diff options
Diffstat (limited to 'arch/riscv')
25 files changed, 266 insertions, 136 deletions
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index f5fe8a7f0e24..a34c531be4e7 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -62,7 +62,6 @@ config RISCV select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL if MMU && 64BIT - select HANDLE_DOMAIN_IRQ select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL @@ -163,6 +162,12 @@ config PAGE_OFFSET default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB +config KASAN_SHADOW_OFFSET + hex + depends on KASAN_GENERIC + default 0xdfffffc800000000 if 64BIT + default 0xffffffff if 32BIT + config ARCH_FLATMEM_ENABLE def_bool !NUMA @@ -563,4 +568,3 @@ source "kernel/power/Kconfig" endmenu source "arch/riscv/kvm/Kconfig" -source "drivers/firmware/Kconfig" diff --git a/arch/riscv/include/asm/kasan.h b/arch/riscv/include/asm/kasan.h index a2b3d9cdbc86..b00f503ec124 100644 --- a/arch/riscv/include/asm/kasan.h +++ b/arch/riscv/include/asm/kasan.h @@ -30,8 +30,7 @@ #define KASAN_SHADOW_SIZE (UL(1) << ((CONFIG_VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT)) #define KASAN_SHADOW_START KERN_VIRT_START #define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE) -#define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << \ - (64 - KASAN_SHADOW_SCALE_SHIFT))) +#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) void kasan_init(void); asmlinkage void kasan_early_init(void); diff --git a/arch/riscv/include/asm/kprobes.h b/arch/riscv/include/asm/kprobes.h index 9ea9b5ec3113..217ef89f22b9 100644 --- a/arch/riscv/include/asm/kprobes.h +++ b/arch/riscv/include/asm/kprobes.h @@ -40,7 +40,7 @@ void arch_remove_kprobe(struct kprobe *p); int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr); bool kprobe_breakpoint_handler(struct pt_regs *regs); bool kprobe_single_step_handler(struct pt_regs *regs); -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); void __kprobes *trampoline_probe_handler(struct pt_regs *regs); #endif /* CONFIG_KPROBES */ diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 46b492c78cbb..0749924d9e55 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -66,7 +66,7 @@ static inline void release_thread(struct task_struct *dead_task) { } -extern unsigned long get_wchan(struct task_struct *p); +extern unsigned long __get_wchan(struct task_struct *p); static inline void wait_for_interrupt(void) diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h index b933b1583c9f..34fbb3ea21d5 100644 --- a/arch/riscv/include/asm/syscall.h +++ b/arch/riscv/include/asm/syscall.h @@ -82,4 +82,5 @@ static inline int syscall_get_arch(struct task_struct *task) #endif } +asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t); #endif /* _ASM_RISCV_SYSCALL_H */ diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index 893e47195e30..208e31bc5d1c 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -16,18 +16,24 @@ #ifdef CONFIG_MMU #include <linux/types.h> -#include <generated/vdso-offsets.h> +/* + * All systems with an MMU have a VDSO, but systems without an MMU don't + * support shared libraries and therefor don't have one. + */ +#ifdef CONFIG_MMU + +#define __VVAR_PAGES 1 -#ifndef CONFIG_GENERIC_TIME_VSYSCALL -struct vdso_data { -}; -#endif +#ifndef __ASSEMBLY__ +#include <generated/vdso-offsets.h> #define VDSO_SYMBOL(base, name) \ (void __user *)((unsigned long)(base) + __vdso_##name##_offset) #endif /* CONFIG_MMU */ -asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t); +#endif /* !