* [PATCH 18/20] powerpc: Add TLB management code for 64-bit Book3E (v2)
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
This adds the TLB miss handler assembly, the low level TLB flush routines
along with the necessary hook for dealing with our virtual page tables
or indirect TLB entries that need to be flushes when PTE pages are freed.
There is currently no support for hugetlbfs
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
v2. Don't break non-Book3E nohash platforms
arch/powerpc/include/asm/mmu-40x.h | 3
arch/powerpc/include/asm/mmu-44x.h | 6
arch/powerpc/include/asm/mmu-8xx.h | 3
arch/powerpc/include/asm/mmu-hash32.h | 6
arch/powerpc/include/asm/mmu_context.h | 8
arch/powerpc/kernel/setup_64.c | 4
arch/powerpc/mm/mmu_decl.h | 14
arch/powerpc/mm/tlb_low_64e.S | 734 +++++++++++++++++++++++++++++++++
arch/powerpc/mm/tlb_nohash.c | 203 ++++++++-
arch/powerpc/mm/tlb_nohash_low.S | 79 +++
10 files changed, 1055 insertions(+), 5 deletions(-)
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-work/arch/powerpc/mm/tlb_low_64e.S 2009-07-24 18:15:31.000000000 +1000
@@ -0,0 +1,734 @@
+/*
+ * Low leve TLB miss handlers for Book3E
+ *
+ * Copyright (C) 2008-2009
+ * Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
+ *
+ * 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 <asm/processor.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/cputable.h>
+#include <asm/pgtable.h>
+#include <asm/reg.h>
+#include <asm/exception-64e.h>
+#include <asm/ppc-opcode.h>
+
+#ifdef CONFIG_PPC_64K_PAGES
+#define VPTE_PMD_SHIFT (PTE_INDEX_SIZE+1)
+#else
+#define VPTE_PMD_SHIFT (PTE_INDEX_SIZE)
+#endif
+#define VPTE_PUD_SHIFT (VPTE_PMD_SHIFT + PMD_INDEX_SIZE)
+#define VPTE_PGD_SHIFT (VPTE_PUD_SHIFT + PUD_INDEX_SIZE)
+#define VPTE_INDEX_SIZE (VPTE_PGD_SHIFT + PGD_INDEX_SIZE)
+
+
+/**********************************************************************
+ * *
+ * TLB miss handling for Book3E with TLB reservation and HES support *
+ * *
+ **********************************************************************/
+
+
+/* Data TLB miss */
+ START_EXCEPTION(data_tlb_miss)
+ TLB_MISS_PROLOG
+
+ /* Now we handle the fault proper. We only save DEAR in normal
+ * fault case since that's the only interesting values here.
+ * We could probably also optimize by not saving SRR0/1 in the
+ * linear mapping case but I'll leave that for later
+ */
+ mfspr r14,SPRN_ESR
+ mfspr r16,SPRN_DEAR /* get faulting address */
+ srdi r15,r16,60 /* get region */
+ cmpldi cr0,r15,0xc /* linear mapping ? */
+ TLB_MISS_STATS_SAVE_INFO
+ beq tlb_load_linear /* yes -> go to linear map load */
+
+ /* The page tables are mapped virtually linear. At this point, though,
+ * we don't know whether we are trying to fault in a first level
+ * virtual address or a virtual page table address. We can get that
+ * from bit 0x1 of the region ID which we have set for a page table
+ */
+ andi. r10,r15,0x1
+ bne- virt_page_table_tlb_miss
+
+ std r14,EX_TLB_ESR(r12); /* save ESR */
+ std r16,EX_TLB_DEAR(r12); /* save DEAR */
+
+ /* We need _PAGE_PRESENT and _PAGE_ACCESSED set */
+ li r11,_PAGE_PRESENT
+ oris r11,r11,_PAGE_ACCESSED@h
+
+ /* We do the user/kernel test for the PID here along with the RW test
+ */
+ cmpldi cr0,r15,0 /* Check for user region */
+
+ /* We pre-test some combination of permissions to avoid double
+ * faults:
+ *
+ * We move the ESR:ST bit into the position of _PAGE_BAP_SW in the PTE
+ * ESR_ST is 0x00800000
+ * _PAGE_BAP_SW is 0x00000010
+ * So the shift is >> 19. This tests for supervisor writeability.
+ * If the page happens to be supervisor writeable and not user
+ * writeable, we will take a new fault later, but that should be
+ * a rare enough case.
+ *
+ * We also move ESR_ST in _PAGE_DIRTY position
+ * _PAGE_DIRTY is 0x00001000 so the shift is >> 11
+ *
+ * MAS1 is preset for all we need except for TID that needs to
+ * be cleared for kernel translations
+ */
+ rlwimi r11,r14,32-19,27,27
+ rlwimi r11,r14,32-16,19,19
+ beq normal_tlb_miss
+ /* XXX replace the RMW cycles with immediate loads + writes */
+1: mfspr r10,SPRN_MAS1
+ cmpldi cr0,r15,8 /* Check for vmalloc region */
+ rlwinm r10,r10,0,16,1 /* Clear TID */
+ mtspr SPRN_MAS1,r10
+ beq+ normal_tlb_miss
+
+ /* We got a crappy address, just fault with whatever DEAR and ESR
+ * are here
+ */
+ TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT)
+ TLB_MISS_EPILOG_ERROR
+ b exc_data_storage_book3e
+
+/* Instruction TLB miss */
+ START_EXCEPTION(instruction_tlb_miss)
+ TLB_MISS_PROLOG
+
+ /* If we take a recursive fault, the second level handler may need
+ * to know whether we are handling a data or instruction fault in
+ * order to get to the right store fault handler. We provide that
+ * info by writing a crazy value in ESR in our exception frame
+ */
+ li r14,-1 /* store to exception frame is done later */
+
+ /* Now we handle the fault proper. We only save DEAR in the non
+ * linear mapping case since we know the linear mapping case will
+ * not re-enter. We could indeed optimize and also not save SRR0/1
+ * in the linear mapping case but I'll leave that for later
+ *
+ * Faulting address is SRR0 which is already in r16
+ */
+ srdi r15,r16,60 /* get region */
+ cmpldi cr0,r15,0xc /* linear mapping ? */
+ TLB_MISS_STATS_SAVE_INFO
+ beq tlb_load_linear /* yes -> go to linear map load */
+
+ /* We do the user/kernel test for the PID here along with the RW test
+ */
+ li r11,_PAGE_PRESENT|_PAGE_HWEXEC /* Base perm */
+ oris r11,r11,_PAGE_ACCESSED@h
+
+ cmpldi cr0,r15,0 /* Check for user region */
+ std r14,EX_TLB_ESR(r12) /* write crazy -1 to frame */
+ beq normal_tlb_miss
+ /* XXX replace the RMW cycles with immediate loads + writes */
+1: mfspr r10,SPRN_MAS1
+ cmpldi cr0,r15,8 /* Check for vmalloc region */
+ rlwinm r10,r10,0,16,1 /* Clear TID */
+ mtspr SPRN_MAS1,r10
+ beq+ normal_tlb_miss
+
+ /* We got a crappy address, just fault */
+ TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT)
+ TLB_MISS_EPILOG_ERROR
+ b exc_instruction_storage_book3e
+
+/*
+ * This is the guts of the first-level TLB miss handler for direct
+ * misses. We are entered with:
+ *
+ * r16 = faulting address
+ * r15 = region ID
+ * r14 = crap (free to use)
+ * r13 = PACA
+ * r12 = TLB exception frame in PACA
+ * r11 = PTE permission mask
+ * r10 = crap (free to use)
+ */
+normal_tlb_miss:
+ /* So we first construct the page table address. We do that by
+ * shifting the bottom of the address (not the region ID) by
+ * PAGE_SHIFT-3, clearing the bottom 3 bits (get a PTE ptr) and
+ * or'ing the fourth high bit.
+ *
+ * NOTE: For 64K pages, we do things slightly differently in
+ * order to handle the weird page table format used by linux
+ */
+ ori r10,r15,0x1
+#ifdef CONFIG_PPC_64K_PAGES
+ /* For the top bits, 16 bytes per PTE */
+ rldicl r14,r16,64-(PAGE_SHIFT-4),PAGE_SHIFT-4+4
+ /* Now create the bottom bits as 0 in position 0x8000 and
+ * the rest calculated for 8 bytes per PTE
+ */
+ rldicl r15,r16,64-(PAGE_SHIFT-3),64-15
+ /* Insert the bottom bits in */
+ rlwimi r14,r15,0,16,31
+#else
+ rldicl r14,r16,64-(PAGE_SHIFT-3),PAGE_SHIFT-3+4
+#endif
+ sldi r15,r10,60
+ clrrdi r14,r14,3
+ or r10,r15,r14
+
+ /* Set the TLB reservation and seach for existing entry. Then load
+ * the entry.
+ */
+ PPC_TLBSRX_DOT(0,r16)
+ ld r14,0(r10)
+ beq normal_tlb_miss_done
+
+finish_normal_tlb_miss:
+ /* Check if required permissions are met */
+ andc. r15,r11,r14
+ bne- normal_tlb_miss_access_fault
+
+ /* Now we build the MAS:
+ *
+ * MAS 0 : Fully setup with defaults in MAS4 and TLBnCFG
+ * MAS 1 : Almost fully setup
+ * - PID already updated by caller if necessary
+ * - TSIZE need change if !base page size, not
+ * yet implemented for now
+ * MAS 2 : Defaults not useful, need to be redone
+ * MAS 3+7 : Needs to be done
+ *
+ * TODO: mix up code below for better scheduling
+ */
+ clrrdi r11,r16,12 /* Clear low crap in EA */
+ rlwimi r11,r14,32-19,27,31 /* Insert WIMGE */
+ mtspr SPRN_MAS2,r11
+
+ /* Check page size, if not standard, update MAS1 */
+ rldicl r11,r14,64-8,64-8
+#ifdef CONFIG_PPC_64K_PAGES
+ cmpldi cr0,r11,BOOK3E_PAGESZ_64K
+#else
+ cmpldi cr0,r11,BOOK3E_PAGESZ_4K
+#endif
+ beq- 1f
+ mfspr r11,SPRN_MAS1
+ rlwimi r11,r14,31,21,24
+ rlwinm r11,r11,0,21,19
+ mtspr SPRN_MAS1,r11
+1:
+ /* Move RPN in position */
+ rldicr r11,r14,64-(PTE_RPN_SHIFT-PAGE_SHIFT),63-PAGE_SHIFT
+ clrldi r15,r11,12 /* Clear crap at the top */
+ rlwimi r15,r14,32-8,22,25 /* Move in U bits */
+ rlwimi r15,r14,32-2,26,31 /* Move in BAP bits */
+
+ /* Mask out SW and UW if !DIRTY (XXX optimize this !) */
+ andi. r11,r14,_PAGE_DIRTY
+ bne 1f
+ li r11,MAS3_SW|MAS3_UW
+ andc r15,r15,r11
+1: mtspr SPRN_MAS7_MAS3,r15
+
+ tlbwe
+
+normal_tlb_miss_done:
+ /* We don't bother with restoring DEAR or ESR since we know we are
+ * level 0 and just going back to userland. They are only needed
+ * if you are going to take an access fault
+ */
+ TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK)
+ TLB_MISS_EPILOG_SUCCESS
+ rfi
+
+normal_tlb_miss_access_fault:
+ /* We need to check if it was an instruction miss */
+ andi. r10,r11,_PAGE_HWEXEC
+ bne 1f
+ ld r14,EX_TLB_DEAR(r12)
+ ld r15,EX_TLB_ESR(r12)
+ mtspr SPRN_DEAR,r14
+ mtspr SPRN_ESR,r15
+ TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT)
+ TLB_MISS_EPILOG_ERROR
+ b exc_data_storage_book3e
+1: TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT)
+ TLB_MISS_EPILOG_ERROR
+ b exc_instruction_storage_book3e
+
+
+/*
+ * This is the guts of the second-level TLB miss handler for direct
+ * misses. We are entered with:
+ *
+ * r16 = virtual page table faulting address
+ * r15 = region (top 4 bits of address)
+ * r14 = crap (free to use)
+ * r13 = PACA
+ * r12 = TLB exception frame in PACA
+ * r11 = crap (free to use)
+ * r10 = crap (free to use)
+ *
+ * Note that this should only ever be called as a second level handler
+ * with the current scheme when using SW load.
+ * That means we can always get the original fault DEAR at
+ * EX_TLB_DEAR-EX_TLB_SIZE(r12)
+ *
+ * It can be re-entered by the linear mapping miss handler. However, to
+ * avoid too much complication, it will restart the whole fault at level
+ * 0 so we don't care too much about clobbers
+ *
+ * XXX That code was written back when we couldn't clobber r14. We can now,
+ * so we could probably optimize things a bit
+ */
+virt_page_table_tlb_miss:
+ /* Are we hitting a kernel page table ? */
+ andi. r10,r15,0x8
+
+ /* The cool thing now is that r10 contains 0 for user and 8 for kernel,
+ * and we happen to have the swapper_pg_dir at offset 8 from the user
+ * pgdir in the PACA :-).
+ */
+ add r11,r10,r13
+
+ /* If kernel, we need to clear MAS1 TID */
+ beq 1f
+ /* XXX replace the RMW cycles with immediate loads + writes */
+ mfspr r10,SPRN_MAS1
+ rlwinm r10,r10,0,16,1 /* Clear TID */
+ mtspr SPRN_MAS1,r10
+1:
+ /* Search if we already have a TLB entry for that virtual address, and
+ * if we do, bail out.
+ */
+ PPC_TLBSRX_DOT(0,r16)
+ beq virt_page_table_tlb_miss_done
+
+ /* Now, we need to walk the page tables. First check if we are in
+ * range.
+ */
+ rldicl. r10,r16,64-(VPTE_INDEX_SIZE+3),VPTE_INDEX_SIZE+3+4
+ bne- virt_page_table_tlb_miss_fault
+
+ /* Get the PGD pointer */
+ ld r15,PACAPGD(r11)
+ cmpldi cr0,r15,0
+ beq- virt_page_table_tlb_miss_fault
+
+ /* Get to PGD entry */
+ rldicl r11,r16,64-VPTE_PGD_SHIFT,64-PGD_INDEX_SIZE-3
+ clrrdi r10,r11,3
+ ldx r15,r10,r15
+ cmpldi cr0,r15,0
+ beq virt_page_table_tlb_miss_fault
+
+#ifndef CONFIG_PPC_64K_PAGES
+ /* Get to PUD entry */
+ rldicl r11,r16,64-VPTE_PUD_SHIFT,64-PUD_INDEX_SIZE-3
+ clrrdi r10,r11,3
+ ldx r15,r10,r15
+ cmpldi cr0,r15,0
+ beq virt_page_table_tlb_miss_fault
+#endif /* CONFIG_PPC_64K_PAGES */
+
+ /* Get to PMD entry */
+ rldicl r11,r16,64-VPTE_PMD_SHIFT,64-PMD_INDEX_SIZE-3
+ clrrdi r10,r11,3
+ ldx r15,r10,r15
+ cmpldi cr0,r15,0
+ beq virt_page_table_tlb_miss_fault
+
+ /* Ok, we're all right, we can now create a kernel translation for
+ * a 4K or 64K page from r16 -> r15.
+ */
+ /* Now we build the MAS:
+ *
+ * MAS 0 : Fully setup with defaults in MAS4 and TLBnCFG
+ * MAS 1 : Almost fully setup
+ * - PID already updated by caller if necessary
+ * - TSIZE for now is base page size always
+ * MAS 2 : Use defaults
+ * MAS 3+7 : Needs to be done
+ *
+ * So we only do MAS 2 and 3 for now...
+ */
+ clrldi r11,r15,4 /* remove region ID from RPN */
+ ori r10,r11,1 /* Or-in SR */
+ mtspr SPRN_MAS7_MAS3,r10
+
+ tlbwe
+
+virt_page_table_tlb_miss_done:
+
+ /* We have overriden MAS2:EPN but currently our primary TLB miss
+ * handler will always restore it so that should not be an issue,
+ * if we ever optimize the primary handler to not write MAS2 on
+ * some cases, we'll have to restore MAS2:EPN here based on the
+ * original fault's DEAR. If we do that we have to modify the
+ * ITLB miss handler to also store SRR0 in the exception frame
+ * as DEAR.
+ *
+ * However, one nasty thing we did is we cleared the reservation
+ * (well, potentially we did). We do a trick here thus if we
+ * are not a level 0 exception (we interrupted the TLB miss) we
+ * offset the return address by -4 in order to replay the tlbsrx
+ * instruction there
+ */
+ subf r10,r13,r12
+ cmpldi cr0,r10,PACA_EXTLB+EX_TLB_SIZE
+ bne- 1f
+ ld r11,PACA_EXTLB+EX_TLB_SIZE+EX_TLB_SRR0(r13)
+ addi r10,r11,-4
+ std r10,PACA_EXTLB+EX_TLB_SIZE+EX_TLB_SRR0(r13)
+1:
+ /* Return to caller, normal case */
+ TLB_MISS_STATS_X(MMSTAT_TLB_MISS_PT_OK);
+ TLB_MISS_EPILOG_SUCCESS
+ rfi
+
+virt_page_table_tlb_miss_fault:
+ /* If we fault here, things are a little bit tricky. We need to call
+ * either data or instruction store fault, and we need to retreive
+ * the original fault address and ESR (for data).
+ *
+ * The thing is, we know that in normal circumstances, this is
+ * always called as a second level tlb miss for SW load or as a first
+ * level TLB miss for HW load, so we should be able to peek at the
+ * relevant informations in the first exception frame in the PACA.
+ *
+ * However, we do need to double check that, because we may just hit
+ * a stray kernel pointer or a userland attack trying to hit those
+ * areas. If that is the case, we do a data fault. (We can't get here
+ * from an instruction tlb miss anyway).
+ *
+ * Note also that when going to a fault, we must unwind the previous
+ * level as well. Since we are doing that, we don't need to clear or
+ * restore the TLB reservation neither.
+ */
+ subf r10,r13,r12
+ cmpldi cr0,r10,PACA_EXTLB+EX_TLB_SIZE
+ bne- virt_page_table_tlb_miss_whacko_fault
+
+ /* We dig the original DEAR and ESR from slot 0 */
+ ld r15,EX_TLB_DEAR+PACA_EXTLB(r13)
+ ld r16,EX_TLB_ESR+PACA_EXTLB(r13)
+
+ /* We check for the "special" ESR value for instruction faults */
+ cmpdi cr0,r16,-1
+ beq 1f
+ mtspr SPRN_DEAR,r15
+ mtspr SPRN_ESR,r16
+ TLB_MISS_STATS_D(MMSTAT_TLB_MISS_PT_FAULT);
+ TLB_MISS_EPILOG_ERROR
+ b exc_data_storage_book3e
+1: TLB_MISS_STATS_I(MMSTAT_TLB_MISS_PT_FAULT);
+ TLB_MISS_EPILOG_ERROR
+ b exc_instruction_storage_book3e
+
+virt_page_table_tlb_miss_whacko_fault:
+ /* The linear fault will restart everything so ESR and DEAR will
+ * not have been clobbered, let's just fault with what we have
+ */
+ TLB_MISS_STATS_X(MMSTAT_TLB_MISS_PT_FAULT);
+ TLB_MISS_EPILOG_ERROR
+ b exc_data_storage_book3e
+
+
+/**************************************************************
+ * *
+ * TLB miss handling for Book3E with hw page table support *
+ * *
+ **************************************************************/
+
+
+/* Data TLB miss */
+ START_EXCEPTION(data_tlb_miss_htw)
+ TLB_MISS_PROLOG
+
+ /* Now we handle the fault proper. We only save DEAR in normal
+ * fault case since that's the only interesting values here.
+ * We could probably also optimize by not saving SRR0/1 in the
+ * linear mapping case but I'll leave that for later
+ */
+ mfspr r14,SPRN_ESR
+ mfspr r16,SPRN_DEAR /* get faulting address */
+ srdi r11,r16,60 /* get region */
+ cmpldi cr0,r11,0xc /* linear mapping ? */
+ TLB_MISS_STATS_SAVE_INFO
+ beq tlb_load_linear /* yes -> go to linear map load */
+
+ /* We do the user/kernel test for the PID here along with the RW test
+ */
+ cmpldi cr0,r11,0 /* Check for user region */
+ ld r15,PACAPGD(r13) /* Load user pgdir */
+ beq htw_tlb_miss
+
+ /* XXX replace the RMW cycles with immediate loads + writes */
+1: mfspr r10,SPRN_MAS1
+ cmpldi cr0,r11,8 /* Check for vmalloc region */
+ rlwinm r10,r10,0,16,1 /* Clear TID */
+ mtspr SPRN_MAS1,r10
+ ld r15,PACA_KERNELPGD(r13) /* Load kernel pgdir */
+ beq+ htw_tlb_miss
+
+ /* We got a crappy address, just fault with whatever DEAR and ESR
+ * are here
+ */
+ TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT)
+ TLB_MISS_EPILOG_ERROR
+ b exc_data_storage_book3e
+
+/* Instruction TLB miss */
+ START_EXCEPTION(instruction_tlb_miss_htw)
+ TLB_MISS_PROLOG
+
+ /* If we take a recursive fault, the second level handler may need
+ * to know whether we are handling a data or instruction fault in
+ * order to get to the right store fault handler. We provide that
+ * info by keeping a crazy value for ESR in r14
+ */
+ li r14,-1 /* store to exception frame is done later */
+
+ /* Now we handle the fault proper. We only save DEAR in the non
+ * linear mapping case since we know the linear mapping case will
+ * not re-enter. We could indeed optimize and also not save SRR0/1
+ * in the linear mapping case but I'll leave that for later
+ *
+ * Faulting address is SRR0 which is already in r16
+ */
+ srdi r11,r16,60 /* get region */
+ cmpldi cr0,r11,0xc /* linear mapping ? */
+ TLB_MISS_STATS_SAVE_INFO
+ beq tlb_load_linear /* yes -> go to linear map load */
+
+ /* We do the user/kernel test for the PID here along with the RW test
+ */
+ cmpldi cr0,r11,0 /* Check for user region */
+ ld r15,PACAPGD(r13) /* Load user pgdir */
+ beq htw_tlb_miss
+
+ /* XXX replace the RMW cycles with immediate loads + writes */
+1: mfspr r10,SPRN_MAS1
+ cmpldi cr0,r11,8 /* Check for vmalloc region */
+ rlwinm r10,r10,0,16,1 /* Clear TID */
+ mtspr SPRN_MAS1,r10
+ ld r15,PACA_KERNELPGD(r13) /* Load kernel pgdir */
+ beq+ htw_tlb_miss
+
+ /* We got a crappy address, just fault */
+ TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT)
+ TLB_MISS_EPILOG_ERROR
+ b exc_instruction_storage_book3e
+
+
+/*
+ * This is the guts of the second-level TLB miss handler for direct
+ * misses. We are entered with:
+ *
+ * r16 = virtual page table faulting address
+ * r15 = PGD pointer
+ * r14 = ESR
+ * r13 = PACA
+ * r12 = TLB exception frame in PACA
+ * r11 = crap (free to use)
+ * r10 = crap (free to use)
+ *
+ * It can be re-entered by the linear mapping miss handler. However, to
+ * avoid too much complication, it will save/restore things for us
+ */
+htw_tlb_miss:
+ /* Search if we already have a TLB entry for that virtual address, and
+ * if we do, bail out.
