diff options
30 files changed, 1141 insertions, 714 deletions
diff --git a/Documentation/arch/riscv/cmodx.rst b/Documentation/arch/riscv/cmodx.rst index 8c48bcff3df9..e009873b2d17 100644 --- a/Documentation/arch/riscv/cmodx.rst +++ b/Documentation/arch/riscv/cmodx.rst @@ -10,13 +10,45 @@ modified by the program itself. Instruction storage and the instruction cache program must enforce its own synchronization with the unprivileged fence.i instruction. -However, the default Linux ABI prohibits the use of fence.i in userspace -applications. At any point the scheduler may migrate a task onto a new hart. If -migration occurs after the userspace synchronized the icache and instruction -storage with fence.i, the icache on the new hart will no longer be clean. This -is due to the behavior of fence.i only affecting the hart that it is called on. -Thus, the hart that the task has been migrated to may not have synchronized -instruction storage and icache. +CMODX in the Kernel Space +--------------------- + +Dynamic ftrace +--------------------- + +Essentially, dynamic ftrace directs the control flow by inserting a function +call at each patchable function entry, and patches it dynamically at runtime to +enable or disable the redirection. In the case of RISC-V, 2 instructions, +AUIPC + JALR, are required to compose a function call. However, it is impossible +to patch 2 instructions and expect that a concurrent read-side executes them +without a race condition. This series makes atmoic code patching possible in +RISC-V ftrace. Kernel preemption makes things even worse as it allows the old +state to persist across the patching process with stop_machine(). + +In order to get rid of stop_machine() and run dynamic ftrace with full kernel +preemption, we partially initialize each patchable function entry at boot-time, +setting the first instruction to AUIPC, and the second to NOP. Now, atmoic +patching is possible because the kernel only has to update one instruction. +According to Ziccif, as long as an instruction is naturally aligned, the ISA +guarantee an atomic update. + +By fixing down the first instruction, AUIPC, the range of the ftrace trampoline +is limited to +-2K from the predetermined target, ftrace_caller, due to the lack +of immediate encoding space in RISC-V. To address the issue, we introduce +CALL_OPS, where an 8B naturally align metadata is added in front of each +pacthable function. The metadata is resolved at the first trampoline, then the +execution can be derect to another custom trampoline. + +CMODX in the User Space +--------------------- + +Though fence.i is an unprivileged instruction, the default Linux ABI prohibits +the use of fence.i in userspace applications. At any point the scheduler may +migrate a task onto a new hart. If migration occurs after the userspace +synchronized the icache and instruction storage with fence.i, the icache on the +new hart will no longer be clean. This is due to the behavior of fence.i only +affecting the hart that it is called on. Thus, the hart that the task has been +migrated to may not have synchronized instruction storage and icache. There are two ways to solve this problem: use the riscv_flush_icache() syscall, or use the ``PR_RISCV_SET_ICACHE_FLUSH_CTX`` prctl() and emit fence.i in diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst index f60bf5991755..a4998ad2dfe0 100644 --- a/Documentation/arch/riscv/hwprobe.rst +++ b/Documentation/arch/riscv/hwprobe.rst @@ -271,6 +271,10 @@ The following keys are defined: * :c:macro:`RISCV_HWPROBE_EXT_ZICBOM`: The Zicbom extension is supported, as ratified in commit 3dd606f ("Create cmobase-v1.0.pdf") of riscv-CMOs. + * :c:macro:`RISCV_HWPROBE_EXT_ZABHA`: The Zabha extension is supported as + ratified in commit 49f49c842ff9 ("Update to Rafified state") of + riscv-zabha. + * :c:macro:`RISCV_HWPROBE_KEY_CPUPERF_0`: Deprecated. Returns similar values to :c:macro:`RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF`, but the key was mistakenly classified as a bitmask rather than a value. diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 28765ce563de..a93af30727ee 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -99,6 +99,7 @@ config RISCV select EDAC_SUPPORT select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE + select FUNCTION_ALIGNMENT_8B if DYNAMIC_FTRACE_WITH_CALL_OPS select GENERIC_ARCH_TOPOLOGY select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS_BROADCAST if SMP @@ -143,6 +144,7 @@ config RISCV select HAVE_ARCH_THREAD_STRUCT_WHITELIST select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU + select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if 64BIT && MMU select HAVE_ARCH_USERFAULTFD_MINOR if 64BIT && USERFAULTFD select HAVE_ARCH_VMAP_STACK if MMU && 64BIT select HAVE_ASM_MODVERSIONS @@ -150,13 +152,15 @@ config RISCV select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS if MMU select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE) - select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + select FUNCTION_ALIGNMENT_4B if HAVE_DYNAMIC_FTRACE && RISCV_ISA_C + select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS if HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS + select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG) select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER if HAVE_DYNAMIC_FTRACE_WITH_ARGS select HAVE_FUNCTION_GRAPH_FREGS - select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION + select HAVE_FUNCTION_TRACER if !XIP_KERNEL select HAVE_EBPF_JIT if MMU select HAVE_GUP_FAST if MMU select HAVE_FUNCTION_ARG_ACCESS_API @@ -236,6 +240,7 @@ config CLANG_SUPPORTS_DYNAMIC_FTRACE config GCC_SUPPORTS_DYNAMIC_FTRACE def_bool CC_IS_GCC depends on $(cc-option,-fpatchable-function-entry=8) + depends on CC_HAS_MIN_FUNCTION_ALIGNMENT || !RISCV_ISA_C config HAVE_SHADOW_CALL_STACK def_bool $(cc-option,-fsanitize=shadow-call-stack) @@ -1186,8 +1191,8 @@ config CMDLINE_FALLBACK config CMDLINE_EXTEND bool "Extend bootloader kernel arguments" help - The command-line arguments provided during boot will be - appended to the built-in command line. This is useful in + The built-in command line will be appended to the command- + line arguments provided during boot. This is useful in cases where the provided arguments are insufficient