From: Uros Bizjak ubizjak@gmail.com

stable inclusion from stable-v5.10.133 commit 0ca2ba6e4d139da809061a25626174f812303b7a category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 6c44221b05236cc65d76cb5dc2463f738edff39d upstream.

Saves one byte in __vmx_vcpu_run for the same functionality.

Cc: Paolo Bonzini pbonzini@redhat.com Cc: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Uros Bizjak ubizjak@gmail.com Message-Id: 20201029140457.126965-1-ubizjak@gmail.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/kvm/vmx/vmenter.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 90ad7a6246e3..e85aa5faa22d 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -132,7 +132,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX

/* Check if vmlaunch or vmresume is needed */ - cmpb $0, %bl + testb %bl, %bl

/* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX

From: Josh Poimboeuf jpoimboe@redhat.com

stable inclusion from stable-v5.10.133 commit 1d516bd72a68e4e610d8e3b5ad99e25807a85947 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit ab4e0744e99b87e1a223e89fc3c9ae44f727c9a6 upstream.

Decouple ORC entries from instructions. This simplifies the control/data flow, and is going to make it easier to support alternative instructions which change the stack layout.

Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/Makefile | 4 - tools/objtool/arch.h | 4 - tools/objtool/builtin-orc.c | 6 +- tools/objtool/check.h | 3 - tools/objtool/objtool.h | 3 +- tools/objtool/orc_gen.c | 272 ++++++++++++++++++------------------ tools/objtool/weak.c | 7 +- 7 files changed, 140 insertions(+), 159 deletions(-)

diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index 5cdb19036d7f..a43096f713c7 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -46,10 +46,6 @@ ifeq ($(SRCARCH),x86) SUBCMD_ORC := y endif

-ifeq ($(SUBCMD_ORC),y) - CFLAGS += -DINSN_USE_ORC -endif - export SUBCMD_CHECK SUBCMD_ORC export srctree OUTPUT CFLAGS SRCARCH AWK include $(srctree)/tools/build/Makefile.include diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index 4a84c3081b8e..5e3f3ea8bb89 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -11,10 +11,6 @@ #include "objtool.h" #include "cfi.h"

-#ifdef INSN_USE_ORC -#include <asm/orc_types.h> -#endif - enum insn_type { INSN_JUMP_CONDITIONAL, INSN_JUMP_UNCONDITIONAL, diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c index 7b31121fa60b..508bdf6ae8dc 100644 --- a/tools/objtool/builtin-orc.c +++ b/tools/objtool/builtin-orc.c @@ -51,11 +51,7 @@ int cmd_orc(int argc, const char **argv) if (list_empty(&file->insn_list)) return 0;

- ret = create_orc(file); - if (ret) - return ret; - - ret = create_orc_sections(file); + ret = orc_create(file); if (ret) return ret;

diff --git a/tools/objtool/check.h b/tools/objtool/check.h index 2804848e628e..c280880f5eb4 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -43,9 +43,6 @@ struct instruction { struct symbol *func; struct list_head stack_ops; struct cfi_state cfi; -#ifdef INSN_USE_ORC - struct orc_entry orc; -#endif };

static inline bool is_static_jump(struct instruction *insn) diff --git a/tools/objtool/objtool.h b/tools/objtool/objtool.h index 4125d4578b23..5e58d3537e2f 100644 --- a/tools/objtool/objtool.h +++ b/tools/objtool/objtool.h @@ -26,7 +26,6 @@ struct objtool_file *objtool_open_read(const char *_objname);

int check(struct objtool_file *file); int orc_dump(const char *objname); -int create_orc(struct objtool_file *file); -int create_orc_sections(struct objtool_file *file); +int orc_create(struct objtool_file *file);

#endif /* _OBJTOOL_H */ diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 9ce68b385a1b..7191b6234120 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -12,89 +12,84 @@ #include "check.h" #include "warn.h"

-int create_orc(struct objtool_file *file) +static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi) { - struct instruction *insn; + struct instruction *insn = container_of(cfi, struct instruction, cfi); + struct cfi_reg *bp = &cfi->regs[CFI_BP];

- for_each_insn(file, insn) { - struct orc_entry *orc = &insn->orc; - struct cfi_reg *cfa = &insn->cfi.cfa; - struct cfi_reg *bp = &insn->cfi.regs[CFI_BP]; + memset(orc, 0, sizeof(*orc));

- if (!insn->sec->text) - continue; - - orc->end = insn->cfi.end; + orc->end = cfi->end;

- if (cfa->base == CFI_UNDEFINED) { - orc->sp_reg = ORC_REG_UNDEFINED; - continue; - } - - switch (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, cfa->base); - return -1; - } + if (cfi->cfa.base == CFI_UNDEFINED) { + orc->sp_reg = ORC_REG_UNDEFINED; + return 0; + }

- 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; - } + 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; + }

