; slbia; isync":::"memory"); diff --git a/arch/powerpc/mm/tlb_64.c b/arch/powerpc/mm/tlb_64.c index cbd34fc813ee..eafbca52bff9 100644 --- a/arch/powerpc/mm/tlb_64.c +++ b/arch/powerpc/mm/tlb_64.c @@ -132,6 +132,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, struct ppc64_tlb_batch *batch = &__get_cpu_var(ppc64_tlb_batch); unsigned long vsid, vaddr; unsigned int psize; + int ssize; real_pte_t rpte; int i; @@ -161,11 +162,14 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, /* Build full vaddr */ if (!is_kernel_addr(addr)) { - vsid = get_vsid(mm->context.id, addr); + ssize = user_segment_size(addr); + vsid = get_vsid(mm->context.id, addr, ssize); WARN_ON(vsid == 0); - } else - vsid = get_kernel_vsid(addr); - vaddr = (vsid << 28 ) | (addr & 0x0fffffff); + } else { + vsid = get_kernel_vsid(addr, mmu_kernel_ssize); + ssize = mmu_kernel_ssize; + } + vaddr = hpt_va(addr, vsid, ssize); rpte = __real_pte(__pte(pte), ptep); /* @@ -175,7 +179,7 @@ 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, 0); + flush_hash_page(vaddr, rpte, psize, ssize, 0); return; } @@ -189,13 +193,15 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr, * We also need to ensure only one page size is present in a given * batch */ - if (i != 0 && (mm != batch->mm || batch->psize != psize)) { + if (i != 0 && (mm != batch->mm || batch->psize != psize || + batch->ssize != ssize)) { __flush_tlb_pending(batch); i = 0; } if (i == 0) { batch->mm = mm; batch->psize = psize; + batch->ssize = ssize; } batch->pte[i] = rpte; batch->vaddr[i] = vaddr; @@ -222,7 +228,7 @@ void __flush_tlb_pending(struct ppc64_tlb_batch *batch) local = 1; if (i == 1) flush_hash_page(batch->vaddr[0], batch->pte[0], - batch->psize, local); + batch->psize, batch->ssize, local); else flush_hash_range(i, local); batch->index = 0; diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index b5a21177bb32..c83c3e3f5178 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -168,7 +168,7 @@ static int __spu_trap_data_seg(struct spu *spu, unsigned long ea) #else psize = mm->context.user_psize; #endif - vsid = (get_vsid(mm->context.id, ea) << SLB_VSID_SHIFT) | + vsid = (get_vsid(mm->context.id, ea, MMU_SEGSIZE_256M) << SLB_VSID_SHIFT) | SLB_VSID_USER; break; case VMALLOC_REGION_ID: @@ -176,12 +176,12 @@ static int __spu_trap_data_seg(struct spu *spu, unsigned long ea) psize = mmu_vmalloc_psize; else psize = mmu_io_psize; - vsid = (get_kernel_vsid(ea) << SLB_VSID_SHIFT) | + vsid = (get_kernel_vsid(ea, MMU_SEGSIZE_256M) << SLB_VSID_SHIFT) | SLB_VSID_KERNEL; break; case KERNEL_REGION_ID: psize = mmu_linear_psize; - vsid = (get_kernel_vsid(ea) << SLB_VSID_SHIFT) | + vsid = (get_kernel_vsid(ea, MMU_SEGSIZE_256M) << SLB_VSID_SHIFT) | SLB_VSID_KERNEL; break; default: diff --git a/arch/powerpc/platforms/cell/spufs/switch.c b/arch/powerpc/platforms/cell/spufs/switch.c index de7e5ee451d2..3d64c81cc6e2 100644 --- a/arch/powerpc/platforms/cell/spufs/switch.c +++ b/arch/powerpc/platforms/cell/spufs/switch.c @@ -699,7 +699,7 @@ static inline void get_kernel_slb(u64 ea, u64 slb[2]) llp = mmu_psize_defs[mmu_linear_psize].sllp; else llp = mmu_psize_defs[mmu_virtual_psize].sllp; - slb[0] = (get_kernel_vsid(ea) << SLB_VSID_SHIFT) | + slb[0] = (get_kernel_vsid(ea, MMU_SEGSIZE_256M) << SLB_VSID_SHIFT) | SLB_VSID_KERNEL | llp; slb[1] = (ea & ESID_MASK) | SLB_ESID_V; } diff --git a/arch/powerpc/platforms/celleb/htab.c b/arch/powerpc/platforms/celleb/htab.c index 5e75c77ea8f3..fbf27c74ebda 100644 --- a/arch/powerpc/platforms/celleb/htab.c +++ b/arch/powerpc/platforms/celleb/htab.c @@ -90,7 +90,7 @@ 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 rflags, unsigned long vflags, - int psize) + int psize, int ssize) { unsigned long lpar_rc; unsigned long slot; @@ -105,7 +105,8 @@ 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) | vflags | HPTE_V_VALID; + hpte_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M) | + vflags | HPTE_V_VALID; hpte_r = hpte_encode_r(pa, psize) | rflags; if (!(vflags & HPTE_V_BOLTED)) @@ -184,12 +185,12 @@ static void beat_lpar_hptab_clear(void) static long beat_lpar_hpte_updatepp(unsigned long slot, unsigned long newpp, unsigned long va, - int psize, int local) + int psize, int ssize, int local) { unsigned long lpar_rc; unsigned long dummy0, dummy1, want_v; - want_v = hpte_encode_v(va, psize); + want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M); DBG_LOW(" update: " "avpnv=%016lx, slot=%016lx, psize: %d, newpp %016lx ... ", @@ -225,8 +226,8 @@ static long beat_lpar_hpte_find(unsigned long va, int psize) long slot; unsigned long want_v, hpte_v; - hash = hpt_hash(va, mmu_psize_defs[psize].shift); - want_v = hpte_encode_v(va, psize); + hash = hpt_hash(va, mmu_psize_defs[psize].shift, MMU_SEGSIZE_256M); + want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M); for (j = 0; j < 2; j++) { slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; @@ -251,11 +252,11 @@ static long beat_lpar_hpte_find(unsigned long va, int psize) static void beat_lpar_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, - int psize) + int psize, int ssize) { unsigned long lpar_rc, slot, vsid, va, dummy0, dummy1; - vsid = get_kernel_vsid(ea); + vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M); va = (vsid << 28) | (ea & 0x0fffffff); spin_lock(&beat_htab_lock); @@ -270,7 +271,7 @@ static void beat_lpar_hpte_updateboltedpp(unsigned long newpp, } static void beat_lpar_hpte_invalidate(unsigned long slot, unsigned long va, - int psize, int local) + int psize, int ssize, int local) { unsigned long want_v; unsigned long lpar_rc; @@ -279,7 +280,7 @@ 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); + want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M); spin_lock_irqsave(&beat_htab_lock, flags); dummy1 = beat_lpar_hpte_getword0(slot); @@ -310,7 +311,7 @@ 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 rflags, unsigned long vflags, - int psize) + int psize, int ssize) { unsigned long lpar_rc; unsigned long slot; @@ -325,7 +326,8 @@ static long beat_lpar_hpte_insert_v3(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) | vflags | HPTE_V_VALID; + hpte_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M) | + vflags | HPTE_V_VALID; hpte_r = hpte_encode_r(pa, psize) | rflags; if (!