and you don't want to or cannot modify them. diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 539d2aef5cab..df57654a615e 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -15,9 +15,9 @@ ifeq ($(CONFIG_DYNAMIC_FTRACE),y) LDFLAGS_vmlinux += --no-relax KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY ifeq ($(CONFIG_RISCV_ISA_C),y) - CC_FLAGS_FTRACE := -fpatchable-function-entry=4 + CC_FLAGS_FTRACE := -fpatchable-function-entry=8,4 else - CC_FLAGS_FTRACE := -fpatchable-function-entry=2 + CC_FLAGS_FTRACE := -fpatchable-function-entry=4,2 endif endif diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index d627f63ee289..22ebea3c2b26 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -20,10 +20,9 @@ extern void *return_address(unsigned int level); #define ftrace_return_address(n) return_address(n) void _mcount(void); -static inline unsigned long ftrace_call_adjust(unsigned long addr) -{ - return addr; -} +unsigned long ftrace_call_adjust(unsigned long addr); +unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip); +#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip) /* * Let's do like x86/arm64 and ignore the compat syscalls. @@ -57,12 +56,21 @@ struct dyn_arch_ftrace { * 2) jalr: setting low-12 offset to ra, jump to ra, and set ra to * return address (original pc + 4) * + * The first 2 instructions for each tracable function is compiled to 2 nop + * instructions. Then, the kernel initializes the first instruction to auipc at + * boot time (<ftrace disable>). The second instruction is patched to jalr to + * start the trace. + * + *<Image>: + * 0: nop + * 4: nop + * *<ftrace enable>: - * 0: auipc t0/ra, 0x? - * 4: jalr t0/ra, ?(t0/ra) + * 0: auipc t0, 0x? + * 4: jalr t0, ?(t0) * *<ftrace disable>: - * 0: nop + * 0: auipc t0, 0x? * 4: nop * * Dynamic ftrace generates probes to call sites, so we must deal with @@ -75,10 +83,9 @@ struct dyn_arch_ftrace { #define AUIPC_OFFSET_MASK (0xfffff000) #define AUIPC_PAD (0x00001000) #define JALR_SHIFT 20 -#define JALR_RA (0x000080e7) -#define AUIPC_RA (0x00000097) #define JALR_T0 (0x000282e7) #define AUIPC_T0 (0x00000297) +#define JALR_RANGE (JALR_SIGN_MASK - 1) #define to_jalr_t0(offset) \ (((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_T0) @@ -96,26 +103,14 @@ do { \ call[1] = to_jalr_t0(offset); \ } while (0) -#define to_jalr_ra(offset) \ - (((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_RA) - -#define to_auipc_ra(offset) \ - ((offset & JALR_SIGN_MASK) ? \ - (((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_RA) : \ - ((offset & AUIPC_OFFSET_MASK) | AUIPC_RA)) - -#define make_call_ra(caller, callee, call) \ -do { \ - unsigned int offset = \ - (unsigned long) (callee) - (unsigned long) (caller); \ - call[0] = to_auipc_ra(offset); \ - call[1] = to_jalr_ra(offset); \ -} while (0) - /* - * Let auipc+jalr be the basic *mcount unit*, so we make it 8 bytes here. + * Only the jalr insn in the auipc+jalr is patched, so we make it 4 + * bytes here. */ -#define MCOUNT_INSN_SIZE 8 +#define MCOUNT_INSN_SIZE 4 +#define MCOUNT_AUIPC_SIZE 4 +#define MCOUNT_JALR_SIZE 4 +#define MCOUNT_NOP4_SIZE 4 #ifndef __ASSEMBLY__ struct dyn_ftrace; @@ -135,6 +130,9 @@ struct __arch_ftrace_regs { unsigned long sp; unsigned long s0; unsigned long t1; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + unsigned long direct_tramp; +#endif union { unsigned long args[8]; struct { @@ -146,6 +144,13 @@ struct __arch_ftrace_regs { unsigned long a5; unsigned long a6; unsigned long a7; +#ifdef CONFIG_CC_IS_CLANG + unsigned long t2; + unsigned long t3; + unsigned long t4; + unsigned long t5; + unsigned long t6; +#endif }; }; }; @@ -221,10 +226,13 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); #define ftrace_graph_func ftrace_graph_func +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr) { arch_ftrace_regs(fregs)->t1 = addr; } +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + #endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ #endif /* __ASSEMBLY__ */ diff --git a/arch/riscv/include/asm/image.h b/arch/riscv/include/asm/image.h index e0b319af3681..8927a6ea1127 100644 --- a/arch/riscv/include/asm/image.h +++ b/arch/riscv/include/asm/image.h @@ -30,6 +30,8 @@ RISCV_HEADER_VERSION_MINOR) #ifndef __ASSEMBLY__ +#define riscv_image_flag_field(flags, field)\ + (((flags) >> field##_SHIFT) & field##_MASK) /** * struct riscv_image_header - riscv kernel image header * @code0: Executable code diff --git a/arch/riscv/include/asm/kexec.h b/arch/riscv/include/asm/kexec.h index 2b56769cb530..b9ee8346cc8c 100644 --- a/arch/riscv/include/asm/kexec.h +++ b/arch/riscv/include/asm/kexec.h @@ -56,6 +56,7 @@ extern riscv_kexec_method riscv_kexec_norelocate; #ifdef CONFIG_KEXEC_FILE extern const struct kexec_file_ops elf_kexec_ops; +extern const struct kexec_file_ops image_kexec_ops; struct purgatory_info; int arch_kexec_apply_relocations_add(struct purgatory_info *pi, @@ -67,6 +68,11 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, struct kimage; int arch_kimage_file_post_load_cleanup(struct kimage *image); #define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup + +int load_extra_segments(struct kimage *image, unsigned long kernel_start, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len); #endif #endif diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index 0897dd99ab8d..a2c00235c447 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -184,7 +184,7 @@ static inline int pud_none(pud_t pud) static inline int pud_bad(pud_t pud) { - return !pud_present(pud); + return !pud_present(pud) || (pud_val(pud) & _PAGE_LEAF); } #define pud_leaf pud_leaf @@ -401,6 +401,7 @@ p4d_t *p4d_offset(pgd_t *pgd, unsigned long address); #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pte_devmap(pte_t pte); static inline pte_t pmd_pte(pmd_t pmd); +static inline pte_t pud_pte(pud_t pud); static inline int pmd_devmap(pmd_t pmd) { @@ -409,7 +410,7 @@ static inline int pmd_devmap(pmd_t pmd) static inline int pud_devmap(pud_t pud) { - return 0; + return pte_devmap(pud_pte(pud)); } static inline int pgd_devmap(pgd_t pgd) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 428e48e5f57d..b84e2ff83cb7 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -902,6 +902,103 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, #define pmdp_collapse_flush pmdp_collapse_flush extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); + +static inline pud_t pud_wrprotect(pud_t pud) +{ + return pte_pud(pte_wrprotect(pud_pte(pud))); +} + +static inline int pud_trans_huge(pud_t pud) +{ + return pud_leaf(pud); +} + +static inline int pud_dirty(pud_t pud) +{ + return pte_dirty(pud_pte(pud)); +} + +static inline pud_t pud_mkyoung(pud_t pud) +{ + return pte_pud(pte_mkyoung(pud_pte(pud))); +} + +static inline pud_t pud_mkold(pud_t pud) +{ + return pte_pud(pte_mkold(pud_pte(pud))); +} + +static inline pud_t pud_mkdirty(pud_t pud) +{ + return pte_pud(pte_mkdirty(pud_pte(pud))); +} + +static inline pud_t pud_mkclean(pud_t pud) +{ + return pte_pud(pte_mkclean(pud_pte(pud))); +} + +static inline pud_t pud_mkwrite(pud_t pud) +{ + return pte_pud(pte_mkwrite_novma(pud_pte(pud))); +} + +static inline pud_t pud_mkhuge(pud_t pud) +{ + return pud; +} + +static inline pud_t pud_mkdevmap(pud_t pud) +{ + return pte_pud(pte_mkdevmap(pud_pte(pud))); +} + +static inline int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty) +{ + return ptep_set_access_flags(vma, address, (pte_t *)pudp, pud_pte(entry), dirty); +} + +static inline int pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp) +{ + return ptep_test_and_clear_young(vma, address, (pte_t *)pudp); +} + +static inline int pud_young(pud_t pud) +{ + return pte_young(pud_pte(pud)); +} + +static inline void update_mmu_cache_pud(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp) +{ + pte_t *ptep = (pte_t *)pudp; + + update_mmu_cache(vma, address, ptep); +} + +static inline pud_t pudp_establish(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, pud_t pud) +{ + page_table_check_pud_set(vma->vm_mm, pudp, pud); + return __pud(atomic_long_xchg((atomic_long_t *)pudp, pud_val(pud))); +} + +static inline pud_t pud_mkinvalid(pud_t pud) +{ + return __pud(pud_val(pud) & ~(_PAGE_PRESENT | _PAGE_PROT_NONE)); +} + +extern pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp); + +static inline pud_t pud_modify(pud_t pud, pgprot_t newprot) +{ + return pte_pud(pte_modify(pud_pte(pud), newprot)); +} + #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 39dfab495a4c..e12c14fea340 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -81,6 +81,10 @@ struct pt_regs; * Thus, the task does not own preempt_v. Any use of Vector will have to * save preempt_v, if dirty, and fallback to non-preemptible kernel-mode * Vector. + * - bit 29: The thread voluntarily calls schedule() while holding an active + * preempt_v. All preempt_v context should be dropped in such case because + * V-regs are caller-saved. Only sstatus.VS=ON is persisted across a + * schedule() call. * - bit 30: The in-kernel preempt_v context is saved, and requries to be * restored when returning to the context that owns the preempt_v. * - bit 31: The in-kernel preempt_v context is dirty, as signaled by the @@ -95,6 +99,7 @@ struct pt_regs; #define RISCV_PREEMPT_V 0x00000100 #define RISCV_PREEMPT_V_DIRTY 0x80000000 #define RISCV_PREEMPT_V_NEED_RESTORE 0x40000000 +#define RISCV_PREEMPT_V_IN_SCHEDULE 0x20000000 /* CPU-specific state of a task */ struct thread_struct { diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h index 2910231977cb..a7dc0e330757 100644 --- a/arch/riscv/include/asm/ptrace.h +++ b/arch/riscv/include/asm/ptrace.h @@ -175,7 +175,7 @@ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, return 0; } -static inline int regs_irqs_disabled(struct pt_regs *regs) +static __always_inline bool regs_irqs_disabled(struct pt_regs *regs) { return !(regs->status & SR_PIE); } diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h index ce0dd0fed764..1a20dd746a49 100644 --- a/arch/riscv/include/asm/tlbflush.h +++ b/arch/riscv/include/asm/tlbflush.h @@ -56,6 +56,8 @@ void local_flush_tlb_kernel_range(unsigned long start, unsigned long end); #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); +void flush_pud_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); #endif bool arch_tlbbatch_should_defer(struct mm_struct *mm); diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h index e8a83f55be2b..45c9b426fcc5 100644 --- a/arch/riscv/include/asm/vector.h +++ b/arch/riscv/include/asm/vector.h @@ -120,6 +120,11 @@ static __always_inline void riscv_v_disable(void) csr_clear(CSR_SSTATUS, SR_VS); } +static __always_inline bool riscv_v_is_on(void) +{ + return !!(csr_read(CSR_SSTATUS) & SR_VS); +} + static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) { asm volatile ( @@ -366,6 +371,11 @@ static inline void __switch_to_vector(struct task_struct *prev, struct pt_regs *regs; if (riscv_preempt_v_started(prev)) { + if (riscv_v_is_on()) { + WARN_ON(prev->thread.riscv_v_flags & RISCV_V_CTX_DEPTH_MASK); + riscv_v_disable(); + prev->thread.riscv_v_flags |= RISCV_PREEMPT_V_IN_SCHEDULE; + } if (riscv_preempt_v_dirty(prev)) { __riscv_v_vstate_save(&prev->thread.kernel_vstate, prev->thread.kernel_vstate.datap); @@ -376,10 +386,16 @@ static inline void __switch_to_vector(struct task_struct *prev, riscv_v_vstate_save(&prev->thread.vstate, regs); } - if (riscv_preempt_v_started(next)) - riscv_preempt_v_set_restore(next); - else + if (riscv_preempt_v_started(next)) { + if (next->thread.riscv_v_flags & RISCV_PREEMPT_V_IN_SCHEDULE) { + next->thread.riscv_v_flags &= ~RISCV_PREEMPT_V_IN_SCHEDULE; + riscv_v_enable(); + } else { + riscv_preempt_v_set_restore(next); + } + } else { riscv_v_vstate_set_restore(next, task_pt_regs(next)); + } } void riscv_v_vstate_ctrl_init(struct task_struct *tsk); diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index 3c2fce939673..fca15f2bf6f3 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -81,6 +81,7 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_EXT_ZICBOM (1ULL << 55) #define RISCV_HWPROBE_EXT_ZAAMO (1ULL << 56) #define RISCV_HWPROBE_EXT_ZALRSC (1ULL << 57) +#define RISCV_HWPROBE_EXT_ZABHA (1ULL << 58) #define RISCV_HWPROBE_KEY_CPUPERF_0 5 #define RISCV_HWPROBE_MISALIGNED_UNKNOWN (0 << 0) #define RISCV_HWPROBE_MISALIGNED_EMULATED (1 << 0) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 8d186bfced45..0ead29826419 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -107,7 +107,7 @@ obj-$(CONFIG_HOTPLUG_CPU) += cpu-hotplug.o obj-$(CONFIG_PARAVIRT) += paravirt.