- orc->sp_offset = cfa->offset; - orc->bp_offset = bp->offset; - orc->type = insn->cfi.type; + 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 create_orc_entry(struct elf *elf, struct section *u_sec, struct section *ip_relocsec, - unsigned int idx, struct section *insn_sec, - unsigned long insn_off, struct orc_entry *o) +static int write_orc_entry(struct elf *elf, struct section *orc_sec, + struct section *ip_rsec, unsigned int idx, + struct section *insn_sec, unsigned long insn_off, + struct orc_entry *o) { struct orc_entry *orc; struct reloc *reloc;

/* populate ORC data */ - orc = (struct orc_entry *)u_sec->data->d_buf + idx; + orc = (struct orc_entry *)orc_sec->data->d_buf + idx; memcpy(orc, o, sizeof(*orc));

/* populate reloc for ip */ @@ -114,102 +109,109 @@ static int create_orc_entry(struct elf *elf, struct section *u_sec, struct secti

reloc->type = R_X86_64_PC32; reloc->offset = idx * sizeof(int); - reloc->sec = ip_relocsec; + reloc->sec = ip_rsec;

elf_add_reloc(elf, reloc);

return 0; }

-int create_orc_sections(struct objtool_file *file) +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; +} + +int orc_create(struct objtool_file *file) { - struct instruction *insn, *prev_insn; - struct section *sec, *u_sec, *ip_relocsec; - unsigned int idx; + struct section *sec, *ip_rsec, *orc_sec; + unsigned int nr = 0, idx = 0; + struct orc_list_entry *entry; + struct list_head orc_list;

- struct orc_entry empty = { - .sp_reg = ORC_REG_UNDEFINED, + struct orc_entry null = { + .sp_reg = ORC_REG_UNDEFINED, .bp_reg = ORC_REG_UNDEFINED, .type = UNWIND_HINT_TYPE_CALL, };

- sec = find_section_by_name(file->elf, ".orc_unwind"); - if (sec) { - WARN("file already has .orc_unwind section, skipping"); - return -1; - } - - /* count the number of needed orcs */ - idx = 0; + /* 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;

- prev_insn = NULL; sec_for_each_insn(file, sec, insn) { - if (!prev_insn || - memcmp(&insn->orc, &prev_insn->orc, - sizeof(struct orc_entry))) { - idx++; - } - prev_insn = insn; + 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; }

- /* section terminator */ - if (prev_insn) - idx++; + /* Add a section terminator */ + if (!empty) { + orc_list_add(&orc_list, &null, sec, sec->len); + nr++; + } } - if (!idx) - return -1; + 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;

- /* create .orc_unwind_ip and .rela.orc_unwind_ip sections */ - sec = elf_create_section(file->elf, ".orc_unwind_ip", 0, sizeof(int), idx); + sec = elf_create_section(file->elf, ".orc_unwind_ip", 0, sizeof(int), nr); if (!sec) return -1; - - ip_relocsec = elf_create_reloc_section(file->elf, sec, SHT_RELA); - if (!ip_relocsec) + ip_rsec = elf_create_reloc_section(file->elf, sec, SHT_RELA); + if (!ip_rsec) return -1;

- /* create .orc_unwind section */ - u_sec = elf_create_section(file->elf, ".orc_unwind", 0, - sizeof(struct orc_entry), idx); - - /* populate sections */ - idx = 0; - for_each_sec(file, sec) { - if (!sec->text) - continue; - - prev_insn = NULL; - sec_for_each_insn(file, sec, insn) { - if (!prev_insn || memcmp(&insn->orc, &prev_insn->orc, - sizeof(struct orc_entry))) { - - if (create_orc_entry(file->elf, u_sec, ip_relocsec, idx, - insn->sec, insn->offset, - &insn->orc)) - return -1; - - idx++; - } - prev_insn = insn; - } - - /* section terminator */ - if (prev_insn) { - if (create_orc_entry(file->elf, u_sec, ip_relocsec, idx, - prev_insn->sec, - prev_insn->offset + prev_insn->len, - &empty)) - return -1; - - idx++; - } + /* Write ORC entries to sections: */ + list_for_each_entry(entry, &orc_list, list) { + if (write_orc_entry(file->elf, orc_sec, ip_rsec, idx++, + entry->insn_sec, entry->insn_off, + &entry->orc)) + return -1; }

- if (elf_rebuild_reloc_section(file->elf, ip_relocsec)) + if (elf_rebuild_reloc_section(file->elf, ip_rsec)) return -1;

return 0; diff --git a/tools/objtool/weak.c b/tools/objtool/weak.c index 7843e9a7a72f..553ec9ce51ba 100644 --- a/tools/objtool/weak.c +++ b/tools/objtool/weak.c @@ -25,12 +25,7 @@ int __weak orc_dump(const char *_objname) UNSUPPORTED("orc"); }

-int __weak create_orc(struct objtool_file *file) -{ - UNSUPPORTED("orc"); -} - -int __weak create_orc_sections(struct objtool_file *file) +int __weak orc_create(struct objtool_file *file) { UNSUPPORTED("orc"); }

From: Josh Poimboeuf jpoimboe@redhat.com

stable inclusion from stable-v5.10.133 commit 917a4f6348d94d9a3c20d78c800dd4715825362d category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit c9c324dc22aab1687da37001b321b6dfa93a0699 upstream.