__ASSEMBLY__ */ + +#endif /* CONFIG_MMU */ #endif /* _ASM_RISCV_VDSO_H */ diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h index 4b989ae15d59..8062996c2dfd 100644 --- a/arch/riscv/include/uapi/asm/unistd.h +++ b/arch/riscv/include/uapi/asm/unistd.h @@ -18,9 +18,10 @@ #ifdef __LP64__ #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SET_GET_RLIMIT -#define __ARCH_WANT_SYS_CLONE3 #endif /* __LP64__ */ +#define __ARCH_WANT_SYS_CLONE3 + #include <asm-generic/unistd.h> /* diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index 24d3827e4837..253126e4beef 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -35,7 +35,6 @@ void asm_offsets(void) OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count); OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp); OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp); - OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu); OFFSET(TASK_THREAD_F0, task_struct, thread.fstate.f[0]); OFFSET(TASK_THREAD_F1, task_struct, thread.fstate.f[1]); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 98f502654edd..ed29e9c8f660 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -130,8 +130,7 @@ skip_context_tracking: /* Handle interrupts */ move a0, sp /* pt_regs */ - la a1, handle_arch_irq - REG_L a1, (a1) + la a1, generic_handle_arch_irq jr a1 1: /* @@ -544,11 +543,6 @@ ENTRY(__switch_to) REG_L s9, TASK_THREAD_S9_RA(a4) REG_L s10, TASK_THREAD_S10_RA(a4) REG_L s11, TASK_THREAD_S11_RA(a4) - /* Swap the CPU entry around. */ - lw a3, TASK_TI_CPU(a0) - lw a4, TASK_TI_CPU(a1) - sw a3, TASK_TI_CPU(a1) - sw a4, TASK_TI_CPU(a0) /* The offset of thread_info in task_struct is zero. */ move tp, a1 ret diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 7f1e5203de88..4716f4cdc038 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -154,11 +154,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ret; } - -int __init ftrace_dyn_arch_init(void) -{ - return 0; -} #endif #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index fce5184b22c3..25ec50573957 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -193,6 +193,7 @@ setup_trap_vector: csrw CSR_SCRATCH, zero ret +.align 2 .Lsecondary_park: /* We lack SMP support or have too many harts, so park this hart */ wfi @@ -317,7 +318,6 @@ clear_bss_done: call setup_trap_vector /* Restore C environment */ la tp, init_task - sw zero, TASK_TI_CPU(tp) la sp, init_thread_union + THREAD_SIZE #ifdef CONFIG_KASAN diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c index aab85a82f419..7142ec42e889 100644 --- a/arch/riscv/kernel/probes/ftrace.c +++ b/arch/riscv/kernel/probes/ftrace.c @@ -15,7 +15,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, if (bit < 0) return; - preempt_disable_notrace(); p = get_kprobe((kprobe_opcode_t *)ip); if (unlikely(!p) || kprobe_disabled(p)) goto out; @@ -52,7 +51,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, __this_cpu_write(current_kprobe, NULL); } out: - preempt_enable_notrace(); ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 00088dc6da4b..e6e950b7cf32 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0+ +#define pr_fmt(fmt) "kprobes: " fmt + #include <linux/kprobes.h> #include <linux/extable.h> #include <linux/slab.h> @@ -50,11 +52,8 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) { unsigned long probe_addr = (unsigned long)p->addr; - if (probe_addr & 0x1) { - pr_warn("Address not aligned.\n"); - - return -EINVAL; - } + if (probe_addr & 0x1) + return -EILSEQ; /* copy instruction */ p->opcode = *p->addr; @@ -191,7 +190,7 @@ static int __kprobes reenter_kprobe(struct kprobe *p, break; case KPROBE_HIT_SS: case KPROBE_REENTER: - pr_warn("Unrecoverable kprobe detected.