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_KEXEC_CORE) += kexec_relocate.o crash_save_regs.o machine_kexec.o -obj-$(CONFIG_KEXEC_FILE) += elf_kexec.o machine_kexec_file.o +obj-$(CONFIG_KEXEC_FILE) += kexec_elf.o kexec_image.o machine_kexec_file.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index 16490755304e..b26334075697 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -493,6 +493,12 @@ void asm_offsets(void) DEFINE(STACKFRAME_SIZE_ON_STACK, ALIGN(sizeof(struct stackframe), STACK_ALIGN)); OFFSET(STACKFRAME_FP, stackframe, fp); OFFSET(STACKFRAME_RA, stackframe, ra); +#ifdef CONFIG_FUNCTION_TRACER + DEFINE(FTRACE_OPS_FUNC, offsetof(struct ftrace_ops, func)); +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + DEFINE(FTRACE_OPS_DIRECT_CALL, offsetof(struct ftrace_ops, direct_call)); +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ +#endif #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS DEFINE(FREGS_SIZE_ON_STACK, ALIGN(sizeof(struct __arch_ftrace_regs), STACK_ALIGN)); @@ -501,6 +507,13 @@ void asm_offsets(void) DEFINE(FREGS_SP, offsetof(struct __arch_ftrace_regs, sp)); DEFINE(FREGS_S0, offsetof(struct __arch_ftrace_regs, s0)); DEFINE(FREGS_T1, offsetof(struct __arch_ftrace_regs, t1)); +#ifdef CONFIG_CC_IS_CLANG + DEFINE(FREGS_T2, offsetof(struct __arch_ftrace_regs, t2)); + DEFINE(FREGS_T3, offsetof(struct __arch_ftrace_regs, t3)); + DEFINE(FREGS_T4, offsetof(struct __arch_ftrace_regs, t4)); + DEFINE(FREGS_T5, offsetof(struct __arch_ftrace_regs, t5)); + DEFINE(FREGS_T6, offsetof(struct __arch_ftrace_regs, t6)); +#endif DEFINE(FREGS_A0, offsetof(struct __arch_ftrace_regs, a0)); DEFINE(FREGS_A1, offsetof(struct __arch_ftrace_regs, a1)); DEFINE(FREGS_A2, offsetof(struct __arch_ftrace_regs, a2)); diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c deleted file mode 100644 index 0dc5450f2c7f..000000000000 --- a/arch/riscv/kernel/elf_kexec.c +++ /dev/null @@ -1,485 +0,0 @@ -// 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 <linux/vmalloc.h> -#include <asm/setup.h> - -int arch_kimage_file_post_load_cleanup(struct kimage *image) -{ - kvfree(image->arch.fdt); - image->arch.fdt = NULL; - - vfree(image->elf_headers); - image->elf_headers = NULL; - image->elf_headers_sz = 0; - - return kexec_image_post_load_cleanup_default(image); -} - -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; - - /* - * Current riscv boot protocol requires 2MB alignment for - * RV64 and 4MB alignment for RV32 - * - */ - kbuf.buf_align = PMD_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; -} - -#ifdef CONFIG_CRASH_DUMP -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; -} -#endif - -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; - void *fdt; - unsigned long old_kernel_pbase = ULONG_MAX; - unsigned long new_kernel_pbase = 0UL; - unsigned long initrd_pbase = 0UL; - unsigned long kernel_start; - 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; - - /* 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; - -#ifdef CONFIG_CRASH_DUMP - /* Add elfcorehdr */ - if (image->type == KEXEC_TYPE_CRASH) { - void *headers; - unsigned long headers_sz; - 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; - - kexec_dprintk("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; - } -#endif - -#ifdef CONFIG_ARCH_SUPPORTS_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; - } - kexec_dprintk("Loaded purgatory at 0x%lx\n", kbuf.mem); - - 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_SUPPORTS_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 = true; - kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; - ret = kexec_add_buffer(&kbuf); - if (ret) - goto out; - initrd_pbase = kbuf.mem; - kexec_dprintk("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; - } - /* Cache the fdt buffer address for memory cleanup */ - image->arch.fdt = fdt; - kexec_dprintk("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; - Elf64_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 section base address */ - 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_PLT: - 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_ADD16: - *(u16 *)loc += val; - break; - case R_RISCV_SUB16: - *(u16 *)loc -= val; - 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; - case R_RISCV_64: - *(u64 *)loc = val; - 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/ftrace.c b/arch/riscv/kernel/ftrace.c index 674dcdfae7a1..4c6c24380cfd 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -8,98 +8,129 @@ #include <linux/ftrace.h> #include <linux/uaccess.h> #include <linux/memory.h> +#include <linux/irqflags.h> #include <linux/stop_machine.h> #include <asm/cacheflush.h> #include <asm/text-patching.h> #ifdef CONFIG_DYNAMIC_FTRACE -void ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) +unsigned long ftrace_call_adjust(unsigned long addr) { - mutex_lock(&text_mutex); + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + return addr + 8 + MCOUNT_AUIPC_SIZE; - /* - * The code sequences we use for ftrace can't be patched while the - * kernel is running, so we need to use stop_machine() to modify them - * for now. This doesn't play nice with text_mutex, we use this flag - * to elide the check. - */ - riscv_patch_in_stop_machine = true; + return addr + MCOUNT_AUIPC_SIZE; +} + +unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip) +{ + return fentry_ip - MCOUNT_AUIPC_SIZE; } -void ftrace_arch_code_modify_post_process(void) __releases(&text_mutex) +void arch_ftrace_update_code(int command) { - riscv_patch_in_stop_machine = false; + mutex_lock(&text_mutex); + command |= FTRACE_MAY_SLEEP; + ftrace_modify_all_code(command); mutex_unlock(&text_mutex); + flush_icache_all(); } -static int ftrace_check_current_call(unsigned long hook_pos, - unsigned int *expected) +static int __ftrace_modify_call(unsigned long source, unsigned long target, bool validate) { + unsigned int call[2], offset; unsigned int replaced[2]; - unsigned int nops[2] = {RISCV_INSN_NOP4, RISCV_INSN_NOP4}; - /* we expect nops at the hook position */ - if (!expected) - expected = nops; + offset = target - source; + call[1] = to_jalr_t0(offset); - /* - * Read the text we want to modify; - * return must be -EFAULT on read error - */ - if (copy_from_kernel_nofault(replaced, (void *)hook_pos, - MCOUNT_INSN_SIZE)) - return -EFAULT; - - /* - * Make sure it is what we expect it to be; - * return must be -EINVAL on failed