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 Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- .../Documentation/stack-validation.txt | 16 +- tools/objtool/check.c | 192 +++++++++--------- tools/objtool/check.h | 6 + tools/objtool/orc_gen.c | 56 ++++- 4 files changed, 159 insertions(+), 111 deletions(-)

diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt index 0542e46c7552..30f38fdc0d56 100644 --- a/tools/objtool/Documentation/stack-validation.txt +++ b/tools/objtool/Documentation/stack-validation.txt @@ -315,13 +315,15 @@ they mean, and suggestions for how to fix them. function tracing inserts additional calls, which is not obvious from the sources).

-10. file.o: warning: func()+0x5c: alternative modifies stack - - This means that an alternative includes instructions that modify the - stack. The problem is that there is only one ORC unwind table, this means - that the ORC unwind entries must be valid for each of the alternatives. - The easiest way to enforce this is to ensure alternatives do not contain - any ORC entries, which in turn implies the above constraint. +10. file.o: warning: func()+0x5c: stack layout conflict in alternatives + + This means that in the use of the alternative() or ALTERNATIVE() + macro, the code paths have conflicting modifications to the stack. + The problem is that there is only one ORC unwind table, which means + that the ORC unwind entries must be consistent for all possible + instruction boundaries regardless of which code has been patched. + This limitation can be overcome by massaging the alternatives with + NOPs to shift the stack changes around so they no longer conflict.

11. file.o: warning: unannotated intra-function call

diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 6143a0790aa4..32fdbd339ca9 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -19,8 +19,6 @@ #include <linux/kernel.h> #include <linux/static_call_types.h>

-#define FAKE_JUMP_OFFSET -1 - struct alternative { struct list_head list; struct instruction *insn; @@ -789,9 +787,6 @@ static int add_jump_destinations(struct objtool_file *file) if (!is_static_jump(insn)) continue;

- if (insn->offset == FAKE_JUMP_OFFSET) - continue; - reloc = find_reloc_by_dest_range(file->elf, insn->sec, insn->offset, insn->len); if (!reloc) { @@ -991,28 +986,15 @@ static int add_call_destinations(struct objtool_file *file) }

/* - * The .alternatives section requires some extra special care, over and above - * what other special sections require: - * - * 1. Because alternatives are patched in-place, we need to insert a fake jump - * instruction at the end so that validate_branch() skips all the original - * replaced instructions when validating the new instruction path. - * - * 2. An added wrinkle is that the new instruction length might be zero. In - * that case the old instructions are replaced with noops. We simulate that - * by creating a fake jump as the only new instruction. - * - * 3. In some cases, the alternative section includes an instruction which - * conditionally jumps to the _end_ of the entry. We have to modify these - * jumps' destinations to point back to .text rather than the end of the - * entry in .altinstr_replacement. + * The .alternatives section requires some extra special care over and above + * other special sections because alternatives are patched in place. */ static int handle_group_alt(struct objtool_file *file, struct special_alt *special_alt, struct instruction *orig_insn, struct instruction **new_insn) { - struct instruction *last_orig_insn, *last_new_insn, *insn, *fake_jump = NULL; + struct instruction *last_orig_insn, *last_new_insn = NULL, *insn, *nop = NULL; struct alt_group *orig_alt_group, *new_alt_group; unsigned long dest_off;

@@ -1022,6 +1004,13 @@ static int handle_group_alt(struct objtool_file *file, WARN("malloc failed"); return -1; } + orig_alt_group->cfi = calloc(special_alt->orig_len, + sizeof(struct cfi_state *)); + if (!orig_alt_group->cfi) { + WARN("calloc failed"); + return -1; + } + last_orig_insn = NULL; insn = orig_insn; sec_for_each_insn_from(file, insn) { @@ -1035,42 +1024,45 @@ static int handle_group_alt(struct objtool_file *file, orig_alt_group->first_insn = orig_insn; orig_alt_group->last_insn = last_orig_insn;

- if (next_insn_same_sec(file, last_orig_insn)) { - fake_jump = malloc(sizeof(*fake_jump)); - if (!fake_jump) { - WARN("malloc failed"); - return -1; - } - memset(fake_jump, 0, sizeof(*fake_jump)); - INIT_LIST_HEAD(&fake_jump->alts); - INIT_LIST_HEAD(&fake_jump->stack_ops); - init_cfi_state(&fake_jump->cfi);

- fake_jump->sec = special_alt->new_sec; - fake_jump->offset = FAKE_JUMP_OFFSET; - fake_jump->type = INSN_JUMP_UNCONDITIONAL; - fake_jump->jump_dest = list_next_entry(last_orig_insn, list); - fake_jump->func = orig_insn->func; + new_alt_group = malloc(sizeof(*new_alt_group)); + if (!new_alt_group) { + WARN("malloc failed"); + return -1; }

