linux-stable/tools/objtool/orc_gen.c

239 lines
5.2 KiB
C
Raw Normal View History

treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 13 Based on 2 normalized pattern(s): this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details you should have received a copy of the gnu general public license along with this program if not see http www gnu org licenses this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details [based] [from] [clk] [highbank] [c] you should have received a copy of the gnu general public license along with this program if not see http www gnu org licenses extracted by the scancode license scanner the SPDX license identifier GPL-2.0-or-later has been chosen to replace the boilerplate/reference in 355 file(s). Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Jilayne Lovejoy <opensource@jilayne.com> Reviewed-by: Steve Winslow <swinslow@gmail.com> Reviewed-by: Allison Randal <allison@lohutok.net> Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190519154041.837383322@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-05-19 13:51:43 +00:00
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com>
*/
#include <stdlib.h>
#include <string.h>
#include <linux/objtool.h>
#include <asm/orc_types.h>
objtool: Rework header include paths Currently objtool headers are being included either by their base name or included via ../ from a parent directory. In case of a base name usage: #include "warn.h" #include "arch_elf.h" it does not make it apparent from which directory the file comes from. To make it slightly better, and actually to avoid name clashes some arch specific files have "arch_" suffix. And files from an arch folder have to revert to including via ../ e.g: #include "../../elf.h" With additional architectures support and the code base growth there is a need for clearer headers naming scheme for multiple reasons: 1. to make it instantly obvious where these files come from (objtool itself / objtool arch|generic folders / some other external files), 2. to avoid name clashes of objtool arch specific headers, potential obtool arch generic headers and the system header files (there is /usr/include/elf.h already), 3. to avoid ../ includes and improve code readability. 4. to give a warm fuzzy feeling to developers who are mostly kernel developers and are accustomed to linux kernel headers arranging scheme. Doesn't this make it instantly obvious where are these files come from? #include <objtool/warn.h> #include <arch/elf.h> And doesn't it look nicer to avoid ugly ../ includes? Which also guarantees this is elf.h from the objtool and not /usr/include/elf.h. #include <objtool/elf.h> This patch defines and implements new objtool headers arranging scheme. Which is: - all generic headers go to include/objtool (similar to include/linux) - all arch headers go to arch/$(SRCARCH)/include/arch (to get arch prefix). This is similar to linux arch specific "asm/*" headers but we are not abusing "asm" name and calling it what it is. This also helps to prevent name clashes (arch is not used in system headers or kernel exports). To bring objtool to this state the following things are done: 1. current top level tools/objtool/ headers are moved into include/objtool/ subdirectory, 2. arch specific headers, currently only arch/x86/include/ are moved into arch/x86/include/arch/ and were stripped of "arch_" suffix, 3. new -I$(srctree)/tools/objtool/include include path to make includes like <objtool/warn.h> possible, 4. rewriting file includes, 5. make git not to ignore include/objtool/ subdirectory. Signed-off-by: Vasily Gorbik <gor@linux.ibm.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
2020-11-12 23:03:32 +00:00
#include <objtool/check.h>
#include <objtool/warn.h>
#include <objtool/endianness.h>
static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi)
{
struct instruction *insn = container_of(cfi, struct instruction, cfi);
struct cfi_reg *bp = &cfi->regs[CFI_BP];
memset(orc, 0, sizeof(*orc));
orc->end = cfi->end;
if (cfi->cfa.base == CFI_UNDEFINED) {
orc->sp_reg = ORC_REG_UNDEFINED;
return 0;
}
switch (cfi->cfa.base) {
case CFI_SP:
orc->sp_reg = ORC_REG_SP;
break;
case CFI_SP_INDIRECT:
orc->sp_reg = ORC_REG_SP_INDIRECT;
break;
case CFI_BP:
orc->sp_reg = ORC_REG_BP;
break;
case CFI_BP_INDIRECT:
orc->sp_reg = ORC_REG_BP_INDIRECT;
break;
case CFI_R10:
orc->sp_reg = ORC_REG_R10;
break;
case CFI_R13:
orc->sp_reg = ORC_REG_R13;
break;
case CFI_DI:
orc->sp_reg = ORC_REG_DI;
