From 4d296c24326783bff1282ac72f310d8bac8df413 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Oct 2008 09:33:06 -0400 Subject: ftrace: remove mcount set The arch dependent function ftrace_mcount_set was only used by the daemon start up code. This patch removes it. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/ftrace.c | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'arch/powerpc/kernel/ftrace.c') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 3855ceb937b..6b75522e8b3 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -126,23 +126,6 @@ notrace int ftrace_update_ftrace_func(ftrace_func_t func) return ret; } -notrace int ftrace_mcount_set(unsigned long *data) -{ - unsigned long ip = (long)(&mcount_call); - unsigned long *addr = data; - unsigned char old[MCOUNT_INSN_SIZE], *new; - - /* - * Replace the mcount stub with a pointer to the - * ip recorder function. - */ - memcpy(old, &mcount_call, MCOUNT_INSN_SIZE); - new = ftrace_call_replace(ip, *addr); - *addr = ftrace_modify_code(ip, old, new); - - return 0; -} - int __init ftrace_dyn_arch_init(void *data) { /* This is running in kstop_machine */ -- cgit v1.2.3 From 15adc048986f6b54b6044f2b6fc4b48f49413e2f Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 23 Oct 2008 09:33:08 -0400 Subject: ftrace, powerpc, sparc64, x86: remove notrace from arch ftrace file The entire file of ftrace.c in the arch code needs to be marked as notrace. It is much cleaner to do this from the Makefile with CFLAGS_REMOVE_ftrace.o. [ powerpc already had this in its Makefile. ] Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/ftrace.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel/ftrace.c') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 6b75522e8b3..f4b006ed0ab 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -28,17 +28,17 @@ static unsigned int ftrace_nop = 0x60000000; #endif -static unsigned int notrace ftrace_calc_offset(long ip, long addr) +static unsigned int ftrace_calc_offset(long ip, long addr) { return (int)(addr - ip); } -notrace unsigned char *ftrace_nop_replace(void) +unsigned char *ftrace_nop_replace(void) { return (char *)&ftrace_nop; } -notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) +unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) { static unsigned int op; @@ -68,7 +68,7 @@ notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr) # define _ASM_PTR " .long " #endif -notrace int +int ftrace_modify_code(unsigned long ip, unsigned char *old_code, unsigned char *new_code) { @@ -113,7 +113,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, return faulted; } -notrace int ftrace_update_ftrace_func(ftrace_func_t func) +int ftrace_update_ftrace_func(ftrace_func_t func) { unsigned long ip = (unsigned long)(&ftrace_call); unsigned char old[MCOUNT_INSN_SIZE], *new; -- cgit v1.2.3 From 8fd6e5a8c81e2e9b912ea33c8425a10729db469b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 14 Nov 2008 16:21:19 -0800 Subject: powerpc: ftrace, convert to new dynamic ftrace arch API Impact: update to PowerPC ftrace arch API This patch converts PowerPC to use the new dynamic ftrace arch API. Thanks to Paul Mackennas for pointing out the mistakes of my original test_24bit_addr function. Signed-off-by: Steven Rostedt --- arch/powerpc/kernel/ftrace.c | 67 ++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 62 insertions(+), 5 deletions(-) (limited to 'arch/powerpc/kernel/ftrace.c') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index f4b006ed0ab..24c023a5cae 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -33,12 +33,12 @@ 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; @@ -68,7 +68,7 @@ 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) { @@ -113,6 +113,62 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, return faulted; } +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)); +} + +int ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char *old, *new; + + /* + * 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(rec->ip, addr)) { + /* within range */ + old = ftrace_call_replace(rec->ip, addr); + new = ftrace_nop_replace(); + return ftrace_modify_code(rec->ip, old, new); + } + + return 