- if (!special_alt->new_len) { - if (!fake_jump) { - WARN("%s: empty alternative at end of section", - special_alt->orig_sec->name); + if (special_alt->new_len < special_alt->orig_len) { + /* + * Insert a fake nop at the end to make the replacement + * alt_group the same size as the original. This is needed to + * allow propagate_alt_cfi() to do its magic. When the last + * instruction affects the stack, the instruction after it (the + * nop) will propagate the new state to the shared CFI array. + */ + nop = malloc(sizeof(*nop)); + if (!nop) { + WARN("malloc failed"); return -1; } + memset(nop, 0, sizeof(*nop)); + INIT_LIST_HEAD(&nop->alts); + INIT_LIST_HEAD(&nop->stack_ops); + init_cfi_state(&nop->cfi);

- *new_insn = fake_jump; - return 0; + nop->sec = special_alt->new_sec; + nop->offset = special_alt->new_off + special_alt->new_len; + nop->len = special_alt->orig_len - special_alt->new_len; + nop->type = INSN_NOP; + nop->func = orig_insn->func; + nop->alt_group = new_alt_group; + nop->ignore = orig_insn->ignore_alts; }

- new_alt_group = malloc(sizeof(*new_alt_group)); - if (!new_alt_group) { - WARN("malloc failed"); - return -1; + if (!special_alt->new_len) { + *new_insn = nop; + goto end; }

- last_new_insn = NULL; insn = *new_insn; sec_for_each_insn_from(file, insn) { struct reloc *alt_reloc; @@ -1109,14 +1101,8 @@ static int handle_group_alt(struct objtool_file *file, continue;

dest_off = arch_jump_destination(insn); - if (dest_off == special_alt->new_off + special_alt->new_len) { - if (!fake_jump) { - WARN("%s: alternative jump to end of section", - special_alt->orig_sec->name); - return -1; - } - insn->jump_dest = fake_jump; - } + if (dest_off == special_alt->new_off + special_alt->new_len) + insn->jump_dest = next_insn_same_sec(file, last_orig_insn);

if (!insn->jump_dest) { WARN_FUNC("can't find alternative jump destination", @@ -1131,13 +1117,13 @@ static int handle_group_alt(struct objtool_file *file, return -1; }

+ if (nop) + list_add(&nop->list, &last_new_insn->list); +end: new_alt_group->orig_group = orig_alt_group; new_alt_group->first_insn = *new_insn; - new_alt_group->last_insn = last_new_insn; - - if (fake_jump) - list_add(&fake_jump->list, &last_new_insn->list); - + new_alt_group->last_insn = nop ? : last_new_insn; + new_alt_group->cfi = orig_alt_group->cfi; return 0; }

@@ -2237,22 +2223,47 @@ static int update_cfi_state(struct instruction *insn, struct cfi_state *cfi, return 0; }

-static int handle_insn_ops(struct instruction *insn, struct insn_state *state) +/* + * The stack layouts of alternatives instructions can sometimes diverge when + * they have stack modifications. That's fine as long as the potential stack + * layouts don't conflict at any given potential instruction boundary. + * + * Flatten the CFIs of the different alternative code streams (both original + * and replacement) into a single shared CFI array which can be used to detect + * conflicts and nicely feed a linear array of ORC entries to the unwinder. + */ +static int propagate_alt_cfi(struct objtool_file *file, struct instruction *insn) { - struct stack_op *op; + struct cfi_state **alt_cfi; + int group_off;

- list_for_each_entry(op, &insn->stack_ops, list) { - struct cfi_state old_cfi = state->cfi; - int res; + if (!insn->alt_group) + return 0;

- res = update_cfi_state(insn, &state->cfi, op); - if (res) - return res; + alt_cfi = insn->alt_group->cfi; + group_off = insn->offset - insn->alt_group->first_insn->offset;

- if (insn->alt_group && memcmp(&state->cfi, &old_cfi, sizeof(struct cfi_state))) { - WARN_FUNC("alternative modifies stack", insn->sec, insn->offset); + if (!alt_cfi[group_off]) { + alt_cfi[group_off] = &insn->cfi; + } else { + if (memcmp(alt_cfi[group_off], &insn->cfi, sizeof(struct cfi_state))) { + WARN_FUNC("stack layout conflict in alternatives", + insn->sec, insn->offset); return -1; } + } + + return 0; +} + +static int handle_insn_ops(struct instruction *insn, struct insn_state *state) +{ + struct stack_op *op; + + list_for_each_entry(op, &insn->stack_ops, list) { + + if (update_cfi_state(insn, &state->cfi, op)) + return 1;

if (op->dest.type == OP_DEST_PUSHF) { if (!state->uaccess_stack) { @@ -2442,28 +2453,20 @@ static int validate_return(struct symbol *func, struct instruction *insn, struct return 0; }

