[ARM] 3377/2: add support for intel xsc3 core
Patch from Lennert Buytenhek
This patch adds support for the new XScale v3 core. This is an
ARMv5 ISA core with the following additions:
- L2 cache
- I/O coherency support (on select chipsets)
- Low-Locality Reference cache attributes (replaces mini-cache)
- Supersections (v6 compatible)
- 36-bit addressing (v6 compatible)
- Single instruction cache line clean/invalidate
- LRU cache replacement (vs round-robin)
I attempted to merge the XSC3 support into proc-xscale.S, but XSC3
cores have separate errata and have to handle things like L2, so it
is simpler to keep it separate.
L2 cache support is currently a build option because the L2 enable
bit must be set before we enable the MMU and there is no easy way to
capture command line parameters at this point.
There are still optimizations that can be done such as using LLR for
copypage (in theory using the exisiting mini-cache code) but those
can be addressed down the road.
Signed-off-by: Deepak Saxena <dsaxena@plexity.net>
Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
new file mode 100644
index 0000000..f90513e
--- /dev/null
+++ b/arch/arm/mm/proc-xsc3.S
@@ -0,0 +1,498 @@
+/*
+ * linux/arch/arm/mm/proc-xsc3.S
+ *
+ * Original Author: Matthew Gilbert
+ * Current Maintainer: Deepak Saxena <dsaxena@plexity.net>
+ *
+ * Copyright 2004 (C) Intel Corp.
+ * Copyright 2005 (c) MontaVista Software, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * MMU functions for the Intel XScale3 Core (XSC3). The XSC3 core is an
+ * extension to Intel's original XScale core that adds the following
+ * features:
+ *
+ * - ARMv6 Supersections
+ * - Low Locality Reference pages (replaces mini-cache)
+ * - 36-bit addressing
+ * - L2 cache
+ * - Cache-coherency if chipset supports it
+ *
+ * Based on orignal XScale code by Nicolas Pitre
+ */
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+#include <asm/assembler.h>
+#include <asm/procinfo.h>
+#include <asm/hardware.h>
+#include <asm/pgtable.h>
+#include <asm/page.h>
+#include <asm/ptrace.h>
+#include "proc-macros.S"
+
+/*
+ * This is the maximum size of an area which will be flushed. If the
+ * area is larger than this, then we flush the whole cache.
+ */
+#define MAX_AREA_SIZE 32768
+
+/*
+ * The cache line size of the I and D cache.
+ */
+#define CACHELINESIZE 32
+
+/*
+ * The size of the data cache.
+ */
+#define CACHESIZE 32768
+
+/*
+ * Run with L2 enabled.
+ */
+#define L2_CACHE_ENABLE 1
+
+/*
+ * Enable the Branch Target Buffer (can cause crashes, see erratum #42.)
+ */
+#define BTB_ENABLE 0
+
+/*
+ * This macro is used to wait for a CP15 write and is needed
+ * when we have to ensure that the last operation to the co-pro
+ * was completed before continuing with operation.
+ */
+ .macro cpwait_ret, lr, rd
+ mrc p15, 0, \rd, c2, c0, 0 @ arbitrary read of cp15
+ sub pc, \lr, \rd, LSR #32 @ wait for completion and
+ @ flush instruction pipeline
+ .endm
+
+/*
+ * This macro cleans & invalidates the entire xsc3 dcache by set & way.
+ */
+
+ .macro clean_d_cache rd, rs
+ mov \rd, #0x1f00
+ orr \rd, \rd, #0x00e0
+1: mcr p15, 0, \rd, c7, c14, 2 @ clean/inv set/way
+ adds \rd, \rd, #0x40000000
+ bcc 1b
+ subs \rd, \rd, #0x20
+ bpl 1b
+ .endm
+
+ .text
+
+/*
+ * cpu_xsc3_proc_init()
+ *
+ * Nothing too exciting at the moment
+ */
+ENTRY(cpu_xsc3_proc_init)
+ mov pc, lr
+
+/*
+ * cpu_xsc3_proc_fin()
+ */
+ENTRY(cpu_xsc3_proc_fin)
+ str lr, [sp, #-4]!
+ mov r0, #PSR_F_BIT|PSR_I_BIT|SVC_MODE
+ msr cpsr_c, r0
+ bl xsc3_flush_kern_cache_all @ clean caches
+ mrc p15, 0, r0, c1, c0, 0 @ ctrl register
+ bic r0, r0, #0x1800 @ ...IZ...........
+ bic r0, r0, #0x0006 @ .............CA.
+ mcr p15, 0, r0, c1, c0, 0 @ disable caches
+ ldr pc, [sp], #4
+
+/*
+ * cpu_xsc3_reset(loc)
+ *
+ * Perform a soft reset of the system. Put the CPU into the
+ * same state as it would be if it had been reset, and branch
+ * to what would be the reset vector.
+ *
+ * loc: location to jump to for soft reset
+ */
+ .align 5
+ENTRY(cpu_xsc3_reset)
+ mov r1, #PSR_F_BIT|PSR_I_BIT|SVC_MODE
+ msr cpsr_c, r1 @ reset CPSR
+ mrc p15, 0, r1, c1, c0, 0 @ ctrl register
+ bic r1, r1, #0x0086 @ ........B....CA.
+ bic r1, r1, #0x3900 @ ..VIZ..S........
+ mcr p15, 0, r1, c1, c0, 0 @ ctrl register
+ mcr p15, 0, ip, c7, c7, 0 @ invalidate I,D caches & BTB
+ bic r1, r1, #0x0001 @ ...............M
+ mcr p15, 0, r1, c1, c0, 0 @ ctrl register
+ @ CAUTION: MMU turned off from this point. We count on the pipeline
+ @ already containing those two last instructions to survive.
+ mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs
+ mov pc, r0
+
+/*
+ * cpu_xsc3_do_idle()
+ *
+ * Cause the processor to idle
+ *
+ * For now we do nothing but go to idle mode for every case
+ *
+ * XScale supports clock switching, but using idle mode support
+ * allows external hardware to react to system state changes.
+
+ MMG: Come back to this one.
+ */
+ .align 5
+
+ENTRY(cpu_xsc3_do_idle)
+ mov r0, #1
+ mcr p14, 0, r0, c7, c0, 0 @ Go to IDLE
+ mov pc, lr
+
+/* ================================= CACHE ================================ */
+
+/*
+ * flush_user_cache_all()
+ *
+ * Invalidate all cache entries in a particular address
+ * space.
+ */
+ENTRY(xsc3_flush_user_cache_all)
+ /* FALLTHROUGH */
+
+/*
+ * flush_kern_cache_all()
+ *
+ * Clean and invalidate the entire cache.
+ */
+ENTRY(xsc3_flush_kern_cache_all)
+ mov r2, #VM_EXEC
+ mov ip, #0
+__flush_whole_cache:
+ clean_d_cache r0, r1
+ tst r2, #VM_EXEC
+ mcrne p15, 0, ip, c7, c5, 0 @ Invalidate I cache & BTB
+ mcrne p15, 0, ip, c7, c10, 4 @ Drain Write Buffer
+ mcrne p15, 0, ip, c7, c5, 4 @ Prefetch Flush
+ mov pc, lr
+
+/*
+ * flush_user_cache_range(start, end, vm_flags)
+ *
+ * Invalidate a range of cache entries in the specified
+ * address space.
+ *
+ * - start - start address (may not be aligned)
+ * - end - end address (exclusive, may not be aligned)
+ * - vma - vma_area_struct describing address space
+ */
+ .align 5
+ENTRY(xsc3_flush_user_cache_range)
+ mov ip, #0
+ sub r3, r1, r0 @ calculate total size
+ cmp r3, #MAX_AREA_SIZE
+ bhs __flush_whole_cache
+
+1: tst r2, #VM_EXEC
+ mcrne p15, 0, r0, c7, c5, 1 @ Invalidate I cache line
+ mcr p15, 0, r0, c7, c14, 1 @ Clean/invalidate D cache line
+ add r0, r0, #CACHELINESIZE
+ cmp r0, r1
+ blo 1b
+ tst r2, #VM_EXEC
+ mcrne p15, 0, ip, c7, c5, 6 @ Invalidate BTB
+ mcrne p15, 0, ip, c7, c10, 4 @ Drain Write Buffer
+ mcrne p15, 0, ip, c7, c5, 4 @ Prefetch Flush
+ mov pc, lr
+
+/*
+ * coherent_kern_range(start, end)
+ *
+ * Ensure coherency between the Icache and the Dcache in the
+ * region described by start. If you have non-snooping
+ * Harvard caches, you need to implement this function.
+ *
+ * - start - virtual start address
+ * - end - virtual end address
+ *
+ * Note: single I-cache line invalidation isn't used here since
+ * it also trashes the mini I-cache used by JTAG debuggers.
+ */
+ENTRY(xsc3_coherent_kern_range)
+/* FALLTHROUGH */
+ENTRY(xsc3_coherent_user_range)
+ bic r0, r0, #CACHELINESIZE - 1
+1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry
+ add r0, r0, #CACHELINESIZE
+ cmp r0, r1
+ blo 1b
+ mov r0, #0
+ mcr p15, 0, r0, c7, c5, 0 @ Invalidate I cache & BTB
+ mcr p15, 0, r0, c7, c10, 4 @ Drain Write Buffer
+ mcr p15, 0, r0, c7, c5, 4 @ Prefetch Flush
+ mov pc, lr
+
+/*
+ * flush_kern_dcache_page(void *page)
+ *
+ * Ensure no D cache aliasing occurs, either with itself or
+ * the I cache
+ *
+ * - addr - page aligned address
+ */
+ENTRY(xsc3_flush_kern_dcache_page)
+ add r1, r0, #PAGE_SZ
+1: mcr p15, 0, r0, c7, c14, 1 @ Clean/Invalidate D Cache line
+ add r0, r0, #CACHELINESIZE
+ cmp r0, r1
+ blo 1b
+ mov r0, #0
+ mcr p15, 0, r0, c7, c5, 0 @ Invalidate I cache & BTB
+ mcr p15, 0, r0, c7, c10, 4 @ Drain Write Buffer
+ mcr p15, 0, r0, c7, c5, 4 @ Prefetch Flush
+ mov pc, lr
+
+/*
+ * dma_inv_range(start, end)
+ *
+ * Invalidate (discard) the specified virtual address range.
+ * May not write back any entries. If 'start' or 'end'
+ * are not cache line aligned, those lines must be written
+ * back.
+ *
+ * - start - virtual start address
+ * - end - virtual end address
+ */
+ENTRY(xsc3_dma_inv_range)
+ tst r0, #CACHELINESIZE - 1
+ bic r0, r0, #CACHELINESIZE - 1
+ mcrne p15, 0, r0, c7, c10, 1 @ clean L1 D entry
+ mcrne p15, 1, r0, c7, c11, 1 @ clean L2 D entry
+ tst r1, #CACHELINESIZE - 1
+ mcrne p15, 0, r1, c7, c10, 1 @ clean L1 D entry
+ mcrne p15, 1, r1, c7, c11, 1 @ clean L2 D entry
+1: mcr p15, 0, r0, c7, c6, 1 @ invalidate L1 D entry
+ mcr p15, 1, r0, c7, c7, 1 @ Invalidate L2 D cache line
+ add r0, r0, #CACHELINESIZE
+ cmp r0, r1
+ blo 1b
+ mcr p15, 0, r0, c7, c10, 4 @ Drain Write Buffer
+ mov pc, lr
+
+/*
+ * dma_clean_range(start, end)
+ *
+ * Clean the specified virtual address range.
+ *
+ * - start - virtual start address
+ * - end - virtual end address
+ */
+ENTRY(xsc3_dma_clean_range)
+ bic r0, r0, #CACHELINESIZE - 1
+1: mcr p15, 0, r0, c7, c10, 1 @ clean L1 D entry
+ mcr p15, 1, r0, c7, c11, 1 @ clean L2 D entry
+ add r0, r0, #CACHELINESIZE
+ cmp r0, r1
+ blo 1b
+ mcr p15, 0, r0, c7, c10, 4 @ Drain Write Buffer
+ mov pc, lr
+
+/*
+ * dma_flush_range(start, end)
+ *
+ * Clean and invalidate the specified virtual address range.
+ *
+ * - start - virtual start address
+ * - end - virtual end address
+ */
+ENTRY(xsc3_dma_flush_range)
+ bic r0, r0, #CACHELINESIZE - 1
+1: mcr p15, 0, r0, c7, c14, 1 @ Clean/invalidate L1 D cache line
+ mcr p15, 1, r0, c7, c11, 1 @ Clean L2 D cache line
+ mcr p15, 1, r0, c7, c7, 1 @ Invalidate L2 D cache line
+ add r0, r0, #CACHELINESIZE
+ cmp r0, r1
+ blo 1b
+ mcr p15, 0, r0, c7, c10, 4 @ Drain Write Buffer
+ mov pc, lr
+
+ENTRY(xsc3_cache_fns)
+ .long xsc3_flush_kern_cache_all
+ .long xsc3_flush_user_cache_all
+ .long xsc3_flush_user_cache_range
+ .long xsc3_coherent_kern_range
+ .long xsc3_coherent_user_range
+ .long xsc3_flush_kern_dcache_page
+ .long xsc3_dma_inv_range
+ .long xsc3_dma_clean_range
+ .long xsc3_dma_flush_range
+
+ENTRY(cpu_xsc3_dcache_clean_area)
+1: mcr p15, 0, r0, c7, c10, 1 @ clean D entry
+ add r0, r0, #CACHELINESIZE
+ subs r1, r1, #CACHELINESIZE
+ bhi 1b
+ mov pc, lr
+
+/* =============================== PageTable ============================== */
+
+/*
+ * cpu_xsc3_switch_mm(pgd)
+ *
+ * Set the translation base pointer to be as described by pgd.
+ *
+ * pgd: new page tables
+ */
+ .align 5
+ENTRY(cpu_xsc3_switch_mm)
+ clean_d_cache r1, r2
+ mcr p15, 0, ip, c7, c5, 0 @ Invalidate I cache & BTB
+ mcr p15, 0, ip, c7, c10, 4 @ Drain Write Buffer
+ mcr p15, 0, ip, c7, c5, 4 @ Prefetch Flush
+#ifdef L2_CACHE_ENABLE
+ orr r0, r0, #0x18 @ cache the page table in L2
+#endif
+ mcr p15, 0, r0, c2, c0, 0 @ load page table pointer
+ mcr p15, 0, ip, c8, c7, 0 @ invalidate I & D TLBs
+ cpwait_ret lr, ip
+
+/*
+ * cpu_xsc3_set_pte(ptep, pte)
+ *
+ * Set a PTE and flush it out
+ *
+ */
+ .align 5
+ENTRY(cpu_xsc3_set_pte)
+ str r1, [r0], #-2048 @ linux version
+
+ bic r2, r1, #0xff0
+ orr r2, r2, #PTE_TYPE_EXT @ extended page
+
+ eor r3, r1, #L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_WRITE | L_PTE_DIRTY
+
+ tst r3, #L_PTE_USER @ User?
+ orrne r2, r2, #PTE_EXT_AP_URO_SRW @ yes -> user r/o, system r/w
+
+ tst r3, #L_PTE_WRITE | L_PTE_DIRTY @ Write and Dirty?
+ orreq r2, r2, #PTE_EXT_AP_UNO_SRW @ yes -> user n/a, system r/w
+ @ combined with user -> user r/w
+
+#if L2_CACHE_ENABLE
+ @ If its cacheable it needs to be in L2 also.
+ eor ip, r1, #L_PTE_CACHEABLE
+ tst ip, #L_PTE_CACHEABLE
+ orreq r2, r2, #PTE_EXT_TEX(0x5)
+#endif
+
+ tst r3, #L_PTE_PRESENT | L_PTE_YOUNG @ Present and Young?
+ movne r2, #0 @ no -> fault
+
+ str r2, [r0] @ hardware version
+ mov ip, #0
+ mcr p15, 0, r0, c7, c10, 1 @ Clean D cache line mcr
+ mcr p15, 0, ip, c7, c10, 4 @ Drain Write Buffer
+ mov pc, lr
+
+ .ltorg
+
+ .align
+
+ __INIT
+
+ .type __xsc3_setup, #function
+__xsc3_setup:
+ mov r0, #PSR_F_BIT|PSR_I_BIT|SVC_MODE
+ msr cpsr_c, r0
+ mcr p15, 0, ip, c7, c7, 0 @ invalidate I, D caches & BTB
+ mcr p15, 0, ip, c7, c10, 4 @ Drain Write Buffer
+ mcr p15, 0, ip, c7, c5, 4 @ Prefetch Flush
+ mcr p15, 0, ip, c8, c7, 0 @ invalidate I, D TLBs
+#if L2_CACHE_ENABLE
+ orr r4, r4, #0x18 @ cache the page table in L2
+#endif
+ mcr p15, 0, r4, c2, c0, 0 @ load page table pointer
+ mov r0, #1 @ Allow access to CP0 and CP13
+ orr r0, r0, #1 << 13 @ Its undefined whether this
+ mcr p15, 0, r0, c15, c1, 0 @ affects USR or SVC modes
+ mrc p15, 0, r0, c1, c0, 1 @ get auxiliary control reg
+ and r0, r0, #2 @ preserve bit P bit setting
+#if L2_CACHE_ENABLE
+ orr r0, r0, #(1 << 10) @ enable L2 for LLR cache
+#endif
+ mcr p15, 0, r0, c1, c0, 1 @ set auxiliary control reg
+ mrc p15, 0, r0, c1, c0, 0 @ get control register
+ bic r0, r0, #0x0200 @ .... ..R. .... ....
+ bic r0, r0, #0x0002 @ .... .... .... ..A.
+ orr r0, r0, #0x0005 @ .... .... .... .C.M
+#if BTB_ENABLE
+ orr r0, r0, #0x3900 @ ..VI Z..S .... ....
+#else
+ orr r0, r0, #0x3100 @ ..VI ...S .... ....
+#endif
+#if L2_CACHE_ENABLE
+ orr r0, r0, #0x4000000 @ L2 enable
+#endif
+ mov pc, lr
+
+ .size __xsc3_setup, . - __xsc3_setup
+
+ __INITDATA
+
+/*
+ * Purpose : Function pointers used to access above functions - all calls
+ * come through these
+ */
+
+ .type xsc3_processor_functions, #object
+ENTRY(xsc3_processor_functions)
+ .word v5t_early_abort
+ .word cpu_xsc3_proc_init
+ .word cpu_xsc3_proc_fin
+ .word cpu_xsc3_reset
+ .word cpu_xsc3_do_idle
+ .word cpu_xsc3_dcache_clean_area
+ .word cpu_xsc3_switch_mm
+ .word cpu_xsc3_set_pte
+ .size xsc3_processor_functions, . - xsc3_processor_functions
+
+ .section ".rodata"
+
+ .type cpu_arch_name, #object
+cpu_arch_name:
+ .asciz "armv5te"
+ .size cpu_arch_name, . - cpu_arch_name
+
+ .type cpu_elf_name, #object
+cpu_elf_name:
+ .asciz "v5"
+ .size cpu_elf_name, . - cpu_elf_name
+
+ .type cpu_xsc3_name, #object
+cpu_xsc3_name:
+ .asciz "XScale-Core3"
+ .size cpu_xsc3_name, . - cpu_xsc3_name
+
+ .align
+
+ .section ".proc.info.init", #alloc, #execinstr
+
+ .type __xsc3_proc_info,#object
+__xsc3_proc_info:
+ .long 0x69056000
+ .long 0xffffe000
+ .long 0x00000c0e
+ b __xsc3_setup
+ .long cpu_arch_name
+ .long cpu_elf_name
+ .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
+ .long cpu_xsc3_name
+ .long xsc3_processor_functions
+ .long v4wbi_tlb_fns
+ .long xsc3_mc_user_fns
+ .long xsc3_cache_fns
+ .size __xsc3_proc_info, . - __xsc3_proc_info