+ *
+ * MAS1:IND should be already set based on MAS4
+ */
+ PPC_TLBSRX_DOT(0,r16)
+ beq htw_tlb_miss_done
+
+ /* Now, we need to walk the page tables. First check if we are in
+ * range.
+ */
+ rldicl. r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4
+ bne- htw_tlb_miss_fault
+
+ /* Get the PGD pointer */
+ cmpldi cr0,r15,0
+ beq- htw_tlb_miss_fault
+
+ /* Get to PGD entry */
+ rldicl r11,r16,64-(PGDIR_SHIFT-3),64-PGD_INDEX_SIZE-3
+ clrrdi r10,r11,3
+ ldx r15,r10,r15
+ cmpldi cr0,r15,0
+ beq htw_tlb_miss_fault
+
+#ifndef CONFIG_PPC_64K_PAGES
+ /* Get to PUD entry */
+ rldicl r11,r16,64-(PUD_SHIFT-3),64-PUD_INDEX_SIZE-3
+ clrrdi r10,r11,3
+ ldx r15,r10,r15
+ cmpldi cr0,r15,0
+ beq htw_tlb_miss_fault
+#endif /* CONFIG_PPC_64K_PAGES */
+
+ /* Get to PMD entry */
+ rldicl r11,r16,64-(PMD_SHIFT-3),64-PMD_INDEX_SIZE-3
+ clrrdi r10,r11,3
+ ldx r15,r10,r15
+ cmpldi cr0,r15,0
+ beq htw_tlb_miss_fault
+
+ /* Ok, we're all right, we can now create an indirect entry for
+ * a 1M or 256M page.
+ *
+ * The last trick is now that because we use "half" pages for
+ * the HTW (1M IND is 2K and 256M IND is 32K) we need to account
+ * for an added LSB bit to the RPN. For 64K pages, there is no
+ * problem as we already use 32K arrays (half PTE pages), but for
+ * 4K page we need to extract a bit from the virtual address and
+ * insert it into the "PA52" bit of the RPN.
+ */
+#ifndef CONFIG_PPC_64K_PAGES
+ rlwimi r15,r16,32-9,20,20
+#endif
+ /* Now we build the MAS:
+ *
+ * MAS 0 : Fully setup with defaults in MAS4 and TLBnCFG
+ * MAS 1 : Almost fully setup
+ * - PID already updated by caller if necessary
+ * - TSIZE for now is base ind page size always
+ * MAS 2 : Use defaults
+ * MAS 3+7 : Needs to be done
+ */
+#ifdef CONFIG_PPC_64K_PAGES
+ ori r10,r15,(BOOK3E_PAGESZ_64K << MAS3_SPSIZE_SHIFT)
+#else
+ ori r10,r15,(BOOK3E_PAGESZ_4K << MAS3_SPSIZE_SHIFT)
+#endif
+ mtspr SPRN_MAS7_MAS3,r10
+
+ tlbwe
+
+htw_tlb_miss_done:
+ /* We don't bother with restoring DEAR or ESR since we know we are
+ * level 0 and just going back to userland. They are only needed
+ * if you are going to take an access fault
+ */
+ TLB_MISS_STATS_X(MMSTAT_TLB_MISS_PT_OK)
+ TLB_MISS_EPILOG_SUCCESS
+ rfi
+
+htw_tlb_miss_fault:
+ /* We need to check if it was an instruction miss. We know this
+ * though because r14 would contain -1
+ */
+ cmpdi cr0,r14,-1
+ beq 1f
+ mtspr SPRN_DEAR,r16
+ mtspr SPRN_ESR,r14
+ TLB_MISS_STATS_D(MMSTAT_TLB_MISS_PT_FAULT)
+ TLB_MISS_EPILOG_ERROR
+ b exc_data_storage_book3e
+1: TLB_MISS_STATS_I(MMSTAT_TLB_MISS_PT_FAULT)
+ TLB_MISS_EPILOG_ERROR
+ b exc_instruction_storage_book3e
+
+/*
+ * This is the guts of "any" level TLB miss handler for kernel linear
+ * mapping misses. We are entered with:
+ *
+ *
+ * r16 = faulting address
+ * r15 = crap (free to use)
+ * r14 = ESR (data) or -1 (instruction)
+ * r13 = PACA
+ * r12 = TLB exception frame in PACA
+ * r11 = crap (free to use)
+ * r10 = crap (free to use)
+ *
+ * In addition we know that we will not re-enter, so in theory, we could
+ * use a simpler epilog not restoring SRR0/1 etc.. but we'll do that later.
+ *
+ * We also need to be careful about MAS registers here & TLB reservation,
+ * as we know we'll have clobbered them if we interrupt the main TLB miss
+ * handlers in which case we probably want to do a full restart at level
+ * 0 rather than saving / restoring the MAS.
+ *
+ * Note: If we care about performance of that core, we can easily shuffle
+ * a few things around
+ */
+tlb_load_linear:
+ /* For now, we assume the linear mapping is contiguous and stops at
+ * linear_map_top. We also assume the size is a multiple of 1G, thus
+ * we only use 1G pages for now. That might have to be changed in a
+ * final implementation, especially when dealing with hypervisors
+ */
+ ld r11,PACATOC(r13)
+ ld r11,linear_map_top@got(r11)
+ ld r10,0(r11)
+ cmpld cr0,r10,r16
+ bge tlb_load_linear_fault
+
+ /* MAS1 need whole new setup. */
+ li r15,(BOOK3E_PAGESZ_1GB<<MAS1_TSIZE_SHIFT)
+ oris r15,r15,MAS1_VALID@h /* MAS1 needs V and TSIZE */
+ mtspr SPRN_MAS1,r15
+
+ /* Already somebody there ? */
+ PPC_TLBSRX_DOT(0,r16)
+ beq tlb_load_linear_done
+
+ /* Now we build the remaining MAS. MAS0 and 2 should be fine
+ * with their defaults, which leaves us with MAS 3 and 7. The
+ * mapping is linear, so we just take the address, clear the
+ * region bits, and or in the permission bits which are currently
+ * hard wired
+ */
+ clrrdi r10,r16,30 /* 1G page index */
+ clrldi r10,r10,4 /* clear region bits */
+ ori r10,r10,MAS3_SR|MAS3_SW|MAS3_SX
+ mtspr SPRN_MAS7_MAS3,r10
+
+ tlbwe
+
+tlb_load_linear_done:
+ /* We use the "error" epilog for success as we do want to
+ * restore to the initial faulting context, whatever it was.
+ * We do that because we can't resume a fault within a TLB
+ * miss handler, due to MAS and TLB reservation being clobbered.
+ */
+ TLB_MISS_STATS_X(MMSTAT_TLB_MISS_LINEAR)
+ TLB_MISS_EPILOG_ERROR
+ rfi
+
+tlb_load_linear_fault:
+ /* We keep the DEAR and ESR around, this shouldn't have happened */
+ cmpdi cr0,r14,-1
+ beq 1f
+ TLB_MISS_EPILOG_ERROR_SPECIAL
+ b exc_data_storage_book3e
+1: TLB_MISS_EPILOG_ERROR_SPECIAL
+ b exc_instruction_storage_book3e
+
+
+#ifdef CONFIG_BOOK3E_MMU_TLB_STATS
+.tlb_stat_inc:
+1: ldarx r8,0,r9
+ addi r8,r8,1
+ stdcx. r8,0,r9
+ bne- 1b
+ blr
+#endif
Index: linux-work/arch/powerpc/mm/mmu_decl.h
===================================================================
--- linux-work.orig/arch/powerpc/mm/mmu_decl.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/mm/mmu_decl.h 2009-07-24 18:15:35.000000000 +1000
@@ -41,7 +41,11 @@ static inline void _tlbil_pid(unsigned i
#else /* CONFIG_40x || CONFIG_8xx */
extern void _tlbil_all(void);
extern void _tlbil_pid(unsigned int pid);
+#ifdef CONFIG_PPC_BOOK3E
+extern void _tlbil_pid_noind(unsigned int pid);
+#else
#define _tlbil_pid_noind(pid) _tlbil_pid(pid)
+#endif
#endif /* !(CONFIG_40x || CONFIG_8xx) */
/*
@@ -53,7 +57,10 @@ static inline void _tlbil_va(unsigned lo
{
asm volatile ("tlbie %0; sync" : : "r" (address) : "memory");
}
-#else /* CONFIG_8xx */
+#elif defined(CONFIG_PPC_BOOK3E)
+extern void _tlbil_va(unsigned long address, unsigned int pid,
+ unsigned int tsize, unsigned int ind);
+#else
extern void __tlbil_va(unsigned long address, unsigned int pid);
static inline void _tlbil_va(unsigned long address, unsigned int pid,
unsigned int tsize, unsigned int ind)
@@ -67,11 +74,16 @@ static inline void _tlbil_va(unsigned lo
* implementation. When that becomes the case, this will be
* an extern.
*/
+#ifdef CONFIG_PPC_BOOK3E
+extern void _tlbivax_bcast(unsigned long address, unsigned int pid,
+ unsigned int tsize, unsigned int ind);
+#else
static inline void _tlbivax_bcast(unsigned long address, unsigned int pid,
unsigned int tsize, unsigned int ind)
{
BUG();
}
+#endif
#else /* CONFIG_PPC_MMU_NOHASH */
Index: linux-work/arch/powerpc/mm/tlb_nohash.c
===================================================================
--- linux-work.orig/arch/powerpc/mm/tlb_nohash.c 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/mm/tlb_nohash.c 2009-07-24 18:15:35.000000000 +1000
@@ -7,8 +7,8 @@
*
* -- BenH
*
- * Copyright 2008 Ben Herrenschmidt <benh@kernel.crashing.org>
- * IBM Corp.
+ * Copyright 2008,2009 Ben Herrenschmidt <benh@kernel.crashing.org>
+ * IBM Corp.
*
* Derived from arch/ppc/mm/init.c:
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -34,12 +34,70 @@
#include <linux/pagemap.h>
#include <linux/preempt.h>
#include <linux/spinlock.h>
+#include <linux/lmb.h>
#include <asm/tlbflush.h>
#include <asm/tlb.h>
+#include <asm/code-patching.h>
#include "mmu_decl.h"
+#ifdef CONFIG_PPC_BOOK3E
+struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
+ [MMU_PAGE_4K] = {
+ .shift = 12,
+ .enc = BOOK3E_PAGESZ_4K,
+ },
+ [MMU_PAGE_16K] = {
+ .shift = 14,
+ .enc = BOOK3E_PAGESZ_16K,
+ },
+ [MMU_PAGE_64K] = {
+ .shift = 16,
+ .enc = BOOK3E_PAGESZ_64K,
+ },
+ [MMU_PAGE_1M] = {
+ .shift = 20,
+ .enc = BOOK3E_PAGESZ_1M,
+ },
+ [MMU_PAGE_16M] = {
+ .shift = 24,
+ .enc = BOOK3E_PAGESZ_16M,
+ },
+ [MMU_PAGE_256M] = {
+ .shift = 28,
+ .enc = BOOK3E_PAGESZ_256M,
+ },
+ [MMU_PAGE_1G] = {
+ .shift = 30,
+ .enc = BOOK3E_PAGESZ_1GB,
+ },
+};
+static inline int mmu_get_tsize(int psize)
+{
+ return mmu_psize_defs[psize].enc;
+}
+#else
+static inline int mmu_get_tsize(int psize)
+{
+ /* This isn't used on !Book3E for now */
+ return 0;
+}
+#endif
+
+/* The variables below are currently only used on 64-bit Book3E
+ * though this will probably be made common with other nohash
+ * implementations at some point
+ */
+#ifdef CONFIG_PPC64
+
+int mmu_linear_psize; /* Page size used for the linear mapping */
+int mmu_pte_psize; /* Page size used for PTE pages */
+int book3e_htw_enabled; /* Is HW tablewalk enabled ? */
+unsigned long linear_map_top; /* Top of linear mapping */
+
+#endif /* CONFIG_PPC64 */
+
/*
* Base TLB flushing operations:
*
@@ -82,7 +140,7 @@ void __local_flush_tlb_page(struct mm_st
void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
__local_flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
- 0 /* tsize unused for now */, 0);
+ mmu_get_tsize(mmu_virtual_psize), 0);
}
EXPORT_SYMBOL(local_flush_tlb_page);
@@ -198,7 +256,7 @@ void __flush_tlb_page(struct mm_struct *
void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
__flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
- 0 /* tsize unused for now */, 0);
+ mmu_get_tsize(mmu_virtual_psize), 0);
}
EXPORT_SYMBOL(flush_tlb_page);
@@ -241,3 +299,140 @@ void tlb_flush(struct mmu_gather *tlb)
/* Push out batch of freed page tables */
pte_free_finish();
}
+
+/*
+ * Below are functions specific to the 64-bit variant of Book3E though that
+ * may change in the future
+ */
+
+#ifdef CONFIG_PPC64
+
+/*
+ * Handling of virtual linear page tables or indirect TLB entries
+ * flushing when PTE pages are freed
+ */
+void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address)
+{
+ int tsize = mmu_psize_defs[mmu_pte_psize].enc;
+
+ if (book3e_htw_enabled) {
+ unsigned long start = address & PMD_MASK;
+ unsigned long end = address + PMD_SIZE;
+ unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift;
+
+ /* This isn't the most optimal, ideally we would factor out the
+ * while preempt & CPU mask mucking around, or even the IPI but
+ * it will do for now
+ */
+ while (start < end) {
+ __flush_tlb_page(tlb->mm, start, tsize, 1);
+ start += size;
+ }
+ } else {
+ unsigned long rmask = 0xf000000000000000ul;
+ unsigned long rid = (address & rmask) | 0x1000000000000000ul;
+ unsigned long vpte = address & ~rmask;
+
+#ifdef CONFIG_PPC_64K_PAGES
+ vpte = (vpte >> (PAGE_SHIFT - 4)) & ~0xfffful;
+#else
+ vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful;
+#endif
+ vpte |= rid;
+ __flush_tlb_page(tlb->mm, vpte, tsize, 0);
+ }
+}
+
+/*
+ * Early initialization of the MMU TLB code
+ */
+static void __early_init_mmu(int boot_cpu)
+{
+ extern unsigned int interrupt_base_book3e;
+ extern unsigned int exc_data_tlb_miss_htw_book3e;
+ extern unsigned int exc_instruction_tlb_miss_htw_book3e;
+
+ unsigned int *ibase = &interrupt_base_book3e;
+ unsigned int mas4;
+
+ /* XXX This will have to be decided at runtime, but right
+ * now our boot and TLB miss code hard wires it
+ */
+ mmu_linear_psize = MMU_PAGE_1G;
+
+
+ /* Check if HW tablewalk is present, and if yes, enable it by:
+ *
+ * - patching the TLB miss handlers to branch to the
+ * one dedicates to it
+ *
+ * - setting the global book3e_htw_enabled
+ *
+ * - Set MAS4:INDD and default page size
+ */
+
+ /* XXX This code only checks for TLB 0 capabilities and doesn't
+ * check what page size combos are supported by the HW. It
+ * also doesn't handle the case where a separate array holds
+ * the IND entries from the array loaded by the PT.
+ */
+ if (boot_cpu) {
+ unsigned int tlb0cfg = mfspr(SPRN_TLB0CFG);
+
+ /* Check if HW loader is supported */
+ if ((tlb0cfg & TLBnCFG_IND) &&
+ (tlb0cfg & TLBnCFG_PT)) {
+ patch_branch(ibase + (0x1c0 / 4),
+ (unsigned long)&exc_data_tlb_miss_htw_book3e, 0);
+ patch_branch(ibase + (0x1e0 / 4),
+ (unsigned long)&exc_instruction_tlb_miss_htw_book3e, 0);
+ book3e_htw_enabled = 1;
+ }
+ pr_info("MMU: Book3E Page Tables %s\n",
+ book3e_htw_enabled ? "Enabled" : "Disabled");
+ }
+
+ /* Set MAS4 based on page table setting */
+
+ mas4 = 0x4 << MAS4_WIMGED_SHIFT;
+ if (book3e_htw_enabled) {
+ mas4 |= mas4 | MAS4_INDD;
+#ifdef CONFIG_PPC_64K_PAGES
+ mas4 |= BOOK3E_PAGESZ_256M << MAS4_TSIZED_SHIFT;
+ mmu_pte_psize = MMU_PAGE_256M;
+#else
+ mas4 |= BOOK3E_PAGESZ_1M << MAS4_TSIZED_SHIFT;
+ mmu_pte_psize = MMU_PAGE_1M;
+#endif
+ } else {
+#ifdef CONFIG_PPC_64K_PAGES
+ mas4 |= BOOK3E_PAGESZ_64K << MAS4_TSIZED_SHIFT;
+#else
+ mas4 |= BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT;
+#endif
+ mmu_pte_psize = mmu_virtual_psize;
+ }
+ mtspr(SPRN_MAS4, mas4);
+
+ /* Set the global containing the top of the linear mapping
+ * for use by the TLB miss code
+ */
+ linear_map_top = lmb_end_of_DRAM();
+
+ /* A sync won't hurt us after mucking around with
+ * the MMU configuration
+ */
+ mb();
+}
+
+void __init early_init_mmu(void)
+{
+ __early_init_mmu(1);
+}
+
+void __cpuinit early_init_mmu_secondary(void)
+{
+ __early_init_mmu(0);
+}
+
+#endif /* CONFIG_PPC64 */
Index: linux-work/arch/powerpc/include/asm/mmu_context.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/mmu_context.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/mmu_context.h 2009-07-24 18:15:31.000000000 +1000
@@ -43,6 +43,10 @@ static inline void switch_mm(struct mm_s
tsk->thread.pgdir = next->pgd;
#endif /* CONFIG_PPC32 */
+ /* 64-bit Book3E keeps track of current PGD in the PACA */
+#ifdef CONFIG_PPC_BOOK3E_64
+ get_paca()->pgd = next->pgd;
+#endif
/* Nothing else to do if we aren't actually switching */
if (prev == next)
return;
@@ -89,6 +93,10 @@ static inline void activate_mm(struct mm
static inline void enter_lazy_tlb(struct mm_struct *mm,
struct task_struct *tsk)
{
+ /* 64-bit Book3E keeps track of current PGD in the PACA */
+#ifdef CONFIG_PPC_BOOK3E_64
+ get_paca()->pgd = NULL;
+#endif
}
#endif /* __KERNEL__ */
Index: linux-work/arch/powerpc/kernel/setup_64.c
===================================================================
--- linux-work.orig/arch/powerpc/kernel/setup_64.c 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/kernel/setup_64.c 2009-07-24 18:15:34.000000000 +1000
@@ -62,6 +62,7 @@
#include <asm/udbg.h>
#include <asm/kexec.h>
#include <asm/swiotlb.h>
+#include <asm/mmu_context.h>
#include "setup.h"
@@ -147,6 +148,9 @@ void __init setup_paca(int cpu)
{
local_paca = &paca[cpu];
mtspr(SPRN_SPRG_PACA, local_paca);
+#ifdef CONFIG_PPC_BOOK3E
+ mtspr(SPRN_SPRG_TLB_EXFRAME, local_paca->extlb);
+#endif
}
/*
Index: linux-work/arch/powerpc/mm/tlb_nohash_low.S
===================================================================
--- linux-work.orig/arch/powerpc/mm/tlb_nohash_low.S 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/mm/tlb_nohash_low.S 2009-07-24 18:15:31.000000000 +1000
@@ -191,6 +191,85 @@ ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_US
isync
1: wrtee r10
blr
+#elif defined(CONFIG_PPC_BOOK3E)
+/*
+ * New Book3E (>= 2.06) implementation
+ *
+ * Note: We may be able to get away without the interrupt masking stuff
+ * if we save/restore MAS6 on exceptions that might modify it
+ */
+_GLOBAL(_tlbil_pid)
+ slwi r4,r3,MAS6_SPID_SHIFT
+ mfmsr r10
+ wrteei 0
+ mtspr SPRN_MAS6,r4
+ PPC_TLBILX_PID(0,0)
+ wrtee r10
+ msync
+ isync
+ blr
+
+_GLOBAL(_tlbil_pid_noind)
+ slwi r4,r3,MAS6_SPID_SHIFT
+ mfmsr r10
+ ori r4,r4,MAS6_SIND
+ wrteei 0
+ mtspr SPRN_MAS6,r4
+ PPC_TLBILX_PID(0,0)
+ wrtee r10
+ msync
+ isync
+ blr
+
+_GLOBAL(_tlbil_all)
+ PPC_TLBILX_ALL(0,0)
+ msync
+ isync
+ blr
+
+_GLOBAL(_tlbil_va)
+ mfmsr r10
+ wrteei 0
+ cmpwi cr0,r6,0
+ slwi r4,r4,MAS6_SPID_SHIFT
+ rlwimi r4,r5,MAS6_ISIZE_SHIFT,MAS6_ISIZE_MASK
+ beq 1f
+ rlwimi r4,r6,MAS6_SIND_SHIFT,MAS6_SIND
+1: mtspr SPRN_MAS6,r4 /* assume AS=0 for now */
+ PPC_TLBILX_VA(0,r3)
+ msync
+ isync
+ wrtee r10
+ blr
+
+_GLOBAL(_tlbivax_bcast)
+ mfmsr r10
+ wrteei 0
+ cmpwi cr0,r6,0
+ slwi r4,r4,MAS6_SPID_SHIFT
+ rlwimi r4,r5,MAS6_ISIZE_SHIFT,MAS6_ISIZE_MASK
+ beq 1f
+ rlwimi r4,r6,MAS6_SIND_SHIFT,MAS6_SIND
+1: mtspr SPRN_MAS6,r4 /* assume AS=0 for now */
+ PPC_TLBIVAX(0,r3)
+ eieio
+ tlbsync
+ sync
+ wrtee r10
+ blr
+
+_GLOBAL(set_context)
+#ifdef CONFIG_BDI_SWITCH
+ /* Context switch the PTE pointer for the Abatron BDI2000.