\n"); + pr_warn("Failed to recover from reentered kprobes.\n"); dump_kprobe(p); BUG(); break; @@ -348,7 +347,7 @@ int __init arch_populate_kprobe_blacklist(void) void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs) { - return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL); + return (void *)kretprobe_trampoline_handler(regs, NULL); } void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, @@ -356,7 +355,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, { ri->ret_addr = (kprobe_opcode_t *)regs->ra; ri->fp = NULL; - regs->ra = (unsigned long) &kretprobe_trampoline; + regs->ra = (unsigned long) &__kretprobe_trampoline; } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/riscv/kernel/probes/kprobes_trampoline.S b/arch/riscv/kernel/probes/kprobes_trampoline.S index 6e85d021e2a2..7bdb09ded39b 100644 --- a/arch/riscv/kernel/probes/kprobes_trampoline.S +++ b/arch/riscv/kernel/probes/kprobes_trampoline.S @@ -75,7 +75,7 @@ REG_L x31, PT_T6(sp) .endm -ENTRY(kretprobe_trampoline) +ENTRY(__kretprobe_trampoline) addi sp, sp, -(PT_SIZE_ON_STACK) save_all_base_regs @@ -90,4 +90,4 @@ ENTRY(kretprobe_trampoline) addi sp, sp, PT_SIZE_ON_STACK ret -ENDPROC(kretprobe_trampoline) +ENDPROC(__kretprobe_trampoline) diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 921d9d7df400..2f6da845c9ae 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -140,12 +140,9 @@ void arch_irq_work_raise(void) void handle_IPI(struct pt_regs *regs) { - struct pt_regs *old_regs = set_irq_regs(regs); unsigned long *pending_ipis = &ipi_data[smp_processor_id()].bits; unsigned long *stats = ipi_data[smp_processor_id()].stats; - irq_enter(); - riscv_clear_ipi(); while (true) { @@ -156,7 +153,7 @@ void handle_IPI(struct pt_regs *regs) ops = xchg(pending_ipis, 0); if (ops == 0) - goto done; + return; if (ops & (1 << IPI_RESCHEDULE)) { stats[IPI_RESCHEDULE]++; @@ -189,10 +186,6 @@ void handle_IPI(struct pt_regs *regs) /* Order data access and bit testing. */ mb(); } - -done: - irq_exit(); - set_irq_regs(old_regs); } static const char * const ipi_names[] = { diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 315db3d0229b..0fcdc0233fac 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -128,16 +128,14 @@ static bool save_wchan(void *arg, unsigned long pc) return true; } -unsigned long get_wchan(struct task_struct *task) +unsigned long __get_wchan(struct task_struct *task) { unsigned long pc = 0; - if (likely(task && task != current && !task_is_running(task))) { - if (!try_get_task_stack(task)) - return 0; - walk_stackframe(task, NULL, save_wchan, &pc); - put_task_stack(task); - } + if (!try_get_task_stack(task)) + return 0; + walk_stackframe(task, NULL, save_wchan, &pc); + put_task_stack(task); return pc; } diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c index a63c667c27b3..44b1420a2270 100644 --- a/arch/riscv/kernel/syscall_table.c +++ b/arch/riscv/kernel/syscall_table.c @@ -7,7 +7,6 @@ #include <linux/linkage.h> #include <linux/syscalls.h> #include <asm-generic/syscalls.h> -#include <asm/vdso.h> #include <asm/syscall.h> #undef __SYSCALL diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 25a3b8849599..b70956d80408 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -12,14 +12,24 @@ #include <linux/binfmts.h> #include <linux/err.h> #include <asm/page.h> +#include <asm/vdso.h> + #ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> #else -#include <asm/vdso.h> +struct vdso_data { +}; #endif extern char vdso_start[], vdso_end[]; +enum vvar_pages { + VVAR_DATA_PAGE_OFFSET, + VVAR_NR_PAGES, +}; + +#define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) + static unsigned int vdso_pages __ro_after_init; static struct page **vdso_pagelist __ro_after_init; @@ -38,7 +48,7 @@ static int __init vdso_init(void) vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT; vdso_pagelist = - kcalloc(vdso_pages + 1, sizeof(struct page *), GFP_KERNEL); + kcalloc(vdso_pages + VVAR_NR_PAGES, sizeof(struct page *), GFP_KERNEL); if (unlikely(vdso_pagelist == NULL)) { pr_err("vdso: pagelist allocation failed\n"); return -ENOMEM; @@ -63,38 +73,41 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, unsigned long vdso_base, vdso_len; int ret; - vdso_len = (vdso_pages + 1) << PAGE_SHIFT; + BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); + + vdso_len = (vdso_pages + VVAR_NR_PAGES) << PAGE_SHIFT; + + if (mmap_write_lock_killable(mm)) + return -EINTR; - mmap_write_lock(mm); vdso_base = get_unmapped_area(NULL, 0, vdso_len, 0, 0); if (IS_ERR_VALUE(vdso_base)) { ret = vdso_base; goto end; } - /* - * Put vDSO base into mm struct. We need to do this before calling - * install_special_mapping or the perf counter mmap tracking code - * will fail to recognise it as a vDSO (since arch_vma_name fails). - */ - mm->context.vdso = (void *)vdso_base; + mm->context.vdso = NULL; + ret = install_special_mapping(mm, vdso_base, VVAR_SIZE, + (VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]); + if (unlikely(ret)) + goto end; ret = - install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT, + install_special_mapping(mm, vdso_base + VVAR_SIZE, + vdso_pages << PAGE_SHIFT, (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), vdso_pagelist); - if (unlikely(ret)) { - mm->context.vdso = NULL; + if (unlikely(ret)) goto end; - } - vdso_base += (vdso_pages << PAGE_SHIFT); - ret = install_special_mapping(mm, vdso_base, PAGE_SIZE, - (VM_READ | VM_MAYREAD), &vdso_pagelist[vdso_pages]); + /* + * Put vDSO base into mm struct. We need to do this before calling + * install_special_mapping or the perf counter mmap tracking code + * will fail to recognise it as a vDSO (since arch_vma_name fails). + */ + mm->context.vdso = (void *)vdso_base + VVAR_SIZE; - if (unlikely(ret)) - mm->context.vdso = NULL; end: mmap_write_unlock(mm); return ret; @@ -105,7 +118,7 @@ const char *arch_vma_name(struct vm_area_struct *vma) if (vma->vm_mm && (vma->vm_start == (long)vma->vm_mm->context.vdso)) return "[vdso]"; if (vma->vm_mm && (vma->vm_start == - (long)vma->vm_mm->context.vdso + PAGE_SIZE)) + (long)vma->vm_mm->context.vdso - VVAR_SIZE)) return "[vdso_data]"; return NULL; } diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S index e6f558bca71b..e9111f700af0 100644 --- a/arch/riscv/kernel/vdso/vdso.lds.S +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -3,12 +3,13 @@ * Copyright (C) 2012 Regents of the University of California */ #include <asm/page.h> +#include <asm/vdso.h> OUTPUT_ARCH(riscv) SECTIONS { - PROVIDE(_vdso_data = . + PAGE_SIZE); + PROVIDE(_vdso_data = . - __VVAR_PAGES * PAGE_SIZE); . = SIZEOF_HEADERS; .hash : { *(.hash) } :text diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index 094118663285..89f81067e09e 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -16,6 +16,8 @@ static void ipi_remote_fence_i(void *info) void flush_icache_all(void) { + local_flush_icache_all(); + if (IS_ENABLED(CONFIG_RISCV_SBI)) sbi_remote_fence_i(NULL); else diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c index 2fc729422151..18bf338303b6 100644 --- a/arch/riscv/mm/extable.c +++ b/arch/riscv/mm/extable.c @@ -11,14 +11,23 @@ #include <linux/module.h> #include <linux/uaccess.h> +#ifdef CONFIG_BPF_JIT +int rv_bpf_fixup_exception(const struct exception_table_entry *ex, struct pt_regs *regs); +#endif + int fixup_exception(struct pt_regs *regs) { const struct exception_table_entry *fixup; fixup = search_exception_tables(regs->epc); - if (fixup) { - regs->epc = fixup->fixup; - return 1; - } - return 0; + if (!fixup) + return 0; + +#ifdef CONFIG_BPF_JIT + if (regs->epc >= BPF_JIT_REGION_START && regs->epc < BPF_JIT_REGION_END) + return rv_bpf_fixup_exception(fixup, regs); +#endif + + regs->epc = fixup->fixup; + return 1; } diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index d7189c8714a9..54294f83513d 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -17,6 +17,9 @@ asmlinkage void __init kasan_early_init(void) uintptr_t i; pgd_t *pgd = early_pg_dir + pgd_index(KASAN_SHADOW_START); + BUILD_BUG_ON(KASAN_SHADOW_OFFSET != + KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT))); + for (i = 0; i < PTRS_PER_PTE; ++i) set_pte(kasan_early_shadow_pte + i, mk_pte(virt_to_page(kasan_early_shadow_page), @@ -172,21 +175,10 @@ void __init kasan_init(void) phys_addr_t p_start, p_end; u64 i; - /* - * Populate all kernel virtual address space with kasan_early_shadow_page - * except for the linear mapping and the modules/kernel/BPF mapping. - */ - kasan_populate_early_shadow((void *)KASAN_SHADOW_START, - (void *)kasan_mem_to_shadow((void *) - VMEMMAP_END)); if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) kasan_shallow_populate( (void *)kasan_mem_to_shadow((void *)VMALLOC_START), (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); - else - kasan_populate_early_shadow( - (void *)kasan_mem_to_shadow((void *)VMALLOC_START), - (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); /* Populate the linear mapping */ for_each_mem_range(i, &p_start, &p_end) { diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index 75c1e9996867..f42d9cd3b64d 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -71,6 +71,7 @@ struct rv_jit_context { int ninsns; int epilogue_offset; int *offset; /* BPF to RV */ + int nexentries; unsigned long flags; int stack_size; }; diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 3af4131c22c7..2ca345c7b0bf 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -5,6 +5,7 @@ * */ +#include <linux/bitfield.h> #include <linux/bpf.h> #include <linux/filter.h> #include "bpf_jit.h" @@ -27,6 +28,21 @@ static const int regmap[] = { [BPF_REG_AX] = RV_REG_T0, }; +static const int pt_regmap[] = { + [RV_REG_A0] = offsetof(struct pt_regs, a0), + [RV_REG_A1] = offsetof(struct pt_regs, a1), + [RV_REG_A2] = offsetof(struct pt_regs, a2), + [RV_REG_A3] = offsetof(struct pt_regs, a3), + [RV_REG_A4] = offsetof(struct pt_regs, a4), + [RV_REG_A5] = offsetof(struct pt_regs, a5), + [RV_REG_S1] = offsetof(struct pt_regs, s1), + [RV_REG_S2] = offsetof(struct pt_regs, s2), + [RV_REG_S3] = offsetof(struct pt_regs, s3), + [RV_REG_S4] = offsetof(struct pt_regs, s4), + [RV_REG_S5] = offsetof(struct pt_regs, s5), + [RV_REG_T0] = offsetof(struct pt_regs, t0), +}; + enum { RV_CTX_F_SEEN_TAIL_CALL = 0, RV_CTX_F_SEEN_CALL = RV_REG_RA, @@ -440,6 +456,69 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx) return 0; } +#define BPF_FIXUP_OFFSET_MASK GENMASK(26, 0) +#define BPF_FIXUP_REG_MASK GENMASK(31, 27) + +int rv_bpf_fixup_exception(const struct exception_table_entry *ex, + struct pt_regs *regs) +{ + off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup); + int regs_offset = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup); + + *(unsigned long *)((void *)regs + pt_regmap[regs_offset]) = 0; + regs->epc = (unsigned long)&ex->fixup - offset; + + return 1; +} + +/* For accesses to BTF pointers, add an entry to the exception table */ +static int add_exception_handler(const struct bpf_insn *insn, + struct rv_jit_context *ctx, + int dst_reg, int insn_len) +{ + struct exception_table_entry *ex; + unsigned long pc; + off_t offset; + + if (!ctx->insns || !ctx->prog->aux->extable || BPF_MODE(insn->code) != BPF_PROBE_MEM) + return 0; + + if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries)) + return -EINVAL; + + if (WARN_ON_ONCE(insn_len > ctx->ninsns)) + return -EINVAL; + + if (WARN_ON_ONCE(!rvc_enabled() && insn_len == 1)) + return -EINVAL; + + ex = &ctx->prog->aux->extable[ctx->nexentries]; + pc = (unsigned long)&ctx->insns[ctx->ninsns - insn_len]; + + offset = pc - (long)&ex->insn; + if (WARN_ON_ONCE(offset >= 0 || offset < INT_MIN)) + return -ERANGE; + ex->insn = pc; + + /* + * Since the extable follows the program, the fixup offset is always + * negative and limited to BPF_JIT_REGION_SIZE. Store a positive value + * to keep things simple, and put the destination register in the upper + * bits. We don't need to worry about buildtime or runtime sort + * modifying the upper bits because the table is already sorted, and + * isn't part of the main exception table. + */ + offset = (long)&ex->fixup - (pc + insn_len * sizeof(u16)); + if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, offset)) + return -ERANGE; + + ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, offset) | + FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg); + + ctx->nexentries++; + return 0; +} + int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, bool extra_pass) { @@ -893,52 +972,86 @@ out_be: /* LDX: dst = *(size *)(src + off) */ case BPF_LDX | BPF_MEM | BPF_B: - if (is_12b_int(off)) { - emit(rv_lbu(rd, off, rs), ctx); + case BPF_LDX | BPF_MEM | BPF_H: + case BPF_LDX | BPF_MEM | BPF_W: + case BPF_LDX | BPF_MEM | BPF_DW: + case BPF_LDX | BPF_PROBE_MEM | BPF_B: + case BPF_LDX | BPF_PROBE_MEM | BPF_H: + case BPF_LDX | BPF_PROBE_MEM | BPF_W: + case BPF_LDX | BPF_PROBE_MEM | BPF_DW: + { + int insn_len, insns_start; + + switch (BPF_SIZE(code)) { + case BPF_B: + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit(rv_lbu(rd, off, rs), ctx); + insn_len = ctx->ninsns - insns_start; + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + emit(rv_lbu(rd, 0, RV_REG_T1), ctx); + insn_len = ctx->ninsns - insns_start; + if (insn_is_zext(&insn[1])) + return 1; break; - } + case BPF_H: + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit(rv_lhu(rd, off, rs), ctx); + insn_len = ctx->ninsns - insns_start; + break; + } - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - emit(rv_lbu(rd, 0, RV_REG_T1), ctx); - if (insn_is_zext(&insn[1])) - return 1; - break; - case BPF_LDX | BPF_MEM | BPF_H: - if (is_12b_int(off)) { - emit(rv_lhu(rd, off, rs), ctx); + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + emit(rv_lhu(rd, 0, RV_REG_T1), ctx); + insn_len = ctx->ninsns - insns_start; + if (insn_is_zext(&insn[1])) + return 1; break; - } + case BPF_W: + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit(rv_lwu(rd, off, rs), ctx); + insn_len = ctx->ninsns - insns_start; + break; + } - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - emit(rv_lhu(rd, 0, RV_REG_T1), ctx); - if (insn_is_zext(&insn[1])) - return 1; - break; - case BPF_LDX | BPF_MEM | BPF_W: - if (is_12b_int(off)) { - emit(rv_lwu(rd, off, rs), ctx); + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + emit(rv_lwu(rd, 0, RV_REG_T1), ctx); + insn_len = ctx->ninsns - insns_start; + if (insn_is_zext(&insn[1])) + return 1; break; - } + case BPF_DW: + if (is_12b_int(off)) { + insns_start = ctx->ninsns; + emit_ld(rd, off, rs, ctx); + insn_len = ctx->ninsns - insns_start; + break; + } - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - emit(rv_lwu(rd, 0, RV_REG_T1), ctx); - if (insn_is_zext(&insn[1])) - return 1; - break; - case BPF_LDX | BPF_MEM | BPF_DW: - if (is_12b_int(off)) { - emit_ld(rd, off, rs, ctx); + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + insns_start = ctx->ninsns; + emit_ld(rd, 0, RV_REG_T1, ctx); + insn_len = ctx->ninsns - insns_start; break; } - emit_imm(RV_REG_T1, off, ctx); - emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); - emit_ld(rd, 0, RV_REG_T1, ctx); + ret = add_exception_handler(insn, ctx, rd, insn_len); + if (ret) + return ret; break; - + } /* speculation barrier */ case BPF_ST | BPF_NOSPEC: break; diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index fed86f42dfbe..be743d700aa7 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -11,7 +11,7 @@ #include "bpf_jit.h" /* Number of iterations to try until offsets converge. */ -#define NR_JIT_ITERATIONS 16 +#define NR_JIT_ITERATIONS 32 static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset) { @@ -41,12 +41,12 @@ bool bpf_jit_needs_zext(void) struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { + unsigned int prog_size = 0, extable_size = 0; bool tmp_blinded = false, extra_pass = false; struct bpf_prog *tmp, *orig_prog = prog; int pass = 0, prev_ninsns = 0, i; struct rv_jit_data *jit_data; struct rv_jit_context *ctx; - unsigned int image_size = 0; if (!prog->jit_requested) return orig_prog; @@ -73,7 +73,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (ctx->offset) { extra_pass = true; - image_size = sizeof(*ctx->insns) * ctx->ninsns; + prog_size = sizeof(*ctx->insns) * ctx->ninsns; goto skip_init_ctx; } @@ -102,10 +102,13 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (ctx->ninsns == prev_ninsns) { if (jit_data->header) break; + /* obtain the actual image size */ + extable_size = prog->aux->num_exentries * + sizeof(struct exception_table_entry); + prog_size = sizeof(*ctx->insns) * ctx->ninsns; - image_size = sizeof(*ctx->insns) * ctx->ninsns; jit_data->header = - bpf_jit_binary_alloc(image_size, + bpf_jit_binary_alloc(prog_size + extable_size, &jit_data->image, sizeof(u32), bpf_fill_ill_insns); @@ -125,14 +128,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) if (i == NR_JIT_ITERATIONS) { pr_err("bpf-jit: image did not converge in <%d passes!\n", i); - bpf_jit_binary_free(jit_data->header); + if (jit_data->header) + bpf_jit_binary_free(jit_data->header); prog = orig_prog; goto out_offset; } + if (extable_size) + prog->aux->extable = (void *)ctx->insns + prog_size; + skip_init_ctx: pass++; ctx->ninsns = 0; + ctx->nexentries = 0; bpf_jit_build_prologue(ctx); if (build_body(ctx, extra_pass, NULL)) { @@ -143,11 +151,11 @@ skip_init_ctx: bpf_jit_build_epilogue(ctx); if (bpf_jit_enable > 1) - bpf_jit_dump(prog->len, image_size, pass, ctx->insns); + bpf_jit_dump(prog->len, prog_size, pass, ctx->insns); prog->bpf_func = (void *)ctx->insns; prog->jited = 1; - prog->jited_len = image_size; + prog->jited_len = prog_size; bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); @@ -166,6 +174,11 @@ out: return prog; } +u64 bpf_jit_alloc_exec_limit(void) +{ + return BPF_JIT_REGION_SIZE; +} + void *bpf_jit_alloc_exec(unsigned long size) { return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, |