-/* - * Alternatives should not contain any ORC entries, this in turn means they - * should not contain any CFI ops, which implies all instructions should have - * the same same CFI state. - * - * It is possible to constuct alternatives that have unreachable holes that go - * unreported (because they're NOPs), such holes would result in CFI_UNDEFINED - * states which then results in ORC entries, which we just said we didn't want. - * - * Avoid them by copying the CFI entry of the first instruction into the whole - * alternative. - */ -static void fill_alternative_cfi(struct objtool_file *file, struct instruction *insn) +static struct instruction *next_insn_to_validate(struct objtool_file *file, + struct instruction *insn) { - struct instruction *first_insn = insn; struct alt_group *alt_group = insn->alt_group;

- sec_for_each_insn_continue(file, insn) { - if (insn->alt_group != alt_group) - break; - insn->cfi = first_insn->cfi; - } + /* + * Simulate the fact that alternatives are patched in-place. When the + * end of a replacement alt_group is reached, redirect objtool flow to + * the end of the original alt_group. + */ + if (alt_group && insn == alt_group->last_insn && alt_group->orig_group) + return next_insn_same_sec(file, alt_group->orig_group->last_insn); + + return next_insn_same_sec(file, insn); }

/* @@ -2484,7 +2487,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, sec = insn->sec;

while (1) { - next_insn = next_insn_same_sec(file, insn); + next_insn = next_insn_to_validate(file, insn);

if (file->c_file && func && insn->func && func != insn->func->pfunc) { WARN("%s() falls through to next function %s()", @@ -2517,6 +2520,9 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,

insn->visited |= visited;

+ if (propagate_alt_cfi(file, insn)) + return 1; + if (!insn->ignore_alts && !list_empty(&insn->alts)) { bool skip_orig = false;

@@ -2532,9 +2538,6 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, } }

- if (insn->alt_group) - fill_alternative_cfi(file, insn); - if (skip_orig) return 0; } @@ -2767,9 +2770,6 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio !strcmp(insn->sec->name, ".altinstr_aux")) return true;

- if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->offset == FAKE_JUMP_OFFSET) - return true; - if (!insn->func) return false;

diff --git a/tools/objtool/check.h b/tools/objtool/check.h index dbf9f34622e8..995a0436d543 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -28,6 +28,12 @@ struct alt_group {

/* First and last instructions in the group */ struct instruction *first_insn, *last_insn; + + /* + * Byte-offset-addressed len-sized array of pointers to CFI structs. + * This is shared with the other alt_groups in the same alternative. + */ + struct cfi_state **cfi; };

struct instruction { diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 7191b6234120..0d62f958dbea 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -141,6 +141,13 @@ static int orc_list_add(struct list_head *orc_list, struct orc_entry *orc, return 0; }

+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, *ip_rsec, *orc_sec; @@ -165,15 +172,48 @@ int orc_create(struct objtool_file *file) continue;

sec_for_each_insn(file, sec, insn) { - if (init_orc_entry(&orc, &insn->cfi)) - return -1; - if (!memcmp(&prev_orc, &orc, sizeof(orc))) + 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; - if (orc_list_add(&orc_list, &orc, sec, insn->offset)) - return -1; - nr++; - prev_orc = orc; - empty = false; + } + + /* + * 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 */

From: Josh Poimboeuf jpoimboe@redhat.com

stable inclusion from stable-v5.10.133 commit 53e89bc78e4351924a1a1474683d47a00c2633f2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit ecf11ba4d066fe527586c6edd6ca68457ca55cf4 upstream.

There's an inconsistency in how sibling calls are detected in non-function asm code, depending on the scope of the object. If the target code is external to the object, objtool considers it a sibling call. If the target code is internal but not a function, objtool *doesn't* consider it a sibling call.

This can cause some inconsistencies between per-object and vmlinux.o validation.

Instead, assume only ELF functions can do sibling calls. This generally matches existing reality, and makes sibling call validation consistent between vmlinux.o and per-object.

Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Link: https://lore.kernel.org/r/0e9ab6f3628cc7bf3bde7aa6762d54d7df19ad78.161126346... Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/check.c | 36 ++++++++++++++++++++++-------------- 1 file changed, 22 insertions(+), 14 deletions(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4f8a760bffca..29e4fca80258 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -109,15 +109,20 @@ static struct instruction *prev_insn_same_sym(struct objtool_file *file,

static bool is_sibling_call(struct instruction *insn) { + /* + * Assume only ELF functions can make sibling calls. This ensures + * sibling call detection consistency between vmlinux.o and individual + * objects. + */ + if (!insn->func) + return false; + /* An indirect jump is either a sibling call or a jump to a table. */ if (insn->type == INSN_JUMP_DYNAMIC) return list_empty(&insn->alts);

- if (!is_static_jump(insn)) - return false; - /* add_jump_destinations() sets insn->call_dest for sibling calls. */ - return !!insn->call_dest; + return (is_static_jump(insn) && insn->call_dest); }

