diff options
Diffstat (limited to 'arch/openrisc/kernel')
27 files changed, 2514 insertions, 1717 deletions
diff --git a/arch/openrisc/kernel/.gitignore b/arch/openrisc/kernel/.gitignore new file mode 100644 index 000000000000..bbb90f92d051 --- /dev/null +++ b/arch/openrisc/kernel/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +vmlinux.lds diff --git a/arch/openrisc/kernel/Makefile b/arch/openrisc/kernel/Makefile index ec6d9d37cefd..19e0eb94f2eb 100644 --- a/arch/openrisc/kernel/Makefile +++ b/arch/openrisc/kernel/Makefile @@ -1,14 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the linux kernel. # -extra-y := head.o vmlinux.lds +always-$(KBUILD_BUILTIN) := vmlinux.lds -obj-y := setup.o or32_ksyms.o process.o dma.o \ +obj-y := head.o setup.o or32_ksyms.o process.o dma.o \ traps.o time.o irq.o entry.o ptrace.o signal.o \ - sys_call_table.o + sys_call_table.o unwinder.o cacheinfo.o +obj-$(CONFIG_JUMP_LABEL) += jump_label.o +obj-$(CONFIG_SMP) += smp.o sync-timer.o +obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_OF) += prom.o +obj-y += patching.o clean: diff --git a/arch/openrisc/kernel/Makefile.syscalls b/arch/openrisc/kernel/Makefile.syscalls new file mode 100644 index 000000000000..525a1e7e7fc9 --- /dev/null +++ b/arch/openrisc/kernel/Makefile.syscalls @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += or1k time32 stat64 rlimit renameat diff --git a/arch/openrisc/kernel/asm-offsets.c b/arch/openrisc/kernel/asm-offsets.c index ddb736855863..3cc826f2216b 100644 --- a/arch/openrisc/kernel/asm-offsets.c +++ b/arch/openrisc/kernel/asm-offsets.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC asm-offsets.c * @@ -9,11 +10,6 @@ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> * - * 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. - * * This program is used to generate definitions needed by * assembly language modules. * @@ -22,6 +18,7 @@ * compile this file to assembler, and then extract the * #defines from the assembly-language output. */ +#define COMPILE_OFFSETS #include <linux/signal.h> #include <linux/sched.h> @@ -36,13 +33,11 @@ #include <linux/thread_info.h> #include <linux/kbuild.h> #include <asm/page.h> -#include <asm/pgtable.h> #include <asm/processor.h> int main(void) { /* offsets into the task_struct */ - DEFINE(TASK_STATE, offsetof(struct task_struct, state)); DEFINE(TASK_FLAGS, offsetof(struct task_struct, flags)); DEFINE(TASK_PTRACE, offsetof(struct task_struct, ptrace)); DEFINE(TASK_THREAD, offsetof(struct task_struct, thread)); diff --git a/arch/openrisc/kernel/cacheinfo.c b/arch/openrisc/kernel/cacheinfo.c new file mode 100644 index 000000000000..61230545e4ff --- /dev/null +++ b/arch/openrisc/kernel/cacheinfo.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * OpenRISC cacheinfo support + * + * Based on work done for MIPS and LoongArch. All original copyrights + * apply as per the original source declaration. + * + * OpenRISC implementation: + * Copyright (C) 2025 Sahil Siddiq <sahilcdq@proton.me> + */ + +#include <linux/cacheinfo.h> +#include <asm/cpuinfo.h> +#include <asm/spr.h> +#include <asm/spr_defs.h> + +static inline void ci_leaf_init(struct cacheinfo *this_leaf, enum cache_type type, + unsigned int level, struct cache_desc *cache, int cpu) +{ + this_leaf->type = type; + this_leaf->level = level; + this_leaf->coherency_line_size = cache->block_size; + this_leaf->number_of_sets = cache->sets; + this_leaf->ways_of_associativity = cache->ways; + this_leaf->size = cache->size; + cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map); +} + +int init_cache_level(unsigned int cpu) +{ + struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()]; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + int leaves = 0, levels = 0; + unsigned long upr = mfspr(SPR_UPR); + unsigned long iccfgr, dccfgr; + + if (!(upr & SPR_UPR_UP)) { + printk(KERN_INFO + "-- no UPR register... unable to detect configuration\n"); + return -ENOENT; + } + + if (cpu_cache_is_present(SPR_UPR_DCP)) { + dccfgr = mfspr(SPR_DCCFGR); + cpuinfo->dcache.ways = 1 << (dccfgr & SPR_DCCFGR_NCW); + cpuinfo->dcache.sets = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3); + cpuinfo->dcache.block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7); + cpuinfo->dcache.size = + cpuinfo->dcache.sets * cpuinfo->dcache.ways * cpuinfo->dcache.block_size; + leaves += 1; + printk(KERN_INFO + "-- dcache: %d bytes total, %d bytes/line, %d set(s), %d way(s)\n", + cpuinfo->dcache.size, cpuinfo->dcache.block_size, + cpuinfo->dcache.sets, cpuinfo->dcache.ways); + } else + printk(KERN_INFO "-- dcache disabled\n"); + + if (cpu_cache_is_present(SPR_UPR_ICP)) { + iccfgr = mfspr(SPR_ICCFGR); + cpuinfo->icache.ways = 1 << (iccfgr & SPR_ICCFGR_NCW); + cpuinfo->icache.sets = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3); + cpuinfo->icache.block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7); + cpuinfo->icache.size = + cpuinfo->icache.sets * cpuinfo->icache.ways * cpuinfo->icache.block_size; + leaves += 1; + printk(KERN_INFO + "-- icache: %d bytes total, %d bytes/line, %d set(s), %d way(s)\n", + cpuinfo->icache.size, cpuinfo->icache.block_size, + cpuinfo->icache.sets, cpuinfo->icache.ways); + } else + printk(KERN_INFO "-- icache disabled\n"); + + if (!leaves) + return -ENOENT; + + levels = 1; + + this_cpu_ci->num_leaves = leaves; + this_cpu_ci->num_levels = levels; + + return 0; +} + +int populate_cache_leaves(unsigned int cpu) +{ + struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()]; + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + struct cacheinfo *this_leaf = this_cpu_ci->info_list; + int level = 1; + + if (cpu_cache_is_present(SPR_UPR_DCP)) { + ci_leaf_init(this_leaf, CACHE_TYPE_DATA, level, &cpuinfo->dcache, cpu); + this_leaf->attributes = ((mfspr(SPR_DCCFGR) & SPR_DCCFGR_CWS) >> 8) ? + CACHE_WRITE_BACK : CACHE_WRITE_THROUGH; + this_leaf++; + } + + if (cpu_cache_is_present(SPR_UPR_ICP)) + ci_leaf_init(this_leaf, CACHE_TYPE_INST, level, &cpuinfo->icache, cpu); + + this_cpu_ci->cpu_map_populated = true; + + return 0; +} diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c index 0b77ddb1ee07..af932a4ad306 100644 --- a/arch/openrisc/kernel/dma.c +++ b/arch/openrisc/kernel/dma.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC Linux * @@ -9,22 +10,14 @@ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> * - * 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. - * * DMA mapping callbacks... - * As alloc_coherent is the only DMA callback being used currently, that's - * the only thing implemented properly. The rest need looking into... */ -#include <linux/dma-mapping.h> -#include <linux/dma-debug.h> -#include <linux/export.h> -#include <linux/dma-attrs.h> +#include <linux/dma-map-ops.h> +#include <linux/pagewalk.h> #include <asm/cpuinfo.h> +#include <asm/cacheflush.h> #include <asm/spr_defs.h> #include <asm/tlbflush.h> @@ -32,23 +25,24 @@ static int page_set_nocache(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { - unsigned long cl; - pte_val(*pte) |= _PAGE_CI; /* * Flush the page out of the TLB so that the new page flags get * picked up next time there's an access */ - flush_tlb_page(NULL, addr); + flush_tlb_kernel_range(addr, addr + PAGE_SIZE); /* Flush page out of dcache */ - for (cl = __pa(addr); cl < __pa(next); cl += cpuinfo.dcache_block_size) - mtspr(SPR_DCBFR, cl); + local_dcache_range_flush(__pa(addr), __pa(next)); return 0; } +static const struct mm_walk_ops set_nocache_walk_ops = { + .pte_entry = page_set_nocache, +}; + static int page_clear_nocache(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) @@ -59,101 +53,56 @@ page_clear_nocache(pte_t *pte, unsigned long addr, * Flush the page out of the TLB so that the new page flags get * picked up next time there's an access */ - flush_tlb_page(NULL, addr); + flush_tlb_kernel_range(addr, addr + PAGE_SIZE); return 0; } -/* - * Alloc "coherent" memory, which for OpenRISC means simply uncached. - * - * This function effectively just calls __get_free_pages, sets the - * cache-inhibit bit on those pages, and makes sure that the pages are - * flushed out of the cache before they are used. - * - * If the NON_CONSISTENT attribute is set, then this function just - * returns "normal", cachable memory. - * - * There are additional flags WEAK_ORDERING and WRITE_COMBINE to take - * into consideration here, too. All current known implementations of - * the OR1K support only strongly ordered memory accesses, so that flag - * is being ignored for now; uncached but write-combined memory is a - * missing feature of the OR1K. - */ -static void * -or1k_dma_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t gfp, - struct dma_attrs *attrs) -{ - unsigned long va; - void *page; - struct mm_walk walk = { - .pte_entry = page_set_nocache, - .mm = &init_mm - }; - - page = alloc_pages_exact(size, gfp); - if (!page) - return NULL; - - /* This gives us the real physical address of the first page. */ - *dma_handle = __pa(page); - - va = (unsigned long)page; +static const struct mm_walk_ops clear_nocache_walk_ops = { + .pte_entry = page_clear_nocache, +}; - if (!dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs)) { - /* - * We need to iterate through the pages, clearing the dcache for - * them and setting the cache-inhibit bit. - */ - if (walk_page_range(va, va + size, &walk)) { - free_pages_exact(page, size); - return NULL; - } - } +void *arch_dma_set_uncached(void *cpu_addr, size_t size) +{ + unsigned long va = (unsigned long)cpu_addr; + int error; - return (void *)va; + /* + * We need to iterate through the pages, clearing the dcache for + * them and setting the cache-inhibit bit. + */ + mmap_write_lock(&init_mm); + error = walk_kernel_page_table_range(va, va + size, + &set_nocache_walk_ops, NULL, NULL); + mmap_write_unlock(&init_mm); + + if (error) + return ERR_PTR(error); + return cpu_addr; } -static void -or1k_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, struct dma_attrs *attrs) +void arch_dma_clear_uncached(void *cpu_addr, size_t size) { - unsigned long va = (unsigned long)vaddr; - struct mm_walk walk = { - .pte_entry = page_clear_nocache, - .mm = &init_mm - }; - - if (!dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs)) { - /* walk_page_range shouldn't be able to fail here */ - WARN_ON(walk_page_range(va, va + size, &walk)); - } + unsigned long va = (unsigned long)cpu_addr; - free_pages_exact(vaddr, size); + mmap_write_lock(&init_mm); + /* walk_page_range shouldn't be able to fail here */ + WARN_ON(walk_kernel_page_table_range(va, va + size, + &clear_nocache_walk_ops, NULL, NULL)); + mmap_write_unlock(&init_mm); } -static dma_addr_t -or1k_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - struct dma_attrs *attrs) +void arch_sync_dma_for_device(phys_addr_t addr, size_t size, + enum dma_data_direction dir) { - unsigned long cl; - dma_addr_t addr = page_to_phys(page) + offset; - switch (dir) { case DMA_TO_DEVICE: /* Flush the dcache for the requested range */ - for (cl = addr; cl < addr + size; - cl += cpuinfo.dcache_block_size) - mtspr(SPR_DCBFR, cl); + local_dcache_range_flush(addr, addr + size); break; case DMA_FROM_DEVICE: /* Invalidate the dcache for the requested range */ - for (cl = addr; cl < addr + size; - cl += cpuinfo.dcache_block_size) - mtspr(SPR_DCBIR, cl); + local_dcache_range_inv(addr, addr + size); break; default: /* @@ -163,92 +112,4 @@ or1k_map_page(struct device *dev, struct page *page, */ break; } - - return addr; -} - -static void -or1k_unmap_page(struct device *dev, dma_addr_t dma_handle, - size_t size, enum dma_data_direction dir, - struct dma_attrs *attrs) -{ - /* Nothing special to do here... */ -} - -static int -or1k_map_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) -{ - struct scatterlist *s; - int i; - - for_each_sg(sg, s, nents, i) { - s->dma_address = or1k_map_page(dev, sg_page(s), s->offset, - s->length, dir, NULL); - } - - return nents; -} - -static void -or1k_unmap_sg(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir, - struct dma_attrs *attrs) -{ - struct scatterlist *s; - int i; - - for_each_sg(sg, s, nents, i) { - or1k_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, NULL); - } -} - -static void -or1k_sync_single_for_cpu(struct device *dev, - dma_addr_t dma_handle, size_t size, - enum dma_data_direction dir) -{ - unsigned long cl; - dma_addr_t addr = dma_handle; - - /* Invalidate the dcache for the requested range */ - for (cl = addr; cl < addr + size; cl += cpuinfo.dcache_block_size) - mtspr(SPR_DCBIR, cl); -} - -static void -or1k_sync_single_for_device(struct device *dev, - dma_addr_t dma_handle, size_t size, - enum dma_data_direction dir) -{ - unsigned long cl; - dma_addr_t addr = dma_handle; - - /* Flush the dcache for the requested range */ - for (cl = addr; cl < addr + size; cl += cpuinfo.dcache_block_size) - mtspr(SPR_DCBFR, cl); -} - -struct dma_map_ops or1k_dma_map_ops = { - .alloc = or1k_dma_alloc, - .free = or1k_dma_free, - .map_page = or1k_map_page, - .unmap_page = or1k_unmap_page, - .map_sg = or1k_map_sg, - .unmap_sg = or1k_unmap_sg, - .sync_single_for_cpu = or1k_sync_single_for_cpu, - .sync_single_for_device = or1k_sync_single_for_device, -}; -EXPORT_SYMBOL(or1k_dma_map_ops); - -/* Number of entries preallocated for DMA-API debugging */ -#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16) - -static int __init dma_init(void) -{ - dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES); - - return 0; } -fs_initcall(dma_init); diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index d8a455ede5a7..c7e90b09645e 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * OpenRISC entry.S * @@ -9,14 +10,10 @@ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> * Copyright (C) 2005 Gyorgy Jeney <nog@bsemi.com> * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> - * - * 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 <linux/linkage.h> +#include <linux/pgtable.h> #include <asm/processor.h> #include <asm/unistd.h> @@ -25,7 +22,6 @@ #include <asm/spr_defs.h> #include <asm/page.h> #include <asm/mmu.h> -#include <asm/pgtable.h> #include <asm/asm-offsets.h> #define DISABLE_INTERRUPTS(t1,t2) \ @@ -42,6 +38,61 @@ /* =========================================================[ macros ]=== */ +#ifdef CONFIG_TRACE_IRQFLAGS +/* + * Trace irq on/off creating a stack frame. + */ +#define TRACE_IRQS_OP(trace_op) \ + l.sw -8(r1),r2 /* store frame pointer */ ;\ + l.sw -4(r1),r9 /* store return address */ ;\ + l.addi r2,r1,0 /* move sp to fp */ ;\ + l.jal trace_op ;\ + l.addi r1,r1,-8 ;\ + l.ori r1,r2,0 /* restore sp */ ;\ + l.lwz r9,-4(r1) /* restore return address */ ;\ + l.lwz r2,-8(r1) /* restore fp */ ;\ +/* + * Trace irq on/off and save registers we need that would otherwise be + * clobbered. + */ +#define TRACE_IRQS_SAVE(t1,trace_op) \ + l.sw -12(r1),t1 /* save extra reg */ ;\ + l.sw -8(r1),r2 /* store frame pointer */ ;\ + l.sw -4(r1),r9 /* store return address */ ;\ + l.addi r2,r1,0 /* move sp to fp */ ;\ + l.jal trace_op ;\ + l.addi r1,r1,-12 ;\ + l.ori r1,r2,0 /* restore sp */ ;\ + l.lwz r9,-4(r1) /* restore return address */ ;\ + l.lwz r2,-8(r1) /* restore fp */ ;\ + l.lwz t1,-12(r1) /* restore extra reg */ + +#define TRACE_IRQS_OFF TRACE_IRQS_OP(trace_hardirqs_off) +#define TRACE_IRQS_ON TRACE_IRQS_OP(trace_hardirqs_on) +#define TRACE_IRQS_ON_SYSCALL \ + TRACE_IRQS_SAVE(r10,trace_hardirqs_on) ;\ + l.lwz r3,PT_GPR3(r1) ;\ + l.lwz r4,PT_GPR4(r1) ;\ + l.lwz r5,PT_GPR5(r1) ;\ + l.lwz r6,PT_GPR6(r1) ;\ + l.lwz r7,PT_GPR7(r1) ;\ + l.lwz r8,PT_GPR8(r1) ;\ + l.lwz r11,PT_GPR11(r1) +#define TRACE_IRQS_OFF_ENTRY \ + l.lwz r5,PT_SR(r1) ;\ + l.andi r3,r5,(SPR_SR_IEE|SPR_SR_TEE) ;\ + l.sfeq r5,r0 /* skip trace if irqs were already off */;\ + l.bf 1f ;\ + l.nop ;\ + TRACE_IRQS_SAVE(r4,trace_hardirqs_off) ;\ +1: +#else +#define TRACE_IRQS_OFF +#define TRACE_IRQS_ON +#define TRACE_IRQS_OFF_ENTRY +#define TRACE_IRQS_ON_SYSCALL +#endif + /* * We need to disable interrupts at beginning of RESTORE_ALL * since interrupt might come in after we've loaded EPC return address @@ -122,8 +173,8 @@ handler: ;\ l.sw PT_GPR28(r1),r28 ;\ l.sw PT_GPR29(r1),r29 ;\ /* r30 already save */ ;\ -/* l.sw PT_GPR30(r1),r30*/ ;\ l.sw PT_GPR31(r1),r31 ;\ + TRACE_IRQS_OFF_ENTRY ;\ /* Store -1 in orig_gpr11 for non-syscall exceptions */ ;\ l.addi r30,r0,-1 ;\ l.sw PT_ORIG_GPR11(r1),r30 @@ -159,9 +210,8 @@ handler: ;\ l.sw PT_GPR27(r1),r27 ;\ l.sw PT_GPR28(r1),r28 ;\ l.sw PT_GPR29(r1),r29 ;\ - /* r31 already saved */ ;\ - l.sw PT_GPR30(r1),r30 ;\ -/* l.sw PT_GPR31(r1),r31 */ ;\ + /* r30 already saved */ ;\ + l.sw PT_GPR31(r1),r31 ;\ /* Store -1 in orig_gpr11 for non-syscall exceptions */ ;\ l.addi r30,r0,-1 ;\ l.sw PT_ORIG_GPR11(r1),r30 ;\ @@ -173,17 +223,24 @@ handler: ;\ l.j _ret_from_exception ;\ l.nop +/* clobbers 'reg' */ +#define CLEAR_LWA_FLAG(reg) \ + l.movhi reg,hi(lwa_flag) ;\ + l.ori reg,reg,lo(lwa_flag) ;\ + l.sw 0(reg),r0 /* * NOTE: one should never assume that SPR_EPC, SPR_ESR, SPR_EEAR * contain the same values as when exception we're handling * occured. in fact they never do. if you need them use * values saved on stack (for SPR_EPC, SPR_ESR) or content * of r4 (for SPR_EEAR). for details look at EXCEPTION_HANDLE() - * in 'arch/or32/kernel/head.S' + * in 'arch/openrisc/kernel/head.S' */ /* =====================================================[ exceptions] === */ + __REF + /* ---[ 0x100: RESET exception ]----------------------------------------- */ EXCEPTION_ENTRY(_tng_kernel_start) @@ -193,6 +250,7 @@ EXCEPTION_ENTRY(_tng_kernel_start) /* ---[ 0x200: BUS exception ]------------------------------------------- */ EXCEPTION_ENTRY(_bus_fault_handler) + CLEAR_LWA_FLAG(r3) /* r4: EA of fault (set by EXCEPTION_HANDLE) */ l.jal do_bus_fault l.addi r3,r1,0 /* pt_regs */ @@ -202,25 +260,21 @@ EXCEPTION_ENTRY(_bus_fault_handler) /* ---[ 0x300: Data Page Fault exception ]------------------------------- */ EXCEPTION_ENTRY(_dtlb_miss_page_fault_handler) + CLEAR_LWA_FLAG(r3) l.and r5,r5,r0 l.j 1f l.nop EXCEPTION_ENTRY(_data_page_fault_handler) + CLEAR_LWA_FLAG(r3) /* set up parameters for do_page_fault */ l.ori r5,r0,0x300 // exception vector 1: l.addi r3,r1,0 // pt_regs /* r4 set be EXCEPTION_HANDLE */ // effective address of fault - /* - * __PHX__: TODO - * - * all this can be written much simpler. look at - * DTLB miss handler in the CONFIG_GUARD_PROTECTED_CORE part - */ #ifdef CONFIG_OPENRISC_NO_SPR_SR_DSX - l.lwz r6,PT_PC(r3) // address of an offending insn + l.lwz r6,PT_PC(r3) // address of an offending insn l.lwz r6,0(r6) // instruction that caused pf l.srli r6,r6,26 // check opcode for jump insn @@ -236,57 +290,57 @@ EXCEPTION_ENTRY(_data_page_fault_handler) l.bf 8f l.sfeqi r6,0x12 // l.jalr l.bf 8f - - l.nop + l.nop l.j 9f - l.nop -8: + l.nop - l.lwz r6,PT_PC(r3) // address of an offending insn +8: // offending insn is in delay slot + l.lwz r6,PT_PC(r3) // address of an offending insn l.addi r6,r6,4 l.lwz r6,0(r6) // instruction that caused pf l.srli r6,r6,26 // get opcode -9: +9: // offending instruction opcode loaded in r6 #else - l.mfspr r6,r0,SPR_SR // SR -// l.lwz r6,PT_SR(r3) // ESR - l.andi r6,r6,SPR_SR_DSX // check for delay slot exception - l.sfeqi r6,0x1 // exception happened in delay slot - l.bnf 7f - l.lwz r6,PT_PC(r3) // address of an offending insn + l.mfspr r6,r0,SPR_SR // SR + l.andi r6,r6,SPR_SR_DSX // check for delay slot exception + l.sfne r6,r0 // exception happened in delay slot + l.bnf 7f + l.lwz r6,PT_PC(r3) // address of an offending insn - l.addi r6,r6,4 // offending insn is in delay slot + l.addi r6,r6,4 // offending insn is in delay slot 7: l.lwz r6,0(r6) // instruction that caused pf l.srli r6,r6,26 // check opcode for write access #endif - l.sfgeui r6,0x34 // check opcode for write access + l.sfgeui r6,0x33 // check opcode for write access l.bnf 1f l.sfleui