comparison - */ - if (memcmp(expected, replaced, sizeof(replaced))) { - pr_err("%p: expected (%08x %08x) but got (%08x %08x)\n", - (void *)hook_pos, expected[0], expected[1], replaced[0], - replaced[1]); - return -EINVAL; + if (validate) { + call[0] = to_auipc_t0(offset); + /* + * Read the text we want to modify; + * return must be -EFAULT on read error + */ + if (copy_from_kernel_nofault(replaced, (void *)source, 2 * MCOUNT_INSN_SIZE)) + return -EFAULT; + + if (replaced[0] != call[0]) { + pr_err("%p: expected (%08x) but got (%08x)\n", + (void *)source, call[0], replaced[0]); + return -EINVAL; + } } + /* Replace the jalr at once. Return -EPERM on write error. */ + if (patch_insn_write((void *)(source + MCOUNT_AUIPC_SIZE), call + 1, MCOUNT_JALR_SIZE)) + return -EPERM; + return 0; } -static int __ftrace_modify_call(unsigned long hook_pos, unsigned long target, - bool enable, bool ra) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS +static const struct ftrace_ops *riscv64_rec_get_ops(struct dyn_ftrace *rec) { - unsigned int call[2]; - unsigned int nops[2] = {RISCV_INSN_NOP4, RISCV_INSN_NOP4}; + const struct ftrace_ops *ops = NULL; - if (ra) - make_call_ra(hook_pos, target, call); - else - make_call_t0(hook_pos, target, call); + if (rec->flags & FTRACE_FL_CALL_OPS_EN) { + ops = ftrace_find_unique_ops(rec); + WARN_ON_ONCE(!ops); + } - /* Replace the auipc-jalr pair at once. Return -EPERM on write error. */ - if (patch_insn_write((void *)hook_pos, enable ? call : nops, MCOUNT_INSN_SIZE)) - return -EPERM; + if (!ops) + ops = &ftrace_list_ops; - return 0; + return ops; +} + +static int ftrace_rec_set_ops(const struct dyn_ftrace *rec, const struct ftrace_ops *ops) +{ + unsigned long literal = ALIGN_DOWN(rec->ip - 12, 8); + + return patch_text_nosync((void *)literal, &ops, sizeof(ops)); +} + +static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) +{ + return ftrace_rec_set_ops(rec, &ftrace_nop_ops); +} + +static int ftrace_rec_update_ops(struct dyn_ftrace *rec) +{ + return ftrace_rec_set_ops(rec, riscv64_rec_get_ops(rec)); } +#else +static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) { return 0; } +static int ftrace_rec_update_ops(struct dyn_ftrace *rec) { return 0; } +#endif int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - unsigned int call[2]; + unsigned long distance, orig_addr, pc = rec->ip - MCOUNT_AUIPC_SIZE; + int ret; - make_call_t0(rec->ip, addr, call); + ret = ftrace_rec_update_ops(rec); + if (ret) + return ret; - if (patch_insn_write((void *)rec->ip, call, MCOUNT_INSN_SIZE)) - return -EPERM; + orig_addr = (unsigned long)&ftrace_caller; + distance = addr > orig_addr ? addr - orig_addr : orig_addr - addr; + if (distance > JALR_RANGE) + addr = FTRACE_ADDR; - return 0; + return __ftrace_modify_call(pc, addr, false); } -int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, - unsigned long addr) +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned int nops[2] = {RISCV_INSN_NOP4, RISCV_INSN_NOP4}; + u32 nop4 = RISCV_INSN_NOP4; + int ret; - if (patch_insn_write((void *)rec->ip, nops, MCOUNT_INSN_SIZE)) + ret = ftrace_rec_set_nop_ops(rec); + if (ret) + return ret; + + if (patch_insn_write((void *)rec->ip, &nop4, MCOUNT_NOP4_SIZE)) return -EPERM; return 0; @@ -114,75 +145,71 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, */ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) { - int out; + unsigned long pc = rec->ip - MCOUNT_AUIPC_SIZE; + unsigned int nops[2], offset; + int ret; - mutex_lock(&text_mutex); - out = ftrace_make_nop(mod, rec, MCOUNT_ADDR); - mutex_unlock(&text_mutex); + ret = ftrace_rec_set_nop_ops(rec); + if (ret) + return ret; - return out; -} + offset = (unsigned long) &ftrace_caller - pc; + nops[0] = to_auipc_t0(offset); + nops[1] = RISCV_INSN_NOP4; -int ftrace_update_ftrace_func(ftrace_func_t func) -{ - int ret = __ftrace_modify_call((unsigned long)&ftrace_call, - (unsigned long)func, true, true); + mutex_lock(&text_mutex); + ret = patch_insn_write((void *)pc, nops, 2 * MCOUNT_INSN_SIZE); + mutex_unlock(&text_mutex); return ret; } -struct ftrace_modify_param { - int command; - atomic_t cpu_count; -}; - -static int __ftrace_modify_code(void *data) +ftrace_func_t ftrace_call_dest = ftrace_stub; +int ftrace_update_ftrace_func(ftrace_func_t func) { - struct ftrace_modify_param *param = data; - - if (atomic_inc_return(¶m->cpu_count) == num_online_cpus()) { - ftrace_modify_all_code(param->command); - /* - * Make sure the patching store is effective *before* we - * increment the counter which releases all waiting CPUs - * by using the release variant of atomic increment. The - * release pairs with the call to local_flush_icache_all() - * on the waiting CPU. - */ - atomic_inc_return_release(¶m->cpu_count); - } else { - while (atomic_read(¶m->cpu_count) <= num_online_cpus()) - cpu_relax(); - - local_flush_icache_all(); - } + /* + * When using CALL_OPS, the function to call is associated with the + * call site, and we don't have a global function pointer to update. + */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + return 0; + WRITE_ONCE(ftrace_call_dest, func); + /* + * The data fence ensure that the update to ftrace_call_dest happens + * before the write to function_trace_op later in the generic ftrace. + * If the sequence is not enforced, then an old ftrace_call_dest may + * race loading a new function_trace_op set in ftrace_modify_all_code + */ + smp_wmb(); + /* + * Updating ftrace dpes not take stop_machine path, so irqs should not + * be disabled. + */ + WARN_ON(irqs_disabled()); + smp_call_function(ftrace_sync_ipi, NULL, 1); return 0; } -void arch_ftrace_update_code(int command) +#else /* CONFIG_DYNAMIC_FTRACE */ +unsigned long ftrace_call_adjust(unsigned long addr) { - struct ftrace_modify_param param = { command, ATOMIC_INIT(0) }; - - stop_machine(__ftrace_modify_code, ¶m, cpu_online_mask); + return addr; } -#endif +#endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { - unsigned int call[2]; - unsigned long caller = rec->ip; + unsigned long caller = rec->ip - MCOUNT_AUIPC_SIZE; int ret; - make_call_t0(caller, old_addr, call); - ret = ftrace_check_current_call(caller, call); - + ret = ftrace_rec_update_ops(rec); if (ret) return ret; - return __ftrace_modify_call(caller, addr, true, false); + return __ftrace_modify_call(caller, FTRACE_ADDR, true); } #endif @@ -210,7 +237,6 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, } #ifdef CONFIG_DYNAMIC_FTRACE -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { @@ -231,19 +257,5 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, if (!function_graph_enter_regs(old, ip, frame_pointer, parent, fregs)) *parent = return_hooker; } -#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ -extern void ftrace_graph_call(void); -int ftrace_enable_ftrace_graph_caller(void) -{ - return __ftrace_modify_call((unsigned long)&ftrace_graph_call, - (unsigned long)&prepare_ftrace_return, true, true); -} - -int ftrace_disable_ftrace_graph_caller(void) -{ - return __ftrace_modify_call((unsigned long)&ftrace_graph_call, - (unsigned long)&prepare_ftrace_return, false, true); -} -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/riscv/kernel/kexec_elf.c b/arch/riscv/kernel/kexec_elf.c new file mode 100644 index 000000000000..f4755d49b89e --- /dev/null +++ b/arch/riscv/kernel/kexec_elf.c @@ -0,0 +1,144 @@ +// 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; + + /* + * Current riscv boot protocol requires 2MB alignment for + * RV64 and 4MB alignment for RV32 + * + */ + kbuf.buf_align = PMD_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 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; + struct elfhdr ehdr; + struct kexec_elf_info elf_info; + + 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; + + /* 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; + + ret = load_extra_segments(image, image->start, kernel_len, + initrd, initrd_len, cmdline, cmdline_len); +out: + kexec_free_elf_info(&elf_info); + return ret ? ERR_PTR(ret) : NULL; +} + +const struct kexec_file_ops elf_kexec_ops = { + .probe = kexec_elf_probe, + .load = elf_kexec_load, +}; diff --git a/arch/riscv/kernel/kexec_image.c b/arch/riscv/kernel/kexec_image.c new file mode 100644 index 000000000000..26a81774a78a --- /dev/null +++ b/arch/riscv/kernel/kexec_image.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RISC-V Kexec image loader + * + */ + +#define pr_fmt(fmt) "kexec_file(Image): " fmt + +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/pe.h> +#include <linux/string.h> +#include <asm/byteorder.h> +#include <asm/image.h> + +static int image_probe(const char *kernel_buf, unsigned long kernel_len) +{ + const struct riscv_image_header *h = (const struct riscv_image_header *)kernel_buf; + + if (!h || kernel_len < sizeof(*h)) + return -EINVAL; + + /* According to Documentation/riscv/boot-image-header.rst, + * use "magic2" field to check when version >= 0.2. + */ + + if (h->version >= RISCV_HEADER_VERSION && + memcmp(&h->magic2, RISCV_IMAGE_MAGIC2, sizeof(h->magic2))) + return -EINVAL; + + return 0; +} + +static void *image_load(struct kimage *image, + char *kernel, unsigned long kernel_len, + char *initrd, unsigned long initrd_len, + char *cmdline, unsigned long cmdline_len) +{ + struct riscv_image_header *h; + u64 flags; + bool be_image, be_kernel; + struct kexec_buf kbuf; + int ret; + + /* Check Image header */ + h = (struct riscv_image_header *)kernel; + if (!h->image_size) { + ret = -EINVAL; + goto out; + } + + /* Check endianness */ + flags = le64_to_cpu(h->flags); + be_image = riscv_image_flag_field(flags, RISCV_IMAGE_FLAG_BE); + be_kernel = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); + if (be_image != be_kernel) { + ret = -EINVAL; + goto out; + } + + /* Load the kernel image */ + kbuf.image = image; + kbuf.buf_min = 0; + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = false; + + kbuf.buffer = kernel; + kbuf.bufsz = kernel_len; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = le64_to_cpu(h->image_size); + kbuf.buf_align = le64_to_cpu(h->text_offset); + + ret = kexec_add_buffer(&kbuf); + if (ret) { + pr_err("Error add kernel image ret=%d\n", ret); + goto out; + } + + image->start = kbuf.mem; + + pr_info("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kbuf.mem, kbuf.bufsz, kbuf.memsz); + + ret = load_extra_segments(image, kbuf.mem, kbuf.memsz, + initrd, initrd_len, cmdline, cmdline_len); + +out: + return ret ? ERR_PTR(ret) : NULL; +} + +const struct kexec_file_ops image_kexec_ops = { + .probe = image_probe, + .load = image_load, +}; diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c index b0bf8c1722c0..e36104af2e24 100644 --- a/arch/riscv/kernel/machine_kexec_file.c +++ b/arch/riscv/kernel/machine_kexec_file.c @@ -7,8 +7,369 @@ * Author: Liao Chang (liaochang1@huawei.com) */ #include <linux/kexec.h> +#include <linux/elf.h> +#include <linux/slab.h> +#include <linux/of.h> +#include <linux/libfdt.h> +#include <linux/types.h> +#include <linux/memblock.h> +#include <linux/vmalloc.h> +#include <asm/setup.h> const struct kexec_file_ops * const kexec_file_loaders[] = { &elf_kexec_ops, + &image_kexec_ops, NULL }; + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + kvfree(image->arch.fdt); + image->arch.fdt = NULL; + + vfree(image->elf_headers); + image->elf_headers = NULL; + image->elf_headers_sz = 0; + + return kexec_image_post_load_cleanup_default(image); +} + +#ifdef CONFIG_CRASH_DUMP +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; +} +#endif + +#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; + Elf64_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_PLT: + 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_ADD16: + *(u16 *)loc += val; + break; + case R_RISCV_SUB16: + *(u16 *)loc -= val; + 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; + case R_RISCV_64: + *(u64 *)loc = val; + break; + default: + pr_err("Unknown rela relocation: %d\n", r_type); + return -ENOEXEC; + } + } + return 0; +} + + +int load_extra_segments(struct kimage *image, unsigned long kernel_start, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len) +{ + int ret; + void *fdt; + unsigned long initrd_pbase = 0UL; + struct kexec_buf kbuf; + char *modified_cmdline = NULL; + + kbuf.image = image; + kbuf.buf_min = kernel_start + kernel_len; + kbuf.buf_max = ULONG_MAX; + +#ifdef CONFIG_CRASH_DUMP + /* Add elfcorehdr */ + if (image->type == KEXEC_TYPE_CRASH) { + void *headers; + unsigned long headers_sz; + 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; + + kexec_dprintk("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; + } +#endif + +#ifdef