+ * The PGDIR is the second parameter.
+ */
+ lis r5, abatron_pteptrs@h
+ ori r5, r5, abatron_pteptrs@l
+ stw r4, 0x4(r5)
+#endif
+ mtspr SPRN_PID,r3
+ isync /* Force context change */
+ blr
#else
#error Unsupported processor type !
#endif
Index: linux-work/arch/powerpc/include/asm/mmu-40x.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/mmu-40x.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/mmu-40x.h 2009-07-24 18:15:31.000000000 +1000
@@ -61,4 +61,7 @@ typedef struct {
#endif /* !__ASSEMBLY__ */
+#define mmu_virtual_psize MMU_PAGE_4K
+#define mmu_linear_psize MMU_PAGE_256M
+
#endif /* _ASM_POWERPC_MMU_40X_H_ */
Index: linux-work/arch/powerpc/include/asm/mmu-44x.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/mmu-44x.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/mmu-44x.h 2009-07-24 18:15:31.000000000 +1000
@@ -79,16 +79,22 @@ typedef struct {
#if (PAGE_SHIFT == 12)
#define PPC44x_TLBE_SIZE PPC44x_TLB_4K
+#define mmu_virtual_psize MMU_PAGE_4K
#elif (PAGE_SHIFT == 14)
#define PPC44x_TLBE_SIZE PPC44x_TLB_16K
+#define mmu_virtual_psize MMU_PAGE_16K
#elif (PAGE_SHIFT == 16)
#define PPC44x_TLBE_SIZE PPC44x_TLB_64K
+#define mmu_virtual_psize MMU_PAGE_64K
#elif (PAGE_SHIFT == 18)
#define PPC44x_TLBE_SIZE PPC44x_TLB_256K
+#define mmu_virtual_psize MMU_PAGE_256K
#else
#error "Unsupported PAGE_SIZE"
#endif
+#define mmu_linear_psize MMU_PAGE_256M
+
#define PPC44x_PGD_OFF_SHIFT (32 - PGDIR_SHIFT + PGD_T_LOG2)
#define PPC44x_PGD_OFF_MASK_BIT (PGDIR_SHIFT - PGD_T_LOG2)
#define PPC44x_PTE_ADD_SHIFT (32 - PGDIR_SHIFT + PTE_SHIFT + PTE_T_LOG2)
Index: linux-work/arch/powerpc/include/asm/mmu-8xx.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/mmu-8xx.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/mmu-8xx.h 2009-07-24 18:15:31.000000000 +1000
@@ -143,4 +143,7 @@ typedef struct {
} mm_context_t;
#endif /* !__ASSEMBLY__ */
+#define mmu_virtual_psize MMU_PAGE_4K
+#define mmu_linear_psize MMU_PAGE_8M
+
#endif /* _ASM_POWERPC_MMU_8XX_H_ */
Index: linux-work/arch/powerpc/include/asm/mmu-hash32.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/mmu-hash32.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/mmu-hash32.h 2009-07-24 18:15:31.000000000 +1000
@@ -80,4 +80,10 @@ typedef struct {
#endif /* !__ASSEMBLY__ */
+/* We happily ignore the smaller BATs on 601, we don't actually use
+ * those definitions on hash32 at the moment anyway
+ */
+#define mmu_virtual_psize MMU_PAGE_4K
+#define mmu_linear_psize MMU_PAGE_256M
+
#endif /* _ASM_POWERPC_MMU_HASH32_H_ */
^ permalink raw reply
* [PATCH 17/20] powerpc/mm: Move around mmu_gathers definition on 64-bit (v2)
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
The definition for the global structure mmu_gathers, used by generic code,
is currently defined in multiple places not including anything used by
64-bit Book3E. This changes it by moving to one place common to all
processors.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
v2. Fix issues due to changes in other patches
arch/powerpc/mm/init_32.c | 2 --
arch/powerpc/mm/pgtable.c | 2 ++
arch/powerpc/mm/tlb_hash64.c | 5 -----
3 files changed, 2 insertions(+), 7 deletions(-)
--- linux-work.orig/arch/powerpc/mm/tlb_hash64.c 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/mm/tlb_hash64.c 2009-07-24 18:14:51.000000000 +1000
@@ -33,11 +33,6 @@
DEFINE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch);
-/* This is declared as we are using the more or less generic
- * arch/powerpc/include/asm/tlb.h file -- tgall
- */
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
/*
* A linux PTE was changed and the corresponding hash table entry
* neesd to be flushed. This function will either perform the flush
Index: linux-work/arch/powerpc/mm/init_32.c
===================================================================
--- linux-work.orig/arch/powerpc/mm/init_32.c 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/mm/init_32.c 2009-07-24 18:14:51.000000000 +1000
@@ -54,8 +54,6 @@
#endif
#define MAX_LOW_MEM CONFIG_LOWMEM_SIZE
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-
phys_addr_t total_memory;
phys_addr_t total_lowmem;
Index: linux-work/arch/powerpc/mm/pgtable.c
===================================================================
--- linux-work.orig/arch/powerpc/mm/pgtable.c 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/mm/pgtable.c 2009-07-24 18:15:05.000000000 +1000
@@ -30,6 +30,8 @@
#include <asm/tlbflush.h>
#include <asm/tlb.h>
+DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
+
#ifdef CONFIG_SMP
/*
^ permalink raw reply
* [PATCH 16/20] powerpc: Add PACA fields specific to 64-bit Book3E processors
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
This adds various fields in the PACA that are for use specifically
by Book3E processors, such as exception save areas, current pgd
pointer, special exceptions kernel stacks etc...
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/include/asm/paca.h | 23 ++++++++++++++++++++---
arch/powerpc/kernel/asm-offsets.c | 14 ++++++++++++++
arch/powerpc/kernel/paca.c | 3 +++
3 files changed, 37 insertions(+), 3 deletions(-)
--- linux-work.orig/arch/powerpc/include/asm/paca.h 2009-07-23 14:29:58.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/paca.h 2009-07-23 14:31:42.000000000 +1000
@@ -14,9 +14,11 @@
#define _ASM_POWERPC_PACA_H
#ifdef __KERNEL__
-#include <asm/types.h>
-#include <asm/lppaca.h>
-#include <asm/mmu.h>
+#include <asm/types.h>
+#include <asm/lppaca.h>
+#include <asm/mmu.h>
+#include <asm/page.h>
+#include <asm/exception-64e.h>
register struct paca_struct *local_paca asm("r13");
@@ -91,6 +93,21 @@ struct paca_struct {
u16 slb_cache[SLB_CACHE_ENTRIES];
#endif /* CONFIG_PPC_STD_MMU_64 */
+#ifdef CONFIG_PPC_BOOK3E
+ pgd_t *pgd; /* Current PGD */
+ pgd_t *kernel_pgd; /* Kernel PGD */
+ u64 exgen[8] __attribute__((aligned(0x80)));
+ u64 extlb[EX_TLB_SIZE*3] __attribute__((aligned(0x80)));
+ u64 exmc[8]; /* used for machine checks */
+ u64 excrit[8]; /* used for crit interrupts */
+ u64 exdbg[8]; /* used for debug interrupts */
+
+ /* Kernel stack pointers for use by special exceptions */
+ void *mc_kstack;
+ void *crit_kstack;
+ void *dbg_kstack;
+#endif /* CONFIG_PPC_BOOK3E */
+
mm_context_t context;
/*
Index: linux-work/arch/powerpc/kernel/asm-offsets.c
===================================================================
--- linux-work.orig/arch/powerpc/kernel/asm-offsets.c 2009-07-23 14:31:35.000000000 +1000
+++ linux-work/arch/powerpc/kernel/asm-offsets.c 2009-07-23 14:31:42.000000000 +1000
@@ -140,6 +140,20 @@ int main(void)
context.high_slices_psize));
DEFINE(MMUPSIZEDEFSIZE, sizeof(struct mmu_psize_def));
#endif /* CONFIG_PPC_MM_SLICES */
+
+#ifdef CONFIG_PPC_BOOK3E
+ DEFINE(PACAPGD, offsetof(struct paca_struct, pgd));
+ DEFINE(PACA_KERNELPGD, offsetof(struct paca_struct, kernel_pgd));
+ DEFINE(PACA_EXGEN, offsetof(struct paca_struct, exgen));
+ DEFINE(PACA_EXTLB, offsetof(struct paca_struct, extlb));
+ DEFINE(PACA_EXMC, offsetof(struct paca_struct, exmc));
+ DEFINE(PACA_EXCRIT, offsetof(struct paca_struct, excrit));
+ DEFINE(PACA_EXDBG, offsetof(struct paca_struct, exdbg));
+ DEFINE(PACA_MC_STACK, offsetof(struct paca_struct, mc_kstack));
+ DEFINE(PACA_CRIT_STACK, offsetof(struct paca_struct, crit_kstack));
+ DEFINE(PACA_DBG_STACK, offsetof(struct paca_struct, dbg_kstack));
+#endif /* CONFIG_PPC_BOOK3E */
+
#ifdef CONFIG_PPC_STD_MMU_64
DEFINE(PACASTABREAL, offsetof(struct paca_struct, stab_real));
DEFINE(PACASTABVIRT, offsetof(struct paca_struct, stab_addr));
Index: linux-work/arch/powerpc/kernel/paca.c
===================================================================
--- linux-work.orig/arch/powerpc/kernel/paca.c 2009-07-23 14:29:58.000000000 +1000
+++ linux-work/arch/powerpc/kernel/paca.c 2009-07-23 14:31:42.000000000 +1000
@@ -13,6 +13,7 @@
#include <asm/lppaca.h>
#include <asm/paca.h>
#include <asm/sections.h>
+#include <asm/pgtable.h>
/* This symbol is provided by the linker - let it fill in the paca
* field correctly */
@@ -87,6 +88,8 @@ void __init initialise_pacas(void)
#ifdef CONFIG_PPC_BOOK3S
new_paca->lppaca_ptr = &lppaca[cpu];
+#else
+ new_paca->kernel_pgd = swapper_pg_dir;
#endif
new_paca->lock_token = 0x8000;
new_paca->paca_index = cpu;
^ permalink raw reply
* [PATCH 15/20] powerpc: Add definitions used by exception handling on 64-bit Book3E (v2)
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
This adds various definitions and macros used by the exception and TLB
miss handling on 64-bit BookE
It also adds the definitions of the SPRGs used for various exception types
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
v2. Change __EXCEPTION_64E_H__ to _ASM_POWERPC_EXCEPTION_64E_H
arch/powerpc/include/asm/exception-64e.h | 201 +++++++++++++++++++++++++++++++
arch/powerpc/include/asm/reg.h | 19 ++
2 files changed, 220 insertions(+)
--- linux-work.orig/arch/powerpc/include/asm/reg.h 2009-07-24 15:57:39.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/reg.h 2009-07-24 15:58:22.000000000 +1000
@@ -652,6 +652,16 @@
* - SPRG2 scratch for exception vectors
* - SPRG3 unused (user visible)
*
+ * 64-bit embedded
+ * - SPRG0 generic exception scratch
+ * - SPRG2 TLB exception stack
+ * - SPRG3 unused (user visible)
+ * - SPRG4 unused (user visible)
+ * - SPRG6 TLB miss scratch (user visible, sorry !)
+ * - SPRG7 critical exception scratch
+ * - SPRG8 machine check exception scratch
+ * - SPRG9 debug exception scratch
+ *
* All 32-bit:
* - SPRG3 current thread_info pointer
* (virtual on BookE, physical on others)
@@ -705,6 +715,15 @@
#define SPRN_SPRG_SCRATCH0 SPRN_SPRG2
#endif
+#ifdef CONFIG_PPC_BOOK3E_64
+#define SPRN_SPRG_MC_SCRATCH SPRN_SPRG8
+#define SPRN_SPRG_CRIT_SCRATCH SPRN_SPRG7
+#define SPRN_SPRG_DBG_SCRATCH SPRN_SPRG9
+#define SPRN_SPRG_TLB_EXFRAME SPRN_SPRG2
+#define SPRN_SPRG_TLB_SCRATCH SPRN_SPRG6
+#define SPRN_SPRG_GEN_SCRATCH SPRN_SPRG0
+#endif
+
#ifdef CONFIG_PPC_BOOK3S_32
#define SPRN_SPRG_SCRATCH0 SPRN_SPRG0
#define SPRN_SPRG_SCRATCH1 SPRN_SPRG1
Index: linux-work/arch/powerpc/include/asm/exception-64e.h
===================================================================
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-work/arch/powerpc/include/asm/exception-64e.h 2009-07-24 15:59:09.000000000 +1000
@@ -0,0 +1,201 @@
+/*
+ * Definitions for use by exception code on Book3-E
+ *
+ * Copyright (C) 2008 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
+ *
+ * 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.
+ */
+#ifndef _ASM_POWERPC_EXCEPTION_64E_H
+#define _ASM_POWERPC_EXCEPTION_64E_H
+
+/*
+ * SPRGs usage an other considerations...
+ *
+ * Since TLB miss and other standard exceptions can be interrupted by
+ * critical exceptions which can themselves be interrupted by machine
+ * checks, and since the two later can themselves cause a TLB miss when
+ * hitting the linear mapping for the kernel stacks, we need to be a bit
+ * creative on how we use SPRGs.
+ *
+ * The base idea is that we have one SRPG reserved for critical and one
+ * for machine check interrupts. Those are used to save a GPR that can
+ * then be used to get the PACA, and store as much context as we need
+ * to save in there. That includes saving the SPRGs used by the TLB miss
+ * handler for linear mapping misses and the associated SRR0/1 due to
+ * the above re-entrancy issue.
+ *
+ * So here's the current usage pattern. It's done regardless of which
+ * SPRGs are user-readable though, thus we might have to change some of
+ * this later. In order to do that more easily, we use special constants
+ * for naming them
+ *
+ * WARNING: Some of these SPRGs are user readable. We need to do something
+ * about it as some point by making sure they can't be used to leak kernel
+ * critical data
+ */
+
+
+/* We are out of SPRGs so we save some things in the PACA. The normal
+ * exception frame is smaller than the CRIT or MC one though
+ */
+#define EX_R1 (0 * 8)
+#define EX_CR (1 * 8)
+#define EX_R10 (2 * 8)
+#define EX_R11 (3 * 8)
+#define EX_R14 (4 * 8)
+#define EX_R15 (5 * 8)
+
+/* The TLB miss exception uses different slots */
+
+#define EX_TLB_R10 ( 0 * 8)
+#define EX_TLB_R11 ( 1 * 8)
+#define EX_TLB_R12 ( 2 * 8)
+#define EX_TLB_R13 ( 3 * 8)
+#define EX_TLB_R14 ( 4 * 8)
+#define EX_TLB_R15 ( 5 * 8)
+#define EX_TLB_R16 ( 6 * 8)
+#define EX_TLB_CR ( 7 * 8)
+#define EX_TLB_DEAR ( 8 * 8) /* Level 0 and 2 only */
+#define EX_TLB_ESR ( 9 * 8) /* Level 0 and 2 only */
+#define EX_TLB_SRR0 (10 * 8)
+#define EX_TLB_SRR1 (11 * 8)
+#define EX_TLB_MMUCR0 (12 * 8) /* Level 0 */
+#define EX_TLB_MAS1 (12 * 8) /* Level 0 */
+#define EX_TLB_MAS2 (13 * 8) /* Level 0 */
+#ifdef CONFIG_BOOK3E_MMU_TLB_STATS
+#define EX_TLB_R8 (14 * 8)
+#define EX_TLB_R9 (15 * 8)
+#define EX_TLB_LR (16 * 8)
+#define EX_TLB_SIZE (17 * 8)
+#else
+#define EX_TLB_SIZE (14 * 8)
+#endif
+
+#define START_EXCEPTION(label) \
+ .globl exc_##label##_book3e; \
+exc_##label##_book3e:
+
+/* TLB miss exception prolog
+ *
+ * This prolog handles re-entrancy (up to 3 levels supported in the PACA
+ * though we currently don't test for overflow). It provides you with a
+ * re-entrancy safe working space of r10...r16 and CR with r12 being used
+ * as the exception area pointer in the PACA for that level of re-entrancy
+ * and r13 containing the PACA pointer.
+ *
+ * SRR0 and SRR1 are saved, but DEAR and ESR are not, since they don't apply
+ * as-is for instruction exceptions. It's up to the actual exception code
+ * to save them as well if required.
+ */
+#define TLB_MISS_PROLOG \
+ mtspr SPRN_SPRG_TLB_SCRATCH,r12; \
+ mfspr r12,SPRN_SPRG_TLB_EXFRAME; \
+ std r10,EX_TLB_R10(r12); \
+ mfcr r10; \
+ std r11,EX_TLB_R11(r12); \
+ mfspr r11,SPRN_SPRG_TLB_SCRATCH; \
+ std r13,EX_TLB_R13(r12); \
+ mfspr r13,SPRN_SPRG_PACA; \
+ std r14,EX_TLB_R14(r12); \
+ addi r14,r12,EX_TLB_SIZE; \
+ std r15,EX_TLB_R15(r12); \
+ mfspr r15,SPRN_SRR1; \
+ std r16,EX_TLB_R16(r12); \
+ mfspr r16,SPRN_SRR0; \
+ std r10,EX_TLB_CR(r12); \
+ std r11,EX_TLB_R12(r12); \
+ mtspr SPRN_SPRG_TLB_EXFRAME,r14; \
+ std r15,EX_TLB_SRR1(r12); \
+ std r16,EX_TLB_SRR0(r12); \
+ TLB_MISS_PROLOG_STATS
+
+/* And these are the matching epilogs that restores things
+ *
+ * There are 3 epilogs:
+ *
+ * - SUCCESS : Unwinds one level
+ * - ERROR : restore from level 0 and reset
+ * - ERROR_SPECIAL : restore from current level and reset
+ *
+ * Normal errors use ERROR, that is, they restore the initial fault context
+ * and trigger a fault. However, there is a special case for linear mapping
+ * errors. Those should basically never happen, but if they do happen, we
+ * want the error to point out the context that did that linear mapping
+ * fault, not the initial level 0 (basically, we got a bogus PGF or something
+ * like that). For userland errors on the linear mapping, there is no
+ * difference since those are always level 0 anyway
+ */
+
+#define TLB_MISS_RESTORE(freg) \
+ ld r14,EX_TLB_CR(r12); \
+ ld r10,EX_TLB_R10(r12); \
+ ld r15,EX_TLB_SRR0(r12); \
+ ld r16,EX_TLB_SRR1(r12); \
+ mtspr SPRN_SPRG_TLB_EXFRAME,freg; \
+ ld r11,EX_TLB_R11(r12); \
+ mtcr r14; \
+ ld r13,EX_TLB_R13(r12); \
+ ld r14,EX_TLB_R14(r12); \
+ mtspr SPRN_SRR0,r15; \
+ ld r15,EX_TLB_R15(r12); \
+ mtspr SPRN_SRR1,r16; \
+ TLB_MISS_RESTORE_STATS \
+ ld r16,EX_TLB_R16(r12); \
+ ld r12,EX_TLB_R12(r12); \
+
+#define TLB_MISS_EPILOG_SUCCESS \
+ TLB_MISS_RESTORE(r12)
+
+#define TLB_MISS_EPILOG_ERROR \
+ addi r12,r13,PACA_EXTLB; \
+ TLB_MISS_RESTORE(r12)
+
+#define TLB_MISS_EPILOG_ERROR_SPECIAL \
+ addi r11,r13,PACA_EXTLB; \
+ TLB_MISS_RESTORE(r11)
+
+#ifdef CONFIG_BOOK3E_MMU_TLB_STATS
+#define TLB_MISS_PROLOG_STATS \
+ mflr r10; \
+ std r8,EX_TLB_R8(r12); \
+ std r9,EX_TLB_R9(r12); \
+ std r10,EX_TLB_LR(r12);
+#define TLB_MISS_RESTORE_STATS \
+ ld r16,EX_TLB_LR(r12); \
+ ld r9,EX_TLB_R9(r12); \
+ ld r8,EX_TLB_R8(r12); \
+ mtlr r16;
+#define TLB_MISS_STATS_D(name) \
+ addi r9,r13,MMSTAT_DSTATS+name; \
+ bl .tlb_stat_inc;
+#define TLB_MISS_STATS_I(name) \
+ addi r9,r13,MMSTAT_ISTATS+name; \
+ bl .tlb_stat_inc;
+#define TLB_MISS_STATS_X(name) \
+ ld r8,PACA_EXTLB+EX_TLB_ESR(r13); \
+ cmpdi cr2,r8,-1; \
+ beq cr2,61f; \
+ addi r9,r13,MMSTAT_DSTATS+name; \
+ b 62f; \
+61: addi r9,r13,MMSTAT_ISTATS+name; \
+62: bl .tlb_stat_inc;
+#define TLB_MISS_STATS_SAVE_INFO \
+ std r14,EX_TLB_ESR(r12); /* save ESR */ \
+
+
+#else
+#define TLB_MISS_PROLOG_STATS
+#define TLB_MISS_RESTORE_STATS
+#define TLB_MISS_STATS_D(name)
+#define TLB_MISS_STATS_I(name)
+#define TLB_MISS_STATS_X(name)
+#define TLB_MISS_STATS_Y(name)
+#define TLB_MISS_STATS_SAVE_INFO
+#endif
+
+
+#endif /* _ASM_POWERPC_EXCEPTION_64E_H */
+
^ permalink raw reply
* [PATCH 14/20] powerpc: Add memory management headers for new 64-bit BookE (v2)
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
This adds the PTE and pgtable format definitions, along with changes
to the kernel memory map and other definitions related to implementing
support for 64-bit Book3E. This also shields some asm-offset bits that
are currently only relevant on 32-bit
We also move the definition of the "linux" page size constants to
the common mmu.h file and add a few sizes that are relevant to
embedded processors.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
v2. Move the list of page size constants to a generic location for
use by all cpu types
arch/powerpc/include/asm/mmu-book3e.h | 27 +++++++++++
arch/powerpc/include/asm/mmu-hash64.h | 20 --------
arch/powerpc/include/asm/mmu.h | 32 ++++++++++++++
arch/powerpc/include/asm/page.h | 4 +
arch/powerpc/include/asm/page_64.h | 10 ++++
arch/powerpc/include/asm/pgtable-ppc64.h | 61 +++++++++++++++++++--------
arch/powerpc/include/asm/pte-book3e.h | 70 +++++++++++++++++++++++++++++++
arch/powerpc/include/asm/pte-common.h | 3 +
arch/powerpc/kernel/asm-offsets.c | 5 +-
9 files changed, 194 insertions(+), 38 deletions(-)
--- /dev/null 1970-01-01 00:00:00.000000000 +0000
+++ linux-work/arch/powerpc/include/asm/pte-book3e.h 2009-07-24 18:14:49.000000000 +1000
@@ -0,0 +1,70 @@
+#ifndef _ASM_POWERPC_PTE_BOOK3E_H
+#define _ASM_POWERPC_PTE_BOOK3E_H
+#ifdef __KERNEL__
+
+/* PTE bit definitions for processors compliant to the Book3E
+ * architecture 2.06 or later. The position of the PTE bits
+ * matches the HW definition of the optional Embedded Page Table
+ * category.
