diff options
Diffstat (limited to 'arch/riscv')
25 files changed, 340 insertions, 230 deletions
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 8fcceb8eda07..c79955655fa4 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -13,9 +13,7 @@ config 32BIT config RISCV def_bool y select ARCH_CLOCKSOURCE_INIT - select ARCH_SUPPORTS_ATOMIC_RMW - select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU - select ARCH_STACKWALK + select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION select ARCH_HAS_BINFMT_FLAT select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DEBUG_VIRTUAL if MMU @@ -31,8 +29,12 @@ config RISCV select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL select ARCH_HAS_STRICT_MODULE_RWX if MMU && !XIP_KERNEL select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST + select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT + select ARCH_STACKWALK + select ARCH_SUPPORTS_ATOMIC_RMW + select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU select ARCH_SUPPORTS_HUGETLBFS if MMU select ARCH_USE_MEMTEST select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU @@ -48,16 +50,16 @@ config RISCV select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_EARLY_IOREMAP select GENERIC_GETTIMEOFDAY if HAVE_GENERIC_VDSO - select GENERIC_IOREMAP + select GENERIC_IDLE_POLL_SETUP + select GENERIC_IOREMAP if MMU select GENERIC_IRQ_MULTI_HANDLER select GENERIC_IRQ_SHOW + select GENERIC_IRQ_SHOW_LEVEL select GENERIC_LIB_DEVMEM_IS_ALLOWED select GENERIC_PCI_IOMAP select GENERIC_PTDUMP if MMU select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD - select GENERIC_STRNCPY_FROM_USER if MMU - select GENERIC_STRNLEN_USER if MMU select GENERIC_TIME_VSYSCALL if MMU && 64BIT select HANDLE_DOMAIN_IRQ select HAVE_ARCH_AUDITSYSCALL @@ -72,6 +74,7 @@ config RISCV select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU + select HAVE_ARCH_THREAD_STRUCT_WHITELIST select HAVE_ARCH_VMAP_STACK if MMU && 64BIT select HAVE_ASM_MODVERSIONS select HAVE_CONTEXT_TRACKING @@ -97,6 +100,7 @@ config RISCV select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select IRQ_DOMAIN + select IRQ_FORCED_THREADING select MODULES_USE_ELF_RELA if MODULES select MODULE_SECTIONS if MODULES select OF @@ -109,6 +113,7 @@ config RISCV select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK + select TRACE_IRQFLAGS_SUPPORT select UACCESS_MEMCPY if !MMU select ZONE_DMA32 if 64BIT @@ -178,9 +183,6 @@ config ARCH_SUPPORTS_UPROBES config STACKTRACE_SUPPORT def_bool y -config TRACE_IRQFLAGS_SUPPORT - def_bool y - config GENERIC_BUG def_bool y depends on BUG @@ -492,10 +494,16 @@ config CC_HAVE_STACKPROTECTOR_TLS config STACKPROTECTOR_PER_TASK def_bool y + depends on !GCC_PLUGIN_RANDSTRUCT depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_TLS +config PHYS_RAM_BASE_FIXED + bool "Explicitly specified physical RAM address" + default n + config PHYS_RAM_BASE hex "Platform Physical RAM address" + depends on PHYS_RAM_BASE_FIXED default "0x80000000" help This is the physical address of RAM in the system. It has to be @@ -508,6 +516,7 @@ config XIP_KERNEL # This prevents XIP from being enabled by all{yes,mod}config, which # fail to build since XIP doesn't support large kernels. depends on !COMPILE_TEST + select PHYS_RAM_BASE_FIXED help Execute-In-Place allows the kernel to run from non-volatile storage directly addressable by the CPU, such as NOR flash. This saves RAM diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index bc74afdbf31e..01906a90c501 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -41,7 +41,7 @@ endif ifeq ($(CONFIG_LD_IS_LLD),y) KBUILD_CFLAGS += -mno-relax KBUILD_AFLAGS += -mno-relax -ifneq ($(LLVM_IAS),1) +ifndef CONFIG_AS_IS_LLVM KBUILD_CFLAGS += -Wa,-mno-relax KBUILD_AFLAGS += -Wa,-mno-relax endif @@ -108,6 +108,12 @@ PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@ +ifeq ($(CONFIG_MMU),y) +prepare: vdso_prepare +vdso_prepare: prepare0 + $(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso include/generated/vdso-offsets.h +endif + ifneq ($(CONFIG_XIP_KERNEL),y) ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_SOC_CANAAN),yy) KBUILD_IMAGE := $(boot)/loader.bin diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts index ec79944065c9..baea7d204639 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts @@ -14,6 +14,10 @@ model = "Microchip PolarFire-SoC Icicle Kit"; compatible = "microchip,mpfs-icicle-kit"; + aliases { + ethernet0 = &emac1; + }; + chosen { stdout-path = &serial0; }; diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi index b9819570a7d1..9d2fbbc1f777 100644 --- a/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi +++ b/arch/riscv/boot/dts/microchip/microchip-mpfs.dtsi @@ -317,7 +317,7 @@ reg = <0x0 0x20112000 0x0 0x2000>; interrupt-parent = <&plic>; interrupts = <70 71 72 73>; - mac-address = [00 00 00 00 00 00]; + local-mac-address = [00 00 00 00 00 00]; clocks = <&clkcfg 5>, <&clkcfg 2>; status = "disabled"; clock-names = "pclk", "hclk"; diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts index b1c3c596578f..2e4ea84f27e7 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -24,7 +24,7 @@ memory@80000000 { device_type = "memory"; - reg = <0x0 0x80000000 0x2 0x00000000>; + reg = <0x0 0x80000000 0x4 0x00000000>; }; soc { diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 1f2be234b11c..bc68231a8fb7 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -132,7 +132,6 @@ CONFIG_DEBUG_PLIST=y CONFIG_DEBUG_SG=y # CONFIG_RCU_TRACE is not set CONFIG_RCU_EQS_DEBUG=y -CONFIG_DEBUG_BLOCK_EXT_DEVT=y # CONFIG_FTRACE is not set # CONFIG_RUNTIME_TESTING_MENU is not set CONFIG_MEMTEST=y diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 8dd02b842fef..434ef5b64599 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -127,7 +127,6 @@ CONFIG_DEBUG_PLIST=y CONFIG_DEBUG_SG=y # CONFIG_RCU_TRACE is not set CONFIG_RCU_EQS_DEBUG=y -CONFIG_DEBUG_BLOCK_EXT_DEVT=y # CONFIG_FTRACE is not set # CONFIG_RUNTIME_TESTING_MENU is not set CONFIG_MEMTEST=y diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h index 6d98cd999680..49b398fe99f1 100644 --- a/arch/riscv/include/asm/efi.h +++ b/arch/riscv/include/asm/efi.h @@ -13,6 +13,7 @@ #ifdef CONFIG_EFI extern void efi_init(void); +extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); #else #define efi_init() #endif @@ -27,10 +28,10 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); #define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE) -/* Load initrd at enough distance from DRAM start */ +/* Load initrd anywhere in system RAM */ static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr) { - return image_addr + SZ_256M; + return ULONG_MAX; } #define alloc_screen_info(x...) (&screen_info) @@ -39,10 +40,6 @@ static inline void free_screen_info(struct screen_info *si) { } -static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) -{ -} - void efi_virtmap_load(void); void efi_virtmap_unload(void); diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index cca8764aed83..109c97e991a6 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -79,8 +79,8 @@ typedef struct page *pgtable_t; #endif #ifdef CONFIG_MMU -extern unsigned long pfn_base; -#define ARCH_PFN_OFFSET (pfn_base) +extern unsigned long riscv_pfn_base; +#define ARCH_PFN_OFFSET (riscv_pfn_base) #else #define ARCH_PFN_OFFSET (PAGE_OFFSET >> PAGE_SHIFT) #endif /* CONFIG_MMU */ @@ -91,10 +91,8 @@ struct kernel_mapping { uintptr_t size; /* Offset between linear mapping virtual address and kernel load address */ unsigned long va_pa_offset; -#ifdef CONFIG_64BIT /* Offset between kernel mapping virtual address and kernel load address */ unsigned long va_kernel_pa_offset; -#endif unsigned long va_kernel_xip_pa_offset; #ifdef CONFIG_XIP_KERNEL uintptr_t xiprom; @@ -103,26 +101,27 @@ struct kernel_mapping { }; extern struct kernel_mapping kernel_map; +extern phys_addr_t phys_ram_base; -#ifdef CONFIG_64BIT #define is_kernel_mapping(x) \ ((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size)) + #define is_linear_mapping(x) \ - ((x) >= PAGE_OFFSET && (x) < kernel_map.virt_addr) + ((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < kernel_map.virt_addr)) #define linear_mapping_pa_to_va(x) ((void *)((unsigned long)(x) + kernel_map.va_pa_offset)) #define kernel_mapping_pa_to_va(y) ({ \ unsigned long _y = y; \ - (_y >= CONFIG_PHYS_RAM_BASE) ? \ - (void *)((unsigned long)(_y) + kernel_map.va_kernel_pa_offset + XIP_OFFSET) : \ - (void *)((unsigned long)(_y) + kernel_map.va_kernel_xip_pa_offset); \ + (IS_ENABLED(CONFIG_XIP_KERNEL) && _y < phys_ram_base) ? \ + (void *)((unsigned long)(_y) + kernel_map.va_kernel_xip_pa_offset) : \ + (void *)((unsigned long)(_y) + kernel_map.va_kernel_pa_offset + XIP_OFFSET); \ }) #define __pa_to_va_nodebug(x) linear_mapping_pa_to_va(x) #define linear_mapping_va_to_pa(x) ((unsigned long)(x) - kernel_map.va_pa_offset) #define kernel_mapping_va_to_pa(y) ({ \ unsigned long _y = y; \ - (_y < kernel_map.virt_addr + XIP_OFFSET) ? \ + (IS_ENABLED(CONFIG_XIP_KERNEL) && _y < kernel_map.virt_addr + XIP_OFFSET) ? \ ((unsigned long)(_y) - kernel_map.va_kernel_xip_pa_offset) : \ ((unsigned long)(_y) - kernel_map.va_kernel_pa_offset - XIP_OFFSET); \ }) @@ -132,15 +131,6 @@ extern struct kernel_mapping kernel_map; is_linear_mapping(_x) ? \ linear_mapping_va_to_pa(_x) : kernel_mapping_va_to_pa(_x); \ }) -#else -#define is_kernel_mapping(x) \ - ((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size)) -#define is_linear_mapping(x) \ - ((x) >= PAGE_OFFSET) - -#define __pa_to_va_nodebug(x) ((void *)((unsigned long) (x) + kernel_map.va_pa_offset)) -#define __va_to_pa_nodebug(x) ((unsigned