From f17c4e01e906c568fb03a2e6c2b99e4ee4587fbf Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 3 Mar 2016 15:26:55 +1100 Subject: powerpc/module: Mark module stubs with a magic value When a module is loaded, calls out to the kernel go via a stub which is generated at runtime. One of these stubs is used to call _mcount(), which is the default target of tracing calls generated by the compiler with -pg. If dynamic ftrace is enabled (which it typically is), another stub is used to call ftrace_caller(), which is the target of tracing calls when ftrace is actually active. ftrace then wants to disable the calls to _mcount() at module startup, and enable/disable the calls to ftrace_caller() when enabling/disabling tracing - all of these it does by patching the code. As part of that code patching, the ftrace code wants to confirm that the branch it is about to modify, is in fact a call to a module stub which calls _mcount() or ftrace_caller(). Currently it does that by inspecting the instructions and confirming they are what it expects. Although that works, the code to do it is pretty intricate because it requires lots of knowledge about the exact format of the stub. We can make that process easier by marking the generated stubs with a magic value, and then looking for that magic value. Altough this is not as rigorous as the current method, I believe it is sufficient in practice. Reviewed-by: Balbir Singh Reviewed-by: Torsten Duwe Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/ftrace.c | 14 ++++---------- 1 file changed, 4 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 44d4d8e..4505cbf 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -106,10 +106,9 @@ static int __ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned int op; - unsigned long entry, ptr; + unsigned long entry, ptr, tramp; unsigned long ip = rec->ip; - void *tramp; + unsigned int op; /* read where this goes */ if (probe_kernel_read(&op, (void *)ip, sizeof(int))) @@ -122,14 +121,9 @@ __ftrace_make_nop(struct module *mod, } /* lets find where the pointer goes */ - tramp = (void *)find_bl_target(ip, op); - - pr_devel("ip:%lx jumps to %p", ip, tramp); + tramp = find_bl_target(ip, op); - if (!is_module_trampoline(tramp)) { - pr_err("Not a trampoline\n"); - return -EINVAL; - } + pr_devel("ip:%lx jumps to %lx", ip, tramp); if (module_trampoline_target(mod, tramp, &ptr)) { pr_err("Failed to get trampoline target\n"); -- cgit v1.1 From c96f83856f56a66a5d7fd730958bec80c9b5a020 Mon Sep 17 00:00:00 2001 From: Torsten Duwe Date: Thu, 3 Mar 2016 15:26:57 +1100 Subject: powerpc/ftrace: Use generic ftrace_modify_all_code() Convert powerpc's arch_ftrace_update_code() from its own version to use the generic default functionality (without stop_machine -- our instructions are properly aligned and the replacements atomic). With this we gain error checking and the much-needed function_trace_op handling. Reviewed-by: Balbir Singh Reviewed-by: Kamalesh Babulal Signed-off-by: Torsten Duwe Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/ftrace.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) (limited to 'arch/powerpc/kernel/ftrace.c') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 4505cbf..62899fb 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -449,20 +449,13 @@ void ftrace_replace_code(int enable) } } +/* + * Use the default ftrace_modify_all_code, but without + * stop_machine(). + */ void arch_ftrace_update_code(int command) { - if (command & FTRACE_UPDATE_CALLS) - ftrace_replace_code(1); - else if (command & FTRACE_DISABLE_CALLS) - ftrace_replace_code(0); - - if (command & FTRACE_UPDATE_TRACE_FUNC) - ftrace_update_ftrace_func(ftrace_trace_function); - - if (command & FTRACE_START_FUNC_RET) - ftrace_enable_ftrace_graph_caller(); - else if (command & FTRACE_STOP_FUNC_RET) - ftrace_disable_ftrace_graph_caller(); + ftrace_modify_all_code(command); } int __init ftrace_dyn_arch_init(void) -- cgit v1.1 From 153086644fd1fb07fb3af84d9f11542a19b1e8b6 Mon Sep 17 00:00:00 2001 From: Torsten Duwe Date: Thu, 3 Mar 2016 15:26:59 +1100 Subject: powerpc/ftrace: Add support for -mprofile-kernel ftrace ABI The gcc switch -mprofile-kernel defines a new ABI for calling _mcount() very early in the function with minimal overhead. Although mprofile-kernel has been available since GCC 3.4, there were bugs which were only fixed recently. Currently it is known to work in GCC 4.9, 5 and 6. Additionally there are two possible code sequences generated by the flag, the first uses mflr/std/bl and the second is optimised to omit the std. Currently only gcc 6 has the optimised sequence. This patch supports both sequences. Initial work started by Vojtech