From ffd618fa39284f8cc343894b566dd42ec6e74e77 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 8 Apr 2011 03:58:48 -0400 Subject: ftrace/recordmcount: Make ignored mcount calls into nops at compile time There are sections that are ignored by ftrace for the function tracing because the text is in a section that can be removed without notice. The mcount calls in these sections are ignored and ftrace never sees them. The downside of this is that the functions in these sections still call mcount. Although the mcount function is defined in assembly simply as a return, this added overhead is unnecessary. The solution is to convert these callers into nops at compile time. A better solution is to add 'notrace' to the section markers, but as new sections come up all the time, it would be nice that they are delt with when they are created. Later patches will deal with finding these sections and doing the proper solution. Thanks to H. Peter Anvin for giving me the right nops to use for x86. Cc: "H. Peter Anvin" Cc: John Reiser Link: http://lkml.kernel.org/r/20110421023738.237101176@goodmis.org Signed-off-by: Steven Rostedt --- scripts/recordmcount.c | 40 ++++++++++++++++++++++-- scripts/recordmcount.h | 82 +++++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 116 insertions(+), 6 deletions(-) diff --git a/scripts/recordmcount.c b/scripts/recordmcount.c index 37c59654c133..78054a41d134 100644 --- a/scripts/recordmcount.c +++ b/scripts/recordmcount.c @@ -118,6 +118,34 @@ umalloc(size_t size) return addr; } +static unsigned char ideal_nop5_x86_64[5] = { 0x0f, 0x1f, 0x44, 0x00, 0x00 }; +static unsigned char ideal_nop5_x86_32[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 }; +static unsigned char *ideal_nop; + +static char rel_type_nop; + +static int (*make_nop)(void *map, size_t const offset); + +static int make_nop_x86(void *map, size_t const offset) +{ + uint32_t *ptr; + unsigned char *op; + + /* Confirm we have 0xe8 0x0 0x0 0x0 0x0 */ + ptr = map + offset; + if (*ptr != 0) + return -1; + + op = map + offset - 1; + if (*op != 0xe8) + return -1; + + /* convert to nop */ + ulseek(fd_map, offset - 1, SEEK_SET); + uwrite(fd_map, ideal_nop, 5); + return 0; +} + /* * Get the whole file as a programming convenience in order to avoid * malloc+lseek+read+free of many pieces. If successful, then mmap @@ -301,7 +329,11 @@ do_file(char const *const fname) w2(ehdr->e_machine), fname); fail_file(); break; - case EM_386: reltype = R_386_32; break; + case EM_386: + reltype = R_386_32; + make_nop = make_nop_x86; + ideal_nop = ideal_nop5_x86_32; + break; case EM_ARM: reltype = R_ARM_ABS32; altmcount = "__gnu_mcount_nc"; break; @@ -312,7 +344,11 @@ do_file(char const *const fname) case EM_S390: /* reltype: e_class */ gpfx = '_'; break; case EM_SH: reltype = R_SH_DIR32; break; case EM_SPARCV9: reltype = R_SPARC_64; gpfx = '_'; break; - case EM_X86_64: reltype = R_X86_64_64; break; + case EM_X86_64: + make_nop = make_nop_x86; + ideal_nop = ideal_nop5_x86_64; + reltype = R_X86_64_64; + break; } /* end switch */ switch (ehdr->e_ident[EI_CLASS]) { diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h index 7f8d5c4c780f..657dbedd1c7f 100644 --- a/scripts/recordmcount.h +++ b/scripts/recordmcount.h @@ -23,6 +23,7 @@ #undef fn_is_fake_mcount #undef MIPS_is_fake_mcount #undef sift_rel_mcount +#undef nop_mcount #undef find_secsym_ndx #undef __has_rel_mcount #undef has_rel_mcount @@ -49,6 +50,7 @@ #ifdef RECORD_MCOUNT_64 # define append_func append64 # define sift_rel_mcount sift64_rel_mcount +# define nop_mcount nop_mcount_64 # define find_secsym_ndx find64_secsym_ndx # define __has_rel_mcount __has64_rel_mcount # define has_rel_mcount has64_rel_mcount @@ -77,6 +79,7 @@ #else # define append_func append32 # define sift_rel_mcount