r6,0x37 l.bnf 1f l.ori r6,r0,0x1 // write access l.j 2f - l.nop + l.nop 1: l.ori r6,r0,0x0 // !write access 2: - /* call fault.c handler in or32/mm/fault.c */ + /* call fault.c handler in openrisc/mm/fault.c */ l.jal do_page_fault - l.nop + l.nop l.j _ret_from_exception - l.nop + l.nop /* ---[ 0x400: Insn Page Fault exception ]------------------------------- */ EXCEPTION_ENTRY(_itlb_miss_page_fault_handler) + CLEAR_LWA_FLAG(r3) l.and r5,r5,r0 l.j 1f l.nop EXCEPTION_ENTRY(_insn_page_fault_handler) + CLEAR_LWA_FLAG(r3) /* set up parameters for do_page_fault */ l.ori r5,r0,0x400 // exception vector 1: @@ -294,25 +348,27 @@ EXCEPTION_ENTRY(_insn_page_fault_handler) /* r4 set be EXCEPTION_HANDLE */ // effective address of fault l.ori r6,r0,0x0 // !write access - /* call fault.c handler in or32/mm/fault.c */ + /* call fault.c handler in openrisc/mm/fault.c */ l.jal do_page_fault - l.nop + l.nop l.j _ret_from_exception - l.nop + l.nop /* ---[ 0x500: Timer exception ]----------------------------------------- */ EXCEPTION_ENTRY(_timer_handler) + CLEAR_LWA_FLAG(r3) l.jal timer_interrupt l.addi r3,r1,0 /* pt_regs */ l.j _ret_from_intr l.nop -/* ---[ 0x600: Aligment exception ]-------------------------------------- */ +/* ---[ 0x600: Alignment exception ]-------------------------------------- */ EXCEPTION_ENTRY(_alignment_handler) + CLEAR_LWA_FLAG(r3) /* r4: EA of fault (set by EXCEPTION_HANDLE) */ l.jal do_unaligned_access l.addi r3,r1,0 /* pt_regs */ @@ -321,8 +377,8 @@ EXCEPTION_ENTRY(_alignment_handler) l.nop #if 0 -EXCEPTION_ENTRY(_aligment_handler) -// l.mfspr r2,r0,SPR_EEAR_BASE /* Load the efective addres */ +EXCEPTION_ENTRY(_alignment_handler) +// l.mfspr r2,r0,SPR_EEAR_BASE /* Load the effective address */ l.addi r2,r4,0 // l.mfspr r5,r0,SPR_EPCR_BASE /* Load the insn address */ l.lwz r5,PT_PC(r1) @@ -491,11 +547,12 @@ EXCEPTION_ENTRY(_external_irq_handler) l.bnf 1f // ext irq enabled, all ok. l.nop +#ifdef CONFIG_PRINTK l.addi r1,r1,-0x8 l.movhi r3,hi(42f) l.ori r3,r3,lo(42f) l.sw 0x0(r1),r3 - l.jal printk + l.jal _printk l.sw 0x4(r1),r4 l.addi r1,r1,0x8 @@ -504,14 +561,16 @@ EXCEPTION_ENTRY(_external_irq_handler) .string "\n\rESR interrupt bug: in _external_irq_handler (ESR %x)\n\r" .align 4 .previous +#endif l.ori r4,r4,SPR_SR_IEE // fix the bug // l.sw PT_SR(r1),r4 1: #endif + CLEAR_LWA_FLAG(r3) l.addi r3,r1,0 - l.movhi r8,hi(do_IRQ) - l.ori r8,r8,lo(do_IRQ) + l.movhi r8,hi(generic_handle_arch_irq) + l.ori r8,r8,lo(generic_handle_arch_irq) l.jalr r8 l.nop l.j _ret_from_intr @@ -542,13 +601,10 @@ UNHANDLED_EXCEPTION(_vector_0xb00,0xb00) */ _string_syscall_return: - .string "syscall return %ld \n\r\0" + .string "syscall r9:0x%08x -> syscall(%ld) return %ld\0" .align 4 ENTRY(_sys_call_handler) - /* syscalls run with interrupts enabled */ - ENABLE_INTERRUPTS(r29) // enable interrupts, r29 is temp - /* r1, EPCR, ESR a already saved */ l.sw PT_GPR2(r1),r2 /* r3-r8 must be saved because syscall restart relies @@ -556,8 +612,12 @@ ENTRY(_sys_call_handler) * they should be clobbered, otherwise */ l.sw PT_GPR3(r1),r3 - /* r4 already saved */ - /* r4 holds the EEAR address of the fault, load the original r4 */ + /* + * r4 already saved + * r4 holds the EEAR address of the fault, use it as screatch reg and + * then load the original r4 + */ + CLEAR_LWA_FLAG(r4) l.lwz r4,PT_GPR4(r1) l.sw PT_GPR5(r1),r5 l.sw PT_GPR6(r1),r6 @@ -582,6 +642,10 @@ ENTRY(_sys_call_handler) /* l.sw PT_GPR30(r1),r30 */ _syscall_check_trace_enter: + /* syscalls run with interrupts enabled */ + TRACE_IRQS_ON_SYSCALL + ENABLE_INTERRUPTS(r29) // enable interrupts, r29 is temp + /* If TIF_SYSCALL_TRACE is set, then we want to do syscall tracing */ l.lwz r30,TI_FLAGS(r10) l.andi r30,r30,_TIF_SYSCALL_TRACE @@ -615,15 +679,25 @@ _syscall_return: _syscall_debug: l.movhi r3,hi(_string_syscall_return) l.ori r3,r3,lo(_string_syscall_return) - l.ori r27,r0,1 + l.ori r27,r0,2 l.sw -4(r1),r27 l.sw -8(r1),r11 - l.addi r1,r1,-8 - l.movhi r27,hi(printk) - l.ori r27,r27,lo(printk) + l.lwz r29,PT_ORIG_GPR11(r1) + l.sw -12(r1),r29 + l.lwz r29,PT_GPR9(r1) + l.sw -16(r1),r29 + l.movhi r27,hi(_printk) + l.ori r27,r27,lo(_printk) l.jalr r27 - l.nop - l.addi r1,r1,8 + l.addi r1,r1,-16 + l.addi r1,r1,16 +#endif +#if 0 +_syscall_show_regs: + l.movhi r27,hi(show_registers) + l.ori r27,r27,lo(show_registers) + l.jalr r27 + l.or r3,r1,r1 #endif _syscall_check_trace_leave: @@ -640,8 +714,13 @@ _syscall_check_trace_leave: * interrupts that set NEED_RESCHED or SIGNALPENDING... really true? */ _syscall_check_work: +#ifdef CONFIG_DEBUG_RSEQ + l.jal rseq_syscall + l.ori r3,r1,0 +#endif /* Here we need to disable interrupts */ DISABLE_INTERRUPTS(r27,r29) + TRACE_IRQS_OFF l.lwz r30,TI_FLAGS(r10) l.andi r30,r30,_TIF_WORK_MASK l.sfne r30,r0 @@ -769,13 +848,22 @@ _syscall_badsys: /******* END SYSCALL HANDLING *******/ -/* ---[ 0xd00: Trap exception ]------------------------------------------ */ +/* ---[ 0xd00: Floating Point exception ]-------------------------------- */ + +EXCEPTION_ENTRY(_fpe_trap_handler) + CLEAR_LWA_FLAG(r3) -UNHANDLED_EXCEPTION(_vector_0xd00,0xd00) + /* r4: EA of fault (set by EXCEPTION_HANDLE) */ + l.jal do_fpe_trap + l.addi r3,r1,0 /* pt_regs */ + + l.j _ret_from_exception + l.nop /* ---[ 0xe00: Trap exception ]------------------------------------------ */ EXCEPTION_ENTRY(_trap_handler) + CLEAR_LWA_FLAG(r3) /* r4: EA of fault (set by EXCEPTION_HANDLE) */ l.jal do_trap l.addi r3,r1,0 /* pt_regs */ @@ -853,39 +941,56 @@ UNHANDLED_EXCEPTION(_vector_0x1f00,0x1f00) /* ========================================================[ return ] === */ +_resume_userspace: + DISABLE_INTERRUPTS(r3,r4) + TRACE_IRQS_OFF + l.lwz r4,TI_FLAGS(r10) + l.andi r13,r4,_TIF_WORK_MASK + l.sfeqi r13,0 + l.bf _restore_all + l.nop + _work_pending: - /* - * if (current_thread_info->flags & _TIF_NEED_RESCHED) - * schedule(); - */ - l.lwz r5,TI_FLAGS(r10) - l.andi r3,r5,_TIF_NEED_RESCHED - l.sfnei r3,0 - l.bnf _work_notifysig + l.lwz r5,PT_ORIG_GPR11(r1) + l.sfltsi r5,0 + l.bnf 1f l.nop - l.jal schedule + l.andi r5,r5,0 +1: + l.jal do_work_pending + l.ori r3,r1,0 /* pt_regs */ + + l.sfeqi r11,0 + l.bf _restore_all l.nop - l.j _resume_userspace + l.sfltsi r11,0 + l.bnf 1f l.nop - -/* Handle pending signals and notify-resume requests. - * do_notify_resume must be passed the latest pushed pt_regs, not - * necessarily the "userspace" ones. Also, pt_regs->syscallno - * must be set so that the syscall restart functionality works. - */ -_work_notifysig: - l.jal do_notify_resume - l.ori r3,r1,0 /* pt_regs */ - -_resume_userspace: - DISABLE_INTERRUPTS(r3,r4) - l.lwz r3,TI_FLAGS(r10) - l.andi r3,r3,_TIF_WORK_MASK - l.sfnei r3,0 - l.bf _work_pending + l.and r11,r11,r0 + l.ori r11,r11,__NR_restart_syscall + l.j _syscall_check_trace_enter l.nop +1: + l.lwz r11,PT_ORIG_GPR11(r1) + /* Restore arg registers */ + l.lwz r3,PT_GPR3(r1) + l.lwz r4,PT_GPR4(r1) + l.lwz r5,PT_GPR5(r1) + l.lwz r6,PT_GPR6(r1) + l.lwz r7,PT_GPR7(r1) + l.j _syscall_check_trace_enter + l.lwz r8,PT_GPR8(r1) _restore_all: +#ifdef CONFIG_TRACE_IRQFLAGS + l.lwz r4,PT_SR(r1) + l.andi r3,r4,(SPR_SR_IEE|SPR_SR_TEE) + l.sfeq r3,r0 /* skip trace if irqs were off */ + l.bf skip_hardirqs_on + l.nop + TRACE_IRQS_ON +skip_hardirqs_on: +#endif RESTORE_ALL /* This returns to userspace code */ @@ -918,11 +1023,10 @@ ENTRY(ret_from_fork) l.lwz r11,PT_GPR11(r1) /* The syscall fast path return expects call-saved registers - * r12-r28 to be untouched, so we restore them here as they + * r14-r28 to be untouched, so we restore them here as they * will have been effectively clobbered when arriving here * via the call to switch() */ - l.lwz r12,PT_GPR12(r1) l.lwz r14,PT_GPR14(r1) l.lwz r16,PT_GPR16(r1) l.lwz r18,PT_GPR18(r1) @@ -954,10 +1058,10 @@ ENTRY(ret_from_fork) /* _switch MUST never lay on page boundry, cause it runs from * effective addresses and beeing interrupted by iTLB miss would kill it. - * dTLB miss seams to never accour in the bad place since data accesses + * dTLB miss seems to never accour in the bad place since data accesses * are from task structures which are always page aligned. * - * The problem happens in RESTORE_ALL_NO_R11 where we first set the EPCR + * The problem happens in RESTORE_ALL where we first set the EPCR * register, then load the previous register values and only at the end call * the l.rfe instruction. If get TLB miss in beetwen the EPCR register gets * garbled and we end up calling l.rfe with the wrong EPCR. (same probably @@ -985,9 +1089,8 @@ ENTRY(_switch) /* No need to store r1/PT_SP as it goes into KSP below */ l.sw PT_GPR2(r1),r2 l.sw PT_GPR9(r1),r9 - /* This is wrong, r12 shouldn't be here... but GCC is broken for the time being - * and expects r12 to be callee-saved... */ - l.sw PT_GPR12(r1),r12 + + /* Save callee-saved registers to the new pt_regs */ l.sw PT_GPR14(r1),r14 l.sw PT_GPR16(r1),r16 l.sw PT_GPR18(r1),r18 @@ -1028,9 +1131,7 @@ ENTRY(_switch) /* No need to restore r10 */ /* ...and do not restore r11 */ - /* This is wrong, r12 shouldn't be here... but GCC is broken for the time being - * and expects r12 to be callee-saved... */ - l.lwz r12,PT_GPR12(r1) + /* Restore callee-saved registers */ l.lwz r14,PT_GPR14(r1) l.lwz r16,PT_GPR16(r1) l.lwz r18,PT_GPR18(r1) @@ -1083,19 +1184,30 @@ _fork_save_extra_regs_and_call: ENTRY(__sys_clone) l.movhi r29,hi(sys_clone) - l.ori r29,r29,lo(sys_clone) l.j _fork_save_extra_regs_and_call - l.addi r7,r1,0 + l.ori r29,r29,lo(sys_clone) + +ENTRY(__sys_clone3) + l.movhi r29,hi(sys_clone3) + l.j _fork_save_extra_regs_and_call + l.ori r29,r29,lo(sys_clone3) ENTRY(__sys_fork) l.movhi r29,hi(sys_fork) - l.ori r29,r29,lo(sys_fork) l.j _fork_save_extra_regs_and_call - l.addi r3,r1,0 + l.ori r29,r29,lo(sys_fork) ENTRY(sys_rt_sigreturn) - l.j _sys_rt_sigreturn + l.jal _sys_rt_sigreturn + l.addi r3,r1,0 + l.sfne r30,r0 + l.bnf _no_syscall_trace + l.nop + l.jal do_syscall_trace_leave l.addi r3,r1,0 +_no_syscall_trace: + l.j _resume_userspace + l.nop /* This is a catch-all syscall for atomic instructions for the OpenRISC 1000. * The functions takes a variable number of parameters depending on which diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S index 1d3c9c28ac25..bd760066f1cd 100644 --- a/arch/openrisc/kernel/head.S +++ b/arch/openrisc/kernel/head.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * OpenRISC head.S * @@ -8,11 +9,6 @@ * Modifications for the OpenRISC architecture: * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> - * - * 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 <linux/linkage.h> @@ -20,24 +16,25 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/serial_reg.h> +#include <linux/pgtable.h> #include <asm/processor.h> #include <asm/page.h> #include <asm/mmu.h> -#include <asm/pgtable.h> +#include <asm/thread_info.h> #include <asm/cache.h> #include <asm/spr_defs.h> #include <asm/asm-offsets.h> #include <linux/of_fdt.h> -#define tophys(rd,rs) \ - l.movhi rd,hi(-KERNELBASE) ;\ +#define tophys(rd,rs) \ + l.movhi rd,hi(-KERNELBASE) ;\ l.add rd,rd,rs -#define CLEAR_GPR(gpr) \ - l.or gpr,r0,r0 +#define CLEAR_GPR(gpr) \ + l.movhi gpr,0x0 -#define LOAD_SYMBOL_2_GPR(gpr,symbol) \ - l.movhi gpr,hi(symbol) ;\ +#define LOAD_SYMBOL_2_GPR(gpr,symbol) \ + l.movhi gpr,hi(symbol) ;\ l.ori gpr,gpr,lo(symbol) @@ -48,9 +45,31 @@ /* ============================================[ tmp store locations ]=== */ +#define SPR_SHADOW_GPR(x) ((x) + SPR_GPR_BASE + 32) + /* * emergency_print temporary stores */ +#ifdef CONFIG_OPENRISC_HAVE_SHADOW_GPRS +#define EMERGENCY_PRINT_STORE_GPR4 l.mtspr r0,r4,SPR_SHADOW_GPR(14) +#define EMERGENCY_PRINT_LOAD_GPR4 l.mfspr r4,r0,SPR_SHADOW_GPR(14) + +#define EMERGENCY_PRINT_STORE_GPR5 l.mtspr r0,r5,SPR_SHADOW_GPR(15) +#define EMERGENCY_PRINT_LOAD_GPR5 l.mfspr r5,r0,SPR_SHADOW_GPR(15) + +#define EMERGENCY_PRINT_STORE_GPR6 l.mtspr r0,r6,SPR_SHADOW_GPR(16) +#define EMERGENCY_PRINT_LOAD_GPR6 l.mfspr r6,r0,SPR_SHADOW_GPR(16) + +#define EMERGENCY_PRINT_STORE_GPR7 l.mtspr r0,r7,SPR_SHADOW_GPR(7) +#define EMERGENCY_PRINT_LOAD_GPR7 l.mfspr r7,r0,SPR_SHADOW_GPR(7) + +#define EMERGENCY_PRINT_STORE_GPR8 l.mtspr r0,r8,SPR_SHADOW_GPR(8) +#define EMERGENCY_PRINT_LOAD_GPR8 l.mfspr r8,r0,SPR_SHADOW_GPR(8) + +#define EMERGENCY_PRINT_STORE_GPR9 l.mtspr r0,r9,SPR_SHADOW_GPR(9) +#define EMERGENCY_PRINT_LOAD_GPR9 l.mfspr r9,r0,SPR_SHADOW_GPR(9) + +#else /* !CONFIG_OPENRISC_HAVE_SHADOW_GPRS */ #define EMERGENCY_PRINT_STORE_GPR4 l.sw 0x20(r0),r4 #define EMERGENCY_PRINT_LOAD_GPR4 l.lwz r4,0x20(r0) @@ -69,13 +88,28 @@ #define EMERGENCY_PRINT_STORE_GPR9 l.sw 0x34(r0),r9 #define EMERGENCY_PRINT_LOAD_GPR9 l.lwz r9,0x34(r0) +#endif /* * TLB miss handlers temorary stores */ -#define EXCEPTION_STORE_GPR9 l.sw 0x10(r0),r9 -#define EXCEPTION_LOAD_GPR9 l.lwz r9,0x10(r0) +#ifdef CONFIG_OPENRISC_HAVE_SHADOW_GPRS +#define EXCEPTION_STORE_GPR2 l.mtspr r0,r2,SPR_SHADOW_GPR(2) +#define EXCEPTION_LOAD_GPR2 l.mfspr r2,r0,SPR_SHADOW_GPR(2) + +#define EXCEPTION_STORE_GPR3 l.mtspr r0,r3,SPR_SHADOW_GPR(3) +#define EXCEPTION_LOAD_GPR3 l.mfspr r3,r0,SPR_SHADOW_GPR(3) + +#define EXCEPTION_STORE_GPR4 l.mtspr r0,r4,SPR_SHADOW_GPR(4) +#define EXCEPTION_LOAD_GPR4 l.mfspr r4,r0,SPR_SHADOW_GPR(4) +#define EXCEPTION_STORE_GPR5 l.mtspr r0,r5,SPR_SHADOW_GPR(5) +#define EXCEPTION_LOAD_GPR5 l.mfspr r5,r0,SPR_SHADOW_GPR(5) + +#define EXCEPTION_STORE_GPR6 l.mtspr r0,r6,SPR_SHADOW_GPR(6) +#define EXCEPTION_LOAD_GPR6 l.mfspr r6,r0,SPR_SHADOW_GPR(6) + +#else /* !CONFIG_OPENRISC_HAVE_SHADOW_GPRS */ #define EXCEPTION_STORE_GPR2 l.sw 0x64(r0),r2 #define EXCEPTION_LOAD_GPR2 l.lwz r2,0x64(r0) @@ -91,35 +125,67 @@ #define EXCEPTION_STORE_GPR6 l.sw 0x74(r0),r6 #define EXCEPTION_LOAD_GPR6 l.lwz r6,0x74(r0) +#endif /* * EXCEPTION_HANDLE temporary stores */ +#ifdef CONFIG_OPENRISC_HAVE_SHADOW_GPRS +#define EXCEPTION_T_STORE_GPR30 l.mtspr r0,r30,SPR_SHADOW_GPR(30) +#define EXCEPTION_T_LOAD_GPR30(reg) l.mfspr reg,r0,SPR_SHADOW_GPR(30) + +#define EXCEPTION_T_STORE_GPR10 l.mtspr r0,r10,SPR_SHADOW_GPR(10) +#define EXCEPTION_T_LOAD_GPR10(reg) l.mfspr reg,r0,SPR_SHADOW_GPR(10) + +#define EXCEPTION_T_STORE_SP l.mtspr r0,r1,SPR_SHADOW_GPR(1) +#define EXCEPTION_T_LOAD_SP(reg) l.mfspr reg,r0,SPR_SHADOW_GPR(1) + +#else /* !CONFIG_OPENRISC_HAVE_SHADOW_GPRS */ #define EXCEPTION_T_STORE_GPR30 l.sw 0x78(r0),r30 #define EXCEPTION_T_LOAD_GPR30(reg) l.lwz reg,0x78(r0) #define EXCEPTION_T_STORE_GPR10 l.sw 0x7c(r0),r10 #define EXCEPTION_T_LOAD_GPR10(reg) l.lwz reg,0x7c(r0) -#define EXCEPTION_T_STORE_SP l.sw 0x80(r0),r1 +#define EXCEPTION_T_STORE_SP l.sw 0x80(r0),r1 #define EXCEPTION_T_LOAD_SP(reg) l.lwz reg,0x80(r0) - -/* - * For UNHANLDED_EXCEPTION - */ - -#define EXCEPTION_T_STORE_GPR31 l.sw 0x84(r0),r31 -#define EXCEPTION_T_LOAD_GPR31(reg) l.lwz reg,0x84(r0) +#endif /* =========================================================[ macros ]=== */ - +#ifdef CONFIG_SMP +#define GET_CURRENT_PGD(reg,t1) \ + LOAD_SYMBOL_2_GPR(reg,current_pgd) ;\ + l.mfspr t1,r0,SPR_COREID ;\ + l.slli t1,t1,2 ;\ + l.add reg,reg,t1 ;\ + tophys (t1,reg) ;\ + l.lwz reg,0(t1) +#else #define GET_CURRENT_PGD(reg,t1) \ LOAD_SYMBOL_2_GPR(reg,current_pgd) ;\ tophys (t1,reg) ;\ l.lwz reg,0(t1) +#endif +/* Load r10 from current_thread_info_set - clobbers r1 and r30 */ +#ifdef CONFIG_SMP +#define GET_CURRENT_THREAD_INFO \ + LOAD_SYMBOL_2_GPR(r1,current_thread_info_set) ;\ + tophys (r30,r1) ;\ + l.mfspr r10,r0,SPR_COREID ;\ + l.slli r10,r10,2 ;\ + l.add r30,r30,r10 ;\ + /* r10: current_thread_info */ ;\ + l.lwz r10,0(r30) +#else +#define GET_CURRENT_THREAD_INFO \ + LOAD_SYMBOL_2_GPR(r1,current_thread_info_set) ;\ + tophys (r30,r1) ;\ + /* r10: current_thread_info */ ;\ + l.lwz r10,0(r30) +#endif /* * DSCR: this is a common hook for handling exceptions. it will save @@ -140,8 +206,7 @@ * r4 - EEAR exception EA * r10 - current pointing to current_thread_info struct * r12 - syscall 0, since we didn't come from syscall - * r13 - temp it actually contains new SR, not needed anymore - * r31 - handler address of the handler we'll jump to + * r30 - handler address of the handler we'll jump to * * handler has to save remaining registers to the exception * ksp frame *before* tainting them! @@ -162,10 +227,7 @@ l.bnf 2f /* kernel_mode */ ;\ EXCEPTION_T_STORE_SP /* delay slot */ ;\ 1: /* user_mode: */ ;\ - LOAD_SYMBOL_2_GPR(r1,current_thread_info_set) ;\ - tophys (r30,r1) ;\ - /* r10: current_thread_info */ ;\ - l.lwz r10,0(r30) ;\ + GET_CURRENT_THREAD_INFO ;\ tophys (r30,r10) ;\ l.lwz r1,(TI_KSP)(r30) ;\ /* fall through */ ;\ @@ -177,6 +239,7 @@ /* r1 is KSP, r30 is __pa(KSP) */ ;\ tophys (r30,r1) ;\ l.sw PT_GPR12(r30),r12 ;\ + /* r4 use for tmp before EA */ ;\ l.mfspr r12,r0,SPR_EPCR_BASE ;\ l.sw PT_PC(r30),r12 ;\ l.mfspr r12,r0,SPR_ESR_BASE ;\ @@ -196,7 +259,10 @@ /* r12 == 1 if we come from syscall */ ;\ CLEAR_GPR(r12) ;\ /* ----- turn on MMU ----- */ ;\ - l.ori r30,r0,(EXCEPTION_SR) ;\ + /* Carry DSX into exception SR */ ;\ + l.mfspr r30,r0,SPR_SR ;\ + l.andi r30,r30,SPR_SR_DSX ;\ + l.ori r30,r30,(EXCEPTION_SR) ;\ l.mtspr r0,r30,SPR_ESR_BASE ;\ /* r30: EA address of handler */ ;\ LOAD_SYMBOL_2_GPR(r30,handler) ;\ @@ -225,25 +291,29 @@ * */ #define UNHANDLED_EXCEPTION(handler) \ - EXCEPTION_T_STORE_GPR31 ;\ + EXCEPTION_T_STORE_GPR30 ;\ EXCEPTION_T_STORE_GPR10 ;\ EXCEPTION_T_STORE_SP ;\ /* temporary store r3, r9 into r1, r10 */ ;\ l.addi r1,r3,0x0 ;\ l.addi r10,r9,0x0 ;\ - /* the string referenced by r3 must be low enough */ ;\ + LOAD_SYMBOL_2_GPR(r9,_string_unhandled_exception) ;\ + tophys (r3,r9) ;\ l.jal _emergency_print ;\ - l.ori r3,r0,lo(_string_unhandled_exception) ;\ + l.nop ;\ l.mfspr r3,r0,SPR_NPC ;\ l.jal _emergency_print_nr ;\ - l.andi r3,r3,0x1f00 ;\ - /* the string referenced by r3 must be low enough */ ;\ + l.andi r3,r3,0x1f00 ;\ + LOAD_SYMBOL_2_GPR(r9,_string_epc_prefix) ;\ + tophys (r3,r9) ;\ l.jal _emergency_print ;\ - l.ori r3,r0,lo(_string_epc_prefix) ;\ + l.nop ;\ l.jal _emergency_print_nr ;\ - l.mfspr r3,r0,SPR_EPCR_BASE ;\ + l.mfspr r3,r0,SPR_EPCR_BASE ;\ + LOAD_SYMBOL_2_GPR(r9,_string_nl) ;\ + tophys (r3,r9) ;\ l.jal _emergency_print ;\ - l.ori r3,r0,lo(_string_nl) ;\ + l.nop ;\ /* end of printing */ ;\ l.addi r3,r1,0x0 ;\ l.addi r9,r10,0x0 ;\ @@ -254,39 +324,41 @@ /* r1: KSP, r10: current, r31: __pa(KSP) */ ;\ /* r12: temp, syscall indicator, r13 temp */ ;\ l.addi r1,r1,-(INT_FRAME_SIZE) ;\ - /* r1 is KSP, r31 is __pa(KSP) */ ;\ - tophys (r31,r1) ;\ - l.sw PT_GPR12(r31),r12 ;\ + /* r1 is KSP, r30 is __pa(KSP) */ ;\ + tophys (r30,r1) ;\ + l.sw PT_GPR12(r30),r12 ;\ l.mfspr r12,r0,SPR_EPCR_BASE ;\ - l.sw PT_PC(r31),r12 ;\ + l.sw PT_PC(r30),r12 ;\ l.mfspr r12,r0,SPR_ESR_BASE ;\ - l.sw PT_SR(r31),r12 ;\ + l.sw PT_SR(r30),r12 ;\ /* save r31 */ ;\ - EXCEPTION_T_LOAD_GPR31(r12) ;\ - l.sw PT_GPR31(r31),r12 ;\ + EXCEPTION_T_LOAD_GPR30(r12) ;\ + l.sw PT_GPR30(r30),r12 ;\ /* save r10 as was prior to exception */ ;\ EXCEPTION_T_LOAD_GPR10(r12) ;\ - l.sw PT_GPR10(r31),r12 ;\ - /* save PT_SP as was prior to exception */ ;\ + l.sw PT_GPR10(r30),r12 ;\ + /* save PT_SP as was prior to exception */ ;\ EXCEPTION_T_LOAD_SP(r12) ;\ - l.sw PT_SP(r31),r12 ;\ - l.sw PT_GPR13(r31),r13 ;\ + l.sw PT_SP(r30),r12 ;\ + l.sw PT_GPR13(r30),r13 ;\ /* --> */ ;\ /* save exception r4, set r4 = EA */ ;\ - l.sw PT_GPR4(r31),r4 ;\ + l.sw PT_GPR4(r30),r4 ;\ l.mfspr r4,r0,SPR_EEAR_BASE ;\ /* r12 == 1 if we come from syscall */ ;\ CLEAR_GPR(r12) ;\ /* ----- play a MMU trick ----- */ ;\ - l.ori r31,r0,(EXCEPTION_SR) ;\ - l.mtspr r0,r31,SPR_ESR_BASE ;\ + l.ori r30,r0,(EXCEPTION_SR) ;\ + l.mtspr r0,r30,SPR_ESR_BASE ;\ /* r31: EA address of handler */ ;\ - LOAD_SYMBOL_2_GPR(r31,handler) ;\ - l.mtspr r0,r31,SPR_EPCR_BASE ;\ + LOAD_SYMBOL_2_GPR(r30,handler) ;\ + l.mtspr r0,r30,SPR_EPCR_BASE ;\ l.rfe /* =====================================================[ exceptions] === */ + __HEAD + /* ---[ 0x100: RESET exception ]----------------------------------------- */ .org 0x100 /* Jump to .init code at _start which lives in the .head section @@ -324,7 +396,7 @@ _dispatch_do_ipage_fault: .org 0x500 EXCEPTION_HANDLE(_timer_handler) -/* ---[ 0x600: Aligment exception ]-------------------------------------- */ +/* ---[ 0x600: Alignment exception ]------------------------------------- */ .org 0x600 EXCEPTION_HANDLE(_alignment_handler) @@ -354,9 +426,9 @@ _dispatch_do_ipage_fault: .org 0xc00 EXCEPTION_HANDLE(_sys_call_handler) -/* ---[ 0xd00: Trap exception ]------------------------------------------ */ +/* ---[ 0xd00: Floating point exception ]-------------------------------- */ .org 0xd00 - UNHANDLED_EXCEPTION(_vector_0xd00) + EXCEPTION_HANDLE(_fpe_trap_handler) /* ---[ 0xe00: Trap exception ]------------------------------------------ */ .org 0xe00 @@ -436,12 +508,15 @@ _dispatch_do_ipage_fault: /* .text*/ -/* This early stuff belongs in HEAD, but some of the functions below definitely +/* This early stuff belongs in the .init.text section, but some of the functions below definitely * don't... */ - __HEAD + __INIT .global _start _start: + /* Init r0 to zero as per spec */ + CLEAR_GPR(r0) + /* save kernel parameters */ l.or r25,r0,r3 /* pointer to fdt */ @@ -452,6 +527,15 @@ _start: l.ori r3,r0,0x1 l.mtspr r0,r3,SPR_SR + /* + * Start the TTCR as early as possible, so that the RNG can make use of + * measurements of boot time from the earliest opportunity. Especially + * important is that the TTCR does not return zero by the time we reach + * random_init(). + */ + l.movhi r3,hi(SPR_TTMR_CR) + l.mtspr r0,r3,SPR_TTMR + CLEAR_GPR(r1) CLEAR_GPR(r2) CLEAR_GPR(r3) @@ -483,10 +567,17 @@ _start: CLEAR_GPR(r30) CLEAR_GPR(r31) +#ifdef CONFIG_SMP + l.mfspr r26,r0,SPR_COREID + l.sfeq r26,r0 + l.bnf secondary_wait + l.nop +#endif /* * set up initial ksp and current */ - LOAD_SYMBOL_2_GPR(r1,init_thread_union+0x2000) // setup kernel stack + /* setup kernel stack */ + LOAD_SYMBOL_2_GPR(r1,init_thread_union + THREAD_SIZE) LOAD_SYMBOL_2_GPR(r10,init_thread_union) // setup current tophys (r31,r10) l.sw TI_KSP(r31), r1 @@ -520,24 +611,10 @@ enable_dc: l.nop flush_tlb: - /* - * I N V A L I D A T E T L B e n t r i e s - */ - LOAD_SYMBOL_2_GPR(r5,SPR_DTLBMR_BASE(0)) - LOAD_SYMBOL_2_GPR(r6,SPR_ITLBMR_BASE(0)) - l.addi r7,r0,128 /* Maximum number of sets */ -1: - l.mtspr r5,r0,0x0 - l.mtspr r6,r0,0x0 - - l.addi r5,r5,1 - l.addi r6,r6,1 - l.sfeq r7,r0 - l.bnf 1b - l.addi r7,r7,-1 - + l.jal _flush_tlb + l.nop -/* The MMU needs to be enabled before or32_early_setup is called */ +/* The MMU needs to be enabled before or1k_early_setup is called */ enable_mmu: /* @@ -579,9 +656,9 @@ enable_mmu: /* magic number mismatch, set fdt pointer to null */ l.or r25,r0,r0 _fdt_found: - /* pass fdt pointer to or32_early_setup in r3 */ + /* pass fdt pointer to or1k_early_setup in r3 */ l.or r3,r0,r25 - LOAD_SYMBOL_2_GPR(r24, or32_early_setup) + LOAD_SYMBOL_2_GPR(r24, or1k_early_setup) l.jalr r24 l.nop @@ -627,10 +704,124 @@ jump_start_kernel: l.jr r30 l.nop -/* ========================================[ cache ]=== */ +_flush_tlb: + /* + * I N V A L I D A T E T L B e n t r i e s + */ + LOAD_SYMBOL_2_GPR(r5,SPR_DTLBMR_BASE(0)) + LOAD_SYMBOL_2_GPR(r6,SPR_ITLBMR_BASE(0)) + l.addi r7,r0,128 /* Maximum number of sets */ +1: + l.mtspr r5,r0,0x0 + l.mtspr r6,r0,0x0 + + l.addi r5,r5,1 + l.addi r6,r6,1 + l.sfeq r7,r0 + l.bnf 1b + l.addi r7,r7,-1 + + l.jr r9 + l.nop + +#ifdef CONFIG_SMP +secondary_wait: + /* Doze the cpu until we are asked to run */ + /* If we dont have power management skip doze */ + l.mfspr r25,r0,SPR_UPR + l.andi r25,r25,SPR_UPR_PMP + l.sfeq r25,r0 + l.bf secondary_check_release + l.nop + + /* Setup special secondary exception handler */ + LOAD_SYMBOL_2_GPR(r3, _secondary_evbar) + tophys(r25,r3) + l.mtspr r0,r25,SPR_EVBAR + + /* Enable Interrupts */ + l.mfspr r25,r0,SPR_SR + l.ori r25,r25,SPR_SR_IEE + l.mtspr r0,r25,SPR_SR + + /* Unmask interrupts interrupts */ + l.mfspr r25,r0,SPR_PICMR + l.ori r25,r25,0xffff + l.mtspr r0,r25,SPR_PICMR + + /* Doze */ + l.mfspr r25,r0,SPR_PMR + LOAD_SYMBOL_2_GPR(r3, SPR_PMR_DME) + l.or r25,r25,r3 + l.mtspr r0,r25,SPR_PMR + + /* Wakeup - Restore exception handler */ + l.mtspr r0,r0,SPR_EVBAR + +secondary_check_release: + /* + * Check if we actually got the release signal, if not go-back to + * sleep. + */ + l.mfspr r25,r0,SPR_COREID + LOAD_SYMBOL_2_GPR(r3, secondary_release) + tophys(r4, r3) + l.lwz r3,0(r4) + l.sfeq r25,r3 + l.bnf secondary_wait + l.nop + /* fall through to secondary_init */ + +secondary_init: + /* + * set up initial ksp and current + */ + LOAD_SYMBOL_2_GPR(r10, secondary_thread_info) + tophys (r30,r10) + l.lwz r10,0(r30) + l.addi r1,r10,THREAD_SIZE + tophys (r30,r10) + l.sw TI_KSP(r30),r1 + + l.jal _ic_enable + l.nop + + l.jal _dc_enable + l.nop + + l.jal _flush_tlb + l.nop + + /* + * enable dmmu & immu + */ + l.mfspr r30,r0,SPR_SR + l.movhi r28,hi(SPR_SR_DME | SPR_SR_IME) + l.ori r28,r28,lo(SPR_SR_DME | SPR_SR_IME) + l.or r30,r30,r28 + /* + * This is a bit tricky, we need to switch over from physical addresses + * to virtual addresses on the fly. + * To do that, we first set up ESR with the IME and DME bits set. + * Then EPCR is set to secondary_start and then a l.rfe is issued to + * "jump" to that. + */ + l.mtspr r0,r30,SPR_ESR_BASE + LOAD_SYMBOL_2_GPR(r30, secondary_start) + l.mtspr r0,r30,SPR_EPCR_BASE + l.rfe + +secondary_start: + LOAD_SYMBOL_2_GPR(r30, secondary_start_kernel) + l.jr r30 + l.nop + +#endif + +/* ==========================================================[ cache ]=== */ - /* aligment here so we don't change memory offsets with - * memory controler defined + /* alignment here so we don't change memory offsets with + * memory controller defined */ .align 0x2000 @@ -754,11 +945,6 @@ _dc_enable: /* ===============================================[ page table masks ]=== */ -/* bit 4 is used in hardware as write back cache bit. we never use this bit - * explicitly, so we can reuse it as _PAGE_FILE bit and mask it out when - * writing into hardware pte's - */ - #define DTLB_UP_CONVERT_MASK 0x3fa #define ITLB_UP_CONVERT_MASK 0x3a @@ -976,8 +1162,6 @@ ENTRY(dtlb_miss_handler) EXCEPTION_STORE_GPR2 EXCEPTION_STORE_GPR3 EXCEPTION_STORE_GPR4 - EXCEPTION_STORE_GPR5 - EXCEPTION_STORE_GPR6 /* * get EA of the miss */ @@ -985,91 +1169,70 @@ ENTRY(dtlb_miss_handler) /* * pmd = (pmd_t *)(current_pgd + pgd_index(daddr)); */ - GET_CURRENT_PGD(r3,r5) // r3 is current_pgd, r5 is temp + GET_CURRENT_PGD(r3,r4) // r3 is current_pgd, r4 is temp l.srli r4,r2,0x18 // >> PAGE_SHIFT + (PAGE_SHIFT - 2) l.slli r4,r4,0x2 // to get address << 2 - l.add r5,r4,r3 // r4 is pgd_index(daddr) + l.add r3,r4,r3 // r4 is pgd_index(daddr) /* * if (pmd_none(*pmd)) * goto pmd_none: */ - tophys (r4,r5) + tophys (r4,r3) l.lwz r3,0x0(r4) // get *pmd value l.sfne r3,r0 l.bnf d_pmd_none - l.andi r3,r3,~PAGE_MASK //0x1fff // ~PAGE_MASK - /* - * if (pmd_bad(*pmd)) - * pmd_clear(pmd) - * goto pmd_bad: - */ -// l.sfeq r3,r0 // check *pmd value -// l.bf d_pmd_good - l.addi r3,r0,0xffffe000 // PAGE_MASK -// l.j d_pmd_bad -// l.sw 0x0(r4),r0 // clear pmd + l.addi r3,r0,0xffffe000 // PAGE_MASK + d_pmd_good: /* * pte = *pte_offset(pmd, daddr); */ l.lwz r4,0x0(r4) // get **pmd value l.and r4,r4,r3 // & PAGE_MASK - l.srli r5,r2,0xd // >> PAGE_SHIFT, r2 == EEAR - l.andi r3,r5,0x7ff // (1UL << PAGE_SHIFT - 2) - 1 + l.srli r2,r2,0xd // >> PAGE_SHIFT, r2 == EEAR + l.andi r3,r2,0x7ff // (1UL << PAGE_SHIFT - 2) - 1 l.slli r3,r3,0x2 // to get address << 2 l.add r3,r3,r4 - l.lwz r2,0x0(r3) // this is pte at last + l.lwz r3,0x0(r3) // this is pte at last /* * if (!pte_present(pte)) */ - l.andi r4,r2,0x1 + l.andi r4,r3,0x1 l.sfne r4,r0 // is pte present l.bnf d_pte_not_present - l.addi r3,r0,0xffffe3fa // PAGE_MASK | DTLB_UP_CONVERT_MASK + l.addi r4,r0,0xffffe3fa // PAGE_MASK | DTLB_UP_CONVERT_MASK /* * fill DTLB TR register */ - l.and r4,r2,r3 // apply the mask + l.and r4,r3,r4 // apply the mask // Determine number of DMMU sets - l.mfspr r6, r0, SPR_DMMUCFGR - l.andi r6, r6, SPR_DMMUCFGR_NTS - l.srli r6, r6, SPR_DMMUCFGR_NTS_OFF + l.mfspr r2, r0, SPR_DMMUCFGR + l.andi r2, r2, SPR_DMMUCFGR_NTS + l.srli r2, r2, SPR_DMMUCFGR_NTS_OFF l.ori r3, r0, 0x1 - l.sll r3, r3, r6 // r3 = number DMMU sets DMMUCFGR - l.addi r6, r3, -1 // r6 = nsets mask - l.and r5, r5, r6 // calc offset: & (NUM_TLB_ENTRIES-1) + l.sll r3, r3, r2 // r3 = number DMMU sets DMMUCFGR + l.addi r2, r3, -1 // r2 = nsets mask + l.mfspr r3, r0, SPR_EEAR_BASE + l.srli r3, r3, 0xd // >> PAGE_SHIFT + l.and r2, r3, r2 // calc offset: & (NUM_TLB_ENTRIES-1) //NUM_TLB_ENTRIES - l.mtspr r5,r4,SPR_DTLBTR_BASE(0) + l.mtspr r2,r4,SPR_DTLBTR_BASE(0) /* * fill DTLB MR register */ - l.mfspr r2,r0,SPR_EEAR_BASE - l.addi r3,r0,0xffffe000 // PAGE_MASK - l.and r4,r2,r3 // apply PAGE_MASK to EA (__PHX__ do we really need this?) - l.ori r4,r4,0x1 // set hardware valid bit: DTBL_MR entry - l.mtspr r5,r4,SPR_DTLBMR_BASE(0) + l.slli r3, r3, 0xd /* << PAGE_SHIFT => EA & PAGE_MASK */ + l.ori r4,r3,0x1 // set hardware valid bit: DTBL_MR entry + l.mtspr r2,r4,SPR_DTLBMR_BASE(0) EXCEPTION_LOAD_GPR2 EXCEPTION_LOAD_GPR3 EXCEPTION_LOAD_GPR4 - EXCEPTION_LOAD_GPR5 - EXCEPTION_LOAD_GPR6 - l.rfe -d_pmd_bad: - l.nop 1 - EXCEPTION_LOAD_GPR2 - EXCEPTION_LOAD_GPR3 - EXCEPTION_LOAD_GPR4 - EXCEPTION_LOAD_GPR5 - EXCEPTION_LOAD_GPR6 l.rfe d_pmd_none: d_pte_not_present: EXCEPTION_LOAD_GPR2 EXCEPTION_LOAD_GPR3 EXCEPTION_LOAD_GPR4 - EXCEPTION_LOAD_GPR5 - EXCEPTION_LOAD_GPR6 EXCEPTION_HANDLE(_dtlb_miss_page_fault_handler) /* ==============================================[ ITLB miss handler ]=== */ @@ -1077,8 +1240,6 @@ ENTRY(itlb_miss_handler) EXCEPTION_STORE_GPR2 EXCEPTION_STORE_GPR3 EXCEPTION_STORE_GPR4 - EXCEPTION_STORE_GPR5 - EXCEPTION_STORE_GPR6 /* * get EA of the miss */ @@ -1088,30 +1249,19 @@ ENTRY(itlb_miss_handler) * pmd = (pmd_t *)(current_pgd + pgd_index(daddr)); * */ - GET_CURRENT_PGD(r3,r5) // r3 is current_pgd, r5 is temp + GET_CURRENT_PGD(r3,r4) // r3 is current_pgd, r5 is temp l.srli r4,r2,0x18 // >> PAGE_SHIFT + (PAGE_SHIFT - 2) l.slli r4,r4,0x2 // to get address << 2 - l.add r5,r4,r3 // r4 is pgd_index(daddr) + l.add r3,r4,r3 // r4 is pgd_index(daddr) /* * if (pmd_none(*pmd)) * goto pmd_none: */ - tophys (r4,r5) + tophys (r4,r3) l.lwz r3,0x0(r4) // get *pmd value l.sfne r3,r0 l.bnf i_pmd_none - l.andi r3,r3,0x1fff // ~PAGE_MASK - /* - * if (pmd_bad(*pmd)) - * pmd_clear(pmd) - * goto pmd_bad: - */ - -// l.sfeq r3,r0 // check *pmd value -// l.bf i_pmd_good - l.addi r3,r0,0xffffe000 // PAGE_MASK -// l.j i_pmd_bad -// l.sw 0x0(r4),r0 // clear pmd + l.addi r3,r0,0xffffe000 // PAGE_MASK i_pmd_good: /* @@ -1120,35 +1270,36 @@ i_pmd_good: */ l.lwz r4,0x0(r4) // get **pmd value l.and r4,r4,r3 // & PAGE_MASK - l.srli r5,r2,0xd // >> PAGE_SHIFT, r2 == EEAR - l.andi r3,r5,0x7ff // (1UL << PAGE_SHIFT - 2) - 1 + l.srli r2,r2,0xd // >> PAGE_SHIFT, r2 == EEAR + l.andi r3,r2,0x7ff // (1UL << PAGE_SHIFT - 2) - 1 l.slli r3,r3,0x2 // to get address << 2 l.add r3,r3,r4 - l.lwz r2,0x0(r3) // this is pte at last + l.lwz r3,0x0(r3) // this is pte at last /* * if (!pte_present(pte)) * */ - l.andi r4,r2,0x1 + l.andi r4,r3,0x1 l.sfne r4,r0 // is pte present l.bnf i_pte_not_present - l.addi r3,r0,0xffffe03a // PAGE_MASK | ITLB_UP_CONVERT_MASK + l.addi r4,r0,0xffffe03a // PAGE_MASK | ITLB_UP_CONVERT_MASK /* * fill ITLB TR register */ - l.and r4,r2,r3 // apply the mask - l.andi r3,r2,0x7c0 // _PAGE_EXEC | _PAGE_SRE | _PAGE_SWE | _PAGE_URE | _PAGE_UWE -// l.andi r3,r2,0x400 // _PAGE_EXEC + l.and r4,r3,r4 // apply the mask + l.andi r3,r3,0x7c0 // _PAGE_EXEC | _PAGE_SRE | _PAGE_SWE | _PAGE_URE | _PAGE_UWE l.sfeq r3,r0 l.bf itlb_tr_fill //_workaround // Determine number of IMMU sets - l.mfspr r6, r0, SPR_IMMUCFGR - l.andi r6, r6, SPR_IMMUCFGR_NTS - l.srli r6, r6, SPR_IMMUCFGR_NTS_OFF + l.mfspr r2, r0, SPR_IMMUCFGR + l.andi r2, r2, SPR_IMMUCFGR_NTS + l.srli r2, r2, SPR_IMMUCFGR_NTS_OFF l.ori r3, r0, 0x1 - l.sll r3, r3, r6 // r3 = number IMMU sets IMMUCFGR - l.addi r6, r3, -1 // r6 = nsets mask - l.and r5, r5, r6 // calc offset: & (NUM_TLB_ENTRIES-1) + l.sll r3, r3, r2 // r3 = number IMMU sets IMMUCFGR + l.addi r2, r3, -1 // r2 = nsets mask + l.mfspr r3, r0, SPR_EEAR_BASE + l.srli r3, r3, 0xd // >> PAGE_SHIFT + l.and r2, r3, r2 // calc offset: & (NUM_TLB_ENTRIES-1) /* * __PHX__ :: fixme @@ -1160,38 +1311,24 @@ i_pmd_good: itlb_tr_fill_workaround: l.ori r4,r4,0xc0 // | (SPR_ITLBTR_UXE | ITLBTR_SXE) itlb_tr_fill: - l.mtspr r5,r4,SPR_ITLBTR_BASE(0) + l.mtspr r2,r4,SPR_ITLBTR_BASE(0) /* * fill DTLB MR register */ - l.mfspr r2,r0,SPR_EEAR_BASE - l.addi r3,r0,0xffffe000 // PAGE_MASK - l.and r4,r2,r3 // apply PAGE_MASK to EA (__PHX__ do we really need this?) - l.ori r4,r4,0x1 // set hardware valid bit: DTBL_MR entry - l.mtspr r5,r4,SPR_ITLBMR_BASE(0) + l.slli r3, r3, 0xd /* << PAGE_SHIFT => EA & PAGE_MASK */ + l.ori r4,r3,0x1 // set hardware valid bit: ITBL_MR entry + l.mtspr r2,r4,SPR_ITLBMR_BASE(0) EXCEPTION_LOAD_GPR2 EXCEPTION_LOAD_GPR3 EXCEPTION_LOAD_GPR4 - EXCEPTION_LOAD_GPR5 - EXCEPTION_LOAD_GPR6 l.rfe -i_pmd_bad: - l.nop 1 - EXCEPTION_LOAD_GPR2 - EXCEPTION_LOAD_GPR3 - EXCEPTION_LOAD_GPR4 - EXCEPTION_LOAD_GPR5 - EXCEPTION_LOAD_GPR6 - l.rfe i_pmd_none: i_pte_not_present: EXCEPTION_LOAD_GPR2 EXCEPTION_LOAD_GPR3 EXCEPTION_LOAD_GPR4 - EXCEPTION_LOAD_GPR5 - EXCEPTION_LOAD_GPR6 EXCEPTION_HANDLE(_itlb_miss_page_fault_handler) /* ==============================================[ boot tlb handlers ]=== */ @@ -1199,274 +1336,110 @@ i_pte_not_present: /* =================================================[ debugging aids ]=== */ - .align 64 -_immu_trampoline: - .space 64 -_immu_trampoline_top: - -#define TRAMP_SLOT_0 (0x0) -#define TRAMP_SLOT_1 (0x4) -#define TRAMP_SLOT_2 (0x8) -#define TRAMP_SLOT_3 (0xc) -#define TRAMP_SLOT_4 (0x10) -#define TRAMP_SLOT_5 (0x14) -#define TRAMP_FRAME_SIZE (0x18) - -ENTRY(_immu_trampoline_workaround) - // r2 EEA - // r6 is physical EEA - tophys(r6,r2) - - LOAD_SYMBOL_2_GPR(r5,_immu_trampoline) - tophys (r3,r5) // r3 is trampoline (physical) - - LOAD_SYMBOL_2_GPR(r4,0x15000000) - l.sw TRAMP_SLOT_0(r3),r4 - l.sw TRAMP_SLOT_1(r3),r4 - l.sw TRAMP_SLOT_4(r3),r4 - l.sw TRAMP_SLOT_5(r3),r4 - - // EPC = EEA - 0x4 - l.lwz r4,0x0(r6) // load op @ EEA + 0x0 (fc address) - l.sw TRAMP_SLOT_3(r3),r4 // store it to _immu_trampoline_data - l.lwz r4,-0x4(r6) // load op @ EEA - 0x4 (f8 address) - l.sw TRAMP_SLOT_2(r3),r4 // store it to _immu_trampoline_data - - l.srli r5,r4,26 // check opcode for write access - l.sfeqi r5,0 // l.j - l.bf 0f - l.sfeqi r5,0x11 // l.jr - l.bf 1f - l.sfeqi r5,1 // l.jal - l.bf 2f - l.sfeqi r5,0x12 // l.jalr - l.bf 3f - l.sfeqi r5,3 // l.bnf - l.bf 4f - l.sfeqi r5,4 // l.bf - l.bf 5f -99: - l.nop - l.j 99b // should never happen - l.nop 1 - - // r2 is EEA - // r3 is trampoline address (physical) - // r4 is instruction - // r6 is physical(EEA) - // - // r5 - -2: // l.jal - - /* 19 20 aa aa l.movhi r9,0xaaaa - * a9 29 bb bb l.ori r9,0xbbbb - * - * where 0xaaaabbbb is EEA + 0x4 shifted right 2 - */ - - l.addi r6,r2,0x4 // this is 0xaaaabbbb - - // l.movhi r9,0xaaaa - l.ori r5,r0,0x1920 // 0x1920 == l.movhi r9 - l.sh (TRAMP_SLOT_0+0x0)(r3),r5 - l.srli r5,r6,16 - l.sh (TRAMP_SLOT_0+0x2)(r3),r5 - - // l.ori r9,0xbbbb - l.ori r5,r0,0xa929 // 0xa929 == l.ori r9 - l.sh (TRAMP_SLOT_1+0x0)(r3),r5 - l.andi r5,r6,0xffff - l.sh (TRAMP_SLOT_1+0x2)(r3),r5 - - /* falthrough, need to set up new jump offset */ - - -0: // l.j - l.slli r6,r4,6 // original offset shifted left 6 - 2 -// l.srli r6,r6,6 // original offset shifted right 2 - - l.slli r4,r2,4 // old jump position: EEA shifted left 4 -// l.srli r4,r4,6 // old jump position: shifted right 2 - - l.addi r5,r3,0xc // new jump position (physical) - l.slli r5,r5,4 // new jump position: shifted left 4 - - // calculate new jump offset - // new_off = old_off + (old_jump - new_jump) - - l.sub r5,r4,r5 // old_jump - new_jump - l.add r5,r6,r5 // orig_off + (old_jump - new_jump) - l.srli r5,r5,6 // new offset shifted right 2 - - // r5 is new jump offset - // l.j has opcode 0x0... - l.sw TRAMP_SLOT_2(r3),r5 // write it back - - l.j trampoline_out - l.nop - -/* ----------------------------- */ - -3: // l.jalr - - /* 19 20 aa aa l.movhi r9,0xaaaa - * a9 29 bb bb l.ori r9,0xbbbb - * - * where 0xaaaabbbb is EEA + 0x4 shifted right 2 - */ - - l.addi r6,r2,0x4 // this is 0xaaaabbbb - - // l.movhi r9,0xaaaa - l.ori r5,r0,0x1920 // 0x1920 == l.movhi r9 - l.sh (TRAMP_SLOT_0+0x0)(r3),r5 - l.srli r5,r6,16 - l.sh (TRAMP_SLOT_0+0x2)(r3),r5 - - // l.ori r9,0xbbbb - l.ori r5,r0,0xa929 // 0xa929 == l.ori r9 - l.sh (TRAMP_SLOT_1+0x0)(r3),r5 - l.andi r5,r6,0xffff - l.sh (TRAMP_SLOT_1+0x2)(r3),r5 - - l.lhz r5,(TRAMP_SLOT_2+0x0)(r3) // load hi part of jump instruction - l.andi r5,r5,0x3ff // clear out opcode part - l.ori r5,r5,0x4400 // opcode changed from l.jalr -> l.jr - l.sh (TRAMP_SLOT_2+0x0)(r3),r5 // write it back - - /* falthrough */ - -1: // l.jr - l.j trampoline_out - l.nop - -/* ----------------------------- */ - -4: // l.bnf -5: // l.bf - l.slli r6,r4,6 // original offset shifted left 6 - 2 -// l.srli r6,r6,6 // original offset shifted right 2 - - l.slli r4,r2,4 // old jump position: EEA shifted left 4 -// l.srli r4,r4,6 // old jump position: shifted right 2 - - l.addi r5,r3,0xc // new jump position (physical) - l.slli r5,r5,4 // new jump position: shifted left 4 - - // calculate new jump offset - // new_off = old_off + (old_jump - new_jump) - - l.add r6,r6,r4 // (orig_off + old_jump) - l.sub r6,r6,r5 // (orig_off + old_jump) - new_jump - l.srli r6,r6,6 // new offset shifted right 2 - - // r6 is new jump offset - l.lwz r4,(TRAMP_SLOT_2+0x0)(r3) // load jump instruction - l.srli r4,r4,16 - l.andi r4,r4,0xfc00 // get opcode part - l.slli r4,r4,16 - l.or r6,r4,r6 // l.b(n)f new offset - l.sw TRAMP_SLOT_2(r3),r6 // write it back - - /* we need to add l.j to EEA + 0x8 */ - tophys (r4,r2) // may not be needed (due to shifts down_ - l.addi r4,r4,(0x8 - 0x8) // jump target = r2 + 0x8 (compensate for 0x8) - // jump position = r5 + 0x8 (0x8 compensated) - l.sub r4,r4,r5 // jump offset = target - new_position + 0x8 - - l.slli r4,r4,4 // the amount of info in imediate of jump - l.srli r4,r4,6 // jump instruction with offset - l.sw TRAMP_SLOT_4(r3),r4 // write it to 4th slot - - /* fallthrough */ - -trampoline_out: - // set up new EPC to point to our trampoline code - LOAD_SYMBOL_2_GPR(r5,_immu_trampoline) - l.mtspr r0,r5,SPR_EPCR_BASE - - // immu_trampoline is (4x) CACHE_LINE aligned - // and only 6 instructions long, - // so we need to invalidate only 2 lines - - /* Establish cache block size - If BS=0, 16; - If BS=1, 32; - r14 contain block size - */ - l.mfspr r21,r0,SPR_ICCFGR - l.andi r21,r21,SPR_ICCFGR_CBS - l.srli r21,r21,7 - l.ori r23,r0,16 - l.sll r14,r23,r21 - - l.mtspr r0,r5,SPR_ICBIR - l.add r5,r5,r14 - l.mtspr r0,r5,SPR_ICBIR - - l.jr r9 - l.nop - - /* - * DSCR: prints a string referenced by r3. + * DESC: Prints ASCII character stored in r7 * - * PRMS: r3 - address of the first character of null - * terminated string to be printed + * PRMS: r7 - a 32-bit value with an ASCII character in the first byte + * position. * - * PREQ: UART at UART_BASE_ADD has to be initialized + * PREQ: The UART at UART_BASE_ADD has to be initialized * - * POST: caller should be aware that r3, r9 are changed + * POST: internally used but restores: + * r4 - to store UART_BASE_ADD + * r5 - for loading OFF_TXFULL / THRE,TEMT + * r6 - for storing bitmask (SERIAL_8250) */ -ENTRY(_emergency_print) +ENTRY(_emergency_putc) EMERGENCY_PRINT_STORE_GPR4 EMERGENCY_PRINT_STORE_GPR5 EMERGENCY_PRINT_STORE_GPR6 - EMERGENCY_PRINT_STORE_GPR7 -2: - l.lbz r7,0(r3) - l.sfeq r7,r0 - l.bf 9f - l.nop -// putc: l.movhi r4,hi(UART_BASE_ADD) + l.ori r4,r4,lo(UART_BASE_ADD) + +#if defined(CONFIG_SERIAL_LITEUART) + /* Check OFF_TXFULL