CONFIG_ARCH_SUPPORTS_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; + } + kexec_dprintk("Loaded purgatory at 0x%lx\n", kbuf.mem); + + 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_SUPPORTS_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 = true; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out; + initrd_pbase = kbuf.mem; + kexec_dprintk("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; + } + /* Cache the fdt buffer address for memory cleanup */ + image->arch.fdt = fdt; + kexec_dprintk("Loaded device tree at 0x%lx\n", kbuf.mem); + goto out; + +out_free_fdt: + kvfree(fdt); +out: + kfree(modified_cmdline); + return ret; +} diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S index 745dd4c4a69c..48f6c4f7dca0 100644 --- a/arch/riscv/kernel/mcount-dyn.S +++ b/arch/riscv/kernel/mcount-dyn.S @@ -13,7 +13,6 @@ .text -#define FENTRY_RA_OFFSET 8 #define ABI_SIZE_ON_STACK 80 #define ABI_A0 0 #define ABI_A1 8 @@ -56,16 +55,13 @@ addi sp, sp, ABI_SIZE_ON_STACK .endm -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS - /** * SAVE_ABI_REGS - save regs against the ftrace_regs struct * * After the stack is established, * * 0(sp) stores the PC of the traced function which can be accessed -* by &(fregs)->epc in tracing function. Note that the real -* function entry address should be computed with -FENTRY_RA_OFFSET. +* by &(fregs)->epc in tracing function. * * 8(sp) stores the function return address (i.e. parent IP) that * can be accessed by &(fregs)->ra in tracing function. @@ -86,17 +82,20 @@ * +++++++++ **/ .macro SAVE_ABI_REGS - mv t4, sp // Save original SP in T4 addi sp, sp, -FREGS_SIZE_ON_STACK - REG_S t0, FREGS_EPC(sp) REG_S x1, FREGS_RA(sp) - REG_S t4, FREGS_SP(sp) // Put original SP on stack #ifdef HAVE_FUNCTION_GRAPH_FP_TEST REG_S x8, FREGS_S0(sp) #endif REG_S x6, FREGS_T1(sp) - +#ifdef CONFIG_CC_IS_CLANG + REG_S x7, FREGS_T2(sp) + REG_S x28, FREGS_T3(sp) + REG_S x29, FREGS_T4(sp) + REG_S x30, FREGS_T5(sp) + REG_S x31, FREGS_T6(sp) +#endif // save the arguments REG_S x10, FREGS_A0(sp) REG_S x11, FREGS_A1(sp) @@ -106,16 +105,25 @@ REG_S x15, FREGS_A5(sp) REG_S x16, FREGS_A6(sp) REG_S x17, FREGS_A7(sp) + mv a0, sp + addi a0, a0, FREGS_SIZE_ON_STACK + REG_S a0, FREGS_SP(sp) // Put original SP on stack .endm - .macro RESTORE_ABI_REGS, all=0 + .macro RESTORE_ABI_REGS REG_L t0, FREGS_EPC(sp) REG_L x1, FREGS_RA(sp) #ifdef HAVE_FUNCTION_GRAPH_FP_TEST REG_L x8, FREGS_S0(sp) #endif REG_L x6, FREGS_T1(sp) - +#ifdef CONFIG_CC_IS_CLANG + REG_L x7, FREGS_T2(sp) + REG_L x28, FREGS_T3(sp) + REG_L x29, FREGS_T4(sp) + REG_L x30, FREGS_T5(sp) + REG_L x31, FREGS_T6(sp) +#endif // restore the arguments REG_L x10, FREGS_A0(sp) REG_L x11, FREGS_A1(sp) @@ -130,60 +138,71 @@ .endm .macro PREPARE_ARGS - addi a0, t0, -FENTRY_RA_OFFSET + addi a0, t0, -MCOUNT_JALR_SIZE // ip (callsite's jalr insn) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + mv a1, ra // parent_ip + REG_L a2, -16(t0) // op + REG_L ra, FTRACE_OPS_FUNC(a2) // op->func +#else la a1, function_trace_op - REG_L a2, 0(a1) - mv a1, ra - mv a3, sp + REG_L a2, 0(a1) // op + mv a1, ra // parent_ip +#endif + mv a3, sp // regs .endm -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ - -#ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS SYM_FUNC_START(ftrace_caller) - SAVE_ABI - - addi a0, t0, -FENTRY_RA_OFFSET - la a1, function_trace_op - REG_L a2, 0(a1) - mv a1, ra - mv a3, sp +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + /* + * When CALL_OPS is enabled (2 or 4) nops [8B] are placed before the + * function entry, these are later overwritten with the pointer to the + * associated struct ftrace_ops. + * + * -8: &ftrace_ops of the associated tracer function. + *<ftrace enable>: + * 0: auipc t0/ra, 0x? + * 4: jalr t0/ra, ?(t0/ra) + * + * -8: &ftrace_nop_ops + *<ftrace disable>: + * 0: nop + * 4: nop + * + * t0 is set to ip+8 after the jalr is executed at the callsite, + * so we find the associated op at t0-16. + */ + REG_L t1, -16(t0) // op Should be SZ_REG instead of 16 -SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) - call ftrace_stub - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - addi a0, sp, ABI_RA - REG_L a1, ABI_T0(sp) - addi a1, a1, -FENTRY_RA_OFFSET -#ifdef HAVE_FUNCTION_GRAPH_FP_TEST - mv a2, s0 +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + /* + * If the op has a direct call, handle it immediately without + * saving/restoring registers. + */ + REG_L t1, FTRACE_OPS_DIRECT_CALL(t1) + bnez t1, ftrace_caller_direct #endif -SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) - call ftrace_stub #endif - RESTORE_ABI - jr t0 -SYM_FUNC_END(ftrace_caller) - -#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ -SYM_FUNC_START(ftrace_caller) - mv t1, zero SAVE_ABI_REGS PREPARE_ARGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + jalr ra +#else SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) - call ftrace_stub - + REG_L ra, ftrace_call_dest + jalr ra, 0(ra) +#endif RESTORE_ABI_REGS - bnez t1, .Ldirect +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + bnez t1, ftrace_caller_direct +#endif jr t0 -.Ldirect: +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_INNER_LABEL(ftrace_caller_direct, SYM_L_LOCAL) jr t1 +#endif SYM_FUNC_END(ftrace_caller) -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ - #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS SYM_CODE_START(ftrace_stub_direct_tramp) jr t0 diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c index 91d0b355ceef..75551ac6504c 100644 --- a/arch/riscv/kernel/module-sections.c +++ b/arch/riscv/kernel/module-sections.