(vflags & HPTE_V_BOLTED)) @@ -363,13 +365,13 @@ 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, - int psize, int local) + int psize, int ssize, int local) { unsigned long lpar_rc; unsigned long want_v; unsigned long pss; - want_v = hpte_encode_v(va, psize); + want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M); pss = (psize == MMU_PAGE_4K) ? -1UL : mmu_psize_defs[psize].penc; DBG_LOW(" update: " @@ -391,7 +393,7 @@ static long beat_lpar_hpte_updatepp_v3(unsigned long slot, } static void beat_lpar_hpte_invalidate_v3(unsigned long slot, unsigned long va, - int psize, int local) + int psize, int ssize, int local) { unsigned long want_v; unsigned long lpar_rc; @@ -399,7 +401,7 @@ static void beat_lpar_hpte_invalidate_v3(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); + want_v = hpte_encode_v(va, 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/iseries/htab.c b/arch/powerpc/platforms/iseries/htab.c index b4e2c7a038e1..15a7097e5dd7 100644 --- a/arch/powerpc/platforms/iseries/htab.c +++ b/arch/powerpc/platforms/iseries/htab.c @@ -86,7 +86,8 @@ long iSeries_hpte_insert(unsigned long hpte_group, unsigned long va, } - lhpte.v = hpte_encode_v(va, MMU_PAGE_4K) | vflags | HPTE_V_VALID; + lhpte.v = hpte_encode_v(va, MMU_PAGE_4K, MMU_SEGSIZE_256M) | + vflags | HPTE_V_VALID; lhpte.r = hpte_encode_r(phys_to_abs(pa), MMU_PAGE_4K) | rflags; /* Now fill in the actual HPTE */ @@ -142,7 +143,7 @@ static long iSeries_hpte_remove(unsigned long hpte_group) * bits 61..63 : PP2,PP1,PP0 */ static long iSeries_hpte_updatepp(unsigned long slot, unsigned long newpp, - unsigned long va, int psize, int local) + unsigned long va, int psize, int ssize, int local) { struct hash_pte hpte; unsigned long want_v; @@ -150,7 +151,7 @@ static long iSeries_hpte_updatepp(unsigned long slot, unsigned long newpp, iSeries_hlock(slot); HvCallHpt_get(&hpte, slot); - want_v = hpte_encode_v(va, MMU_PAGE_4K); + want_v = hpte_encode_v(va, MMU_PAGE_4K, MMU_SEGSIZE_256M); if (HPTE_V_COMPARE(hpte.v, want_v) && (hpte.v & HPTE_V_VALID)) { /* @@ -205,14 +206,14 @@ static long iSeries_hpte_find(unsigned long vpn) * No need to lock here because we should be the only user. */ static void iSeries_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, - int psize) + int psize, int ssize) { unsigned long vsid,va,vpn; long slot; BUG_ON(psize != MMU_PAGE_4K); - vsid = get_kernel_vsid(ea); + vsid = get_kernel_vsid(ea, MMU_SEGSIZE_256M); va = (vsid << 28) | (ea & 0x0fffffff); vpn = va >> HW_PAGE_SHIFT; slot = iSeries_hpte_find(vpn); @@ -222,7 +223,7 @@ static void iSeries_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, } static void iSeries_hpte_invalidate(unsigned long slot, unsigned long va, - int psize, int local) + int psize, int ssize, int local) { unsigned long hpte_v; unsigned long avpn = va >> 23; diff --git a/arch/powerpc/platforms/ps3/htab.c b/arch/powerpc/platforms/ps3/htab.c index 5d2e176a1b18..7382f195c4f8 100644 --- a/arch/powerpc/platforms/ps3/htab.c +++ b/arch/powerpc/platforms/ps3/htab.c @@ -60,7 +60,8 @@ static void _debug_dump_hpte(unsigned long pa, unsigned long va, } static long ps3_hpte_insert(unsigned long hpte_group, unsigned long va, - unsigned long pa, unsigned long rflags, unsigned long vflags, int psize) + unsigned long pa, unsigned long rflags, unsigned long vflags, + int psize, int ssize) { unsigned long slot; struct hash_pte lhpte; @@ -72,7 +73,8 @@ static long ps3_hpte_insert(unsigned long hpte_group, unsigned long va, vflags &= ~HPTE_V_SECONDARY; /* this bit is ignored */ - lhpte.v = hpte_encode_v(va, psize) | vflags | HPTE_V_VALID; + lhpte.v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M) | + vflags | HPTE_V_VALID; lhpte.r = hpte_encode_r(ps3_mm_phys_to_lpar(pa), psize) | rflags; p_pteg = hpte_group / HPTES_PER_GROUP; @@ -167,14 +169,14 @@ 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 local) + unsigned long va, int psize, int ssize, int local) { unsigned long flags; unsigned long result; unsigned long pteg, bit; unsigned long hpte_v, want_v; - want_v = hpte_encode_v(va, psize); + want_v = hpte_encode_v(va, psize, MMU_SEGSIZE_256M); spin_lock_irqsave(&ps3_bolttab_lock, flags); @@ -205,13 +207,13 @@ static long ps3_hpte_updatepp(unsigned long slot, unsigned long newpp, } static void ps3_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, - int psize) + int psize, int ssize) { panic("ps3_hpte_updateboltedpp() not implemented"); } static void ps3_hpte_invalidate(unsigned long slot, unsigned long va, - int psize, int local) + int psize, int ssize, int local) { unsigned long flags; unsigned long result; diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index ea327ca345c6..9a455d46379d 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -284,7 +284,7 @@ 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 psize, int ssize) { unsigned long lpar_rc; unsigned long flags; @@ -296,7 +296,7 @@ static long pSeries_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) | vflags | HPTE_V_VALID; + hpte_v = hpte_encode_v(va, psize, ssize) | vflags | HPTE_V_VALID; hpte_r = hpte_encode_r(pa, psize) | rflags; if (!(vflags & HPTE_V_BOLTED)) @@ -391,6 +391,22 @@ 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. @@ -400,18 +416,18 @@ static void pSeries_lpar_hptab_clear(void) static long pSeries_lpar_hpte_updatepp(unsigned long slot, unsigned long newpp, unsigned long va, - int psize, int local) + 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_v(va, psize); + want_v = hpte_encode_avpn(va, psize, ssize); DBG_LOW(" update: avpnv=%016lx, hash=%016lx, f=%x, psize: %d ... ", - want_v & HPTE_V_AVPN, slot, flags, psize); + want_v, slot, flags, psize); - lpar_rc = plpar_pte_protect(flags, slot, want_v & HPTE_V_AVPN); + lpar_rc = plpar_pte_protect(flags, slot, want_v); if (lpar_rc == H_NOT_FOUND) { DBG_LOW("not found !\n"); @@ -444,32 +460,25 @@ static unsigned long pSeries_lpar_hpte_getword0(unsigned long slot) return dword0; } -static long pSeries_lpar_hpte_find(unsigned long va, int psize) +static long pSeries_lpar_hpte_find(unsigned long va, int psize, int ssize) { unsigned long hash; - unsigned long i, j; + unsigned long i; long slot; unsigned long want_v, hpte_v; - hash = hpt_hash(va, mmu_psize_defs[psize].shift); - want_v = hpte_encode_v(va, psize); - - for (j = 0; j < 2; j++) { - slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; - for (i = 0; i < HPTES_PER_GROUP; i++) { - hpte_v = pSeries_lpar_hpte_getword0(slot); - - if (HPTE_V_COMPARE(hpte_v, want_v) - && (hpte_v & HPTE_V_VALID) - && (!!