diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-03-01 09:27:00 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-03-01 09:27:00 -0800 |
| commit | a8356cdb5bd5abc74f814d76bd37900997fad35d (patch) | |
| tree | 8a546eb732cad0262cd3ff514a51b7051f721278 | |
| parent | 64e851689e441e66e001ae063d4536602f9f74cb (diff) | |
| parent | 8883bf83127d533abb415b204eabc064863ae6c9 (diff) | |
| download | iio-a8356cdb5bd5abc74f814d76bd37900997fad35d.tar.gz | |
Merge tag 'loongarch-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson
Pull LoongArch updates from Huacai Chen:
- Make -mstrict-align configurable
- Add kernel relocation and KASLR support
- Add single kernel image implementation for kdump
- Add hardware breakpoints/watchpoints support
- Add kprobes/kretprobes/kprobes_on_ftrace support
- Add LoongArch support for some selftests.
* tag 'loongarch-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson: (23 commits)
selftests/ftrace: Add LoongArch kprobe args string tests support
selftests/seccomp: Add LoongArch selftesting support
tools: Add LoongArch build infrastructure
samples/kprobes: Add LoongArch support
LoongArch: Mark some assembler symbols as non-kprobe-able
LoongArch: Add kprobes on ftrace support
LoongArch: Add kretprobes support
LoongArch: Add kprobes support
LoongArch: Simulate branch and PC* instructions
LoongArch: ptrace: Add hardware single step support
LoongArch: ptrace: Add function argument access API
LoongArch: ptrace: Expose hardware breakpoints to debuggers
LoongArch: Add hardware breakpoints/watchpoints support
LoongArch: kdump: Add crashkernel=YM handling
LoongArch: kdump: Add single kernel image implementation
LoongArch: Add support for kernel address space layout randomization (KASLR)
LoongArch: Add support for kernel relocation
LoongArch: Add la_abs macro implementation
LoongArch: Add JUMP_VIRT_ADDR macro implementation to avoid using la.abs
LoongArch: Use la.pcrel instead of la.abs when it's trivially possible
...
47 files changed, 2665 insertions, 130 deletions
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index 9cc8b84f7eb03..7fd51257e0ed4 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -94,15 +94,21 @@ config LOONGARCH select HAVE_DYNAMIC_FTRACE_WITH_ARGS select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT + select HAVE_EFFICIENT_UNALIGNED_ACCESS if !ARCH_STRICT_ALIGN select HAVE_EXIT_THREAD select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GENERIC_VDSO + select HAVE_HW_BREAKPOINT if PERF_EVENTS select HAVE_IOREMAP_PROT select HAVE_IRQ_EXIT_ON_IRQ_STACK select HAVE_IRQ_TIME_ACCOUNTING + select HAVE_KPROBES + select HAVE_KPROBES_ON_FTRACE + select HAVE_KRETPROBES select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI select HAVE_PCI @@ -441,6 +447,24 @@ config ARCH_IOREMAP protection support. However, you can enable LoongArch DMW-based ioremap() for better performance. +config ARCH_STRICT_ALIGN + bool "Enable -mstrict-align to prevent unaligned accesses" if EXPERT + default y + help + Not all LoongArch cores support h/w unaligned access, we can use + -mstrict-align build parameter to prevent unaligned accesses. + + CPUs with h/w unaligned access support: + Loongson-2K2000/2K3000/3A5000/3C5000/3D5000. + + CPUs without h/w unaligned access support: + Loongson-2K500/2K1000. + + This option is enabled by default to make the kernel be able to run + on all LoongArch systems. But you can disable it manually if you want + to run kernel only on systems with h/w unaligned access support in + order to optimise for performance. + config KEXEC bool "Kexec system call" select KEXEC_CORE @@ -454,6 +478,7 @@ config KEXEC config CRASH_DUMP bool "Build kdump crash kernel" + select RELOCATABLE help Generate crash dump after being started by kexec. This should be normally only set in special crash dump kernels which are @@ -463,16 +488,38 @@ config CRASH_DUMP For more details see Documentation/admin-guide/kdump/kdump.rst -config PHYSICAL_START - hex "Physical address where the kernel is loaded" - default "0x90000000a0000000" - depends on CRASH_DUMP +config RELOCATABLE + bool "Relocatable kernel" help - This gives the XKPRANGE address where the kernel is loaded. - If you plan to use kernel for capturing the crash dump change - this value to start of the reserved region (the "X" value as - specified in the "crashkernel=YM@XM" command line boot parameter - passed to the panic-ed kernel). + This builds the kernel as a Position Independent Executable (PIE), + which retains all relocation metadata required, so as to relocate + the kernel binary at runtime to a different virtual address from + its link address. + +config RANDOMIZE_BASE + bool "Randomize the address of the kernel (KASLR)" + depends on RELOCATABLE + help + Randomizes the physical and virtual address at which the + kernel image is loaded, as a security feature that + deters exploit attempts relying on knowledge of the location + of kernel internals. + + The kernel will be offset by up to RANDOMIZE_BASE_MAX_OFFSET. + + If unsure, say N. + +config RANDOMIZE_BASE_MAX_OFFSET + hex "Maximum KASLR offset" if EXPERT + depends on RANDOMIZE_BASE + range 0x0 0x10000000 + default "0x01000000" + help + When KASLR is active, this provides the maximum offset that will + be applied to the kernel image. It should be set according to the + amount of physical RAM available in the target system. + + This is limited by the size of the lower address memory, 256MB. config SECCOMP bool "Enable seccomp to safely compute untrusted bytecode" diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index 4402387d27551..f71edf5741011 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -71,14 +71,15 @@ KBUILD_AFLAGS_MODULE += -Wa,-mla-global-with-abs KBUILD_CFLAGS_MODULE += -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs endif +ifeq ($(CONFIG_RELOCATABLE),y) +KBUILD_CFLAGS_KERNEL += -fPIE +LDFLAGS_vmlinux += -static -pie --no-dynamic-linker -z notext +endif + cflags-y += -ffreestanding cflags-y += $(call cc-option, -mno-check-zero-division) -ifndef CONFIG_PHYSICAL_START load-y = 0x9000000000200000 -else -load-y = $(CONFIG_PHYSICAL_START) -endif bootvars-y = VMLINUX_LOAD_ADDRESS=$(load-y) drivers-$(CONFIG_PCI) += arch/loongarch/pci/ @@ -91,10 +92,15 @@ KBUILD_CPPFLAGS += -DVMLINUX_LOAD_ADDRESS=$(load-y) # instead of .eh_frame so we don't discard them. KBUILD_CFLAGS += -fno-asynchronous-unwind-tables +ifdef CONFIG_ARCH_STRICT_ALIGN # Don't emit unaligned accesses. # Not all LoongArch cores support unaligned access, and as kernel we can't # rely on others to provide emulation for these accesses. KBUILD_CFLAGS += $(call cc-option,-mstrict-align) +else +# Optimise for performance on hardware supports unaligned access. +KBUILD_CFLAGS += $(call cc-option,-mno-strict-align) +endif KBUILD_CFLAGS += -isystem $(shell $(CC) -print-file-name=include) diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig index eb84cae642e58..e18213f01cc47 100644 --- a/arch/loongarch/configs/loongson3_defconfig +++ b/arch/loongarch/configs/loongson3_defconfig @@ -48,6 +48,7 @@ CONFIG_HOTPLUG_CPU=y CONFIG_NR_CPUS=64 CONFIG_NUMA=y CONFIG_KEXEC=y +CONFIG_CRASH_DUMP=y CONFIG_SUSPEND=y CONFIG_HIBERNATION=y CONFIG_ACPI=y diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h index d342935e5a72d..8fb699b4d40af 100644 --- a/arch/loongarch/include/asm/addrspace.h +++ b/arch/loongarch/include/asm/addrspace.h @@ -125,4 +125,6 @@ extern unsigned long vm_map_base; #define ISA_IOSIZE SZ_16K #define IO_SPACE_LIMIT (PCI_IOSIZE - 1) +#define PHYS_LINK_KADDR PHYSADDR(VMLINUX_LOAD_ADDRESS) + #endif /* _ASM_ADDRSPACE_H */ diff --git a/arch/loongarch/include/asm/asm.h b/arch/loongarch/include/asm/asm.h index 40eea6aa469e1..f591b3245def6 100644 --- a/arch/loongarch/include/asm/asm.h +++ b/arch/loongarch/include/asm/asm.h @@ -188,4 +188,14 @@ #define PTRLOG 3 #endif +/* Annotate a function as being unsuitable for kprobes. */ +#ifdef CONFIG_KPROBES +#define _ASM_NOKPROBE(name) \ + .pushsection "_kprobe_blacklist", "aw"; \ + .quad name; \ + .popsection +#else +#define _ASM_NOKPROBE(name) +#endif + #endif /* __ASM_ASM_H */ diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h index be037a40580d4..c51a1b43acb44 100644 --- a/arch/loongarch/include/asm/asmmacro.h +++ b/arch/loongarch/include/asm/asmmacro.h @@ -274,4 +274,21 @@ nor \dst, \src, zero .endm +.macro la_abs reg, sym +#ifndef CONFIG_RELOCATABLE + la.abs \reg, \sym +#else + 766: + lu12i.w \reg, 0 + ori \reg, \reg, 0 + lu32i.d \reg, 0 + lu52i.d \reg, \reg, 0 + .pushsection ".la_abs", "aw", %progbits + 768: + .dword 768b-766b + .dword \sym + .popsection +#endif +.endm + #endif /* _ASM_ASMMACRO_H */ diff --git a/arch/loongarch/include/asm/cpu.h b/arch/loongarch/include/asm/cpu.h index 754f285067913..c3da917594728 100644 --- a/arch/loongarch/include/asm/cpu.h +++ b/arch/loongarch/include/asm/cpu.h @@ -36,7 +36,7 @@ #define PRID_SERIES_LA132 0x8000 /* Loongson 32bit */ #define PRID_SERIES_LA264 0xa000 /* Loongson 64bit, 2-issue */ -#define PRID_SERIES_LA364 0xb000 /* Loongson 64bit，3-issue */ +#define PRID_SERIES_LA364 0xb000 /* Loongson 64bit, 3-issue */ #define PRID_SERIES_LA464 0xc000 /* Loongson 64bit, 4-issue */ #define PRID_SERIES_LA664 0xd000 /* Loongson 64bit, 6-issue */ diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h new file mode 100644 index 0000000000000..21447fb1efc77 --- /dev/null +++ b/arch/loongarch/include/asm/hw_breakpoint.h @@ -0,0 +1,145 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2023 Loongson Technology Corporation Limited + */ +#ifndef __ASM_HW_BREAKPOINT_H +#define __ASM_HW_BREAKPOINT_H + +#include <asm/loongarch.h> + +#ifdef __KERNEL__ + +/* Breakpoint */ +#define LOONGARCH_BREAKPOINT_EXECUTE (0 << 0) + +/* Watchpoints */ +#define LOONGARCH_BREAKPOINT_LOAD (1 << 0) +#define LOONGARCH_BREAKPOINT_STORE (1 << 1) + +struct arch_hw_breakpoint_ctrl { + u32 __reserved : 28, + len : 2, + type : 2; +}; + +struct arch_hw_breakpoint { + u64 address; + u64 mask; + struct arch_hw_breakpoint_ctrl ctrl; +}; + +/* Lengths */ +#define LOONGARCH_BREAKPOINT_LEN_1 0b11 +#define LOONGARCH_BREAKPOINT_LEN_2 0b10 +#define LOONGARCH_BREAKPOINT_LEN_4 0b01 +#define LOONGARCH_BREAKPOINT_LEN_8 0b00 + +/* + * Limits. + * Changing these will require modifications to the register accessors. + */ +#define LOONGARCH_MAX_BRP 8 +#define LOONGARCH_MAX_WRP 8 + +/* Virtual debug register bases. */ +#define CSR_CFG_ADDR 0 +#define CSR_CFG_MASK (CSR_CFG_ADDR + LOONGARCH_MAX_BRP) +#define CSR_CFG_CTRL (CSR_CFG_MASK + LOONGARCH_MAX_BRP) +#define CSR_CFG_ASID (CSR_CFG_CTRL + LOONGARCH_MAX_WRP) + +/* Debug register names. */ +#define LOONGARCH_CSR_NAME_ADDR ADDR +#define LOONGARCH_CSR_NAME_MASK MASK +#define LOONGARCH_CSR_NAME_CTRL CTRL +#define LOONGARCH_CSR_NAME_ASID ASID + +/* Accessor macros for the debug registers. */ +#define LOONGARCH_CSR_WATCH_READ(N, REG, T, VAL) \ +do { \ + if (T == 0) \ + VAL = csr_read64(LOONGARCH_CSR_##IB##N##REG); \ + else \ + VAL = csr_read64(LOONGARCH_CSR_##DB##N##REG); \ +} while (0) + +#define LOONGARCH_CSR_WATCH_WRITE(N, REG, T, VAL) \ +do { \ + if (T == 0) \ + csr_write64(VAL, LOONGARCH_CSR_##IB##N##REG); \ + else \ + csr_write64(VAL, LOONGARCH_CSR_##DB##N##REG); \ +} while (0) + +/* Exact number */ +#define CSR_FWPC_NUM 0x3f +#define CSR_MWPC_NUM 0x3f + +#define CTRL_PLV_ENABLE 0x1e + +#define MWPnCFG3_LoadEn 8 +#define MWPnCFG3_StoreEn 9 + +#define MWPnCFG3_Type_mask 0x3 +#define MWPnCFG3_Size_mask 0x3 + +static inline u32 encode_ctrl_reg(struct arch_hw_breakpoint_ctrl ctrl) +{ + return (ctrl.len << 10) | (ctrl.type << 8); +} + +static inline void decode_ctrl_reg(u32 reg, struct arch_hw_breakpoint_ctrl *ctrl) +{ + reg >>= 8; + ctrl->type = reg & MWPnCFG3_Type_mask; + reg >>= 2; + ctrl->len = reg & MWPnCFG3_Size_mask; +} + +struct task_struct; +struct notifier_block; +struct perf_event; +struct perf_event_attr; + +extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, + int *gen_len, int *gen_type, int *offset); +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, + unsigned long val, void *data); + +extern int arch_install_hw_breakpoint(struct perf_event *bp); +extern void arch_uninstall_hw_breakpoint(struct perf_event *bp); +extern int hw_breakpoint_slots(int type); +extern void hw_breakpoint_pmu_read(struct perf_event *bp); + +void breakpoint_handler(struct pt_regs *regs); +void watchpoint_handler(struct pt_regs *regs); + +#ifdef CONFIG_HAVE_HW_BREAKPOINT +extern void ptrace_hw_copy_thread(struct task_struct *task); +extern void hw_breakpoint_thread_switch(struct task_struct *next); +#else +static inline void ptrace_hw_copy_thread(struct task_struct *task) +{ +} +static inline void hw_breakpoint_thread_switch(struct task_struct *next) +{ +} +#endif + +/* Determine number of BRP registers available. */ +static inline int get_num_brps(void) +{ + return