diff options
Diffstat (limited to 'arch/powerpc')
| -rw-r--r-- | arch/powerpc/Kconfig | 2 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/ftrace.h | 14 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/module.h | 16 | ||||
| -rw-r--r-- | arch/powerpc/include/asm/topology.h | 1 | ||||
| -rw-r--r-- | arch/powerpc/kernel/ftrace.c | 473 | ||||
| -rw-r--r-- | arch/powerpc/kernel/idle.c | 5 | ||||
| -rw-r--r-- | arch/powerpc/kernel/module_32.c | 10 | ||||
| -rw-r--r-- | arch/powerpc/kernel/module_64.c | 13 |
8 files changed, 490 insertions, 44 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 525c13a..adb23ea 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -141,7 +141,7 @@ config GENERIC_NVRAM bool default y if PPC32 -config SCHED_NO_NO_OMIT_FRAME_POINTER +config SCHED_OMIT_FRAME_POINTER bool default y diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index b298f7a..e5f2ae8 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -7,7 +7,19 @@ #ifndef __ASSEMBLY__ extern void _mcount(void); -#endif + +#ifdef CONFIG_DYNAMIC_FTRACE +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + /* reloction of mcount call site is the same as the address */ + return addr; +} + +struct dyn_arch_ftrace { + struct module *mod; +}; +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index e5f14b1..0845488 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -34,11 +34,19 @@ struct mod_arch_specific { #ifdef __powerpc64__ unsigned int stubs_section; /* Index of stubs section in module */ unsigned int toc_section; /* What section is the TOC? */ -#else +#ifdef CONFIG_DYNAMIC_FTRACE + unsigned long toc; + unsigned long tramp; +#endif + +#else /* powerpc64 */ /* Indices of PLT sections within module. */ unsigned int core_plt_section; unsigned int init_plt_section; +#ifdef CONFIG_DYNAMIC_FTRACE + unsigned long tramp; #endif +#endif /* powerpc64 */ /* List of BUG addresses, source line numbers and filenames */ struct list_head bug_list; @@ -68,6 +76,12 @@ struct mod_arch_specific { # endif /* MODULE */ #endif +#ifdef CONFIG_DYNAMIC_FTRACE +# ifdef MODULE + asm(".section .ftrace.tramp,\"ax\",@nobits; .align 3; .previous"); +# endif /* MODULE */ +#endif + struct exception_table_entry; void sort_ex_table(struct exception_table_entry *start, diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index c32da6f..373fca3 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -48,7 +48,6 @@ static inline int pcibus_to_node(struct pci_bus *bus) /* sched_domains SD_NODE_INIT for PPC64 machines */ #define SD_NODE_INIT (struct sched_domain) { \ - .span = CPU_MASK_NONE, \ .parent = NULL, \ .child = NULL, \ .groups = NULL, \ diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index f4b006e..3271cd6 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -9,22 +9,30 @@ #include <linux/spinlock.h> #include <linux/hardirq.h> +#include <linux/uaccess.h> +#include <linux/module.h> #include <linux/ftrace.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/list.h> #include <asm/cacheflush.h> +#include <asm/code-patching.h> #include <asm/ftrace.h> +#if 0 +#define DEBUGP printk +#else +#define DEBUGP(fmt , ...) do { } while (0) +#endif -static unsigned int ftrace_nop = 0x60000000; +static unsigned int ftrace_nop = PPC_NOP_INSTR; #ifdef CONFIG_PPC32 # define GET_ADDR(addr) addr #else /* PowerPC64's functions are data that points to the functions */ -# define GET_ADDR(addr) *(unsigned long *)addr +# define GET_ADDR(addr) (*(unsigned long *)addr) #endif @@ -33,12 +41,12 @@ static unsigned int ftrace_calc_offset(long ip, long addr) return (int)(addr - ip); } -unsigned char *ftrace_nop_replace(void) +static unsigned char *ftrace_nop_replace(void) { return (char *)&ftrace_nop; } -unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) { static unsigned int op; @@ -68,49 +76,434 @@ unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) # define _ASM_PTR " .long " #endif -int +static int ftrace_modify_code(unsigned long ip, unsigned char *old_code, unsigned char *new_code) { - unsigned replaced; - unsigned old = *(unsigned *)old_code; - unsigned new = *(unsigned *)new_code; - int faulted = 0; + unsigned char replaced[MCOUNT_INSN_SIZE]; /* * Note: Due to modules and __init, code can * disappear and change, we need to protect