+ */
+
+/* Architected bits */
+#define _PAGE_PRESENT 0x000001 /* software: pte contains a translation */
+#define _PAGE_FILE 0x000002 /* (!present only) software: pte holds file offset */
+#define _PAGE_SW1 0x000002
+#define _PAGE_BAP_SR 0x000004
+#define _PAGE_BAP_UR 0x000008
+#define _PAGE_BAP_SW 0x000010
+#define _PAGE_BAP_UW 0x000020
+#define _PAGE_BAP_SX 0x000040
+#define _PAGE_BAP_UX 0x000080
+#define _PAGE_PSIZE_MSK 0x000f00
+#define _PAGE_PSIZE_4K 0x000200
+#define _PAGE_PSIZE_64K 0x000600
+#define _PAGE_PSIZE_1M 0x000a00
+#define _PAGE_PSIZE_16M 0x000e00
+#define _PAGE_DIRTY 0x001000 /* C: page changed */
+#define _PAGE_SW0 0x002000
+#define _PAGE_U3 0x004000
+#define _PAGE_U2 0x008000
+#define _PAGE_U1 0x010000
+#define _PAGE_U0 0x020000
+#define _PAGE_ACCESSED 0x040000
+#define _PAGE_LENDIAN 0x080000
+#define _PAGE_GUARDED 0x100000
+#define _PAGE_COHERENT 0x200000 /* M: enforce memory coherence */
+#define _PAGE_NO_CACHE 0x400000 /* I: cache inhibit */
+#define _PAGE_WRITETHRU 0x800000 /* W: cache write-through */
+
+/* "Higher level" linux bit combinations */
+#define _PAGE_EXEC _PAGE_BAP_SX /* Can be executed from potentially */
+#define _PAGE_HWEXEC _PAGE_BAP_UX /* .. and was cache cleaned */
+#define _PAGE_RW (_PAGE_BAP_SW | _PAGE_BAP_UW) /* User write permission */
+#define _PAGE_KERNEL_RW (_PAGE_BAP_SW | _PAGE_BAP_SR | _PAGE_DIRTY)
+#define _PAGE_KERNEL_RO (_PAGE_BAP_SR)
+#define _PAGE_USER (_PAGE_BAP_UR | _PAGE_BAP_SR) /* Can be read */
+
+#define _PAGE_HASHPTE 0
+#define _PAGE_BUSY 0
+
+#define _PAGE_SPECIAL _PAGE_SW0
+
+/* Flags to be preserved on PTE modifications */
+#define _PAGE_HPTEFLAGS _PAGE_BUSY
+
+/* Base page size */
+#ifdef CONFIG_PPC_64K_PAGES
+#define _PAGE_PSIZE _PAGE_PSIZE_64K
+#define PTE_RPN_SHIFT (28)
+#else
+#define _PAGE_PSIZE _PAGE_PSIZE_4K
+#define PTE_RPN_SHIFT (24)
+#endif
+
+/* On 32-bit, we never clear the top part of the PTE */
+#ifdef CONFIG_PPC32
+#define _PTE_NONE_MASK 0xffffffff00000000ULL
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_PTE_FSL_BOOKE_H */
Index: linux-work/arch/powerpc/include/asm/pgtable-ppc64.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/pgtable-ppc64.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/pgtable-ppc64.h 2009-07-24 18:15:35.000000000 +1000
@@ -5,11 +5,6 @@
* the ppc64 hashed page table.
*/
-#ifndef __ASSEMBLY__
-#include <linux/stddef.h>
-#include <asm/tlbflush.h>
-#endif /* __ASSEMBLY__ */
-
#ifdef CONFIG_PPC_64K_PAGES
#include <asm/pgtable-ppc64-64k.h>
#else
@@ -38,26 +33,46 @@
#endif
/*
- * Define the address range of the vmalloc VM area.
+ * Define the address range of the kernel non-linear virtual area
+ */
+
+#ifdef CONFIG_PPC_BOOK3E
+#define KERN_VIRT_START ASM_CONST(0x8000000000000000)
+#else
+#define KERN_VIRT_START ASM_CONST(0xD000000000000000)
+#endif
+#define KERN_VIRT_SIZE PGTABLE_RANGE
+
+/*
+ * The vmalloc space starts at the beginning of that region, and
+ * occupies half of it on hash CPUs and a quarter of it on Book3E
*/
-#define VMALLOC_START ASM_CONST(0xD000000000000000)
-#define VMALLOC_SIZE (PGTABLE_RANGE >> 1)
-#define VMALLOC_END (VMALLOC_START + VMALLOC_SIZE)
+#define VMALLOC_START KERN_VIRT_START
+#ifdef CONFIG_PPC_BOOK3E
+#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 2)
+#else
+#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1)
+#endif
+#define VMALLOC_END (VMALLOC_START + VMALLOC_SIZE)
/*
- * Define the address ranges for MMIO and IO space :
+ * The second half of the kernel virtual space is used for IO mappings,
+ * it's itself carved into the PIO region (ISA and PHB IO space) and
+ * the ioremap space
*
- * ISA_IO_BASE = VMALLOC_END, 64K reserved area
+ * ISA_IO_BASE = KERN_IO_START, 64K reserved area
* PHB_IO_BASE = ISA_IO_BASE + 64K to ISA_IO_BASE + 2G, PHB IO spaces
* IOREMAP_BASE = ISA_IO_BASE + 2G to VMALLOC_START + PGTABLE_RANGE
*/
+#define KERN_IO_START (KERN_VIRT_START + (KERN_VIRT_SIZE >> 1))
#define FULL_IO_SIZE 0x80000000ul
-#define ISA_IO_BASE (VMALLOC_END)
-#define ISA_IO_END (VMALLOC_END + 0x10000ul)
+#define ISA_IO_BASE (KERN_IO_START)
+#define ISA_IO_END (KERN_IO_START + 0x10000ul)
#define PHB_IO_BASE (ISA_IO_END)
-#define PHB_IO_END (VMALLOC_END + FULL_IO_SIZE)
+#define PHB_IO_END (KERN_IO_START + FULL_IO_SIZE)
#define IOREMAP_BASE (PHB_IO_END)
-#define IOREMAP_END (VMALLOC_START + PGTABLE_RANGE)
+#define IOREMAP_END (KERN_VIRT_START + KERN_VIRT_SIZE)
+
/*
* Region IDs
@@ -72,19 +87,28 @@
#define USER_REGION_ID (0UL)
/*
- * Defines the address of the vmemap area, in its own region
+ * Defines the address of the vmemap area, in its own region on
+ * hash table CPUs and after the vmalloc space on Book3E
*/
+#ifdef CONFIG_PPC_BOOK3E
+#define VMEMMAP_BASE VMALLOC_END
+#define VMEMMAP_END KERN_IO_START
+#else
#define VMEMMAP_BASE (VMEMMAP_REGION_ID << REGION_SHIFT)
+#endif
#define vmemmap ((struct page *)VMEMMAP_BASE)
/*
* Include the PTE bits definitions
*/
+#ifdef CONFIG_PPC_BOOK3S
#include <asm/pte-hash64.h>
+#else
+#include <asm/pte-book3e.h>
+#endif
#include <asm/pte-common.h>
-
#ifdef CONFIG_PPC_MM_SLICES
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
@@ -92,6 +116,9 @@
#ifndef __ASSEMBLY__
+#include <linux/stddef.h>
+#include <asm/tlbflush.h>
+
/*
* This is the default implementation of various PTE accessors, it's
* used in all cases except Book3S with 64K pages where we have a
Index: linux-work/arch/powerpc/include/asm/pte-common.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/pte-common.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/pte-common.h 2009-07-24 18:14:49.000000000 +1000
@@ -34,6 +34,9 @@
#ifndef _PAGE_4K_PFN
#define _PAGE_4K_PFN 0
#endif
+#ifndef _PAGE_SAO
+#define _PAGE_SAO 0
+#endif
#ifndef _PAGE_PSIZE
#define _PAGE_PSIZE 0
#endif
Index: linux-work/arch/powerpc/include/asm/mmu-book3e.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/mmu-book3e.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/mmu-book3e.h 2009-07-24 18:15:35.000000000 +1000
@@ -170,6 +170,33 @@ typedef struct {
unsigned int active;
unsigned long vdso_base;
} mm_context_t;
+
+/* Page size definitions, common between 32 and 64-bit
+ *
+ * shift : is the "PAGE_SHIFT" value for that page size
+ * penc : is the pte encoding mask
+ *
+ */
+struct mmu_psize_def
+{
+ unsigned int shift; /* number of bits */
+ unsigned int enc; /* PTE encoding */
+};
+extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
+
+/* The page sizes use the same names as 64-bit hash but are
+ * constants
+ */
+#if defined(CONFIG_PPC_4K_PAGES)
+#define mmu_virtual_psize MMU_PAGE_4K
+#elif defined(CONFIG_PPC_64K_PAGES)
+#define mmu_virtual_psize MMU_PAGE_64K
+#else
+#error Unsupported page size
+#endif
+
+extern int mmu_linear_psize;
+
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_POWERPC_MMU_BOOK3E_H_ */
Index: linux-work/arch/powerpc/include/asm/page_64.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/page_64.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/page_64.h 2009-07-24 18:14:49.000000000 +1000
@@ -135,12 +135,22 @@ extern void slice_set_range_psize(struct
#endif /* __ASSEMBLY__ */
#else
#define slice_init()
+#ifdef CONFIG_PPC_STD_MMU_64
#define get_slice_psize(mm, addr) ((mm)->context.user_psize)
#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)
+#else /* CONFIG_PPC_STD_MMU_64 */
+#ifdef CONFIG_PPC_64K_PAGES
+#define get_slice_psize(mm, addr) MMU_PAGE_64K
+#else /* CONFIG_PPC_64K_PAGES */
+#define get_slice_psize(mm, addr) MMU_PAGE_4K
+#endif /* !CONFIG_PPC_64K_PAGES */
+#define slice_set_user_psize(mm, psize) do { BUG(); } while(0)
+#endif /* !CONFIG_PPC_STD_MMU_64 */
+
#define slice_set_range_psize(mm, start, len, psize) \
slice_set_user_psize((mm), (psize))
#define slice_mm_new_context(mm) 1
Index: linux-work/arch/powerpc/include/asm/mmu.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/mmu.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/mmu.h 2009-07-24 18:21:12.000000000 +1000
@@ -17,6 +17,7 @@
#define MMU_FTR_TYPE_40x ASM_CONST(0x00000004)
#define MMU_FTR_TYPE_44x ASM_CONST(0x00000008)
#define MMU_FTR_TYPE_FSL_E ASM_CONST(0x00000010)
+#define MMU_FTR_TYPE_3E ASM_CONST(0x00000020)
/*
* This is individual features
@@ -73,6 +74,36 @@ extern void early_init_mmu_secondary(voi
#endif /* !__ASSEMBLY__ */
+/* The kernel use the constants below to index in the page sizes array.
+ * The use of fixed constants for this purpose is better for performances
+ * of the low level hash refill handlers.
+ *
+ * A non supported page size has a "shift" field set to 0
+ *
+ * Any new page size being implemented can get a new entry in here. Whether
+ * the kernel will use it or not is a different matter though. The actual page
+ * size used by hugetlbfs is not defined here and may be made variable
+ *
+ * Note: This array ended up being a false good idea as it's growing to the
+ * point where I wonder if we should replace it with something different,
+ * to think about, feedback welcome. --BenH.
+ */
+
+/* There are #define as they have to be used in assembly */
+#define MMU_PAGE_4K 0
+#define MMU_PAGE_16K 1
+#define MMU_PAGE_64K 2
+#define MMU_PAGE_64K_AP 3 /* "Admixed pages" (hash64 only) */
+#define MMU_PAGE_256K 4
+#define MMU_PAGE_1M 5
+#define MMU_PAGE_8M 6
+#define MMU_PAGE_16M 7
+#define MMU_PAGE_256M 8
+#define MMU_PAGE_1G 9
+#define MMU_PAGE_16G 10
+#define MMU_PAGE_64G 11
+#define MMU_PAGE_COUNT 12
+
#if defined(CONFIG_PPC_STD_MMU_64)
/* 64-bit classic hash table MMU */
@@ -94,5 +125,6 @@ extern void early_init_mmu_secondary(voi
# include <asm/mmu-8xx.h>
#endif
+
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_MMU_H_ */
Index: linux-work/arch/powerpc/kernel/asm-offsets.c
===================================================================
--- linux-work.orig/arch/powerpc/kernel/asm-offsets.c 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/kernel/asm-offsets.c 2009-07-24 18:19:55.000000000 +1000
@@ -52,9 +52,11 @@
#include <linux/kvm_host.h>
#endif
+#ifdef CONFIG_PPC32
#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
#include "head_booke.h"
#endif
+#endif
#if defined(CONFIG_FSL_BOOKE)
#include "../mm/mmu_decl.h"
@@ -260,6 +262,7 @@ int main(void)
DEFINE(_SRR1, STACK_FRAME_OVERHEAD+sizeof(struct pt_regs)+8);
#endif /* CONFIG_PPC64 */
+#if defined(CONFIG_PPC32)
#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
DEFINE(EXC_LVL_SIZE, STACK_EXC_LVL_FRAME_SIZE);
DEFINE(MAS0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0));
@@ -278,7 +281,7 @@ int main(void)
DEFINE(_DSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr1));
DEFINE(SAVED_KSP_LIMIT, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, saved_ksp_limit));
#endif
-
+#endif
DEFINE(CLONE_VM, CLONE_VM);
DEFINE(CLONE_UNTRACED, CLONE_UNTRACED);
Index: linux-work/arch/powerpc/include/asm/page.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/page.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/page.h 2009-07-24 18:14:49.000000000 +1000
@@ -139,7 +139,11 @@ extern phys_addr_t kernstart_addr;
* Don't compare things with KERNELBASE or PAGE_OFFSET to test for
* "kernelness", use is_kernel_addr() - it should do what you want.
*/
+#ifdef CONFIG_PPC_BOOK3E_64
+#define is_kernel_addr(x) ((x) >= 0x8000000000000000ul)
+#else
#define is_kernel_addr(x) ((x) >= PAGE_OFFSET)
+#endif
#ifndef __ASSEMBLY__
Index: linux-work/arch/powerpc/include/asm/mmu-hash64.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/mmu-hash64.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/mmu-hash64.h 2009-07-24 18:14:49.000000000 +1000
@@ -139,26 +139,6 @@ struct mmu_psize_def
#endif /* __ASSEMBLY__ */
/*
- * The kernel use the constants below to index in the page sizes array.
- * The use of fixed constants for this purpose is better for performances
- * of the low level hash refill handlers.
- *
- * A non supported page size has a "shift" field set to 0
- *
- * Any new page size being implemented can get a new entry in here. Whether
- * the kernel will use it or not is a different matter though. The actual page
- * size used by hugetlbfs is not defined here and may be made variable
- */
-
-#define MMU_PAGE_4K 0 /* 4K */
-#define MMU_PAGE_64K 1 /* 64K */
-#define MMU_PAGE_64K_AP 2 /* 64K Admixed (in a 4K segment) */
-#define MMU_PAGE_1M 3 /* 1M */
-#define MMU_PAGE_16M 4 /* 16M */
-#define MMU_PAGE_16G 5 /* 16G */
-#define MMU_PAGE_COUNT 6
-
-/*
* Segment sizes.
* These are the values used by hardware in the B field of
* SLB entries and the first dword of MMU hashtable entries.
^ permalink raw reply
* [PATCH 13/20] powerpc: Add SPR definitions for new 64-bit BookE (v2)
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
This adds various SPRs defined on 64-bit BookE, along with changes
to the definition of the base MSR values to add the values needed
for 64-bit Book3E.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
v2. Remove trailing whitespace and add comments about the EPCR bits
Don't break 8xx due to missing MSR_USER definition
arch/powerpc/include/asm/reg.h | 10 ++------
arch/powerpc/include/asm/reg_booke.h | 42 ++++++++++++++++++++++++++++++++---
2 files changed, 42 insertions(+), 10 deletions(-)
--- linux-work.orig/arch/powerpc/include/asm/reg.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/reg.h 2009-07-24 18:40:53.000000000 +1000
@@ -98,19 +98,15 @@
#define MSR_RI __MASK(MSR_RI_LG) /* Recoverable Exception */
#define MSR_LE __MASK(MSR_LE_LG) /* Little Endian */
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC_BOOK3S_64)
+/* Server variant */
#define MSR_ MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_ISF |MSR_HV
#define MSR_KERNEL MSR_ | MSR_SF
-
#define MSR_USER32 MSR_ | MSR_PR | MSR_EE
#define MSR_USER64 MSR_USER32 | MSR_SF
-
-#else /* 32-bit */
+#elif defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_8xx)
/* Default MSR for kernel mode. */
-#ifndef MSR_KERNEL /* reg_booke.h also defines this */
#define MSR_KERNEL (MSR_ME|MSR_RI|MSR_IR|MSR_DR)
-#endif
-
#define MSR_USER (MSR_KERNEL|MSR_PR|MSR_EE)
#endif
Index: linux-work/arch/powerpc/include/asm/reg_booke.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/reg_booke.h 2009-07-24 18:14:35.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/reg_booke.h 2009-07-24 18:14:47.000000000 +1000
@@ -18,18 +18,26 @@
#define MSR_IS MSR_IR /* Instruction Space */
#define MSR_DS MSR_DR /* Data Space */
#define MSR_PMM (1<<2) /* Performance monitor mark bit */
+#define MSR_CM (1<<31) /* Computation Mode (0=32-bit, 1=64-bit) */
-/* Default MSR for kernel mode. */
-#if defined (CONFIG_40x)
+#if defined(CONFIG_PPC_BOOK3E_64)
+#define MSR_ MSR_ME | MSR_CE
+#define MSR_KERNEL MSR_ | MSR_CM
+#define MSR_USER32 MSR_ | MSR_PR | MSR_EE
+#define MSR_USER64 MSR_USER32 | MSR_CM
+#elif defined (CONFIG_40x)
#define MSR_KERNEL (MSR_ME|MSR_RI|MSR_IR|MSR_DR|MSR_CE)
-#elif defined(CONFIG_BOOKE)
+#define MSR_USER (MSR_KERNEL|MSR_PR|MSR_EE)
+#else
#define MSR_KERNEL (MSR_ME|MSR_RI|MSR_CE)
+#define MSR_USER (MSR_KERNEL|MSR_PR|MSR_EE)
#endif
/* Special Purpose Registers (SPRNs)*/
#define SPRN_DECAR 0x036 /* Decrementer Auto Reload Register */
#define SPRN_IVPR 0x03F /* Interrupt Vector Prefix Register */
#define SPRN_USPRG0 0x100 /* User Special Purpose Register General 0 */
+#define SPRN_SPRG3R 0x103 /* Special Purpose Register General 3 Read */
#define SPRN_SPRG4R 0x104 /* Special Purpose Register General 4 Read */
#define SPRN_SPRG5R 0x105 /* Special Purpose Register General 5 Read */
#define SPRN_SPRG6R 0x106 /* Special Purpose Register General 6 Read */
@@ -38,11 +46,18 @@
#define SPRN_SPRG5W 0x115 /* Special Purpose Register General 5 Write */
#define SPRN_SPRG6W 0x116 /* Special Purpose Register General 6 Write */
#define SPRN_SPRG7W 0x117 /* Special Purpose Register General 7 Write */
+#define SPRN_EPCR 0x133 /* Embedded Processor Control Register */
#define SPRN_DBCR2 0x136 /* Debug Control Register 2 */
#define SPRN_IAC3 0x13A /* Instruction Address Compare 3 */
#define SPRN_IAC4 0x13B /* Instruction Address Compare 4 */
#define SPRN_DVC1 0x13E /* Data Value Compare Register 1 */
#define SPRN_DVC2 0x13F /* Data Value Compare Register 2 */
+#define SPRN_MAS8 0x155 /* MMU Assist Register 8 */
+#define SPRN_TLB0PS 0x158 /* TLB 0 Page Size Register */
+#define SPRN_MAS5_MAS6 0x15c /* MMU Assist Register 5 || 6 */
+#define SPRN_MAS8_MAS1 0x15d /* MMU Assist Register 8 || 1 */
+#define SPRN_MAS7_MAS3 0x174 /* MMU Assist Register 7 || 3 */
+#define SPRN_MAS0_MAS1 0x175 /* MMU Assist Register 0 || 1 */
#define SPRN_IVOR0 0x190 /* Interrupt Vector Offset Register 0 */
#define SPRN_IVOR1 0x191 /* Interrupt Vector Offset Register 1 */
#define SPRN_IVOR2 0x192 /* Interrupt Vector Offset Register 2 */
@@ -425,6 +440,27 @@
#define SGR_NORMAL 0 /* Speculative fetching allowed. */
#define SGR_GUARDED 1 /* Speculative fetching disallowed. */
+/* Bit definitions for EPCR */
+#define SPRN_EPCR_EXTGS 0x80000000 /* External Input interrupt
+ * directed to Guest state */
+#define SPRN_EPCR_DTLBGS 0x40000000 /* Data TLB Error interrupt
+ * directed to guest state */
+#define SPRN_EPCR_ITLBGS 0x20000000 /* Instr. TLB error interrupt
+ * directed to guest state */
+#define SPRN_EPCR_DSIGS 0x10000000 /* Data Storage interrupt
+ * directed to guest state */
+#define SPRN_EPCR_ISIGS 0x08000000 /* Instr. Storage interrupt
+ * directed to guest state */
+#define SPRN_EPCR_DUVD 0x04000000 /* Disable Hypervisor Debug */
+#define SPRN_EPCR_ICM 0x02000000 /* Interrupt computation mode
+ * (copied to MSR:CM on intr) */
+#define SPRN_EPCR_GICM 0x01000000 /* Guest Interrupt Comp. mode */
+#define SPRN_EPCR_DGTMI 0x00800000 /* Disable TLB Guest Management
+ * instructions */
+#define SPRN_EPCR_DMIUH 0x00400000 /* Disable MAS Interrupt updates
+ * for hypervisor */
+
+
/*
* The IBM-403 is an even more odd special case, as it is much
* older than the IBM-405 series. We put these down here incase someone
^ permalink raw reply
* [PATCH 12/20] powerpc/mm: Rework & cleanup page table freeing code path
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
That patch used to just add a hook to page table flushing but
pulling that string brought out a whole bunch of issues, so it
now does that and more:
- We now make the RCU batching of page freeing SMP only, as I
believe it was intended initially. We make a few more things compile
to nothing on !CONFIG_SMP
- Some macros are turned into functions, though that forced me to
out of line a few stuffs due to unsolvable include depenencies,
however it's probably better that way anyway, it's not -that-
critical code path.