0; +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned char *old, *new; + + /* + * 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(rec->ip, addr)) { + /* within range */ + old = ftrace_nop_replace(); + new = ftrace_call_replace(rec->ip, addr); + return ftrace_modify_code(rec->ip, old, new); + } + + return 0; +} + int ftrace_update_ftrace_func(ftrace_func_t func) { unsigned long ip = (unsigned long)(&ftrace_call); @@ -128,9 +184,10 @@ 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; } -- cgit v1.2.3 From e4486fe316895e87672a563c4f36393218f84ff1 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 14 Nov 2008 16:21:20 -0800 Subject: powerpc: ftrace, use probe_kernel API to modify code Impact: use cleaner probe_kernel API over assembly Using probe_kernel_read/write interface is a much cleaner approach than the current assembly version. Signed-off-by: Steven Rostedt --- arch/powerpc/kernel/ftrace.c | 53 ++++++++++++++++++-------------------------- 1 file changed, 21 insertions(+), 32 deletions(-) (limited to 'arch/powerpc/kernel/ftrace.c') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 24c023a5cae..1adfbb268d8 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -72,45 +73,33 @@ 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; } static int test_24bit_addr(unsigned long ip, unsigned long addr) -- cgit v1.2.3 From f48cb8b48b0b10025ca9c451b9b32cac3fcd33ba Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 14 Nov 2008 20:47:03 -0800 Subject: powerpc/ppc64: ftrace, handle module trampolines for dyn ftrace Impact: Allow 64 bit PowerPC to trace modules with dynamic ftrace This adds code to handle the PPC64 module trampolines, and allows for PPC64 to use dynamic ftrace. Thanks to Paul Mackerras for these updates: - fix the mod and rec->arch.mod NULL checks. - fix to is_bl_op compare. Thanks to Milton Miller for: - finding the nasty race with using two nops, and recommending instead that I use a branch 8 forward. Signed-off-by: Steven Rostedt --- arch/powerpc/kernel/ftrace.c | 278 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 268 insertions(+), 10 deletions(-) (limited to 'arch/powerpc/kernel/ftrace.c') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 1adfbb268d8..1aec559bdfc 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -10,22 +10,29 @@ #include #include #include +#include #include #include #include #include #include +#include #include +#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 @@ -102,6 +109,9 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, 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; @@ -119,43 +129,292 @@ static int test_24bit_addr(unsigned long ip, unsigned long addr) 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, + * 0x39, 0x8c, 0x00, 0x00, addi r12,r12, + * 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 <==== 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) +{ + /* Ignore modules for PPC32 (for now) */ + 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(rec->ip, addr)) { + if (test_24bit_addr(ip, addr)) { /* within range */ - old = ftrace_call_replace(rec->ip, addr); + old = ftrace_call_replace(ip, addr); new = ftrace_nop_replace(); - return ftrace_modify_code(rec->ip, old, new); + return ftrace_modify_code(ip, old, new); + } + +#ifdef CONFIG_PPC64 + /* + * 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; +#endif /* CONFIG_PPC64 */ + + 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) +{ + /* PPC32 ignores modules for now */ + 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(rec->ip, addr)) { + if (test_24bit_addr(ip, addr)) { /* within range */ old = ftrace_nop_replace(); - new = ftrace_call_replace(rec->ip, addr); - return ftrace_modify_code(rec->ip, old, new); + new = ftrace_call_replace(ip, addr); + return ftrace_modify_code(ip, old, new); } - return 0; +#ifdef CONFIG_PPC64 + /* + * 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; + } +#endif + + return __ftrace_make_call(rec, addr); } int ftrace_update_ftrace_func(ftrace_func_t func) @@ -180,4 +439,3 @@ int __init ftrace_dyn_arch_init(void *data) return 0; } - -- cgit v1.2.3 From 7cc45e64323c8a1042f56e6a8d1dc982f98d52a8 