status */ +1: l.lwz r5,4(r4) + l.andi r5,r5,0xff + l.sfnei r5,0 + l.bf 1b + l.nop + /* Write character */ + l.andi r7,r7,0xff + l.sw 0(r4),r7 +#elif defined(CONFIG_SERIAL_8250) + /* Check UART LSR THRE (hold) bit */ l.addi r6,r0,0x20 1: l.lbz r5,5(r4) l.andi r5,r5,0x20 l.sfeq r5,r6 l.bnf 1b - l.nop + l.nop + /* Write character */ l.sb 0(r4),r7 + /* Check UART LSR THRE|TEMT (hold, empty) bits */ l.addi r6,r0,0x60 1: l.lbz r5,5(r4) l.andi r5,r5,0x60 l.sfeq r5,r6 l.bnf 1b - l.nop + l.nop +#endif + EMERGENCY_PRINT_LOAD_GPR6 + EMERGENCY_PRINT_LOAD_GPR5 + EMERGENCY_PRINT_LOAD_GPR4 + l.jr r9 + l.nop + +/* + * DSCR: prints a string referenced by r3. + * + * PRMS: r3 - address of the first character of null + * terminated string to be printed + * + * PREQ: UART at UART_BASE_ADD has to be initialized + * + * POST: caller should be aware that r3, r9 are changed + */ +ENTRY(_emergency_print) + EMERGENCY_PRINT_STORE_GPR7 + EMERGENCY_PRINT_STORE_GPR9 + + /* Load character to r7, check for null terminator */ +2: l.lbz r7,0(r3) + l.sfeqi r7,0x0 + l.bf 9f + l.nop + + l.jal _emergency_putc + l.nop /* next character */ l.j 2b - l.addi r3,r3,0x1 + l.addi r3,r3,0x1 9: + EMERGENCY_PRINT_LOAD_GPR9 EMERGENCY_PRINT_LOAD_GPR7 - EMERGENCY_PRINT_LOAD_GPR6 - EMERGENCY_PRINT_LOAD_GPR5 - EMERGENCY_PRINT_LOAD_GPR4 l.jr r9 - l.nop + l.nop +/* + * DSCR: prints a number in r3 in hex. + * + * PRMS: r3 - a 32-bit unsigned integer + * + * PREQ: UART at UART_BASE_ADD has to be initialized + * + * POST: caller should be aware that r3, r9 are changed + */ ENTRY(_emergency_print_nr) - EMERGENCY_PRINT_STORE_GPR4 - EMERGENCY_PRINT_STORE_GPR5 - EMERGENCY_PRINT_STORE_GPR6 EMERGENCY_PRINT_STORE_GPR7 EMERGENCY_PRINT_STORE_GPR8 + EMERGENCY_PRINT_STORE_GPR9 l.addi r8,r0,32 // shift register @@ -1478,58 +1451,39 @@ ENTRY(_emergency_print_nr) /* don't skip the last zero if number == 0x0 */ l.sfeqi r8,0x4 l.bf 2f - l.nop + l.nop l.sfeq r7,r0 l.bf 1b - l.nop + l.nop 2: l.srl r7,r3,r8 l.andi r7,r7,0xf l.sflts r8,r0 - l.bf 9f + l.bf 9f + /* Numbers greater than 9 translate to a-f */ l.sfgtui r7,0x9 l.bnf 8f - l.nop + l.nop l.addi r7,r7,0x27 -8: - l.addi r7,r7,0x30 -// putc: - l.movhi r4,hi(UART_BASE_ADD) - - l.addi r6,r0,0x20 -1: l.lbz r5,5(r4) - l.andi r5,r5,0x20 - l.sfeq r5,r6 - l.bnf 1b - l.nop - - l.sb 0(r4),r7 - - l.addi r6,r0,0x60 -1: l.lbz r5,5(r4) - l.andi r5,r5,0x60 - l.sfeq r5,r6 - l.bnf 1b - l.nop + /* Convert to ascii and output character */ +8: l.jal _emergency_putc + l.addi r7,r7,0x30 /* next character */ l.j 2b l.addi r8,r8,-0x4 9: + EMERGENCY_PRINT_LOAD_GPR9 EMERGENCY_PRINT_LOAD_GPR8 EMERGENCY_PRINT_LOAD_GPR7 - EMERGENCY_PRINT_LOAD_GPR6 - EMERGENCY_PRINT_LOAD_GPR5 - EMERGENCY_PRINT_LOAD_GPR4 l.jr r9 - l.nop - + l.nop /* * This should be used for debugging only. @@ -1554,7 +1508,9 @@ ENTRY(_emergency_print_nr) ENTRY(_early_uart_init) l.movhi r3,hi(UART_BASE_ADD) + l.ori r3,r3,lo(UART_BASE_ADD) +#if defined(CONFIG_SERIAL_8250) l.addi r4,r0,0x7 l.sb 0x2(r3),r4 @@ -1572,36 +1528,38 @@ ENTRY(_early_uart_init) l.addi r4,r0,((UART_DIVISOR) & 0x000000ff) l.sb UART_DLL(r3),r4 l.sb 0x3(r3),r5 +#endif l.jr r9 - l.nop + l.nop + + .align 0x1000 + .global _secondary_evbar +_secondary_evbar: -_string_copying_linux: - .string "\n\n\n\n\n\rCopying Linux... \0" + .space 0x800 + /* Just disable interrupts and Return */ + l.ori r3,r0,SPR_SR_SM + l.mtspr r0,r3,SPR_ESR_BASE + l.rfe -_string_ok_booting: - .string "Ok, booting the kernel.\n\r\0" + .section .rodata _string_unhandled_exception: - .string "\n\rRunarunaround: Unhandled exception 0x\0" + .string "\r\nRunarunaround: Unhandled exception 0x\0" _string_epc_prefix: .string ": EPC=0x\0" _string_nl: - .string "\n\r\0" - - .global _string_esr_irq_bug -_string_esr_irq_bug: - .string "\n\rESR external interrupt bug, for details look into entry.S\n\r\0" - + .string "\r\n\0" /* ========================================[ page aligned structures ]=== */ /* * .data section should be page aligned - * (look into arch/or32/kernel/vmlinux.lds) + * (look into arch/openrisc/kernel/vmlinux.lds.S) */ .section .data,"aw" .align 8192 diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c index 8ec77bc9f1e7..f38e10962a84 100644 --- a/arch/openrisc/kernel/irq.c +++ b/arch/openrisc/kernel/irq.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC irq.c * @@ -7,20 +8,14 @@ * * Modifications for the OpenRISC architecture: * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> - * - * 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 <linux/interrupt.h> #include <linux/init.h> -#include <linux/of.h> #include <linux/ftrace.h> #include <linux/irq.h> +#include <linux/irqchip.h> #include <linux/export.h> -#include <linux/irqdomain.h> #include <linux/irqflags.h> /* read interrupt enabled status */ @@ -37,150 +32,7 @@ void arch_local_irq_restore(unsigned long flags) } EXPORT_SYMBOL(arch_local_irq_restore); - -/* OR1K PIC implementation */ - -/* We're a couple of cycles faster than the generic implementations with - * these 'fast' versions. - */ - -static void or1k_pic_mask(struct irq_data *data) -{ - mtspr(SPR_PICMR, mfspr(SPR_PICMR) & ~(1UL << data->hwirq)); -} - -static void or1k_pic_unmask(struct irq_data *data) -{ - mtspr(SPR_PICMR, mfspr(SPR_PICMR) | (1UL << data->hwirq)); -} - -static void or1k_pic_ack(struct irq_data *data) -{ - /* EDGE-triggered interrupts need to be ack'ed in order to clear - * the latch. - * LEVEL-triggered interrupts do not need to be ack'ed; however, - * ack'ing the interrupt has no ill-effect and is quicker than - * trying to figure out what type it is... - */ - - /* The OpenRISC 1000 spec says to write a 1 to the bit to ack the - * interrupt, but the OR1200 does this backwards and requires a 0 - * to be written... - */ - -#ifdef CONFIG_OR1K_1200 - /* There are two oddities with the OR1200 PIC implementation: - * i) LEVEL-triggered interrupts are latched and need to be cleared - * ii) the interrupt latch is cleared by writing a 0 to the bit, - * as opposed to a 1 as mandated by the spec - */ - - mtspr(SPR_PICSR, mfspr(SPR_PICSR) & ~(1UL << data->hwirq)); -#else - WARN(1, "Interrupt handling possibly broken\n"); - mtspr(SPR_PICSR, (1UL << data->hwirq)); -#endif -} - -static void or1k_pic_mask_ack(struct irq_data *data) -{ - /* Comments for pic_ack apply here, too */ - -#ifdef CONFIG_OR1K_1200 - mtspr(SPR_PICMR, mfspr(SPR_PICMR) & ~(1UL << data->hwirq)); - mtspr(SPR_PICSR, mfspr(SPR_PICSR) & ~(1UL << data->hwirq)); -#else - WARN(1, "Interrupt handling possibly broken\n"); - mtspr(SPR_PICMR, (1UL << data->hwirq)); - mtspr(SPR_PICSR, (1UL << data->hwirq)); -#endif -} - -#if 0 -static int or1k_pic_set_type(struct irq_data *data, unsigned int flow_type) -{ - /* There's nothing to do in the PIC configuration when changing - * flow type. Level and edge-triggered interrupts are both - * supported, but it's PIC-implementation specific which type - * is handled. */ - - return irq_setup_alt_chip(data, flow_type); -} -#endif - -static struct irq_chip or1k_dev = { - .name = "or1k-PIC", - .irq_unmask = or1k_pic_unmask, - .irq_mask = or1k_pic_mask, - .irq_ack = or1k_pic_ack, - .irq_mask_ack = or1k_pic_mask_ack, -}; - -static struct irq_domain *root_domain; - -static inline int pic_get_irq(int first) -{ - int hwirq; - - hwirq = ffs(mfspr(SPR_PICSR) >> first); - if (!hwirq) - return NO_IRQ; - else - hwirq = hwirq + first -1; - - return irq_find_mapping(root_domain, hwirq); -} - - -static int or1k_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) -{ - irq_set_chip_and_handler_name(irq, &or1k_dev, - handle_level_irq, "level"); - irq_set_status_flags(irq, IRQ_LEVEL | IRQ_NOPROBE); - - return 0; -} - -static const struct irq_domain_ops or1k_irq_domain_ops = { - .xlate = irq_domain_xlate_onecell, - .map = or1k_map, -}; - -/* - * This sets up the IRQ domain for the PIC built in to the OpenRISC - * 1000 CPU. This is the "root" domain as these are the interrupts - * that directly trigger an exception in the CPU. - */ -static void __init or1k_irq_init(void) -{ - struct device_node *intc = NULL; - - /* The interrupt controller device node is mandatory */ - intc = of_find_compatible_node(NULL, NULL, "opencores,or1k-pic"); - BUG_ON(!intc); - - /* Disable all interrupts until explicitly requested */ - mtspr(SPR_PICMR, (0UL)); - - root_domain = irq_domain_add_linear(intc, 32, - &or1k_irq_domain_ops, NULL); -} - void __init init_IRQ(void) { - or1k_irq_init(); -} - -void __irq_entry do_IRQ(struct pt_regs *regs) -{ - int irq = -1; - struct pt_regs *old_regs = set_irq_regs(regs); - - irq_enter(); - - while ((irq = pic_get_irq(irq + 1)) != NO_IRQ) - generic_handle_irq(irq); - - irq_exit(); - set_irq_regs(old_regs); + irqchip_init(); } diff --git a/arch/openrisc/kernel/jump_label.c b/arch/openrisc/kernel/jump_label.c new file mode 100644 index 000000000000..ab7137c23b46 --- /dev/null +++ b/arch/openrisc/kernel/jump_label.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025 Chen Miao + * + * Based on arch/arm/kernel/jump_label.c + */ +#include <linux/jump_label.h> +#include <linux/kernel.h> +#include <linux/memory.h> +#include <asm/bug.h> +#include <asm/cacheflush.h> +#include <asm/text-patching.h> + +bool arch_jump_label_transform_queue(struct jump_entry *entry, + enum jump_label_type type) +{ + void *addr = (void *)jump_entry_code(entry); + u32 insn; + + if (type == JUMP_LABEL_JMP) { + long offset; + + offset = jump_entry_target(entry) - jump_entry_code(entry); + /* + * The actual maximum range of the l.j instruction's offset is -134,217,728 + * ~ 134,217,724 (sign 26-bit imm). + * For the original jump range, we need to right-shift N by 2 to obtain the + * instruction's offset. + */ + WARN_ON_ONCE(offset < -134217728 || offset > 134217724); + + /* 26bit imm mask */ + offset = (offset >> 2) & 0x03ffffff; + + insn = offset; + } else { + insn = OPENRISC_INSN_NOP; + } + + if (early_boot_irqs_disabled) + copy_to_kernel_nofault(addr, &insn, sizeof(insn)); + else + patch_insn_write(addr, insn); + + return true; +} + +void arch_jump_label_transform_apply(void) +{ + kick_all_cpus_sync(); +} diff --git a/arch/openrisc/kernel/module.c b/arch/openrisc/kernel/module.c index 10ff50f0202a..4ac4fbaa827c 100644 --- a/arch/openrisc/kernel/module.c +++ b/arch/openrisc/kernel/module.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC module.c * @@ -7,11 +8,6 @@ * * Modifications for the OpenRISC architecture: * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> - * - * 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 <linux/moduleloader.h> @@ -43,24 +39,36 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, value = sym->st_value + rel[i].r_addend; switch (ELF32_R_TYPE(rel[i].r_info)) { - case R_OR32_32: + case R_OR1K_32: *location = value; break; - case R_OR32_CONST: - location = (uint16_t *)location + 1; - *((uint16_t *)location) = (uint16_t) (value); + case R_OR1K_LO_16_IN_INSN: + *((uint16_t *)location + 1) = value; break; - case R_OR32_CONSTH: - location = (uint16_t *)location + 1; - *((uint16_t *)location) = (uint16_t) (value >> 16); + case R_OR1K_HI_16_IN_INSN: + *((uint16_t *)location + 1) = value >> 16; break; - case R_OR32_JUMPTARG: + case R_OR1K_INSN_REL_26: value -= (uint32_t)location; value >>= 2; value &= 0x03ffffff; value |= *location & 0xfc000000; *location = value; break; + case R_OR1K_32_PCREL: + value -= (uint32_t)location; + *location = value; + break; + case R_OR1K_AHI16: + /* Adjust the operand to match with a signed LO16. */ + value += 0x8000; + *((uint16_t *)location + 1) = value >> 16; + break; + case R_OR1K_SLO16: + /* Split value lower 16-bits. */ + value = ((value & 0xf800) << 10) | (value & 0x7ff); + *location = (*location & ~0x3e007ff) | value; + break; default: pr_err("module %s: Unknown relocation: %u\n", me->name, ELF32_R_TYPE(rel[i].r_info)); diff --git a/arch/openrisc/kernel/or32_ksyms.c b/arch/openrisc/kernel/or32_ksyms.c index 83ccf7c0c58d..212e5f85004c 100644 --- a/arch/openrisc/kernel/or32_ksyms.c +++ b/arch/openrisc/kernel/or32_ksyms.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC or32_ksyms.c * @@ -8,28 +9,23 @@ * Modifications for the OpenRISC architecture: * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> - * - * 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 <linux/module.h> +#include <linux/export.h> #include <linux/elfcore.h> #include <linux/sched.h> #include <linux/in6.h> #include <linux/interrupt.h> #include <linux/vmalloc.h> #include <linux/semaphore.h> +#include <linux/pgtable.h> #include <asm/processor.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/checksum.h> #include <asm/io.h> #include <asm/hardirq.h> #include <asm/delay.h> -#include <asm/pgalloc.h> #define DECLARE_EXPORT(name) extern void name(void); EXPORT_SYMBOL(name) @@ -42,5 +38,9 @@ DECLARE_EXPORT(__muldi3); DECLARE_EXPORT(__ashrdi3); DECLARE_EXPORT(__ashldi3); DECLARE_EXPORT(__lshrdi3); +DECLARE_EXPORT(__ucmpdi2); +EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(__copy_tofrom_user); +EXPORT_SYMBOL(__clear_user); +EXPORT_SYMBOL(memset); diff --git a/arch/openrisc/kernel/patching.c b/arch/openrisc/kernel/patching.c new file mode 100644 index 000000000000..d186172beb33 --- /dev/null +++ b/arch/openrisc/kernel/patching.c @@ -0,0 +1,79 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2020 SiFive + * Copyright (C) 2025 Chen Miao + */ + +#include <linux/mm.h> +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/uaccess.h> + +#include <asm/insn-def.h> +#include <asm/cacheflush.h> +#include <asm/page.h> +#include <asm/fixmap.h> +#include <asm/text-patching.h> +#include <asm/sections.h> + +static DEFINE_RAW_SPINLOCK(patch_lock); + +static __always_inline void *patch_map(void *addr, int fixmap) +{ + uintptr_t uaddr = (uintptr_t) addr; + phys_addr_t phys; + + if (core_kernel_text(uaddr)) { + phys = __pa_symbol(addr); + } else { + struct page *page = vmalloc_to_page(addr); + BUG_ON(!page); + phys = page_to_phys(page) + offset_in_page(addr); + } + + return (void *)set_fixmap_offset(fixmap, phys); +} + +static void patch_unmap(int fixmap) +{ + clear_fixmap(fixmap); +} + +static int __patch_insn_write(void *addr, u32 insn) +{ + void *waddr = addr; + unsigned long flags = 0; + int ret; + + raw_spin_lock_irqsave(&patch_lock, flags); + + waddr = patch_map(addr, FIX_TEXT_POKE0); + + ret = copy_to_kernel_nofault(waddr, &insn, OPENRISC_INSN_SIZE); + local_icache_range_inv((unsigned long)waddr, + (unsigned long)waddr + OPENRISC_INSN_SIZE); + + patch_unmap(FIX_TEXT_POKE0); + + raw_spin_unlock_irqrestore(&patch_lock, flags); + + return ret; +} + +/* + * patch_insn_write - Write a single instruction to a specified memory location + * This API provides a single-instruction patching, primarily used for runtime + * code modification. + * By the way, the insn size must be 4 bytes. + */ +int patch_insn_write(void *addr, u32 insn) +{ + u32 *tp = addr; + int ret; + + if ((uintptr_t) tp & 0x3) + return -EINVAL; + + ret = __patch_insn_write(tp, insn); + + return ret; +} diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 386af258591d..73ffb9fa3118 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC process.c * @@ -9,21 +10,18 @@ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> * - * 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. - * * This file handles the architecture-dependent parts of process handling... */ #define __KERNEL_SYSCALLS__ -#include <stdarg.h> - +#include <linux/cpu.h> #include <linux/errno.h> #include <linux/sched.h> +#include <linux/sched/debug.h> +#include <linux/sched/task.h> +#include <linux/sched/task_stack.h> #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/mm.h> #include <linux/stddef.h> #include <linux/unistd.h> @@ -35,12 +33,14 @@ #include <linux/init_task.h> #include <linux/mqueue.h> #include <linux/fs.h> +#include <linux/reboot.h> -#include <asm/uaccess.h> -#include <asm/pgtable.h> +#include <linux/uaccess.h> +#include <asm/fpu.h> #include <asm/io.h> #include <asm/processor.h> #include <asm/spr_defs.h> +#include <asm/switch_to.h> #include <linux/smp.h> @@ -51,9 +51,27 @@ */ struct thread_info *current_thread_info_set[NR_CPUS] = { &init_thread_info, }; -void machine_restart(void) +void machine_restart(char *cmd) +{ + do_kernel_restart(cmd); + + __asm__("l.nop 13"); + + /* Give a grace period for failure to restart of 1s */ + mdelay(1000); + + /* Whoops - the platform was unable to reboot. Tell the user! */ + pr_emerg("Reboot failed -- System halted\n"); + while (1); +} + +/* + * This is used if a sys-off handler was not set by a power management + * driver, in this case we can assume we are on a simulator. On + * OpenRISC simulators l.nop 1 will trigger the simulator exit. + */ +static void default_power_off(void) { - printk(KERN_INFO "*** MACHINE RESTART ***\n"); __asm__("l.nop 1"); } @@ -72,10 +90,24 @@ void machine_halt(void) void machine_power_off(void) { printk(KERN_INFO "*** MACHINE POWER OFF ***\n"); - __asm__("l.nop 1"); + do_kernel_power_off(); + default_power_off(); +} + +/* + * Send the doze signal to the cpu if available. + * Make sure, that all interrupts are enabled + */ +void arch_cpu_idle(void) +{ + raw_local_irq_enable(); + if (mfspr(SPR_UPR) & SPR_UPR_PMP) + mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME); + raw_local_irq_disable(); } -void (*pm_power_off) (void) = machine_power_off; +void (*pm_power_off)(void) = NULL; +EXPORT_SYMBOL(pm_power_off); /* * When a process does an "exec", machine state like FPU and debug @@ -88,22 +120,11 @@ void flush_thread(void) void show_regs(struct pt_regs *regs) { - extern void show_registers(struct pt_regs *regs); - show_regs_print_info(KERN_DEFAULT); /* __PHX__ cleanup this mess */ show_registers(regs); } -unsigned long thread_saved_pc(struct task_struct *t) -{ - return (unsigned long)user_regs(t->stack)->pc; -} - -void release_thread(struct task_struct *dead_task) -{ -} - /* * Copy the thread-specific (arch specific) info from the current * process to the new one p @@ -116,7 +137,7 @@ extern asmlinkage void ret_from_fork(void); * @usp: user stack pointer or fn for kernel thread * @arg: arg to fn for kernel thread; always NULL for userspace thread * @p: the newly created task - * @regs: CPU context to copy for userspace thread; always NULL for kthread + * @tls: the Thread Local Storage pointer for the new process * * At the top of a newly initialized kernel stack are two stacked pt_reg * structures. The first (topmost) is the userspace context of the thread. @@ -142,9 +163,11 @@ extern asmlinkage void ret_from_fork(void); */ int -copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, struct task_struct *p) +copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { + u64 clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long tls = args->tls; struct pt_regs *userregs; struct pt_regs *kregs; unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE; @@ -152,8 +175,6 @@ copy_thread(unsigned long clone_flags, unsigned long usp, top_of_kernel_stack = sp; - p->set_child_tid = p->clear_child_tid = NULL; - /* Locate userspace context on stack... */ sp -= STACK_FRAME_OVERHEAD; /* redzone */ sp -= sizeof(struct pt_regs); @@ -164,15 +185,22 @@ copy_thread(unsigned long clone_flags, unsigned long usp, sp -= sizeof(struct pt_regs); kregs = (struct pt_regs *)sp; - if (unlikely(p->flags & PF_KTHREAD)) { + if (unlikely(args->fn)) { memset(kregs, 0, sizeof(struct pt_regs)); - kregs->gpr[20] = usp; /* fn, kernel thread */ - kregs->gpr[22] = arg; + kregs->gpr[20] = (unsigned long)args->fn; + kregs->gpr[22] = (unsigned long)args->fn_arg; } else { *userregs = *current_pt_regs(); if (usp) userregs->sp = usp; + + /* + * For CLONE_SETTLS set "tp" (r10) to the TLS pointer. + */ + if (clone_flags & CLONE_SETTLS) + userregs->gpr[10] = tls; + userregs->gpr[11] = 0; /* Result from fork() */ kregs->gpr[20] = 0; /* Userspace thread */ @@ -197,7 +225,6 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { unsigned long sr = mfspr(SPR_SR) & ~SPR_SR_SM; - set_fs(USER_DS); memset(regs, 0, sizeof(struct pt_regs)); regs->pc = pc; @@ -205,15 +232,9 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) regs->sp = sp; } -/* Fill in the fpu structure for a core dump. */ -int dump_fpu(struct pt_regs *regs, elf_fpregset_t * fpu) -{ - /* TODO */ - return 0; -} - extern struct thread_info *_switch(struct thread_info *old_ti, struct thread_info *new_ti); +extern int lwa_flag; struct task_struct *__switch_to(struct task_struct *old, struct task_struct *new) @@ -224,6 +245,8 @@ struct task_struct *__switch_to(struct task_struct *old, local_irq_save(flags); + save_fpu(current); + /* current_set is an array of saved current pointers * (one for each cpu). we need them at user->kernel transition, * while we save them at kernel->user transition @@ -231,9 +254,13 @@ struct task_struct *__switch_to(struct task_struct *old, new_ti = new->stack; old_ti = old->stack; + lwa_flag = 0; + current_thread_info_set[smp_processor_id()] = new_ti; last = (_switch(old_ti, new_ti))->task; + restore_fpu(current); + local_irq_restore(flags); return last; @@ -253,7 +280,7 @@ void dump_elf_thread(elf_greg_t *dest, struct pt_regs* regs) dest[35] = 0; } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { /* TODO */ diff --git a/arch/openrisc/kernel/prom.c b/arch/openrisc/kernel/prom.c index 5869e3fa5dd3..e424e9bd12a7 100644 --- a/arch/openrisc/kernel/prom.c +++ b/arch/openrisc/kernel/prom.