/* @@ -788,7 +793,7 @@ static int add_jump_destinations(struct objtool_file *file) continue;

reloc = find_reloc_by_dest_range(file->elf, insn->sec, - insn->offset, insn->len); + insn->offset, insn->len); if (!reloc) { dest_sec = insn->sec; dest_off = arch_jump_destination(insn); @@ -808,18 +813,21 @@ static int add_jump_destinations(struct objtool_file *file)

insn->retpoline_safe = true; continue; - } else if (reloc->sym->sec->idx) { - dest_sec = reloc->sym->sec; - dest_off = reloc->sym->sym.st_value + - arch_dest_reloc_offset(reloc->addend); - } else { - /* external sibling call */ + } else if (insn->func) { + /* internal or external sibling call (with reloc) */ insn->call_dest = reloc->sym; if (insn->call_dest->static_call_tramp) { list_add_tail(&insn->static_call_node, &file->static_call_list); } continue; + } else if (reloc->sym->sec->idx) { + dest_sec = reloc->sym->sec; + dest_off = reloc->sym->sym.st_value + + arch_dest_reloc_offset(reloc->addend); + } else { + /* non-func asm code jumping to another file */ + continue; }

insn->jump_dest = find_insn(file, dest_sec, dest_off); @@ -868,7 +876,7 @@ static int add_jump_destinations(struct objtool_file *file) } else if (insn->jump_dest->func->pfunc != insn->func->pfunc && insn->jump_dest->offset == insn->jump_dest->func->offset) {

- /* internal sibling call */ + /* internal sibling call (without reloc) */ insn->call_dest = insn->jump_dest->func; if (insn->call_dest->static_call_tramp) { list_add_tail(&insn->static_call_node, @@ -2570,7 +2578,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,

case INSN_JUMP_CONDITIONAL: case INSN_JUMP_UNCONDITIONAL: - if (func && is_sibling_call(insn)) { + if (is_sibling_call(insn)) { ret = validate_sibling_call(insn, &state); if (ret) return ret; @@ -2592,7 +2600,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,

case INSN_JUMP_DYNAMIC: case INSN_JUMP_DYNAMIC_CONDITIONAL: - if (func && is_sibling_call(insn)) { + if (is_sibling_call(insn)) { ret = validate_sibling_call(insn, &state); if (ret) return ret;

From: Josh Poimboeuf jpoimboe@redhat.com

stable inclusion from stable-v5.10.133 commit b626e17c11f58d49b01bd8bcdf0e0ec11570b6df category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit cde07a4e4434ddfb9b1616ac971edf6d66329804 upstream.

The OBJECT_FILES_NON_STANDARD annotation is used to tell objtool to ignore a file. File-level ignores won't work when validating vmlinux.o.

Tweak the ELF metadata and unwind hints to allow objtool to follow the code.

Cc: Juergen Gross jgross@suse.com Reviewed-by: Boris Ostrovsky boris.ostrovsky@oracle.com Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Link: https://lore.kernel.org/r/8b042a09c69e8645f3b133ef6653ba28f896807d.161126346... Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/xen/Makefile | 1 - arch/x86/xen/xen-asm.S | 29 +++++++++++++++++++---------- 2 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index fc5c5ba4aacb..40b5779fce21 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -OBJECT_FILES_NON_STANDARD_xen-asm.o := y

ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 011ec649f388..e75f60a06056 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -14,6 +14,7 @@ #include <asm/thread_info.h> #include <asm/asm.h> #include <asm/frame.h> +#include <asm/unwind_hints.h>

#include <xen/interface/xen.h>

@@ -147,6 +148,7 @@ SYM_FUNC_END(xen_read_cr2_direct);

.macro xen_pv_trap name SYM_CODE_START(xen_\name) + UNWIND_HINT_EMPTY pop %rcx pop %r11 jmp \name @@ -186,6 +188,7 @@ xen_pv_trap asm_exc_xen_hypervisor_callback SYM_CODE_START(xen_early_idt_handler_array) i = 0 .rept NUM_EXCEPTION_VECTORS + UNWIND_HINT_EMPTY pop %rcx pop %r11 jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE @@ -212,11 +215,13 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 * rsp->rax } */ SYM_CODE_START(xen_iret) + UNWIND_HINT_EMPTY pushq $0 jmp hypercall_iret SYM_CODE_END(xen_iret)

SYM_CODE_START(xen_sysret64) + UNWIND_HINT_EMPTY /* * We're already on the usermode stack at this point, but * still with the kernel gs, so we can easily switch back. @@ -271,7 +276,8 @@ SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode) */

/* Normal 64-bit system call target */ -SYM_FUNC_START(xen_syscall_target) +SYM_CODE_START(xen_syscall_target) + UNWIND_HINT_EMPTY popq %rcx popq %r11

@@ -284,12 +290,13 @@ SYM_FUNC_START(xen_syscall_target) movq $__USER_CS, 1*8(%rsp)

jmp entry_SYSCALL_64_after_hwframe -SYM_FUNC_END(xen_syscall_target) +SYM_CODE_END(xen_syscall_target)