- 32-bit didn't call pte_free_finish() on tlb_flush() which means
that it wouldn't push out the batch to RCU for delayed freeing when
a bunch of page tables have been freed, they would just stay in there
until the batch gets full.
64-bit BookE will use that hook to maintain the virtually linear
page tables or the indirect entries in the TLB when using the
HW loader.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/include/asm/pgalloc.h | 39 ++++++++++++++++++++++++++-----------
arch/powerpc/include/asm/tlb.h | 38 ++----------------------------------
arch/powerpc/mm/pgtable.c | 10 +++++++++
arch/powerpc/mm/tlb_hash32.c | 3 ++
arch/powerpc/mm/tlb_hash64.c | 15 ++++++++++++++
arch/powerpc/mm/tlb_nohash.c | 8 +++++++
6 files changed, 67 insertions(+), 46 deletions(-)
--- linux-work.orig/arch/powerpc/include/asm/pgalloc.h 2009-07-24 17:39:52.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/pgalloc.h 2009-07-24 17:41:40.000000000 +1000
@@ -4,6 +4,15 @@
#include <linux/mm.h>
+#ifdef CONFIG_PPC_BOOK3E
+extern void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address);
+#else /* CONFIG_PPC_BOOK3E */
+static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
+ unsigned long address)
+{
+}
+#endif /* !CONFIG_PPC_BOOK3E */
+
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
{
free_page((unsigned long)pte);
@@ -35,19 +44,27 @@ static inline pgtable_free_t pgtable_fre
#include <asm/pgalloc-32.h>
#endif
-extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
-
#ifdef CONFIG_SMP
-#define __pte_free_tlb(tlb,ptepage,address) \
-do { \
- pgtable_page_dtor(ptepage); \
- pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
- PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1)); \
-} while (0)
-#else
-#define __pte_free_tlb(tlb, pte, address) pte_free((tlb)->mm, (pte))
-#endif
+extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
+extern void pte_free_finish(void);
+#else /* CONFIG_SMP */
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf)
+{
+ pgtable_free(pgf);
+}
+static inline void pte_free_finish(void) { }
+#endif /* !CONFIG_SMP */
+static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
+ unsigned long address)
+{
+ pgtable_free_t pgf = pgtable_free_cache(page_address(ptepage),
+ PTE_NONCACHE_NUM,
+ PTE_TABLE_SIZE-1);
+ tlb_flush_pgtable(tlb, address);
+ pgtable_page_dtor(ptepage);
+ pgtable_free_tlb(tlb, pgf);
+}
#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_PGALLOC_H */
Index: linux-work/arch/powerpc/include/asm/tlb.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/tlb.h 2009-07-24 17:39:52.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/tlb.h 2009-07-24 17:41:40.000000000 +1000
@@ -25,57 +25,25 @@
#include <linux/pagemap.h>
-struct mmu_gather;
-
#define tlb_start_vma(tlb, vma) do { } while (0)
#define tlb_end_vma(tlb, vma) do { } while (0)
-#if !defined(CONFIG_PPC_STD_MMU)
-
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
-#elif defined(__powerpc64__)
-
-extern void pte_free_finish(void);
-
-static inline void tlb_flush(struct mmu_gather *tlb)
-{
- struct ppc64_tlb_batch *tlbbatch = &__get_cpu_var(ppc64_tlb_batch);
-
- /* If there's a TLB batch pending, then we must flush it because the
- * pages are going to be freed and we really don't want to have a CPU
- * access a freed page because it has a stale TLB
- */
- if (tlbbatch->index)
- __flush_tlb_pending(tlbbatch);
-
- pte_free_finish();
-}
-
-#else
-
extern void tlb_flush(struct mmu_gather *tlb);
-#endif
-
/* Get the generic bits... */
#include <asm-generic/tlb.h>
-#if !defined(CONFIG_PPC_STD_MMU) || defined(__powerpc64__)
-
-#define __tlb_remove_tlb_entry(tlb, pte, address) do { } while (0)
-
-#else
extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep,
unsigned long address);
static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
- unsigned long address)
+ unsigned long address)
{
+#ifdef PPC_STD_MMU_32
if (pte_val(*ptep) & _PAGE_HASHPTE)
flush_hash_entry(tlb->mm, ptep, address);
+#endif
}
-#endif
#endif /* __KERNEL__ */
#endif /* __ASM_POWERPC_TLB_H */
Index: linux-work/arch/powerpc/mm/pgtable.c
===================================================================
--- linux-work.orig/arch/powerpc/mm/pgtable.c 2009-07-24 17:39:52.000000000 +1000
+++ linux-work/arch/powerpc/mm/pgtable.c 2009-07-24 17:41:40.000000000 +1000
@@ -30,6 +30,14 @@
#include <asm/tlbflush.h>
#include <asm/tlb.h>
+#ifdef CONFIG_SMP
+
+/*
+ * Handle batching of page table freeing on SMP. Page tables are
+ * queued up and send to be freed later by RCU in order to avoid
+ * freeing a page table page that is being walked without locks
+ */
+
static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
static unsigned long pte_freelist_forced_free;
@@ -116,6 +124,8 @@ void pte_free_finish(void)
*batchp = NULL;
}
+#endif /* CONFIG_SMP */
+
/*
* Handle i/d cache flushing, called from set_pte_at() or ptep_set_access_flags()
*/
Index: linux-work/arch/powerpc/mm/tlb_hash32.c
===================================================================
--- linux-work.orig/arch/powerpc/mm/tlb_hash32.c 2009-07-24 17:39:52.000000000 +1000
+++ linux-work/arch/powerpc/mm/tlb_hash32.c 2009-07-24 17:41:40.000000000 +1000
@@ -71,6 +71,9 @@ void tlb_flush(struct mmu_gather *tlb)
*/
_tlbia();
}
+
+ /* Push out batch of freed page tables */
+ pte_free_finish();
}
/*
Index: linux-work/arch/powerpc/mm/tlb_hash64.c
===================================================================
--- linux-work.orig/arch/powerpc/mm/tlb_hash64.c 2009-07-24 17:39:52.000000000 +1000
+++ linux-work/arch/powerpc/mm/tlb_hash64.c 2009-07-24 17:41:40.000000000 +1000
@@ -154,6 +154,21 @@ void __flush_tlb_pending(struct ppc64_tl
batch->index = 0;
}
+void tlb_flush(struct mmu_gather *tlb)
+{
+ struct ppc64_tlb_batch *tlbbatch = &__get_cpu_var(ppc64_tlb_batch);
+
+ /* If there's a TLB batch pending, then we must flush it because the
+ * pages are going to be freed and we really don't want to have a CPU
+ * access a freed page because it has a stale TLB
+ */
+ if (tlbbatch->index)
+ __flush_tlb_pending(tlbbatch);
+
+ /* Push out batch of freed page tables */
+ pte_free_finish();
+}
+
/**
* __flush_hash_table_range - Flush all HPTEs for a given address range
* from the hash table (and the TLB). But keeps
Index: linux-work/arch/powerpc/mm/tlb_nohash.c
===================================================================
--- linux-work.orig/arch/powerpc/mm/tlb_nohash.c 2009-07-24 17:41:33.000000000 +1000
+++ linux-work/arch/powerpc/mm/tlb_nohash.c 2009-07-24 17:41:40.000000000 +1000
@@ -233,3 +233,11 @@ void flush_tlb_range(struct vm_area_stru
flush_tlb_mm(vma->vm_mm);
}
EXPORT_SYMBOL(flush_tlb_range);
+
+void tlb_flush(struct mmu_gather *tlb)
+{
+ flush_tlb_mm(tlb->mm);
+
+ /* Push out batch of freed page tables */
+ pte_free_finish();
+}
^ permalink raw reply
* [PATCH 11/20] powerpc: Move definitions of secondary CPU spinloop to header file (v2)
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
Those definitions are currently declared extern in the .c file where
they are used, move them to a header file instead.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
--
v2. Move more definitions to the header and update more call sites
arch/powerpc/include/asm/smp.h | 9 +++++++++
arch/powerpc/kernel/prom_init.c | 4 ----
arch/powerpc/kernel/setup_64.c | 3 ---
arch/powerpc/platforms/85xx/smp.c | 1 -
arch/powerpc/platforms/86xx/mpc86xx_smp.c | 1 -
arch/powerpc/platforms/cell/smp.c | 2 --
arch/powerpc/platforms/pseries/smp.c | 2 --
7 files changed, 9 insertions(+), 13 deletions(-)
--- linux-work.orig/arch/powerpc/include/asm/smp.h 2009-07-24 15:31:07.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/smp.h 2009-07-24 16:03:50.000000000 +1000
@@ -148,6 +148,15 @@ extern struct smp_ops_t *smp_ops;
extern void arch_send_call_function_single_ipi(int cpu);
extern void arch_send_call_function_ipi(cpumask_t mask);
+/* Definitions relative to the secondary CPU spin loop
+ * and entry point. Not all of them exist on both 32 and
+ * 64-bit but defining them all here doesn't harm
+ */
+extern void generic_secondary_smp_init(void);
+extern unsigned long __secondary_hold_spinloop;
+extern unsigned long __secondary_hold_acknowledge;
+extern char __secondary_hold;
+
#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
Index: linux-work/arch/powerpc/kernel/setup_64.c
===================================================================
--- linux-work.orig/arch/powerpc/kernel/setup_64.c 2009-07-24 15:32:37.000000000 +1000
+++ linux-work/arch/powerpc/kernel/setup_64.c 2009-07-24 15:57:00.000000000 +1000
@@ -230,9 +230,6 @@ void early_setup_secondary(void)
#endif /* CONFIG_SMP */
#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
-extern unsigned long __secondary_hold_spinloop;
-extern void generic_secondary_smp_init(void);
-
void smp_release_cpus(void)
{
unsigned long *ptr;
Index: linux-work/arch/powerpc/kernel/prom_init.c
===================================================================
--- linux-work.orig/arch/powerpc/kernel/prom_init.c 2009-07-24 16:01:44.000000000 +1000
+++ linux-work/arch/powerpc/kernel/prom_init.c 2009-07-24 16:02:27.000000000 +1000
@@ -1259,10 +1259,6 @@ static void __init prom_initialize_tce_t
*
* -- Cort
*/
-extern char __secondary_hold;
-extern unsigned long __secondary_hold_spinloop;
-extern unsigned long __secondary_hold_acknowledge;
-
/*
* We want to reference the copy of __secondary_hold_* in the
* 0 - 0x100 address range
Index: linux-work/arch/powerpc/platforms/85xx/smp.c
===================================================================
--- linux-work.orig/arch/powerpc/platforms/85xx/smp.c 2009-07-24 16:02:47.000000000 +1000
+++ linux-work/arch/powerpc/platforms/85xx/smp.c 2009-07-24 16:02:54.000000000 +1000
@@ -25,7 +25,6 @@
#include <sysdev/fsl_soc.h>
-extern volatile unsigned long __secondary_hold_acknowledge;
extern void __early_start(void);
#define BOOT_ENTRY_ADDR_UPPER 0
Index: linux-work/arch/powerpc/platforms/86xx/mpc86xx_smp.c
===================================================================
--- linux-work.orig/arch/powerpc/platforms/86xx/mpc86xx_smp.c 2009-07-24 16:03:06.000000000 +1000
+++ linux-work/arch/powerpc/platforms/86xx/mpc86xx_smp.c 2009-07-24 16:03:11.000000000 +1000
@@ -27,7 +27,6 @@
#include "mpc86xx.h"
extern void __secondary_start_mpc86xx(void);
-extern unsigned long __secondary_hold_acknowledge;
#define MCM_PORT_CONFIG_OFFSET 0x10
Index: linux-work/arch/powerpc/platforms/cell/smp.c
===================================================================
--- linux-work.orig/arch/powerpc/platforms/cell/smp.c 2009-07-24 16:00:37.000000000 +1000
+++ linux-work/arch/powerpc/platforms/cell/smp.c 2009-07-24 16:00:56.000000000 +1000
@@ -58,8 +58,6 @@
*/
static cpumask_t of_spin_map;
-extern void generic_secondary_smp_init(unsigned long);
-
/**
* smp_startup_cpu() - start the given cpu
*
Index: linux-work/arch/powerpc/platforms/pseries/smp.c
===================================================================
--- linux-work.orig/arch/powerpc/platforms/pseries/smp.c 2009-07-24 16:01:23.000000000 +1000
+++ linux-work/arch/powerpc/platforms/pseries/smp.c 2009-07-24 16:01:25.000000000 +1000
@@ -56,8 +56,6 @@
*/
static cpumask_t of_spin_map;
-extern void generic_secondary_smp_init(unsigned long);
-
/**
* smp_startup_cpu() - start the given cpu
*
^ permalink raw reply
* [PATCH 10/20] powerpc: Clean ifdef usage in copy_thread()
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
Currently, a single ifdef covers SLB related bits and more generic ppc64
related bits, split this in two separate ifdef's since 64-bit BookE will
need one but not the other.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/kernel/process.c | 2 ++
1 file changed, 2 insertions(+)
--- linux-work.orig/arch/powerpc/kernel/process.c 2009-07-22 16:30:49.000000000 +1000
+++ linux-work/arch/powerpc/kernel/process.c 2009-07-22 16:31:02.000000000 +1000
@@ -664,6 +664,7 @@ int copy_thread(unsigned long clone_flag
sp_vsid |= SLB_VSID_KERNEL | llp;
p->thread.ksp_vsid = sp_vsid;
}
+#endif /* CONFIG_PPC_STD_MMU_64 */
/*
* The PPC64 ABI makes use of a TOC to contain function
@@ -671,6 +672,7 @@ int copy_thread(unsigned long clone_flag
* to the TOC entry. The first entry is a pointer to the actual
* function.
*/
+#ifdef CONFIG_PPC64
kregs->nip = *((unsigned long *)ret_from_fork);
#else
kregs->nip = (unsigned long)ret_from_fork;
^ permalink raw reply
* [PATCH 9/20] powerpc/mm: Call mmu_context_init() from ppc64 (v2)
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
Our 64-bit hash context handling has no init function, but 64-bit Book3E
will use the common mmu_context_nohash.c code which does, so define an
empty inline mmu_context_init() for 64-bit server and call it from
our 64-bit setup_arch()
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Kumar Gala <galak@kernel.crashing.org>
---
v2. Remove whitespace addition to mmu_context_hash64.c
arch/powerpc/include/asm/mmu_context.h | 7 ++++++-
arch/powerpc/kernel/setup_64.c | 4 ++++
2 files changed, 10 insertions(+), 1 deletion(-)
--- linux-work.orig/arch/powerpc/include/asm/mmu_context.h 2009-07-22 16:25:25.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/mmu_context.h 2009-07-22 16:25:50.000000000 +1000
@@ -14,7 +14,6 @@
/*
* Most if the context management is out of line
*/
-extern void mmu_context_init(void);
extern int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
extern void destroy_context(struct mm_struct *mm);
@@ -23,6 +22,12 @@ extern void switch_stab(struct task_stru
extern void switch_slb(struct task_struct *tsk, struct mm_struct *mm);
extern void set_context(unsigned long id, pgd_t *pgd);
+#ifdef CONFIG_PPC_BOOK3S_64
+static inline void mmu_context_init(void) { }
+#else
+extern void mmu_context_init(void);
+#endif
+
/*
* switch_mm is the entry point called from the architecture independent
* code in kernel/sched.c
Index: linux-work/arch/powerpc/kernel/setup_64.c
===================================================================
--- linux-work.orig/arch/powerpc/kernel/setup_64.c 2009-07-22 16:26:23.000000000 +1000
+++ linux-work/arch/powerpc/kernel/setup_64.c 2009-07-22 16:26:31.000000000 +1000
@@ -534,6 +534,10 @@ void __init setup_arch(char **cmdline_p)
#endif
paging_init();
+
+ /* Initialize the MMU context management stuff */
+ mmu_context_init();
+
ppc64_boot_msg(0x15, "Setup Done");
}
^ permalink raw reply
* [PATCH 8/20] powerpc/mm: Make low level TLB flush ops on BookE take additional args (v2)
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
We need to pass down whether the page is direct or indirect and we'll
need to pass the page size to _tlbil_va and _tlbivax_bcast
We also add a new low level _tlbil_pid_noind() which does a TLB flush
by PID but avoids flushing indirect entries if possible
This implements those new prototypes but defines them with inlines
or macros so that no additional arguments are actually passed on current
processors.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
v2. __tlbil_va() declaration had the wrong number of arguments
also remove a stray trailing semicolon
arch/powerpc/include/asm/tlbflush.h | 11 +++++++--
arch/powerpc/mm/mmu_decl.h | 16 +++++++++++--
arch/powerpc/mm/tlb_nohash.c | 42 ++++++++++++++++++++++++++----------
arch/powerpc/mm/tlb_nohash_low.S | 6 ++---
4 files changed, 56 insertions(+), 19 deletions(-)
--- linux-work.orig/arch/powerpc/include/asm/tlbflush.h 2009-07-24 16:24:08.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/tlbflush.h 2009-07-24 16:24:12.000000000 +1000
@@ -6,7 +6,7 @@
*
* - flush_tlb_mm(mm) flushes the specified mm context TLB's
* - flush_tlb_page(vma, vmaddr) flushes one page
- * - local_flush_tlb_mm(mm) flushes the specified mm context on
+ * - local_flush_tlb_mm(mm, full) flushes the specified mm context on
* the local processor
* - local_flush_tlb_page(vma, vmaddr) flushes one page on the local processor
* - flush_tlb_page_nohash(vma, vmaddr) flushes one page if SW loaded TLB
@@ -29,7 +29,8 @@
* specific tlbie's
*/
-#include <linux/mm.h>
+struct vm_area_struct;
+struct mm_struct;
#define MMU_NO_CONTEXT ((unsigned int)-1)
@@ -40,12 +41,18 @@ extern void flush_tlb_kernel_range(unsig
extern void local_flush_tlb_mm(struct mm_struct *mm);
extern void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+extern void __local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
+ int tsize, int ind);
+
#ifdef CONFIG_SMP
extern void flush_tlb_mm(struct mm_struct *mm);
extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+extern void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
+ int tsize, int ind);
#else
#define flush_tlb_mm(mm) local_flush_tlb_mm(mm)
#define flush_tlb_page(vma,addr) local_flush_tlb_page(vma,addr)
+#define __flush_tlb_page(mm,addr,p,i) __local_flush_tlb_page(mm,addr,p,i)
#endif
#define flush_tlb_page_nohash(vma,addr) flush_tlb_page(vma,addr)
Index: linux-work/arch/powerpc/mm/mmu_decl.h
===================================================================
--- linux-work.orig/arch/powerpc/mm/mmu_decl.h 2009-07-24 16:24:08.000000000 +1000
+++ linux-work/arch/powerpc/mm/mmu_decl.h 2009-07-24 17:04:57.000000000 +1000
@@ -36,21 +36,30 @@ static inline void _tlbil_pid(unsigned i
{
asm volatile ("sync; tlbia; isync" : : : "memory");
}
+#define _tlbil_pid_noind(pid) _tlbil_pid(pid)
+
#else /* CONFIG_40x || CONFIG_8xx */
extern void _tlbil_all(void);
extern void _tlbil_pid(unsigned int pid);
+#define _tlbil_pid_noind(pid) _tlbil_pid(pid)
#endif /* !(CONFIG_40x || CONFIG_8xx) */
/*
* On 8xx, we directly inline tlbie, on others, it's extern
*/
#ifdef CONFIG_8xx
-static inline void _tlbil_va(unsigned long address, unsigned int pid)
+static inline void _tlbil_va(unsigned long address, unsigned int pid,
+ unsigned int tsize, unsigned int ind)
{
asm volatile ("tlbie %0; sync" : : "r" (address) : "memory");
}
#else /* CONFIG_8xx */
-extern void _tlbil_va(unsigned long address, unsigned int pid);
+extern void __tlbil_va(unsigned long address, unsigned int pid);
+static inline void _tlbil_va(unsigned long address, unsigned int pid,
+ unsigned int tsize, unsigned int ind)
+{
+ __tlbil_va(address, pid);
+}
#endif /* CONIFG_8xx */
/*
@@ -58,7 +67,8 @@ extern void _tlbil_va(unsigned long addr
* implementation. When that becomes the case, this will be
* an extern.