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC prom.c * @@ -8,99 +9,19 @@ * Modifications for the OpenRISC architecture: * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> * - * 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. - * * Architecture specific procedures for creating, accessing and * interpreting the device tree. - * */ -#include <stdarg.h> -#include <linux/kernel.h> -#include <linux/string.h> #include <linux/init.h> -#include <linux/threads.h> -#include <linux/spinlock.h> #include <linux/types.h> -#include <linux/pci.h> -#include <linux/stringify.h> -#include <linux/delay.h> -#include <linux/initrd.h> -#include <linux/bitops.h> -#include <linux/module.h> -#include <linux/kexec.h> -#include <linux/debugfs.h> -#include <linux/irq.h> #include <linux/memblock.h> #include <linux/of_fdt.h> -#include <asm/prom.h> #include <asm/page.h> -#include <asm/processor.h> -#include <asm/irq.h> -#include <linux/io.h> -#include <asm/mmu.h> -#include <asm/pgtable.h> -#include <asm/sections.h> -#include <asm/setup.h> - -extern char cmd_line[COMMAND_LINE_SIZE]; - -void __init early_init_dt_add_memory_arch(u64 base, u64 size) -{ - size &= PAGE_MASK; - memblock_add(base, size); -} - -void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) -{ - return __va(memblock_alloc(size, align)); -} void __init early_init_devtree(void *params) { - void *alloc; - - /* Setup flat device-tree pointer */ - initial_boot_params = params; - - - /* Retrieve various informations from the /chosen node of the - * device-tree, including the platform type, initrd location and - * size, TCE reserve, and more ... - */ - of_scan_flat_dt(early_init_dt_scan_chosen, cmd_line); - - /* Scan memory nodes and rebuild MEMBLOCKs */ - of_scan_flat_dt(early_init_dt_scan_root, NULL); - of_scan_flat_dt(early_init_dt_scan_memory, NULL); - - /* Save command line for /proc/cmdline and then parse parameters */ - strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE); - + early_init_dt_scan(params, __pa(params)); memblock_allow_resize(); - - /* We must copy the flattend device tree from init memory to regular - * memory because the device tree references the strings in it - * directly. - */ - - alloc = __va(memblock_alloc(initial_boot_params->totalsize, PAGE_SIZE)); - - memcpy(alloc, initial_boot_params, initial_boot_params->totalsize); - - initial_boot_params = alloc; -} - -#ifdef CONFIG_BLK_DEV_INITRD -void __init early_init_dt_setup_initrd_arch(unsigned long start, - unsigned long end) -{ - initrd_start = (unsigned long)__va(start); - initrd_end = (unsigned long)__va(end); - initrd_below_start_ok = 1; } -#endif diff --git a/arch/openrisc/kernel/ptrace.c b/arch/openrisc/kernel/ptrace.c index 71a2a0c34c65..552489b24855 100644 --- a/arch/openrisc/kernel/ptrace.c +++ b/arch/openrisc/kernel/ptrace.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC ptrace.c * @@ -9,16 +10,11 @@ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> * Copyright (C) 2005 Gyorgy Jeney <nog@bsemi.com> * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> - * - * 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 <stddef.h> #include <linux/kernel.h> #include <linux/sched.h> +#include <linux/sched/task_stack.h> #include <linux/string.h> #include <linux/mm.h> @@ -26,13 +22,14 @@ #include <linux/ptrace.h> #include <linux/audit.h> #include <linux/regset.h> -#include <linux/tracehook.h> #include <linux/elf.h> #include <asm/thread_info.h> -#include <asm/segment.h> #include <asm/page.h> -#include <asm/pgtable.h> + +asmlinkage long do_syscall_trace_enter(struct pt_regs *regs); + +asmlinkage void do_syscall_trace_leave(struct pt_regs *regs); /* * Copy the thread state to a regset that can be interpreted by userspace. @@ -50,29 +47,15 @@ */ static int genregs_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user * ubuf) + struct membuf to) { const struct pt_regs *regs = task_pt_regs(target); - int ret; /* r0 */ - ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, 0, 4); - - if (!ret) - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - regs->gpr+1, 4, 4*32); - if (!ret) - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - ®s->pc, 4*32, 4*33); - if (!ret) - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - ®s->sr, 4*33, 4*34); - if (!ret) - ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, - 4*34, -1); - - return ret; + membuf_zero(&to, 4); + membuf_write(&to, regs->gpr + 1, 31 * 4); + membuf_store(&to, regs->pc); + return membuf_store(&to, regs->sr); } /* @@ -87,10 +70,9 @@ static int genregs_set(struct task_struct *target, int ret; /* ignore r0 */ - ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, 4); + user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, 4); /* r1 - r31 */ - if (!ret) - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs->gpr+1, 4, 4*32); /* PC */ if (!ret) @@ -101,28 +83,64 @@ static int genregs_set(struct task_struct *target, * the Supervision register */ if (!ret) - ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, - 4*33, -1); + user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 4*33, -1); return ret; } +#ifdef CONFIG_FPU +/* + * As OpenRISC shares GPRs and floating point registers we don't need to export + * the floating point registers again. So here we only export the fpcsr special + * purpose register. + */ +static int fpregs_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + return membuf_store(&to, target->thread.fpcsr); +} + +static int fpregs_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + /* FPCSR */ + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.fpcsr, 0, 4); +} +#endif + /* * Define the register sets available on OpenRISC under Linux */ enum or1k_regset { REGSET_GENERAL, +#ifdef CONFIG_FPU + REGSET_FPU, +#endif }; static const struct user_regset or1k_regsets[] = { [REGSET_GENERAL] = { - .core_note_type = NT_PRSTATUS, + USER_REGSET_NOTE_TYPE(PRSTATUS), .n = ELF_NGREG, .size = sizeof(long), .align = sizeof(long), - .get = genregs_get, + .regset_get = genregs_get, .set = genregs_set, }, +#ifdef CONFIG_FPU + [REGSET_FPU] = { + USER_REGSET_NOTE_TYPE(PRFPREG), + .n = sizeof(struct __or1k_fpu_state) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .regset_get = fpregs_get, + .set = fpregs_set, + }, +#endif }; static const struct user_regset_view user_or1k_native_view = { @@ -142,6 +160,102 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task) * in exit.c or in signal.c. */ +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +static const struct pt_regs_offset regoffset_table[] = { + REG_OFFSET_NAME(sr), + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(gpr2), + REG_OFFSET_NAME(gpr3), + REG_OFFSET_NAME(gpr4), + REG_OFFSET_NAME(gpr5), + REG_OFFSET_NAME(gpr6), + REG_OFFSET_NAME(gpr7), + REG_OFFSET_NAME(gpr8), + REG_OFFSET_NAME(gpr9), + REG_OFFSET_NAME(gpr10), + REG_OFFSET_NAME(gpr11), + REG_OFFSET_NAME(gpr12), + REG_OFFSET_NAME(gpr13), + REG_OFFSET_NAME(gpr14), + REG_OFFSET_NAME(gpr15), + REG_OFFSET_NAME(gpr16), + REG_OFFSET_NAME(gpr17), + REG_OFFSET_NAME(gpr18), + REG_OFFSET_NAME(gpr19), + REG_OFFSET_NAME(gpr20), + REG_OFFSET_NAME(gpr21), + REG_OFFSET_NAME(gpr22), + REG_OFFSET_NAME(gpr23), + REG_OFFSET_NAME(gpr24), + REG_OFFSET_NAME(gpr25), + REG_OFFSET_NAME(gpr26), + REG_OFFSET_NAME(gpr27), + REG_OFFSET_NAME(gpr28), + REG_OFFSET_NAME(gpr29), + REG_OFFSET_NAME(gpr30), + REG_OFFSET_NAME(gpr31), + REG_OFFSET_NAME(pc), + REG_OFFSET_NAME(orig_gpr11), + REG_OFFSET_END, +}; + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} + +/** + * regs_within_kernel_stack() - check the address in the stack + * @regs: pt_regs which contains kernel stack pointer. + * @addr: address which is checked. + * + * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). + * If @addr is within the kernel stack, it returns true. If not, returns false. + */ +static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) +{ + return (addr & ~(THREAD_SIZE - 1)) == + (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return *addr; + else + return 0; +} /* * Called by kernel/ptrace.c when detaching.. @@ -179,7 +293,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) long ret = 0; if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) + ptrace_report_syscall_entry(regs)) /* * Tracing decided this syscall should not happen. * We'll return a bogus call number to get an ENOSYS @@ -187,8 +301,7 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) */ ret = -1L; - audit_syscall_entry(AUDIT_ARCH_OPENRISC, regs->gpr[11], - regs->gpr[3], regs->gpr[4], + audit_syscall_entry(regs->gpr[11], regs->gpr[3], regs->gpr[4], regs->gpr[5], regs->gpr[6]); return ret ? : regs->gpr[11]; @@ -202,5 +315,5 @@ asmlinkage void do_syscall_trace_leave(struct pt_regs *regs) step = test_thread_flag(TIF_SINGLESTEP); if (step || test_thread_flag(TIF_SYSCALL_TRACE)) - tracehook_report_syscall_exit(regs, step); + ptrace_report_syscall_exit(regs, step); } diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c index f4d5bedc3b4f..000a9cc10e6f 100644 --- a/arch/openrisc/kernel/setup.c +++ b/arch/openrisc/kernel/setup.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC setup.c * @@ -9,11 +10,6 @@ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> * - * 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. - * * This file handles the architecture-dependent parts of initialization */ @@ -30,18 +26,15 @@ #include <linux/delay.h> #include <linux/console.h> #include <linux/init.h> -#include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/seq_file.h> #include <linux/serial.h> #include <linux/initrd.h> #include <linux/of_fdt.h> #include <linux/of.h> -#include <linux/memblock.h> #include <linux/device.h> -#include <linux/of_platform.h> -#include <asm/segment.h> -#include <asm/pgtable.h> +#include <asm/sections.h> #include <asm/types.h> #include <asm/setup.h> #include <asm/io.h> @@ -50,36 +43,28 @@ #include "vmlinux.h" -char __initdata cmd_line[COMMAND_LINE_SIZE] = CONFIG_CMDLINE; - -static unsigned long __init setup_memory(void) +static void __init setup_memory(void) { - unsigned long bootmap_size; unsigned long ram_start_pfn; - unsigned long free_ram_start_pfn; unsigned long ram_end_pfn; phys_addr_t memory_start, memory_end; - struct memblock_region *region; memory_end = memory_start = 0; - /* Find main memory where is the kernel */ - for_each_memblock(memory, region) { - memory_start = region->base; - memory_end = region->base + region->size; - printk(KERN_INFO "%s: Memory: 0x%x-0x%x\n", __func__, - memory_start, memory_end); - } + /* Find main memory where is the kernel, we assume its the only one */ + memory_start = memblock_start_of_DRAM(); + memory_end = memblock_end_of_DRAM(); if (!memory_end) { panic("No memory!"); } ram_start_pfn = PFN_UP(memory_start); - /* free_ram_start_pfn is first page after kernel */ - free_ram_start_pfn = PFN_UP(__pa(&_end)); ram_end_pfn = PFN_DOWN(memblock_end_of_DRAM()); + /* setup bootmem globals (we use no_bootmem, but mm still depends on this) */ + min_low_pfn = ram_start_pfn; + max_low_pfn = ram_end_pfn; max_pfn = ram_end_pfn; /* @@ -87,25 +72,26 @@ static unsigned long __init setup_memory(void) * * This makes the memory from the end of the kernel to the end of * RAM usable. - * init_bootmem sets the global values min_low_pfn, max_low_pfn. */ - bootmap_size = init_bootmem(free_ram_start_pfn, - ram_end_pfn - ram_start_pfn); - free_bootmem(PFN_PHYS(free_ram_start_pfn), - (ram_end_pfn - free_ram_start_pfn) << PAGE_SHIFT); - reserve_bootmem(PFN_PHYS(free_ram_start_pfn), bootmap_size, - BOOTMEM_DEFAULT); - - for_each_memblock(reserved, region) { - printk(KERN_INFO "Reserved - 0x%08x-0x%08x\n", - (u32) region->base, (u32) region->size); - reserve_bootmem(region->base, region->size, BOOTMEM_DEFAULT); + memblock_reserve(__pa(_stext), _end - _stext); + +#ifdef CONFIG_BLK_DEV_INITRD + /* Then reserve the initrd, if any */ + if (initrd_start && (initrd_end > initrd_start)) { + unsigned long aligned_start = ALIGN_DOWN(initrd_start, PAGE_SIZE); + unsigned long aligned_end = ALIGN(initrd_end, PAGE_SIZE); + + memblock_reserve(__pa(aligned_start), aligned_end - aligned_start); } +#endif /* CONFIG_BLK_DEV_INITRD */ + + early_init_fdt_reserve_self(); + early_init_fdt_scan_reserved_mem(); - return ram_end_pfn; + memblock_dump_all(); } -struct cpuinfo cpuinfo; +struct cpuinfo_or1k cpuinfo_or1k[NR_CPUS]; static void print_cpuinfo(void) { @@ -113,12 +99,13 @@ static void print_cpuinfo(void) unsigned long vr = mfspr(SPR_VR); unsigned int version; unsigned int revision; + struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()]; version = (vr & SPR_VR_VER) >> 24; revision = (vr & SPR_VR_REV); printk(KERN_INFO "CPU: OpenRISC-%x (revision %d) @%d MHz\n", - version, revision, cpuinfo.clock_frequency / 1000000); + version, revision, cpuinfo->clock_frequency / 1000000); if (!(upr & SPR_UPR_UP)) { printk(KERN_INFO @@ -126,19 +113,6 @@ static void print_cpuinfo(void) return; } - if (upr & SPR_UPR_DCP) - printk(KERN_INFO - "-- dcache: %4d bytes total, %2d bytes/line, %d way(s)\n", - cpuinfo.dcache_size, cpuinfo.dcache_block_size, 1); - else - printk(KERN_INFO "-- dcache disabled\n"); - if (upr & SPR_UPR_ICP) - printk(KERN_INFO - "-- icache: %4d bytes total, %2d bytes/line, %d way(s)\n", - cpuinfo.icache_size, cpuinfo.icache_block_size, 1); - else - printk(KERN_INFO "-- icache disabled\n"); - if (upr & SPR_UPR_DMP) printk(KERN_INFO "-- dmmu: %4d entries, %lu way(s)\n", 1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2), @@ -166,42 +140,31 @@ static void print_cpuinfo(void) void __init setup_cpuinfo(void) { struct device_node *cpu; - unsigned long iccfgr, dccfgr; - unsigned long cache_set_size, cache_ways; + int cpu_id = smp_processor_id(); + struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[cpu_id]; - cpu = of_find_compatible_node(NULL, NULL, "opencores,or1200-rtlsvn481"); + cpu = of_get_cpu_node(cpu_id, NULL); if (!cpu) - panic("No compatible CPU found in device tree...\n"); - - iccfgr = mfspr(SPR_ICCFGR); - cache_ways = 1 << (iccfgr & SPR_ICCFGR_NCW); - cache_set_size = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3); - cpuinfo.icache_block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7); - cpuinfo.icache_size = - cache_set_size * cache_ways * cpuinfo.icache_block_size; - - dccfgr = mfspr(SPR_DCCFGR); - cache_ways = 1 << (dccfgr & SPR_DCCFGR_NCW); - cache_set_size = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3); - cpuinfo.dcache_block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7); - cpuinfo.dcache_size = - cache_set_size * cache_ways * cpuinfo.dcache_block_size; + panic("Couldn't find CPU%d in device tree...\n", cpu_id); if (of_property_read_u32(cpu, "clock-frequency", - &cpuinfo.clock_frequency)) { + &cpuinfo->clock_frequency)) { printk(KERN_WARNING "Device tree missing CPU 'clock-frequency' parameter." "Assuming frequency 25MHZ" "This is probably not what you want."); } + cpuinfo->coreid = mfspr(SPR_COREID); + of_node_put(cpu); print_cpuinfo(); } /** - * or32_early_setup + * or1k_early_setup + * @fdt: pointer to the start of the device tree in memory or NULL * * Handles the pointer to the device tree that this kernel is to use * for establishing the available platform devices. @@ -209,26 +172,17 @@ void __init setup_cpuinfo(void) * Falls back on built-in device tree in case null pointer is passed. */ -void __init or32_early_setup(unsigned int fdt) +void __init or1k_early_setup(void *fdt) { - if (fdt) { - early_init_devtree((void*) fdt); - printk(KERN_INFO "FDT at 0x%08x\n", fdt); - } else { - early_init_devtree(__dtb_start); - printk(KERN_INFO "Compiled-in FDT at %p\n", __dtb_start); + if (fdt) + pr_info("FDT at %p\n", fdt); + else { + fdt = __dtb_start; + pr_info("Compiled-in FDT at %p\n", fdt); } + early_init_devtree(fdt); } -static int __init openrisc_device_probe(void) -{ - of_platform_populate(NULL, NULL, NULL, NULL); - - return 0; -} - -device_initcall(openrisc_device_probe); - static inline unsigned long extract_value_bits(unsigned long reg, short bit_nr, short width) { @@ -244,21 +198,6 @@ static inline unsigned long extract_value(unsigned long reg, unsigned long mask) return mask & reg; } -void __init detect_unit_config(unsigned long upr, unsigned long mask, - char *text, void (*func) (void)) -{ - if (text != NULL) - printk("%s", text); - - if (upr & mask) { - if (func != NULL) - func(); - else - printk("present\n"); - } else - printk("not present\n"); -} - /* * calibrate_delay * @@ -267,11 +206,11 @@ void __init detect_unit_config(unsigned long upr, unsigned long mask, * */ -void __cpuinit calibrate_delay(void) +void calibrate_delay(void) { const int *val; - struct device_node *cpu = NULL; - cpu = of_find_compatible_node(NULL, NULL, "opencores,or1200-rtlsvn481"); + struct device_node *cpu = of_get_cpu_node(smp_processor_id(), NULL); + val = of_get_property(cpu, "clock-frequency", NULL); if (!val) panic("no cpu 'clock-frequency' parameter in device tree"); @@ -279,93 +218,114 @@ void __cpuinit calibrate_delay(void) pr_cont("%lu.%02lu BogoMIPS (lpj=%lu)\n", loops_per_jiffy / (500000 / HZ), (loops_per_jiffy / (5000 / HZ)) % 100, loops_per_jiffy); + + of_node_put(cpu); } void __init setup_arch(char **cmdline_p) { - unsigned long max_low_pfn; + /* setup memblock allocator */ + setup_memory(); - unflatten_device_tree(); + unflatten_and_copy_device_tree(); setup_cpuinfo(); +#ifdef CONFIG_SMP + smp_init_cpus(); +#endif + /* process 1's initial memory region is the kernel code/data */ - init_mm.start_code = (unsigned long)&_stext; - init_mm.end_code = (unsigned long)&_etext; - init_mm.end_data = (unsigned long)&_edata; - init_mm.brk = (unsigned long)&_end; + setup_initial_init_mm(_stext, _etext, _edata, _end); #ifdef CONFIG_BLK_DEV_INITRD - initrd_start = (unsigned long)&__initrd_start; - initrd_end = (unsigned long)&__initrd_end; if (initrd_start == initrd_end) { + printk(KERN_INFO "Initial ramdisk not found\n"); initrd_start = 0; initrd_end = 0; + } else { + printk(KERN_INFO "Initial ramdisk at: 0x%p (%lu bytes)\n", + (void *)(initrd_start), initrd_end - initrd_start); + initrd_below_start_ok = 1; } - initrd_below_start_ok = 1; #endif - - /* setup bootmem allocator */ - max_low_pfn = setup_memory(); + /* perform jump_table sorting before paging_init locks down read only memory */ + jump_label_init(); /* paging_init() sets up the MMU and marks all pages as reserved */ paging_init(); -#if defined(CONFIG_VT) && defined(CONFIG_DUMMY_CONSOLE) - if (!conswitchp) - conswitchp = &dummy_con; -#endif - - *cmdline_p = cmd_line; + *cmdline_p = boot_command_line; - printk(KERN_INFO "OpenRISC Linux -- http://openrisc.net\n"); + printk(KERN_INFO "OpenRISC Linux -- http://openrisc.io\n"); } static int show_cpuinfo(struct seq_file *m, void *v) { - unsigned long vr; - int version, revision; + unsigned int vr, cpucfgr; + unsigned int avr; + unsigned int version; +#ifdef CONFIG_SMP + struct cpuinfo_or1k *cpuinfo = v; + seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid); +#endif vr = mfspr(SPR_VR); - version = (vr & SPR_VR_VER) >> 24; - revision = vr & SPR_VR_REV; - - return seq_printf(m, - "cpu\t\t: OpenRISC-%x\n" - "revision\t: %d\n" - "frequency\t: %ld\n" - "dcache size\t: %d bytes\n" - "dcache block size\t: %d bytes\n" - "icache size\t: %d bytes\n" - "icache block size\t: %d bytes\n" - "immu\t\t: %d entries, %lu ways\n" - "dmmu\t\t: %d entries, %lu ways\n" - "bogomips\t: %lu.