#ifdef CONFIG_IA32_EMULATION

/* 32-bit compat syscall target */ -SYM_FUNC_START(xen_syscall32_target) +SYM_CODE_START(xen_syscall32_target) + UNWIND_HINT_EMPTY popq %rcx popq %r11

@@ -302,10 +309,11 @@ SYM_FUNC_START(xen_syscall32_target) movq $__USER32_CS, 1*8(%rsp)

jmp entry_SYSCALL_compat_after_hwframe -SYM_FUNC_END(xen_syscall32_target) +SYM_CODE_END(xen_syscall32_target)

/* 32-bit compat sysenter target */ -SYM_FUNC_START(xen_sysenter_target) +SYM_CODE_START(xen_sysenter_target) + UNWIND_HINT_EMPTY /* * NB: Xen is polite and clears TF from EFLAGS for us. This means * that we don't need to guard against single step exceptions here. @@ -322,17 +330,18 @@ SYM_FUNC_START(xen_sysenter_target) movq $__USER32_CS, 1*8(%rsp)

jmp entry_SYSENTER_compat_after_hwframe -SYM_FUNC_END(xen_sysenter_target) +SYM_CODE_END(xen_sysenter_target)

#else /* !CONFIG_IA32_EMULATION */

-SYM_FUNC_START_ALIAS(xen_syscall32_target) -SYM_FUNC_START(xen_sysenter_target) +SYM_CODE_START(xen_syscall32_target) +SYM_CODE_START(xen_sysenter_target) + UNWIND_HINT_EMPTY lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax pushq $0 jmp hypercall_iret -SYM_FUNC_END(xen_sysenter_target) -SYM_FUNC_END_ALIAS(xen_syscall32_target) +SYM_CODE_END(xen_sysenter_target) +SYM_CODE_END(xen_syscall32_target)

#endif /* CONFIG_IA32_EMULATION */

From: Juergen Gross jgross@suse.com

stable inclusion from stable-v5.10.133 commit c9cf908b89ca3b5aa6563181bf78764ac1ab793e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 5e21a3ecad1500e35b46701e7f3f232e15d78e69 upstream.

Merge arch/x86/include/asm/alternative-asm.h into arch/x86/include/asm/alternative.h in order to make it easier to use common definitions later.

Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Borislav Petkov bp@suse.de Link: https://lkml.kernel.org/r/20210311142319.4723-2-jgross@suse.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/entry/entry_32.S | 2 +- arch/x86/entry/vdso/vdso32/system_call.S | 2 +- arch/x86/include/asm/alternative-asm.h | 114 ----------------------- arch/x86/include/asm/alternative.h | 112 +++++++++++++++++++++- arch/x86/include/asm/nospec-branch.h | 1 - arch/x86/include/asm/smap.h | 5 +- arch/x86/lib/atomic64_386_32.S | 2 +- arch/x86/lib/atomic64_cx8_32.S | 2 +- arch/x86/lib/copy_page_64.S | 2 +- arch/x86/lib/copy_user_64.S | 2 +- arch/x86/lib/memcpy_64.S | 2 +- arch/x86/lib/memmove_64.S | 2 +- arch/x86/lib/memset_64.S | 2 +- arch/x86/lib/retpoline.S | 2 +- 14 files changed, 120 insertions(+), 132 deletions(-) delete mode 100644 arch/x86/include/asm/alternative-asm.h

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index df8c017e6161..4e079f250962 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -40,7 +40,7 @@ #include <asm/processor-flags.h> #include <asm/irq_vectors.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/asm.h> #include <asm/smap.h> #include <asm/frame.h> diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S index de1fff7188aa..d6a6080bade0 100644 --- a/arch/x86/entry/vdso/vdso32/system_call.S +++ b/arch/x86/entry/vdso/vdso32/system_call.S @@ -6,7 +6,7 @@ #include <linux/linkage.h> #include <asm/dwarf2.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h>