against faulting - * as well as code changing. + * as well as code changing. We do this by using the + * probe_kernel_* functions. * * No real locking needed, this code is run through - * kstop_machine. + * kstop_machine, or before SMP starts. */ - asm volatile ( - "1: lwz %1, 0(%2)\n" - " cmpw %1, %5\n" - " bne 2f\n" - " stwu %3, 0(%2)\n" - "2:\n" - ".section .fixup, \"ax\"\n" - "3: li %0, 1\n" - " b 2b\n" - ".previous\n" - ".section __ex_table,\"a\"\n" - _ASM_ALIGN "\n" - _ASM_PTR "1b, 3b\n" - ".previous" - : "=r"(faulted), "=r"(replaced) - : "r"(ip), "r"(new), - "0"(faulted), "r"(old) - : "memory"); - - if (replaced != old && replaced != new) - faulted = 2; - - if (!faulted) - flush_icache_range(ip, ip + 8); - - return faulted; + + /* read the text we want to modify */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure it is what we expect it to be */ + if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) + return -EINVAL; + + /* replace the text with the new text */ + if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) + return -EPERM; + + flush_icache_range(ip, ip + 8); + + return 0; +} + +/* + * Helper functions that are the same for both PPC64 and PPC32. + */ +static int test_24bit_addr(unsigned long ip, unsigned long addr) +{ + long diff; + + /* + * Can we get to addr from ip in 24 bits? + * (26 really, since we mulitply by 4 for 4 byte alignment) + */ + diff = addr - ip; + + /* + * Return true if diff is less than 1 << 25 + * and greater than -1 << 26. + */ + return (diff < (1 << 25)) && (diff > (-1 << 26)); +} + +static int is_bl_op(unsigned int op) +{ + return (op & 0xfc000003) == 0x48000001; +} + +static int test_offset(unsigned long offset) +{ + return (offset + 0x2000000 > 0x3ffffff) || ((offset & 3) != 0); +} + +static unsigned long find_bl_target(unsigned long ip, unsigned int op) +{ + static int offset; + + offset = (op & 0x03fffffc); + /* make it signed */ + if (offset & 0x02000000) + offset |= 0xfe000000; + + return ip + (long)offset; +} + +static unsigned int branch_offset(unsigned long offset) +{ + /* return "bl ip+offset" */ + return 0x48000001 | (offset & 0x03fffffc); +} + +#ifdef CONFIG_PPC64 +static int +__ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char replaced[MCOUNT_INSN_SIZE * 2]; + unsigned int *op = (unsigned *)&replaced; + unsigned char jmp[8]; + unsigned long *ptr = (unsigned long *)&jmp; + unsigned long ip = rec->ip; + unsigned long tramp; + int offset; + + /* read where this goes */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure that that this is still a 24bit jump */ + if (!is_bl_op(*op)) { + printk(KERN_ERR "Not expected bl: opcode is %x\n", *op); + return -EINVAL; + } + + /* lets find where the pointer goes */ + tramp = find_bl_target(ip, *op); + + /* + * On PPC64 the trampoline looks like: + * 0x3d, 0x82, 0x00, 0x00, addis r12,r2, <high> + * 0x39, 0x8c, 0x00, 0x00, addi r12,r12, <low> + * Where the bytes 2,3,6 and 7 make up the 32bit offset + * to the TOC that holds the pointer. + * to jump to. + * 0xf8, 0x41, 0x00, 0x28, std r2,40(r1) + * 0xe9, 0x6c, 0x00, 0x20, ld r11,32(r12) + * The actually address is 32 bytes from the offset + * into the TOC. + * 0xe8, 0x4c, 0x00, 0x28, ld r2,40(r12) + */ + + DEBUGP("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc); + + /* Find where the trampoline jumps to */ + if (probe_kernel_read(jmp, (void *)tramp, 8)) { + printk(KERN_ERR "Failed to read %lx\n", tramp); + return -EFAULT; + } + + DEBUGP(" %08x %08x", + (unsigned)(*ptr >> 32), + (unsigned)*ptr); + + offset = (unsigned)jmp[2] << 24 | + (unsigned)jmp[3] << 16 | + (unsigned)jmp[6] << 8 | + (unsigned)jmp[7]; + + DEBUGP(" %x ", offset); + + /* get the address this jumps too */ + tramp = mod->arch.toc + offset + 32; + DEBUGP("toc: %lx", tramp); + + if (probe_kernel_read(jmp, (void *)tramp, 8)) { + printk(KERN_ERR "Failed to read %lx\n", tramp); + return -EFAULT; + } + + DEBUGP(" %08x %08x\n", + (unsigned)(*ptr >> 32), + (unsigned)*ptr); + + /* This should match what was called */ + if (*ptr != GET_ADDR(addr)) { + printk(KERN_ERR "addr does not match %lx\n", *ptr); + return -EINVAL; + } + + /* + * We want to nop the line, but the next line is + * 0xe8, 0x41, 0x00, 0x28 ld r2,40(r1) + * This needs to be turned to a nop