*/
-static inline void _tlbivax_bcast(unsigned long address, unsigned int pid)
+static inline void _tlbivax_bcast(unsigned long address, unsigned int pid,
+ unsigned int tsize, unsigned int ind)
{
BUG();
}
Index: linux-work/arch/powerpc/mm/tlb_nohash.c
===================================================================
--- linux-work.orig/arch/powerpc/mm/tlb_nohash.c 2009-07-24 16:24:08.000000000 +1000
+++ linux-work/arch/powerpc/mm/tlb_nohash.c 2009-07-24 17:41:33.000000000 +1000
@@ -67,18 +67,24 @@ void local_flush_tlb_mm(struct mm_struct
}
EXPORT_SYMBOL(local_flush_tlb_mm);
-void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+void __local_flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
+ int tsize, int ind)
{
unsigned int pid;
preempt_disable();
- pid = vma ? vma->vm_mm->context.id : 0;
+ pid = mm ? mm->context.id : 0;
if (pid != MMU_NO_CONTEXT)
- _tlbil_va(vmaddr, pid);
+ _tlbil_va(vmaddr, pid, tsize, ind);
preempt_enable();
}
-EXPORT_SYMBOL(local_flush_tlb_page);
+void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+ __local_flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
+ 0 /* tsize unused for now */, 0);
+}
+EXPORT_SYMBOL(local_flush_tlb_page);
/*
* And here are the SMP non-local implementations
@@ -96,6 +102,8 @@ static int mm_is_core_local(struct mm_st
struct tlb_flush_param {
unsigned long addr;
unsigned int pid;
+ unsigned int tsize;
+ unsigned int ind;
};
static void do_flush_tlb_mm_ipi(void *param)
@@ -109,7 +117,7 @@ static void do_flush_tlb_page_ipi(void *
{
struct tlb_flush_param *p = param;
- _tlbil_va(p->addr, p->pid);
+ _tlbil_va(p->addr, p->pid, p->tsize, p->ind);
}
@@ -149,37 +157,49 @@ void flush_tlb_mm(struct mm_struct *mm)
}
EXPORT_SYMBOL(flush_tlb_mm);
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+void __flush_tlb_page(struct mm_struct *mm, unsigned long vmaddr,
+ int tsize, int ind)
{
struct cpumask *cpu_mask;
unsigned int pid;
preempt_disable();
- pid = vma ? vma->vm_mm->context.id : 0;
+ pid = mm ? mm->context.id : 0;
if (unlikely(pid == MMU_NO_CONTEXT))
goto bail;
- cpu_mask = mm_cpumask(vma->vm_mm);
+ cpu_mask = mm_cpumask(mm);
if (!mm_is_core_local(mm)) {
/* If broadcast tlbivax is supported, use it */
if (mmu_has_feature(MMU_FTR_USE_TLBIVAX_BCAST)) {
int lock = mmu_has_feature(MMU_FTR_LOCK_BCAST_INVAL);
if (lock)
spin_lock(&tlbivax_lock);
- _tlbivax_bcast(vmaddr, pid);
+ _tlbivax_bcast(vmaddr, pid, tsize, ind);
if (lock)
spin_unlock(&tlbivax_lock);
goto bail;
} else {
- struct tlb_flush_param p = { .pid = pid, .addr = vmaddr };
+ struct tlb_flush_param p = {
+ .pid = pid,
+ .addr = vmaddr,
+ .tsize = tsize,
+ .ind = ind,
+ };
/* Ignores smp_processor_id() even if set in cpu_mask */
smp_call_function_many(cpu_mask,
do_flush_tlb_page_ipi, &p, 1);
}
}
- _tlbil_va(vmaddr, pid);
+ _tlbil_va(vmaddr, pid, tsize, ind);
bail:
preempt_enable();
}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+ __flush_tlb_page(vma ? vma->vm_mm : NULL, vmaddr,
+ 0 /* tsize unused for now */, 0);
+}
EXPORT_SYMBOL(flush_tlb_page);
#endif /* CONFIG_SMP */
Index: linux-work/arch/powerpc/mm/tlb_nohash_low.S
===================================================================
--- linux-work.orig/arch/powerpc/mm/tlb_nohash_low.S 2009-07-24 16:24:08.000000000 +1000
+++ linux-work/arch/powerpc/mm/tlb_nohash_low.S 2009-07-24 17:04:57.000000000 +1000
@@ -39,7 +39,7 @@
/*
* 40x implementation needs only tlbil_va
*/
-_GLOBAL(_tlbil_va)
+_GLOBAL(__tlbil_va)
/* We run the search with interrupts disabled because we have to change
* the PID and I don't want to preempt when that happens.
*/
@@ -71,7 +71,7 @@ _GLOBAL(_tlbil_va)
* 440 implementation uses tlbsx/we for tlbil_va and a full sweep
* of the TLB for everything else.
*/
-_GLOBAL(_tlbil_va)
+_GLOBAL(__tlbil_va)
mfspr r5,SPRN_MMUCR
rlwimi r5,r4,0,24,31 /* Set TID */
@@ -170,7 +170,7 @@ ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_US
* Flush MMU TLB for a particular address, but only on the local processor
* (no broadcast)
*/
-_GLOBAL(_tlbil_va)
+_GLOBAL(__tlbil_va)
mfmsr r10
wrteei 0
slwi r4,r4,16
^ permalink raw reply
* [PATCH 7/20] powerpc: Modify some ppc_asm.h macros to accomodate 64-bits Book3E
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
The way I intend to use tophys/tovirt on 64-bit BookE is different
from the "trick" that we currently play for 32-bit BookE so change
the condition of definition of these macros to make it so.
Also, make sure we only use rfid and mtmsrd instead of rfi and mtmsr
for 64-bit server processors, not all 64-bit processors.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Kumar Gala <galak@kernel.crashing.org>
---
arch/powerpc/include/asm/ppc_asm.h | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
--- linux-work.orig/arch/powerpc/include/asm/ppc_asm.h 2009-07-22 15:53:06.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/ppc_asm.h 2009-07-22 15:58:24.000000000 +1000
@@ -375,8 +375,15 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
#define PPC440EP_ERR42
#endif
-
-#if defined(CONFIG_BOOKE)
+/*
+ * toreal/fromreal/tophys/tovirt macros. 32-bit BookE makes them
+ * keep the address intact to be compatible with code shared with
+ * 32-bit classic.
+ *
+ * On the other hand, I find it useful to have them behave as expected
+ * by their name (ie always do the addition) on 64-bit BookE
+ */
+#if defined(CONFIG_BOOKE) && !defined(CONFIG_PPC64)
#define toreal(rd)
#define fromreal(rd)
@@ -426,10 +433,9 @@ END_FTR_SECTION_IFCLR(CPU_FTR_601)
.previous
#endif
-#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S_64
#define RFI rfid
#define MTMSRD(r) mtmsrd r
-
#else
#define FIX_SRR1(ra, rb)
#ifndef CONFIG_40x
^ permalink raw reply
* [PATCH 6/20] powerpc/mm: Add support for early ioremap on non-hash 64-bit processors
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
This adds some code to do early ioremap's using page tables instead of
bolting entries in the hash table. This will be used by the upcoming
64-bits BookE port.
The patch also changes the test for early vs. late ioremap to use
slab_is_available() instead of our old hackish mem_init_done.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/mm/pgtable_64.c | 59 +++++++++++++++++++++++++++++++++++++++----
1 file changed, 54 insertions(+), 5 deletions(-)
--- linux-work.orig/arch/powerpc/mm/pgtable_64.c 2009-07-22 15:49:09.000000000 +1000
+++ linux-work/arch/powerpc/mm/pgtable_64.c 2009-07-23 14:56:39.000000000 +1000
@@ -33,6 +33,8 @@
#include <linux/stddef.h>
#include <linux/vmalloc.h>
#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/lmb.h>
#include <asm/pgalloc.h>
#include <asm/page.h>
@@ -55,19 +57,36 @@
unsigned long ioremap_bot = IOREMAP_BASE;
+
+#ifdef CONFIG_PPC_MMU_NOHASH
+static void *early_alloc_pgtable(unsigned long size)
+{
+ void *pt;
+
+ if (init_bootmem_done)
+ pt = __alloc_bootmem(size, size, __pa(MAX_DMA_ADDRESS));
+ else
+ pt = __va(lmb_alloc_base(size, size,
+ __pa(MAX_DMA_ADDRESS)));
+ memset(pt, 0, size);
+
+ return pt;
+}
+#endif /* CONFIG_PPC_MMU_NOHASH */
+
/*
- * map_io_page currently only called by __ioremap
- * map_io_page adds an entry to the ioremap page table
+ * map_kernel_page currently only called by __ioremap
+ * map_kernel_page adds an entry to the ioremap page table
* and adds an entry to the HPT, possibly bolting it
*/
-static int map_io_page(unsigned long ea, unsigned long pa, int flags)
+static int map_kernel_page(unsigned long ea, unsigned long pa, int flags)
{
pgd_t *pgdp;
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
- if (mem_init_done) {
+ if (slab_is_available()) {
pgdp = pgd_offset_k(ea);
pudp = pud_alloc(&init_mm, pgdp, ea);
if (!pudp)
@@ -81,6 +100,35 @@ static int map_io_page(unsigned long ea,
set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
__pgprot(flags)));
} else {
+#ifdef CONFIG_PPC_MMU_NOHASH
+ /* Warning ! This will blow up if bootmem is not initialized
+ * which our ppc64 code is keen to do that, we'll need to
+ * fix it and/or be more careful
+ */
+ pgdp = pgd_offset_k(ea);
+#ifdef PUD_TABLE_SIZE
+ if (pgd_none(*pgdp)) {
+ pudp = early_alloc_pgtable(PUD_TABLE_SIZE);
+ BUG_ON(pudp == NULL);
+ pgd_populate(&init_mm, pgdp, pudp);
+ }
+#endif /* PUD_TABLE_SIZE */
+ pudp = pud_offset(pgdp, ea);
+ if (pud_none(*pudp)) {
+ pmdp = early_alloc_pgtable(PMD_TABLE_SIZE);
+ BUG_ON(pmdp == NULL);
+ pud_populate(&init_mm, pudp, pmdp);
+ }
+ pmdp = pmd_offset(pudp, ea);
+ if (!pmd_present(*pmdp)) {
+ ptep = early_alloc_pgtable(PAGE_SIZE);
+ BUG_ON(ptep == NULL);
+ pmd_populate_kernel(&init_mm, pmdp, ptep);
+ }
+ ptep = pte_offset_kernel(pmdp, ea);
+ set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
+ __pgprot(flags)));
+#else /* CONFIG_PPC_MMU_NOHASH */
/*
* If the mm subsystem is not fully up, we cannot create a
* linux page table entry for this mapping. Simply bolt an
@@ -93,6 +141,7 @@ static int map_io_page(unsigned long ea,
"memory at %016lx !\n", pa);
return -ENOMEM;
}
+#endif /* !CONFIG_PPC_MMU_NOHASH */
}
return 0;
}
@@ -124,7 +173,7 @@ void __iomem * __ioremap_at(phys_addr_t
WARN_ON(size & ~PAGE_MASK);
for (i = 0; i < size; i += PAGE_SIZE)
- if (map_io_page((unsigned long)ea+i, pa+i, flags))
+ if (map_kernel_page((unsigned long)ea+i, pa+i, flags))
return NULL;
return (void __iomem *)ea;
^ permalink raw reply
* [PATCH 5/20] powerpc/mm: Add more bit definitions for Book3E MMU registers
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
This adds various additional bit definitions for various MMU related
SPRs used on Book3E.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/include/asm/mmu-book3e.h | 168 ++++++++++++++++++++++++----------
1 file changed, 119 insertions(+), 49 deletions(-)
--- linux-work.orig/arch/powerpc/include/asm/mmu-book3e.h 2009-07-22 15:19:22.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/mmu-book3e.h 2009-07-22 15:30:58.000000000 +1000
@@ -38,58 +38,128 @@
#define BOOK3E_PAGESZ_1TB 30
#define BOOK3E_PAGESZ_2TB 31
-#define MAS0_TLBSEL(x) ((x << 28) & 0x30000000)
-#define MAS0_ESEL(x) ((x << 16) & 0x0FFF0000)
-#define MAS0_NV(x) ((x) & 0x00000FFF)
-
-#define MAS1_VALID 0x80000000
-#define MAS1_IPROT 0x40000000
-#define MAS1_TID(x) ((x << 16) & 0x3FFF0000)
-#define MAS1_IND 0x00002000
-#define MAS1_TS 0x00001000
-#define MAS1_TSIZE(x) ((x << 7) & 0x00000F80)
-
-#define MAS2_EPN 0xFFFFF000
-#define MAS2_X0 0x00000040
-#define MAS2_X1 0x00000020
-#define MAS2_W 0x00000010
-#define MAS2_I 0x00000008
-#define MAS2_M 0x00000004
-#define MAS2_G 0x00000002
-#define MAS2_E 0x00000001
+/* MAS registers bit definitions */
+
+#define MAS0_TLBSEL(x) ((x << 28) & 0x30000000)
+#define MAS0_ESEL(x) ((x << 16) & 0x0FFF0000)
+#define MAS0_NV(x) ((x) & 0x00000FFF)
+#define MAS0_HES 0x00004000
+#define MAS0_WQ_ALLWAYS 0x00000000
+#define MAS0_WQ_COND 0x00001000
+#define MAS0_WQ_CLR_RSRV 0x00002000
+
+#define MAS1_VALID 0x80000000
+#define MAS1_IPROT 0x40000000
+#define MAS1_TID(x) ((x << 16) & 0x3FFF0000)
+#define MAS1_IND 0x00002000
+#define MAS1_TS 0x00001000
+#define MAS1_TSIZE_MASK 0x00000f80
+#define MAS1_TSIZE_SHIFT 7
+#define MAS1_TSIZE(x) ((x << MAS1_TSIZE_SHIFT) & MAS1_TSIZE_MASK)
+
+#define MAS2_EPN 0xFFFFF000
+#define MAS2_X0 0x00000040
+#define MAS2_X1 0x00000020
+#define MAS2_W 0x00000010
+#define MAS2_I 0x00000008
+#define MAS2_M 0x00000004
+#define MAS2_G 0x00000002
+#define MAS2_E 0x00000001
#define MAS2_EPN_MASK(size) (~0 << (size + 10))
#define MAS2_VAL(addr, size, flags) ((addr) & MAS2_EPN_MASK(size) | (flags))
-#define MAS3_RPN 0xFFFFF000
-#define MAS3_U0 0x00000200
-#define MAS3_U1 0x00000100
-#define MAS3_U2 0x00000080
-#define MAS3_U3 0x00000040
-#define MAS3_UX 0x00000020
-#define MAS3_SX 0x00000010
-#define MAS3_UW 0x00000008
-#define MAS3_SW 0x00000004
-#define MAS3_UR 0x00000002
-#define MAS3_SR 0x00000001
-
-#define MAS4_TLBSELD(x) MAS0_TLBSEL(x)
-#define MAS4_INDD 0x00008000
-#define MAS4_TSIZED(x) MAS1_TSIZE(x)
-#define MAS4_X0D 0x00000040
-#define MAS4_X1D 0x00000020
-#define MAS4_WD 0x00000010
-#define MAS4_ID 0x00000008
-#define MAS4_MD 0x00000004
-#define MAS4_GD 0x00000002
-#define MAS4_ED 0x00000001
-
-#define MAS6_SPID0 0x3FFF0000
-#define MAS6_SPID1 0x00007FFE
-#define MAS6_ISIZE(x) MAS1_TSIZE(x)
-#define MAS6_SAS 0x00000001
-#define MAS6_SPID MAS6_SPID0
-
-#define MAS7_RPN 0xFFFFFFFF
+#define MAS3_RPN 0xFFFFF000
+#define MAS3_U0 0x00000200
+#define MAS3_U1 0x00000100
+#define MAS3_U2 0x00000080
+#define MAS3_U3 0x00000040
+#define MAS3_UX 0x00000020
+#define MAS3_SX 0x00000010
+#define MAS3_UW 0x00000008
+#define MAS3_SW 0x00000004
+#define MAS3_UR 0x00000002
+#define MAS3_SR 0x00000001
+#define MAS3_SPSIZE 0x0000003e
+#define MAS3_SPSIZE_SHIFT 1
+
+#define MAS4_TLBSELD(x) MAS0_TLBSEL(x)
+#define MAS4_INDD 0x00008000 /* Default IND */
+#define MAS4_TSIZED(x) MAS1_TSIZE(x)
+#define MAS4_X0D 0x00000040
+#define MAS4_X1D 0x00000020
+#define MAS4_WD 0x00000010
+#define MAS4_ID 0x00000008
+#define MAS4_MD 0x00000004
+#define MAS4_GD 0x00000002
+#define MAS4_ED 0x00000001
+#define MAS4_WIMGED_MASK 0x0000001f /* Default WIMGE */
+#define MAS4_WIMGED_SHIFT 0
+#define MAS4_VLED MAS4_X1D /* Default VLE */
+#define MAS4_ACMD 0x000000c0 /* Default ACM */
+#define MAS4_ACMD_SHIFT 6
+#define MAS4_TSIZED_MASK 0x00000f80 /* Default TSIZE */
+#define MAS4_TSIZED_SHIFT 7
+
+#define MAS6_SPID0 0x3FFF0000
+#define MAS6_SPID1 0x00007FFE
+#define MAS6_ISIZE(x) MAS1_TSIZE(x)
+#define MAS6_SAS 0x00000001
+#define MAS6_SPID MAS6_SPID0
+#define MAS6_SIND 0x00000002 /* Indirect page */
+#define MAS6_SIND_SHIFT 1
+#define MAS6_SPID_MASK 0x3fff0000
+#define MAS6_SPID_SHIFT 16
+#define MAS6_ISIZE_MASK 0x00000f80
+#define MAS6_ISIZE_SHIFT 7
+
+#define MAS7_RPN 0xFFFFFFFF
+
+/* TLBnCFG encoding */
+#define TLBnCFG_N_ENTRY 0x00000fff /* number of entries */
+#define TLBnCFG_HES 0x00002000 /* HW select supported */
+#define TLBnCFG_IPROT 0x00008000 /* IPROT supported */
+#define TLBnCFG_GTWE 0x00010000 /* Guest can write */
+#define TLBnCFG_IND 0x00020000 /* IND entries supported */
+#define TLBnCFG_PT 0x00040000 /* Can load from page table */
+#define TLBnCFG_ASSOC 0xff000000 /* Associativity */
+
+/* TLBnPS encoding */
+#define TLBnPS_4K 0x00000004
+#define TLBnPS_8K 0x00000008
+#define TLBnPS_16K 0x00000010
+#define TLBnPS_32K 0x00000020
+#define TLBnPS_64K 0x00000040
+#define TLBnPS_128K 0x00000080
+#define TLBnPS_256K 0x00000100
+#define TLBnPS_512K 0x00000200
+#define TLBnPS_1M 0x00000400
+#define TLBnPS_2M 0x00000800
+#define TLBnPS_4M 0x00001000
+#define TLBnPS_8M 0x00002000
+#define TLBnPS_16M 0x00004000
+#define TLBnPS_32M 0x00008000
+#define TLBnPS_64M 0x00010000
+#define TLBnPS_128M 0x00020000
+#define TLBnPS_256M 0x00040000
+#define TLBnPS_512M 0x00080000
+#define TLBnPS_1G 0x00100000
+#define TLBnPS_2G 0x00200000
+#define TLBnPS_4G 0x00400000
+#define TLBnPS_8G 0x00800000
+#define TLBnPS_16G 0x01000000
+#define TLBnPS_32G 0x02000000
+#define TLBnPS_64G 0x04000000
+#define TLBnPS_128G 0x08000000
+#define TLBnPS_256G 0x10000000
+
+/* tlbilx action encoding */
+#define TLBILX_T_ALL 0
+#define TLBILX_T_TID 1
+#define TLBILX_T_FULLMATCH 3
+#define TLBILX_T_CLASS0 4
+#define TLBILX_T_CLASS1 5
+#define TLBILX_T_CLASS2 6
+#define TLBILX_T_CLASS3 7
#ifndef __ASSEMBLY__
^ permalink raw reply
* [PATCH 4/20] powerpc/mm: Add opcode definitions for tlbivax and tlbsrx.
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
This adds the opcode definitions to ppc-opcode.h for the two instructions
tlbivax and tlbsrx. as defined by Book3E 2.06
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/include/asm/ppc-opcode.h | 6 ++++++
1 file changed, 6 insertions(+)
--- linux-work.orig/arch/powerpc/include/asm/ppc-opcode.h 2009-07-22 15:25:45.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/ppc-opcode.h 2009-07-22 15:26:05.000000000 +1000
@@ -48,6 +48,8 @@
#define PPC_INST_TLBIE 0x7c000264
#define PPC_INST_TLBILX 0x7c000024
#define PPC_INST_WAIT 0x7c00007c
+#define PPC_INST_TLBIVAX 0x7c000624
+#define PPC_INST_TLBSRX_DOT 0x7c0006a5
/* macros to insert fields into opcodes */
#define __PPC_RA(a) (((a) & 0x1f) << 16)
@@ -76,6 +78,10 @@
__PPC_WC(w))
#define PPC_TLBIE(lp,a) stringify_in_c(.long PPC_INST_TLBIE | \
__PPC_RB(a) | __PPC_RS(lp))
+#define PPC_TLBSRX_DOT(a,b) stringify_in_c(.long PPC_INST_TLBSRX_DOT | \
+ __PPC_RA(a) | __PPC_RB(b))
+#define PPC_TLBIVAX(a,b) stringify_in_c(.long PPC_INST_TLBIVAX | \
+ __PPC_RA(a) | __PPC_RB(b))
/*
* Define what the VSX XX1 form instructions will look like, then add
^ permalink raw reply
* [PATCH 3/20] powerpc/mm: Add HW threads support to no_hash TLB management
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
The current "no hash" MMU context management code is written with
the assumption that one CPU == one TLB. This is not the case on
implementations that support HW multithreading, where several
linux CPUs can share the same TLB.
This adds some basic support for this to our context management
and our TLB flushing code.
It also cleans up the optional debugging output a bit
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/include/asm/cputhreads.h | 16 +++++
arch/powerpc/mm/mmu_context_nohash.c | 93 ++++++++++++++++++++++------------
arch/powerpc/mm/tlb_nohash.c | 10 ++-
3 files changed, 86 insertions(+), 33 deletions(-)
--- linux-work.orig/arch/powerpc/mm/mmu_context_nohash.c 2009-07-21 12:43:27.000000000 +1000
+++ linux-work/arch/powerpc/mm/mmu_context_nohash.c 2009-07-21 12:56:16.000000000 +1000
@@ -25,10 +25,20 @@
* also clear mm->cpu_vm_mask bits when processes are migrated
*/
-#undef DEBUG
-#define DEBUG_STEAL_ONLY
-#undef DEBUG_MAP_CONSISTENCY
-/*#define DEBUG_CLAMP_LAST_CONTEXT 15 */
+#define DEBUG_MAP_CONSISTENCY
+#define DEBUG_CLAMP_LAST_CONTEXT 31
+//#define DEBUG_HARDER
+
+/* We don't use DEBUG because it tends to be compiled in always nowadays
+ * and this would generate way too much output
+ */
+#ifdef DEBUG_HARDER
+#define pr_hard(args...) printk(KERN_DEBUG args)
+#define pr_hardcont(args...) printk(KERN_CONT args)
+#else
+#define pr_hard(args...) do { } while(0)
+#define pr_hardcont(args...) do { } while(0)
+#endif
#include <linux/kernel.h>
#include <linux/mm.h>
@@ -71,7 +81,7 @@ static DEFINE_SPINLOCK(context_lock);
static unsigned int steal_context_smp(unsigned int id)
{
struct mm_struct *mm;
- unsigned int cpu, max;
+ unsigned int cpu, max, i;
max = last_context - first_context;
@@ -89,15 +99,22 @@ static unsigned int steal_context_smp(un
id = first_context;
continue;
}
- pr_devel("[%d] steal context %d from mm @%p\n",
- smp_processor_id(), id, mm);
+ pr_hardcont(" | steal %d from 0x%p", id, mm);
/* Mark this mm has having no context anymore */
mm->context.id = MMU_NO_CONTEXT;
- /* Mark it stale on all CPUs that used this mm */
- for_each_cpu(cpu, mm_cpumask(mm))
- __set_bit(id, stale_map[cpu]);
+ /* Mark it stale on all CPUs that used this mm. For threaded
+ * implementations, we set it on all threads on each core
+ * represented in the mask. A future implementation will use
+ * a core map instead but this will do for now.