(hpte_v & HPTE_V_SECONDARY) == j)) { - /* HPTE matches */ - if (j) - slot = -slot; - return slot; - } - ++slot; - } - hash = ~hash; + hash = hpt_hash(va, mmu_psize_defs[psize].shift, ssize); + want_v = hpte_encode_avpn(va, psize, ssize); + + /* Bolted entries are always in the primary group */ + slot = (hash & htab_hash_mask) * HPTES_PER_GROUP; + for (i = 0; i < HPTES_PER_GROUP; i++) { + hpte_v = pSeries_lpar_hpte_getword0(slot); + + if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) + /* HPTE matches */ + return slot; + ++slot; } return -1; @@ -477,14 +486,14 @@ static long pSeries_lpar_hpte_find(unsigned long va, int psize) static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp, unsigned long ea, - int psize) + int psize, int ssize) { unsigned long lpar_rc, slot, vsid, va, flags; - vsid = get_kernel_vsid(ea); - va = (vsid << 28) | (ea & 0x0fffffff); + vsid = get_kernel_vsid(ea, ssize); + va = hpt_va(ea, vsid, ssize); - slot = pSeries_lpar_hpte_find(va, psize); + slot = pSeries_lpar_hpte_find(va, psize, ssize); BUG_ON(slot == -1); flags = newpp & 7; @@ -494,7 +503,7 @@ static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp, } static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va, - int psize, int local) + int psize, int ssize, int local) { unsigned long want_v; unsigned long lpar_rc; @@ -503,9 +512,8 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long va, DBG_LOW(" inval : slot=%lx, va=%016lx, psize: %d, local: %d", slot, va, psize, local); - want_v = hpte_encode_v(va, psize); - lpar_rc = plpar_pte_remove(H_AVPN, slot, want_v & HPTE_V_AVPN, - &dummy1, &dummy2); + want_v = hpte_encode_avpn(va, psize, ssize); + lpar_rc = plpar_pte_remove(H_AVPN, slot, want_v, &dummy1, &dummy2); if (lpar_rc == H_NOT_FOUND) return; @@ -533,18 +541,19 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local) unsigned long va; unsigned long hash, index, shift, hidx, slot; real_pte_t pte; - int psize; + int psize, ssize; if (lock_tlbie) spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags); psize = batch->psize; + ssize = batch->ssize; pix = 0; for (i = 0; i < number; i++) { va = batch->vaddr[i]; pte = batch->pte[i]; pte_iterate_hashed_subpages(pte, psize, va, index, shift) { - hash = hpt_hash(va, shift); + hash = hpt_hash(va, shift, ssize); hidx = __rpte_to_hidx(pte, index); if (hidx & _PTEIDX_SECONDARY) hash = ~hash; @@ -552,11 +561,11 @@ static void pSeries_lpar_flush_hash_range(unsigned long number, int local) slot += hidx & _PTEIDX_GROUP_IX; if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) { pSeries_lpar_hpte_invalidate(slot, va, psize, - local); + ssize, local); } else { param[pix] = HBR_REQUEST | HBR_AVPN | slot; - param[pix+1] = hpte_encode_v(va, psize) & - HPTE_V_AVPN; + param[pix+1] = hpte_encode_avpn(va, psize, + ssize); pix += 2; if (pix == 8) { rc = plpar_hcall9(H_BULK_REMOVE, param, diff --git a/include/asm-powerpc/cputable.h b/include/asm-powerpc/cputable.h index d913f460e710..ae093ef68363 100644 --- a/include/asm-powerpc/cputable.h +++ b/include/asm-powerpc/cputable.h @@ -164,6 +164,7 @@ extern void do_feature_fixups(unsigned long value, void *fixup_start, #define CPU_FTR_CELL_TB_BUG LONG_ASM_CONST(0x0000800000000000) #define CPU_FTR_SPURR LONG_ASM_CONST(0x0001000000000000) #define CPU_FTR_DSCR LONG_ASM_CONST(0x0002000000000000) +#define CPU_FTR_1T_SEGMENT LONG_ASM_CONST(0x0004000000000000) #ifndef __ASSEMBLY__ @@ -374,7 +375,7 @@ extern void do_feature_fixups(unsigned