csr_read64(LOONGARCH_CSR_FWPC) & CSR_FWPC_NUM; +} + +/* Determine number of WRP registers available. */ +static inline int get_num_wrps(void) +{ + return csr_read64(LOONGARCH_CSR_MWPC) & CSR_MWPC_NUM; +} + +#endif /* __KERNEL__ */ +#endif /* __ASM_BREAKPOINT_H */ diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h index 7eedd83fd0d72..a04fe755d7193 100644 --- a/arch/loongarch/include/asm/inst.h +++ b/arch/loongarch/include/asm/inst.h @@ -7,6 +7,7 @@ #include <linux/types.h> #include <asm/asm.h> +#include <asm/ptrace.h> #define INSN_NOP 0x03400000 #define INSN_BREAK 0x002a0000 @@ -23,6 +24,10 @@ #define ADDR_IMM(addr, INSN) ((addr & ADDR_IMMMASK_##INSN) >> ADDR_IMMSHIFT_##INSN) +enum reg0i15_op { + break_op = 0x54, +}; + enum reg0i26_op { b_op = 0x14, bl_op = 0x15, @@ -32,6 +37,7 @@ enum reg1i20_op { lu12iw_op = 0x0a, lu32id_op = 0x0b, pcaddi_op = 0x0c, + pcalau12i_op = 0x0d, pcaddu12i_op = 0x0e, pcaddu18i_op = 0x0f, }; @@ -178,6 +184,11 @@ enum reg3sa2_op { alsld_op = 0x16, }; +struct reg0i15_format { + unsigned int immediate : 15; + unsigned int opcode : 17; +}; + struct reg0i26_format { unsigned int immediate_h : 10; unsigned int immediate_l : 16; @@ -263,6 +274,7 @@ struct reg3sa2_format { union loongarch_instruction { unsigned int word; + struct reg0i15_format reg0i15_format; struct reg0i26_format reg0i26_format; struct reg1i20_format reg1i20_format; struct reg1i21_format reg1i21_format; @@ -321,6 +333,11 @@ static inline bool is_imm_negative(unsigned long val, unsigned int bit) return val & (1UL << (bit - 1)); } +static inline bool is_break_ins(union loongarch_instruction *ip) +{ + return ip->reg0i15_format.opcode == break_op; +} + static inline bool is_pc_ins(union loongarch_instruction *ip) { return ip->reg1i20_format.opcode >= pcaddi_op && @@ -351,6 +368,47 @@ static inline bool is_stack_alloc_ins(union loongarch_instruction *ip) is_imm12_negative(ip->reg2i12_format.immediate); } +static inline bool is_self_loop_ins(union loongarch_instruction *ip, struct pt_regs *regs) +{ + switch (ip->reg0i26_format.opcode) { + case b_op: + case bl_op: + if (ip->reg0i26_format.immediate_l == 0 + && ip->reg0i26_format.immediate_h == 0) + return true; + } + + switch (ip->reg1i21_format.opcode) { + case beqz_op: + case bnez_op: + case bceqz_op: + if (ip->reg1i21_format.immediate_l == 0 + && ip->reg1i21_format.immediate_h == 0) + return true; + } + + switch (ip->reg2i16_format.opcode) { + case beq_op: + case bne_op: + case blt_op: + case bge_op: + case bltu_op: + case bgeu_op: + if (ip->reg2i16_format.immediate == 0) + return true; + break; + case jirl_op: + if (regs->regs[ip->reg2i16_format.rj] + + ((unsigned long)ip->reg2i16_format.immediate << 2) == (unsigned long)ip) + return true; + } + + return false; +} + +void simu_pc(struct pt_regs *regs, union loongarch_instruction insn); +void simu_branch(struct pt_regs *regs, union loongarch_instruction insn); + int larch_insn_read(void *addr, u32 *insnp); int larch_insn_write(void *addr, u32 insn); int larch_insn_patch_text(void *addr, u32 insn); diff --git a/arch/loongarch/include/asm/kprobes.h b/arch/loongarch/include/asm/kprobes.h new file mode 100644 index 0000000000000..798020ae02c69 --- /dev/null +++ b/arch/loongarch/include/asm/kprobes.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_LOONGARCH_KPROBES_H +#define __ASM_LOONGARCH_KPROBES_H + +#include <asm-generic/kprobes.h> + +#ifdef CONFIG_KPROBES + +#include <asm/inst.h> +#include <asm/cacheflush.h> + +#define __ARCH_WANT_KPROBES_INSN_SLOT +#define MAX_INSN_SIZE 2 + +#define flush_insn_slot(p) \ +do { \ + if (p->addr) \ + flush_icache_range((unsigned long)p->addr, \ + (unsigned long)p->addr + \ + (MAX_INSN_SIZE * sizeof(kprobe_opcode_t))); \ +} while (0) + +#define kretprobe_blacklist_size 0 + +typedef union loongarch_instruction kprobe_opcode_t; + +/* Architecture specific copy of original instruction */ +struct arch_specific_insn { + /* copy of the original instruction */ + kprobe_opcode_t *insn; + /* restore address after simulation */ + unsigned long restore; +}; + +struct prev_kprobe { + struct kprobe *kp; + unsigned int status; +}; + +/* per-cpu kprobe control block */ +struct kprobe_ctlblk { + unsigned int kprobe_status; + unsigned long saved_status; + struct prev_kprobe prev_kprobe; +}; + +void arch_remove_kprobe(struct kprobe *p); +bool kprobe_fault_handler(struct pt_regs *regs, int trapnr); +bool kprobe_breakpoint_handler(struct pt_regs *regs); +bool kprobe_singlestep_handler(struct pt_regs *regs); + +void __kretprobe_trampoline(void); +void *trampoline_probe_handler(struct pt_regs *regs); + +#else /* !CONFIG_KPROBES */ + +static inline bool kprobe_breakpoint_handler(struct pt_regs *regs) { return false; } +static inline bool kprobe_singlestep_handler(struct pt_regs *regs) { return false; } + +#endif /* CONFIG_KPROBES */ +#endif /* __ASM_LOONGARCH_KPROBES_H */ diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h index 7f8d57a61c8bd..65b7dcdea16d0 100644 --- a/arch/loongarch/include/asm/loongarch.h +++ b/arch/loongarch/include/asm/loongarch.h @@ -970,42 +970,42 @@ static __always_inline void iocsr_write64(u64 val, u32 reg) #define LOONGARCH_CSR_DB0ADDR 0x310 /* data breakpoint 0 address */ #define LOONGARCH_CSR_DB0MASK 0x311 /* data breakpoint 0 mask */ -#define LOONGARCH_CSR_DB0CTL 0x312 /* data breakpoint 0 control */ +#define LOONGARCH_CSR_DB0CTRL 0x312 /* data breakpoint 0 control */ #define LOONGARCH_CSR_DB0ASID 0x313 /* data breakpoint 0 asid */ #define LOONGARCH_CSR_DB1ADDR 0x318 /* data breakpoint 1 address */ #define LOONGARCH_CSR_DB1MASK 0x319 /* data breakpoint 1 mask */ -#define LOONGARCH_CSR_DB1CTL 0x31a /* data breakpoint 1 control */ +#define LOONGARCH_CSR_DB1CTRL 0x31a /* data breakpoint 1 control */ #define LOONGARCH_CSR_DB1ASID 0x31b /* data breakpoint 1 asid */ #define LOONGARCH_CSR_DB2ADDR 0x320 /* data breakpoint 2 address */ #define LOONGARCH_CSR_DB2MASK 0x321 /* data breakpoint 2 mask */ -#define LOONGARCH_CSR_DB2CTL 0x322 /* data breakpoint 2 control */ +#define LOONGARCH_CSR_DB2CTRL 0x322 /* data breakpoint 2 control */ #define LOONGARCH_CSR_DB2ASID 0x323 /* data breakpoint 2 asid */ #define LOONGARCH_CSR_DB3ADDR 0x328 /* data breakpoint 3 address */ #define LOONGARCH_CSR_DB3MASK 0x329 /* data breakpoint 3 mask */ -#define LOONGARCH_CSR_DB3CTL 0x32a /* data breakpoint 3 control */ +#define LOONGARCH_CSR_DB3CTRL 0x32a /* data breakpoint 3 control */ #define LOONGARCH_CSR_DB3ASID 0x32b /* data breakpoint 3 asid */ #define LOONGARCH_CSR_DB4ADDR 0x330 /* data breakpoint 4 address */ #define LOONGARCH_CSR_DB4MASK 0x331 /* data breakpoint 4 maks */ -#define LOONGARCH_CSR_DB4CTL 0x332 /* data breakpoint 4 control */ +#define LOONGARCH_CSR_DB4CTRL 0x332 /* data breakpoint 4 control */ #define LOONGARCH_CSR_DB4ASID 0x333 /* data breakpoint 4 asid */ #define LOONGARCH_CSR_DB5ADDR 0x338 /* data breakpoint 5 address */ #define LOONGARCH_CSR_DB5MASK 0x339 /* data breakpoint 5 mask */ -#define LOONGARCH_CSR_DB5CTL 0x33a /* data breakpoint 5 control */ +#define LOONGARCH_CSR_DB5CTRL 0x33a /* data breakpoint 5 control */ #define LOONGARCH_CSR_DB5ASID 0x33b /* data breakpoint 5 asid */ #define LOONGARCH_CSR_DB6ADDR 0x340 /* data breakpoint 6 address */ #define LOONGARCH_CSR_DB6MASK 0x341 /* data breakpoint 6 mask */ -#define LOONGARCH_CSR_DB6CTL 0x342 /* data breakpoint 6 control */ +#define LOONGARCH_CSR_DB6CTRL 0x342 /* data breakpoint 6 control */ #define LOONGARCH_CSR_DB6ASID 0x343 /* data breakpoint 6 asid */ #define LOONGARCH_CSR_DB7ADDR 0x348 /* data breakpoint 7 address */ #define LOONGARCH_CSR_DB7MASK 0x349 /* data breakpoint 7 mask */ -#define LOONGARCH_CSR_DB7CTL 0x34a /* data breakpoint 7 control */ +#define LOONGARCH_CSR_DB7CTRL 0x34a /* data breakpoint 7 control */ #define LOONGARCH_CSR_DB7ASID 0x34b /* data breakpoint 7 asid */ #define LOONGARCH_CSR_FWPC 0x380 /* instruction breakpoint config */ @@ -1013,48 +1013,51 @@ static __always_inline void iocsr_write64(u64 val, u32 reg) #define LOONGARCH_CSR_IB0ADDR 0x390 /* inst breakpoint 0 address */ #define LOONGARCH_CSR_IB0MASK 0x391 /* inst breakpoint 0 mask */ -#define LOONGARCH_CSR_IB0CTL 0x392 /* inst breakpoint 0 control */ +#define LOONGARCH_CSR_IB0CTRL 0x392 /* inst breakpoint 0 control */ #define LOONGARCH_CSR_IB0ASID 0x393 /* inst breakpoint 0 asid */ #define LOONGARCH_CSR_IB1ADDR 0x398 /* inst breakpoint 1 address */ #define LOONGARCH_CSR_IB1MASK 0x399 /* inst breakpoint 1 mask */ -#define LOONGARCH_CSR_IB1CTL 0x39a /* inst breakpoint 1 control */ +#define LOONGARCH_CSR_IB1CTRL 0x39a /* inst breakpoint 1 control */ #define LOONGARCH_CSR_IB1ASID 0x39b /* inst breakpoint 1 asid */ #define LOONGARCH_CSR_IB2ADDR 0x3a0 /* inst breakpoint 2 address */ #define LOONGARCH_CSR_IB2MASK 0x3a1 /* inst breakpoint 2 mask */ -#define LOONGARCH_CSR_IB2CTL 0x3a2 /* inst breakpoint 2 control */ +#define LOONGARCH_CSR_IB2CTRL 0x3a2 /* inst breakpoint 2 control */ #define LOONGARCH_CSR_IB2ASID 0x3a3 /* inst breakpoint 2 asid */ #define LOONGARCH_CSR_IB3ADDR 0x3a8 /* inst breakpoint 3 address */ #define LOONGARCH_CSR_IB3MASK 0x3a9 /* breakpoint 3 mask */ -#define LOONGARCH_CSR_IB3CTL 0x3aa /* inst breakpoint 3 control */ +#define LOONGARCH_CSR_IB3CTRL 0x3aa /* inst breakpoint 3 control */ #define LOONGARCH_CSR_IB3ASID 0x3ab /* inst breakpoint 3 asid */ #define LOONGARCH_CSR_IB4ADDR 0x3b0 /* inst breakpoint 4 address */ #define LOONGARCH_CSR_IB4MASK 0x3b1 /* inst breakpoint 4 mask */ -#define LOONGARCH_CSR_IB4CTL 0x3b2 /* inst breakpoint 4 control */ +#define LOONGARCH_CSR_IB4CTRL 0x3b2 /* inst breakpoint 4 control */ #define LOONGARCH_CSR_IB4ASID 0x3b3 /* inst breakpoint 4 asid */ #define LOONGARCH_CSR_IB5ADDR 0x3b8 /* inst breakpoint 5 address */ #define LOONGARCH_CSR_IB5MASK 0x3b9 /* inst breakpoint 5 mask */ -#define LOONGARCH_CSR_IB5CTL 0x3ba /* inst breakpoint 5 control */ +#define LOONGARCH_CSR_IB5CTRL 0x3ba /* inst breakpoint 5 control */ #define LOONGARCH_CSR_IB5ASID 0x3bb /* inst breakpoint 5 asid */ #define LOONGARCH_CSR_IB6ADDR 0x3c0 /* inst breakpoint 6 address */ #define LOONGARCH_CSR_IB6MASK 0x3c1 /* inst breakpoint 6 mask */ -#define LOONGARCH_CSR_IB6CTL 0x3c2 /* inst breakpoint 6 control */ +#define LOONGARCH_CSR_IB6CTRL 0x3c2 /* inst breakpoint 6 control */ #define LOONGARCH_CSR_IB6ASID 0x3c3 /* inst breakpoint 6 asid */ #define LOONGARCH_CSR_IB7ADDR 0x3c8 /* inst breakpoint 7 address */ #define LOONGARCH_CSR_IB7MASK 0x3c9 /* inst breakpoint 7 mask */ -#define LOONGARCH_CSR_IB7CTL 0x3ca /* inst breakpoint 7 control */ +#define LOONGARCH_CSR_IB7CTRL 0x3ca /* inst breakpoint 7 control */ #define LOONGARCH_CSR_IB7ASID 0x3cb /* inst breakpoint 7 asid */ #define LOONGARCH_CSR_DEBUG 0x500 /* debug config */ #define LOONGARCH_CSR_DERA 0x501 /* debug era */ #define LOONGARCH_CSR_DESAVE 0x502 /* debug save */ +#define CSR_FWPC_SKIP_SHIFT 16 +#define CSR_FWPC_SKIP (_ULCAST_(1) << CSR_FWPC_SKIP_SHIFT) + /* * CSR_ECFG IM */ diff --git a/arch/loongarch/include/asm/processor.h b/arch/loongarch/include/asm/processor.h index 7184f1dc61f27..636e1c66398c1 100644 --- a/arch/loongarch/include/asm/processor.h +++ b/arch/loongarch/include/asm/processor.h @@ -11,6 +11,7 @@ #include <asm/cpu.h> #include <asm/cpu-info.h> +#include <asm/hw_breakpoint.h> #include <asm/loongarch.h> #include <asm/vdso/processor.h> #include <uapi/asm/ptrace.h> @@ -124,13 +125,18 @@ struct thread_struct { /* Other stuff associated with the thread. */ unsigned long trap_nr; unsigned long error_code; + unsigned long single_step; /* Used by PTRACE_SINGLESTEP */ struct loongarch_vdso_info *vdso; /* - * FPU & vector registers, must be at last because - * they are conditionally copied at fork(). + * FPU & vector registers, must be at the last of inherited + * context because they are conditionally copied at fork(). */ struct loongarch_fpu fpu FPU_ALIGN; + + /* Hardware breakpoints pinned to this task. */ + struct perf_event *hbp_break[LOONGARCH_MAX_BRP]; + struct perf_event *hbp_watch[LOONGARCH_MAX_WRP]; }; #define thread_saved_ra(tsk) (tsk->thread.sched_ra) @@ -172,6 +178,8 @@ struct thread_struct { .fcc = 0, \ .fpr = {{{0,},},}, \ }, \ + .hbp_break = {0}, \ + .hbp_watch = {0}, \ } struct task_struct; @@ -184,10 +192,6 @@ extern unsigned long boot_option_idle_override; */ extern void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp); -static inline void flush_thread(void) -{ -} - unsigned long __get_wchan(struct task_struct *p); #define __KSTK_TOS(tsk) ((unsigned long)task_stack_page(tsk) + \ diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h index 59c4608de91db..d761db943335c 100644 --- a/arch/loongarch/include/asm/ptrace.h +++ b/arch/loongarch/include/asm/ptrace.h @@ -6,6 +6,7 @@ #define _ASM_PTRACE_H #include <asm/page.h> +#include <asm/irqflags.h> #include <asm/thread_info.h> #include <uapi/asm/ptrace.h> @@ -109,6 +110,40 