+ */
+ for_each_cpu(cpu, mm_cpumask(mm)) {
+ for (i = cpu_first_thread_in_core(cpu);
+ i <= cpu_last_thread_in_core(cpu); i++)
+ __set_bit(id, stale_map[i]);
+ cpu = i - 1;
+ }
return id;
}
@@ -126,7 +143,7 @@ static unsigned int steal_context_up(uns
/* Pick up the victim mm */
mm = context_mm[id];
- pr_devel("[%d] steal context %d from mm @%p\n", cpu, id, mm);
+ pr_hardcont(" | steal %d from 0x%p", id, mm);
/* Flush the TLB for that context */
local_flush_tlb_mm(mm);
@@ -179,19 +196,14 @@ void switch_mmu_context(struct mm_struct
/* No lockless fast path .. yet */
spin_lock(&context_lock);
-#ifndef DEBUG_STEAL_ONLY
- pr_devel("[%d] activating context for mm @%p, active=%d, id=%d\n",
- cpu, next, next->context.active, next->context.id);
-#endif
+ pr_hard("[%d] activating context for mm @%p, active=%d, id=%d",
+ cpu, next, next->context.active, next->context.id);
#ifdef CONFIG_SMP
/* Mark us active and the previous one not anymore */
next->context.active++;
if (prev) {
-#ifndef DEBUG_STEAL_ONLY
- pr_devel(" old context %p active was: %d\n",
- prev, prev->context.active);
-#endif
+ pr_hardcont(" (old=0x%p a=%d)", prev, prev->context.active);
WARN_ON(prev->context.active < 1);
prev->context.active--;
}
@@ -201,8 +213,14 @@ void switch_mmu_context(struct mm_struct
/* If we already have a valid assigned context, skip all that */
id = next->context.id;
- if (likely(id != MMU_NO_CONTEXT))
+ if (likely(id != MMU_NO_CONTEXT)) {
+#ifdef DEBUG_MAP_CONSISTENCY
+ if (context_mm[id] != next)
+ pr_err("MMU: mm 0x%p has id %d but context_mm[%d] says 0x%p\n",
+ next, id, id, context_mm[id]);
+#endif
goto ctxt_ok;
+ }
/* We really don't have a context, let's try to acquire one */
id = next_context;
@@ -234,11 +252,7 @@ void switch_mmu_context(struct mm_struct
next_context = id + 1;
context_mm[id] = next;
next->context.id = id;
-
-#ifndef DEBUG_STEAL_ONLY
- pr_devel("[%d] picked up new id %d, nrf is now %d\n",
- cpu, id, nr_free_contexts);
-#endif
+ pr_hardcont(" | new id=%d,nrf=%d", id, nr_free_contexts);
context_check_map();
ctxt_ok:
@@ -247,15 +261,20 @@ void switch_mmu_context(struct mm_struct
* local TLB for it and unmark it before we use it
*/
if (test_bit(id, stale_map[cpu])) {
- pr_devel("[%d] flushing stale context %d for mm @%p !\n",
- cpu, id, next);
+ pr_hardcont(" | stale flush %d [%d..%d]",
+ id, cpu_first_thread_in_core(cpu),
+ cpu_last_thread_in_core(cpu));
+
local_flush_tlb_mm(next);
/* XXX This clear should ultimately be part of local_flush_tlb_mm */
- __clear_bit(id, stale_map[cpu]);
+ for (cpu = cpu_first_thread_in_core(cpu);
+ cpu <= cpu_last_thread_in_core(cpu); cpu++)
+ __clear_bit(id, stale_map[cpu]);
}
/* Flick the MMU and release lock */
+ pr_hardcont(" -> %d\n", id);
set_context(id, next->pgd);
spin_unlock(&context_lock);
}
@@ -265,6 +284,8 @@ void switch_mmu_context(struct mm_struct
*/
int init_new_context(struct task_struct *t, struct mm_struct *mm)
{
+ pr_hard("initing context for mm @%p\n", mm);
+
mm->context.id = MMU_NO_CONTEXT;
mm->context.active = 0;
@@ -304,7 +325,9 @@ static int __cpuinit mmu_context_cpu_not
unsigned long action, void *hcpu)
{
unsigned int cpu = (unsigned int)(long)hcpu;
-
+#ifdef CONFIG_HOTPLUG_CPU
+ struct task_struct *p;
+#endif
/* We don't touch CPU 0 map, it's allocated at aboot and kept
* around forever
*/
@@ -323,8 +346,16 @@ static int __cpuinit mmu_context_cpu_not
pr_devel("MMU: Freeing stale context map for CPU %d\n", cpu);
kfree(stale_map[cpu]);
stale_map[cpu] = NULL;
- break;
-#endif
+
+ /* We also clear the cpu_vm_mask bits of CPUs going away */
+ read_lock(&tasklist_lock);
+ for_each_process(p) {
+ if (p->mm)
+ cpu_mask_clear_cpu(cpu, mm_cpumask(p->mm));
+ }
+ read_unlock(&tasklist_lock);
+ break;
+#endif /* CONFIG_HOTPLUG_CPU */
}
return NOTIFY_OK;
}
Index: linux-work/arch/powerpc/include/asm/cputhreads.h
===================================================================
--- linux-work.orig/arch/powerpc/include/asm/cputhreads.h 2009-07-21 12:43:27.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/cputhreads.h 2009-07-21 12:56:16.000000000 +1000
@@ -5,6 +5,15 @@
/*
* Mapping of threads to cores
+ *
+ * Note: This implementation is limited to a power of 2 number of
+ * threads per core and the same number for each core in the system
+ * (though it would work if some processors had less threads as long
+ * as the CPU numbers are still allocated, just not brought offline).
+ *
+ * However, the API allows for a different implementation in the future
+ * if needed, as long as you only use the functions and not the variables
+ * directly.
*/
#ifdef CONFIG_SMP
@@ -67,5 +76,12 @@ static inline int cpu_first_thread_in_co
return cpu & ~(threads_per_core - 1);
}
+static inline int cpu_last_thread_in_core(int cpu)
+{
+ return cpu | (threads_per_core - 1);
+}
+
+
+
#endif /* _ASM_POWERPC_CPUTHREADS_H */
Index: linux-work/arch/powerpc/mm/tlb_nohash.c
===================================================================
--- linux-work.orig/arch/powerpc/mm/tlb_nohash.c 2009-07-21 12:43:31.000000000 +1000
+++ linux-work/arch/powerpc/mm/tlb_nohash.c 2009-07-21 12:57:21.000000000 +1000
@@ -87,6 +87,12 @@ EXPORT_SYMBOL(local_flush_tlb_page);
static DEFINE_SPINLOCK(tlbivax_lock);
+static int mm_is_core_local(struct mm_struct *mm)
+{
+ return cpumask_subset(mm_cpumask(mm),
+ topology_thread_cpumask(smp_processor_id()));
+}
+
struct tlb_flush_param {
unsigned long addr;
unsigned int pid;
@@ -131,7 +137,7 @@ void flush_tlb_mm(struct mm_struct *mm)
pid = mm->context.id;
if (unlikely(pid == MMU_NO_CONTEXT))
goto no_context;
- if (!cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
+ if (!mm_is_core_local(mm)) {
struct tlb_flush_param p = { .pid = pid };
/* Ignores smp_processor_id() even if set. */
smp_call_function_many(mm_cpumask(mm),
@@ -153,7 +159,7 @@ void flush_tlb_page(struct vm_area_struc
if (unlikely(pid == MMU_NO_CONTEXT))
goto bail;
cpu_mask = mm_cpumask(vma->vm_mm);
- if (!cpumask_equal(cpu_mask, cpumask_of(smp_processor_id()))) {
+ if (!mm_is_core_local(mm)) {
/* If broadcast tlbivax is supported, use it */
if (mmu_has_feature(MMU_FTR_USE_TLBIVAX_BCAST)) {
int lock = mmu_has_feature(MMU_FTR_LOCK_BCAST_INVAL);
^ permalink raw reply
* [PATCH 2/20] powerpc/of: Remove useless register save/restore when calling OF back
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
enter_prom() used to save and restore registers such as CTR, XER etc..
which are volatile, or SRR0,1... which we don't care about. This
removes a bunch of useless code and while at it turns an mtmsrd into
an MTMSRD macro which will be useful to Book3E.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/kernel/entry_64.S | 38 ++++++--------------------------------
1 file changed, 6 insertions(+), 32 deletions(-)
--- linux-work.orig/arch/powerpc/kernel/entry_64.S 2009-07-22 15:20:26.000000000 +1000
+++ linux-work/arch/powerpc/kernel/entry_64.S 2009-07-22 15:22:44.000000000 +1000
@@ -823,30 +823,17 @@ _GLOBAL(enter_prom)
* of all registers that it saves. We therefore save those registers
* PROM might touch to the stack. (r0, r3-r13 are caller saved)
*/
- SAVE_8GPRS(2, r1)
+ SAVE_GPR(2, r1)
SAVE_GPR(13, r1)
SAVE_8GPRS(14, r1)
SAVE_10GPRS(22, r1)
- mfcr r4
- std r4,_CCR(r1)
- mfctr r5
- std r5,_CTR(r1)
- mfspr r6,SPRN_XER
- std r6,_XER(r1)
- mfdar r7
- std r7,_DAR(r1)
- mfdsisr r8
- std r8,_DSISR(r1)
- mfsrr0 r9
- std r9,_SRR0(r1)
- mfsrr1 r10
- std r10,_SRR1(r1)
+ mfcr r10
mfmsr r11
+ std r10,_CCR(r1)
std r11,_MSR(r1)
/* Get the PROM entrypoint */
- ld r0,GPR4(r1)
- mtlr r0
+ mtlr r4
/* Switch MSR to 32 bits mode
*/
@@ -860,8 +847,7 @@ _GLOBAL(enter_prom)
mtmsrd r11
isync
- /* Restore arguments & enter PROM here... */
- ld r3,GPR3(r1)
+ /* Enter PROM here... */
blrl
/* Just make sure that r1 top 32 bits didn't get
@@ -871,7 +857,7 @@ _GLOBAL(enter_prom)
/* Restore the MSR (back to 64 bits) */
ld r0,_MSR(r1)
- mtmsrd r0
+ MTMSRD(r0)
isync
/* Restore other registers */
@@ -881,18 +867,6 @@ _GLOBAL(enter_prom)
REST_10GPRS(22, r1)
ld r4,_CCR(r1)
mtcr r4
- ld r5,_CTR(r1)
- mtctr r5
- ld r6,_XER(r1)
- mtspr SPRN_XER,r6
- ld r7,_DAR(r1)
- mtdar r7
- ld r8,_DSISR(r1)
- mtdsisr r8
- ld r9,_SRR0(r1)
- mtsrr0 r9
- ld r10,_SRR1(r1)
- mtsrr1 r10
addi r1,r1,PROM_FRAME_SIZE
ld r0,16(r1)
^ permalink raw reply
* [PATCH 1/20] powerpc/mm: Fix misplaced #endif in pgtable-ppc64-64k.h
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1248426902.401617.944220131651.qpush@grosgo>
A misplaced #endif causes more definitions than intended to be
protected by #ifndef __ASSEMBLY__. This breaks upcoming 64-bit
BookE support patch when using 64k pages.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/include/asm/pgtable-ppc64-64k.h | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
--- linux-work.orig/arch/powerpc/include/asm/pgtable-ppc64-64k.h 2009-07-22 11:45:34.000000000 +1000
+++ linux-work/arch/powerpc/include/asm/pgtable-ppc64-64k.h 2009-07-22 11:45:47.000000000 +1000
@@ -10,10 +10,10 @@
#define PGD_INDEX_SIZE 4
#ifndef __ASSEMBLY__
-
#define PTE_TABLE_SIZE (sizeof(real_pte_t) << PTE_INDEX_SIZE)
#define PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE)
#define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE)
+#endif /* __ASSEMBLY__ */
#define PTRS_PER_PTE (1 << PTE_INDEX_SIZE)
#define PTRS_PER_PMD (1 << PMD_INDEX_SIZE)
@@ -32,8 +32,6 @@
#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
#define PGDIR_MASK (~(PGDIR_SIZE-1))
-#endif /* __ASSEMBLY__ */
-
/* Bits to mask out from a PMD to get to the PTE page */
#define PMD_MASKED_BITS 0x1ff
/* Bits to mask out from a PGD/PUD to get to the PMD page */
^ permalink raw reply
* [PATCH 0/20] powerpc: base 64-bit Book3E processor support (v2)
From: Benjamin Herrenschmidt @ 2009-07-24 9:15 UTC (permalink / raw)
To: linuxppc-dev
Here is a series of patches that implement some basic support
for 64-bit Book3E processors that comply to architecture 2.06.
There is no specific processor announced yet. The patches make
some shortcut which means they currently rely on an implementation
that supports MMU v2 with support for the "HES" feature (HW entry
select) and with support for the "TLB reservation" feature. They
also assume a single unified TLB array. I shouldn't be very hard
to implement support for other variants of the architecture on
top of this though.
The current set of patch has no proper support yet for hugetlb,
nor for "special" interrupt levels (debug, critical and machine
check). Some minimal support for debug/critical levels is provided
specifically for the "Debug" interrupt (single step etc...) only
when it occurs from within user space code.
The intend is to merge these in 2.6.32. They rely on pretty much
all the other patches I've been posting lately including the
generic changes to add the virtual address argument to pte_free_tlb.
v2. Various fixes, some addressing comments recieved and a whole
bunch fixing other issues including breakage of existing platforms
^ permalink raw reply
* Re: BUG in dma-mapping.h:218 // MESH SCSI driver not working
From: Benjamin Herrenschmidt @ 2009-07-24 8:52 UTC (permalink / raw)
To: Stef Simoens; +Cc: linuxppc-dev
In-Reply-To: <4A68E1CE.4040307@scarlet.be>
On Fri, 2009-07-24 at 00:18 +0200, Stef Simoens wrote:
> I tried the latest 2.6.31-rc3-git3 (without any other patch).
> However, I have the same behaviour as the patched 2.6.30 (so: no BUG,
> but the mesh_abort messages).
>
> Anybody knows what's going wrong, and how to fix it? I've read the
> history of this list of June and July ... but I didn't find any other
> reports of the problem I'm encountering...
>
Would it be possible for you to roughly find out at what kernel version
it stopped working ? (Some kernels may need my patch to avoid crashing)
I have a machine with a MESH here that -appears- to work, at least it
did last time I tried it which was a couple of weeks ago, I'll try again
just to be sure.
Cheers,
Ben.
^ permalink raw reply
* Re: [PATCH 4/20] powerpc/mm: Add opcode definitions for tlbivax and tlbsrx.
From: Kumar Gala @ 2009-07-24 4:52 UTC (permalink / raw)
To: Benjamin Herrenschmidt; +Cc: linuxppc-dev
In-Reply-To: <1248387158.25467.3.camel@pasglop>
On Jul 23, 2009, at 5:12 PM, Benjamin Herrenschmidt wrote:
> On Thu, 2009-07-23 at 10:55 -0500, Kumar Gala wrote:
>> On Jul 23, 2009, at 12:59 AM, Benjamin Herrenschmidt wrote:
>>
>>> This adds the opcode definitions to ppc-opcode.h for the two
>>> instructions
>>> tlbivax and tlbsrx. as defined by Book3E 2.06
>>>
>>> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
>>> ---
>>>
>>> arch/powerpc/include/asm/ppc-opcode.h | 6 ++++++
>>> 1 file changed, 6 insertions(+)
>>
>> Do we really have binutils that don't have tlbivax properly at this
>> point?
>
> I don't know for sure, I like being consistent with the rest though
> and so I use those macros for all those MMU opcodes. Also means that
> I have no problem building with my current toolchain without passing
> a specific -mcpu option or anything like that :-)
>
> We can change that back later if you want.
ok, just wondering.. at some point we should decide which way we want
to go, since we use "tlbivax" today on e500/fsl-booke.
- k
^ permalink raw reply
* [PATCH 4/5] powerpc: use dma_map_ops struct
From: FUJITA Tomonori @ 2009-07-24 3:24 UTC (permalink / raw)
To: linuxppc-dev; +Cc: FUJITA Tomonori, linux-kernel
In-Reply-To: <1248405855-15546-1-git-send-email-fujita.tomonori@lab.ntt.co.jp>
This converts uses dma_map_ops struct (in include/linux/dma-mapping.h)
instead of POWERPC homegrown dma_mapping_ops.
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
---
arch/powerpc/include/asm/device.h | 4 +-
arch/powerpc/include/asm/dma-mapping.h | 84 ++++++++-----------------------
arch/powerpc/include/asm/pci.h | 4 +-
arch/powerpc/include/asm/swiotlb.h | 2 +-
arch/powerpc/kernel/dma-iommu.c | 2 +-
arch/powerpc/kernel/dma-swiotlb.c | 2 +-
arch/powerpc/kernel/dma.c | 2 +-
arch/powerpc/kernel/ibmebus.c | 2 +-
arch/powerpc/kernel/pci-common.c | 6 +-
arch/powerpc/kernel/vio.c | 2 +-
arch/powerpc/platforms/cell/iommu.c | 2 +-
arch/powerpc/platforms/ps3/system-bus.c | 4 +-
12 files changed, 37 insertions(+), 79 deletions(-)
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 0086f8d..67fcd7f 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -6,7 +6,7 @@
#ifndef _ASM_POWERPC_DEVICE_H
#define _ASM_POWERPC_DEVICE_H
-struct dma_mapping_ops;
+struct dma_map_ops;
struct device_node;
struct dev_archdata {
@@ -14,7 +14,7 @@ struct dev_archdata {
struct device_node *of_node;
/* DMA operations on that device */
- struct dma_mapping_ops *dma_ops;
+ struct dma_map_ops *dma_ops;
void *dma_data;
#ifdef CONFIG_SWIOTLB
dma_addr_t max_direct_dma_addr;
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 1765c37..8ca2b51 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -64,56 +64,14 @@ static inline unsigned long device_to_mask(struct device *dev)
}
/*
- * DMA operations are abstracted for G5 vs. i/pSeries, PCI vs. VIO
- */
-struct dma_mapping_ops {
- void * (*alloc_coherent)(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag);
- void (*free_coherent)(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_handle);
- int (*map_sg)(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction direction,
- struct dma_attrs *attrs);
- void (*unmap_sg)(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction direction,
- struct dma_attrs *attrs);
- int (*dma_supported)(struct device *dev, u64 mask);
- int (*set_dma_mask)(struct device *dev, u64 dma_mask);
- dma_addr_t (*map_page)(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction direction,
- struct dma_attrs *attrs);
- void (*unmap_page)(struct device *dev,
- dma_addr_t dma_address, size_t size,
- enum dma_data_direction direction,
- struct dma_attrs *attrs);
-#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
- void (*sync_single_range_for_cpu)(struct device *hwdev,
- dma_addr_t dma_handle, unsigned long offset,
- size_t size,
- enum dma_data_direction direction);
- void (*sync_single_range_for_device)(struct device *hwdev,
- dma_addr_t dma_handle, unsigned long offset,
- size_t size,
- enum dma_data_direction direction);
- void (*sync_sg_for_cpu)(struct device *hwdev,
- struct scatterlist *sg, int nelems,
- enum dma_data_direction direction);
- void (*sync_sg_for_device)(struct device *hwdev,
- struct scatterlist *sg, int nelems,
- enum dma_data_direction direction);
-#endif
-};
-
-/*
* Available generic sets of operations
*/
#ifdef CONFIG_PPC64
-extern struct dma_mapping_ops dma_iommu_ops;
+extern struct dma_map_ops dma_iommu_ops;
#endif
-extern struct dma_mapping_ops dma_direct_ops;
+extern struct dma_map_ops dma_direct_ops;
-static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
{
/* We don't handle the NULL dev case for ISA for now. We could
* do it via an out of line call but it is not needed for now. The
@@ -126,14 +84,14 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
return dev->archdata.dma_ops;
}
-static inline void set_dma_ops(struct device *dev, struct dma_mapping_ops *ops)
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
{
dev->archdata.dma_ops = ops;
}
static inline int dma_supported(struct device *dev, u64 mask)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
if (unlikely(dma_ops == NULL))
return 0;
@@ -147,7 +105,7 @@ static inline int dma_supported(struct device *dev, u64 mask)
static inline int dma_set_mask(struct device *dev, u64 dma_mask)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
if (unlikely(dma_ops == NULL))
return -EIO;
@@ -161,7 +119,7 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask)
/*
* map_/unmap_single actually call through to map/unmap_page now that all the
- * dma_mapping_ops have been converted over. We just have to get the page and
+ * dma_map_ops have been converted over. We just have to get the page and
* offset to pass through to map_page
*/
static inline dma_addr_t dma_map_single_attrs(struct device *dev,
@@ -170,7 +128,7 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev,
enum dma_data_direction direction,
struct dma_attrs *attrs)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
@@ -185,7 +143,7 @@ static inline void dma_unmap_single_attrs(struct device *dev,
enum dma_data_direction direction,
struct dma_attrs *attrs)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
@@ -198,7 +156,7 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev,
enum dma_data_direction direction,
struct dma_attrs *attrs)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
@@ -211,7 +169,7 @@ static inline void dma_unmap_page_attrs(struct device *dev,
enum dma_data_direction direction,
struct dma_attrs *attrs)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
@@ -222,7 +180,7 @@ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
int nents, enum dma_data_direction direction,
struct dma_attrs *attrs)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
return dma_ops->map_sg(dev, sg, nents, direction, attrs);
@@ -234,7 +192,7 @@ static inline void dma_unmap_sg_attrs(struct device *dev,
enum dma_data_direction direction,
struct dma_attrs *attrs)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
dma_ops->unmap_sg(dev, sg, nhwentries, direction, attrs);
@@ -243,7 +201,7 @@ static inline void dma_unmap_sg_attrs(struct device *dev,
static inline void *dma_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t flag)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
@@ -252,7 +210,7 @@ static inline void *dma_alloc_coherent(struct device *dev, size_t size,
static inline void dma_free_coherent(struct device *dev, size_t size,
void *cpu_addr, dma_addr_t dma_handle)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
@@ -304,7 +262,7 @@ static inline void dma_sync_single_for_cpu(struct device *dev,
dma_addr_t dma_handle, size_t size,
enum dma_data_direction direction)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
@@ -317,7 +275,7 @@ static inline void dma_sync_single_for_device(struct device *dev,
dma_addr_t dma_handle, size_t size,
enum dma_data_direction direction)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
@@ -330,7 +288,7 @@ static inline void dma_sync_sg_for_cpu(struct device *dev,
struct scatterlist *sgl, int nents,
enum dma_data_direction direction)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
@@ -342,7 +300,7 @@ static inline void dma_sync_sg_for_device(struct device *dev,
struct scatterlist *sgl, int nents,
enum dma_data_direction direction)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
@@ -354,7 +312,7 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev,
dma_addr_t dma_handle, unsigned long offset, size_t size,
enum dma_data_direction direction)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
@@ -367,7 +325,7 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
dma_addr_t dma_handle, unsigned long offset, size_t size,
enum dma_data_direction direction)
{
- struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+ struct dma_map_ops *dma_ops = get_dma_ops(dev);
BUG_ON(!dma_ops);
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index d9483c5..7ae46d7 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -61,8 +61,8 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
}
#ifdef CONFIG_PCI
-extern void set_pci_dma_ops(struct dma_mapping_ops *dma_ops);
-extern struct dma_mapping_ops *get_pci_dma_ops(void);
+extern void set_pci_dma_ops(struct dma_map_ops *dma_ops);
+extern struct dma_map_ops *get_pci_dma_ops(void);
#else /* CONFIG_PCI */
#define set_pci_dma_ops(d)
#define get_pci_dma_ops() NULL
diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h
index 21ce0a3..8979d4c 100644
--- a/arch/powerpc/include/asm/swiotlb.h
+++ b/arch/powerpc/include/asm/swiotlb.h
@@ -13,7 +13,7 @@
#include <linux/swiotlb.h>
-extern struct dma_mapping_ops swiotlb_dma_ops;
+extern struct dma_map_ops swiotlb_dma_ops;
static inline void dma_mark_clean(void *addr, size_t size) {}
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 2983ada..87ddb3f 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -89,7 +89,7 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask)
return 1;
}
-struct dma_mapping_ops dma_iommu_ops = {
+struct dma_map_ops dma_iommu_ops = {
.alloc_coherent = dma_iommu_alloc_coherent,
.free_coherent = dma_iommu_free_coherent,
.map_sg = dma_iommu_map_sg,
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index ca141e1..d1143a6 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -31,7 +31,7 @@ unsigned int ppc_swiotlb_enable;
* map_page, and unmap_page on highmem, use normal dma_ops
* for everything else.