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Sat, 15 Nov 2008 02:39:05 -0500 Subject: powerpc/ppc32: ftrace, dynamic ftrace to handle modules Impact: add ability to trace modules on 32 bit PowerPC This patch performs the necessary trampoline calls to handle modules with dynamic ftrace on 32 bit PowerPC. Signed-off-by: Steven Rostedt --- arch/powerpc/kernel/ftrace.c | 101 ++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 95 insertions(+), 6 deletions(-) (limited to 'arch/powerpc/kernel/ftrace.c') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 1aec559bdfc..3271cd698e4 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -274,7 +274,63 @@ static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - /* Ignore modules for PPC32 (for now) */ + 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 */ @@ -297,7 +353,6 @@ int ftrace_make_nop(struct module *mod, return ftrace_modify_code(ip, old, new); } -#ifdef CONFIG_PPC64 /* * Out of range jumps are called from modules. * We should either already have a pointer to the module @@ -320,7 +375,6 @@ int ftrace_make_nop(struct module *mod, /* nothing to do if mod == rec->arch.mod */ } else mod = rec->arch.mod; -#endif /* CONFIG_PPC64 */ return __ftrace_make_nop(mod, rec, addr); @@ -380,7 +434,44 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - /* PPC32 ignores modules for now */ + 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 */ @@ -402,7 +493,6 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return ftrace_modify_code(ip, old, new); } -#ifdef CONFIG_PPC64 /* * Out of range jumps are called from modules. * Being that we are converting from nop, it had better @@ -412,7 +502,6 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) printk(KERN_ERR "No module loaded\n"); return -EINVAL; } -#endif return __ftrace_make_call(rec, addr); } -- cgit v1.2.3 From d9af12b72bfe2a4efc1d347e0ac1c669b85dcea9 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 25 Nov 2008 06:39:18 -0800 Subject: powerpc: ftrace, fix cast aliasing and add code verification Impact: clean up and robustness addition This patch addresses the comments made by Paul Mackerras. It removes the type casting between unsigned int and unsigned char pointers, and replaces them with a use of all unsigned int. Verification that the jump is indeed made to a trampoline has also been added. Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/ftrace.c | 121 +++++++++++++++++++++++-------------------- 1 file changed, 65 insertions(+), 56 deletions(-) (limited to 'arch/powerpc/kernel/ftrace.c') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 3271cd698e4..ea454a00440 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -162,26 +162,25 @@ 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 int op; + unsigned int jmp[5]; + unsigned long ptr; unsigned long ip = rec->ip; unsigned long tramp; int offset; /* read where this goes */ - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (probe_kernel_read(&op, (void *)ip, sizeof(int))) 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); + 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); + tramp = find_bl_target(ip, op); /* * On PPC64 the trampoline looks like: @@ -200,19 +199,25 @@ __ftrace_make_nop(struct module *mod, 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)) { + if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) { printk(KERN_ERR "Failed to read %lx\n", tramp); return -EFAULT; } - DEBUGP(" %08x %08x", - (unsigned)(*ptr >> 32), - (unsigned)*ptr); + DEBUGP(" %08x %08x", jmp[0], jmp[1]); + + /* verify that this is what we expect it to be */ + if (((jmp[0] & 0xffff0000) != 0x3d820000) || + ((jmp[1] & 0xffff0000) != 0x398c0000) || + (jmp[2] != 0xf8410028) || + (jmp[3] != 0xe96c0020) || + (jmp[4] != 0xe84c0028)) { + printk(KERN_ERR "Not a trampoline\n"); + return -EINVAL; + } - offset = (unsigned)jmp[2] << 24 | - (unsigned)jmp[3] << 16 | - (unsigned)jmp[6] << 8 | - (unsigned)jmp[7]; + offset = (unsigned)((unsigned short)jmp[0]) << 16 | + (unsigned)((unsigned short)jmp[1]); DEBUGP(" %x ", offset); @@ -225,13 +230,13 @@ __ftrace_make_nop(struct module *mod, return -EFAULT; } - DEBUGP(" %08x %08x\n", - (unsigned)(*ptr >> 32), - (unsigned)*ptr); + DEBUGP(" %08x %08x\n", jmp[0], jmp[1]); + + ptr = ((unsigned long)jmp[0] << 32) + jmp[1]; /* This should match what was called */ - if (*ptr != GET_ADDR(addr)) { - printk(KERN_ERR "addr does not match %lx\n", *ptr); + if (ptr != GET_ADDR(addr)) { + printk(KERN_ERR "addr does not match %lx\n", ptr); return -EINVAL; } @@ -240,11 +245,11 @@ __ftrace_make_nop(struct module *mod, * 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)) + if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) return -EFAULT; - if (*op != 0xe8410028) { - printk(KERN_ERR "Next line is not ld! (%08x)\n", *op); + if (op != 0xe8410028) { + printk(KERN_ERR "Next line is not ld! (%08x)\n", op); return -EINVAL; } @@ -261,9 +266,9 @@ __ftrace_make_nop(struct module *mod, * ld r2,40(r1) * 1: */ - op[0] = 0x48000008; /* b +8 */ + op = 0x48000008; /* b +8 */ - if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE)) + if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) return -EPERM; return 0; @@ -274,46 +279,52 @@ 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 int op; + unsigned int jmp[4]; unsigned long ip = rec->ip; unsigned long tramp; - int offset; - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (probe_kernel_read(&op, (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); + 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); + tramp = find_bl_target(ip, op); /* * On PPC32 the trampoline looks like: - * lis r11,sym@ha - * addi r11,r11,sym@l - * mtctr r11 - * bctr + * 0x3d, 0x60, 0x00, 0x00 lis r11,sym@ha + * 0x39, 0x6b, 0x00, 0x00 addi r11,r11,sym@l + * 0x7d, 0x69, 0x03, 0xa6 mtctr r11 + * 0x4e, 0x80, 0x04, 0x20 bctr */ DEBUGP("ip:%lx jumps to %lx", ip, tramp); /* Find where the trampoline jumps to */ - if (probe_kernel_read(jmp, (void *)tramp, 8)) { + if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) { printk(KERN_ERR "Failed to read %lx\n", tramp); return -EFAULT; } - DEBUGP(" %08x %08x ", ptr[0], ptr[1]); + DEBUGP(" %08x %08x ", jmp[0], jmp[1]); + + /* verify that this is what we expect it to be */ + if (((jmp[0] & 0xffff0000) != 0x3d600000) || + ((jmp[1] & 0xffff0000) != 0x396b0000) || + (jmp[2] != 0x7d6903a6) || + (jmp[3] != 0x4e800420)) { + printk(KERN_ERR "Not a trampoline\n"); + return -EINVAL; + } - tramp = (ptr[1] & 0xffff) | - ((ptr[0] & 0xffff) << 16); + tramp = (jmp[1] & 0xffff) | + ((jmp[0] & 0xffff) << 16); if (tramp & 0x8000) tramp -= 0x10000; @@ -326,9 +337,9 @@ __ftrace_make_nop(struct module *mod, return -EINVAL; } - op[0] = PPC_NOP_INSTR; + op = PPC_NOP_INSTR; - if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE)) + if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) return -EPERM; return 0; @@ -384,13 +395,12 @@ int ftrace_make_nop(struct module *mod, 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 int op[2]; unsigned long ip = rec->ip; unsigned long offset; /* read where this goes */ - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE * 2)) + if (probe_kernel_read(op, (void *)ip, MCOUNT_INSN_SIZE * 2)) return -EFAULT; /* @@ -425,7 +435,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) DEBUGP("write to %lx\n", rec->ip); - if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE * 2)) + if (probe_kernel_write((void *)ip, op, MCOUNT_INSN_SIZE * 2)) return -EPERM; return 0; @@ -434,18 +444,17 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - unsigned char replaced[MCOUNT_INSN_SIZE]; - unsigned int *op = (unsigned *)&replaced; + unsigned int op; unsigned long ip = rec->ip; unsigned long offset; /* read where this goes */ - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (probe_kernel_read(&op, (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]); + if (op != PPC_NOP_INSTR) { + printk(KERN_ERR "Expected NOP but have %x\n", op); return -EINVAL; } @@ -465,11 +474,11 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) } /* Set to "bl addr" */ - op[0] = branch_offset(offset); + op = branch_offset(offset); DEBUGP("write to %lx\n", rec->ip); - if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE)) + if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) return -EPERM; return 0; -- cgit v1.2.3 From ec682cef2d2c1a25a198d32a87fe2649da671d1e Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 25 Nov 2008 10:22:48 -0800 Subject: powerpc: ftrace, added missing icache flush Impact: fix to PowerPC code modification After modifying code it is essential to flush the icache. This patch adds the missing flush. Reported-by: Paul Mackerras Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/ftrace.