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsi struct task_struct; +/** + * regs_get_kernel_argument() - get Nth function argument in kernel + * @regs: pt_regs of that context + * @n: function argument number (start from 0) + * + * regs_get_argument() returns @n th argument of the function call. + * Note that this chooses most probably assignment, in some case + * it can be incorrect. + * This is expected to be called from kprobes or ftrace with regs + * where the top of stack is the return address. + */ +static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, + unsigned int n) +{ +#define NR_REG_ARGUMENTS 8 + static const unsigned int args[] = { + offsetof(struct pt_regs, regs[4]), + offsetof(struct pt_regs, regs[5]), + offsetof(struct pt_regs, regs[6]), + offsetof(struct pt_regs, regs[7]), + offsetof(struct pt_regs, regs[8]), + offsetof(struct pt_regs, regs[9]), + offsetof(struct pt_regs, regs[10]), + offsetof(struct pt_regs, regs[11]), + }; + + if (n < NR_REG_ARGUMENTS) + return regs_get_register(regs, args[n]); + else { + n -= NR_REG_ARGUMENTS; + return regs_get_kernel_stack_nth(regs, n); + } +} + /* * Does the process account for user or for system time? */ @@ -149,4 +184,8 @@ static inline void user_stack_pointer_set(struct pt_regs *regs, regs->regs[3] = val; } +#ifdef CONFIG_HAVE_HW_BREAKPOINT +#define arch_has_single_step() (1) +#endif + #endif /* _ASM_PTRACE_H */ diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h index 72ead58039f3e..be05c0e706a2e 100644 --- a/arch/loongarch/include/asm/setup.h +++ b/arch/loongarch/include/asm/setup.h @@ -21,4 +21,20 @@ extern void per_cpu_trap_init(int cpu); extern void set_handler(unsigned long offset, void *addr, unsigned long len); extern void set_merr_handler(unsigned long offset, void *addr, unsigned long len); +#ifdef CONFIG_RELOCATABLE + +struct rela_la_abs { + long offset; + long symvalue; +}; + +extern long __la_abs_begin; +extern long __la_abs_end; +extern long __rela_dyn_begin; +extern long __rela_dyn_end; + +extern void * __init relocate_kernel(void); + +#endif + #endif /* __SETUP_H */ diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h index 4ca953062b5be..7df80e6ae9d2c 100644 --- a/arch/loongarch/include/asm/stackframe.h +++ b/arch/loongarch/include/asm/stackframe.h @@ -7,6 +7,7 @@ #include <linux/threads.h> +#include <asm/addrspace.h> #include <asm/asm.h> #include <asm/asmmacro.h> #include <asm/asm-offsets.h> @@ -36,6 +37,14 @@ cfi_restore \reg \offset \docfi .endm +/* Jump to the runtime virtual address. */ + .macro JUMP_VIRT_ADDR temp1 temp2 + li.d \temp1, CACHE_BASE + pcaddi \temp2, 0 + or \temp1, \temp1, \temp2 + jirl zero, \temp1, 0xc + .endm + .macro BACKUP_T0T1 csrwr t0, EXCEPTION_KS0 csrwr t1, EXCEPTION_KS1 @@ -77,7 +86,7 @@ * new value in sp. */ .macro get_saved_sp docfi=0 - la.abs t1, kernelsp + la_abs t1, kernelsp #ifdef CONFIG_SMP csrrd t0, PERCPU_BASE_KS LONG_ADD t1, t1, t0 @@ -90,7 +99,7 @@ .endm .macro set_saved_sp stackp temp temp2 - la.abs \temp, kernelsp + la.pcrel \temp, kernelsp #ifdef CONFIG_SMP LONG_ADD \temp, \temp, u0 #endif diff --git a/arch/loongarch/include/asm/switch_to.h b/arch/loongarch/include/asm/switch_to.h index 43a5ab162d38b..24e3094bebab1 100644 --- a/arch/loongarch/include/asm/switch_to.h +++ b/arch/loongarch/include/asm/switch_to.h @@ -34,6 +34,7 @@ extern asmlinkage struct task_struct *__switch_to(struct task_struct *prev, #define switch_to(prev, next, last) \ do { \ lose_fpu_inatomic(1, prev); \ + hw_breakpoint_thread_switch(next); \ (last) = __switch_to(prev, next, task_thread_info(next), \ __builtin_return_address(0), __builtin_frame_address(0)); \ } while (0) diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h index 255899d4a7c36..0d22991ae430d 100644 --- a/arch/loongarch/include/asm/uaccess.h +++ b/arch/loongarch/include/asm/uaccess.h @@ -22,7 +22,6 @@ extern u64 __ua_limit; #define __UA_ADDR ".dword" -#define __UA_LA "la.abs" #define __UA_LIMIT __ua_limit /* diff --git a/arch/loongarch/include/uapi/asm/ptrace.h b/arch/loongarch/include/uapi/asm/ptrace.h index 083193f4a5d5d..cc48ed2620212 100644 --- a/arch/loongarch/include/uapi/asm/ptrace.h +++ b/arch/loongarch/include/uapi/asm/ptrace.h @@ -46,6 +46,15 @@ struct user_fp_state { uint32_t fcsr; }; +struct user_watch_state { + uint16_t dbg_info; + struct { + uint64_t addr; + uint64_t mask; + uint32_t ctrl; + } dbg_regs[8]; +}; + #define PTRACE_SYSEMU 0x1f #define PTRACE_SYSEMU_SINGLESTEP 0x20 diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index c8cfbd562921d..78d4e33843054 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -8,13 +8,15 @@ extra-y := vmlinux.lds obj-y += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \ traps.o irq.o idle.o process.o dma.o mem.o io.o reset.o switch.o \ elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \ - alternative.o unaligned.o unwind.o + alternative.o unwind.o obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_EFI) += efi.o obj-$(CONFIG_CPU_HAS_FPU) += fpu.o +obj-$(CONFIG_ARCH_STRICT_ALIGN) += unaligned.o + ifdef CONFIG_FUNCTION_TRACER ifndef CONFIG_DYNAMIC_FTRACE obj-y += mcount.o ftrace.o @@ -39,6 +41,8 @@ obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_MAGIC_SYSRQ) += sysrq.o +obj-$(CONFIG_RELOCATABLE) += relocate.o + obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o @@ -46,5 +50,8 @@ obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o obj-$(CONFIG_UNWINDER_PROLOGUE) += unwind_prologue.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_regs.o +obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o + +obj-$(CONFIG_KPROBES) += kprobes.o kprobes_trampoline.o CPPFLAGS_vmlinux.lds := $(KBUILD_CFLAGS) diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S index d53b631c90227..d737e3cf42d3f 100644 --- a/arch/loongarch/kernel/entry.S +++ b/arch/loongarch/kernel/entry.S @@ -19,70 +19,71 @@ .cfi_sections .debug_frame .align 5 SYM_FUNC_START(handle_syscall) - csrrd t0, PERCPU_BASE_KS - la.abs t1, kernelsp - add.d t1, t1, t0 - move t2, sp - ld.d sp, t1, 0 + csrrd t0, PERCPU_BASE_KS + la.pcrel t1, kernelsp + add.d t1, t1, t0 + move t2, sp + ld.d sp, t1, 0 - addi.d sp, sp, -PT_SIZE - cfi_st t2, PT_R3 + addi.d sp, sp, -PT_SIZE + cfi_st t2, PT_R3 cfi_rel_offset sp, PT_R3 - st.d zero, sp, PT_R0 - csrrd t2, LOONGARCH_CSR_PRMD - st.d t2, sp, PT_PRMD - csrrd t2, LOONGARCH_CSR_CRMD - st.d t2, sp, PT_CRMD - csrrd t2, LOONGARCH_CSR_EUEN - st.d t2, sp, PT_EUEN - csrrd t2, LOONGARCH_CSR_ECFG - st.d t2, sp, PT_ECFG - csrrd t2, LOONGARCH_CSR_ESTAT - st.d t2, sp, PT_ESTAT - cfi_st ra, PT_R1 - cfi_st a0, PT_R4 - cfi_st a1, PT_R5 - cfi_st a2, PT_R6 - cfi_st a3, PT_R7 - cfi_st a4, PT_R8 - cfi_st a5, PT_R9 - cfi_st a6, PT_R10 - cfi_st a7, PT_R11 - csrrd ra, LOONGARCH_CSR_ERA - st.d ra, sp, PT_ERA + st.d zero, sp, PT_R0 + csrrd t2, LOONGARCH_CSR_PRMD + st.d t2, sp, PT_PRMD + csrrd t2, LOONGARCH_CSR_CRMD + st.d t2, sp, PT_CRMD + csrrd t2, LOONGARCH_CSR_EUEN + st.d t2, sp, PT_EUEN + csrrd t2, LOONGARCH_CSR_ECFG + st.d t2, sp, PT_ECFG + csrrd t2, LOONGARCH_CSR_ESTAT + st.d t2, sp, PT_ESTAT + cfi_st ra, PT_R1 + cfi_st a0, PT_R4 + cfi_st a1, PT_R5 + cfi_st a2, PT_R6 + cfi_st a3, PT_R7 + cfi_st a4, PT_R8 + cfi_st a5, PT_R9 + cfi_st a6, PT_R10 + cfi_st a7, PT_R11 + csrrd ra, LOONGARCH_CSR_ERA + st.d ra, sp, PT_ERA cfi_rel_offset ra, PT_ERA - cfi_st tp, PT_R2 - cfi_st u0, PT_R21 - cfi_st fp, PT_R22 + cfi_st tp, PT_R2 + cfi_st u0, PT_R21 + cfi_st fp, PT_R22 SAVE_STATIC - move u0, t0 - li.d tp, ~_THREAD_MASK - and tp, tp, sp + move u0, t0 + li.d tp, ~_THREAD_MASK + and tp, tp, sp - move a0, sp - bl do_syscall + move a0, sp + bl do_syscall RESTORE_ALL_AND_RET SYM_FUNC_END(handle_syscall) +_ASM_NOKPROBE(handle_syscall) SYM_CODE_START(ret_from_fork) - bl schedule_tail # a0 = struct task_struct *prev - move a0, sp - bl syscall_exit_to_user_mode + bl schedule_tail # a0 = struct task_struct *prev + move a0, sp + bl syscall_exit_to_user_mode RESTORE_STATIC RESTORE_SOME RESTORE_SP_AND_RET SYM_CODE_END(ret_from_fork) SYM_CODE_START(ret_from_kernel_thread) - bl schedule_tail # a0 = struct task_struct *prev - move a0, s1 - jirl ra, s0, 0 - move a0, sp - bl syscall_exit_to_user_mode + bl schedule_tail # a0 = struct task_struct *prev + move a0, s1 + jirl ra, s0, 0 + move a0, sp + bl syscall_exit_to_user_mode RESTORE_STATIC RESTORE_SOME RESTORE_SP_AND_RET diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c index 0f07591cab309..4a3ef8516ccc6 100644 --- a/arch/loongarch/kernel/ftrace_dyn.c +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -6,6 +6,7 @@ */ #include <linux/ftrace.h> +#include <linux/kprobes.h> #include <linux/uaccess.h> #include <asm/inst.h> @@ -271,3 +272,66 @@ int ftrace_disable_ftrace_graph_caller(void) } #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + +#ifdef CONFIG_KPROBES_ON_FTRACE +/* Ftrace callback handler for kprobes -- called under preepmt disabled */ +void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct ftrace_regs *fregs) +{ + int bit; + struct pt_regs *regs; + struct kprobe *p; + struct kprobe_ctlblk *kcb; + + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) + return; + + p = get_kprobe((kprobe_opcode_t *)ip); + if (unlikely(!p) || kprobe_disabled(p)) + goto out; + + regs = ftrace_get_regs(fregs); + if (!regs) + goto out; + + kcb = get_kprobe_ctlblk(); + if (kprobe_running()) { + kprobes_inc_nmissed_count(p); + } else { + unsigned long orig_ip = instruction_pointer(regs); + + instruction_pointer_set(regs, ip); + + __this_cpu_write(current_kprobe, p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + if (!p->pre_handler || !p->pre_handler(p, regs)) { + /* + * Emulate singlestep (and also recover regs->csr_era) + * as if there is a nop + */ + instruction_pointer_set(regs, (unsigned long)p->addr + MCOUNT_INSN_SIZE); + if (unlikely(p->post_handler)) { + kcb->kprobe_status = KPROBE_HIT_SSDONE; + p->post_handler(p, regs, 0); + } + instruction_pointer_set(regs, orig_ip); + } + + /* + * If pre_handler returns !0, it changes regs->csr_era. We have to + * skip emulating post_handler. + */ + __this_cpu_write(current_kprobe, NULL); + } +out: + ftrace_test_recursion_unlock(bit); +} +NOKPROBE_SYMBOL(kprobe_ftrace_handler); + +int arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + p->ainsn.insn = NULL; + return 0; +} +#endif /* CONFIG_KPROBES_ON_FTRACE */ diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 7e5c293ed89f7..44ff1ff642601 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -34,7 +34,7 @@ SYM_FUNC_END(__arch_cpu_idle) SYM_FUNC_START(handle_vint) BACKUP_T0T1 SAVE_ALL - la.abs t1, __arch_cpu_idle + la_abs t1, __arch_cpu_idle LONG_L t0, sp, PT_ERA /* 32 byte rollback region */ ori t0, t0, 0x1f @@ -43,7 +43,7 @@ SYM_FUNC_START(handle_vint) LONG_S t0, sp, PT_ERA 1: move a0, sp move a1, sp - la.abs t0, do_vint + la_abs t0, do_vint jirl ra, t0, 0 RESTORE_ALL_AND_RET SYM_FUNC_END(handle_vint) @@ -72,7 +72,7 @@ SYM_FUNC_END(except_vec_cex) SAVE_ALL build_prep_\prep move a0, sp - la.abs t0, do_\handler + la_abs t0, do_\handler jirl ra, t0, 0 668: RESTORE_ALL_AND_RET @@ -93,6 +93,6 @@ SYM_FUNC_END(except_vec_cex) BUILD_HANDLER reserved reserved none /* others */ SYM_FUNC_START(handle_sys) - la.abs t0, handle_syscall + la_abs t0, handle_syscall jr t0 SYM_FUNC_END(handle_sys) diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S index 57bada6b4e931..aa64b179744f5 100644 --- a/arch/loongarch/kernel/head.S +++ b/arch/loongarch/kernel/head.S @@ -24,7 +24,7 @@ _head: .org 0x8 .dword kernel_entry /* Kernel entry point */ .dword _end - _text /* Kernel image effective size */ - .quad 0 /* Kernel image load offset from start of RAM */ + .quad PHYS_LINK_KADDR /* Kernel image load offset from start of RAM */ .org 0x38 /* 0x20 ~ 0x37 reserved */ .long LINUX_PE_MAGIC .long pe_header - _head /* Offset to the PE header */ @@ -50,11 +50,8 @@ SYM_CODE_START(kernel_entry) # kernel entry point li.d t0, CSR_DMW1_INIT # CA, PLV0, 0x9000 xxxx xxxx xxxx csrwr t0, LOONGARCH_CSR_DMWIN1 - /* We might not get launched at the address the kernel is linked to, - so we jump there. */ - la.abs t0, 0f - jr t0 -0: + JUMP_VIRT_ADDR t0, t1 + /* Enable PG */ li.w t0, 0xb0 # PLV=0, IE=0, PG=1 csrwr t0, LOONGARCH_CSR_CRMD @@ -89,6 +86,23 @@ SYM_CODE_START(kernel_entry) # kernel entry point PTR_ADD sp, sp, tp set_saved_sp sp, t0, t1 +#ifdef CONFIG_RELOCATABLE + + bl relocate_kernel + +#ifdef CONFIG_RANDOMIZE_BASE + /* Repoint the sp into the new kernel */ + PTR_LI sp, (_THREAD_SIZE - PT_SIZE) + PTR_ADD sp, sp, tp + set_saved_sp sp, t0, t1 +#endif + + /* relocate_kernel() returns the new kernel entry point */ + jr a0 + ASM_BUG() + +#endif + bl start_kernel ASM_BUG() @@ -106,9 +120,8 @@ SYM_CODE_START(smpboot_entry) li.d t0, CSR_DMW1_INIT # CA, PLV0 csrwr t0, LOONGARCH_CSR_DMWIN1 - la.abs t0, 0f - jr t0 -0: + JUMP_VIRT_ADDR t0, t1 + /* Enable PG */ li.w t0, 0xb0 # PLV=0, IE=0, PG=1 csrwr t0, LOONGARCH_CSR_CRMD @@ -117,7 +130,7 @@ SYM_CODE_START(smpboot_entry) li.w t0, 0x00 # FPE=0, SXE=0, ASXE=0, BTE=0 csrwr t0, LOONGARCH_CSR_EUEN - la.abs t0, cpuboot_data + la.pcrel t0, cpuboot_data ld.d sp, t0, CPU_BOOT_STACK ld.d tp, t0, CPU_BOOT_TINFO diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c new file mode 100644 index 0000000000000..2406c95b34cc4 --- /dev/null +++ b/arch/loongarch/kernel/hw_breakpoint.c @@ -0,0 +1,548 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2023 Loongson Technology Corporation Limited + */ +#define pr_fmt(fmt) "hw-breakpoint: " fmt + +#include <linux/hw_breakpoint.h> +#include <linux/kprobes.h> +#include <linux/perf_event.h> + +#include <asm/hw_breakpoint.h> + +/* Breakpoint currently in use for each BRP. */ +static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[LOONGARCH_MAX_BRP]); + +/* Watchpoint currently in use for each WRP. */ +static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[LOONGARCH_MAX_WRP]); + +int hw_breakpoint_slots(int type) +{ + /* + * We can be called early, so don't rely on + * our static variables being initialised. + */ + switch (type) { + case TYPE_INST: + return get_num_brps(); + case TYPE_DATA: + return get_num_wrps(); + default: + pr_warn("unknown slot type: %d\n", type); + return 0; + } +} + +#define READ_WB_REG_CASE(OFF, N, REG, T, VAL) \ + case (OFF + N): \ + LOONGARCH_CSR_WATCH_READ(N, REG, T, VAL); \ + break + +#define WRITE_WB_REG_CASE(OFF, N, REG, T, VAL) \ + case (OFF + N): \ + LOONGARCH_CSR_WATCH_WRITE(N, REG, T, VAL); \ + break + +#define GEN_READ_WB_REG_CASES(OFF, REG, T, VAL) \ + READ_WB_REG_CASE(OFF, 0, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 1, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 2, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 3, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 4, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 5, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 6, REG, T, VAL); \ + READ_WB_REG_CASE(OFF, 7, REG, T, VAL); + +#define GEN_WRITE_WB_REG_CASES(OFF, REG, T, VAL) \ + WRITE_WB_REG_CASE(OFF, 0, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 1, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 2, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 3, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 4, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 5, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 6, REG, T, VAL); \ + WRITE_WB_REG_CASE(OFF, 7, REG, T, VAL); + +static u64 read_wb_reg(int reg, int n, int t) +{ + u64 val = 0; + + switch (reg + n) { + GEN_READ_WB_REG_CASES(CSR_CFG_ADDR, ADDR, t, val); + GEN_READ_WB_REG_CASES(CSR_CFG_MASK, MASK, t, val); + GEN_READ_WB_REG_CASES(CSR_CFG_CTRL, CTRL, t, val); + GEN_READ_WB_REG_CASES(CSR_CFG_ASID, ASID, t, val); + default: + pr_warn("Attempt to read from unknown breakpoint register %d\n", n); + } + + return val; +} +NOKPROBE_SYMBOL(read_wb_reg); + +static void write_wb_reg(int reg, int n, int t, u64 val) +{ + switch (reg + n) { + GEN_WRITE_WB_REG_CASES(CSR_CFG_ADDR, ADDR, t, val); + GEN_WRITE_WB_REG_CASES(CSR_CFG_MASK, MASK, t, val); + GEN_WRITE_WB_REG_CASES(CSR_CFG_CTRL, CTRL, t, val); + GEN_WRITE_WB_REG_CASES(CSR_CFG_ASID, ASID, t, val); + default: + pr_warn("Attempt to write to unknown breakpoint register %d\n", n); + } +} +NOKPROBE_SYMBOL(write_wb_reg); + +enum hw_breakpoint_ops { + HW_BREAKPOINT_INSTALL, + HW_BREAKPOINT_UNINSTALL, +}; + +/* + * hw_breakpoint_slot_setup - Find and setup a perf slot according to operations + * + * @slots: pointer to array of slots + * @max_slots: max number of slots + * @bp: perf_event to setup + * @ops: operation to be carried out on the slot + * + * Return: + * slot index on success + * -ENOSPC if no slot is available/matches + * -EINVAL on wrong operations parameter + */ + +static int hw_breakpoint_slot_setup(struct perf_event **slots, int max_slots, + struct perf_event *bp, enum hw_breakpoint_ops ops) +{ + int i; + struct perf_event **slot; + + for (i = 0; i < max_slots; ++i) { + slot = &slots[i]; + switch (ops) { + case HW_BREAKPOINT_INSTALL: + if (!*slot) { + *slot = bp; + return i; + } + break; + case HW_BREAKPOINT_UNINSTALL: + if (*slot == bp) { + *slot = NULL; + return i; + } + break; + default: + pr_warn_once("Unhandled hw breakpoint ops %d\n", ops); + return -EINVAL; + } + } + + return -ENOSPC; +} + +void ptrace_hw_copy_thread(struct task_struct *tsk) +{ + memset(tsk->thread.hbp_break, 0, sizeof(tsk->thread.hbp_break)); + memset(tsk->thread.hbp_watch, 0, sizeof(tsk->thread.hbp_watch)); +} + +/* + * Unregister breakpoints from this task and reset the pointers in the thread_struct. + */ +void flush_ptrace_hw_breakpoint(struct task_struct *tsk) +{ + int i; + struct thread_struct *t = &tsk->thread; + + for (i = 0; i < LOONGARCH_MAX_BRP; i++) { + if (t->hbp_break[i]) { + unregister_hw_breakpoint(t->hbp_break[i]); + t->hbp_break[i] = NULL; + } + } + + for (i = 0; i < LOONGARCH_MAX_WRP; i++) { + if (t->hbp_watch[i]) { + unregister_hw_breakpoint(t->hbp_watch[i]); + t->hbp_watch[i] = NULL; + } + } +} + +static int hw_breakpoint_control(struct perf_event *bp, + enum hw_breakpoint_ops ops) +{ + u32 ctrl; + int i, max_slots, enable; + struct perf_event **slots; + struct arch_hw_breakpoint *info = counter_arch_bp(bp); + + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { + /* Breakpoint */ + slots = this_cpu_ptr(bp_on_reg); + max_slots = boot_cpu_data.watch_ireg_count; + } else { + /* Watchpoint */ + slots = this_cpu_ptr(wp_on_reg); + max_slots = boot_cpu_data.watch_dreg_count; + } + + i = hw_breakpoint_slot_setup(slots, max_slots, bp, ops); + + if (WARN_ONCE(i < 0, "Can't find any breakpoint slot")) + return i; + + switch (ops) { + case HW_BREAKPOINT_INSTALL: + /* Set the FWPnCFG/MWPnCFG 1~4 register. */ + write_wb_reg(CSR_CFG_ADDR, i, 0, info->address); + write_wb_reg(CSR_CFG_ADDR, i, 1, info->address); + write_wb_reg(CSR_CFG_MASK, i, 0, info->mask); + write_wb_reg(CSR_CFG_MASK, i, 1, info->mask); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) { + write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE); + } else { + ctrl = encode_ctrl_reg(info->ctrl); + write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | CTRL_PLV_ENABLE | + 1 << MWPnCFG3_LoadEn | 1 << MWPnCFG3_StoreEn); + } + enable = csr_read64(LOONGARCH_CSR_CRMD); + csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD); + break; + case HW_BREAKPOINT_UNINSTALL: + /* Reset the FWPnCFG/MWPnCFG 1~4 register. */ + write_wb_reg(CSR_CFG_ADDR, i, 0, 0); + write_wb_reg(CSR_CFG_ADDR, i, 1, 0); + write_wb_reg(CSR_CFG_MASK, i, 0, 0); + write_wb_reg(CSR_CFG_MASK, i, 1, 0); + write_wb_reg(CSR_CFG_CTRL, i, 0, 0); + write_wb_reg(CSR_CFG_CTRL, i, 1, 0); + write_wb_reg(CSR_CFG_ASID, i, 0, 0); + write_wb_reg(CSR_CFG_ASID, i, 1, 0); + break; + } + + return 0; +} + +/* + * Install a perf counter breakpoint. + */ +int arch_install_hw_breakpoint(struct perf_event *bp) +{ + return hw_breakpoint_control(bp, HW_BREAKPOINT_INSTALL); +} + +void arch_uninstall_hw_breakpoint(struct perf_event *bp) +{ + hw_breakpoint_control(bp, HW_BREAKPOINT_UNINSTALL); +} + +static int get_hbp_len(u8 hbp_len) +{ + unsigned int len_in_bytes = 0; + + switch (hbp_len) { + case LOONGARCH_BREAKPOINT_LEN_1: + len_in_bytes = 1; + break; + case LOONGARCH_BREAKPOINT_LEN_2: + len_in_bytes = 2; + break; + case LOONGARCH_BREAKPOINT_LEN_4: + len_in_bytes = 4; + break; + case LOONGARCH_BREAKPOINT_LEN_8: + len_in_bytes = 8; + break; + } + + return len_in_bytes; +} + +/* + * Check whether bp virtual address is in kernel space. + */ +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) +{ + unsigned int len; + unsigned long va; + + va = hw->address; + len = get_hbp_len(hw->ctrl.len); + + return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); +} + +/* + * Extract generic type and length encodings from an arch_hw_breakpoint_ctrl. + * Hopefully this will disappear when ptrace can bypass the conversion + * to generic breakpoint descriptions. + */ +int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, + int *gen_len, int *gen_type, int *offset) +{ + /* Type */ + switch (ctrl.type) { + case LOONGARCH_BREAKPOINT_EXECUTE: + *gen_type = HW_BREAKPOINT_X; + break; + case LOONGARCH_BREAKPOINT_LOAD: + *gen_type = HW_BREAKPOINT_R; + break; + case LOONGARCH_BREAKPOINT_STORE: + *gen_type = HW_BREAKPOINT_W; + break; + case LOONGARCH_BREAKPOINT_LOAD | LOONGARCH_BREAKPOINT_STORE: + *gen_type = HW_BREAKPOINT_RW; + break; + default: + return -EINVAL; + } + + if (!ctrl.len) + return -EINVAL; + + *offset = __ffs(ctrl.len); + + /* Len */ + switch (ctrl.len) { + case LOONGARCH_BREAKPOINT_LEN_1: + *gen_len = HW_BREAKPOINT_LEN_1; + break; + case LOONGARCH_BREAKPOINT_LEN_2: + *gen_len = HW_BREAKPOINT_LEN_2; + break; + case LOONGARCH_BREAKPOINT_LEN_4: + *gen_len = HW_BREAKPOINT_LEN_4; + break; + case LOONGARCH_BREAKPOINT_LEN_8: + *gen_len = HW_BREAKPOINT_LEN_8; + break; + default: + return -EINVAL; + } + + return 0; +} + +/* + * Construct an arch_hw_breakpoint from a perf_event. + */ +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) +{ + /* Type */ + switch (attr->bp_type) { + case HW_BREAKPOINT_X: + hw->ctrl.type = LOONGARCH_BREAKPOINT_EXECUTE; + break; + case HW_BREAKPOINT_R: + hw->ctrl.type = LOONGARCH_BREAKPOINT_LOAD; + break; + case HW_BREAKPOINT_W: + hw->ctrl.type = LOONGARCH_BREAKPOINT_STORE; + break; + case HW_BREAKPOINT_RW: + hw->ctrl.type = LOONGARCH_BREAKPOINT_LOAD | LOONGARCH_BREAKPOINT_STORE; + break; + default: + return -EINVAL; + } + + /* Len */ + switch (attr->bp_len) { + case HW_BREAKPOINT_LEN_1: + hw->ctrl.len = LOONGARCH_BREAKPOINT_LEN_1; + break; + case HW_BREAKPOINT_LEN_2: + hw->ctrl.len = LOONGARCH_BREAKPOINT_LEN_2; + break; + case HW_BREAKPOINT_LEN_4: + hw->ctrl.len = LOONGARCH_BREAKPOINT_LEN_4; + break; + case HW_BREAKPOINT_LEN_8: + hw->ctrl.len = LOONGARCH_BREAKPOINT_LEN_8; + break; + default: + return -EINVAL; + } + + /* Address */ + hw->address = attr->bp_addr; + + return 0; +} + +/* + * Validate the arch-specific HW Breakpoint register settings. + */ +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) +{ + int ret; + u64 alignment_mask, offset; + + /* Build the arch_hw_breakpoint. */ + ret = arch_build_bp_info(bp, attr, hw); + if (ret) + return ret; + + if (hw->ctrl.type != LOONGARCH_BREAKPOINT_EXECUTE) + alignment_mask = 0x7; + offset = hw->address & alignment_mask; + + hw->address &= ~alignment_mask; + hw->ctrl.len <<= offset; + + return 0; +} + +static void update_bp_registers(struct pt_regs *regs, int enable, int type) +{ + u32 ctrl; + int i, max_slots; + struct perf_event **slots; + struct arch_hw_breakpoint *info; + + switch (type) { + case 0: + slots = this_cpu_ptr(bp_on_reg); + max_slots = boot_cpu_data.watch_ireg_count; + break; + case 1: + slots = this_cpu_ptr(wp_on_reg); + max_slots = boot_cpu_data.watch_dreg_count; + break; + default: + return; + } + + for (i = 0; i < max_slots; ++i) { + if (!slots[i]) + continue; + + info = counter_arch_bp(slots[i]); + if (enable) { + if ((info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) && (type == 0)) { + write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE); + write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE); + } else { + ctrl = read_wb_reg(CSR_CFG_CTRL, i, 1); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_LOAD) + ctrl |= 0x1 << MWPnCFG3_LoadEn; + if (info->ctrl.type == LOONGARCH_BREAKPOINT_STORE) + ctrl |= 0x1 << MWPnCFG3_StoreEn; + write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl); + } + regs->csr_prmd |= CSR_PRMD_PWE; + } else { + if ((info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) && (type == 0)) { + write_wb_reg(CSR_CFG_CTRL, i, 0, 0); + } else { + ctrl = read_wb_reg(CSR_CFG_CTRL, i, 1); + if (info->ctrl.type == LOONGARCH_BREAKPOINT_LOAD) + ctrl &= ~0x1 << MWPnCFG3_LoadEn; + if (info->ctrl.type == LOONGARCH_BREAKPOINT_STORE) + ctrl &= ~0x1 << MWPnCFG3_StoreEn; + write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl); + } + regs->csr_prmd &= ~CSR_PRMD_PWE; + } + } +} +NOKPROBE_SYMBOL(update_bp_registers); + +/* + * Debug exception handlers. + */ +void breakpoint_handler(struct pt_regs *regs) +{ + int i; + struct perf_event *bp, **slots; + + slots = this_cpu_ptr(bp_on_reg); + + for (i = 0; i < boot_cpu_data.watch_ireg_count; ++i) { + bp = slots[i]; + if (bp == NULL) + continue; + perf_bp_event(bp, regs); + } + update_bp_registers(regs, 0, 0); +} +NOKPROBE_SYMBOL(breakpoint_handler); + +void watchpoint_handler(struct pt_regs *regs) +{ + int i; + struct perf_event *wp, **slots; + + slots = this_cpu_ptr(wp_on_reg); + + for (i = 0; i < boot_cpu_data.watch_dreg_count; ++i) { + wp = slots[i]; + if (wp == NULL) + continue; + perf_bp_event(wp, regs); + } + update_bp_registers(regs, 0, 1); +} +NOKPROBE_SYMBOL(watchpoint_handler); + +static int __init arch_hw_breakpoint_init(void) +{ + int cpu; + + boot_cpu_data.watch_ireg_count = get_num_brps(); + boot_cpu_data.watch_dreg_count = get_num_wrps(); + + pr_info("Found %d breakpoint and %d watchpoint registers.