too. + */ + if (probe_kernel_read(replaced, (void *)(ip+4), MCOUNT_INSN_SIZE)) + return -EFAULT; + + if (*op != 0xe8410028) { + printk(KERN_ERR "Next line is not ld! (%08x)\n", *op); + return -EINVAL; + } + + /* + * Milton Miller pointed out that we can not blindly do nops. + * If a task was preempted when calling a trace function, + * the nops will remove the way to restore the TOC in r2 + * and the r2 TOC will get corrupted. + */ + + /* + * Replace: + * bl <tramp> <==== will be replaced with "b 1f" + * ld r2,40(r1) + * 1: + */ + op[0] = 0x48000008; /* b +8 */ + + if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE)) + return -EPERM; + + return 0; +} + +#else /* !PPC64 */ +static int +__ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char replaced[MCOUNT_INSN_SIZE]; + unsigned int *op = (unsigned *)&replaced; + unsigned char jmp[8]; + unsigned int *ptr = (unsigned int *)&jmp; + unsigned long ip = rec->ip; + unsigned long tramp; + int offset; + + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Make sure that that this is still a 24bit jump */ + if (!is_bl_op(*op)) { + printk(KERN_ERR "Not expected bl: opcode is %x\n", *op); + return -EINVAL; + } + + /* lets find where the pointer goes */ + tramp = find_bl_target(ip, *op); + + /* + * On PPC32 the trampoline looks like: + * lis r11,sym@ha + * addi r11,r11,sym@l + * mtctr r11 + * bctr + */ + + DEBUGP("ip:%lx jumps to %lx", ip, tramp); + + /* Find where the trampoline jumps to */ + if (probe_kernel_read(jmp, (void *)tramp, 8)) { + printk(KERN_ERR "Failed to read %lx\n", tramp); + return -EFAULT; + } + + DEBUGP(" %08x %08x ", ptr[0], ptr[1]); + + tramp = (ptr[1] & 0xffff) | + ((ptr[0] & 0xffff) << 16); + if (tramp & 0x8000) + tramp -= 0x10000; + + DEBUGP(" %x ", tramp); + + if (tramp != addr) { + printk(KERN_ERR + "Trampoline location %08lx does not match addr\n", + tramp); + return -EINVAL; + } + + op[0] = PPC_NOP_INSTR; + + if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE)) + return -EPERM; + + return 0; +} +#endif /* PPC64 */ + +int ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char *old, *new; + unsigned long ip = rec->ip; + + /* + * If the calling address is more that 24 bits away, + * then we had to use a trampoline to make the call. + * Otherwise just update the call site. + */ + if (test_24bit_addr(ip, addr)) { + /* within range */ + old = ftrace_call_replace(ip, addr); + new = ftrace_nop_replace(); + return ftrace_modify_code(ip, old, new); + } + + /* + * Out of range jumps are called from modules. + * We should either already have a pointer to the module + * or it has been passed in. + */ + if (!rec->arch.mod) { + if (!mod) { + printk(KERN_ERR "No module loaded addr=%lx\n", + addr); + return -EFAULT; + } + rec->arch.mod = mod; + } else if (mod) { + if (mod != rec->arch.mod) { + printk(KERN_ERR + "Record mod %p not equal to passed in mod %p\n", + rec->arch.mod, mod); + return -EINVAL; + } + /* nothing to do if mod == rec->arch.mod */ + } else + mod = rec->arch.mod; + + return __ftrace_make_nop(mod, rec, addr); + +} + +#ifdef CONFIG_PPC64 +static int +__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char replaced[MCOUNT_INSN_SIZE * 2]; + unsigned int *op = (unsigned *)&replaced; + unsigned long ip = rec->ip; + unsigned long offset; + + /* read where this goes */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE * 2)) + return -EFAULT; + + /* + * It should be pointing to two nops or + * b +8; ld r2,40(r1) + */ + if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) && + ((op[0] != PPC_NOP_INSTR) || (op[1] != PPC_NOP_INSTR))) { + printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]); + return -EINVAL; + } + + /* If we never set up a trampoline to ftrace_caller, then bail */ + if (!rec->arch.mod->arch.tramp) { + printk(KERN_ERR "No ftrace trampoline\n"); + return -EINVAL; + } + + /* now calculate a jump to the ftrace caller trampoline */ + offset = rec->arch.mod->arch.tramp - ip; + + if (test_offset(offset)) { + printk(KERN_ERR "REL24 %li out of range!\n", + (long int)offset); + return -EINVAL; + } + + /* Set to "bl addr" */ + op[0] = branch_offset(offset); + /* ld r2,40(r1) */ + op[1] = 0xe8410028; + + DEBUGP("write to %lx\n", rec->ip); + + if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE * 2)) + return -EPERM; + + return 0; +} +#else +static int +__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char replaced[MCOUNT_INSN_SIZE]; + unsigned int *op = (unsigned *)&replaced; + unsigned long ip = rec->ip; + unsigned long offset; + + /* read where this goes */ + if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* It should be pointing to a nop */ + if (op[0] != PPC_NOP_INSTR) { + printk(KERN_ERR "Expected NOP but have %x\n", op[0]); + return -EINVAL; + } + + /* If we never set up a trampoline to ftrace_caller, then bail */ + if (!rec->arch.mod->arch.tramp) { + printk(KERN_ERR "No ftrace trampoline\n"); + return -EINVAL; + } + + /* now calculate a jump to the ftrace caller trampoline */ + offset = rec->arch.mod->arch.tramp - ip; + + if (test_offset(offset)) { + printk(KERN_ERR "REL24 %li out of range!\n", + (long int)offset); + return -EINVAL; + } + + /* Set to "bl addr" */ + op[0] = branch_offset(offset); + + DEBUGP("write to %lx\n", rec->ip); + + if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE)) + return -EPERM; + + return 0; +} +#endif /* CONFIG_PPC64 */ + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char *old, *new; + unsigned long ip = rec->ip; + + /* + * If the calling address is more that 24 bits away, + * then we had to use a trampoline to make the call. + * Otherwise just update the call site. + */ + if (test_24bit_addr(ip, addr)) { + /* within range */ + old = ftrace_nop_replace(); + new = ftrace_call_replace(ip, addr); + return ftrace_modify_code(ip, old, new); + } + + /* + * Out of range jumps are called from modules. + * Being that we are converting from nop, it had better + * already have a module defined. + */ + if (!rec->arch.mod) { + printk(KERN_ERR "No module loaded\n"); + return -EINVAL; + } + + return __ftrace_make_call(rec, addr); } int ftrace_update_ftrace_func(ftrace_func_t func) @@ -128,10 +521,10 @@ int ftrace_update_ftrace_func(ftrace_func_t func) int __init ftrace_dyn_arch_init(void *data) { - /* This is running in kstop_machine */ + /* caller expects data to be zero */ + unsigned long *p = data; - ftrace_mcount_set(data); + *p = 0; return 0; } - diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 31982d0..88d9c1d 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -69,10 +69,15 @@ void cpu_idle(void) smp_mb(); local_irq_disable(); + /* Don't trace irqs off for idle */ + stop_critical_timings(); + /* check again after disabling irqs */ if (!need_resched() && !cpu_should_die()) ppc_md.power_save(); + start_critical_timings(); + local_irq_enable(); set_thread_flag(TIF_POLLING_NRFLAG); diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index 2df91a0..f832773 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -22,6 +22,7 @@ #include <linux/fs.h> #include <linux/string.h> #include <linux/kernel.h> +#include <linux/ftrace.h> #include <linux/cache.h> #include <linux/bug.h> #include <linux/sort.h> @@ -53,6 +54,9 @@ static unsigned int count_relocs(const Elf32_Rela *rela, unsigned int num) r_addend = rela[i].r_addend; } +#ifdef CONFIG_DYNAMIC_FTRACE + _count_relocs++; /* add one for ftrace_caller */ +#endif return _count_relocs; } @@ -306,5 +310,11 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, return -ENOEXEC; } } +#ifdef CONFIG_DYNAMIC_FTRACE + module->arch.tramp = + do_plt_call(module->module_core, + (unsigned long)ftrace_caller, + sechdrs, module); +#endif return 0; } diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 1af2377..8992b03 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -20,6 +20,7 @@ #include <linux/moduleloader.h> #include <linux/err.h> #include <linux/vmalloc.h> +#include <linux/ftrace.h> #include <linux/bug.h> #include <asm/module.h> #include <asm/firmware.h> @@ -163,6 +164,11 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, } } +#ifdef CONFIG_DYNAMIC_FTRACE + /* make the trampoline to the ftrace_caller */ + relocs++; +#endif + DEBUGP("Looks like a total of %lu stubs, max\n", relocs); return relocs * sizeof(struct ppc64_stub_entry); } @@ -441,5 +447,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, } } +#ifdef CONFIG_DYNAMIC_FTRACE + me->arch.toc = my_r2(sechdrs, me); + me->arch.tramp = stub_for_addr(sechdrs, + (unsigned long)ftrace_caller, + me); +#endif + return 0; } |