long)(x) - kernel_map.va_pa_offset) -#endif /* CONFIG_64BIT */ #ifdef CONFIG_DEBUG_VIRTUAL extern phys_addr_t __virt_to_phys(unsigned long x); diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 021ed64ee608..46b492c78cbb 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -37,6 +37,14 @@ struct thread_struct { unsigned long bad_cause; }; +/* Whitelist the fstate from the task_struct for hardened usercopy */ +static inline void arch_thread_struct_whitelist(unsigned long *offset, + unsigned long *size) +{ + *offset = offsetof(struct thread_struct, fstate); + *size = sizeof_field(struct thread_struct, fstate); +} + #define INIT_THREAD { \ .sp = sizeof(init_stack) + (long)&init_stack, \ } diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index 1453a2f563bc..893e47195e30 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -8,26 +8,25 @@ #ifndef _ASM_RISCV_VDSO_H #define _ASM_RISCV_VDSO_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 + #include <linux/types.h> +#include <generated/vdso-offsets.h> #ifndef CONFIG_GENERIC_TIME_VSYSCALL struct vdso_data { }; #endif -/* - * The VDSO symbols are mapped into Linux so we can just use regular symbol - * addressing to get their offsets in userspace. The symbols are mapped at an - * offset of 0, but since the linker must support setting weak undefined - * symbols to the absolute address 0 it also happens to support other low - * addresses even when the code model suggests those low addresses would not - * otherwise be availiable. - */ #define VDSO_SYMBOL(base, name) \ -({ \ - extern const char __vdso_##name[]; \ - (void __user *)((unsigned long)(base) + __vdso_##name); \ -}) + (void __user *)((unsigned long)(base) + __vdso_##name##_offset) + +#endif /* CONFIG_MMU */ asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t); diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index d3081e4d9600..3397ddac1a30 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -11,7 +11,7 @@ endif CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) ifdef CONFIG_KEXEC -AFLAGS_kexec_relocate.o := -mcmodel=medany -mno-relax +AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax) endif extra-y += head.o diff --git a/arch/riscv/kernel/probes/decode-insn.c b/arch/riscv/kernel/probes/decode-insn.c index 0ed043acc882..64f6183b4717 100644 --- a/arch/riscv/kernel/probes/decode-insn.c +++ b/arch/riscv/kernel/probes/decode-insn.c @@ -38,11 +38,10 @@ riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *api) RISCV_INSN_REJECTED(c_ebreak, insn); #endif - RISCV_INSN_REJECTED(auipc, insn); - RISCV_INSN_REJECTED(branch, insn); - RISCV_INSN_SET_SIMULATE(jal, insn); RISCV_INSN_SET_SIMULATE(jalr, insn); + RISCV_INSN_SET_SIMULATE(auipc, insn); + RISCV_INSN_SET_SIMULATE(branch, insn); return INSN_GOOD; } diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c index 2519ce26377d..d73e96f6ed7c 100644 --- a/arch/riscv/kernel/probes/simulate-insn.c +++ b/arch/riscv/kernel/probes/simulate-insn.c @@ -83,3 +83,115 @@ bool __kprobes simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *reg return ret; } + +#define auipc_rd_idx(opcode) \ + ((opcode >> 7) & 0x1f) + +#define auipc_imm(opcode) \ + ((((opcode) >> 12) & 0xfffff) << 12) + +#if __riscv_xlen == 64 +#define auipc_offset(opcode) sign_extend64(auipc_imm(opcode), 31) +#elif __riscv_xlen == 32 +#define auipc_offset(opcode) auipc_imm(opcode) +#else +#error "Unexpected __riscv_xlen" +#endif + +bool __kprobes simulate_auipc(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * auipc instruction: + * 31 12 11 7 6 0 + * | imm[31:12] | rd | opcode | + * 20 5 7 + */ + + u32 rd_idx = auipc_rd_idx(opcode); + unsigned long rd_val = addr + auipc_offset(opcode); + + if (!rv_insn_reg_set_val(regs, rd_idx, rd_val)) + return false; + + instruction_pointer_set(regs, addr + 4); + + return true; +} + +#define branch_rs1_idx(opcode) \ + (((opcode) >> 15) & 0x1f) + +#define branch_rs2_idx(opcode) \ + (((opcode) >> 20) & 0x1f) + +#define branch_funct3(opcode) \ + (((opcode) >> 12) & 0x7) + +#define branch_imm(opcode) \ + (((((opcode) >> 8) & 0xf ) << 1) | \ + ((((opcode) >> 25) & 0x3f) << 5) | \ + ((((opcode) >> 7) & 0x1 ) << 11) | \ + ((((opcode) >> 31) & 0x1 ) << 12)) + +#define branch_offset(opcode) \ + sign_extend32((branch_imm(opcode)), 12) + +#define BRANCH_BEQ 0x0 +#define BRANCH_BNE 0x1 +#define BRANCH_BLT 0x4 +#define BRANCH_BGE 0x5 +#define BRANCH_BLTU 0x6 +#define BRANCH_BGEU 0x7 + +bool __kprobes simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * branch instructions: + * 31 30 25 24 20 19 15 14 12 11 8 7 6 0 + * | imm[12] | imm[10:5] | rs2 | rs1 | funct3 | imm[4:1] | imm[11] | opcode | + * 1 6 5 5 3 4 1 7 + * imm[12|10:5] rs2 rs1 000 imm[4:1|11] 1100011 BEQ + * imm[12|10:5] rs2 rs1 001 imm[4:1|11] 1100011 BNE + * imm[12|10:5] rs2 rs1 100 imm[4:1|11] 