sift32_rel_mcount +# define nop_mcount nop_mcount_32 # define find_secsym_ndx find32_secsym_ndx # define __has_rel_mcount __has32_rel_mcount # define has_rel_mcount has32_rel_mcount @@ -304,6 +307,70 @@ static uint_t *sift_rel_mcount(uint_t *mlocp, return mlocp; } +/* + * Read the relocation table again, but this time its called on sections + * that are not going to be traced. The mcount calls here will be converted + * into nops. + */ +static void nop_mcount(Elf_Shdr const *const relhdr, + Elf_Ehdr const *const ehdr) +{ + Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff) + + (void *)ehdr); + unsigned const symsec_sh_link = w(relhdr->sh_link); + Elf_Shdr const *const symsec = &shdr0[symsec_sh_link]; + Elf_Sym const *const sym0 = (Elf_Sym const *)(_w(symsec->sh_offset) + + (void *)ehdr); + + Elf_Shdr const *const strsec = &shdr0[w(symsec->sh_link)]; + char const *const str0 = (char const *)(_w(strsec->sh_offset) + + (void *)ehdr); + + Elf_Rel const *const rel0 = (Elf_Rel const *)(_w(relhdr->sh_offset) + + (void *)ehdr); + unsigned rel_entsize = _w(relhdr->sh_entsize); + unsigned const nrel = _w(relhdr->sh_size) / rel_entsize; + Elf_Rel const *relp = rel0; + + Elf_Shdr const *const shdr = &shdr0[w(relhdr->sh_info)]; + + unsigned mcountsym = 0; + unsigned t; + + for (t = nrel; t; --t) { + int ret = -1; + + if (!mcountsym) { + Elf_Sym const *const symp = + &sym0[Elf_r_sym(relp)]; + char const *symname = &str0[w(symp->st_name)]; + char const *mcount = gpfx == '_' ? "_mcount" : "mcount"; + + if (symname[0] == '.') + ++symname; /* ppc64 hack */ + if (strcmp(mcount, symname) == 0 || + (altmcount && strcmp(altmcount, symname) == 0)) + mcountsym = Elf_r_sym(relp); + } + + if (mcountsym == Elf_r_sym(relp) && !is_fake_mcount(relp)) + ret = make_nop((void *)ehdr, shdr->sh_offset + relp->r_offset); + + /* + * If we successfully removed the mcount, mark the relocation + * as a nop (don't do anything with it). + */ + if (!ret) { + Elf_Rel rel; + rel = *(Elf_Rel *)relp; + Elf_r_info(&rel, Elf_r_sym(relp), rel_type_nop); + ulseek(fd_map, (void *)relp - (void *)ehdr, SEEK_SET); + uwrite(fd_map, &rel, sizeof(rel)); + } + relp = (Elf_Rel const *)(rel_entsize + (void *)relp); + } +} + /* * Find a symbol in the given section, to be used as the base for relocating @@ -360,8 +427,7 @@ __has_rel_mcount(Elf_Shdr const *const relhdr, /* is SHT_REL or SHT_RELA */ succeed_file(); } if (w(txthdr->sh_type) != SHT_PROGBITS || - !(w(txthdr->sh_flags) & SHF_EXECINSTR) || - !is_mcounted_section_name(txtname)) + !(w(txthdr->sh_flags) & SHF_EXECINSTR)) return NULL; return txtname; } @@ -384,9 +450,11 @@ static unsigned tot_relsize(Elf_Shdr const *const shdr0, { unsigned totrelsz = 0; Elf_Shdr const *shdrp = shdr0; + char const *txtname; for (; nhdr; --nhdr, ++shdrp) { - if (has_rel_mcount(shdrp, shdr0, shstrtab, fname)) + txtname = has_rel_mcount(shdrp, shdr0, shstrtab, fname); + if (txtname && is_mcounted_section_name(txtname)) totrelsz += _w(shdrp->sh_size); } return totrelsz; @@ -422,7 +490,7 @@ do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype) for (relhdr = shdr0, k = nhdr; k; --k, ++relhdr) { char const *const txtname = has_rel_mcount(relhdr, shdr0, shstrtab, fname); - if (txtname) { + if (txtname && is_mcounted_section_name(txtname)) { uint_t recval = 0; unsigned const recsym = find_secsym_ndx( w(relhdr->sh_info), txtname, &recval, @@ -433,6 +501,12 @@ do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype) mlocp = sift_rel_mcount(mlocp, (void *)mlocp - (void *)mloc0, &mrelp, relhdr, ehdr, recsym, recval, reltype); + } else if (make_nop && txtname) { + /* + * This section is ignored by ftrace, but still + * has mcount calls. Convert them to nops now. + */ + nop_mcount(relhdr, ehdr); } } if (mloc0 != mlocp) { -- cgit v1.2.3