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'arch/powerpc/kernel/ftrace.c') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index ea454a00440..a4640e4f117 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -271,6 +271,9 @@ __ftrace_make_nop(struct module *mod, if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) return -EPERM; + + flush_icache_range(ip, ip + 8); + return 0; } @@ -342,6 +345,8 @@ __ftrace_make_nop(struct module *mod, if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) return -EPERM; + flush_icache_range(ip, ip + 8); + return 0; } #endif /* PPC64 */ @@ -438,6 +443,8 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (probe_kernel_write((void *)ip, op, MCOUNT_INSN_SIZE * 2)) return -EPERM; + flush_icache_range(ip, ip + 8); + return 0; } #else @@ -481,6 +488,8 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) return -EPERM; + flush_icache_range(ip, ip + 8); + return 0; } #endif /* CONFIG_PPC64 */ -- cgit v1.2.3 From 0029ff87529dff01a4b9c5bf380a0caacb5f7418 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 25 Nov 2008 14:06:19 -0800 Subject: powerpc: ftrace, use create_branch Impact: clean up Paul Mackerras pointed out that the code to determine if the branch can reach the destination is incorrect. Michael Ellerman suggested to pull out the code from create_branch and use that. Simply using create_branch is probably the best. Reported-by: Michael Ellerman Reported-by: Paul Mackerras Signed-off-by: Steven Rostedt Signed-off-by: Ingo Molnar --- arch/powerpc/kernel/ftrace.c | 54 ++++++++++---------------------------------- 1 file changed, 12 insertions(+), 42 deletions(-) (limited to 'arch/powerpc/kernel/ftrace.c') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index a4640e4f117..5355244c99f 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -114,19 +114,9 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, */ 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)); + /* use the create_branch to verify that this offset can be branched */ + return create_branch((unsigned int *)ip, addr, 0); } static int is_bl_op(unsigned int op) @@ -134,11 +124,6 @@ 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; @@ -151,12 +136,6 @@ static unsigned long find_bl_target(unsigned long ip, unsigned int op) 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, @@ -402,7 +381,6 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { unsigned int op[2]; unsigned long ip = rec->ip; - unsigned long offset; /* read where this goes */ if (probe_kernel_read(op, (void *)ip, MCOUNT_INSN_SIZE * 2)) @@ -424,17 +402,14 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) 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); + /* create the branch to the trampoline */ + op[0] = create_branch((unsigned int *)ip, + rec->arch.mod->arch.tramp, BRANCH_SET_LINK); + if (!op[0]) { + printk(KERN_ERR "REL24 out of range!\n"); return -EINVAL; } - /* Set to "bl addr" */ - op[0] = branch_offset(offset); /* ld r2,40(r1) */ op[1] = 0xe8410028; @@ -453,7 +428,6 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { unsigned int op; unsigned long ip = rec->ip; - unsigned long offset; /* read where this goes */ if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE)) @@ -471,18 +445,14 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) 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); + /* create the branch to the trampoline */ + op = create_branch((unsigned int *)ip, + rec->arch.mod->arch.tramp, BRANCH_SET_LINK); + if (!op) { + printk(KERN_ERR "REL24 out of range!\n"); return -EINVAL; } - /* Set to "bl addr" */ - op = branch_offset(offset); - DEBUGP("write to %lx\n", rec->ip); if (probe_kernel_write((void *)ip, &op, MCOUNT_INSN_SIZE)) -- cgit v1.2.3