break;
case CFI_DX:
orc->sp_reg = ORC_REG_DX;
break;
default:
WARN_FUNC("unknown CFA base reg %d",
insn->sec, insn->offset, cfi->cfa.base);
return -1;
}
switch (bp->base) {
case CFI_UNDEFINED:
orc->bp_reg = ORC_REG_UNDEFINED;
break;
case CFI_CFA:
orc->bp_reg = ORC_REG_PREV_SP;
break;
case CFI_BP:
orc->bp_reg = ORC_REG_BP;
break;
default:
WARN_FUNC("unknown BP base reg %d",
insn->sec, insn->offset, bp->base);
return -1;
}
orc->sp_offset = cfi->cfa.offset;
orc->bp_offset = bp->offset;
orc->type = cfi->type;
return 0;
}
static int write_orc_entry(struct elf *elf, struct section *orc_sec,
struct section *ip_sec, unsigned int idx,
struct section *insn_sec, unsigned long insn_off,
struct orc_entry *o)
{
struct orc_entry *orc;
/* populate ORC data */
orc = (struct orc_entry *)orc_sec->data->d_buf + idx;
memcpy(orc, o, sizeof(*orc));
orc->sp_offset = bswap_if_needed(orc->sp_offset);
orc->bp_offset = bswap_if_needed(orc->bp_offset);
objtool: Rename rela to reloc Before supporting additional relocation types rename the relevant types and functions from "rela" to "reloc". This work be done with the following regex: sed -e 's/struct rela/struct reloc/g' \ -e 's/\([_\*]\)rela\(s\{0,1\}\)/\1reloc\2/g' \ -e 's/tmprela\(s\{0,1\}\)/tmpreloc\1/g' \ -e 's/relasec/relocsec/g' \ -e 's/rela_list/reloc_list/g' \ -e 's/rela_hash/reloc_hash/g' \ -e 's/add_rela/add_reloc/g' \ -e 's/rela->/reloc->/g' \ -e '/rela[,\.]/{ s/\([^\.>]\)rela\([\.,]\)/\1reloc\2/g ; }' \ -e 's/rela =/reloc =/g' \ -e 's/relas =/relocs =/g' \ -e 's/relas\[/relocs[/g' \ -e 's/relaname =/relocname =/g' \ -e 's/= rela\;/= reloc\;/g' \ -e 's/= relas\;/= relocs\;/g' \ -e 's/= relaname\;/= relocname\;/g' \ -e 's/, rela)/, reloc)/g' \ -e 's/\([ @]\)rela\([ "]\)/\1reloc\2/g' \ -e 's/ rela$/ reloc/g' \ -e 's/, relaname/, relocname/g' \ -e 's/sec->rela/sec->reloc/g' \ -e 's/(\(!\{0,1\}\)rela/(\1reloc/g' \ -i \ arch.h \ arch/x86/decode.c \ check.c \ check.h \ elf.c \ elf.h \ orc_gen.c \ special.c Notable exceptions which complicate the regex include gelf_* library calls and standard/expected section names which still use "rela" because they encode the type of relocation expected. Also, keep "rela" in the struct because it encodes a specific type of relocation we currently expect. It will eventually turn into a member of an anonymous union when a susequent patch adds implicit addend, or "rel", relocation support. Signed-off-by: Matt Helsley <mhelsley@vmware.com> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
2020-05-29 21:01:13 +00:00
/* populate reloc for ip */
if (elf_add_reloc_to_insn(elf, ip_sec, idx * sizeof(int), R_X86_64_PC32,
insn_sec, insn_off))
return -1;
return 0;
}
struct orc_list_entry {
struct list_head list;
struct orc_entry orc;
struct section *insn_sec;
unsigned long insn_off;
};
static int orc_list_add(struct list_head *orc_list, struct orc_entry *orc,
struct section *sec, unsigned long offset)
{
struct orc_list_entry *entry = malloc(sizeof(*entry));
if (!entry) {
WARN("malloc failed");
return -1;
}
entry->orc = *orc;
entry->insn_sec = sec;
entry->insn_off = offset;
list_add_tail(&entry->list, orc_list);
return 0;
}
objtool: Support stack layout changes in alternatives The ORC unwinder showed a warning [1] which revealed the stack layout didn't match what was expected. The problem was that paravirt patching had replaced "CALL *pv_ops.irq.save_fl" with "PUSHF;POP". That changed the stack layout between the PUSHF and the POP, so unwinding from an interrupt which occurred between those two instructions would fail. Part of the agreed upon solution was to rework the custom paravirt patching code to use alternatives instead, since objtool already knows how to read alternatives (and converging runtime patching infrastructure is always a good thing anyway). But the main problem still remains, which is that runtime patching can change the stack layout. Making stack layout changes in alternatives was disallowed with commit 7117f16bf460 ("objtool: Fix ORC vs alternatives"), but now that paravirt is going to be doing it, it needs to be supported. One way to do so would be to modify the ORC table when the code gets patched. But ORC is simple -- a good thing! -- and it's best to leave it alone. Instead, support stack layout changes by "flattening" all possible stack states (CFI) from parallel alternative code streams into a single set of linear states. The only necessary limitation is that CFI conflicts are disallowed at all possible instruction boundaries. For example, this scenario is allowed: Alt1 Alt2 Alt3 0x00 CALL *pv_ops.save_fl CALL xen_save_fl PUSHF 0x01 POP %RAX 0x02 NOP ... 