\n", + boot_cpu_data.watch_ireg_count, boot_cpu_data.watch_dreg_count); + + for (cpu = 1; cpu < NR_CPUS; cpu++) { + cpu_data[cpu].watch_ireg_count = boot_cpu_data.watch_ireg_count; + cpu_data[cpu].watch_dreg_count = boot_cpu_data.watch_dreg_count; + } + + return 0; +} +arch_initcall(arch_hw_breakpoint_init); + +void hw_breakpoint_thread_switch(struct task_struct *next) +{ + u64 addr, mask; + struct pt_regs *regs = task_pt_regs(next); + + if (test_tsk_thread_flag(next, TIF_SINGLESTEP)) { + addr = read_wb_reg(CSR_CFG_ADDR, 0, 0); + mask = read_wb_reg(CSR_CFG_MASK, 0, 0); + if (!((regs->csr_era ^ addr) & ~mask)) + csr_write32(CSR_FWPC_SKIP, LOONGARCH_CSR_FWPS); + regs->csr_prmd |= CSR_PRMD_PWE; + } else { + /* Update breakpoints */ + update_bp_registers(regs, 1, 0); + /* Update watchpoints */ + update_bp_registers(regs, 1, 1); + } +} + +void hw_breakpoint_pmu_read(struct perf_event *bp) +{ +} + +/* + * Dummy function to register with die_notifier. + */ +int hw_breakpoint_exceptions_notify(struct notifier_block *unused, + unsigned long val, void *data) +{ + return NOTIFY_DONE; +} diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c index badc590870423..258ef267cd306 100644 --- a/arch/loongarch/kernel/inst.c +++ b/arch/loongarch/kernel/inst.c @@ -10,6 +10,129 @@ static DEFINE_RAW_SPINLOCK(patch_lock); +void simu_pc(struct pt_regs *regs, union loongarch_instruction insn) +{ + unsigned long pc = regs->csr_era; + unsigned int rd = insn.reg1i20_format.rd; + unsigned int imm = insn.reg1i20_format.immediate; + + if (pc & 3) { + pr_warn("%s: invalid pc 0x%lx\n", __func__, pc); + return; + } + + switch (insn.reg1i20_format.opcode) { + case pcaddi_op: + regs->regs[rd] = pc + sign_extend64(imm << 2, 21); + break; + case pcaddu12i_op: + regs->regs[rd] = pc + sign_extend64(imm << 12, 31); + break; + case pcaddu18i_op: + regs->regs[rd] = pc + sign_extend64(imm << 18, 37); + break; + case pcalau12i_op: + regs->regs[rd] = pc + sign_extend64(imm << 12, 31); + regs->regs[rd] &= ~((1 << 12) - 1); + break; + default: + pr_info("%s: unknown opcode\n", __func__); + return; + } + + regs->csr_era += LOONGARCH_INSN_SIZE; +} + +void simu_branch(struct pt_regs *regs, union loongarch_instruction insn) +{ + unsigned int imm, imm_l, imm_h, rd, rj; + unsigned long pc = regs->csr_era; + + if (pc & 3) { + pr_warn("%s: invalid pc 0x%lx\n", __func__, pc); + return; + } + + imm_l = insn.reg0i26_format.immediate_l; + imm_h = insn.reg0i26_format.immediate_h; + switch (insn.reg0i26_format.opcode) { + case b_op: + regs->csr_era = pc + sign_extend64((imm_h << 16 | imm_l) << 2, 27); + return; + case bl_op: + regs->csr_era = pc + sign_extend64((imm_h << 16 | imm_l) << 2, 27); + regs->regs[1] = pc + LOONGARCH_INSN_SIZE; + return; + } + + imm_l = insn.reg1i21_format.immediate_l; + imm_h = insn.reg1i21_format.immediate_h; + rj = insn.reg1i21_format.rj; + switch (insn.reg1i21_format.opcode) { + case beqz_op: + if (regs->regs[rj] == 0) + regs->csr_era = pc + sign_extend64((imm_h << 16 | imm_l) << 2, 22); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + return; + case bnez_op: + if (regs->regs[rj] != 0) + regs->csr_era = pc + sign_extend64((imm_h << 16 | imm_l) << 2, 22); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + return; + } + + imm = insn.reg2i16_format.immediate; + rj = insn.reg2i16_format.rj; + rd = insn.reg2i16_format.rd; + switch (insn.reg2i16_format.opcode) { + case beq_op: + if (regs->regs[rj] == regs->regs[rd]) + regs->csr_era = pc + sign_extend64(imm << 2, 17); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + break; + case bne_op: + if (regs->regs[rj] != regs->regs[rd]) + regs->csr_era = pc + sign_extend64(imm << 2, 17); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + break; + case blt_op: + if ((long)regs->regs[rj] < (long)regs->regs[rd]) + regs->csr_era = pc + sign_extend64(imm << 2, 17); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + break; + case bge_op: + if ((long)regs->regs[rj] >= (long)regs->regs[rd]) + regs->csr_era = pc + sign_extend64(imm << 2, 17); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + break; + case bltu_op: + if (regs->regs[rj] < regs->regs[rd]) + regs->csr_era = pc + sign_extend64(imm << 2, 17); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + break; + case bgeu_op: + if (regs->regs[rj] >= regs->regs[rd]) + regs->csr_era = pc + sign_extend64(imm << 2, 17); + else + regs->csr_era = pc + LOONGARCH_INSN_SIZE; + break; + case jirl_op: + regs->csr_era = regs->regs[rj] + sign_extend64(imm << 2, 17); + regs->regs[rd] = pc + LOONGARCH_INSN_SIZE; + break; + default: + pr_info("%s: unknown opcode\n", __func__); + return; + } +} + int larch_insn_read(void *addr, u32 *insnp) { int ret; diff --git a/arch/loongarch/kernel/kprobes.c b/arch/loongarch/kernel/kprobes.c new file mode 100644 index 0000000000000..56c8c4b09a429 --- /dev/null +++ b/arch/loongarch/kernel/kprobes.c @@ -0,0 +1,406 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/kdebug.h> +#include <linux/kprobes.h> +#include <linux/preempt.h> +#include <asm/break.h> + +static const union loongarch_instruction breakpoint_insn = { + .reg0i15_format = { + .opcode = break_op, + .immediate = BRK_KPROBE_BP, + } +}; + +static const union loongarch_instruction singlestep_insn = { + .reg0i15_format = { + .opcode = break_op, + .immediate = BRK_KPROBE_SSTEPBP, + } +}; + +DEFINE_PER_CPU(struct kprobe *, current_kprobe); +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +static bool insns_not_supported(union loongarch_instruction insn) +{ + switch (insn.reg2i14_format.opcode) { + case llw_op: + case lld_op: + case scw_op: + case scd_op: + pr_notice("kprobe: ll and sc instructions are not supported\n"); + return true; + } + + switch (insn.reg1i21_format.opcode) { + case bceqz_op: + pr_notice("kprobe: bceqz and bcnez instructions are not supported\n"); + return true; + } + + return false; +} +NOKPROBE_SYMBOL(insns_not_supported); + +static bool insns_need_simulation(struct kprobe *p) +{ + if (is_pc_ins(&p->opcode)) + return true; + + if (is_branch_ins(&p->opcode)) + return true; + + return false; +} +NOKPROBE_SYMBOL(insns_need_simulation); + +static void arch_simulate_insn(struct kprobe *p, struct pt_regs *regs) +{ + if (is_pc_ins(&p->opcode)) + simu_pc(regs, p->opcode); + else if (is_branch_ins(&p->opcode)) + simu_branch(regs, p->opcode); +} +NOKPROBE_SYMBOL(arch_simulate_insn); + +static void arch_prepare_ss_slot(struct kprobe *p) +{ + p->ainsn.insn[0] = *p->addr; + p->ainsn.insn[1] = singlestep_insn; + p->ainsn.restore = (unsigned long)p->addr + LOONGARCH_INSN_SIZE; +} +NOKPROBE_SYMBOL(arch_prepare_ss_slot); + +static void arch_prepare_simulate(struct kprobe *p) +{ + p->ainsn.restore = 0; +} +NOKPROBE_SYMBOL(arch_prepare_simulate); + +int arch_prepare_kprobe(struct kprobe *p) +{ + if ((unsigned long)p->addr & 0x3) + return -EILSEQ; + + /* copy instruction */ + p->opcode = *p->addr; + + /* decode instruction */ + if (insns_not_supported(p->opcode)) + return -EINVAL; + + if (insns_need_simulation(p)) { + p->ainsn.insn = NULL; + } else { + p->ainsn.insn = get_insn_slot(); + if (!p->ainsn.insn) + return -ENOMEM; + } + + /* prepare the instruction */ + if (p->ainsn.insn) + arch_prepare_ss_slot(p); + else + arch_prepare_simulate(p); + + return 0; +} +NOKPROBE_SYMBOL(arch_prepare_kprobe); + +/* Install breakpoint in text */ +void arch_arm_kprobe(struct kprobe *p) +{ + *p->addr = breakpoint_insn; + flush_insn_slot(p); +} +NOKPROBE_SYMBOL(arch_arm_kprobe); + +/* Remove breakpoint from text */ +void arch_disarm_kprobe(struct kprobe *p) +{ + *p->addr = p->opcode; + flush_insn_slot(p); +} +NOKPROBE_SYMBOL(arch_disarm_kprobe); + +void arch_remove_kprobe(struct kprobe *p) +{ + if (p->ainsn.insn) { + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; + } +} +NOKPROBE_SYMBOL(arch_remove_kprobe); + +static void save_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + kcb->prev_kprobe.kp = kprobe_running(); + kcb->prev_kprobe.status = kcb->kprobe_status; +} +NOKPROBE_SYMBOL(save_previous_kprobe); + +static void restore_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); + kcb->kprobe_status = kcb->prev_kprobe.status; +} +NOKPROBE_SYMBOL(restore_previous_kprobe); + +static void set_current_kprobe(struct kprobe *p) +{ + __this_cpu_write(current_kprobe, p); +} +NOKPROBE_SYMBOL(set_current_kprobe); + +/* + * Interrupts need to be disabled before single-step mode is set, + * and not reenabled until after single-step mode ends. + * Without disabling interrupt on local CPU, there is a chance of + * interrupt occurrence in the period of exception return and start + * of out-of-line single-step, that result in wrongly single stepping + * into the interrupt handler. + */ +static void save_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + kcb->saved_status = regs->csr_prmd; + regs->csr_prmd &= ~CSR_PRMD_PIE; +} +NOKPROBE_SYMBOL(save_local_irqflag); + +static void restore_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + regs->csr_prmd = kcb->saved_status; +} +NOKPROBE_SYMBOL(restore_local_irqflag); + +static void post_kprobe_handler(struct kprobe *cur, struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + /* return addr restore if non-branching insn */ + if (cur->ainsn.restore != 0) + instruction_pointer_set(regs, cur->ainsn.restore); + + /* restore back original saved kprobe variables and continue */ + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); + preempt_enable_no_resched(); + return; + } + + /* + * update the kcb status even if the cur->post_handler is + * not set because reset_curent_kprobe() doesn't update kcb. + */ + kcb->kprobe_status = KPROBE_HIT_SSDONE; + if (cur->post_handler) + cur->post_handler(cur, regs, 0); + + reset_current_kprobe(); + preempt_enable_no_resched(); +} +NOKPROBE_SYMBOL(post_kprobe_handler); + +static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb, int reenter) +{ + if (reenter) { + save_previous_kprobe(kcb); + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_REENTER; + } else { + kcb->kprobe_status = KPROBE_HIT_SS; + } + + if (p->ainsn.insn) { + /* IRQs and single stepping do not mix well */ + save_local_irqflag(kcb, regs); + /* set ip register to prepare for single stepping */ + regs->csr_era = (unsigned long)p->ainsn.insn; + } else { + /* simulate single steping */ + arch_simulate_insn(p, regs); + /* now go for post processing */ + post_kprobe_handler(p, kcb, regs); + } +} +NOKPROBE_SYMBOL(setup_singlestep); + +static bool reenter_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + switch (kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_HIT_SSDONE: + case KPROBE_HIT_ACTIVE: + kprobes_inc_nmissed_count(p); + setup_singlestep(p, regs, kcb, 1); + break; + case KPROBE_REENTER: + pr_warn("Failed to recover from reentered kprobes.