long value, void *fixup_start, #define CPU_FTRS_POSSIBLE \ (CPU_FTRS_POWER3 | CPU_FTRS_RS64 | CPU_FTRS_POWER4 | \ CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | CPU_FTRS_POWER6 | \ - CPU_FTRS_CELL | CPU_FTRS_PA6T) + CPU_FTRS_CELL | CPU_FTRS_PA6T | CPU_FTR_1T_SEGMENT) #else enum { CPU_FTRS_POSSIBLE = diff --git a/include/asm-powerpc/machdep.h b/include/asm-powerpc/machdep.h index cc7c17f16a9a..6968f4300dca 100644 --- a/include/asm-powerpc/machdep.h +++ b/include/asm-powerpc/machdep.h @@ -51,22 +51,22 @@ struct machdep_calls { #ifdef CONFIG_PPC64 void (*hpte_invalidate)(unsigned long slot, unsigned long va, - int psize, + int psize, int ssize, int local); long (*hpte_updatepp)(unsigned long slot, unsigned long newpp, unsigned long va, - int pize, + int psize, int ssize, int local); void (*hpte_updateboltedpp)(unsigned long newpp, unsigned long ea, - int psize); + int psize, int ssize); long (*hpte_insert)(unsigned long hpte_group, unsigned long va, unsigned long prpn, unsigned long rflags, unsigned long vflags, - int psize); + int psize, int ssize); long (*hpte_remove)(unsigned long hpte_group); void (*flush_hash_range)(unsigned long number, int local); diff --git a/include/asm-powerpc/mmu-hash64.h b/include/asm-powerpc/mmu-hash64.h index b22b0d20e157..82328dec2b52 100644 --- a/include/asm-powerpc/mmu-hash64.h +++ b/include/asm-powerpc/mmu-hash64.h @@ -47,6 +47,8 @@ extern char initial_stab[]; /* Bits in the SLB VSID word */ #define SLB_VSID_SHIFT 12 +#define SLB_VSID_SHIFT_1T 24 +#define SLB_VSID_SSIZE_SHIFT 62 #define SLB_VSID_B ASM_CONST(0xc000000000000000) #define SLB_VSID_B_256M ASM_CONST(0x0000000000000000) #define SLB_VSID_B_1T ASM_CONST(0x4000000000000000) @@ -66,6 +68,7 @@ extern char initial_stab[]; #define SLB_VSID_USER (SLB_VSID_KP|SLB_VSID_KS|SLB_VSID_C) #define SLBIE_C (0x08000000) +#define SLBIE_SSIZE_SHIFT 25 /* * Hash table @@ -77,7 +80,7 @@ extern char initial_stab[]; #define HPTE_V_AVPN_SHIFT 7 #define HPTE_V_AVPN ASM_CONST(0x3fffffffffffff80) #define HPTE_V_AVPN_VAL(x) (((x) & HPTE_V_AVPN) >> HPTE_V_AVPN_SHIFT) -#define HPTE_V_COMPARE(x,y) (!(((x) ^ (y)) & HPTE_V_AVPN)) +#define HPTE_V_COMPARE(x,y) (!(((x) ^ (y)) & 0xffffffffffffff80)) #define HPTE_V_BOLTED ASM_CONST(0x0000000000000010) #define HPTE_V_LOCK ASM_CONST(0x0000000000000008) #define HPTE_V_LARGE ASM_CONST(0x0000000000000004) @@ -164,16 +167,19 @@ struct mmu_psize_def #define MMU_SEGSIZE_256M 0 #define MMU_SEGSIZE_1T 1 + #ifndef __ASSEMBLY__ /* - * The current system page sizes + * The current system page and segment sizes */ extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; extern int mmu_linear_psize; extern int mmu_virtual_psize; extern int mmu_vmalloc_psize; extern int mmu_io_psize; +extern int mmu_kernel_ssize; +extern int mmu_highuser_ssize; /* * If the processor supports 64k normal pages but not 64k cache @@ -195,13 +201,15 @@ extern int mmu_huge_psize; * 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) +static inline unsigned long hpte_encode_v(unsigned long va, int psize, + int ssize) { - unsigned long v = + unsigned long v; v = (va >> 23) & ~(mmu_psize_defs[psize].avpnm); v <<= HPTE_V_AVPN_SHIFT; if (psize != MMU_PAGE_4K) v |= HPTE_V_LARGE; + v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT; return