0x05 NOP ... 0x07 <insn> The unwind information for offset-0x00 is identical for all 3 alternatives. Similarly offset-0x05 and higher also are identical (and the same as 0x00). However offset-0x01 has deviating CFI, but that is only relevant for Alt3, neither of the other alternative instruction streams will ever hit that offset. This scenario is NOT allowed: Alt1 Alt2 0x00 CALL *pv_ops.save_fl PUSHF 0x01 NOP6 ... 0x07 NOP POP %RAX The problem here is that offset-0x7, which is an instruction boundary in both possible instruction patch streams, has two conflicting stack layouts. [ The above examples were stolen from Peter Zijlstra. ] The new flattened CFI array is used both for the detection of conflicts (like the second example above) and the generation of linear ORC entries. BTW, another benefit of these changes is that, thanks to some related cleanups (new fake nops and alt_group struct) objtool can finally be rid of fake jumps, which were a constant source of headaches. [1] https://lkml.kernel.org/r/20201111170536.arx2zbn4ngvjoov7@treble Cc: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
2020-12-18 20:26:21 +00:00
static unsigned long alt_group_len(struct alt_group *alt_group)
{
return alt_group->last_insn->offset +
alt_group->last_insn->len -
alt_group->first_insn->offset;
}
int orc_create(struct objtool_file *file)
{
struct section *sec, *orc_sec;
unsigned int nr = 0, idx = 0;
struct orc_list_entry *entry;
struct list_head orc_list;
struct orc_entry null = {
.sp_reg = ORC_REG_UNDEFINED,
.bp_reg = ORC_REG_UNDEFINED,
.type = UNWIND_HINT_TYPE_CALL,
};
/* Build a deduplicated list of ORC entries: */
INIT_LIST_HEAD(&orc_list);
for_each_sec(file, sec) {
struct orc_entry orc, prev_orc = {0};
struct instruction *insn;
bool empty = true;
if (!sec->text)
continue;
sec_for_each_insn(file, sec, insn) {
objtool: Support stack layout changes in alternatives The ORC unwinder showed a warning [1] which revealed the stack layout didn't match what was expected. The problem was that paravirt patching had replaced "CALL *pv_ops.irq.save_fl" with "PUSHF;POP". That changed the stack layout between the PUSHF and the POP, so unwinding from an interrupt which occurred between those two instructions would fail. Part of the agreed upon solution was to rework the custom paravirt patching code to use alternatives instead, since objtool already knows how to read alternatives (and converging runtime patching infrastructure is always a good thing anyway). But the main problem still remains, which is that runtime patching can change the stack layout. Making stack layout changes in alternatives was disallowed with commit 7117f16bf460 ("objtool: Fix ORC vs alternatives"), but now that paravirt is going to be doing it, it needs to be supported. One way to do so would be to modify the ORC table when the code gets patched. But ORC is simple -- a good thing! -- and it's best to leave it alone. Instead, support stack layout changes by "flattening" all possible stack states (CFI) from parallel alternative code streams into a single set of linear states. The only necessary limitation is that CFI conflicts are disallowed at all possible instruction boundaries. For example, this scenario is allowed: Alt1 Alt2 Alt3 0x00 CALL *pv_ops.save_fl CALL xen_save_fl PUSHF 0x01 POP %RAX 0x02 NOP ... 0x05 NOP ... 0x07 <insn> The unwind information for offset-0x00 is identical for all 3 alternatives. Similarly offset-0x05 and higher also are identical (and the same as 0x00). However offset-0x01 has deviating CFI, but that is only relevant for Alt3, neither of the other alternative instruction streams will ever hit that offset. This scenario is NOT allowed: Alt1 Alt2 0x00 CALL *pv_ops.save_fl PUSHF 0x01 NOP6 ... 0x07 NOP POP %RAX The problem here is that offset-0x7, which is an instruction boundary in both possible instruction patch streams, has two conflicting stack layouts. [ The above examples were stolen from Peter Zijlstra. ] The new flattened CFI array is used both for the detection of conflicts (like the second example above) and the generation of linear ORC entries. BTW, another benefit of these changes is that, thanks to some related cleanups (new fake nops and alt_group struct) objtool can finally be rid of fake jumps, which were a constant source of headaches. [1] https://lkml.kernel.org/r/20201111170536.arx2zbn4ngvjoov7@treble Cc: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