*/
-struct dma_mapping_ops swiotlb_dma_ops = {
+struct dma_map_ops swiotlb_dma_ops = {
.alloc_coherent = dma_direct_alloc_coherent,
.free_coherent = dma_direct_free_coherent,
.map_sg = swiotlb_map_sg_attrs,
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 20a60d6..3e8bb9a 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -140,7 +140,7 @@ static inline void dma_direct_sync_single_range(struct device *dev,
}
#endif
-struct dma_mapping_ops dma_direct_ops = {
+struct dma_map_ops dma_direct_ops = {
.alloc_coherent = dma_direct_alloc_coherent,
.free_coherent = dma_direct_free_coherent,
.map_sg = dma_direct_map_sg,
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 6e3f624..a4c8b38 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -127,7 +127,7 @@ static int ibmebus_dma_supported(struct device *dev, u64 mask)
return 1;
}
-static struct dma_mapping_ops ibmebus_dma_ops = {
+static struct dma_map_ops ibmebus_dma_ops = {
.alloc_coherent = ibmebus_alloc_coherent,
.free_coherent = ibmebus_free_coherent,
.map_sg = ibmebus_map_sg,
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 5a56e97..7585f1f 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -50,14 +50,14 @@ resource_size_t isa_mem_base;
unsigned int ppc_pci_flags = 0;
-static struct dma_mapping_ops *pci_dma_ops = &dma_direct_ops;
+static struct dma_map_ops *pci_dma_ops = &dma_direct_ops;
-void set_pci_dma_ops(struct dma_mapping_ops *dma_ops)
+void set_pci_dma_ops(struct dma_map_ops *dma_ops)
{
pci_dma_ops = dma_ops;
}
-struct dma_mapping_ops *get_pci_dma_ops(void)
+struct dma_map_ops *get_pci_dma_ops(void)
{
return pci_dma_ops;
}
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 819e59f..bc7b41e 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -601,7 +601,7 @@ static void vio_dma_iommu_unmap_sg(struct device *dev,
vio_cmo_dealloc(viodev, alloc_size);
}
-struct dma_mapping_ops vio_dma_mapping_ops = {
+struct dma_map_ops vio_dma_mapping_ops = {
.alloc_coherent = vio_dma_iommu_alloc_coherent,
.free_coherent = vio_dma_iommu_free_coherent,
.map_sg = vio_dma_iommu_map_sg,
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 5b34fc2..416db17 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -642,7 +642,7 @@ static int dma_fixed_dma_supported(struct device *dev, u64 mask)
static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask);
-struct dma_mapping_ops dma_iommu_fixed_ops = {
+struct dma_map_ops dma_iommu_fixed_ops = {
.alloc_coherent = dma_fixed_alloc_coherent,
.free_coherent = dma_fixed_free_coherent,
.map_sg = dma_fixed_map_sg,
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 3f763c5..02ddcc2 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -694,7 +694,7 @@ static int ps3_dma_supported(struct device *_dev, u64 mask)
return mask >= DMA_BIT_MASK(32);
}
-static struct dma_mapping_ops ps3_sb_dma_ops = {
+static struct dma_map_ops ps3_sb_dma_ops = {
.alloc_coherent = ps3_alloc_coherent,
.free_coherent = ps3_free_coherent,
.map_sg = ps3_sb_map_sg,
@@ -704,7 +704,7 @@ static struct dma_mapping_ops ps3_sb_dma_ops = {
.unmap_page = ps3_unmap_page,
};
-static struct dma_mapping_ops ps3_ioc0_dma_ops = {
+static struct dma_map_ops ps3_ioc0_dma_ops = {
.alloc_coherent = ps3_alloc_coherent,
.free_coherent = ps3_free_coherent,
.map_sg = ps3_ioc0_map_sg,
--
1.6.0.6
^ permalink raw reply related
* [PATCH 1/5] powerpc: remove addr_needs_map in struct dma_mapping_ops
From: FUJITA Tomonori @ 2009-07-24 3:24 UTC (permalink / raw)
To: linuxppc-dev; +Cc: FUJITA Tomonori, linux-kernel
In-Reply-To: <1248405855-15546-1-git-send-email-fujita.tomonori@lab.ntt.co.jp>
This patch adds max_direct_dma_addr to struct dev_archdata to remove
addr_needs_map in struct dma_mapping_ops. It also converts
dma_capable() to use max_direct_dma_addr.
max_direct_dma_addr is initialized in pci_dma_dev_setup_swiotlb(),
called via ppc_md.pci_dma_dev_setup hook.
For further information:
http://marc.info/?t=124719060200001&r=1&w=2
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
---
arch/powerpc/include/asm/device.h | 3 ++
arch/powerpc/include/asm/dma-mapping.h | 8 +++---
arch/powerpc/include/asm/swiotlb.h | 5 +--
arch/powerpc/kernel/dma-swiotlb.c | 36 +++++++++++----------------
arch/powerpc/platforms/85xx/mpc8536_ds.c | 1 +
arch/powerpc/platforms/85xx/mpc85xx_ds.c | 1 +
arch/powerpc/platforms/85xx/mpc85xx_mds.c | 1 +
arch/powerpc/platforms/86xx/mpc86xx_hpcn.c | 1 +
8 files changed, 28 insertions(+), 28 deletions(-)
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index 7d2277c..0086f8d 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -16,6 +16,9 @@ struct dev_archdata {
/* DMA operations on that device */
struct dma_mapping_ops *dma_ops;
void *dma_data;
+#ifdef CONFIG_SWIOTLB
+ dma_addr_t max_direct_dma_addr;
+#endif
};
static inline void dev_archdata_set_node(struct dev_archdata *ad,
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 0c34371..1765c37 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -87,8 +87,6 @@ struct dma_mapping_ops {
dma_addr_t dma_address, size_t size,
enum dma_data_direction direction,
struct dma_attrs *attrs);
- int (*addr_needs_map)(struct device *dev, dma_addr_t addr,
- size_t size);
#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
void (*sync_single_range_for_cpu)(struct device *hwdev,
dma_addr_t dma_handle, unsigned long offset,
@@ -426,10 +424,12 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
{
- struct dma_mapping_ops *ops = get_dma_ops(dev);
+#ifdef CONFIG_SWIOTLB
+ struct dev_archdata *sd = &dev->archdata;
- if (ops->addr_needs_map && ops->addr_needs_map(dev, addr, size))
+ if (sd->max_direct_dma_addr && addr + size > sd->max_direct_dma_addr)
return 0;
+#endif
if (!dev->dma_mask)
return 0;
diff --git a/arch/powerpc/include/asm/swiotlb.h b/arch/powerpc/include/asm/swiotlb.h
index 30891d6..31e0e43 100644
--- a/arch/powerpc/include/asm/swiotlb.h
+++ b/arch/powerpc/include/asm/swiotlb.h
@@ -16,12 +16,11 @@
extern struct dma_mapping_ops swiotlb_dma_ops;
extern struct dma_mapping_ops swiotlb_pci_dma_ops;
-int swiotlb_arch_address_needs_mapping(struct device *, dma_addr_t,
- size_t size);
-
static inline void dma_mark_clean(void *addr, size_t size) {}
extern unsigned int ppc_swiotlb_enable;
int __init swiotlb_setup_bus_notifier(void);
+extern void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev);
+
#endif /* __ASM_SWIOTLB_H */
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index e8a57de..c9f6a30 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -25,26 +25,6 @@ int swiotlb __read_mostly;
unsigned int ppc_swiotlb_enable;
/*
- * Determine if an address is reachable by a pci device, or if we must bounce.
- */
-static int
-swiotlb_pci_addr_needs_map(struct device *hwdev, dma_addr_t addr, size_t size)
-{
- dma_addr_t max;
- struct pci_controller *hose;
- struct pci_dev *pdev = to_pci_dev(hwdev);
-
- hose = pci_bus_to_host(pdev->bus);
- max = hose->dma_window_base_cur + hose->dma_window_size;
-
- /* check that we're within mapped pci window space */
- if ((addr + size > max) | (addr < hose->dma_window_base_cur))
- return 1;
-
- return 0;
-}
-
-/*
* At the moment, all platforms that use this code only require
* swiotlb to be used if we're operating on HIGHMEM. Since
* we don't ever call anything other than map_sg, unmap_sg,
@@ -73,22 +53,36 @@ struct dma_mapping_ops swiotlb_pci_dma_ops = {
.dma_supported = swiotlb_dma_supported,
.map_page = swiotlb_map_page,
.unmap_page = swiotlb_unmap_page,
- .addr_needs_map = swiotlb_pci_addr_needs_map,
.sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
.sync_single_range_for_device = swiotlb_sync_single_range_for_device,
.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
.sync_sg_for_device = swiotlb_sync_sg_for_device
};
+void pci_dma_dev_setup_swiotlb(struct pci_dev *pdev)
+{
+ struct pci_controller *hose;
+ struct dev_archdata *sd;
+
+ hose = pci_bus_to_host(pdev->bus);
+ sd = &pdev->dev.archdata;
+ sd->max_direct_dma_addr =
+ hose->dma_window_base_cur + hose->dma_window_size;
+}
+
static int ppc_swiotlb_bus_notify(struct notifier_block *nb,
unsigned long action, void *data)
{
struct device *dev = data;
+ struct dev_archdata *sd;
/* We are only intereted in device addition */
if (action != BUS_NOTIFY_ADD_DEVICE)
return 0;
+ sd = &dev->archdata;
+ sd->max_direct_dma_addr = 0;
+
/* May need to bounce if the device can't address all of DRAM */
if (dma_get_mask(dev) < lmb_end_of_DRAM())
set_dma_ops(dev, &swiotlb_dma_ops);
diff --git a/arch/powerpc/platforms/85xx/mpc8536_ds.c b/arch/powerpc/platforms/85xx/mpc8536_ds.c
index 055ff41..bf052c0 100644
--- a/arch/powerpc/platforms/85xx/mpc8536_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc8536_ds.c
@@ -97,6 +97,7 @@ static void __init mpc8536_ds_setup_arch(void)
if (lmb_end_of_DRAM() > max) {
ppc_swiotlb_enable = 1;
set_pci_dma_ops(&swiotlb_pci_dma_ops);
+ ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
}
#endif
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index 849c0ac..c6f92cc 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -193,6 +193,7 @@ static void __init mpc85xx_ds_setup_arch(void)
if (lmb_end_of_DRAM() > max) {
ppc_swiotlb_enable = 1;
set_pci_dma_ops(&swiotlb_pci_dma_ops);
+ ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
}
#endif
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index 60ed9c0..8b8e5f9 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -242,6 +242,7 @@ static void __init mpc85xx_mds_setup_arch(void)
if (lmb_end_of_DRAM() > max) {
ppc_swiotlb_enable = 1;
set_pci_dma_ops(&swiotlb_pci_dma_ops);
+ ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
}
#endif
}
diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
index 6632702..8032301 100644
--- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
+++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c
@@ -106,6 +106,7 @@ mpc86xx_hpcn_setup_arch(void)
if (lmb_end_of_DRAM() > max) {
ppc_swiotlb_enable = 1;
set_pci_dma_ops(&swiotlb_pci_dma_ops);
+ ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
}
#endif
}
--
1.6.0.6
^ permalink raw reply related
* [PATCH 0/5] powerpc: use asm-generic/dma-mapping-common.h
From: FUJITA Tomonori @ 2009-07-24 3:24 UTC (permalink / raw)
To: linuxppc-dev; +Cc: fujita.tomonori, linux-kernel
This patchset converts POWERPC to use asm-generic/dma-mapping-common.h.
The major change is removing addr_needs_map in struct dma_mapping_ops
(1/5):
http://marc.info/?t=124719060200001&r=1&w=2
This is on the top of my swiotlb cleanup patchset:
http://marc.info/?l=linuxppc-embedded&m=124718920320951&w=2
The patchset also is available via a git tree:
git://git.kernel.org/pub/scm/linux/kernel/git/tomo/linux-2.6-misc.git powerpc
=
arch/powerpc/Kconfig | 2 +-
arch/powerpc/include/asm/device.h | 7 +-
arch/powerpc/include/asm/dma-mapping.h | 308 ++--------------------------
arch/powerpc/include/asm/pci.h | 4 +-
arch/powerpc/include/asm/swiotlb.h | 8 +-
arch/powerpc/kernel/dma-iommu.c | 2 +-
arch/powerpc/kernel/dma-swiotlb.c | 50 ++---
arch/powerpc/kernel/dma.c | 2 +-
arch/powerpc/kernel/ibmebus.c | 2 +-
arch/powerpc/kernel/pci-common.c | 6 +-
arch/powerpc/kernel/vio.c | 2 +-
arch/powerpc/platforms/85xx/mpc8536_ds.c | 3 +-
arch/powerpc/platforms/85xx/mpc85xx_ds.c | 3 +-
arch/powerpc/platforms/85xx/mpc85xx_mds.c | 3 +-
arch/powerpc/platforms/86xx/mpc86xx_hpcn.c | 3 +-
arch/powerpc/platforms/cell/iommu.c | 2 +-
arch/powerpc/platforms/ps3/system-bus.c | 4 +-
include/linux/dma-mapping.h | 1 +
18 files changed, 63 insertions(+), 349 deletions(-)
^ permalink raw reply
* [PATCH 5/5] powerpc: use asm-generic/dma-mapping-common.h
From: FUJITA Tomonori @ 2009-07-24 3:24 UTC (permalink / raw)
To: linuxppc-dev; +Cc: FUJITA Tomonori, linux-kernel
In-Reply-To: <1248405855-15546-1-git-send-email-fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
---
arch/powerpc/Kconfig | 2 +-
arch/powerpc/include/asm/dma-mapping.h | 242 +-------------------------------
2 files changed, 7 insertions(+), 237 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d00131c..0603b6c 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -120,7 +120,7 @@ config PPC
select HAVE_KRETPROBES
select HAVE_ARCH_TRACEHOOK
select HAVE_LMB
- select HAVE_DMA_ATTRS if PPC64
+ select HAVE_DMA_ATTRS
select USE_GENERIC_SMP_HELPERS if SMP
select HAVE_OPROFILE
select HAVE_SYSCALL_WRAPPERS if PPC64
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 8ca2b51..91217e4 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -14,6 +14,7 @@
#include <linux/mm.h>
#include <linux/scatterlist.h>
#include <linux/dma-attrs.h>
+#include <linux/dma-debug.h>
#include <asm/io.h>
#include <asm/swiotlb.h>
@@ -89,6 +90,11 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
dev->archdata.dma_ops = ops;
}
+/* this will be removed soon */
+#define flush_write_buffers()
+
+#include <asm-generic/dma-mapping-common.h>
+
static inline int dma_supported(struct device *dev, u64 mask)
{
struct dma_map_ops *dma_ops = get_dma_ops(dev);
@@ -117,87 +123,6 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask)
return 0;
}
-/*
- * map_/unmap_single actually call through to map/unmap_page now that all the
- * dma_map_ops have been converted over. We just have to get the page and
- * offset to pass through to map_page
- */
-static inline dma_addr_t dma_map_single_attrs(struct device *dev,
- void *cpu_addr,
- size_t size,
- enum dma_data_direction direction,
- struct dma_attrs *attrs)
-{
- struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
- BUG_ON(!dma_ops);
-
- return dma_ops->map_page(dev, virt_to_page(cpu_addr),
- (unsigned long)cpu_addr % PAGE_SIZE, size,
- direction, attrs);
-}
-
-static inline void dma_unmap_single_attrs(struct device *dev,
- dma_addr_t dma_addr,
- size_t size,
- enum dma_data_direction direction,
- struct dma_attrs *attrs)
-{
- struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
- BUG_ON(!dma_ops);
-
- dma_ops->unmap_page(dev, dma_addr, size, direction, attrs);
-}
-
-static inline dma_addr_t dma_map_page_attrs(struct device *dev,
- struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction direction,
- struct dma_attrs *attrs)
-{
- struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
- BUG_ON(!dma_ops);
-
- return dma_ops->map_page(dev, page, offset, size, direction, attrs);
-}
-
-static inline void dma_unmap_page_attrs(struct device *dev,
- dma_addr_t dma_address,
- size_t size,
- enum dma_data_direction direction,
- struct dma_attrs *attrs)
-{
- struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
- BUG_ON(!dma_ops);
-
- dma_ops->unmap_page(dev, dma_address, size, direction, attrs);
-}
-
-static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction direction,
- struct dma_attrs *attrs)
-{
- struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
- BUG_ON(!dma_ops);
- return dma_ops->map_sg(dev, sg, nents, direction, attrs);
-}
-
-static inline void dma_unmap_sg_attrs(struct device *dev,
- struct scatterlist *sg,
- int nhwentries,
- enum dma_data_direction direction,
- struct dma_attrs *attrs)
-{
- struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
- BUG_ON(!dma_ops);
- dma_ops->unmap_sg(dev, sg, nhwentries, direction, attrs);
-}
-
static inline void *dma_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t flag)
{
@@ -216,161 +141,6 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
}
-static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
- size_t size,
- enum dma_data_direction direction)
-{
- return dma_map_single_attrs(dev, cpu_addr, size, direction, NULL);
-}
-
-static inline void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
- size_t size,
- enum dma_data_direction direction)
-{
- dma_unmap_single_attrs(dev, dma_addr, size, direction, NULL);
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction direction)
-{
- return dma_map_page_attrs(dev, page, offset, size, direction, NULL);
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
- size_t size,
- enum dma_data_direction direction)
-{
- dma_unmap_page_attrs(dev, dma_address, size, direction, NULL);
-}
-
-static inline int dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, enum dma_data_direction direction)
-{
- return dma_map_sg_attrs(dev, sg, nents, direction, NULL);
-}
-
-static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
- int nhwentries,
- enum dma_data_direction direction)
-{
- dma_unmap_sg_attrs(dev, sg, nhwentries, direction, NULL);
-}
-
-#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
-static inline void dma_sync_single_for_cpu(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- enum dma_data_direction direction)
-{
- struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
- BUG_ON(!dma_ops);
-
- if (dma_ops->sync_single_range_for_cpu)
- dma_ops->sync_single_range_for_cpu(dev, dma_handle, 0,
- size, direction);
-}
-
-static inline void dma_sync_single_for_device(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- enum dma_data_direction direction)
-{
- struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
- BUG_ON(!dma_ops);
-
- if (dma_ops->sync_single_range_for_device)
- dma_ops->sync_single_range_for_device(dev, dma_handle,
- 0, size, direction);
-}
-
-static inline void dma_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sgl, int nents,
- enum dma_data_direction direction)
-{
- struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
- BUG_ON(!dma_ops);
-
- if (dma_ops->sync_sg_for_cpu)
- dma_ops->sync_sg_for_cpu(dev, sgl, nents, direction);
-}
-
-static inline void dma_sync_sg_for_device(struct device *dev,
- struct scatterlist *sgl, int nents,
- enum dma_data_direction direction)
-{
- struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
- BUG_ON(!dma_ops);
-
- if (dma_ops->sync_sg_for_device)
- dma_ops->sync_sg_for_device(dev, sgl, nents, direction);
-}
-
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
- dma_addr_t dma_handle, unsigned long offset, size_t size,
- enum dma_data_direction direction)
-{
- struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
- BUG_ON(!dma_ops);
-
- if (dma_ops->sync_single_range_for_cpu)
- dma_ops->sync_single_range_for_cpu(dev, dma_handle,
- offset, size, direction);
-}
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
- dma_addr_t dma_handle, unsigned long offset, size_t size,
- enum dma_data_direction direction)
-{
- struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
- BUG_ON(!dma_ops);
-
- if (dma_ops->sync_single_range_for_device)
- dma_ops->sync_single_range_for_device(dev, dma_handle, offset,
- size, direction);
-}
-#else /* CONFIG_PPC_NEED_DMA_SYNC_OPS */
-static inline void dma_sync_single_for_cpu(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- enum dma_data_direction direction)
-{
-}
-
-static inline void dma_sync_single_for_device(struct device *dev,
- dma_addr_t dma_handle, size_t size,
- enum dma_data_direction direction)
-{
-}
-
-static inline void dma_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sgl, int nents,
- enum dma_data_direction direction)
-{
-}
-
-static inline void dma_sync_sg_for_device(struct device *dev,
- struct scatterlist *sgl, int nents,
- enum dma_data_direction direction)
-{
-}
-
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
- dma_addr_t dma_handle, unsigned long offset, size_t size,
- enum dma_data_direction direction)
-{
-}
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
- dma_addr_t dma_handle, unsigned long offset, size_t size,
- enum dma_data_direction direction)
-{
-}
-#endif
-
static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
#ifdef CONFIG_PPC64
--
1.6.0.6
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox