diff options
Diffstat (limited to 'arch/riscv/kernel')
31 files changed, 1320 insertions, 52 deletions
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 87adbe47bc15..c71d6591d539 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -14,10 +14,25 @@ ifdef CONFIG_KEXEC AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax) endif +# cmodel=medany and notrace when patching early +ifdef CONFIG_RISCV_ALTERNATIVE_EARLY +CFLAGS_alternative.o := -mcmodel=medany +CFLAGS_cpufeature.o := -mcmodel=medany +ifdef CONFIG_FTRACE +CFLAGS_REMOVE_alternative.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_cpufeature.o = $(CC_FLAGS_FTRACE) +endif +ifdef CONFIG_KASAN +KASAN_SANITIZE_alternative.o := n +KASAN_SANITIZE_cpufeature.o := n +endif +endif + extra-y += head.o extra-y += vmlinux.lds obj-y += soc.o +obj-$(CONFIG_RISCV_ALTERNATIVE) += alternative.o obj-y += cpu.o obj-y += cpufeature.o obj-y += entry.o @@ -64,8 +79,12 @@ endif obj-$(CONFIG_HOTPLUG_CPU) += cpu-hotplug.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_KEXEC) += kexec_relocate.o crash_save_regs.o machine_kexec.o +obj-$(CONFIG_KEXEC_FILE) += elf_kexec.o machine_kexec_file.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_EFI) += efi.o +obj-$(CONFIG_COMPAT) += compat_syscall_table.o +obj-$(CONFIG_COMPAT) += compat_signal.o +obj-$(CONFIG_COMPAT) += compat_vdso/ diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c new file mode 100644 index 000000000000..c9d0d3c53223 --- /dev/null +++ b/arch/riscv/kernel/alternative.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * alternative runtime patching + * inspired by the ARM64 and x86 version + * + * Copyright (C) 2021 Sifive. + */ + +#include <linux/init.h> +#include <linux/module.h> +#include <linux/cpu.h> +#include <linux/uaccess.h> +#include <asm/alternative.h> +#include <asm/sections.h> +#include <asm/vendorid_list.h> +#include <asm/sbi.h> +#include <asm/csr.h> + +struct cpu_manufacturer_info_t { + unsigned long vendor_id; + unsigned long arch_id; + unsigned long imp_id; + void (*vendor_patch_func)(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage); +}; + +static void __init_or_module riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info) +{ +#ifdef CONFIG_RISCV_M_MODE + cpu_mfr_info->vendor_id = csr_read(CSR_MVENDORID); + cpu_mfr_info->arch_id = csr_read(CSR_MARCHID); + cpu_mfr_info->imp_id = csr_read(CSR_MIMPID); +#else + cpu_mfr_info->vendor_id = sbi_get_mvendorid(); + cpu_mfr_info->arch_id = sbi_get_marchid(); + cpu_mfr_info->imp_id = sbi_get_mimpid(); +#endif + + switch (cpu_mfr_info->vendor_id) { +#ifdef CONFIG_ERRATA_SIFIVE + case SIFIVE_VENDOR_ID: + cpu_mfr_info->vendor_patch_func = sifive_errata_patch_func; + break; +#endif +#ifdef CONFIG_ERRATA_THEAD + case THEAD_VENDOR_ID: + cpu_mfr_info->vendor_patch_func = thead_errata_patch_func; + break; +#endif + default: + cpu_mfr_info->vendor_patch_func = NULL; + } +} + +/* + * This is called very early in the boot process (directly after we run + * a feature detect on the boot CPU). No need to worry about other CPUs + * here. + */ +static void __init_or_module _apply_alternatives(struct alt_entry *begin, + struct alt_entry *end, + unsigned int stage) +{ + struct cpu_manufacturer_info_t cpu_mfr_info; + + riscv_fill_cpu_mfr_info(&cpu_mfr_info); + + riscv_cpufeature_patch_func(begin, end, stage); + + if (!cpu_mfr_info.vendor_patch_func) + return; + + cpu_mfr_info.vendor_patch_func(begin, end, + cpu_mfr_info.arch_id, + cpu_mfr_info.imp_id, + stage); +} + +void __init apply_boot_alternatives(void) +{ + /* If called on non-boot cpu things could go wrong */ + WARN_ON(smp_processor_id() != 0); + + _apply_alternatives((struct alt_entry *)__alt_start, + (struct alt_entry *)__alt_end, + RISCV_ALTERNATIVES_BOOT); +} + +/* + * apply_early_boot_alternatives() is called from setup_vm() with MMU-off. + * + * Following requirements should be honoured for it to work correctly: + * 1) It should use PC-relative addressing for accessing kernel symbols. + * To achieve this we always use GCC cmodel=medany. + * 2) The compiler instrumentation for FTRACE will not work for setup_vm() + * so disable compiler instrumentation when FTRACE is enabled. + * + * Currently, the above requirements are honoured by using custom CFLAGS + * for alternative.o in kernel/Makefile. + */ +void __init apply_early_boot_alternatives(void) +{ +#ifdef CONFIG_RISCV_ALTERNATIVE_EARLY + _apply_alternatives((struct alt_entry *)__alt_start, + (struct alt_entry *)__alt_end, + RISCV_ALTERNATIVES_EARLY_BOOT); +#endif +} + +#ifdef CONFIG_MODULES +void apply_module_alternatives(void *start, size_t length) +{ + _apply_alternatives((struct alt_entry *)start, + (struct alt_entry *)(start + length), + RISCV_ALTERNATIVES_MODULE); +} +#endif diff --git a/arch/riscv/kernel/compat_signal.c b/arch/riscv/kernel/compat_signal.c new file mode 100644 index 000000000000..6ec4e34255a9 --- /dev/null +++ b/arch/riscv/kernel/compat_signal.c @@ -0,0 +1,243 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/compat.h> +#include <linux/signal.h> +#include <linux/uaccess.h> +#include <linux/syscalls.h> +#include <linux/linkage.h> + +#include <asm/csr.h> +#include <asm/signal32.h> +#include <asm/switch_to.h> +#include <asm/ucontext.h> +#include <asm/vdso.h> + +#define COMPAT_DEBUG_SIG 0 + +struct compat_sigcontext { + struct compat_user_regs_struct sc_regs; + union __riscv_fp_state sc_fpregs; +}; + +struct compat_ucontext { + compat_ulong_t uc_flags; + struct compat_ucontext *uc_link; + compat_stack_t uc_stack; + sigset_t uc_sigmask; + /* There's some padding here to allow sigset_t to be expanded in the + * future. Though this is unlikely, other architectures put uc_sigmask + * at the end of this structure and explicitly state it can be + * expanded, so we didn't want to box ourselves in here. */ + __u8 __unused[1024 / 8 - sizeof(sigset_t)]; + /* We can't put uc_sigmask at the end of this structure because we need + * to be able to expand sigcontext in the future. For example, the + * vector ISA extension will almost certainly add ISA state. We want + * to ensure all user-visible ISA state can be saved and restored via a + * ucontext, so we're putting this at the end in order to allow for + * infinite extensibility. Since we know this will be extended and we + * assume sigset_t won't be extended an extreme amount, we're + * prioritizing this. */ + struct compat_sigcontext uc_mcontext; +}; + +struct compat_rt_sigframe { + struct compat_siginfo info; + struct compat_ucontext uc; +}; + +#ifdef CONFIG_FPU +static long compat_restore_fp_state(struct pt_regs *regs, + union __riscv_fp_state __user *sc_fpregs) +{ + long err; + struct __riscv_d_ext_state __user *state = &sc_fpregs->d; + size_t i; + + err = __copy_from_user(¤t->thread.fstate, state, sizeof(*state)); + if (unlikely(err)) + return err; + + fstate_restore(current, regs); + + /* We support no other extension state at this time. */ + for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) { + u32 value; + + err = __get_user(value, &sc_fpregs->q.reserved[i]); + if (unlikely(err)) + break; + if (value != 0) + return -EINVAL; + } + + return err; +} + +static long compat_save_fp_state(struct pt_regs *regs, + union __riscv_fp_state __user *sc_fpregs) +{ + long err; + struct __riscv_d_ext_state __user *state = &sc_fpregs->d; + size_t i; + + fstate_save(current, regs); + err = __copy_to_user(state, ¤t->thread.fstate, sizeof(*state)); + if (unlikely(err)) + return err; + + /* We support no other extension state at this time. */ + for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) { + err = __put_user(0, &sc_fpregs->q.reserved[i]); + if (unlikely(err)) + break; + } + + return err; +} +#else +#define compat_save_fp_state(task, regs) (0) +#define compat_restore_fp_state(task, regs) (0) +#endif + +static long compat_restore_sigcontext(struct pt_regs *regs, + struct compat_sigcontext __user *sc) +{ + long err; + struct compat_user_regs_struct cregs; + + /* sc_regs is structured the same as the start of pt_regs */ + err = __copy_from_user(&cregs, &sc->sc_regs, sizeof(sc->sc_regs)); + + cregs_to_regs(&cregs, regs); + + /* Restore the floating-point state. */ + if (has_fpu()) + err |= compat_restore_fp_state(regs, &sc->sc_fpregs); + return err; +} + +COMPAT_SYSCALL_DEFINE0(rt_sigreturn) +{ + struct pt_regs *regs = current_pt_regs(); + struct compat_rt_sigframe __user *frame; + struct task_struct *task; + sigset_t set; + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; + + frame = (struct compat_rt_sigframe __user *)regs->sp; + + if (!access_ok(frame, sizeof(*frame))) + goto badframe; + + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + goto badframe; + + set_current_blocked(&set); + + if (compat_restore_sigcontext(regs, &frame->uc.uc_mcontext)) + goto badframe; + + if (compat_restore_altstack(&frame->uc.uc_stack)) + goto badframe; + + return regs->a0; + +badframe: + task = current; + if (show_unhandled_signals) { + pr_info_ratelimited( + "%s[%d]: bad frame in %s: frame=%p pc=%p sp=%p\n", + task->comm, task_pid_nr(task), __func__, + frame, (void *)regs->epc, (void *)regs->sp); + } + force_sig(SIGSEGV); + return 0; +} + +static long compat_setup_sigcontext(struct compat_rt_sigframe __user *frame, + struct pt_regs *regs) +{ + struct compat_sigcontext __user *sc = &frame->uc.uc_mcontext; + struct compat_user_regs_struct cregs; + long err; + + regs_to_cregs(&cregs, regs); + + /* sc_regs is structured the same as the start of pt_regs */ + err = __copy_to_user(&sc->sc_regs, &cregs, sizeof(sc->sc_regs)); + /* Save the floating-point state. */ + if (has_fpu()) + err |= compat_save_fp_state(regs, &sc->sc_fpregs); + return err; +} + +static inline void __user *compat_get_sigframe(struct ksignal *ksig, + struct pt_regs *regs, size_t framesize) +{ + unsigned long sp; + /* Default to using normal stack */ + sp = regs->sp; + + /* + * 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 (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize))) + return (void __user __force *)(-1UL); + + /* This is the X/Open sanctioned signal stack switching. */ + sp = sigsp(sp, ksig) - framesize; + + /* Align the stack frame. */ + sp &= ~0xfUL; + + return (void __user *)sp; +} + +int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set, + struct pt_regs *regs) +{ + struct compat_rt_sigframe __user *frame; + long err = 0; + + frame = compat_get_sigframe(ksig, regs, sizeof(*frame)); + if (!access_ok(frame, sizeof(*frame))) + return -EFAULT; + + err |= copy_siginfo_to_user32(&frame->info, &ksig->info); + + /* Create the ucontext. */ + err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(NULL, &frame->uc.uc_link); + err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); + err |= compat_setup_sigcontext(frame, regs); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) + return -EFAULT; + + regs->ra = (unsigned long)COMPAT_VDSO_SYMBOL( + current->mm->context.vdso, rt_sigreturn); + + /* + * Set up registers for signal handler. + * Registers that we don't modify keep the value they had from + * user-space at the time we took the signal. + * We always pass siginfo and mcontext, regardless of SA_SIGINFO, + * since some things rely on this (e.g. glibc's debug/segfault.c). + */ + regs->epc = (unsigned long)ksig->ka.sa.sa_handler; + regs->sp = (unsigned long)frame; + regs->a0 = ksig->sig; /* a0: signal number */ + regs->a1 = (unsigned long)(&frame->info); /* a1: siginfo pointer */ + regs->a2 = (unsigned long)(&frame->uc); /* a2: ucontext pointer */ + +#if COMPAT_DEBUG_SIG + pr_info("SIG deliver (%s:%d): sig=%d pc=%p ra=%p sp=%p\n", + current->comm, task_pid_nr(current), ksig->sig, + (void *)regs->epc, (void *)regs->ra, frame); +#endif + + return 0; +} diff --git a/arch/riscv/kernel/compat_syscall_table.c b/arch/riscv/kernel/compat_syscall_table.c new file mode 100644 index 000000000000..651f2b009c28 --- /dev/null +++ b/arch/riscv/kernel/compat_syscall_table.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define __SYSCALL_COMPAT + +#include <linux/compat.h> +#include <linux/syscalls.h> +#include <asm-generic/mman-common.h> +#include <asm-generic/syscalls.h> +#include <asm/syscall.h> + +#undef __SYSCALL +#define __SYSCALL(nr, call) [nr] = (call), + +asmlinkage long compat_sys_rt_sigreturn(void); + +void * const compat_sys_call_table[__NR_syscalls] = { + [0 ... __NR_syscalls - 1] = sys_ni_syscall, +#include <asm/unistd.h> +}; diff --git a/arch/riscv/kernel/compat_vdso/.gitignore b/arch/riscv/kernel/compat_vdso/.gitignore new file mode 100644 index 000000000000..19d83d846c1e --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +compat_vdso.lds diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile new file mode 100644 index 000000000000..260daf3236d3 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -0,0 +1,78 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for compat_vdso +# + +# Symbols present in the compat_vdso +compat_vdso-syms = rt_sigreturn +compat_vdso-syms += getcpu +compat_vdso-syms += flush_icache + +COMPAT_CC := $(CC) +COMPAT_LD := $(LD) + +COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +COMPAT_LD_FLAGS := -melf32lriscv + +# Files to link into the compat_vdso +obj-compat_vdso = $(patsubst %, %.o, $(compat_vdso-syms)) note.o + +# Build rules +targets := $(obj-compat_vdso) compat_vdso.so compat_vdso.so.dbg compat_vdso.lds +obj-compat_vdso := $(addprefix $(obj)/, $(obj-compat_vdso)) + +obj-y += compat_vdso.o +CPPFLAGS_compat_vdso.lds += -P -C -U$(ARCH) + +# Disable profiling and instrumentation for VDSO code +GCOV_PROFILE := n +KCOV_INSTRUMENT := n +KASAN_SANITIZE := n +UBSAN_SANITIZE := n + +# Force dependency +$(obj)/compat_vdso.o: $(obj)/compat_vdso.so + +# link rule for the .so file, .lds has to be first +$(obj)/compat_vdso.so.dbg: $(obj)/compat_vdso.lds $(obj-compat_vdso) FORCE + $(call if_changed,compat_vdsold) +LDFLAGS_compat_vdso.so.dbg = -shared -S -soname=linux-compat_vdso.so.1 \ + --build-id=sha1 --hash-style=both --eh-frame-hdr + +$(obj-compat_vdso): %.o: %.S FORCE + $(call if_changed_dep,compat_vdsoas) + +# strip rule for the .so file +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg FORCE + $(call if_changed,objcopy) + +# Generate VDSO offsets using helper script +gen-compat_vdsosym := $(srctree)/$(src)/gen_compat_vdso_offsets.sh +quiet_cmd_compat_vdsosym = VDSOSYM $@ + cmd_compat_vdsosym = $(NM) $< | $(gen-compat_vdsosym) | LC_ALL=C sort > $@ + +include/generated/compat_vdso-offsets.h: $(obj)/compat_vdso.so.dbg FORCE + $(call if_changed,compat_vdsosym) + +# actual build commands +# The DSO images are built using a special linker script +# Make sure only to export the intended __compat_vdso_xxx symbol offsets. +quiet_cmd_compat_vdsold = VDSOLD $@ + cmd_compat_vdsold = $(COMPAT_LD) $(ld_flags) $(COMPAT_LD_FLAGS) -T $(filter-out FORCE,$^) -o $@.tmp && \ + $(OBJCOPY) $(patsubst %, -G __compat_vdso_%, $(compat_vdso-syms)) $@.tmp $@ && \ + rm $@.tmp + +# actual build commands +quiet_cmd_compat_vdsoas = VDSOAS $@ + cmd_compat_vdsoas = $(COMPAT_CC) $(a_flags) $(COMPAT_CC_FLAGS) -c -o $@ $< + +# install commands for the unstripped file +quiet_cmd_compat_vdso_install = INSTALL $@ + cmd_compat_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/compat_vdso/$@ + +compat_vdso.so: $(obj)/compat_vdso.so.dbg + @mkdir -p $(MODLIB)/compat_vdso + $(call cmd,compat_vdso_install) + +compat_vdso_install: compat_vdso.so diff --git a/arch/riscv/kernel/compat_vdso/compat_vdso.S b/arch/riscv/kernel/compat_vdso/compat_vdso.S new file mode 100644 index 000000000000..ffd66237e091 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/compat_vdso.S @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#define vdso_start compat_vdso_start +#define vdso_end compat_vdso_end + +#define __VDSO_PATH "arch/riscv/kernel/compat_vdso/compat_vdso.so" + +#include "../vdso/vdso.S" diff --git a/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S b/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S new file mode 100644 index 000000000000..c7c9355d311e --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/vdso.lds.S" diff --git a/arch/riscv/kernel/compat_vdso/flush_icache.S b/arch/riscv/kernel/compat_vdso/flush_icache.S new file mode 100644 index 000000000000..523dd8b96045 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/flush_icache.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/flush_icache.S" diff --git a/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh b/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh new file mode 100755 index 000000000000..8ac070c783b3 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh @@ -0,0 +1,5 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +LC_ALL=C +sed -n -e 's/^[0]\+\(0[0-9a-fA-F]*\) . \(__vdso_[a-zA-Z0-9_]*\)$/\#define compat\2_offset\t0x\1/p' diff --git a/arch/riscv/kernel/compat_vdso/getcpu.S b/arch/riscv/kernel/compat_vdso/getcpu.S new file mode 100644 index 000000000000..10f463efe271 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/getcpu.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/getcpu.S" diff --git a/arch/riscv/kernel/compat_vdso/note.S b/arch/riscv/kernel/compat_vdso/note.S new file mode 100644 index 000000000000..b10312907542 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/note.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/note.S" diff --git a/arch/riscv/kernel/compat_vdso/rt_sigreturn.S b/arch/riscv/kernel/compat_vdso/rt_sigreturn.S new file mode 100644 index 000000000000..884aada4facc --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/rt_sigreturn.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/rt_sigreturn.S" diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index ccb617791e56..fba9e9f46a8c 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -88,6 +88,7 @@ int riscv_of_parent_hartid(struct device_node *node) */ static struct riscv_isa_ext_data isa_ext_arr[] = { __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), + __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT), __RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX), }; @@ -138,6 +139,7 @@ static void print_mmu(struct seq_file *f) { char sv_type[16]; +#ifdef CONFIG_MMU #if defined(CONFIG_32BIT) strncpy(sv_type, "sv32", 5); #elif defined(CONFIG_64BIT) @@ -148,6 +150,9 @@ static void print_mmu(struct seq_file *f) else strncpy(sv_type, "sv39", 5); #endif +#else + strncpy(sv_type, "none", 5); +#endif /* CONFIG_MMU */ seq_printf(f, "mmu\t\t: %s\n", sv_type); } diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 1b2d42d7f589..dea3ea19deee 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -8,9 +8,15 @@ #include <linux/bitmap.h> #include <linux/ctype.h> +#include <linux/libfdt.h> +#include <linux/module.h> #include <linux/of.h> -#include <asm/processor.h> +#include <asm/alternative.h> +#include <asm/errata_list.h> #include <asm/hwcap.h> +#include <asm/patch.h> +#include <asm/pgtable.h> +#include <asm/processor.h> #include <asm/smp.h> #include <asm/switch_to.h> @@ -192,6 +198,7 @@ void __init riscv_fill_hwcap(void) set_bit(*ext - 'a', this_isa); } else { SET_ISA_EXT_MAP("sscofpmf", RISCV_ISA_EXT_SSCOFPMF); + SET_ISA_EXT_MAP("svpbmt", RISCV_ISA_EXT_SVPBMT); } #undef SET_ISA_EXT_MAP } @@ -237,3 +244,74 @@ void __init riscv_fill_hwcap(void) static_branch_enable(&cpu_hwcap_fpu); #endif } + +#ifdef CONFIG_RISCV_ALTERNATIVE +struct cpufeature_info { + char name[ERRATA_STRING_LENGTH_MAX]; + bool (*check_func)(unsigned int stage); +}; + +static bool __init_or_module cpufeature_svpbmt_check_func(unsigned int stage) +{ +#ifdef CONFIG_RISCV_ISA_SVPBMT + switch (stage) { + case RISCV_ALTERNATIVES_EARLY_BOOT: + return false; + default: + return riscv_isa_extension_available(NULL, SVPBMT); + } +#endif + + return false; +} + +static const struct cpufeature_info __initdata_or_module +cpufeature_list[CPUFEATURE_NUMBER] = { + { + .name = "svpbmt", + .check_func = cpufeature_svpbmt_check_func + }, +}; + +static u32 __init_or_module cpufeature_probe(unsigned int stage) +{ + const struct cpufeature_info *info; + u32 cpu_req_feature = 0; + int idx; + + for (idx = 0; idx < CPUFEATURE_NUMBER; idx++) { + info = &cpufeature_list[idx]; + + if (info->check_func(stage)) + cpu_req_feature |= (1U << idx); + } + + return cpu_req_feature; +} + +void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin, + struct alt_entry *end, + unsigned int stage) +{ + u32 cpu_req_feature = cpufeature_probe(stage); + u32 cpu_apply_feature = 0; + struct alt_entry *alt; + u32 tmp; + + for (alt = begin; alt < end; alt++) { + if (alt->vendor_id != 0) + continue; + if (alt->errata_id >= CPUFEATURE_NUMBER) { + WARN(1, "This feature id:%d is not in kernel cpufeature list", + alt->errata_id); + continue; + } + + tmp = (1U << alt->errata_id); + if (cpu_req_feature & tmp) { + patch_text_nosync(alt->old_ptr, alt->alt_ptr, alt->alt_len); + cpu_apply_feature |= tmp; + } + } +} +#endif diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c new file mode 100644 index 000000000000..9cb85095fd45 --- /dev/null +++ b/arch/riscv/kernel/elf_kexec.c @@ -0,0 +1,448 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Load ELF vmlinux file for the kexec_file_load syscall. + * + * Copyright (C) 2021 Huawei Technologies Co, Ltd. + * + * Author: Liao Chang (liaochang1@huawei.com) + * + * Based on kexec-tools' kexec-elf-riscv.c, heavily modified + * for kernel. + */ + +#define pr_fmt(fmt) "kexec_image: " fmt + +#include <linux/elf.h> +#include <linux/kexec.h> +#include <linux/slab.h> +#include <linux/of.h> +#include <linux/libfdt.h> +#include <linux/types.h> +#include <linux/memblock.h> +#include <asm/setup.h> + +static int riscv_kexec_elf_load(struct kimage *image, struct elfhdr *ehdr, + struct kexec_elf_info *elf_info, unsigned long old_pbase, + unsigned long new_pbase) +{ + int i; + int ret = 0; + size_t size; + struct kexec_buf kbuf; + const struct elf_phdr *phdr; + + kbuf.image = image; + + for (i = 0; i < ehdr->e_phnum; i++) { + phdr = &elf_info->proghdrs[i]; + if (phdr->p_type != PT_LOAD) + continue; + + size = phdr->p_filesz; + if (size > phdr->p_memsz) + size = phdr->p_memsz; + + kbuf.buffer = (void *) elf_info->buffer + phdr->p_offset; + kbuf.bufsz = size; + kbuf.buf_align = phdr->p_align; + kbuf.mem = phdr->p_paddr - old_pbase + new_pbase; + kbuf.memsz = phdr->p_memsz; + kbuf.top_down = false; + ret = kexec_add_buffer(&kbuf); + if (ret) + break; + } + + return ret; +} + +/* + * Go through the available phsyical memory regions and find one that hold + * an image of the specified size. + */ +static int elf_find_pbase(struct kimage *image, unsigned long kernel_len, + struct elfhdr *ehdr, struct kexec_elf_info *elf_info, + unsigned long *old_pbase, unsigned long *new_pbase) +{ + int i; + int ret; + struct kexec_buf kbuf; + const struct elf_phdr *phdr; + unsigned long lowest_paddr = ULONG_MAX; + unsigned long lowest_vaddr = ULONG_MAX; + + for (i = 0; i < ehdr->e_phnum; i++) { + phdr = &elf_info->proghdrs[i]; + if (phdr->p_type != PT_LOAD) + continue; + + if (lowest_paddr > phdr->p_paddr) + lowest_paddr = phdr->p_paddr; + + if (lowest_vaddr > phdr->p_vaddr) + lowest_vaddr = phdr->p_vaddr; + } + + kbuf.image = image; + kbuf.buf_min = lowest_paddr; + kbuf.buf_max = ULONG_MAX; + kbuf.buf_align = PAGE_SIZE; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = ALIGN(kernel_len, PAGE_SIZE); + kbuf.top_down = false; + ret = arch_kexec_locate_mem_hole(&kbuf); + if (!ret) { + *old_pbase = lowest_paddr; + *new_pbase = kbuf.mem; + image->start = ehdr->e_entry - lowest_vaddr + kbuf.mem; + } + return ret; +} + +static int get_nr_ram_ranges_callback(struct resource *res, void *arg) +{ + unsigned int *nr_ranges = arg; + + (*nr_ranges)++; + return 0; +} + +static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) +{ + struct crash_mem *cmem = arg; + + cmem->ranges[cmem->nr_ranges].start = res->start; + cmem->ranges[cmem->nr_ranges].end = res->end; + cmem->nr_ranges++; + + return 0; +} + +static int prepare_elf_headers(void **addr, unsigned long *sz) +{ + struct crash_mem *cmem; + unsigned int nr_ranges; + int ret; + + nr_ranges = 1; /* For exclusion of crashkernel region */ + walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); + + cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL); + if (!cmem) + return -ENOMEM; + + cmem->max_nr_ranges = nr_ranges; + cmem->nr_ranges = 0; + ret = walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); + if (ret) + goto out; + + /* Exclude crashkernel region */ + ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + if (!ret) + ret = crash_prepare_elf64_headers(cmem, true, addr, sz); + +out: + kfree(cmem); + return ret; +} + +static char *setup_kdump_cmdline(struct kimage *image, char *cmdline, + unsigned long cmdline_len) +{ + int elfcorehdr_strlen; + char *cmdline_ptr; + + cmdline_ptr = kzalloc(COMMAND_LINE_SIZE, GFP_KERNEL); + if (!cmdline_ptr) + return NULL; + + elfcorehdr_strlen = sprintf(cmdline_ptr, "elfcorehdr=0x%lx ", + image->elf_load_addr); + + if (elfcorehdr_strlen + cmdline_len > COMMAND_LINE_SIZE) { + pr_err("Appending elfcorehdr=<addr> exceeds cmdline size\n"); + kfree(cmdline_ptr); + return NULL; + } + + memcpy(cmdline_ptr + elfcorehdr_strlen, cmdline, cmdline_len); + /* Ensure it's nul terminated */ + cmdline_ptr[COMMAND_LINE_SIZE - 1] = '\0'; + return cmdline_ptr; +} + +static void *elf_kexec_load(struct kimage *image, char *kernel_buf, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len) +{ + int ret; + unsigned long old_kernel_pbase = ULONG_MAX; + unsigned long new_kernel_pbase = 0UL; + unsigned long initrd_pbase = 0UL; + unsigned long headers_sz; + unsigned long kernel_start; + void *fdt, *headers; + struct elfhdr ehdr; + struct kexec_buf kbuf; + struct kexec_elf_info elf_info; + char *modified_cmdline = NULL; + + ret = kexec_build_elf_info(kernel_buf, kernel_len, &ehdr, &elf_info); + if (ret) + return ERR_PTR(ret); + + ret = elf_find_pbase(image, kernel_len, &ehdr, &elf_info, + &old_kernel_pbase, &new_kernel_pbase); + if (ret) + goto out; + kernel_start = image->start; + pr_notice("The entry point of kernel at 0x%lx\n", image->start); + + /* Add the kernel binary to the image */ + ret = riscv_kexec_elf_load(image, &ehdr, &elf_info, + old_kernel_pbase, new_kernel_pbase); + if (ret) + goto out; + + kbuf.image = image; + kbuf.buf_min = new_kernel_pbase + kernel_len; + kbuf.buf_max = ULONG_MAX; + + /* Add elfcorehdr */ + if (image->type == KEXEC_TYPE_CRASH) { + ret = prepare_elf_headers(&headers, &headers_sz); + if (ret) { + pr_err("Preparing elf core header failed\n"); + goto out; + } + + kbuf.buffer = headers; + kbuf.bufsz = headers_sz; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = headers_sz; + kbuf.buf_align = ELF_CORE_HEADER_ALIGN; + kbuf.top_down = true; + + ret = kexec_add_buffer(&kbuf); + if (ret) { + vfree(headers); + goto out; + } + image->elf_headers = headers; + image->elf_load_addr = kbuf.mem; + image->elf_headers_sz = headers_sz; + + pr_debug("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + image->elf_load_addr, kbuf.bufsz, kbuf.memsz); + + /* Setup cmdline for kdump kernel case */ + modified_cmdline = setup_kdump_cmdline(image, cmdline, + cmdline_len); + if (!modified_cmdline) { + pr_err("Setting up cmdline for kdump kernel failed\n"); + ret = -EINVAL; + goto out; + } + cmdline = modified_cmdline; + } + +#ifdef CONFIG_ARCH_HAS_KEXEC_PURGATORY + /* Add purgatory to the image */ + kbuf.top_down = true; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + ret = kexec_load_purgatory(image, &kbuf); + if (ret) { + pr_err("Error loading purgatory ret=%d\n", ret); + goto out; + } + ret = kexec_purgatory_get_set_symbol(image, "riscv_kernel_entry", + &kernel_start, + sizeof(kernel_start), 0); + if (ret) + pr_err("Error update purgatory ret=%d\n", ret); +#endif /* CONFIG_ARCH_HAS_KEXEC_PURGATORY */ + + /* Add the initrd to the image */ + if (initrd != NULL) { + kbuf.buffer = initrd; + kbuf.bufsz = kbuf.memsz = initrd_len; + kbuf.buf_align = PAGE_SIZE; + kbuf.top_down = false; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out; + initrd_pbase = kbuf.mem; + pr_notice("Loaded initrd at 0x%lx\n", initrd_pbase); + } + + /* Add the DTB to the image */ + fdt = of_kexec_alloc_and_setup_fdt(image, initrd_pbase, + initrd_len, cmdline, 0); + if (!fdt) { + pr_err("Error setting up the new device tree.\n"); + ret = -EINVAL; + goto out; + } + + fdt_pack(fdt); + kbuf.buffer = fdt; + kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt); + kbuf.buf_align = PAGE_SIZE; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.top_down = true; + ret = kexec_add_buffer(&kbuf); + if (ret) { + pr_err("Error add DTB kbuf ret=%d\n", ret); + goto out_free_fdt; + } + pr_notice("Loaded device tree at 0x%lx\n", kbuf.mem); + goto out; + +out_free_fdt: + kvfree(fdt); +out: + kfree(modified_cmdline); + kexec_free_elf_info(&elf_info); + return ret ? ERR_PTR(ret) : NULL; +} + +#define RV_X(x, s, n) (((x) >> (s)) & ((1 << (n)) - 1)) +#define RISCV_IMM_BITS 12 +#define RISCV_IMM_REACH (1LL << RISCV_IMM_BITS) +#define RISCV_CONST_HIGH_PART(x) \ + (((x) + (RISCV_IMM_REACH >> 1)) & ~(RISCV_IMM_REACH - 1)) +#define RISCV_CONST_LOW_PART(x) ((x) - RISCV_CONST_HIGH_PART(x)) + +#define ENCODE_ITYPE_IMM(x) \ + (RV_X(x, 0, 12) << 20) +#define ENCODE_BTYPE_IMM(x) \ + ((RV_X(x, 1, 4) << 8) | (RV_X(x, 5, 6) << 25) | \ + (RV_X(x, 11, 1) << 7) | (RV_X(x, 12, 1) << 31)) +#define ENCODE_UTYPE_IMM(x) \ + (RV_X(x, 12, 20) << 12) +#define ENCODE_JTYPE_IMM(x) \ + ((RV_X(x, 1, 10) << 21) | (RV_X(x, 11, 1) << 20) | \ + (RV_X(x, 12, 8) << 12) | (RV_X(x, 20, 1) << 31)) +#define ENCODE_CBTYPE_IMM(x) \ + ((RV_X(x, 1, 2) << 3) | (RV_X(x, 3, 2) << 10) | (RV_X(x, 5, 1) << 2) | \ + (RV_X(x, 6, 2) << 5) | (RV_X(x, 8, 1) << 12)) +#define ENCODE_CJTYPE_IMM(x) \ + ((RV_X(x, 1, 3) << 3) | (RV_X(x, 4, 1) << 11) | (RV_X(x, 5, 1) << 2) | \ + (RV_X(x, 6, 1) << 7) | (RV_X(x, 7, 1) << 6) | (RV_X(x, 8, 2) << 9) | \ + (RV_X(x, 10, 1) << 8) | (RV_X(x, 11, 1) << 12)) +#define ENCODE_UJTYPE_IMM(x) \ + (ENCODE_UTYPE_IMM(RISCV_CONST_HIGH_PART(x)) | \ + (ENCODE_ITYPE_IMM(RISCV_CONST_LOW_PART(x)) << 32)) +#define ENCODE_UITYPE_IMM(x) \ + (ENCODE_UTYPE_IMM(x) | (ENCODE_ITYPE_IMM(x) << 32)) + +#define CLEAN_IMM(type, x) \ + ((~ENCODE_##type##_IMM((uint64_t)(-1))) & (x)) + +int arch_kexec_apply_relocations_add(struct purgatory_info *pi, + Elf_Shdr *section, + const Elf_Shdr *relsec, + const Elf_Shdr *symtab) +{ + const char *strtab, *name, *shstrtab; + const Elf_Shdr *sechdrs; + Elf_Rela *relas; + int i, r_type; + + /* String & section header string table */ + sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff; + strtab = (char *)pi->ehdr + sechdrs[symtab->sh_link].sh_offset; + shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset; + + relas = (void *)pi->ehdr + relsec->sh_offset; + + for (i = 0; i < relsec->sh_size / sizeof(*relas); i++) { + const Elf_Sym *sym; /* symbol to relocate */ + unsigned long addr; /* final location after relocation */ + unsigned long val; /* relocated symbol value */ + unsigned long sec_base; /* relocated symbol value */ + void *loc; /* tmp location to modify */ + + sym = (void *)pi->ehdr + symtab->sh_offset; + sym += ELF64_R_SYM(relas[i].r_info); + + if (sym->st_name) + name = strtab + sym->st_name; + else + name = shstrtab + sechdrs[sym->st_shndx].sh_name; + + loc = pi->purgatory_buf; + loc += section->sh_offset; + loc += relas[i].r_offset; + + if (sym->st_shndx == SHN_ABS) + sec_base = 0; + else if (sym->st_shndx >= pi->ehdr->e_shnum) { + pr_err("Invalid section %d for symbol %s\n", + sym->st_shndx, name); + return -ENOEXEC; + } else + sec_base = pi->sechdrs[sym->st_shndx].sh_addr; + + val = sym->st_value; + val += sec_base; + val += relas[i].r_addend; + + addr = section->sh_addr + relas[i].r_offset; + + r_type = ELF64_R_TYPE(relas[i].r_info); + + switch (r_type) { + case R_RISCV_BRANCH: + *(u32 *)loc = CLEAN_IMM(BTYPE, *(u32 *)loc) | + ENCODE_BTYPE_IMM(val - addr); + break; + case R_RISCV_JAL: + *(u32 *)loc = CLEAN_IMM(JTYPE, *(u32 *)loc) | + ENCODE_JTYPE_IMM(val - addr); + break; + /* + * With no R_RISCV_PCREL_LO12_S, R_RISCV_PCREL_LO12_I + * sym is expected to be next to R_RISCV_PCREL_HI20 + * in purgatory relsec. Handle it like R_RISCV_CALL + * sym, instead of searching the whole relsec. + */ + case R_RISCV_PCREL_HI20: + case R_RISCV_CALL: + *(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) | + ENCODE_UJTYPE_IMM(val - addr); + break; + case R_RISCV_RVC_BRANCH: + *(u32 *)loc = CLEAN_IMM(CBTYPE, *(u32 *)loc) | + ENCODE_CBTYPE_IMM(val - addr); + break; + case R_RISCV_RVC_JUMP: + *(u32 *)loc = CLEAN_IMM(CJTYPE, *(u32 *)loc) | + ENCODE_CJTYPE_IMM(val - addr); + break; + case R_RISCV_ADD32: + *(u32 *)loc += val; + break; + case R_RISCV_SUB32: + *(u32 *)loc -= val; + break; + /* It has been applied by R_RISCV_PCREL_HI20 sym */ + case R_RISCV_PCREL_LO12_I: + case R_RISCV_ALIGN: + case R_RISCV_RELAX: + break; + default: + pr_err("Unknown rela relocation: %d\n", r_type); + return -ENOEXEC; + } + } + return 0; +} + +const struct kexec_file_ops elf_kexec_ops = { + .probe = kexec_elf_probe, + .load = elf_kexec_load, +}; diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index c8b9ce274b9a..2e5b88ca11ce 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -207,13 +207,27 @@ check_syscall_nr: * Syscall number held in a7. * If syscall number is above allowed value, redirect to ni_syscall. */ - bgeu a7, t0, 1f + bgeu a7, t0, 3f +#ifdef CONFIG_COMPAT + REG_L s0, PT_STATUS(sp) + srli s0, s0, SR_UXL_SHIFT + andi s0, s0, (SR_UXL >> SR_UXL_SHIFT) + li t0, (SR_UXL_32 >> SR_UXL_SHIFT) + sub t0, s0, t0 + bnez t0, 1f + + /* Call compat_syscall */ + la s0, compat_sys_call_table + j 2f +1: +#endif /* Call syscall */ la s0, sys_call_table +2: slli t0, a7, RISCV_LGPTR add s0, s0, t0 REG_L s0, 0(s0) -1: +3: jalr s0 ret_from_syscall: diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 893b8bb69391..273eb0fa1f50 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -14,6 +14,7 @@ #include <asm/cpu_ops_sbi.h> #include <asm/hwcap.h> #include <asm/image.h> +#include <asm/xip_fixup.h> #include "efi-header.S" __HEAD diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c index cbef0fc73afa..df8e24559035 100644 --- a/arch/riscv/kernel/machine_kexec.c +++ b/arch/riscv/kernel/machine_kexec.c @@ -65,7 +65,9 @@ machine_kexec_prepare(struct kimage *image) if (image->segment[i].memsz <= sizeof(fdt)) continue; - if (copy_from_user(&fdt, image->segment[i].buf, sizeof(fdt))) + if (image->file_mode) + memcpy(&fdt, image->segment[i].buf, sizeof(fdt)); + else if (copy_from_user(&fdt, image->segment[i].buf, sizeof(fdt))) continue; if (fdt_check_header(&fdt)) diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c new file mode 100644 index 000000000000..b0bf8c1722c0 --- /dev/null +++ b/arch/riscv/kernel/machine_kexec_file.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * kexec_file for riscv, use vmlinux as the dump-capture kernel image. + * + * Copyright (C) 2021 Huawei Technologies Co, Ltd. + * + * Author: Liao Chang (liaochang1@huawei.com) + */ +#include <linux/kexec.h> + +const struct kexec_file_ops * const kexec_file_loaders[] = { + &elf_kexec_ops, + NULL +}; diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index c29cef90d1dd..91fe16bfaa07 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -11,6 +11,7 @@ #include <linux/vmalloc.h> #include <linux/sizes.h> #include <linux/pgtable.h> +#include <asm/alternative.h> #include <asm/sections.h> /* @@ -427,3 +428,31 @@ void *module_alloc(unsigned long size) __builtin_return_address(0)); } #endif + +static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + const char *name) +{ + const Elf_Shdr *s, *se; + const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + + for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) { + if (strcmp(name, secstrs + s->sh_name) == 0) + return s; + } + + return NULL; +} + +int module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + const Elf_Shdr *s; + + s = find_section(hdr, sechdrs, ".alternative"); + if (s) + apply_module_alternatives((void *)s->sh_addr, s->sh_size); + + return 0; +} diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 504b496787aa..1c7be865ab31 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -84,6 +84,34 @@ void show_regs(struct pt_regs *regs) dump_backtrace(regs, NULL, KERN_DEFAULT); } +#ifdef CONFIG_COMPAT +static bool compat_mode_supported __read_mostly; + +bool compat_elf_check_arch(Elf32_Ehdr *hdr) +{ + return compat_mode_supported && + hdr->e_machine == EM_RISCV && + hdr->e_ident[EI_CLASS] == ELFCLASS32; +} + +static int __init compat_mode_detect(void) +{ + unsigned long tmp = csr_read(CSR_STATUS); + + csr_write(CSR_STATUS, (tmp & ~SR_UXL) | SR_UXL_32); + compat_mode_supported = + (csr_read(CSR_STATUS) & SR_UXL) == SR_UXL_32; + + csr_write(CSR_STATUS, tmp); + + pr_info("riscv: ELF compat mode %s", + compat_mode_supported ? "supported" : "failed"); + + return 0; +} +early_initcall(compat_mode_detect); +#endif + void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) { @@ -98,6 +126,15 @@ void start_thread(struct pt_regs *regs, unsigned long pc, } regs->epc = pc; regs->sp = sp; + +#ifdef CONFIG_64BIT + regs->status &= ~SR_UXL; + + if (is_compat_task()) + regs->status |= SR_UXL_32; + else + regs->status |= SR_UXL_64; +#endif } void flush_thread(void) diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 793c7da0554b..2ae8280ae475 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -12,6 +12,7 @@ #include <asm/thread_info.h> #include <asm/switch_to.h> #include <linux/audit.h> +#include <linux/compat.h> #include <linux/ptrace.h> #include <linux/elf.h> #include <linux/regset.h> @@ -110,11 +111,6 @@ static const struct user_regset_view riscv_user_native_view = { .n = ARRAY_SIZE(riscv_user_regset), }; -const struct user_regset_view *task_user_regset_view(struct task_struct *task) -{ - return &riscv_user_native_view; -} - struct pt_regs_offset { const char *name; int offset; @@ -272,3 +268,84 @@ __visible void do_syscall_trace_exit(struct pt_regs *regs) trace_sys_exit(regs, regs_return_value(regs)); #endif } + +#ifdef CONFIG_COMPAT +static int compat_riscv_gpr_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct compat_user_regs_struct cregs; + + regs_to_cregs(&cregs, task_pt_regs(target)); + + return membuf_write(&to, &cregs, + sizeof(struct compat_user_regs_struct)); +} + +static int compat_riscv_gpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct compat_user_regs_struct cregs; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &cregs, 0, -1); + + cregs_to_regs(&cregs, task_pt_regs(target)); + + return ret; +} + +static const struct user_regset compat_riscv_user_regset[] = { + [REGSET_X] = { + .core_note_type = NT_PRSTATUS, + .n = ELF_NGREG, + .size = sizeof(compat_elf_greg_t), + .align = sizeof(compat_elf_greg_t), + .regset_get = compat_riscv_gpr_get, + .set = compat_riscv_gpr_set, + }, +#ifdef CONFIG_FPU + [REGSET_F] = { + .core_note_type = NT_PRFPREG, + .n = ELF_NFPREG, + .size = sizeof(elf_fpreg_t), + .align = sizeof(elf_fpreg_t), + .regset_get = riscv_fpr_get, + .set = riscv_fpr_set, + }, +#endif +}; + +static const struct user_regset_view compat_riscv_user_native_view = { + .name = "riscv", + .e_machine = EM_RISCV, + .regsets = compat_riscv_user_regset, + .n = ARRAY_SIZE(compat_riscv_user_regset), +}; + +long compat_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t caddr, compat_ulong_t cdata) +{ + long ret = -EIO; + + switch (request) { + default: + ret = compat_ptrace_request(child, request, caddr, cdata); + break; + } + + return ret; +} +#endif /* CONFIG_COMPAT */ + +const struct user_regset_view *task_user_regset_view(struct task_struct *task) +{ +#ifdef CONFIG_COMPAT + if (test_tsk_thread_flag(task, TIF_32BIT)) + return &compat_riscv_user_native_view; + else +#endif + return &riscv_user_native_view; +} diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 834eb652a7b9..e0373a3056e8 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -21,6 +21,7 @@ #include <linux/efi.h> #include <linux/crash_dump.h> +#include <asm/alternative.h> #include <asm/cpu_ops.h> #include <asm/early_ioremap.h> #include <asm/pgtable.h> @@ -295,6 +296,7 @@ void __init setup_arch(char **cmdline_p) #endif riscv_fill_hwcap(); + apply_boot_alternatives(); } static int __init topology_init(void) diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 9f4e59f80551..38b05ca6fe66 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -6,6 +6,7 @@ * Copyright (C) 2012 Regents of the University of California */ +#include <linux/compat.h> #include <linux/signal.h> #include <linux/uaccess.h> #include <linux/syscalls.h> @@ -14,6 +15,7 @@ #include <asm/ucontext.h> #include <asm/vdso.h> +#include <asm/signal32.h> #include <asm/switch_to.h> #include <asm/csr.h> @@ -261,7 +263,10 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ - ret = setup_rt_frame(ksig, oldset, regs); + if (is_compat_task()) + ret = compat_setup_rt_frame(ksig, oldset, regs); + else + ret = setup_rt_frame(ksig, oldset, regs); signal_setup_done(ret, ksig, 0); } diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 622f226454d5..f1e4948a4b52 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -32,7 +32,6 @@ #include <asm/sections.h> #include <asm/sbi.h> #include <asm/smp.h> -#include <asm/alternative.h> #include "head.h" @@ -41,9 +40,6 @@ static DECLARE_COMPLETION(cpu_running); void __init smp_prepare_boot_cpu(void) { init_cpu_topology(); -#ifdef CONFIG_RISCV_ERRATA_ALTERNATIVE - apply_boot_alternatives(); -#endif } void __init smp_prepare_cpus(unsigned int max_cpus) diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S index 4b07b809a2b8..aafcca58c19d 100644 --- a/arch/riscv/kernel/suspend_entry.S +++ b/arch/riscv/kernel/suspend_entry.S @@ -8,6 +8,7 @@ #include <asm/asm.h> #include <asm/asm-offsets.h> #include <asm/csr.h> +#include <asm/xip_fixup.h> .text .altmacro diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 12f8a7fce78b..9c0194f176fc 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -33,7 +33,9 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, { return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 0); } -#else +#endif + +#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT) SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, unsigned long, prot, unsigned long, flags, unsigned long, fd, off_t, offset) @@ -44,7 +46,7 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, */ return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12); } -#endif /* !CONFIG_64BIT */ +#endif /* * Allows the instruction cache to be flushed from userspace. Despite RISC-V diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index fe92e119e6a3..b40426509244 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -86,7 +86,7 @@ static void do_trap_error(struct pt_regs *regs, int signo, int code, } } -#if defined (CONFIG_XIP_KERNEL) && defined (CONFIG_RISCV_ERRATA_ALTERNATIVE) +#if defined(CONFIG_XIP_KERNEL) && defined(CONFIG_RISCV_ALTERNATIVE) #define __trap_section __section(".xip.traps") #else #define __trap_section diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index a9436a65161a..69b05b6c181b 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -23,6 +23,9 @@ struct vdso_data { #endif extern char vdso_start[], vdso_end[]; +#ifdef CONFIG_COMPAT +extern char compat_vdso_start[], compat_vdso_end[]; +#endif enum vvar_pages { VVAR_DATA_PAGE_OFFSET, @@ -30,6 +33,11 @@ enum vvar_pages { VVAR_NR_PAGES, }; +enum rv_vdso_map { + RV_VDSO_MAP_VVAR, + RV_VDSO_MAP_VDSO, +}; + #define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) /* @@ -52,12 +60,6 @@ struct __vdso_info { struct vm_special_mapping *cm; }; -static struct __vdso_info vdso_info __ro_after_init = { - .name = "vdso", - .vdso_code_start = vdso_start, - .vdso_code_end = vdso_end, -}; - static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma) { @@ -66,37 +68,33 @@ static int vdso_mremap(const struct vm_special_mapping *sm, return 0; } -static int __init __vdso_init(void) +static void __init __vdso_init(struct __vdso_info *vdso_info) { unsigned int i; struct page **vdso_pagelist; unsigned long pfn; - if (memcmp(vdso_info.vdso_code_start, "\177ELF", 4)) { - pr_err("vDSO is not a valid ELF object!\n"); - return -EINVAL; - } + if (memcmp(vdso_info->vdso_code_start, "\177ELF", 4)) + panic("vDSO is not a valid ELF object!\n"); - vdso_info.vdso_pages = ( - vdso_info.vdso_code_end - - vdso_info.vdso_code_start) >> + vdso_info->vdso_pages = ( + vdso_info->vdso_code_end - + vdso_info->vdso_code_start) >> PAGE_SHIFT; - vdso_pagelist = kcalloc(vdso_info.vdso_pages, + vdso_pagelist = kcalloc(vdso_info->vdso_pages, sizeof(struct page *), GFP_KERNEL); if (vdso_pagelist == NULL) - return -ENOMEM; + panic("vDSO kcalloc failed!\n"); /* Grab the vDSO code pages. */ - pfn = sym_to_pfn(vdso_info.vdso_code_start); + pfn = sym_to_pfn(vdso_info->vdso_code_start); - for (i = 0; i < vdso_info.vdso_pages; i++) + for (i = 0; i < vdso_info->vdso_pages; i++) vdso_pagelist[i] = pfn_to_page(pfn + i); - vdso_info.cm->pages = vdso_pagelist; - - return 0; + vdso_info->cm->pages = vdso_pagelist; } #ifdef CONFIG_TIME_NS @@ -116,13 +114,14 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) { struct mm_struct *mm = task->mm; struct vm_area_struct *vma; + struct __vdso_info *vdso_info = mm->context.vdso_info; mmap_read_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) { unsigned long size = vma->vm_end - vma->vm_start; - if (vma_is_special_mapping(vma, vdso_info.dm)) + if (vma_is_special_mapping(vma, vdso_info->dm)) zap_page_range(vma, vma->vm_start, size); } @@ -187,12 +186,27 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, return vmf_insert_pfn(vma, vmf->address, pfn); } -enum rv_vdso_map { - RV_VDSO_MAP_VVAR, - RV_VDSO_MAP_VDSO, +static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = { + [RV_VDSO_MAP_VVAR] = { + .name = "[vvar]", + .fault = vvar_fault, + }, + [RV_VDSO_MAP_VDSO] = { + .name = "[vdso]", + .mremap = vdso_mremap, + }, }; -static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = { +static struct __vdso_info vdso_info __ro_after_init = { + .name = "vdso", + .vdso_code_start = vdso_start, + .vdso_code_end = vdso_end, + .dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR], + .cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO], +}; + +#ifdef CONFIG_COMPAT +static struct vm_special_mapping rv_compat_vdso_maps[] __ro_after_init = { [RV_VDSO_MAP_VVAR] = { .name = "[vvar]", .fault = vvar_fault, @@ -203,25 +217,37 @@ static struct vm_special_mapping rv_vdso_maps[] __ro_after_init = { }, }; +static struct __vdso_info compat_vdso_info __ro_after_init = { + .name = "compat_vdso", + .vdso_code_start = compat_vdso_start, + .vdso_code_end = compat_vdso_end, + .dm = &rv_compat_vdso_maps[RV_VDSO_MAP_VVAR], + .cm = &rv_compat_vdso_maps[RV_VDSO_MAP_VDSO], +}; +#endif + static int __init vdso_init(void) { - vdso_info.dm = &rv_vdso_maps[RV_VDSO_MAP_VVAR]; - vdso_info.cm = &rv_vdso_maps[RV_VDSO_MAP_VDSO]; + __vdso_init(&vdso_info); +#ifdef CONFIG_COMPAT + __vdso_init(&compat_vdso_info); +#endif - return __vdso_init(); + return 0; } arch_initcall(vdso_init); static int __setup_additional_pages(struct mm_struct *mm, struct linux_binprm *bprm, - int uses_interp) + int uses_interp, + struct __vdso_info *vdso_info) { unsigned long vdso_base, vdso_text_len, vdso_mapping_len; void *ret; BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES); - vdso_text_len = vdso_info.vdso_pages << PAGE_SHIFT; + vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT; /* Be sure to map the data page */ vdso_mapping_len = vdso_text_len + VVAR_SIZE; @@ -232,16 +258,18 @@ static int __setup_additional_pages(struct mm_struct *mm, } ret = _install_special_mapping(mm, vdso_base, VVAR_SIZE, - (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info.dm); + (VM_READ | VM_MAYREAD | VM_PFNMAP), vdso_info->dm); if (IS_ERR(ret)) goto up_fail; vdso_base += VVAR_SIZE; mm->context.vdso = (void *)vdso_base; + mm->context.vdso_info = (void *)vdso_info; + ret = _install_special_mapping(mm, vdso_base, vdso_text_len, (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC), - vdso_info.cm); + vdso_info->cm); if (IS_ERR(ret)) goto up_fail; @@ -253,6 +281,24 @@ up_fail: return PTR_ERR(ret); } +#ifdef CONFIG_COMPAT +int compat_arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp) +{ + struct mm_struct *mm = current->mm; + int ret; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = __setup_additional_pages(mm, bprm, uses_interp, + &compat_vdso_info); + mmap_write_unlock(mm); + + return ret; +} +#endif + int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { struct mm_struct *mm = current->mm; @@ -261,7 +307,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (mmap_write_lock_killable(mm)) return -EINTR; - ret = __setup_additional_pages(mm, bprm, uses_interp); + ret = __setup_additional_pages(mm, bprm, uses_interp, &vdso_info); mmap_write_unlock(mm); return ret; diff --git a/arch/riscv/kernel/vdso/vdso.S b/arch/riscv/kernel/vdso/vdso.S index df222245be05..83f1c899e8d8 100644 --- a/arch/riscv/kernel/vdso/vdso.S +++ b/arch/riscv/kernel/vdso/vdso.S @@ -7,12 +7,16 @@ #include <linux/linkage.h> #include <asm/page.h> +#ifndef __VDSO_PATH +#define __VDSO_PATH "arch/riscv/kernel/vdso/vdso.so" +#endif + __PAGE_ALIGNED_DATA .globl vdso_start, vdso_end .balign PAGE_SIZE vdso_start: - .incbin "arch/riscv/kernel/vdso/vdso.so" + .incbin __VDSO_PATH .balign PAGE_SIZE vdso_end: |