2020-12-18 20:26:21 +00:00
struct alt_group *alt_group = insn->alt_group;
int i;
if (!alt_group) {
if (init_orc_entry(&orc, &insn->cfi))
return -1;
if (!memcmp(&prev_orc, &orc, sizeof(orc)))
continue;
if (orc_list_add(&orc_list, &orc, sec,
insn->offset))
return -1;
nr++;
prev_orc = orc;
empty = false;
continue;
objtool: Support stack layout changes in alternatives The ORC unwinder showed a warning [1] which revealed the stack layout didn't match what was expected. The problem was that paravirt patching had replaced "CALL *pv_ops.irq.save_fl" with "PUSHF;POP". That changed the stack layout between the PUSHF and the POP, so unwinding from an interrupt which occurred between those two instructions would fail. Part of the agreed upon solution was to rework the custom paravirt patching code to use alternatives instead, since objtool already knows how to read alternatives (and converging runtime patching infrastructure is always a good thing anyway). But the main problem still remains, which is that runtime patching can change the stack layout. Making stack layout changes in alternatives was disallowed with commit 7117f16bf460 ("objtool: Fix ORC vs alternatives"), but now that paravirt is going to be doing it, it needs to be supported. One way to do so would be to modify the ORC table when the code gets patched. But ORC is simple -- a good thing! -- and it's best to leave it alone. Instead, support stack layout changes by "flattening" all possible stack states (CFI) from parallel alternative code streams into a single set of linear states. The only necessary limitation is that CFI conflicts are disallowed at all possible instruction boundaries. For example, this scenario is allowed: Alt1 Alt2 Alt3 0x00 CALL *pv_ops.save_fl CALL xen_save_fl PUSHF 0x01 POP %RAX 0x02 NOP ... 0x05 NOP ... 0x07 <insn> The unwind information for offset-0x00 is identical for all 3 alternatives. Similarly offset-0x05 and higher also are identical (and the same as 0x00). However offset-0x01 has deviating CFI, but that is only relevant for Alt3, neither of the other alternative instruction streams will ever hit that offset. This scenario is NOT allowed: Alt1 Alt2 0x00 CALL *pv_ops.save_fl PUSHF 0x01 NOP6 ... 0x07 NOP POP %RAX The problem here is that offset-0x7, which is an instruction boundary in both possible instruction patch streams, has two conflicting stack layouts. [ The above examples were stolen from Peter Zijlstra. ] The new flattened CFI array is used both for the detection of conflicts (like the second example above) and the generation of linear ORC entries. BTW, another benefit of these changes is that, thanks to some related cleanups (new fake nops and alt_group struct) objtool can finally be rid of fake jumps, which were a constant source of headaches. [1] https://lkml.kernel.org/r/20201111170536.arx2zbn4ngvjoov7@treble Cc: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com> Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
2020-12-18 20:26:21 +00:00
}
/*
* Alternatives can have different stack layout
* possibilities (but they shouldn't conflict).
* Instead of traversing the instructions, use the
* alt_group's flattened byte-offset-addressed CFI
* array.
*/
for (i = 0; i < alt_group_len(alt_group); i++) {
struct cfi_state *cfi = alt_group->cfi[i];
if (!cfi)
continue;
if (init_orc_entry(&orc, cfi))
return -1;
if (!memcmp(&prev_orc, &orc, sizeof(orc)))
continue;
if (orc_list_add(&orc_list, &orc, insn->sec,
insn->offset + i))
return -1;
nr++;
prev_orc = orc;
empty = false;
}
/* Skip to the end of the alt_group */
insn = alt_group->last_insn;
}
/* Add a section terminator */
if (!empty) {
orc_list_add(&orc_list, &null, sec, sec->len);
nr++;
}
}
if (!nr)
return 0;
/* Create .orc_unwind, .orc_unwind_ip and .rela.orc_unwind_ip sections: */
sec = find_section_by_name(file->elf, ".orc_unwind");
if (sec) {
WARN("file already has .orc_unwind section, skipping");
return -1;
}
orc_sec = elf_create_section(file->elf, ".orc_unwind", 0,
sizeof(struct orc_entry), nr);
if (!orc_sec)
return -1;
sec = elf_create_section(file->elf, ".orc_unwind_ip", 0, sizeof(int), nr);
if (!sec)
return -1;
/* Write ORC entries to sections: */
list_for_each_entry(entry, &orc_list, list) {
if (write_orc_entry(file->elf, orc_sec, sec, idx++,
entry->insn_sec, entry->insn_off,
&entry->orc))
return -1;
}
return 0;
}