1100011 BLT + * imm[12|10:5] rs2 rs1 101 imm[4:1|11] 1100011 BGE + * imm[12|10:5] rs2 rs1 110 imm[4:1|11] 1100011 BLTU + * imm[12|10:5] rs2 rs1 111 imm[4:1|11] 1100011 BGEU + */ + + s32 offset; + s32 offset_tmp; + unsigned long rs1_val; + unsigned long rs2_val; + + if (!rv_insn_reg_get_val(regs, branch_rs1_idx(opcode), &rs1_val) || + !rv_insn_reg_get_val(regs, branch_rs2_idx(opcode), &rs2_val)) + return false; + + offset_tmp = branch_offset(opcode); + switch (branch_funct3(opcode)) { + case BRANCH_BEQ: + offset = (rs1_val == rs2_val) ? offset_tmp : 4; + break; + case BRANCH_BNE: + offset = (rs1_val != rs2_val) ? offset_tmp : 4; + break; + case BRANCH_BLT: + offset = ((long)rs1_val < (long)rs2_val) ? offset_tmp : 4; + break; + case BRANCH_BGE: + offset = ((long)rs1_val >= (long)rs2_val) ? offset_tmp : 4; + break; + case BRANCH_BLTU: + offset = (rs1_val < rs2_val) ? offset_tmp : 4; + break; + case BRANCH_BGEU: + offset = (rs1_val >= rs2_val) ? offset_tmp : 4; + break; + default: + return false; + } + + instruction_pointer_set(regs, addr + offset); + + return true; +} diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c index 1a85305720e8..9c0511119bad 100644 --- a/arch/riscv/kernel/ptrace.c +++ b/arch/riscv/kernel/ptrace.c @@ -10,6 +10,7 @@ #include <asm/ptrace.h> #include <asm/syscall.h> #include <asm/thread_info.h> +#include <asm/switch_to.h> #include <linux/audit.h> #include <linux/ptrace.h> #include <linux/elf.h> @@ -56,6 +57,9 @@ static int riscv_fpr_get(struct task_struct *target, { struct __riscv_d_ext_state *fstate = &target->thread.fstate; + if (target == current) + fstate_save(current, task_pt_regs(current)); + membuf_write(&to, fstate, offsetof(struct __riscv_d_ext_state, fcsr)); membuf_store(&to, fstate->fcsr); return membuf_zero(&to, 4); // explicitly pad diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 18bd0e4bc36c..b9620e5f00ba 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -229,8 +229,8 @@ static void __init init_resources(void) } /* Clean-up any unused pre-allocated resources */ - mem_res_sz = (num_resources - res_idx + 1) * sizeof(*mem_res); - memblock_free(__pa(mem_res), mem_res_sz); + if (res_idx >= 0) + memblock_free(__pa(mem_res), (res_idx + 1) * sizeof(*mem_res)); return; error: @@ -255,7 +255,7 @@ static void __init parse_dtb(void) pr_err("No DTB passed to the kernel\n"); #ifdef CONFIG_CMDLINE_FORCE - strlcpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); + strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); pr_info("Forcing kernel command line to: %s\n", boot_command_line); #endif } diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index ff467b98c3e3..315db3d0229b 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -27,7 +27,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, fp = frame_pointer(regs); sp = user_stack_pointer(regs); pc = instruction_pointer(regs); - } else if (task == current) { + } else if (task == NULL || task == current) { fp = (unsigned long)__builtin_frame_address(1); sp = (unsigned long)__builtin_frame_address(0); pc = (unsigned long)__builtin_return_address(0); @@ -132,8 +132,12 @@ unsigned long get_wchan(struct task_struct *task) { unsigned long pc = 0; - if (likely(task && task != current && !task_is_running(task))) + 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); + } return pc; } diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 0a98fd0ddfe9..0daaa3e4630d 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -199,11 +199,6 @@ int is_valid_bugaddr(unsigned long pc) } #endif /* CONFIG_GENERIC_BUG */ -/* stvec & scratch is already set from head.S */ -void __init trap_init(void) -{ -} - #ifdef CONFIG_VMAP_STACK static DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack)__aligned(16); diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 24d936c147cd..f2e065671e4d 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -23,10 +23,10 @@ ifneq ($(c-gettimeofday-y),) endif # Build rules -targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-syms.S +targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) -obj-y += vdso.o vdso-syms.o +obj-y += vdso.o CPPFLAGS_vdso.lds += -P -C -U$(ARCH) # Disable -pg to prevent insert call site @@ -36,6 +36,7 @@ CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os GCOV_PROFILE := n KCOV_INSTRUMENT := n KASAN_SANITIZE := n +UBSAN_SANITIZE := n # Force dependency $(obj)/vdso.o: $(obj)/vdso.so @@ -43,20 +44,22 @@ $(obj)/vdso.o: $(obj)/vdso.so # link rule for the .so file, .lds has to be first $(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold) -LDFLAGS_vdso.so.dbg = -shared -s -soname=linux-vdso.so.1 \ +LDFLAGS_vdso.so.dbg = -shared -S -soname=linux-vdso.so.1 \ --build-id=sha1 --hash-style=both --eh-frame-hdr -# We also create a special relocatable object that should mirror the symbol -# table and layout of the linked DSO. With ld --just-symbols we can then -# refer to these symbols in the kernel code rather than hand-coded addresses. -$(obj)/vdso-syms.S: $(obj)/vdso.so FORCE - $(call if_changed,so2s) - # 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-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh +quiet_cmd_vdsosym = VDSOSYM $@ + cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ + +include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE + $(call if_changed,vdsosym) + # actual build commands # The DSO images are built using a special linker script # Make sure only to export the intended __vdso_xxx symbol offsets. @@ -65,11 +68,6 @@ quiet_cmd_vdsold = VDSOLD $@ $(OBJCOPY) $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \ rm $@.tmp -# Extracts symbol offsets from the VDSO, converting them into an assembly file -# that contains the same symbols at the same offsets. -quiet_cmd_so2s = SO2S $@ - cmd_so2s = $(NM) -D $< | $(srctree)/$(src)/so2s.sh > $@ - # install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ diff --git a/arch/riscv/kernel/vdso/gen_vdso_offsets.sh b/arch/riscv/kernel/vdso/gen_vdso_offsets.sh new file mode 100755 index 000000000000..c2e5613f3495 --- /dev/null +++ b/arch/riscv/kernel/vdso/gen_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 \2_offset\t0x\1/p' diff --git a/arch/riscv/kernel/vdso/so2s.sh b/arch/riscv/kernel/vdso/so2s.sh deleted file mode 100755 index e64cb6d9440e..000000000000 --- a/arch/riscv/kernel/vdso/so2s.sh +++ /dev/null @@ -1,6 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0+ -# Copyright 2020 Palmer Dabbelt <palmerdabbelt@google.com> - -sed 's!\([0-9a-f]*\) T \([a-z0-9_]*\)\(@@LINUX_4.15\)*!.global \2\n.set \2,0x\1!' \ -| grep '^\.' diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S index bceb0629e440..63bc691cff91 100644 --- a/arch/riscv/lib/uaccess.S +++ b/arch/riscv/lib/uaccess.S @@ -30,23 +30,23 @@ ENTRY(__asm_copy_from_user) * t0 - end of uncopied dst */ add t0, a0, a2 - bgtu a0, t0, 5f /* * Use byte copy only if too small. + * SZREG holds 4 for RV32 and 8 for RV64 */ - li a3, 8*SZREG /* size must be larger than size in word_copy */ + li a3, 9*SZREG /* size must be larger than size in word_copy */ bltu a2, a3, .Lbyte_copy_tail /* - * Copy first bytes until dst is align to word boundary. + * Copy first bytes until dst is aligned to word boundary. * a0 - start of dst * t1 - start of aligned dst */ addi t1, a0, SZREG-1 andi t1, t1, ~(SZREG-1) /* dst is already aligned, skip */ - beq a0, t1, .Lskip_first_bytes + beq a0, t1, .Lskip_align_dst 1: /* a5 - one byte for copying data */ fixup lb a5, 0(a1), 10f @@ -55,7 +55,7 @@ ENTRY(__asm_copy_from_user) addi a0, a0, 1 /* dst */ bltu a0, t1, 1b /* t1 - start of aligned dst */ -.Lskip_first_bytes: +.Lskip_align_dst: /* * Now dst is aligned. * Use shift-copy if src is misaligned. @@ -72,10 +72,9 @@ ENTRY(__asm_copy_from_user) * * a0 - start of aligned dst * a1 - start of aligned src - * a3 - a1 & mask:(SZREG-1) * t0 - end of aligned dst */ - addi t0, t0, -(8*SZREG-1) /* not to over run */ + addi t0, t0, -(8*SZREG) /* not to over run */ 2: fixup REG_L a4, 0(a1), 10f fixup REG_L a5, SZREG(a1), 10f @@ -97,7 +96,7 @@ ENTRY(__asm_copy_from_user) addi a1, a1, 8*SZREG bltu a0, t0, 2b - addi t0, t0, 8*SZREG-1 /* revert to original value */ + addi t0, t0, 8*SZREG /* revert to original value */ j .Lbyte_copy_tail .Lshift_copy: @@ -107,7 +106,7 @@ ENTRY(__asm_copy_from_user) * For misaligned copy we still perform aligned word copy, but * we need to use the value fetched from the previous iteration and * do some shifts. - * This is safe because reading less than a word size. + * This is safe because reading is less than a word size. * * a0 - start of aligned dst * a1 - start of src @@ -117,7 +116,7 @@ ENTRY(__asm_copy_from_user) */ /* calculating aligned word boundary for dst */ andi t1, t0, ~(SZREG-1) - /* Converting unaligned src to aligned arc */ + /* Converting unaligned src to aligned src */ andi a1, a1, ~(SZREG-1) /* @@ -125,11 +124,11 @@ ENTRY(__asm_copy_from_user) * t3 - prev shift * t4 - current shift */ - slli t3, a3, LGREG + slli t3, a3, 3 /* converting bytes in a3 to bits */ li a5, SZREG*8 sub t4, a5, t3 - /* Load the first word to combine with seceond word */ + /* Load the first word to combine with second word */ fixup REG_L a5, 0(a1), 10f 3: @@ -161,7 +160,7 @@ ENTRY(__asm_copy_from_user) * a1 - start of remaining src * t0 - end of remaining dst */ - bgeu a0, t0, 5f + bgeu a0, t0, .Lout_copy_user /* check if end of copy */ 4: fixup lb a5, 0(a1), 10f addi a1, a1, 1 /* src */ @@ -169,7 +168,7 @@ ENTRY(__asm_copy_from_user) addi a0, a0, 1 /* dst */ bltu a0, t0, 4b /* t0 - end of dst */ -5: +.Lout_copy_user: /* Disable access to user memory */ csrc CSR_STATUS, t6 li a0, 0 diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 269fc648ef3d..c0cddf0fc22d 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -19,6 +19,7 @@ #include <linux/set_memory.h> #include <linux/dma-map-ops.h> #include <linux/crash_dump.h> +#include <linux/hugetlb.h> #include <asm/fixmap.h> #include <asm/tlbflush.h> @@ -36,6 +37,9 @@ EXPORT_SYMBOL(kernel_map); #define kernel_map (*(struct kernel_mapping *)XIP_FIXUP(&kernel_map)) #endif +phys_addr_t phys_ram_base __ro_after_init; +EXPORT_SYMBOL(phys_ram_base); + #ifdef CONFIG_XIP_KERNEL extern char _xiprom[], _exiprom[]; #endif @@ -127,10 +131,17 @@ void __init mem_init(void) } /* - * The default maximal physical memory size is -PAGE_OFFSET, - * limit the memory size via mem. + * The default maximal physical memory size is -PAGE_OFFSET for 32-bit kernel, + * whereas for 64-bit kernel, the end of the virtual address space is occupied + * by the modules/BPF/kernel mappings which reduces the available size of the + * linear mapping. + * Limit the memory size via mem. */ +#ifdef CONFIG_64BIT +static phys_addr_t memory_limit = -PAGE_OFFSET - SZ_4G; +#else static phys_addr_t memory_limit = -PAGE_OFFSET; +#endif static int __init early_mem(char *p) { @@ -152,8 +163,8 @@ static void __init setup_bootmem(void) { phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); - phys_addr_t max_mapped_addr = __pa(~(ulong)0); - phys_addr_t dram_end; + phys_addr_t __maybe_unused max_mapped_addr; + phys_addr_t phys_ram_end; #ifdef CONFIG_XIP_KERNEL vmlinux_start = __pa_symbol(&_sdata); @@ -174,18 +185,28 @@ static void __init setup_bootmem(void) #endif memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); - dram_end = memblock_end_of_DRAM(); + + phys_ram_end = memblock_end_of_DRAM(); +#ifndef CONFIG_64BIT +#ifndef CONFIG_XIP_KERNEL + phys_ram_base = memblock_start_of_DRAM(); +#endif /* * memblock allocator is not aware of the fact that last 4K bytes of * the addressable memory can not be mapped because of IS_ERR_VALUE * macro. Make sure that last 4k bytes are not usable by memblock - * if end of dram is equal to maximum addressable memory. + * if end of dram is equal to maximum addressable memory. For 64-bit + * kernel, this problem can't happen here as the end of the virtual + * address space is occupied by the kernel mapping then this check must + * be done as soon as the kernel mapping base address is determined. */ - if (max_mapped_addr == (dram_end - 1)) + max_mapped_addr = __pa(~(ulong)0); + if (max_mapped_addr == (phys_ram_end - 1)) memblock_set_current_limit(max_mapped_addr - 4096); +#endif - min_low_pfn = PFN_UP(memblock_start_of_DRAM()); - max_low_pfn = max_pfn = PFN_DOWN(dram_end); + min_low_pfn = PFN_UP(phys_ram_base); + max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end); dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); @@ -202,6 +223,8 @@ static void __init setup_bootmem(void) early_init_fdt_scan_reserved_mem(); dma_contiguous_reserve(dma32_phys_limit); + if (IS_ENABLED(CONFIG_64BIT)) + hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); memblock_allow_resize(); } @@ -214,14 +237,15 @@ static struct pt_alloc_ops _pt_ops __initdata; #define pt_ops _pt_ops #endif -unsigned long pfn_base __ro_after_init; -EXPORT_SYMBOL(pfn_base); +unsigned long riscv_pfn_base __ro_after_init; +EXPORT_SYMBOL(riscv_pfn_base); pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss; pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss; static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss; pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); +static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE); #ifdef CONFIG_XIP_KERNEL #define trampoline_pg_dir ((pgd_t *)XIP_FIXUP(trampoline_pg_dir)) @@ -302,7 +326,6 @@ static void __init create_pte_mapping(pte_t *ptep, static pmd_t trampoline_pmd[PTRS_PER_PMD] __page_aligned_bss; static pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss; static pmd_t early_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE); -static pmd_t early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE); #ifdef CONFIG_XIP_KERNEL #define trampoline_pmd ((pmd_t *)XIP_FIXUP(trampoline_pmd)) @@ -388,6 +411,7 @@ static void __init create_pmd_mapping(pmd_t *pmdp, #define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot) \ create_pte_mapping(__nextp, __va, __pa, __sz, __prot) #define fixmap_pgd_next fixmap_pte +#define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot) #endif void __init create_pgd_mapping(pgd_t *pgdp, @@ -495,55 +519,87 @@ static __init pgprot_t pgprot_from_va(uintptr_t va) #endif #ifdef CONFIG_XIP_KERNEL -static void __init create_kernel_page_table(pgd_t *pgdir, uintptr_t map_size, +static void __init create_kernel_page_table(pgd_t *pgdir, __always_unused bool early) { uintptr_t va, end_va; /* Map the flash resident part */ end_va = kernel_map.virt_addr + kernel_map.xiprom_sz; - for (va = kernel_map.virt_addr; va < end_va; va += map_size) + for (va = kernel_map.virt_addr; va < end_va; va += PMD_SIZE) create_pgd_mapping(pgdir, va, kernel_map.xiprom + (va - kernel_map.virt_addr), - map_size, PAGE_KERNEL_EXEC); + PMD_SIZE, PAGE_KERNEL_EXEC); /* Map the data in RAM */ end_va = kernel_map.virt_addr + XIP_OFFSET + kernel_map.size; - for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += map_size) + for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += PMD_SIZE) create_pgd_mapping(pgdir, va, kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)), - map_size, PAGE_KERNEL); + PMD_SIZE, PAGE_KERNEL); } #else -static void __init create_kernel_page_table(pgd_t *pgdir, uintptr_t map_size, - bool early) +static void __init create_kernel_page_table(pgd_t *pgdir, bool early) { uintptr_t va, end_va; end_va = kernel_map.virt_addr + kernel_map.size; - for (va = kernel_map.virt_addr; va < end_va; va += map_size) + for (va = kernel_map.virt_addr; va < end_va; va += PMD_SIZE) create_pgd_mapping(pgdir, va, kernel_map.phys_addr + (va - kernel_map.virt_addr), - map_size, + PMD_SIZE, early ? PAGE_KERNEL_EXEC : pgprot_from_va(va)); } #endif -asmlinkage void __init setup_vm(uintptr_t dtb_pa) +/* + * Setup a 4MB mapping that encompasses the device tree: for 64-bit kernel, + * this means 2 PMD entries whereas for 32-bit kernel, this is only 1 PGDIR + * entry. + */ +static void __init create_fdt_early_page_table(pgd_t *pgdir, uintptr_t dtb_pa) { - uintptr_t __maybe_unused pa; - uintptr_t map_size; -#ifndef __PAGETABLE_PMD_FOLDED - pmd_t fix_bmap_spmd, fix_bmap_epmd; +#ifndef CONFIG_BUILTIN_DTB + uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1); + + create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, + IS_ENABLED(CONFIG_64BIT) ? (uintptr_t)early_dtb_pmd : pa, + PGDIR_SIZE, + IS_ENABLED(CONFIG_64BIT) ? PAGE_TABLE : PAGE_KERNEL); + + if (IS_ENABLED(CONFIG_64BIT)) { + create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA, + pa, PMD_SIZE, PAGE_KERNEL); + create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE, + pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL); + } + + dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1)); +#else + /* + * For 64-bit kernel, __va can't be used since it would return a linear + * mapping address whereas dtb_early_va will be used before + * setup_vm_final installs the linear mapping. For 32-bit kernel, as the + * kernel is mapped in the linear mapping, that makes no difference. + */ + dtb_early_va = kernel_mapping_pa_to_va(XIP_FIXUP(dtb_pa)); #endif + dtb_early_pa = dtb_pa; +} + +asmlinkage void __init setup_vm(uintptr_t dtb_pa) +{ + pmd_t __maybe_unused fix_bmap_spmd, fix_bmap_epmd; + kernel_map.virt_addr = KERNEL_LINK_ADDR; #ifdef CONFIG_XIP_KERNEL kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR; kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom); + phys_ram_base = CONFIG_PHYS_RAM_BASE; kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata); @@ -552,23 +608,22 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) kernel_map.phys_addr = (uintptr_t)(&_start); kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr; #endif - kernel_map.va_pa_offset = PAGE_OFFSET - kernel_map.phys_addr; -#ifdef CONFIG_64BIT kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr; -#endif - pfn_base = PFN_DOWN(kernel_map.phys_addr); - - /* - * Enforce boot alignment requirements of RV32 and - * RV64 by only allowing PMD or PGD mappings. - */ - map_size = PMD_SIZE; + riscv_pfn_base = PFN_DOWN(kernel_map.phys_addr); /* Sanity check alignment and size */ BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0); - BUG_ON((kernel_map.phys_addr % map_size) != 0); + BUG_ON((kernel_map.phys_addr % PMD_SIZE) != 0); + +#ifdef CONFIG_64BIT + /* + * The last 4K bytes of the addressable memory can not be mapped because + * of IS_ERR_VALUE macro. + */ + BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K); +#endif pt_ops.alloc_pte = alloc_pte_early; pt_ops.get_pte_virt = get_pte_virt_early; @@ -605,50 +660,10 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) * us to reach paging_init(). We map all memory banks later * in setup_vm_final() below. */ - create_kernel_page_table(early_pg_dir, map_size, true); + create_kernel_page_table(early_pg_dir, true); -#ifndef __PAGETABLE_PMD_FOLDED - /* Setup early PMD for DTB */ - create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, - (uintptr_t)early_dtb_pmd, PGDIR_SIZE, PAGE_TABLE); -#ifndef CONFIG_BUILTIN_DTB - /* Create two consecutive PMD mappings for FDT early scan */ - pa = dtb_pa & ~(PMD_SIZE - 1); - create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA, - pa, PMD_SIZE, PAGE_KERNEL); - create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE, - pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL); - dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1)); -#else /* CONFIG_BUILTIN_DTB */ -#ifdef CONFIG_64BIT - /* - * __va can't be used since it would return a linear mapping address - * whereas dtb_early_va will be used before setup_vm_final installs - * the linear mapping. - */ - dtb_early_va = kernel_mapping_pa_to_va(XIP_FIXUP(dtb_pa)); -#else - dtb_early_va = __va(dtb_pa); -#endif /* CONFIG_64BIT */ -#endif /* CONFIG_BUILTIN_DTB */ -#else -#ifndef CONFIG_BUILTIN_DTB - /* Create two consecutive PGD mappings for FDT early scan */ - pa = dtb_pa & ~(PGDIR_SIZE - 1); - create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, - pa, PGDIR_SIZE, PAGE_KERNEL); - create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA + PGDIR_SIZE, - pa + PGDIR_SIZE, PGDIR_SIZE, PAGE_KERNEL); - dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PGDIR_SIZE - 1)); -#else /* CONFIG_BUILTIN_DTB */ -#ifdef CONFIG_64BIT - dtb_early_va = kernel_mapping_pa_to_va(XIP_FIXUP(dtb_pa)); -#else - dtb_early_va = __va(dtb_pa); -#endif /* CONFIG_64BIT */ -#endif /* CONFIG_BUILTIN_DTB */ -#endif - dtb_early_pa = dtb_pa; + /* Setup early mapping for FDT early scan */ + create_fdt_early_page_table(early_pg_dir, dtb_pa); /* * Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap @@ -709,6 +724,8 @@ static void __init setup_vm_final(void) if (start <= __pa(PAGE_OFFSET) && __pa(PAGE_OFFSET) < end) start = __pa(PAGE_OFFSET); + if (end >= __pa(PAGE_OFFSET) + memory_limit) + end = __pa(PAGE_OFFSET) + memory_limit; map_size = best_map_size(start, end - start); for (pa = start; pa < end; pa += map_size) { @@ -721,7 +738,7 @@ static void __init setup_vm_final(void) #ifdef CONFIG_64BIT /* Map the kernel */ - create_kernel_page_table(swapper_pg_dir, PMD_SIZE, false); + create_kernel_page_table(swapper_pg_dir, false); #endif /* Clear fixmap PTE and PMD mappings */ @@ -788,38 +805,22 @@ static void __init reserve_crashkernel(void) crash_size = PAGE_ALIGN(crash_size); - if (crash_base == 0) { - /* - * Current riscv boot protocol requires 2MB alignment for - * RV64 and 4MB alignment for RV32 (hugepage size) - */ - crash_base = memblock_find_in_range(search_start, search_end, - crash_size, PMD_SIZE); - - if (crash_base == 0) { - pr_warn("crashkernel: couldn't allocate %lldKB\n", - crash_size >> 10); - return; - } - } else { - /* User specifies base address explicitly. */ - if (!memblock_is_region_memory(crash_base, crash_size)) { - pr_warn("crashkernel: requested region is not memory\n"); - return; - } - - if (memblock_is_region_reserved(crash_base, crash_size)) { - pr_warn("crashkernel: requested region is reserved\n"); - return; - } - + if (crash_base) { + search_start = crash_base; + search_end = crash_base + crash_size; + } - if (!IS_ALIGNED(crash_base, PMD_SIZE)) { - pr_warn("crashkernel: requested region is misaligned\n"); - return; - } + /* + * Current riscv boot protocol requires 2MB alignment for + * RV64 and 4MB alignment for RV32 (hugepage size) + */ + crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE, + search_start, search_end); + if (crash_base == 0) { + pr_warn("crashkernel: couldn't allocate %lldKB\n", + crash_size >> 10); + return; } - memblock_reserve(crash_base, crash_size); pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n", crash_base, crash_base + crash_size, crash_size >> 20); @@ -829,26 +830,6 @@ static void __init reserve_crashkernel(void) } #endif /* CONFIG_KEXEC_CORE */ -#ifdef CONFIG_CRASH_DUMP -/* - * We keep track of the ELF core header of the crashed - * kernel with a reserved-memory region with compatible - * string "linux,elfcorehdr". Here we register a callback - * to populate elfcorehdr_addr/size when this region is - * present. Note that this region will be marked as - * reserved once we call early_init_fdt_scan_reserved_mem() - * later on. - */ -static int __init elfcore_hdr_setup(struct reserved_mem *rmem) -{ - elfcorehdr_addr = rmem->base; - elfcorehdr_size = rmem->size; - return 0; -} - -RESERVEDMEM_OF_DECLARE(elfcorehdr, "linux,elfcorehdr", elfcore_hdr_setup); -#endif - void __init paging_init(void) { setup_bootmem(); diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index 81de865f4c7c..e6497424cbf6 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -1251,6 +1251,10 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, return -1; break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + case BPF_ST | BPF_MEM | BPF_B: case BPF_ST | BPF_MEM | BPF_H: case BPF_ST | BPF_MEM | BPF_W: diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 87e3bf5b9086..3af4131c22c7 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -939,6 +939,10 @@ out_be: emit_ld(rd, 0, RV_REG_T1, ctx); break; + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_B: emit_imm(RV_REG_T1, imm, ctx); |