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/moduleloader.h> +#include <linux/sort.h> unsigned long module_emit_got_entry(struct module *mod, unsigned long val) { @@ -55,44 +56,70 @@ unsigned long module_emit_plt_entry(struct module *mod, unsigned long val) return (unsigned long)&plt[i]; } -static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y) +#define cmp_3way(a, b) ((a) < (b) ? -1 : (a) > (b)) + +static int cmp_rela(const void *a, const void *b) { - return x->r_info == y->r_info && x->r_addend == y->r_addend; + const Elf_Rela *x = a, *y = b; + int i; + + /* sort by type, symbol index and addend */ + i = cmp_3way(x->r_info, y->r_info); + if (i == 0) + i = cmp_3way(x->r_addend, y->r_addend); + return i; } static bool duplicate_rela(const Elf_Rela *rela, int idx) { - int i; - for (i = 0; i < idx; i++) { - if (is_rela_equal(&rela[i], &rela[idx])) - return true; - } - return false; + /* + * Entries are sorted by type, symbol index and addend. That means + * that, if a duplicate entry exists, it must be in the preceding slot. + */ + return idx > 0 && cmp_rela(rela + idx, rela + idx - 1) == 0; } -static void count_max_entries(Elf_Rela *relas, int num, +static void count_max_entries(const Elf_Rela *relas, size_t num, unsigned int *plts, unsigned int *gots) { - for (int i = 0; i < num; i++) { + for (size_t i = 0; i < num; i++) { + if (duplicate_rela(relas, i)) + continue; + switch (ELF_R_TYPE(relas[i].r_info)) { case R_RISCV_CALL_PLT: case R_RISCV_PLT32: - if (!duplicate_rela(relas, i)) - (*plts)++; + (*plts)++; break; case R_RISCV_GOT_HI20: - if (!duplicate_rela(relas, i)) - (*gots)++; + (*gots)++; break; + default: + unreachable(); } } } +static bool rela_needs_plt_got_entry(const Elf_Rela *rela) +{ + switch (ELF_R_TYPE(rela->r_info)) { + case R_RISCV_CALL_PLT: + case R_RISCV_GOT_HI20: + case R_RISCV_PLT32: + return true; + default: + return false; + } +} + int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings, struct module *mod) { + size_t num_scratch_relas = 0; unsigned int num_plts = 0; unsigned int num_gots = 0; + Elf_Rela *scratch = NULL; + size_t scratch_size = 0; int i; /* @@ -122,9 +149,10 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, /* Calculate the maxinum number of entries */ for (i = 0; i < ehdr->e_shnum; i++) { + size_t num_relas = sechdrs[i].sh_size / sizeof(Elf_Rela); Elf_Rela *relas = (void *)ehdr + sechdrs[i].sh_offset; - int num_rela = sechdrs[i].sh_size / sizeof(Elf_Rela); Elf_Shdr *dst_sec = sechdrs + sechdrs[i].sh_info; + size_t scratch_size_needed; if (sechdrs[i].sh_type != SHT_RELA) continue; @@ -133,7 +161,28 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, if (!(dst_sec->sh_flags & SHF_EXECINSTR)) continue; - count_max_entries(relas, num_rela, &num_plts, &num_gots); + /* + * apply_relocate_add() relies on HI20 and LO12 relocation pairs being + * close together, so sort a copy of the section to avoid interfering. + */ + scratch_size_needed = (num_scratch_relas + num_relas) * sizeof(*scratch); + if (scratch_size_needed > scratch_size) { + scratch_size = scratch_size_needed; + scratch = kvrealloc(scratch, scratch_size, GFP_KERNEL); + if (!scratch) + return -ENOMEM; + } + + for (size_t j = 0; j < num_relas; j++) + if (rela_needs_plt_got_entry(&relas[j])) + scratch[num_scratch_relas++] = relas[j]; + } + + if (scratch) { + /* sort the accumulated PLT/GOT relocations so duplicates are adjacent */ + sort(scratch, num_scratch_relas, sizeof(*scratch), cmp_rela, NULL); + count_max_entries(scratch, num_scratch_relas, &num_plts, &num_gots); + kvfree(scratch); } mod->arch.plt.shdr->sh_type = SHT_NOBITS; diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index 249aec8594a9..ed3123396a96 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -96,6 +96,7 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair, * presence in the hart_isa bitmap, are made. */ EXT_KEY(ZAAMO); + EXT_KEY(ZABHA); EXT_KEY(ZACAS); EXT_KEY(ZALRSC); EXT_KEY(ZAWRS); diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index 6265052ef8b6..bf9a3b5aae73 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -24,7 +24,20 @@ void flush_icache_all(void) if (num_online_cpus() < 2) return; - else if (riscv_use_sbi_for_rfence()) + + /* + * Make sure all previous writes to the D$ are ordered before making + * the IPI. The RISC-V spec states that a hart must execute a data fence + * before triggering a remote fence.i in order to make the modification + * visable for remote harts. + * + * IPIs on RISC-V are triggered by MMIO writes to either CLINT or + * S-IMSIC, so the fence ensures previous data writes "happen before" + * the MMIO. + */ + RISCV_FENCE(w, o); + + if (riscv_use_sbi_for_rfence()) sbi_remote_fence_i(NULL); else on_each_cpu(ipi_remote_fence_i, NULL, 1); diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c index 4ae67324f992..8b6c0a112a8d 100644 --- a/arch/riscv/mm/pgtable.c +++ b/arch/riscv/mm/pgtable.c @@ -154,4 +154,14 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, flush_tlb_mm(vma->vm_mm); return pmd; } + +pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp) +{ + VM_WARN_ON_ONCE(!pud_present(*pudp)); + pud_t old = pudp_establish(vma, address, pudp, pud_mkinvalid(*pudp)); + + flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); + return old; +} #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c index f9e27ba1df99..97c8fde3cbfe 100644 --- a/arch/riscv/mm/tlbflush.c +++ b/arch/riscv/mm/tlbflush.c @@ -182,6 +182,13 @@ void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, __flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm), start, end - start, PMD_SIZE); } + +void flush_pud_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + __flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm), + start, end - start, PUD_SIZE); +} #endif bool arch_tlbbatch_should_defer(struct mm_struct *mm) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index fbabc3d848b3..30374478cb07 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -635,6 +635,8 @@ enum { #define ftrace_get_symaddr(fentry_ip) (0) #endif +void ftrace_sync_ipi(void *data); + #ifdef CONFIG_DYNAMIC_FTRACE void ftrace_arch_code_modify_prepare(void); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 61130bb34d6c..31e9fe3bf964 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -188,7 +188,7 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, op->saved_func(ip, parent_ip, op, fregs); } -static void ftrace_sync_ipi(void *data) +void ftrace_sync_ipi(void *data) { /* Probably not needed, but do it anyway */ smp_rmb(); diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index fbf6d0f73af9..55b1409b0593 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1733,6 +1733,12 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, continue; } + /* Reject RISCV ELF "mapping symbols" */ + if (ehdr.e_machine == EM_RISCV) { + if (elf_name[0] == '$' && strchr("dx", elf_name[1])) + continue; + } + if (runtime_ss->opdsec && sym.st_shndx == runtime_ss->opdidx) { u32 offset = sym.st_value - syms_ss->opdshdr.sh_addr; u64 *opd = opddata->d_buf + offset; |