v; } @@ -226,20 +234,40 @@ static inline unsigned long hpte_encode_r(unsigned long pa, int psize) } /* - * This hashes a virtual address for a 256Mb segment only for now + * Build a VA given VSID, EA and segment size */ +static inline unsigned long hpt_va(unsigned long ea, unsigned long vsid, + int ssize) +{ + if (ssize == MMU_SEGSIZE_256M) + return (vsid << 28) | (ea & 0xfffffffUL); + return (vsid << 40) | (ea & 0xffffffffffUL); +} -static inline unsigned long hpt_hash(unsigned long va, unsigned int shift) +/* + * This hashes a virtual address + */ + +static inline unsigned long hpt_hash(unsigned long va, unsigned int shift, + int ssize) { - return ((va >> 28) & 0x7fffffffffUL) ^ ((va & 0x0fffffffUL) >> shift); + unsigned long hash, vsid; + + if (ssize == MMU_SEGSIZE_256M) { + hash = (va >> 28) ^ ((va & 0x0fffffffUL) >> shift); + } else { + vsid = va >> 40; + hash = vsid ^ (vsid << 25) ^ ((va & 0xffffffffffUL) >> shift); + } + return hash & 0x7fffffffffUL; } extern int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, pte_t *ptep, unsigned long trap, - unsigned int local); + unsigned int local, int ssize); extern int __hash_page_64K(unsigned long ea, unsigned long access, unsigned long vsid, pte_t *ptep, unsigned long trap, - unsigned int local); + unsigned int local, int ssize); struct mm_struct; extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap); extern int hash_huge_page(struct mm_struct *mm, unsigned long access, @@ -248,7 +276,7 @@ extern int hash_huge_page(struct mm_struct *mm, unsigned long access, extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend, unsigned long pstart, unsigned long mode, - int psize); + int psize, int ssize); extern void htab_initialize(void); extern void htab_initialize_secondary(void); @@ -317,12 +345,17 @@ extern void slb_vmalloc_update(void); * which are used by the iSeries firmware. */ -#define VSID_MULTIPLIER ASM_CONST(200730139) /* 28-bit prime */ -#define VSID_BITS 36 -#define VSID_MODULUS ((1UL<= \ @@ -355,7 +388,7 @@ extern void slb_vmalloc_update(void); * doesn't, the answer is the low 36 bits of r3+1. So in all \ * cases the answer is the low 36 bits of (r3 + ((r3+1) >> 36))*/\ addi rx,rt,1; \ - srdi rx,rx,VSID_BITS; /* extract 2^36 bit */ \ + srdi rx,rx,VSID_BITS_##size; /* extract 2^VSID_BITS bit */ \ add rt,rt,rx @@ -377,37 +410,60 @@ typedef struct { } mm_context_t; -static inline unsigned long vsid_scramble(unsigned long protovsid) -{ #if 0 - /* The code below is equivalent to this function for arguments - * < 2^VSID_BITS, which is all this should ever be called - * with. However gcc is not clever enough to compute the - * modulus (2^n-1) without a second multiply. */ - return ((protovsid * VSID_MULTIPLIER) % VSID_MODULUS); -#else /* 1 */ - unsigned long x; +/* + * The code below is equivalent to this function for arguments + * < 2^VSID_BITS, which is all this should ever be called + * with. However gcc is not clever enough to compute the + * modulus (2^n-1) without a second multiply. + */ +#define vsid_scrample(protovsid, size) \ + ((((protovsid) * VSID_MULTIPLIER_##size) % VSID_MODULUS_##size)) - x = protovsid * VSID_MULTIPLIER; - x = (x >> VSID_BITS) + (x & VSID_MODULUS); - return (x + ((x+1) >> VSID_BITS)) & VSID_MODULUS; +#else /* 1 */ +#define vsid_scramble(protovsid, size) \ + ({ \ + unsigned long x; \ + x = (protovsid) * VSID_MULTIPLIER_##size; \ + x = (x >> VSID_BITS_##size) + (x & VSID_MODULUS_##size); \ + (x + ((x+1) >> VSID_BITS_##size)) & VSID_MODULUS_##size; \ + }) #endif /* 1 */ -} /* This is only valid for addresses >= KERNELBASE */ -static inline unsigned long get_kernel_vsid(unsigned long ea) +static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize) { - return vsid_scramble(ea >> SID_SHIFT); + if (ssize == MMU_SEGSIZE_256M) + return vsid_scramble(ea >> SID_SHIFT, 256M); + return vsid_scramble(ea >> SID_SHIFT_1T, 1T); } -/* This is only valid for user addresses (which are below 2^41) */ -static inline unsigned long get_vsid(unsigned long context, unsigned long ea) +/* Returns the segment size indicator for a user address */ +static inline int user_segment_size(unsigned long addr) { - return vsid_scramble((context << USER_ESID_BITS) - | (ea >> SID_SHIFT)); + /* Use 1T segments if possible for addresses >= 1T */ + if (addr >= (1UL << SID_SHIFT_1T)) + return mmu_highuser_ssize; + return MMU_SEGSIZE_256M; } -#define VSID_SCRAMBLE(pvsid) (((pvsid) * VSID_MULTIPLIER) % VSID_MODULUS) +/* This is only valid for user addresses (which are below 2^44) */ +static inline unsigned long get_vsid(unsigned long context, unsigned long ea, + int ssize) +{ + if (ssize == MMU_SEGSIZE_256M) + return vsid_scramble((context << USER_ESID_BITS) + | (ea >> SID_SHIFT), 256M); + return vsid_scramble((context << USER_ESID_BITS_1T) + | (ea >> SID_SHIFT_1T), 1T); +} + +/* + * This is only used on legacy iSeries in lparmap.c, + * hence the 256MB segment assumption. + */ +#define VSID_SCRAMBLE(pvsid) (((pvsid) * VSID_MULTIPLIER_256M) % \ + VSID_MODULUS_256M) #define KERNEL_VSID(ea) VSID_SCRAMBLE(GET_ESID(ea)) /* Physical address used by some IO functions */ diff --git a/include/asm-powerpc/page_64.h b/include/asm-powerpc/page_64.h index 56a2df0f6836..4ee82c61e4d7 100644 --- a/include/asm-powerpc/page_64.h +++ b/include/asm-powerpc/page_64.h @@ -26,12 +26,18 @@ */ #define PAGE_FACTOR (PAGE_SHIFT - HW_PAGE_SHIFT) -/* Segment size */ +/* Segment size; normal 256M segments */ #define SID_SHIFT 28 #define SID_MASK ASM_CONST(0xfffffffff) #define ESID_MASK 0xfffffffff0000000UL #define GET_ESID(x) (((x) >> SID_SHIFT) & SID_MASK) +/* 1T segments */ +#define SID_SHIFT_1T 40 +#define SID_MASK_1T 0xffffffUL +#define ESID_MASK_1T 0xffffff0000000000UL +#define GET_ESID_1T(x) (((x) >> SID_SHIFT_1T) & SID_MASK_1T) + #ifndef __ASSEMBLY__ #include diff --git a/include/asm-powerpc/tlbflush.h b/include/asm-powerpc/tlbflush.h index 99a0439baa50..a022f806bb21 100644 --- a/include/asm-powerpc/tlbflush.h +++ b/include/asm-powerpc/tlbflush.h @@ -97,6 +97,7 @@ struct ppc64_tlb_batch { real_pte_t pte[PPC64_TLB_BATCH_NR]; unsigned long vaddr[PPC64_TLB_BATCH_NR]; unsigned int psize; + int ssize; }; DECLARE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch); @@ -127,7 +128,7 @@ static inline void arch_leave_lazy_mmu_mode(void) extern void flush_hash_page(unsigned long va, real_pte_t pte, int psize, - int local); + int ssize, int local); extern void flush_hash_range(unsigned long number, int local); -- cgit v1.2.3