%02lu\n", - version, - revision, - loops_per_jiffy * HZ, - cpuinfo.dcache_size, - cpuinfo.dcache_block_size, - cpuinfo.icache_size, - cpuinfo.icache_block_size, - 1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2), - 1 + (mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTW), - 1 << ((mfspr(SPR_IMMUCFGR) & SPR_IMMUCFGR_NTS) >> 2), - 1 + (mfspr(SPR_IMMUCFGR) & SPR_IMMUCFGR_NTW), - (loops_per_jiffy * HZ) / 500000, - ((loops_per_jiffy * HZ) / 5000) % 100); + cpucfgr = mfspr(SPR_CPUCFGR); + + if (vr & SPR_VR_UVRP) { + vr = mfspr(SPR_VR2); + version = vr & SPR_VR2_VER; + avr = mfspr(SPR_AVR); + seq_printf(m, "cpu architecture\t: " + "OpenRISC 1000 (%d.%d-rev%d)\n", + (avr >> 24) & 0xff, + (avr >> 16) & 0xff, + (avr >> 8) & 0xff); + seq_printf(m, "cpu implementation id\t: 0x%x\n", + (vr & SPR_VR2_CPUID) >> 24); + seq_printf(m, "cpu version\t\t: 0x%x\n", version); + } else { + version = (vr & SPR_VR_VER) >> 24; + seq_printf(m, "cpu\t\t\t: OpenRISC-%x\n", version); + seq_printf(m, "revision\t\t: %d\n", vr & SPR_VR_REV); + } + seq_printf(m, "frequency\t\t: %ld\n", loops_per_jiffy * HZ); + seq_printf(m, "immu\t\t\t: %d entries, %lu ways\n", + 1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2), + 1 + (mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTW)); + seq_printf(m, "dmmu\t\t\t: %d entries, %lu ways\n", + 1 << ((mfspr(SPR_IMMUCFGR) & SPR_IMMUCFGR_NTS) >> 2), + 1 + (mfspr(SPR_IMMUCFGR) & SPR_IMMUCFGR_NTW)); + seq_printf(m, "bogomips\t\t: %lu.%02lu\n", + (loops_per_jiffy * HZ) / 500000, + ((loops_per_jiffy * HZ) / 5000) % 100); + + seq_puts(m, "features\t\t: "); + seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OB32S ? "orbis32" : ""); + seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OB64S ? "orbis64" : ""); + seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OF32S ? "orfpx32" : ""); + seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OF64S ? "orfpx64" : ""); + seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OV64S ? "orvdx64" : ""); + seq_puts(m, "\n"); + + seq_puts(m, "\n"); + + return 0; } -static void *c_start(struct seq_file *m, loff_t * pos) +static void *c_start(struct seq_file *m, loff_t *pos) { - /* We only have one CPU... */ - return *pos < 1 ? (void *)1 : NULL; + *pos = cpumask_next(*pos - 1, cpu_online_mask); + if ((*pos) < nr_cpu_ids) + return &cpuinfo_or1k[*pos]; + return NULL; } -static void *c_next(struct seq_file *m, void *v, loff_t * pos) +static void *c_next(struct seq_file *m, void *v, loff_t *pos) { - ++*pos; - return NULL; + (*pos)++; + return c_start(m, pos); } static void c_stop(struct seq_file *m, void *v) diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c index ae167f7e081a..f70a13ee0593 100644 --- a/arch/openrisc/kernel/signal.c +++ b/arch/openrisc/kernel/signal.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC signal.c * @@ -8,11 +9,6 @@ * Modifications for the OpenRISC architecture: * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> - * - * 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 <linux/sched.h> @@ -25,58 +21,90 @@ #include <linux/ptrace.h> #include <linux/unistd.h> #include <linux/stddef.h> -#include <linux/tracehook.h> +#include <linux/resume_user_mode.h> +#include <asm/fpu.h> #include <asm/processor.h> +#include <asm/syscall.h> #include <asm/ucontext.h> -#include <asm/uaccess.h> - -#define DEBUG_SIG 0 +#include <linux/uaccess.h> struct rt_sigframe { - struct siginfo *pinfo; - void *puc; struct siginfo info; struct ucontext uc; unsigned char retcode[16]; /* trampoline code */ }; -static int restore_sigcontext(struct pt_regs *regs, struct sigcontext *sc) +asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs); + +asmlinkage int do_work_pending(struct pt_regs *regs, unsigned int thread_flags, + int syscall); + +#ifdef CONFIG_FPU +static long restore_fp_state(struct sigcontext __user *sc) +{ + long err; + + err = __copy_from_user(¤t->thread.fpcsr, &sc->fpcsr, sizeof(unsigned long)); + if (unlikely(err)) + return err; + + /* Restore the FPU state */ + restore_fpu(current); + + return 0; +} + +static long save_fp_state(struct sigcontext __user *sc) { - unsigned int err = 0; + long err; + + /* Sync the user FPU state so we can copy to sigcontext */ + save_fpu(current); - /* Alwys make any pending restarted system call return -EINTR */ - current_thread_info()->restart_block.fn = do_no_restart_syscall; + err = __copy_to_user(&sc->fpcsr, ¤t->thread.fpcsr, sizeof(unsigned long)); + + return err; +} +#else +#define save_fp_state(sc) (0) +#define restore_fp_state(sc) (0) +#endif + +static int restore_sigcontext(struct pt_regs *regs, + struct sigcontext __user *sc) +{ + int err = 0; + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; /* * Restore the regs from &sc->regs. - * (sc is already checked for VERIFY_READ since the sigframe was + * (sc is already checked since the sigframe was * checked in sys_sigreturn previously) */ - if (__copy_from_user(regs, sc->regs.gpr, 32 * sizeof(unsigned long))) - goto badframe; - if (__copy_from_user(®s->pc, &sc->regs.pc, sizeof(unsigned long))) - goto badframe; - if (__copy_from_user(®s->sr, &sc->regs.sr, sizeof(unsigned long))) - goto badframe; + err |= __copy_from_user(regs, sc->regs.gpr, 32 * sizeof(unsigned long)); + err |= __copy_from_user(®s->pc, &sc->regs.pc, sizeof(unsigned long)); + err |= __copy_from_user(®s->sr, &sc->regs.sr, sizeof(unsigned long)); + err |= restore_fp_state(sc); /* make sure the SM-bit is cleared so user-mode cannot fool us */ regs->sr &= ~SPR_SR_SM; + regs->orig_gpr11 = -1; /* Avoid syscall restart checks */ + /* TODO: the other ports use regs->orig_XX to disable syscall checks * after this completes, but we don't use that mechanism. maybe we can * use it now ? */ return err; - -badframe: - return 1; } asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs) { - struct rt_sigframe *frame = (struct rt_sigframe __user *)regs->sp; + struct rt_sigframe __user *frame = (struct rt_sigframe __user *)regs->sp; sigset_t set; /* @@ -84,10 +112,10 @@ asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs) * then frame should be dword aligned here. If it's * not, then the user is trying to mess with us. */ - if (((long)frame) & 3) + if (((unsigned long)frame) & 3) goto badframe; - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + if (!access_ok(frame, sizeof(*frame))) goto badframe; if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) goto badframe; @@ -103,7 +131,7 @@ asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs) return regs->gpr[11]; badframe: - force_sig(SIGSEGV, current); + force_sig(SIGSEGV); return 0; } @@ -111,20 +139,18 @@ badframe: * Set up a signal frame. */ -static int setup_sigcontext(struct sigcontext *sc, struct pt_regs *regs, - unsigned long mask) +static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc) { int err = 0; /* copy the regs */ - + /* There should be no need to save callee-saved registers here... + * ...but we save them anyway. Revisit this + */ err |= __copy_to_user(sc->regs.gpr, regs, 32 * sizeof(unsigned long)); err |= __copy_to_user(&sc->regs.pc, ®s->pc, sizeof(unsigned long)); err |= __copy_to_user(&sc->regs.sr, ®s->sr, sizeof(unsigned long)); - - /* then some other stuff */ - - err |= __put_user(mask, &sc->oldmask); + err |= save_fp_state(sc); return err; } @@ -139,30 +165,16 @@ static inline unsigned long align_sigframe(unsigned long sp) * or the alternate stack. */ -static inline void __user *get_sigframe(struct k_sigaction *ka, +static inline void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size) { unsigned long sp = regs->sp; - int onsigstack = on_sig_stack(sp); /* redzone */ sp -= STACK_FRAME_OVERHEAD; - - /* This is the X/Open sanctioned signal stack switching. */ - if ((ka->sa.sa_flags & SA_ONSTACK) && !onsigstack) { - if (current->sas_ss_size) - sp = current->sas_ss_sp + current->sas_ss_size; - } - + sp = sigsp(sp, ksig); sp = align_sigframe(sp - frame_size); - /* - * If we are on the alternate signal stack and would overflow it, don't. - * Return an always-bogus address instead so we will die with SIGSEGV. - */ - if (onsigstack && !likely(on_sig_stack(sp))) - return (void __user *)-1L; - return (void __user *)sp; } @@ -173,55 +185,51 @@ static inline void __user *get_sigframe(struct k_sigaction *ka, * trampoline which performs the syscall sigreturn, or a provided * user-mode trampoline. */ -static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, - sigset_t *set, struct pt_regs *regs) +static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, + struct pt_regs *regs) { - struct rt_sigframe *frame; + struct rt_sigframe __user *frame; unsigned long return_ip; int err = 0; - frame = get_sigframe(ka, regs, sizeof(*frame)); + frame = get_sigframe(ksig, regs, sizeof(*frame)); - if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) - goto give_sigsegv; + if (!access_ok(frame, sizeof(*frame))) + return -EFAULT; - err |= __put_user(&frame->info, &frame->pinfo); - err |= __put_user(&frame->uc, &frame->puc); + /* Create siginfo. */ + if (ksig->ka.sa.sa_flags & SA_SIGINFO) + err |= copy_siginfo_to_user(&frame->info, &ksig->info); - if (ka->sa.sa_flags & SA_SIGINFO) - err |= copy_siginfo_to_user(&frame->info, info); - if (err) - goto give_sigsegv; - - /* Clear all the bits of the ucontext we don't use. */ - err |= __clear_user(&frame->uc, offsetof(struct ucontext, uc_mcontext)); + /* Create the ucontext. */ err |= __put_user(0, &frame->uc.uc_flags); err |= __put_user(NULL, &frame->uc.uc_link); err |= __save_altstack(&frame->uc.uc_stack, regs->sp); - err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0]); + err |= setup_sigcontext(regs, &frame->uc.uc_mcontext); err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); if (err) - goto give_sigsegv; + return -EFAULT; /* trampoline - the desired return ip is the retcode itself */ return_ip = (unsigned long)&frame->retcode; - /* This is l.ori r11,r0,__NR_sigreturn, l.sys 1 */ - err |= __put_user(0xa960, (short *)(frame->retcode + 0)); - err |= __put_user(__NR_rt_sigreturn, (short *)(frame->retcode + 2)); - err |= __put_user(0x20000001, (unsigned long *)(frame->retcode + 4)); - err |= __put_user(0x15000000, (unsigned long *)(frame->retcode + 8)); + /* This is: + l.ori r11,r0,__NR_sigreturn + l.sys 1 + */ + err |= __put_user(0xa960, (short __user *)(frame->retcode + 0)); + err |= __put_user(__NR_rt_sigreturn, (short __user *)(frame->retcode + 2)); + err |= __put_user(0x20000001, (unsigned long __user *)(frame->retcode + 4)); + err |= __put_user(0x15000000, (unsigned long __user *)(frame->retcode + 8)); if (err) - goto give_sigsegv; - - /* TODO what is the current->exec_domain stuff and invmap ? */ + return -EFAULT; /* Set up registers for signal handler */ - regs->pc = (unsigned long)ka->sa.sa_handler; /* what we enter NOW */ + regs->pc = (unsigned long)ksig->ka.sa.sa_handler; /* what we enter NOW */ regs->gpr[9] = (unsigned long)return_ip; /* what we enter LATER */ - regs->gpr[3] = (unsigned long)sig; /* arg 1: signo */ + regs->gpr[3] = (unsigned long)ksig->sig; /* arg 1: signo */ regs->gpr[4] = (unsigned long)&frame->info; /* arg 2: (siginfo_t*) */ regs->gpr[5] = (unsigned long)&frame->uc; /* arg 3: ucontext */ @@ -229,25 +237,18 @@ static int setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, regs->sp = (unsigned long)frame; return 0; - -give_sigsegv: - force_sigsegv(sig, current); - return -EFAULT; } static inline void -handle_signal(unsigned long sig, - siginfo_t *info, struct k_sigaction *ka, - struct pt_regs *regs) +handle_signal(struct ksignal *ksig, struct pt_regs *regs) { int ret; - ret = setup_rt_frame(sig, ka, info, sigmask_to_save(), regs); - if (ret) - return; + rseq_signal_deliver(ksig, regs); + + ret = setup_rt_frame(ksig, sigmask_to_save(), regs); - signal_delivered(sig, info, ka, regs, - test_thread_flag(TIF_SINGLESTEP)); + signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP)); } /* @@ -262,82 +263,98 @@ handle_signal(unsigned long sig, * mode below. */ -void do_signal(struct pt_regs *regs) +static int do_signal(struct pt_regs *regs, int syscall) { - siginfo_t info; - int signr; - struct k_sigaction ka; - - /* - * We want the common case to go fast, which - * is why we may in certain cases get here from - * kernel mode. Just return without doing anything - * if so. - */ - if (!user_mode(regs)) - return; - - signr = get_signal_to_deliver(&info, &ka, regs, NULL); - - /* If we are coming out of a syscall then we need - * to check if the syscall was interrupted and wants to be - * restarted after handling the signal. If so, the original - * syscall number is put back into r11 and the PC rewound to - * point at the l.sys instruction that resulted in the - * original syscall. Syscall results other than the four - * below mean that the syscall executed to completion and no - * restart is necessary. - */ - if (regs->orig_gpr11) { - int restart = 0; - - switch (regs->gpr[11]) { + struct ksignal ksig; + unsigned long continue_addr = 0; + unsigned long restart_addr = 0; + unsigned long retval = 0; + int restart = 0; + + if (syscall) { + continue_addr = regs->pc; + restart_addr = continue_addr - 4; + retval = regs->gpr[11]; + + /* + * Setup syscall restart here so that a debugger will + * see the already changed PC. + */ + switch (retval) { case -ERESTART_RESTARTBLOCK: + restart = -2; + fallthrough; case -ERESTARTNOHAND: - /* Restart if there is no signal handler */ - restart = (signr <= 0); - break; case -ERESTARTSYS: - /* Restart if there no signal handler or - * SA_RESTART flag is set */ - restart = (signr <= 0 || (ka.sa.sa_flags & SA_RESTART)); - break; case -ERESTARTNOINTR: - /* Always restart */ - restart = 1; + restart++; + regs->gpr[11] = regs->orig_gpr11; + regs->pc = restart_addr; break; } - - if (restart) { - if (regs->gpr[11] == -ERESTART_RESTARTBLOCK) - regs->gpr[11] = __NR_restart_syscall; - else - regs->gpr[11] = regs->orig_gpr11; - regs->pc -= 4; - } else { - regs->gpr[11] = -EINTR; - } } - if (signr <= 0) { - /* no signal to deliver so we just put the saved sigmask - * back */ + /* + * Get the signal to deliver. During the call to get_signal the + * debugger may change all our registers so we may need to revert + * the decision to restart the syscall; specifically, if the PC is + * changed, don't restart the syscall. + */ + if (get_signal(&ksig)) { + if (unlikely(restart) && regs->pc == restart_addr) { + if (retval == -ERESTARTNOHAND || + retval == -ERESTART_RESTARTBLOCK + || (retval == -ERESTARTSYS + && !(ksig.ka.sa.sa_flags & SA_RESTART))) { + /* No automatic restart */ + regs->gpr[11] = -EINTR; + regs->pc = continue_addr; + } + } + handle_signal(&ksig, regs); + } else { + /* no handler */ restore_saved_sigmask(); - } else { /* signr > 0 */ - /* Whee! Actually deliver the signal. */ - handle_signal(signr, &info, &ka, regs); + /* + * Restore pt_regs PC as syscall restart will be handled by + * kernel without return to userspace + */ + if (unlikely(restart) && regs->pc == restart_addr) { + regs->pc = continue_addr; + return restart; + } } - return; + return 0; } -asmlinkage void do_notify_resume(struct pt_regs *regs) +asmlinkage int +do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) { - if (current_thread_info()->flags & _TIF_SIGPENDING) - do_signal(regs); - - if (current_thread_info()->flags & _TIF_NOTIFY_RESUME) { - clear_thread_flag(TIF_NOTIFY_RESUME); - tracehook_notify_resume(regs); - } + do { + if (likely(thread_flags & _TIF_NEED_RESCHED)) { + schedule(); + } else { + if (unlikely(!user_mode(regs))) + return 0; + local_irq_enable(); + if (thread_flags & (_TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL)) { + int restart = do_signal(regs, syscall); + if (unlikely(restart)) { + /* + * Restart without handlers. + * Deal with it without leaving + * the kernel space. + */ + return restart; + } + syscall = 0; + } else { + resume_user_mode_work(regs); + } + } + local_irq_disable(); + thread_flags = read_thread_flags(); + } while (thread_flags & _TIF_WORK_MASK); + return 0; } diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c new file mode 100644 index 000000000000..86da4bc5ee0b --- /dev/null +++ b/arch/openrisc/kernel/smp.c @@ -0,0 +1,328 @@ +/* + * Copyright (C) 2014 Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> + * Copyright (C) 2017 Stafford Horne <shorne@gmail.com> + * + * Based on arm64 and arc implementations + * Copyright (C) 2013 ARM Ltd. + * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#include <linux/smp.h> +#include <linux/cpu.h> +#include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/irq.h> +#include <linux/of.h> +#include <asm/cpuinfo.h> +#include <asm/mmu_context.h> +#include <asm/tlbflush.h> +#include <asm/cacheflush.h> +#include <asm/time.h> + +asmlinkage __init void secondary_start_kernel(void); + +static void (*smp_cross_call)(const struct cpumask *, unsigned int); + +unsigned long secondary_release = -1; +struct thread_info *secondary_thread_info; + +enum ipi_msg_type { + IPI_WAKEUP, + IPI_RESCHEDULE, + IPI_CALL_FUNC, + IPI_CALL_FUNC_SINGLE, +}; + +static DEFINE_SPINLOCK(boot_lock); + +static void boot_secondary(unsigned int cpu, struct task_struct *idle) +{ + /* + * set synchronisation state between this boot processor + * and the secondary one + */ + spin_lock(&boot_lock); + + secondary_release = cpu; + smp_cross_call(cpumask_of(cpu), IPI_WAKEUP); + + /* + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ + spin_unlock(&boot_lock); +} + +void __init smp_init_cpus(void) +{ + struct device_node *cpu; + u32 cpu_id; + + for_each_of_cpu_node(cpu) { + cpu_id = of_get_cpu_hwid(cpu, 0); + if (cpu_id < NR_CPUS) + set_cpu_possible(cpu_id, true); + } +} + +void __init smp_prepare_cpus(unsigned int max_cpus) +{ + unsigned int cpu; + + /* + * Initialise the present map, which describes the set of CPUs + * actually populated at the present time. + */ + for_each_possible_cpu(cpu) { + if (cpu < max_cpus) + set_cpu_present(cpu, true); + } +} + +void __init smp_cpus_done(unsigned int max_cpus) +{ +} + +static DECLARE_COMPLETION(cpu_running); + +int __cpu_up(unsigned int cpu, struct task_struct *idle) +{ + if (smp_cross_call == NULL) { + pr_warn("CPU%u: failed to start, IPI controller missing", + cpu); + return -EIO; + } + + secondary_thread_info = task_thread_info(idle); + current_pgd[cpu] = init_mm.pgd; + + boot_secondary(cpu, idle); + if (!wait_for_completion_timeout(&cpu_running, + msecs_to_jiffies(1000))) { + pr_crit("CPU%u: failed to start\n", cpu); + return -EIO; + } + synchronise_count_master(cpu); + + return 0; +} + +asmlinkage __init void secondary_start_kernel(void) +{ + struct mm_struct *mm = &init_mm; + unsigned int cpu = smp_processor_id(); + /* + * All kernel threads share the same mm context; grab a + * reference and switch to it. + */ + mmgrab(mm); + current->active_mm = mm; + cpumask_set_cpu(cpu, mm_cpumask(mm)); + + pr_info("CPU%u: Booted secondary processor\n", cpu); + + setup_cpuinfo(); + openrisc_clockevent_init(); + + notify_cpu_starting(cpu); + + /* + * OK, now it's safe to let the boot CPU continue + */ + complete(&cpu_running); + + synchronise_count_slave(cpu); + set_cpu_online(cpu, true); + + local_irq_enable(); + /* + * OK, it's off to the idle thread for us + */ + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); +} + +void handle_IPI(unsigned int ipi_msg) +{ + unsigned int cpu = smp_processor_id(); + + switch (ipi_msg) { + case IPI_WAKEUP: + break; + + case IPI_RESCHEDULE: + scheduler_ipi(); + break; + + case IPI_CALL_FUNC: + generic_smp_call_function_interrupt(); + break; + + case IPI_CALL_FUNC_SINGLE: + generic_smp_call_function_single_interrupt(); + break; + + default: + WARN(1, "CPU%u: Unknown IPI message 0x%x\n", cpu, ipi_msg); + break; + } +} + +void arch_smp_send_reschedule(int cpu) +{ + smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE); +} + +static void stop_this_cpu(void *dummy) +{ + /* Remove this CPU */ + set_cpu_online(smp_processor_id(), false); + + local_irq_disable(); + /* CPU Doze */ + if (mfspr(SPR_UPR) & SPR_UPR_PMP) + mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME); + /* If that didn't work, infinite loop */ + while (1) + ; +} + +void smp_send_stop(void) +{ + smp_call_function(stop_this_cpu, NULL, 0); +} + +void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int)) +{ + smp_cross_call = fn; +} + +void arch_send_call_function_single_ipi(int cpu) +{ + smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE); +} + +void arch_send_call_function_ipi_mask(const struct cpumask *mask) +{ + smp_cross_call(mask, IPI_CALL_FUNC); +} + +/* TLB flush operations - Performed on each CPU*/ +static inline void ipi_flush_tlb_all(void *ignored) +{ + local_flush_tlb_all(); +} + +static inline void ipi_flush_tlb_mm(void *info) +{ + struct mm_struct *mm = (struct mm_struct *)info; + + local_flush_tlb_mm(mm); +} + +static void smp_flush_tlb_mm(struct cpumask *cmask, struct mm_struct *mm) +{ + unsigned int cpuid; + + if (cpumask_empty(cmask)) + return; + + cpuid = get_cpu(); + + if (cpumask_any_but(cmask, cpuid) >= nr_cpu_ids) { + /* local cpu is the only cpu present in cpumask */ + local_flush_tlb_mm(mm); + } else { + on_each_cpu_mask(cmask, ipi_flush_tlb_mm, mm, 1); + } + put_cpu(); +} + +struct flush_tlb_data { + unsigned long addr1; + unsigned long addr2; +}; + +static inline void ipi_flush_tlb_page(void *info) +{ + struct flush_tlb_data *fd = (struct flush_tlb_data *)info; + + local_flush_tlb_page(NULL, fd->addr1); +} + +static inline void ipi_flush_tlb_range(void *info) +{ + struct flush_tlb_data *fd = (struct flush_tlb_data *)info; + + local_flush_tlb_range(NULL, fd->addr1, fd->addr2); +} + +static void smp_flush_tlb_range(const struct cpumask *cmask, unsigned long start, + unsigned long end) +{ + unsigned int cpuid; + + if (cpumask_empty(cmask)) + return; + + cpuid = get_cpu(); + + if (cpumask_any_but(cmask, cpuid) >= nr_cpu_ids) { + /* local cpu is the only cpu present in cpumask */ + if ((end - start) <= PAGE_SIZE) + local_flush_tlb_page(NULL, start); + else + local_flush_tlb_range(NULL, start, end); + } else { + struct flush_tlb_data fd; + + fd.addr1 = start; + fd.addr2 = end; + + if ((end - start) <= PAGE_SIZE) + on_each_cpu_mask(cmask, ipi_flush_tlb_page, &fd, 1); + else + on_each_cpu_mask(cmask, ipi_flush_tlb_range, &fd, 1); + } + put_cpu(); +} + +void flush_tlb_all(void) +{ + on_each_cpu(ipi_flush_tlb_all, NULL, 1); +} + +void flush_tlb_mm(struct mm_struct *mm) +{ + smp_flush_tlb_mm(mm_cpumask(mm), mm); +} + +void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) +{ + smp_flush_tlb_range(mm_cpumask(vma->vm_mm), uaddr, uaddr + PAGE_SIZE); +} + +void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + const struct cpumask *cmask = vma ? mm_cpumask(vma->vm_mm) + : cpu_online_mask; + smp_flush_tlb_range(cmask, start, end); +} + +/* Instruction cache invalidate - performed on each cpu */ +static void ipi_icache_page_inv(void *arg) +{ + struct page *page = arg; + + local_icache_page_inv(page); +} + +void smp_icache_page_inv(struct page *page) +{ + on_each_cpu(ipi_icache_page_inv, page, 1); +} +EXPORT_SYMBOL(smp_icache_page_inv); diff --git a/arch/openrisc/kernel/stacktrace.c b/arch/openrisc/kernel/stacktrace.c new file mode 100644 index 000000000000..54d38809e22c --- /dev/null +++ b/arch/openrisc/kernel/stacktrace.c @@ -0,0 +1,100 @@ +/* + * Stack trace utility for OpenRISC + * + * Copyright (C) 2017 Stafford Horne <shorne@gmail.com> + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + * + * Losely based on work from sh and powerpc. + */ + +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/sched/debug.h> +#include <linux/sched/task_stack.h> +#include <linux/stacktrace.h> + +#include <asm/processor.h> +#include <asm/unwinder.h> + +/* + * Save stack-backtrace addresses into a stack_trace buffer. + */ +static void +save_stack_address(void *data, unsigned long addr, int reliable) +{ + struct stack_trace *trace = data; + + if (!reliable) + return; + + if (trace->skip > 0) { + trace->skip--; + return; + } + + if (trace->nr_entries < trace->max_entries) + trace->entries[trace->nr_entries++] = addr; +} + +void save_stack_trace(struct stack_trace *trace) +{ + unwind_stack(trace, (unsigned long *) &trace, save_stack_address); +} +EXPORT_SYMBOL_GPL(save_stack_trace); + +static void +save_stack_address_nosched(void *data, unsigned long addr, int reliable) +{ + struct stack_trace *trace = (struct stack_trace *)data; + + if (!reliable) + return; + + if (in_sched_functions(addr)) + return; + + if (trace->skip > 0) { + trace->skip--; + return; + } + + if (trace->nr_entries < trace->max_entries) + trace->entries[trace->nr_entries++] = addr; +} + +void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + unsigned long *sp = NULL; + + if (!try_get_task_stack(tsk)) + return; + + if (tsk == current) + sp = (unsigned long *) &sp; + else { + unsigned long ksp; + + /* Locate stack from kernel context */ + ksp = task_thread_info(tsk)->ksp; + ksp += STACK_FRAME_OVERHEAD; /* redzone */ + ksp += sizeof(struct pt_regs); + + sp = (unsigned long *) ksp; + } + + unwind_stack(trace, sp, save_stack_address_nosched); + + put_task_stack(tsk); +} +EXPORT_SYMBOL_GPL(save_stack_trace_tsk); + +void +save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) +{ + unwind_stack(trace, (unsigned long *) regs->sp, + save_stack_address_nosched); +} +EXPORT_SYMBOL_GPL(save_stack_trace_regs); diff --git a/arch/openrisc/kernel/sync-timer.c b/arch/openrisc/kernel/sync-timer.c new file mode 100644 index 000000000000..ed8d835caca1 --- /dev/null +++ b/arch/openrisc/kernel/sync-timer.c @@ -0,0 +1,120 @@ +/* + * OR1K timer synchronisation + * + * Based on work from MIPS implementation. + * + * All CPUs will have their count registers synchronised to the CPU0 next time + * value. This can cause a small timewarp for CPU0. All other CPU's should + * not have done anything significant (but they may have had interrupts + * enabled briefly - prom_smp_finish() should not be responsible for enabling + * interrupts...) + */ + +#include <linux/kernel.h> +#include <linux/irqflags.h> +#include <linux/cpumask.h> + +#include <asm/time.h> +#include <asm/timex.h> +#include <linux/atomic.h> +#include <asm/barrier.h> + +#include <asm/spr.h> + +static unsigned int initcount; +static atomic_t count_count_start = ATOMIC_INIT(0); +static atomic_t count_count_stop = ATOMIC_INIT(0); + +#define COUNTON 100 +#define NR_LOOPS 3 + +void synchronise_count_master(int cpu) +{ + int i; + unsigned long flags; + + pr_info("Synchronize counters for CPU %u: ", cpu); + + local_irq_save(flags); + + /* + * We loop a few times to get a primed instruction cache, + * then the last pass is more or less synchronised and + * the master and slaves each set their cycle counters to a known + * value all at once. This reduces the chance of having random offsets + * between the processors, and guarantees that the maximum + * delay between the cycle counters is never bigger than + * the latency of information-passing (cachelines) between + * two CPUs. + */ + + for (i = 0; i < NR_LOOPS; i++) { + /* slaves loop on '!= 2' */ + while (atomic_read(&count_count_start) != 1) + mb(); + atomic_set(&count_count_stop, 0); + smp_wmb(); + + /* Let the slave writes its count register */ + atomic_inc(&count_count_start); + + /* Count will be initialised to current timer */ + if (i == 1) + initcount = get_cycles(); + + /* + * Everyone initialises count in the last loop: + */ + if (i == NR_LOOPS-1) + openrisc_timer_set(initcount); + + /* + * Wait for slave to leave the synchronization point: + */ + while (atomic_read(&count_count_stop) != 1) + mb(); + atomic_set(&count_count_start, 0); + smp_wmb(); + atomic_inc(&count_count_stop); + } + /* Arrange for an interrupt in a short while */ + openrisc_timer_set_next(COUNTON); + + local_irq_restore(flags); + + /* + * i386 code reported the skew here, but the + * count registers were almost certainly out of sync + * so no point in alarming people + */ + pr_cont("done.\n"); +} + +void synchronise_count_slave(int cpu) +{ + int i; + + /* + * Not every cpu is online at the time this gets called, + * so we first wait for the master to say everyone is ready + */ + + for (i = 0; i < NR_LOOPS; i++) { + atomic_inc(&count_count_start); + while (atomic_read(&count_count_start) != 2) + mb(); + + /* + * Everyone initialises count in the last loop: + */ + if (i == NR_LOOPS-1) + openrisc_timer_set(initcount); + + atomic_inc(&count_count_stop); + while (atomic_read(&count_count_stop) != 2) + mb(); + } + /* Arrange for an interrupt in a short while */ + openrisc_timer_set_next(COUNTON); +} +#undef NR_LOOPS diff --git a/arch/openrisc/kernel/sys_call_table.c b/arch/openrisc/kernel/sys_call_table.c index e1f8ce8c72a8..b2f57e2538f7 100644 --- a/arch/openrisc/kernel/sys_call_table.c +++ b/arch/openrisc/kernel/sys_call_table.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC sys_call_table.c * @@ -7,11 +8,6 @@ * * Modifications for the OpenRISC architecture: * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> - * - * 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 <linux/syscalls.h> @@ -20,9 +16,14 @@ #include <asm/syscalls.h> -#undef __SYSCALL #define __SYSCALL(nr, call) [nr] = (call), +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) + +#define sys_mmap2 sys_mmap_pgoff +#define sys_clone __sys_clone +#define sys_clone3 __sys_clone3 +#define sys_fork __sys_fork void *sys_call_table[__NR_syscalls] = { -#include <asm/unistd.h> +#include <asm/syscall_table_32.h> }; diff --git a/arch/openrisc/kernel/time.c b/arch/openrisc/kernel/time.c index 7c52e9494a8d..764c7bfb5df3 100644 --- a/arch/openrisc/kernel/time.c +++ b/arch/openrisc/kernel/time.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC time.c * @@ -7,11 +8,6 @@ * * Modifications for the OpenRISC architecture: * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> - * - * 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 <linux/kernel.h> @@ -24,11 +20,21 @@ #include <linux/clockchips.h> #include <linux/irq.h> #include <linux/io.h> +#include <linux/of_clk.h> #include <asm/cpuinfo.h> +#include <asm/time.h> -static int openrisc_timer_set_next_event(unsigned long delta, - struct clock_event_device *dev) +irqreturn_t __irq_entry timer_interrupt(struct pt_regs *regs); + +/* Test the timer ticks to count, used in sync routine */ +inline void openrisc_timer_set(unsigned long count) +{ + mtspr(SPR_TTCR, count); +} + +/* Set the timer to trigger in delta cycles */ +inline void openrisc_timer_set_next(unsigned long delta) { u32 c; @@ -44,31 +50,13 @@ static int openrisc_timer_set_next_event(unsigned long delta, * Keep timer in continuous mode always. */ mtspr(SPR_TTMR, SPR_TTMR_CR | SPR_TTMR_IE | c); - - return 0; } -static void openrisc_timer_set_mode(enum clock_event_mode mode, - struct clock_event_device *evt) +static int openrisc_timer_set_next_event(unsigned long delta, + struct clock_event_device *dev) { - switch (mode) { - case CLOCK_EVT_MODE_PERIODIC: - pr_debug(KERN_INFO "%s: periodic\n", __func__); - BUG(); - break; - case CLOCK_EVT_MODE_ONESHOT: - pr_debug(KERN_INFO "%s: oneshot\n", __func__); - break; - case CLOCK_EVT_MODE_UNUSED: - pr_debug(KERN_INFO "%s: unused\n", __func__); - break; - case CLOCK_EVT_MODE_SHUTDOWN: - pr_debug(KERN_INFO "%s: shutdown\n", __func__); - break; - case CLOCK_EVT_MODE_RESUME: - pr_debug(KERN_INFO "%s: resume\n", __func__); - break; - } + openrisc_timer_set_next(delta); + return 0; } /* This is the clock event device based on the OR1K tick timer. @@ -76,14 +64,32 @@ static void openrisc_timer_set_mode(enum clock_event_mode mode, * timers) we cannot enable the PERIODIC feature. The tick timer can run using * one-shot events, so no problem. */ +static DEFINE_PER_CPU(struct clock_event_device, clockevent_openrisc_timer); -static struct clock_event_device clockevent_openrisc_timer = { - .name = "openrisc_timer_clockevent", - .features = CLOCK_EVT_FEAT_ONESHOT, - .rating = 300, - .set_next_event = openrisc_timer_set_next_event, - .set_mode = openrisc_timer_set_mode, -}; +void openrisc_clockevent_init(void) +{ + unsigned int cpu = smp_processor_id(); + struct clock_event_device *evt = + &per_cpu(clockevent_openrisc_timer, cpu); + struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[cpu]; + + mtspr(SPR_TTMR, SPR_TTMR_CR); + +#ifdef CONFIG_SMP + evt->broadcast = tick_broadcast; +#endif + evt->name = "openrisc_timer_clockevent", + evt->features = CLOCK_EVT_FEAT_ONESHOT, + evt->rating = 300, + evt->set_next_event = openrisc_timer_set_next_event, + + evt->cpumask = cpumask_of(cpu); + + /* We only have 28 bits */ + clockevents_config_and_register(evt, cpuinfo->clock_frequency, + 100, 0x0fffffff); + +} static inline void timer_ack(void) { @@ -107,7 +113,9 @@ static inline void timer_ack(void) irqreturn_t __irq_entry timer_interrupt(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); - struct clock_event_device *evt = &clockevent_openrisc_timer; + unsigned int cpu = smp_processor_id(); + struct clock_event_device *evt = + &per_cpu(clockevent_openrisc_timer, cpu); timer_ack(); @@ -123,27 +131,15 @@ irqreturn_t __irq_entry timer_interrupt(struct pt_regs *regs) return IRQ_HANDLED; } -static __init void openrisc_clockevent_init(void) -{ - clockevent_openrisc_timer.cpumask = cpumask_of(0); - - /* We only have 28 bits */ - clockevents_config_and_register(&clockevent_openrisc_timer, - cpuinfo.clock_frequency, - 100, 0x0fffffff); - -} - -/** +/* * Clocksource: Based on OpenRISC timer/counter * * This sets up the OpenRISC Tick Timer as a clock source. The tick timer * is 32 bits wide and runs at the CPU clock frequency. */ - -static cycle_t openrisc_timer_read(struct clocksource *cs) +static u64 openrisc_timer_read(struct clocksource *cs) { - return (cycle_t) mfspr(SPR_TTCR); + return (u64) mfspr(SPR_TTCR); } static struct clocksource openrisc_timer = { @@ -156,7 +152,9 @@ static struct clocksource openrisc_timer = { static int __init openrisc_timer_init(void) { - if (clocksource_register_hz(&openrisc_timer, cpuinfo.clock_frequency)) + struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()]; + + if (clocksource_register_hz(&openrisc_timer, cpuinfo->clock_frequency)) panic("failed to register clocksource"); /* Enable the incrementer: 'continuous' mode with interrupt disabled */ @@ -175,4 +173,7 @@ void __init time_init(void) openrisc_timer_init(); openrisc_clockevent_init(); + + of_clk_init(NULL); + timer_probe(); } diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index 3d3f6062f49c..c195be9cc9fc 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * OpenRISC traps.c * @@ -9,21 +10,17 @@ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> * - * 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. - * * Here we handle the break vectors not used by the system call * mechanism, as well as some general stack/register dumping * things. - * */ #include <linux/init.h> #include <linux/sched.h> +#include <linux/sched/debug.h> +#include <linux/sched/task_stack.h> #include <linux/kernel.h> -#include <linux/module.h> +#include <linux/extable.h> #include <linux/kmod.h> #include <linux/string.h> #include <linux/errno.h> @@ -31,78 +28,50 @@ #include <linux/timer.h> #include <linux/mm.h> #include <linux/kallsyms.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> -#include <asm/segment.h> +#include <asm/bug.h> +#include <asm/fpu.h> #include <asm/io.h> -#include <asm/pgtable.h> - -extern char _etext, _stext; - -int kstack_depth_to_print = 0x180; +#include <asm/processor.h> +#include <asm/unwinder.h> +#include <asm/sections.h> + +int lwa_flag; +static unsigned long __user *lwa_addr; + +asmlinkage void unhandled_exception(struct pt_regs *regs, int ea, int vector); +asmlinkage void do_trap(struct pt_regs *regs, unsigned long address); +asmlinkage void do_fpe_trap(struct pt_regs *regs, unsigned long address); +asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address); +asmlinkage void do_bus_fault(struct pt_regs *regs, unsigned long address); +asmlinkage void do_illegal_instruction(struct pt_regs *regs, + unsigned long address); -static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) +static void print_trace(void *data, unsigned long addr, int reliable) { - return p > (void *)tinfo && p < (void *)tinfo + THREAD_SIZE - 3; + const char *loglvl = data; + + pr_info("%s[<%p>] %s%pS\n", loglvl, (void *) addr, reliable ? "" : "? ", + (void *) addr); } -void show_trace(struct task_struct *task, unsigned long *stack) +static void print_data(unsigned long base_addr, unsigned long word, int i) { - struct thread_info *context; - unsigned long addr; - - context = (struct thread_info *) - ((unsigned long)stack & (~(THREAD_SIZE - 1))); - - while (valid_stack_ptr(context, stack)) { - addr = *stack++; - if (__kernel_text_address(addr)) { - printk(" [<%08lx>]", addr); - print_symbol(" %s", addr); - printk("\n"); - } - } - printk(" =======================\n"); + if (i == 0) + pr_info("(%08lx:)\t%08lx", base_addr + (i * 4), word); + else + pr_info(" %08lx:\t%08lx", base_addr + (i * 4), word); } /* displays a short stack trace */ -void show_stack(struct task_struct *task, unsigned long *esp) +void show_stack(struct task_struct *task, unsigned long *esp, const char *loglvl) { - unsigned long addr, *stack; - int i; - if (esp == NULL) esp = (unsigned long *)&esp; - stack = esp; - - printk("Stack dump [0x%08lx]:\n", (unsigned long)esp); - for (i = 0; i < kstack_depth_to_print; i++) { - if (kstack_end(stack)) - break; - if (__get_user(addr, stack)) { - /* This message matches "failing address" marked - s390 in ksymoops, so lines containing it will - not be filtered out by ksymoops. */ - printk("Failing address 0x%lx\n", (unsigned long)stack); - break; - } - stack++; - - printk("sp + %02d: 0x%08lx\n", i * 4, addr); - } - printk("\n"); - - show_trace(task, esp); - - return; -} - -void show_trace_task(struct task_struct *tsk) -{ - /* - * TODO: SysRq-T trace dump... - */ + pr_info("%sCall trace:\n", loglvl); + unwind_stack((void *)loglvl, esp, print_trace); } void show_registers(struct pt_regs *regs) @@ -111,149 +80,87 @@ void show_registers(struct pt_regs *regs) int in_kernel = 1; unsigned long esp; - esp = (unsigned long)(®s->sp); + esp = (unsigned long)(regs->sp); if (user_mode(regs)) in_kernel = 0; - printk("CPU #: %d\n" - " PC: %08lx SR: %08lx SP: %08lx\n", - smp_processor_id(), regs->pc, regs->sr, regs->sp); - printk("GPR00: %08lx GPR01: %08lx GPR02: %08lx GPR03: %08lx\n", - 0L, regs->gpr[1], regs->gpr[2], regs->gpr[3]); - printk("GPR04: %08lx GPR05: %08lx GPR06: %08lx GPR07: %08lx\n", - regs->gpr[4], regs->gpr[5], regs->gpr[6], regs->gpr[7]); - printk("GPR08: %08lx GPR09: %08lx GPR10: %08lx GPR11: %08lx\n", - regs->gpr[8], regs->gpr[9], regs->gpr[10], regs->gpr[11]); - printk("GPR12: %08lx GPR13: %08lx GPR14: %08lx GPR15: %08lx\n", - regs->gpr[12], regs->gpr[13], regs->gpr[14], regs->gpr[15]); - printk("GPR16: %08lx GPR17: %08lx GPR18: %08lx GPR19: %08lx\n", - regs->gpr[16], regs->gpr[17], regs->gpr[18], regs->gpr[19]); - printk("GPR20: %08lx GPR21: %08lx GPR22: %08lx GPR23: %08lx\n", - regs->gpr[20], regs->gpr[21], regs->gpr[22], regs->gpr[23]); - printk("GPR24: %08lx GPR25: %08lx GPR26: %08lx GPR27: %08lx\n", - regs->gpr[24], regs->gpr[25], regs->gpr[26], regs->gpr[27]); - printk("GPR28: %08lx GPR29: %08lx GPR30: %08lx GPR31: %08lx\n", - regs->gpr[28], regs->gpr[29], regs->gpr[30], regs->gpr[31]); - printk(" RES: %08lx oGPR11: %08lx\n", - regs->gpr[11], regs->orig_gpr11); - - printk("Process %s (pid: %d, stackpage=%08lx)\n", - current->comm, current->pid, (unsigned long)current); + pr_info("CPU #: %d\n" + " PC: %08lx SR: %08lx SP: %08lx\n", + smp_processor_id(), regs->pc, regs->sr, regs->sp); + pr_info("GPR00: %08lx GPR01: %08lx GPR02: %08lx GPR03: %08lx\n", + 0L, regs->gpr[1], regs->gpr[2], regs->gpr[3]); + pr_info("GPR04: %08lx GPR05: %08lx GPR06: %08lx GPR07: %08lx\n", + regs->gpr[4], regs->gpr[5], regs->gpr[6], regs->gpr[7]); + pr_info("GPR08: %08lx GPR09: %08lx GPR10: %08lx GPR11: %08lx\n", + regs->gpr[8], regs->gpr[9], regs->gpr[10], regs->gpr[11]); + pr_info("GPR12: %08lx GPR13: %08lx GPR14: %08lx GPR15: %08lx\n", + regs->gpr[12], regs->gpr[13], regs->gpr[14], regs->gpr[15]); + pr_info("GPR16: %08lx GPR17: %08lx GPR18: %08lx GPR19: %08lx\n", + regs->gpr[16], regs->gpr[17], regs->gpr[18], regs->gpr[19]); + pr_info("GPR20: %08lx GPR21: %08lx GPR22: %08lx GPR23: %08lx\n", + regs->gpr[20], regs->gpr[21], regs->gpr[22], regs->gpr[23]); + pr_info("GPR24: %08lx GPR25: %08lx GPR26: %08lx GPR27: %08lx\n", + regs->gpr[24], regs->gpr[25], regs->gpr[26], regs->gpr[27]); + pr_info("GPR28: %08lx GPR29: %08lx GPR30: %08lx GPR31: %08lx\n", + regs->gpr[28], regs->gpr[29], regs->gpr[30], regs->gpr[31]); + pr_info(" RES: %08lx oGPR11: %08lx\n", + regs->gpr[11], regs->orig_gpr11); + + pr_info("Process %s (pid: %d, stackpage=%08lx)\n", + current->comm, current->pid, (unsigned long)current); /* * When in-kernel, we also print out the stack and code at the * time of the fault.. */ if (in_kernel) { - printk("\nStack: "); - show_stack(NULL, (unsigned long *)esp); + pr_info("\nStack: "); + show_stack(NULL, (unsigned long *)esp, KERN_EMERG); - printk("\nCode: "); - if (regs->pc < PAGE_OFFSET) - goto bad; + if (esp < PAGE_OFFSET) + goto bad_stack; - for (i = -24; i < 24; i++) { - unsigned char c; - if (__get_user(c, &((unsigned char *)regs->pc)[i])) { -bad: - printk(" Bad PC value."); + pr_info("\n"); + for (i = -8; i < 24; i += 1) { + unsigned long word; + + if (__get_user(word, &((unsigned long *)esp)[i])) { +bad_stack: + pr_info(" Bad Stack value."); break; } - if (i == 0) - printk("(%02x) ", c); - else - printk("%02x ", c); + print_data(esp, word, i); } - } - printk("\n"); -} -void nommu_dump_state(struct pt_regs *regs, - unsigned long ea, unsigned long vector) -{ - int i; - unsigned long addr, stack = regs->sp; - - printk("\n\r[nommu_dump_state] :: ea %lx, vector %lx\n\r", ea, vector); - - printk("CPU #: %d\n" - " PC: %08lx SR: %08lx SP: %08lx\n", - 0, regs->pc, regs->sr, regs->sp); - printk("GPR00: %08lx GPR01: %08lx GPR02: %08lx GPR03: %08lx\n", - 0L, regs->gpr[1], regs->gpr[2], regs->gpr[3]); - printk("GPR04: %08lx GPR05: %08lx GPR06: %08lx GPR07: %08lx\n", - regs->gpr[4], regs->gpr[5], regs->gpr[6], regs->gpr[7]); - printk("GPR08: %08lx GPR09: %08lx GPR10: %08lx GPR11: %08lx\n", - regs->gpr[8], regs->gpr[9], regs->gpr[10], regs->gpr[11]); - printk("GPR12: %08lx GPR13: %08lx GPR14: %08lx GPR15: %08lx\n", - regs->gpr[12], regs->gpr[13], regs->gpr[14], regs->gpr[15]); - printk("GPR16: %08lx GPR17: %08lx GPR18: %08lx GPR19: %08lx\n", - regs->gpr[16], regs->gpr[17], regs->gpr[18], regs->gpr[19]); - printk("GPR20: %08lx GPR21: %08lx GPR22: %08lx GPR23: %08lx\n", - regs->gpr[20], regs->gpr[21], regs->gpr[22], regs->gpr[23]); - printk("GPR24: %08lx GPR25: %08lx GPR26: %08lx GPR27: %08lx\n", - regs->gpr[24], regs->gpr[25], regs->gpr[26], regs->gpr[27]); - printk("GPR28: %08lx GPR29: %08lx GPR30: %08lx GPR31: %08lx\n", - regs->gpr[28], regs->gpr[29], regs->gpr[30], regs->gpr[31]); - printk(" RES: %08lx oGPR11: %08lx\n", - regs->gpr[11], regs->orig_gpr11); - - printk("Process %s (pid: %d, stackpage=%08lx)\n", - ((struct task_struct *)(__pa(current)))->comm, - ((struct task_struct *)(__pa(current)))->pid, - (unsigned long)current); - - printk("\nStack: "); - printk("Stack dump [0x%08lx]:\n", (unsigned long)stack); - for (i = 0; i < kstack_depth_to_print; i++) { - if (((long)stack & (THREAD_SIZE - 1)) == 0) - break; - stack++; - - printk("%lx :: sp + %02d: 0x%08lx\n", stack, i * 4, - *((unsigned long *)(__pa(stack)))); - } - printk("\n"); - - printk("Call Trace: "); - i = 1; - while (((long)stack & (THREAD_SIZE - 1)) != 0) { - addr = *((unsigned long *)__pa(stack)); - stack++; - - if (kernel_text_address(addr)) { - if (i && ((i % 6) == 0)) - printk("\n "); - printk(" [<%08lx>]", addr); - i++; - } - } - printk("\n"); + pr_info("\nCode: "); + if (regs->pc < PAGE_OFFSET) + goto bad; - printk("\nCode: "); + for (i = -6; i < 6; i += 1) { + unsigned long word; - for (i = -24; i < 24; i++) { - unsigned char c; - c = ((unsigned char *)(__pa(regs->pc)))[i]; + if (__get_user(word, &((unsigned long *)regs->pc)[i])) { +bad: + pr_info(" Bad PC value."); + break; + } - if (i == 0) - printk("(%02x) ", c); - else - printk("%02x ", c); + print_data(regs->pc, word, i); + } } - printk("\n"); + pr_info("\n"); } /* This is normally the 'Oops' routine */ -void die(const char *str, struct pt_regs *regs, long err) +void __noreturn die(const char *str, struct pt_regs *regs, long err) { console_verbose(); - printk("\n%s#: %04lx\n", str, err & 0xffff); + pr_emerg("\n%s#: %04lx\n", str, err & 0xffff); show_registers(regs); #ifdef CONFIG_JUMP_UPON_UNHANDLED_EXCEPTION - printk("\n\nUNHANDLED_EXCEPTION: entering infinite loop\n"); + pr_emerg("\n\nUNHANDLED_EXCEPTION: entering infinite loop\n"); /* shut down interrupts */ local_irq_disable(); @@ -261,56 +168,65 @@ void die(const char *str, struct pt_regs *regs, long err) __asm__ __volatile__("l.nop 1"); do {} while (1); #endif - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } -/* This is normally the 'Oops' routine */ -void die_if_kernel(const char *str, struct pt_regs *regs, long err) +asmlinkage void unhandled_exception(struct pt_regs *regs, int ea, int vector) { - if (user_mode(regs)) - return; - - die(str, regs, err); -} - -void unhandled_exception(struct pt_regs *regs, int ea, int vector) -{ - printk("Unable to handle exception at EA =0x%x, vector 0x%x", - ea, vector); + pr_emerg("Unable to handle exception at EA =0x%x, vector 0x%x", + ea, vector); die("Oops", regs, 9); } -void __init trap_init(void) +asmlinkage void do_fpe_trap(struct pt_regs *regs, unsigned long address) { - /* Nothing needs to be done */ + if (user_mode(regs)) { + int code = FPE_FLTUNK; +#ifdef CONFIG_FPU + unsigned long fpcsr; + + save_fpu(current); + fpcsr = current->thread.fpcsr; + + if (fpcsr & SPR_FPCSR_IVF) + code = FPE_FLTINV; + else if (fpcsr & SPR_FPCSR_OVF) + code = FPE_FLTOVF; + else if (fpcsr & SPR_FPCSR_UNF) + code = FPE_FLTUND; + else if (fpcsr & SPR_FPCSR_DZF) + code = FPE_FLTDIV; + else if (fpcsr & SPR_FPCSR_IXF) + code = FPE_FLTRES; + + /* Clear all flags */ + current->thread.fpcsr &= ~SPR_FPCSR_ALLF; + restore_fpu(current); +#endif + force_sig_fault(SIGFPE, code, (void __user *)regs->pc); + } else { + pr_emerg("KERNEL: Illegal fpe exception 0x%.8lx\n", regs->pc); + die("Die:", regs, SIGFPE); + } } asmlinkage void do_trap(struct pt_regs *regs, unsigned long address) { - siginfo_t info; - memset(&info, 0, sizeof(info)); - info.si_signo = SIGTRAP; - info.si_code = TRAP_TRACE; - info.si_addr = (void *)address; - force_sig_info(SIGTRAP, &info, current); - - regs->pc += 4; + if (user_mode(regs)) { + force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->pc); + } else { + pr_emerg("KERNEL: Illegal trap exception 0x%.8lx\n", regs->pc); + die("Die:", regs, SIGILL); + } } asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address) { - siginfo_t info; - if (user_mode(regs)) { - /* Send a SIGSEGV */ - info.si_signo = SIGSEGV; - info.si_errno = 0; - /* info.si_code has been set above */ - info.si_addr = (void *)address; - force_sig_info(SIGSEGV, &info, current); + /* Send a SIGBUS */ + force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)address); } else { - printk("KERNEL: Unaligned Access 0x%.8lx\n", address); - show_registers(regs); + pr_emerg("KERNEL: Unaligned Access 0x%.8lx\n", address); die("Die:", regs, address); } @@ -318,38 +234,206 @@ asmlinkage void do_unaligned_access(struct pt_regs *regs, unsigned long address) asmlinkage void do_bus_fault(struct pt_regs *regs, unsigned long address) { - siginfo_t info; - if (user_mode(regs)) { /* Send a SIGBUS */ - info.si_signo = SIGBUS; - info.si_errno = 0; - info.si_code = BUS_ADRERR; - info.si_addr = (void *)address; - force_sig_info(SIGBUS, &info, current); + force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address); } else { /* Kernel mode */ - printk("KERNEL: Bus error (SIGBUS) 0x%.8lx\n", address); - show_registers(regs); + pr_emerg("KERNEL: Bus error (SIGBUS) 0x%.8lx\n", address); die("Die:", regs, address); } } +static inline int in_delay_slot(struct pt_regs *regs) +{ +#ifdef CONFIG_OPENRISC_NO_SPR_SR_DSX + /* No delay slot flag, do the old way */ + unsigned int op, insn; + + insn = *((unsigned int *)regs->pc); + op = insn >> 26; + switch (op) { + case 0x00: /* l.j */ + case 0x01: /* l.jal */ + case 0x03: /* l.bnf */ + case 0x04: /* l.bf */ + case 0x11: /* l.jr */ + case 0x12: /* l.jalr */ + return 1; + default: + return 0; + } +#else + return mfspr(SPR_SR) & SPR_SR_DSX; +#endif +} + +static inline void adjust_pc(struct pt_regs *regs, unsigned long address) +{ + int displacement; + unsigned int rb, op, jmp; + + if (unlikely(in_delay_slot(regs))) { + /* In delay slot, instruction at pc is a branch, simulate it */ + jmp = *((unsigned int *)regs->pc); + + displacement = sign_extend32(((jmp) & 0x3ffffff) << 2, 27); + rb = (jmp & 0x0000ffff) >> 11; + op = jmp >> 26; + + switch (op) { + case 0x00: /* l.j */ + regs->pc += displacement; + return; + case 0x01: /* l.jal */ + regs->pc += displacement; + regs->gpr[9] = regs->pc + 8; + return; + case 0x03: /* l.bnf */ + if (regs->sr & SPR_SR_F) + regs->pc += 8; + else + regs->pc += displacement; + return; + case 0x04: /* l.bf */ + if (regs->sr & SPR_SR_F) + regs->pc += displacement; + else + regs->pc += 8; + return; + case 0x11: /* l.jr */ + regs->pc = regs->gpr[rb]; + return; + case 0x12: /* l.jalr */ + regs->pc = regs->gpr[rb]; + regs->gpr[9] = regs->pc + 8; + return; + default: + break; + } + } else { + regs->pc += 4; + } +} + +static inline void simulate_lwa(struct pt_regs *regs, unsigned long address, + unsigned int insn) +{ + unsigned int ra, rd; + unsigned long value; + unsigned long orig_pc; + long imm; + + const struct exception_table_entry *entry; + + orig_pc = regs->pc; + adjust_pc(regs, address); + + ra = (insn >> 16) & 0x1f; + rd = (insn >> 21) & 0x1f; + imm = (short)insn; + lwa_addr = (unsigned long __user *)(regs->gpr[ra] + imm); + + if ((unsigned long)lwa_addr & 0x3) { + do_unaligned_access(regs, address); + return; + } + + if (get_user(value, lwa_addr)) { + if (user_mode(regs)) { + force_sig(SIGSEGV); + return; + } + + if ((entry = search_exception_tables(orig_pc))) { + regs->pc = entry->fixup; + return; + } + + /* kernel access in kernel space, load it directly */ + value = *((unsigned long *)lwa_addr); + } + + lwa_flag = 1; + regs->gpr[rd] = value; +} + +static inline void simulate_swa(struct pt_regs *regs, unsigned long address, + unsigned int insn) +{ + unsigned long __user *vaddr; + unsigned long orig_pc; + unsigned int ra, rb; + long imm; + + const struct exception_table_entry *entry; + + orig_pc = regs->pc; + adjust_pc(regs, address); + + ra = (insn >> 16) & 0x1f; + rb = (insn >> 11) & 0x1f; + imm = (short)(((insn & 0x2200000) >> 10) | (insn & 0x7ff)); + vaddr = (unsigned long __user *)(regs->gpr[ra] + imm); + + if (!lwa_flag || vaddr != lwa_addr) { + regs->sr &= ~SPR_SR_F; + return; + } + + if ((unsigned long)vaddr & 0x3) { + do_unaligned_access(regs, address); + return; + } + + if (put_user(regs->gpr[rb], vaddr)) { + if (user_mode(regs)) { + force_sig(SIGSEGV); + return; + } + + if ((entry = search_exception_tables(orig_pc))) { + regs->pc = entry->fixup; + return; + } + + /* kernel access in kernel space, store it directly */ + *((unsigned long *)vaddr) = regs->gpr[rb]; + } + + lwa_flag = 0; + regs->sr |= SPR_SR_F; +} + +#define INSN_LWA 0x1b +#define INSN_SWA 0x33 + asmlinkage void do_illegal_instruction(struct pt_regs *regs, unsigned long address) { - siginfo_t info; + unsigned int op; + unsigned int insn = *((unsigned int *)address); + + op = insn >> 26; + + switch (op) { + case INSN_LWA: + simulate_lwa(regs, address, insn); + return; + + case INSN_SWA: + simulate_swa(regs, address, insn); + return; + + default: + break; + } if (user_mode(regs)) { /* Send a SIGILL */ - info.si_signo = SIGILL; - info.si_errno = 0; - info.si_code = ILL_ILLOPC; - info.si_addr = (void *)address; - force_sig_info(SIGBUS, &info, current); + force_sig_fault(SIGILL, ILL_ILLOPC, (void __user *)address); } else { /* Kernel mode */ - printk("KERNEL: Illegal instruction (SIGILL) 0x%.8lx\n", - address); - show_registers(regs); + pr_emerg("KERNEL: Illegal instruction (SIGILL) 0x%.8lx\n", + address); die("Die:", regs, address); } } diff --git a/arch/openrisc/kernel/unwinder.c b/arch/openrisc/kernel/unwinder.c new file mode 100644 index 000000000000..c6ad6f867a6a --- /dev/null +++ b/arch/openrisc/kernel/unwinder.c @@ -0,0 +1,105 @@ +/* + * OpenRISC unwinder.c + * + * Reusable arch specific api for unwinding stacks. + * + * Copyright (C) 2017 Stafford Horne <shorne@gmail.com> + * + * This file is licensed under the terms of the GNU General Public License + * version 2. This program is licensed "as is" without any warranty of any + * kind, whether express or implied. + */ + +#include <linux/sched/task_stack.h> +#include <linux/kernel.h> + +#include <asm/unwinder.h> + +#ifdef CONFIG_FRAME_POINTER +struct or1k_frameinfo { + unsigned long *fp; + unsigned long ra; + unsigned long top; +}; + +/* + * Verify a frameinfo structure. The return address should be a valid text + * address. The frame pointer may be null if its the last frame, otherwise + * the frame pointer should point to a location in the stack after the + * top of the next frame up. + */ +static inline int or1k_frameinfo_valid(struct or1k_frameinfo *frameinfo) +{ + return (frameinfo->fp == NULL || + (!kstack_end(frameinfo->fp) && + frameinfo->fp > &frameinfo->top)) && + __kernel_text_address(frameinfo->ra); +} + +/* + * Create a stack trace doing scanning which is frame pointer aware. We can + * get reliable stack traces by matching the previously found frame + * pointer with the top of the stack address every time we find a valid + * or1k_frameinfo. + * + * Ideally the stack parameter will be passed as FP, but it can not be + * guaranteed. Therefore we scan each address looking for the first sign + * of a return address. + * + * The OpenRISC stack frame looks something like the following. The + * location SP is held in r1 and location FP is held in r2 when frame pointers + * enabled. + * + * SP -> (top of stack) + * - (callee saved registers) + * - (local variables) + * FP-8 -> previous FP \ + * FP-4 -> return address |- or1k_frameinfo + * FP -> (previous top of stack) / + */ +void unwind_stack(void *data, unsigned long *stack, + void (*trace)(void *data, unsigned long addr, int reliable)) +{ + unsigned long *next_fp = NULL; + struct or1k_frameinfo *frameinfo = NULL; + int reliable = 0; + + while (!kstack_end(stack)) { + frameinfo = container_of(stack, + struct or1k_frameinfo, + top); + + if (__kernel_text_address(frameinfo->ra)) { + if (or1k_frameinfo_valid(frameinfo) && + (next_fp == NULL || + next_fp == &frameinfo->top)) { + reliable = 1; + next_fp = frameinfo->fp; + } else + reliable = 0; + + trace(data, frameinfo->ra, reliable); + } + stack++; + } +} + +#else /* CONFIG_FRAME_POINTER */ + +/* + * Create a stack trace by doing a simple scan treating all text addresses + * as return addresses. + */ +void unwind_stack(void *data, unsigned long *stack, + void (*trace)(void *data, unsigned long addr, int reliable)) +{ + unsigned long addr; + + while (!kstack_end(stack)) { + addr = *stack++; + if (__kernel_text_address(addr)) + trace(data, addr, 0); + } +} +#endif /* CONFIG_FRAME_POINTER */ + diff --git a/arch/openrisc/kernel/vmlinux.h b/arch/openrisc/kernel/vmlinux.h index ee842a2d3f36..bdea46c617c7 100644 --- a/arch/openrisc/kernel/vmlinux.h +++ b/arch/openrisc/kernel/vmlinux.h @@ -1,12 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __OPENRISC_VMLINUX_H_ #define __OPENRISC_VMLINUX_H_ -extern char _stext, _etext, _edata, _end; #ifdef CONFIG_BLK_DEV_INITRD extern char __initrd_start, __initrd_end; -extern char __initramfs_start; #endif -extern u32 __dtb_start[]; - #endif diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index 2d69a853b742..049bff45f612 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * OpenRISC vmlinux.lds.S * @@ -9,18 +10,13 @@ * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> * - * 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. - * * ld script for OpenRISC architecture */ /* TODO * - clean up __offset & stuff - * - change all 8192 aligment to PAGE !!! - * - recheck if all aligments are really needed + * - change all 8192 alignment to PAGE !!! + * - recheck if all alignments are really needed */ # define LOAD_OFFSET PAGE_OFFSET @@ -28,9 +24,16 @@ #include <asm/page.h> #include <asm/cache.h> +#include <asm/thread_info.h> #include <asm-generic/vmlinux.lds.h> -OUTPUT_FORMAT("elf32-or32", "elf32-or32", "elf32-or32") +#ifdef __OR1K__ +#define __OUTPUT_FORMAT "elf32-or1k" +#else +#define __OUTPUT_FORMAT "elf32-or32" +#endif + +OUTPUT_FORMAT(__OUTPUT_FORMAT, __OUTPUT_FORMAT, __OUTPUT_FORMAT) jiffies = jiffies_64 + 4; SECTIONS @@ -38,6 +41,8 @@ SECTIONS /* Read-only sections, merged into text segment: */ . = LOAD_BASE ; + _text = .; + /* _s_kernel_ro must be page aligned */ . = ALIGN(PAGE_SIZE); _s_kernel_ro = .; @@ -45,11 +50,13 @@ SECTIONS .text : AT(ADDR(.text) - LOAD_OFFSET) { _stext = .; + HEAD_TEXT TEXT_TEXT SCHED_TEXT LOCK_TEXT KPROBES_TEXT IRQENTRY_TEXT + SOFTIRQENTRY_TEXT *(.fixup) *(.text.__*) _etext = .; @@ -60,26 +67,23 @@ SECTIONS _sdata = .; - /* Page alignment required for RO_DATA_SECTION */ - RO_DATA_SECTION(PAGE_SIZE) + /* Page alignment required for RO_DATA */ + RO_DATA(PAGE_SIZE) _e_kernel_ro = .; /* Whatever comes after _e_kernel_ro had better be page-aligend, too */ /* 32 here is cacheline size... recheck this */ - RW_DATA_SECTION(32, PAGE_SIZE, PAGE_SIZE) + RW_DATA(32, PAGE_SIZE, PAGE_SIZE) _edata = .; EXCEPTION_TABLE(4) - NOTES /* Init code and data */ . = ALIGN(PAGE_SIZE); __init_begin = .; - HEAD_TEXT_SECTION - /* Page aligned */ INIT_TEXT_SECTION(PAGE_SIZE) @@ -90,18 +94,6 @@ SECTIONS __init_end = .; - . = ALIGN(PAGE_SIZE); - .initrd : AT(ADDR(.initrd) - LOAD_OFFSET) - { - __initrd_start = .; - *(.initrd) - __initrd_end = .; - FILL (0); - . = ALIGN (PAGE_SIZE); - } - - __vmlinux_end = .; /* last address of the physical file */ - BSS_SECTION(0, 0, 0x20) _end = .; @@ -109,6 +101,7 @@ SECTIONS /* Throw in the debugging sections */ STABS_DEBUG DWARF_DEBUG + ELF_DETAILS /* Sections to be discarded -- must be last */ DISCARDS |