\n"); + dump_kprobe(p); + WARN_ON_ONCE(1); + break; + default: + WARN_ON(1); + return false; + } + + return true; +} +NOKPROBE_SYMBOL(reenter_kprobe); + +bool kprobe_breakpoint_handler(struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb; + struct kprobe *p, *cur_kprobe; + kprobe_opcode_t *addr = (kprobe_opcode_t *)regs->csr_era; + + /* + * We don't want to be preempted for the entire + * duration of kprobe processing. + */ + preempt_disable(); + kcb = get_kprobe_ctlblk(); + cur_kprobe = kprobe_running(); + + p = get_kprobe(addr); + if (p) { + if (cur_kprobe) { + if (reenter_kprobe(p, regs, kcb)) + return true; + } else { + /* Probe hit */ + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + /* + * If we have no pre-handler or it returned 0, we + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, it will + * modify the execution path and no need to single + * stepping. Let's just reset current kprobe and exit. + * + * pre_handler can hit a breakpoint and can step thru + * before return. + */ + if (!p->pre_handler || !p->pre_handler(p, regs)) { + setup_singlestep(p, regs, kcb, 0); + } else { + reset_current_kprobe(); + preempt_enable_no_resched(); + } + return true; + } + } + + if (addr->word != breakpoint_insn.word) { + /* + * The breakpoint instruction was removed right + * after we hit it. Another cpu has removed + * either a probepoint or a debugger breakpoint + * at this address. In either case, no further + * handling of this interrupt is appropriate. + * Return back to original instruction, and continue. + */ + regs->csr_era = (unsigned long)addr; + preempt_enable_no_resched(); + return true; + } + + preempt_enable_no_resched(); + return false; +} +NOKPROBE_SYMBOL(kprobe_breakpoint_handler); + +bool kprobe_singlestep_handler(struct pt_regs *regs) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long addr = instruction_pointer(regs); + + if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) && + ((unsigned long)&cur->ainsn.insn[1] == addr)) { + restore_local_irqflag(kcb, regs); + post_kprobe_handler(cur, kcb, regs); + return true; + } + + preempt_enable_no_resched(); + return false; +} +NOKPROBE_SYMBOL(kprobe_singlestep_handler); + +bool kprobe_fault_handler(struct pt_regs *regs, int trapnr) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + switch (kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the ip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->csr_era = (unsigned long)cur->addr; + WARN_ON_ONCE(!instruction_pointer(regs)); + + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); + } else { + restore_local_irqflag(kcb, regs); + reset_current_kprobe(); + } + preempt_enable_no_resched(); + break; + } + return false; +} +NOKPROBE_SYMBOL(kprobe_fault_handler); + +/* + * Provide a blacklist of symbols identifying ranges which cannot be kprobed. + * This blacklist is exposed to userspace via debugfs (kprobes/blacklist). + */ +int __init arch_populate_kprobe_blacklist(void) +{ + return kprobe_add_area_blacklist((unsigned long)__irqentry_text_start, + (unsigned long)__irqentry_text_end); +} + +int __init arch_init_kprobes(void) +{ + return 0; +} + +/* ASM function that handles the kretprobes must not be probed */ +NOKPROBE_SYMBOL(__kretprobe_trampoline); + +/* Called from __kretprobe_trampoline */ +void __used *trampoline_probe_handler(struct pt_regs *regs) +{ + return (void *)kretprobe_trampoline_handler(regs, NULL); +} +NOKPROBE_SYMBOL(trampoline_probe_handler); + +void arch_prepare_kretprobe(struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + ri->ret_addr = (kprobe_opcode_t *)regs->regs[1]; + ri->fp = NULL; + + /* Replace the return addr with trampoline addr */ + regs->regs[1] = (unsigned long)&__kretprobe_trampoline; +} +NOKPROBE_SYMBOL(arch_prepare_kretprobe); + +int arch_trampoline_kprobe(struct kprobe *p) +{ + return 0; +} +NOKPROBE_SYMBOL(arch_trampoline_kprobe); diff --git a/arch/loongarch/kernel/kprobes_trampoline.S b/arch/loongarch/kernel/kprobes_trampoline.S new file mode 100644 index 0000000000000..af94b0d213fa9 --- /dev/null +++ b/arch/loongarch/kernel/kprobes_trampoline.S @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#include <linux/linkage.h> +#include <asm/stackframe.h> + + .text + + .macro save_all_base_regs + cfi_st ra, PT_R1 + cfi_st tp, PT_R2 + cfi_st a0, PT_R4 + cfi_st a1, PT_R5 + cfi_st a2, PT_R6 + cfi_st a3, PT_R7 + cfi_st a4, PT_R8 + cfi_st a5, PT_R9 + cfi_st a6, PT_R10 + cfi_st a7, PT_R11 + cfi_st t0, PT_R12 + cfi_st t1, PT_R13 + cfi_st t2, PT_R14 + cfi_st t3, PT_R15 + cfi_st t4, PT_R16 + cfi_st t5, PT_R17 + cfi_st t6, PT_R18 + cfi_st t7, PT_R19 + cfi_st t8, PT_R20 + cfi_st u0, PT_R21 + cfi_st fp, PT_R22 + cfi_st s0, PT_R23 + cfi_st s1, PT_R24 + cfi_st s2, PT_R25 + cfi_st s3, PT_R26 + cfi_st s4, PT_R27 + cfi_st s5, PT_R28 + cfi_st s6, PT_R29 + cfi_st s7, PT_R30 + cfi_st s8, PT_R31 + csrrd t0, LOONGARCH_CSR_CRMD + andi t0, t0, 0x7 /* extract bit[1:0] PLV, bit[2] IE */ + LONG_S t0, sp, PT_CRMD + .endm + + .macro restore_all_base_regs + cfi_ld tp, PT_R2 + cfi_ld a0, PT_R4 + cfi_ld a1, PT_R5 + cfi_ld a2, PT_R6 + cfi_ld a3, PT_R7 + cfi_ld a4, PT_R8 + cfi_ld a5, PT_R9 + cfi_ld a6, PT_R10 + cfi_ld a7, PT_R11 + cfi_ld t0, PT_R12 + cfi_ld t1, PT_R13 + cfi_ld t2, PT_R14 + cfi_ld t3, PT_R15 + cfi_ld t4, PT_R16 + cfi_ld t5, PT_R17 + cfi_ld t6, PT_R18 + cfi_ld t7, PT_R19 + cfi_ld t8, PT_R20 + cfi_ld u0, PT_R21 + cfi_ld fp, PT_R22 + cfi_ld s0, PT_R23 + cfi_ld s1, PT_R24 + cfi_ld s2, PT_R25 + cfi_ld s3, PT_R26 + cfi_ld s4, PT_R27 + cfi_ld s5, PT_R28 + cfi_ld s6, PT_R29 + cfi_ld s7, PT_R30 + cfi_ld s8, PT_R31 + LONG_L t0, sp, PT_CRMD + li.d t1, 0x7 /* mask bit[1:0] PLV, bit[2] IE */ + csrxchg t0, t1, LOONGARCH_CSR_CRMD + .endm + +SYM_CODE_START(__kretprobe_trampoline) + addi.d sp, sp, -PT_SIZE + save_all_base_regs + + addi.d t0, sp, PT_SIZE + LONG_S t0, sp, PT_R3 + + move a0, sp /* pt_regs */ + + bl trampoline_probe_handler + + /* use the result as the return-address */ + move ra, a0 + + restore_all_base_regs + addi.d sp, sp, PT_SIZE + + jr ra +SYM_CODE_END(__kretprobe_trampoline) diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index edfd220a3737a..fa2443c7afb23 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -18,6 +18,7 @@ #include <linux/sched/debug.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> +#include <linux/hw_breakpoint.h> #include <linux/mm.h> #include <linux/stddef.h> #include <linux/unistd.h> @@ -96,6 +97,11 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) regs->regs[3] = sp; } +void flush_thread(void) +{ + flush_ptrace_hw_breakpoint(current); +} + void exit_thread(struct task_struct *tsk) { } @@ -181,6 +187,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) childregs->regs[2] = tls; out: + ptrace_hw_copy_thread(p); clear_tsk_thread_flag(p, TIF_USEDFPU); clear_tsk_thread_flag(p, TIF_USEDSIMD); clear_tsk_thread_flag(p, TIF_LSX_CTX_LIVE); diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c index dc2b82ea894cd..06bceae7d1040 100644 --- a/arch/loongarch/kernel/ptrace.c +++ b/arch/loongarch/kernel/ptrace.c @@ -20,7 +20,9 @@ #include <linux/context_tracking.h> #include <linux/elf.h> #include <linux/errno.h> +#include <linux/hw_breakpoint.h> #include <linux/mm.h> +#include <linux/nospec.h> #include <linux/ptrace.h> #include <linux/regset.h> #include <linux/sched.h> @@ -29,6 +31,7 @@ #include <linux/smp.h> #include <linux/stddef.h> #include <linux/seccomp.h> +#include <linux/thread_info.h> #include <linux/uaccess.h> #include <asm/byteorder.h> @@ -39,6 +42,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/processor.h> +#include <asm/ptrace.h> #include <asm/reg.h> #include <asm/syscall.h> @@ -246,6 +250,384 @@ static int cfg_set(struct task_struct *target, return 0; } +#ifdef CONFIG_HAVE_HW_BREAKPOINT + +/* + * Handle hitting a HW-breakpoint. + */ +static void ptrace_hbptriggered(struct perf_event *bp, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + int i; + struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp); + + for (i = 0; i < LOONGARCH_MAX_BRP; ++i) + if (current->thread.hbp_break[i] == bp) + break; + + for (i = 0; i < LOONGARCH_MAX_WRP; ++i) + if (current->thread.hbp_watch[i] == bp) + break; + + force_sig_ptrace_errno_trap(i, (void __user *)bkpt->address); +} + +static struct perf_event *ptrace_hbp_get_event(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx) +{ + struct perf_event *bp; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + if (idx >= LOONGARCH_MAX_BRP) + return ERR_PTR(-EINVAL); + idx = array_index_nospec(idx, LOONGARCH_MAX_BRP); + bp = tsk->thread.hbp_break[idx]; + break; + case NT_LOONGARCH_HW_WATCH: + if (idx >= LOONGARCH_MAX_WRP) + return ERR_PTR(-EINVAL); + idx = array_index_nospec(idx, LOONGARCH_MAX_WRP); + bp = tsk->thread.hbp_watch[idx]; + break; + } + + return bp; +} + +static int ptrace_hbp_set_event(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, + struct perf_event *bp) +{ + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + if (idx >= LOONGARCH_MAX_BRP) + return -EINVAL; + idx = array_index_nospec(idx, LOONGARCH_MAX_BRP); + tsk->thread.hbp_break[idx] = bp; + break; + case NT_LOONGARCH_HW_WATCH: + if (idx >= LOONGARCH_MAX_WRP) + return -EINVAL; + idx = array_index_nospec(idx, LOONGARCH_MAX_WRP); + tsk->thread.hbp_watch[idx] = bp; + break; + } + + return 0; +} + +static struct perf_event *ptrace_hbp_create(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx) +{ + int err, type; + struct perf_event *bp; + struct perf_event_attr attr; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + type = HW_BREAKPOINT_X; + break; + case NT_LOONGARCH_HW_WATCH: + type = HW_BREAKPOINT_RW; + break; + default: + return ERR_PTR(-EINVAL); + } + + ptrace_breakpoint_init(&attr); + + /* + * Initialise fields to sane defaults + * (i.e. values that will pass validation). + */ + attr.bp_addr = 0; + attr.bp_len = HW_BREAKPOINT_LEN_4; + attr.bp_type = type; + attr.disabled = 1; + + bp = register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL, tsk); + if (IS_ERR(bp)) + return bp; + + err = ptrace_hbp_set_event(note_type, tsk, idx, bp); + if (err) + return ERR_PTR(err); + + return bp; +} + +static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, + struct arch_hw_breakpoint_ctrl ctrl, + struct perf_event_attr *attr) +{ + int err, len, type, offset; + + err = arch_bp_generic_fields(ctrl, &len, &type, &offset); + if (err) + return err; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + if ((type & HW_BREAKPOINT_X) != type) + return -EINVAL; + break; + case NT_LOONGARCH_HW_WATCH: + if ((type & HW_BREAKPOINT_RW) != type) + return -EINVAL; + break; + default: + return -EINVAL; + } + + attr->bp_len = len; + attr->bp_type = type; + attr->bp_addr += offset; + + return 0; +} + +static int ptrace_hbp_get_resource_info(unsigned int note_type, u16 *info) +{ + u8 num; + u16 reg = 0; + + switch (note_type) { + case NT_LOONGARCH_HW_BREAK: + num = hw_breakpoint_slots(TYPE_INST); + break; + case NT_LOONGARCH_HW_WATCH: + num = hw_breakpoint_slots(TYPE_DATA); + break; + default: + return -EINVAL; + } + + *info = reg | num; + + return 0; +} + +static struct perf_event *ptrace_hbp_get_initialised_bp(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx) +{ + struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); + + if (!bp) + bp = ptrace_hbp_create(note_type, tsk, idx); + + return bp; +} + +static int ptrace_hbp_get_ctrl(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u32 *ctrl) +{ + struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); + + if (IS_ERR(bp)) + return PTR_ERR(bp); + + *ctrl = bp ? encode_ctrl_reg(counter_arch_bp(bp)->ctrl) : 0; + + return 0; +} + +static int ptrace_hbp_get_mask(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u64 *mask) +{ + struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); + + if (IS_ERR(bp)) + return PTR_ERR(bp); + + *mask = bp ? counter_arch_bp(bp)->mask : 0; + + return 0; +} + +static int ptrace_hbp_get_addr(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u64 *addr) +{ + struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); + + if (IS_ERR(bp)) + return PTR_ERR(bp); + + *addr = bp ? counter_arch_bp(bp)->address : 0; + + return 0; +} + +static int ptrace_hbp_set_ctrl(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u32 uctrl) +{ + int err; + struct perf_event *bp; + struct perf_event_attr attr; + struct arch_hw_breakpoint_ctrl ctrl; + + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); + if (IS_ERR(bp)) + return PTR_ERR(bp); + + attr = bp->attr; + decode_ctrl_reg(uctrl, &ctrl); + err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); + if (err) + return err; + + return modify_user_hw_breakpoint(bp, &attr); +} + +static int ptrace_hbp_set_mask(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u64 mask) +{ + struct perf_event *bp; + struct perf_event_attr attr; + struct arch_hw_breakpoint *info; + + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); + if (IS_ERR(bp)) + return PTR_ERR(bp); + + attr = bp->attr; + info = counter_arch_bp(bp); + info->mask = mask; + + return modify_user_hw_breakpoint(bp, &attr); +} + +static int ptrace_hbp_set_addr(unsigned int note_type, + struct task_struct *tsk, + unsigned long idx, u64 addr) +{ + struct perf_event *bp; + struct perf_event_attr attr; + + bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); + if (IS_ERR(bp)) + return PTR_ERR(bp); + + attr = bp->attr; + attr.bp_addr = addr; + + return modify_user_hw_breakpoint(bp, &attr); +} + +#define PTRACE_HBP_CTRL_SZ sizeof(u32) +#define PTRACE_HBP_ADDR_SZ sizeof(u64) +#define PTRACE_HBP_MASK_SZ sizeof(u64) + +static int hw_break_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + u16 info; + u32 ctrl; + u64 addr, mask; + int ret, idx = 0; + unsigned int note_type = regset->core_note_type; + + /* Resource info */ + ret = ptrace_hbp_get_resource_info(note_type, &info); + if (ret) + return ret; + + membuf_write(&to, &info, sizeof(info)); + + /* (address, ctrl) registers */ + while (to.left) { + ret = ptrace_hbp_get_addr(note_type, target, idx, &addr); + if (ret) + return ret; + + ret = ptrace_hbp_get_mask(note_type, target, idx, &mask); + if (ret) + return ret; + + ret = ptrace_hbp_get_ctrl(note_type, target, idx, &ctrl); + if (ret) + return ret; + + membuf_store(&to, addr); + membuf_store(&to, mask); + membuf_store(&to, ctrl); + idx++; + } + + return 0; +} + +static int hw_break_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + u32 ctrl; + u64 addr, mask; + int ret, idx = 0, offset, limit; + unsigned int note_type = regset->core_note_type; + + /* Resource info */ + offset = offsetof(struct user_watch_state, dbg_regs); + user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, offset); + + /* (address, ctrl) registers */ + limit = regset->n * regset->size; + while (count && offset < limit) { + if (count < PTRACE_HBP_ADDR_SZ) + return -EINVAL; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr, + offset, offset + PTRACE_HBP_ADDR_SZ); + if (ret) + return ret; + + ret = ptrace_hbp_set_addr(note_type, target, idx, addr); + if (ret) + return ret; + offset += PTRACE_HBP_ADDR_SZ; + + if (!count) + break; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &mask, + offset, offset + PTRACE_HBP_ADDR_SZ); + if (ret) + return ret; + + ret = ptrace_hbp_set_mask(note_type, target, idx, mask); + if (ret) + return ret; + offset += PTRACE_HBP_MASK_SZ; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &mask, + offset, offset + PTRACE_HBP_MASK_SZ); + if (ret) + return ret; + + ret = ptrace_hbp_set_ctrl(note_type, target, idx, ctrl); + if (ret) + return ret; + offset += PTRACE_HBP_CTRL_SZ; + idx++; + } + + return 0; +} + +#endif + struct pt_regs_offset { const char *name; int offset; @@ -319,6 +701,10 @@ enum loongarch_regset { REGSET_GPR, REGSET_FPR, REGSET_CPUCFG, +#ifdef CONFIG_HAVE_HW_BREAKPOINT + REGSET_HW_BREAK, + REGSET_HW_WATCH, +#endif }; static const struct user_regset loongarch64_regsets[] = { @@ -346,6 +732,24 @@ static const struct user_regset loongarch64_regsets[] = { .regset_get = cfg_get, .set = cfg_set, }, +#ifdef CONFIG_HAVE_HW_BREAKPOINT + [REGSET_HW_BREAK] = { + .core_note_type = NT_LOONGARCH_HW_BREAK, + .n = sizeof(struct user_watch_state) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .regset_get = hw_break_get, + .set = hw_break_set, + }, + [REGSET_HW_WATCH] = { + .core_note_type = NT_LOONGARCH_HW_WATCH, + .n = sizeof(struct user_watch_state) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .regset_get = hw_break_get, + .set = hw_break_set, + }, +#endif }; static const struct user_regset_view user_loongarch64_view = { @@ -431,3 +835,71 @@ long arch_ptrace(struct task_struct *child, long request, return ret; } + +#ifdef CONFIG_HAVE_HW_BREAKPOINT +static void ptrace_triggered(struct perf_event *bp, + struct perf_sample_data *data, struct pt_regs *regs) +{ + struct perf_event_attr attr; + + attr = bp->attr; + attr.disabled = true; + modify_user_hw_breakpoint(bp, &attr); +} + +static int set_single_step(struct task_struct *tsk, unsigned long addr) +{ + struct perf_event *bp; + struct perf_event_attr attr; + struct arch_hw_breakpoint *info; + struct thread_struct *thread = &tsk->thread; + + bp = thread->hbp_break[0]; + if (!bp) { + ptrace_breakpoint_init(&attr); + + attr.bp_addr = addr; + attr.bp_len = HW_BREAKPOINT_LEN_8; + attr.bp_type = HW_BREAKPOINT_X; + + bp = register_user_hw_breakpoint(&attr, ptrace_triggered, + NULL, tsk); + if (IS_ERR(bp)) + return PTR_ERR(bp); + + thread->hbp_break[0] = bp; + } else { + int err; + + attr = bp->attr; + attr.bp_addr = addr; + + /* Reenable breakpoint */ + attr.disabled = false; + err = modify_user_hw_breakpoint(bp, &attr); + if (unlikely(err)) + return err; + + csr_write64(attr.bp_addr, LOONGARCH_CSR_IB0ADDR); + } + info = counter_arch_bp(bp); + info->mask = TASK_SIZE - 1; + + return 0; +} + +/* ptrace API */ +void user_enable_single_step(struct task_struct *task) +{ + struct thread_info *ti = task_thread_info(task); + + set_single_step(task, task_pt_regs(task)->csr_era); + task->thread.single_step = task_pt_regs(task)->csr_era; + set_ti_thread_flag(ti, TIF_SINGLESTEP); +} + +void user_disable_single_step(struct task_struct *task) +{ + clear_tsk_thread_flag(task, TIF_SINGLESTEP); +} +#endif diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c new file mode 100644 index 0000000000000..01f94d1e3edf6 --- /dev/null +++ b/arch/loongarch/kernel/relocate.c @@ -0,0 +1,242 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Support for Kernel relocation at boot time + * + * Copyright (C) 2023 Loongson Technology Corporation Limited + */ + +#include <linux/elf.h> +#include <linux/kernel.h> +#include <linux/printk.h> +#include <linux/panic_notifier.h> +#include <linux/start_kernel.h> +#include <asm/bootinfo.h> +#include <asm/early_ioremap.h> +#include <asm/inst.h> +#include <asm/sections.h> +#include <asm/setup.h> + +#define RELOCATED(x) ((void *)((long)x + reloc_offset)) +#define RELOCATED_KASLR(x) ((void *)((long)x + random_offset)) + +static unsigned long reloc_offset; + +static inline void __init relocate_relative(void) +{ + Elf64_Rela *rela, *rela_end; + rela = (Elf64_Rela *)&__rela_dyn_begin; + rela_end = (Elf64_Rela *)&__rela_dyn_end; + + for ( ; rela < rela_end; rela++) { + Elf64_Addr addr = rela->r_offset; + Elf64_Addr relocated_addr = rela->r_addend; + + if (rela->r_info != R_LARCH_RELATIVE) + continue; + + if (relocated_addr >= VMLINUX_LOAD_ADDRESS) + relocated_addr = (Elf64_Addr)RELOCATED(relocated_addr); + + *(Elf64_Addr *)RELOCATED(addr) = relocated_addr; + } +} + +static inline void __init relocate_absolute(long random_offset) +{ + void *begin, *end; + struct rela_la_abs *p; + + begin = RELOCATED_KASLR(&__la_abs_begin); + end = RELOCATED_KASLR(&__la_abs_end); + + for (p = begin; (void *)p < end; p++) { + long v = p->symvalue; + uint32_t lu12iw, ori, lu32id, lu52id; + union loongarch_instruction *insn = (void *)p - p->offset; + + lu12iw = (v >> 12) & 0xfffff; + ori = v & 0xfff; + lu32id = (v >> 32) & 0xfffff; + lu52id = v >> 52; + + insn[0].reg1i20_format.immediate = lu12iw; + insn[1].reg2i12_format.immediate = ori; + insn[2].reg1i20_format.immediate = lu32id; + insn[3].reg2i12_format.immediate = lu52id; + } +} + +#ifdef CONFIG_RANDOMIZE_BASE +static inline __init unsigned long rotate_xor(unsigned long hash, + const void *area, size_t size) +{ + size_t i, diff; + const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash)); + + diff = (void *)ptr - area; + if (size < diff + sizeof(hash)) + return hash; + + size = ALIGN_DOWN(size - diff, sizeof(hash)); + + for (i = 0; i < size / sizeof(hash); i++) { + /* Rotate by odd number of bits and XOR. */ + hash = (hash << ((sizeof(hash) * 8) - 7)) | (hash >> 7); + hash ^= ptr[i]; + } + + return hash; +} + +static inline __init unsigned long get_random_boot(void) +{ + unsigned long hash = 0; + unsigned long entropy = random_get_entropy(); + + /* Attempt to create a simple but unpredictable starting entropy. */ + hash = rotate_xor(hash, linux_banner, strlen(linux_banner)); + + /* Add in any runtime entropy we can get */ + hash = rotate_xor(hash, &entropy, sizeof(entropy)); + + return hash; +} + +static inline __init bool kaslr_disabled(void) +{ + char *str; + const char *builtin_cmdline = CONFIG_CMDLINE; + + str = strstr(builtin_cmdline, "nokaslr"); + if (str == builtin_cmdline || (str > builtin_cmdline && *(str - 1) == ' ')) + return true; + + str = strstr(boot_command_line, "nokaslr"); + if (str == boot_command_line || (str > boot_command_line && *(str - 1) == ' ')) + return true; + + return false; +} + +/* Choose a new address for the kernel */ +static inline void __init *determine_relocation_address(void) +{ + unsigned long kernel_length; + unsigned long random_offset; + void *destination = _text; + + if (kaslr_disabled()) + return destination; + + kernel_length = (long)_end - (long)_text; + + random_offset = get_random_boot() << 16; + random_offset &= (CONFIG_RANDOMIZE_BASE_MAX_OFFSET - 1); + if (random_offset < kernel_length) + random_offset += ALIGN(kernel_length, 0xffff); + + return RELOCATED_KASLR(destination); +} + +static inline int __init relocation_addr_valid(void *location_new) +{ + if ((unsigned long)location_new & 0x00000ffff) + return 0; /* Inappropriately aligned new location */ + + if ((unsigned long)location_new < (unsigned long)_end) + return 0; /* New location overlaps original kernel */ + + return 1; +} +#endif + +static inline void __init update_reloc_offset(unsigned long *addr, long random_offset) +{ + unsigned long *new_addr = (unsigned long *)RELOCATED_KASLR(addr); + + *new_addr = (unsigned long)reloc_offset; +} + +void * __init relocate_kernel(void) +{ + unsigned long kernel_length; + unsigned long random_offset = 0; + void *location_new = _text; /* Default to original kernel start */ + void *kernel_entry = start_kernel; /* Default to original kernel entry point */ + char *cmdline = early_ioremap(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */ + + strscpy(boot_command_line, cmdline, COMMAND_LINE_SIZE); + +#ifdef CONFIG_RANDOMIZE_BASE + location_new = determine_relocation_address(); + + /* Sanity check relocation address */ + if (relocation_addr_valid(location_new)) + random_offset = (unsigned long)location_new - (unsigned long)(_text); +#endif + reloc_offset = (unsigned long)_text - VMLINUX_LOAD_ADDRESS; + + if (random_offset) { + kernel_length = (long)(_end) - (long)(_text); + + /* Copy the kernel to it's new location */ + memcpy(location_new, _text, kernel_length); + + /* Sync the caches ready for execution of new kernel */ + __asm__ __volatile__ ( + "ibar 0 \t\n" + "dbar 0 \t\n" + ::: "memory"); + + reloc_offset += random_offset; + + /* Return the new kernel's entry point */ + kernel_entry = RELOCATED_KASLR(start_kernel); + + /* The current thread is now within the relocated kernel */ + __current_thread_info = RELOCATED_KASLR(__current_thread_info); + + update_reloc_offset(&reloc_offset, random_offset); + } + + if (reloc_offset) + relocate_relative(); + + relocate_absolute(random_offset); + + return kernel_entry; +} + +/* + * Show relocation information on panic. + */ +static void show_kernel_relocation(const char *level) +{ + if (reloc_offset > 0) { + printk(level); + pr_cont("Kernel relocated by 0x%lx\n", reloc_offset); + pr_cont(" .text @ 0x%px\n", _text); + pr_cont(" .data @ 0x%px\n", _sdata); + pr_cont(" .bss @ 0x%px\n", __bss_start); + } +} + +static int kernel_location_notifier_fn(struct notifier_block *self, + unsigned long v, void *p) +{ + show_kernel_relocation(KERN_EMERG); + return NOTIFY_DONE; +} + +static struct notifier_block kernel_location_notifier = { + .notifier_call = kernel_location_notifier_fn +}; + +static int __init register_kernel_offset_dumper(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, + &kernel_location_notifier); + return 0; +} + +arch_initcall(register_kernel_offset_dumper); diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 4344502c0b317..bae84ccf6d367 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -234,11 +234,14 @@ static void __init arch_reserve_vmcore(void) #endif } +/* 2MB alignment for crash kernel regions */ +#define CRASH_ALIGN SZ_2M +#define CRASH_ADDR_MAX SZ_4G + static void __init arch_parse_crashkernel(void) { #ifdef CONFIG_KEXEC int ret; - unsigned long long start; unsigned long long total_mem; unsigned long long crash_base, crash_size; @@ -247,8 +250,13 @@ static void __init arch_parse_crashkernel(void) if (ret < 0 || crash_size <= 0) return; - start = memblock_phys_alloc_range(crash_size, 1, crash_base, crash_base + crash_size); - if (start != crash_base) { + if (crash_base <= 0) { + crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, CRASH_ALIGN, CRASH_ADDR_MAX); + if (!crash_base) { + pr_warn("crashkernel reservation failed - No suitable area found.\n"); + return; + } + } else if (!memblock_phys_alloc_range(crash_size, CRASH_ALIGN, crash_base, crash_base + crash_size)) { pr_warn("Invalid memory region reserved for crash kernel\n"); return; } diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index a6576dea590c0..4351f69d99501 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -140,16 +140,17 @@ static int get_timer_irq(void) int constant_clockevent_init(void) { - int irq; unsigned int cpu = smp_processor_id(); unsigned long min_delta = 0x600; unsigned long max_delta = (1UL << 48) - 1; struct clock_event_device *cd; - static int timer_irq_installed = 0; + static int irq = 0, timer_irq_installed = 0; - irq = get_timer_irq(); - if (irq < 0) - pr_err("Failed to map irq %d (timer)\n", irq); + if (!timer_irq_installed) { + irq = get_timer_irq(); + if (irq < 0) + pr_err("Failed to map irq %d (timer)\n", irq); + } cd = &per_cpu(constant_clockevent_device, cpu); diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index c38a146a973b4..de8ebe20b666c 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -371,9 +371,14 @@ int no_unaligned_warning __read_mostly = 1; /* Only 1 warning by default */ asmlinkage void noinstr do_ale(struct pt_regs *regs) { - unsigned int *pc; irqentry_state_t state = irqentry_enter(regs); +#ifndef CONFIG_ARCH_STRICT_ALIGN + die_if_kernel("Kernel ale access", regs); + force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr); +#else + unsigned int *pc; + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr); /* @@ -397,8 +402,8 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs) sigbus: die_if_kernel("Kernel ale access", regs); force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr); - out: +#endif irqentry_exit(regs, state); } @@ -432,7 +437,9 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs) unsigned long era = exception_era(regs); irqentry_state_t state = irqentry_enter(regs); - local_irq_enable(); + if (regs->csr_prmd & CSR_PRMD_PIE) + local_irq_enable(); + current->thread.trap_nr = read_csr_excode(); if (__get_inst(&opcode, (u32 *)era, user)) goto out_sigsegv; @@ -445,14 +452,12 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs) */ switch (bcode) { case BRK_KPROBE_BP: - if (notify_die(DIE_BREAK, "Kprobe", regs, bcode, - current->thread.trap_nr, SIGTRAP) == NOTIFY_STOP) + if (kprobe_breakpoint_handler(regs)) goto out; else break; case BRK_KPROBE_SSTEPBP: - if (notify_die(DIE_SSTEPBP, "Kprobe_SingleStep", regs, bcode, - current->thread.trap_nr, SIGTRAP) == NOTIFY_STOP) + if (kprobe_singlestep_handler(regs)) goto out; else break; @@ -495,7 +500,9 @@ asmlinkage void noinstr do_bp(struct pt_regs *regs) } out: - local_irq_disable(); + if (regs->csr_prmd & CSR_PRMD_PIE) + local_irq_disable(); + irqentry_exit(regs, state); return; @@ -506,7 +513,52 @@ out_sigsegv: asmlinkage void noinstr do_watch(struct pt_regs *regs) { + irqentry_state_t state = irqentry_enter(regs); + +#ifndef CONFIG_HAVE_HW_BREAKPOINT pr_warn("Hardware watch point handler not implemented!\n"); +#else + if (test_tsk_thread_flag(current, TIF_SINGLESTEP)) { + int llbit = (csr_read32(LOONGARCH_CSR_LLBCTL) & 0x1); + unsigned long pc = instruction_pointer(regs); + union loongarch_instruction *ip = (union loongarch_instruction *)pc; + + if (llbit) { + /* + * When the ll-sc combo is encountered, it is regarded as an single + * instruction. So don't clear llbit and reset CSR.FWPS.Skip until + * the llsc execution is completed. + */ + csr_write32(CSR_FWPC_SKIP, LOONGARCH_CSR_FWPS); + csr_write32(CSR_LLBCTL_KLO, LOONGARCH_CSR_LLBCTL); + goto out; + } + + if (pc == current->thread.single_step) { + /* + * Certain insns are occasionally not skipped when CSR.FWPS.Skip is + * set, such as fld.d/fst.d. So singlestep needs to compare whether + * the csr_era is equal to the value of singlestep which last time set. + */ + if (!is_self_loop_ins(ip, regs)) { + /* + * Check if the given instruction the target pc is equal to the + * current pc, If yes, then we should not set the CSR.FWPS.SKIP + * bit to break the original instruction stream. + */ + csr_write32(CSR_FWPC_SKIP, LOONGARCH_CSR_FWPS); + goto out; + } + } + } else { + breakpoint_handler(regs); + watchpoint_handler(regs); + } + + force_sig(SIGTRAP); +out: +#endif + irqentry_exit(regs, state); } asmlinkage void noinstr do_ri(struct pt_regs *regs) diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S index 78506b31ba61b..0c7b041be9d8d 100644 --- a/arch/loongarch/kernel/vmlinux.lds.S +++ b/arch/loongarch/kernel/vmlinux.lds.S @@ -65,10 +65,21 @@ SECTIONS __alt_instructions_end = .; } +#ifdef CONFIG_RELOCATABLE + . = ALIGN(8); + .la_abs : AT(ADDR(.la_abs) - LOAD_OFFSET) { + __la_abs_begin = .; + *(.la_abs) + __la_abs_end = .; + } +#endif + .got : ALIGN(16) { *(.got) } .plt : ALIGN(16) { *(.plt) } .got.plt : ALIGN(16) { *(.got.plt) } + .data.rel : { *(.data.rel*) } + . = ALIGN(PECOFF_SEGMENT_ALIGN); __init_begin = .; __inittext_begin = .; @@ -92,8 +103,6 @@ SECTIONS PERCPU_SECTION(1 << CONFIG_L1_CACHE_SHIFT) #endif - .rela.dyn : ALIGN(8) { *(.rela.dyn) *(.rela*) } - .init.bss : { *(.init.bss) } @@ -106,6 +115,12 @@ SECTIONS RO_DATA(4096) RW_DATA(1 << CONFIG_L1_CACHE_SHIFT, PAGE_SIZE, THREAD_SIZE) + .rela.dyn : ALIGN(8) { + __rela_dyn_begin = .; + *(.rela.dyn) *(.rela*) + __rela_dyn_end = .; + } + .sdata : { *(.sdata) } @@ -132,6 +147,7 @@ SECTIONS DISCARDS /DISCARD/ : { + *(.dynamic .dynsym .dynstr .hash .gnu.hash) *(.gnu.attributes) *(.options) *(.eh_frame) diff --git a/arch/loongarch/lib/memcpy.S b/arch/loongarch/lib/memcpy.S index 7c07d595ee89a..3b7e1dec71094 100644 --- a/arch/loongarch/lib/memcpy.S +++ b/arch/loongarch/lib/memcpy.S @@ -17,6 +17,7 @@ SYM_FUNC_START(memcpy) ALTERNATIVE "b __memcpy_generic", \ "b __memcpy_fast", CPU_FEATURE_UAL SYM_FUNC_END(memcpy) +_ASM_NOKPROBE(memcpy) EXPORT_SYMBOL(memcpy) @@ -41,6 +42,7 @@ SYM_FUNC_START(__memcpy_generic) 2: move a0, a3 jr ra SYM_FUNC_END(__memcpy_generic) +_ASM_NOKPROBE(__memcpy_generic) /* * void *__memcpy_fast(void *dst, const void *src, size_t n) @@ -93,3 +95,4 @@ SYM_FUNC_START(__memcpy_fast) 3: move a0, a3 jr ra SYM_FUNC_END(__memcpy_fast) +_ASM_NOKPROBE(__memcpy_fast) diff --git a/arch/loongarch/lib/memmove.S b/arch/loongarch/lib/memmove.S index 6ffdb46da78fd..b796c3d6da052 100644 --- a/arch/loongarch/lib/memmove.S +++ b/arch/loongarch/lib/memmove.S @@ -29,6 +29,7 @@ SYM_FUNC_START(memmove) b rmemcpy 4: b __rmemcpy_generic SYM_FUNC_END(memmove) +_ASM_NOKPROBE(memmove) EXPORT_SYMBOL(memmove) @@ -39,6 +40,7 @@ SYM_FUNC_START(rmemcpy) ALTERNATIVE "b __rmemcpy_generic", \ "b __rmemcpy_fast", CPU_FEATURE_UAL SYM_FUNC_END(rmemcpy) +_ASM_NOKPROBE(rmemcpy) /* * void *__rmemcpy_generic(void *dst, const void *src, size_t n) @@ -64,6 +66,7 @@ SYM_FUNC_START(__rmemcpy_generic) 2: move a0, a3 jr ra SYM_FUNC_END(__rmemcpy_generic) +_ASM_NOKPROBE(__rmemcpy_generic) /* * void *__rmemcpy_fast(void *dst, const void *src, size_t n) @@ -119,3 +122,4 @@ SYM_FUNC_START(__rmemcpy_fast) 3: move a0, a3 jr ra SYM_FUNC_END(__rmemcpy_fast) +_ASM_NOKPROBE(__rmemcpy_fast) diff --git a/arch/loongarch/lib/memset.S b/arch/loongarch/lib/memset.S index e7cb4ea3747d7..a9eb732ab2adb 100644 --- a/arch/loongarch/lib/memset.S +++ b/arch/loongarch/lib/memset.S @@ -23,6 +23,7 @@ SYM_FUNC_START(memset) ALTERNATIVE "b __memset_generic", \ "b __memset_fast", CPU_FEATURE_UAL SYM_FUNC_END(memset) +_ASM_NOKPROBE(memset) EXPORT_SYMBOL(memset) @@ -45,6 +46,7 @@ SYM_FUNC_START(__memset_generic) 2: move a0, a3 jr ra SYM_FUNC_END(__memset_generic) +_ASM_NOKPROBE(__memset_generic) /* * void *__memset_fast(void *s, int c, size_t n) @@ -89,3 +91,4 @@ SYM_FUNC_START(__memset_fast) 3: move a0, a3 jr ra SYM_FUNC_END(__memset_fast) +_ASM_NOKPROBE(__memset_fast) diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c index 1ccd53655cab0..449087bd589d3 100644 --- a/arch/loongarch/mm/fault.c +++ b/arch/loongarch/mm/fault.c @@ -135,6 +135,9 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, struct vm_area_struct *vma = NULL; vm_fault_t fault; + if (kprobe_page_fault(regs, current->thread.trap_nr)) + return; + /* * We fault-in kernel-space virtual memory on-demand. The * 'reference' page table is init_mm.pgd. diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index 58781c6e4191a..244e2f5aeee56 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -24,8 +24,7 @@ move a0, sp REG_S a2, sp, PT_BVADDR li.w a1, \write - la.abs t0, do_page_fault - jirl ra, t0, 0 + bl do_page_fault RESTORE_ALL_AND_RET SYM_FUNC_END(tlb_do_page_fault_\write) .endm @@ -40,7 +39,7 @@ SYM_FUNC_START(handle_tlb_protect) move a1, zero csrrd a2, LOONGARCH_CSR_BADV REG_S a2, sp, PT_BVADDR - la.abs t0, do_page_fault + la_abs t0, do_page_fault jirl ra, t0, 0 RESTORE_ALL_AND_RET SYM_FUNC_END(handle_tlb_protect) @@ -116,7 +115,7 @@ smp_pgtable_change_load: #ifdef CONFIG_64BIT vmalloc_load: - la.abs t1, swapper_pg_dir + la_abs t1, swapper_pg_dir b vmalloc_done_load #endif @@ -187,7 +186,7 @@ tlb_huge_update_load: nopage_tlb_load: dbar 0 csrrd ra, EXCEPTION_KS2 - la.abs t0, tlb_do_page_fault_0 + la_abs t0, tlb_do_page_fault_0 jr t0 SYM_FUNC_END(handle_tlb_load) @@ -263,7 +262,7 @@ smp_pgtable_change_store: #ifdef CONFIG_64BIT vmalloc_store: - la.abs t1, swapper_pg_dir + la_abs t1, swapper_pg_dir b vmalloc_done_store #endif @@ -336,7 +335,7 @@ tlb_huge_update_store: nopage_tlb_store: dbar 0 csrrd ra, EXCEPTION_KS2 - la.abs t0, tlb_do_page_fault_1 + la_abs t0, tlb_do_page_fault_1 jr t0 SYM_FUNC_END(handle_tlb_store) @@ -411,7 +410,7 @@ smp_pgtable_change_modify: #ifdef CONFIG_64BIT vmalloc_modify: - la.abs t1, swapper_pg_dir + la_abs t1, swapper_pg_dir b vmalloc_done_modify #endif @@ -483,7 +482,7 @@ tlb_huge_update_modify: nopage_tlb_modify: dbar 0 csrrd ra, EXCEPTION_KS2 - la.abs t0, tlb_do_page_fault_1 + la_abs t0, tlb_do_page_fault_1 jr t0 SYM_FUNC_END(handle_tlb_modify) diff --git a/arch/loongarch/power/suspend_asm.S b/arch/loongarch/power/suspend_asm.S index eb2675642f9f4..90da899c06a19 100644 --- a/arch/loongarch/power/suspend_asm.S +++ b/arch/loongarch/power/suspend_asm.S @@ -78,9 +78,8 @@ SYM_INNER_LABEL(loongarch_wakeup_start, SYM_L_GLOBAL) li.d t0, CSR_DMW1_INIT # CA, PLV0 csrwr t0, LOONGARCH_CSR_DMWIN1 - la.abs t0, 0f - jr t0 -0: + JUMP_VIRT_ADDR t0, t1 + la.pcrel t0, acpi_saved_sp ld.d sp, t0, 0 SETUP_WAKEUP diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 68de6f4c4eee3..ac3da855fb197 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -445,6 +445,8 @@ typedef struct elf64_shdr { #define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */ #define NT_LOONGARCH_LASX 0xa03 /* LoongArch Loongson Advanced SIMD Extension registers */ #define NT_LOONGARCH_LBT 0xa04 /* LoongArch Loongson Binary Translation registers */ +#define NT_LOONGARCH_HW_BREAK 0xa05 /* LoongArch hardware breakpoint registers */ +#define NT_LOONGARCH_HW_WATCH 0xa06 /* LoongArch hardware watchpoint registers */ /* Note types with note name "GNU" */ #define NT_GNU_PROPERTY_TYPE_0 5 diff --git a/samples/kprobes/kprobe_example.c b/samples/kprobes/kprobe_example.c index fd346f58ddbaf..ef44c614c6d90 100644 --- a/samples/kprobes/kprobe_example.c +++ b/samples/kprobes/kprobe_example.c @@ -55,6 +55,10 @@ static int __kprobes handler_pre(struct kprobe *p, struct pt_regs *regs) pr_info("<%s> p->addr, 0x%p, ip = 0x%lx, flags = 0x%lx\n", p->symbol_name, p->addr, regs->psw.addr, regs->flags); #endif +#ifdef CONFIG_LOONGARCH + pr_info("<%s> p->addr = 0x%p, era = 0x%lx, estat = 0x%lx\n", + p->symbol_name, p->addr, regs->csr_era, regs->csr_estat); +#endif /* A dump_stack() here will give a stack backtrace */ return 0; @@ -92,6 +96,10 @@ static void __kprobes handler_post(struct kprobe *p, struct pt_regs *regs, pr_info("<%s> p->addr, 0x%p, flags = 0x%lx\n", p->symbol_name, p->addr, regs->flags); #endif +#ifdef CONFIG_LOONGARCH + pr_info("<%s> p->addr = 0x%p, estat = 0x%lx\n", + p->symbol_name, p->addr, regs->csr_estat); +#endif } static int __init kprobe_init(void) diff --git a/tools/arch/loongarch/include/uapi/asm/bitsperlong.h b/tools/arch/loongarch/include/uapi/asm/bitsperlong.h new file mode 100644 index 0000000000000..d4e32b3d48437 --- /dev/null +++ b/tools/arch/loongarch/include/uapi/asm/bitsperlong.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_LOONGARCH_BITSPERLONG_H +#define __ASM_LOONGARCH_BITSPERLONG_H + +#define __BITS_PER_LONG (__SIZEOF_POINTER__ * 8) + +#include <asm-generic/bitsperlong.h> + +#endif /* __ASM_LOONGARCH_BITSPERLONG_H */ diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch index 0c6c7f4568878..1c72d07cb9fed 100644 --- a/tools/scripts/Makefile.arch +++ b/tools/scripts/Makefile.arch @@ -5,7 +5,7 @@ HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ -e s/s390x/s390/ -e s/parisc64/parisc/ \ -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ - -e s/riscv.*/riscv/) + -e s/riscv.*/riscv/ -e s/loongarch.*/loongarch/) ifndef ARCH ARCH := $(HOSTARCH) @@ -34,6 +34,15 @@ ifeq ($(ARCH),sh64) SRCARCH := sh endif +# Additional ARCH settings for loongarch +ifeq ($(ARCH),loongarch32) + SRCARCH := loongarch +endif + +ifeq ($(ARCH),loongarch64) + SRCARCH := loongarch +endif + LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1) ifeq ($(LP64), 1) IS_64_BIT := 1 diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc index 4597415652221..a4f8e7c53c1f7 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc @@ -28,6 +28,9 @@ s390*) mips*) ARG1=%r4 ;; +loongarch*) + ARG1=%r4 +;; *) echo "Please implement other architecture here" exit_untested diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc index d4662c8cf407f..1df61e13a812b 100644 --- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc @@ -40,6 +40,10 @@ mips*) GOODREG=%r4 BADREG=%r12 ;; +loongarch*) + GOODREG=%r4 + BADREG=%r12 +;; *) echo "Please implement other architecture here" exit_untested diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 61386e499b77d..43ec36b179dc0 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -128,6 +128,8 @@ struct seccomp_data { # define __NR_seccomp 277 # elif defined(__csky__) # define __NR_seccomp 277 +# elif defined(__loongarch__) +# define __NR_seccomp 277 # elif defined(__hppa__) # define __NR_seccomp 338 # elif defined(__powerpc__) @@ -1755,6 +1757,10 @@ TEST_F(TRACE_poke, getpid_runs_normally) NT_ARM_SYSTEM_CALL, &__v)); \ } while (0) # define SYSCALL_RET(_regs) (_regs).regs[0] +#elif defined(__loongarch__) +# define ARCH_REGS struct user_pt_regs +# define SYSCALL_NUM(_regs) (_regs).regs[11] +# define SYSCALL_RET(_regs) (_regs).regs[4] #elif defined(__riscv) && __riscv_xlen == 64 # define ARCH_REGS struct user_regs_struct # define SYSCALL_NUM(_regs) (_regs).a7 |