Pavlik, used with permission. Key changes: - rework _mcount() to work for both the old and new ABIs. - implement new versions of ftrace_caller() and ftrace_graph_caller() which deal with the new ABI. - updates to __ftrace_make_nop() to recognise the new mcount calling sequence. - updates to __ftrace_make_call() to recognise the nop'ed sequence. - implement ftrace_modify_call(). - updates to the module loader to surpress the toc save in the module stub when calling mcount with the new ABI. Reviewed-by: Balbir Singh Signed-off-by: Torsten Duwe Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/ftrace.c | 103 ++++++++++++++++++++++++++++++++++++------- 1 file changed, 87 insertions(+), 16 deletions(-) (limited to 'arch/powerpc/kernel/ftrace.c') diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index 62899fb..9dac18da 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -61,8 +61,11 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new) return -EFAULT; /* Make sure it is what we expect it to be */ - if (replaced != old) + if (replaced != old) { + pr_err("%p: replaced (%#x) != old (%#x)", + (void *)ip, replaced, old); return -EINVAL; + } /* replace the text with the new text */ if (patch_instruction((unsigned int *)ip, new)) @@ -108,11 +111,13 @@ __ftrace_make_nop(struct module *mod, { unsigned long entry, ptr, tramp; unsigned long ip = rec->ip; - unsigned int op; + unsigned int op, pop; /* read where this goes */ - if (probe_kernel_read(&op, (void *)ip, sizeof(int))) + if (probe_kernel_read(&op, (void *)ip, sizeof(int))) { + pr_err("Fetching opcode failed.\n"); return -EFAULT; + } /* Make sure that that this is still a 24bit jump */ if (!is_bl_op(op)) { @@ -152,10 +157,42 @@ __ftrace_make_nop(struct module *mod, * * Use a b +8 to jump over the load. */ - op = 0x48000008; /* b +8 */ - if (patch_instruction((unsigned int *)ip, op)) + pop = PPC_INST_BRANCH | 8; /* b +8 */ + + /* + * Check what is in the next instruction. We can see ld r2,40(r1), but + * on first pass after boot we will see mflr r0. + */ + if (probe_kernel_read(&op, (void *)(ip+4), MCOUNT_INSN_SIZE)) { + pr_err("Fetching op failed.\n"); + return -EFAULT; + } + + if (op != PPC_INST_LD_TOC) { + unsigned int inst; + + if (probe_kernel_read(&inst, (void *)(ip - 4), 4)) { + pr_err("Fetching instruction at %lx failed.\n", ip - 4); + return -EFAULT; + } + + /* We expect either a mlfr r0, or a std r0, LRSAVE(r1) */ + if (inst != PPC_INST_MFLR && inst != PPC_INST_STD_LR) { + pr_err("Unexpected instructions around bl _mcount\n" + "when enabling dynamic ftrace!\t" + "(%08x,bl,%08x)\n", inst, op); + return -EINVAL; + } + + /* When using -mkernel_profile there is no load to jump over */ + pop = PPC_INST_NOP; + } + + if (patch_instruction((unsigned int *)ip, pop)) { + pr_err("Patching NOP failed.\n"); return -EPERM; + } return 0; } @@ -281,16 +318,15 @@ int ftrace_make_nop(struct module *mod, #ifdef CONFIG_MODULES #ifdef CONFIG_PPC64 +/* + * Examine the existing instructions for __ftrace_make_call. + * They should effectively be a NOP, and follow formal constraints, + * depending on the ABI. Return false if they don't. + */ +#ifndef CC_USING_MPROFILE_KERNEL static int -__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1) { - unsigned int op[2]; - void *ip = (void *)rec->ip; - - /* read where this goes */ - if (probe_kernel_read(op, ip, sizeof(op))) - return -EFAULT; - /* * We expect to see: * @@ -300,8 +336,34 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * The load offset is different depending on the ABI. For simplicity * just mask it out when doing the compare. */ - if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) { - pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]); + if ((op0 != 0x48000008) || ((op1 & 0xffff0000) != 0xe8410000)) + return 0; + return 1; +} +#else +static int +expected_nop_sequence(void *ip, unsigned int op0, unsigned int op1) +{ + /* look for patched "NOP" on ppc64 with -mprofile-kernel */ + if (op0 != PPC_INST_NOP) + return 0; + return 1; +} +#endif + +static int +__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned int op[2]; + void *ip = (void *)rec->ip; + + /* read where this goes */ + if (probe_kernel_read(op, ip, sizeof(op))) + return -EFAULT; + + if (!expected_nop_sequence(ip, op[0], op[1])) { + pr_err("Unexpected call sequence at %p: %x %x\n", + ip, op[0], op[1]); return -EINVAL; } @@ -324,7 +386,16 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return 0; } -#else + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + return ftrace_make_call(rec, addr); +} +#endif + +#else /* !CONFIG_PPC64: */ static int __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { -- cgit v1.1