.text .globl __kernel_vsyscall diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h deleted file mode 100644 index 464034db299f..000000000000 --- a/arch/x86/include/asm/alternative-asm.h +++ /dev/null @@ -1,114 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_ALTERNATIVE_ASM_H -#define _ASM_X86_ALTERNATIVE_ASM_H - -#ifdef __ASSEMBLY__ - -#include <asm/asm.h> - -#ifdef CONFIG_SMP - .macro LOCK_PREFIX -672: lock - .pushsection .smp_locks,"a" - .balign 4 - .long 672b - . - .popsection - .endm -#else - .macro LOCK_PREFIX - .endm -#endif - -/* - * objtool annotation to ignore the alternatives and only consider the original - * instruction(s). - */ -.macro ANNOTATE_IGNORE_ALTERNATIVE - .Lannotate_@: - .pushsection .discard.ignore_alts - .long .Lannotate_@ - . - .popsection -.endm - -/* - * Issue one struct alt_instr descriptor entry (need to put it into - * the section .altinstructions, see below). This entry contains - * enough information for the alternatives patching code to patch an - * instruction. See apply_alternatives(). - */ -.macro altinstruction_entry orig alt feature orig_len alt_len pad_len - .long \orig - . - .long \alt - . - .word \feature - .byte \orig_len - .byte \alt_len - .byte \pad_len -.endm - -/* - * Define an alternative between two instructions. If @feature is - * present, early code in apply_alternatives() replaces @oldinstr with - * @newinstr. ".skip" directive takes care of proper instruction padding - * in case @newinstr is longer than @oldinstr. - */ -.macro ALTERNATIVE oldinstr, newinstr, feature -140: - \oldinstr -141: - .skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90 -142: - - .pushsection .altinstructions,"a" - altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b - .popsection - - .pushsection .altinstr_replacement,"ax" -143: - \newinstr -144: - .popsection -.endm - -#define old_len 141b-140b -#define new_len1 144f-143f -#define new_len2 145f-144f - -/* - * gas compatible max based on the idea from: - * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax - * - * The additional "-" is needed because gas uses a "true" value of -1. - */ -#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) - - -/* - * Same as ALTERNATIVE macro above but for two alternatives. If CPU - * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has - * @feature2, it replaces @oldinstr with @feature2. - */ -.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2 -140: - \oldinstr -141: - .skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \ - (alt_max_short(new_len1, new_len2) - (old_len)),0x90 -142: - - .pushsection .altinstructions,"a" - altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b - altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b - .popsection - - .pushsection .altinstr_replacement,"ax" -143: - \newinstr1 -144: - \newinstr2 -145: - .popsection -.endm - -#endif /* __ASSEMBLY__ */ - -#endif /* _ASM_X86_ALTERNATIVE_ASM_H */ diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 13adca37c99a..aa5f246fdc07 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -2,13 +2,14 @@ #ifndef _ASM_X86_ALTERNATIVE_H #define _ASM_X86_ALTERNATIVE_H

-#ifndef __ASSEMBLY__ - #include <linux/types.h> -#include <linux/stddef.h> #include <linux/stringify.h> #include <asm/asm.h>

+#ifndef __ASSEMBLY__ + +#include <linux/stddef.h> + /* * Alternative inline assembly for SMP. * @@ -271,6 +272,111 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr

+#else /* __ASSEMBLY__ */ + +#ifdef CONFIG_SMP + .macro LOCK_PREFIX +672: lock + .pushsection .smp_locks,"a" + .balign 4 + .long 672b - . + .popsection + .endm +#else + .macro LOCK_PREFIX + .endm +#endif + +/* + * objtool annotation to ignore the alternatives and only consider the original + * instruction(s). + */ +.macro ANNOTATE_IGNORE_ALTERNATIVE + .Lannotate_@: + .pushsection .discard.ignore_alts + .long .Lannotate_@ - . + .popsection +.endm + +/* + * Issue one struct alt_instr descriptor entry (need to put it into + * the section .altinstructions, see below). This entry contains + * enough information for the alternatives patching code to patch an + * instruction. See apply_alternatives(). + */ +.macro altinstruction_entry orig alt feature orig_len alt_len pad_len + .long \orig - . + .long \alt - . + .word \feature + .byte \orig_len + .byte \alt_len + .byte \pad_len +.endm + +/* + * Define an alternative between two instructions. If @feature is + * present, early code in apply_alternatives() replaces @oldinstr with + * @newinstr. ".skip" directive takes care of proper instruction padding + * in case @newinstr is longer than @oldinstr. + */ +.macro ALTERNATIVE oldinstr, newinstr, feature +140: + \oldinstr +141: + .skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90 +142: + + .pushsection .altinstructions,"a" + altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b + .popsection + + .pushsection .altinstr_replacement,"ax" +143: + \newinstr +144: + .popsection +.endm + +#define old_len 141b-140b +#define new_len1 144f-143f +#define new_len2 145f-144f + +/* + * gas compatible max based on the idea from: + * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax + * + * The additional "-" is needed because gas uses a "true" value of -1. + */ +#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) + + +/* + * Same as ALTERNATIVE macro above but for two alternatives. If CPU + * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has + * @feature2, it replaces @oldinstr with @feature2. + */ +.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2 +140: + \oldinstr +141: + .skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \ + (alt_max_short(new_len1, new_len2) - (old_len)),0x90 +142: + + .pushsection .altinstructions,"a" + altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b + altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b + .popsection + + .pushsection .altinstr_replacement,"ax" +143: + \newinstr1 +144: + \newinstr2 +145: + .popsection +.endm + #endif /* __ASSEMBLY__ */

#endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index e247151c3dcf..c5820916cd4f 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -7,7 +7,6 @@ #include <linux/objtool.h>

#include <asm/alternative.h> -#include <asm/alternative-asm.h> #include <asm/cpufeatures.h> #include <asm/msr-index.h> #include <asm/unwind_hints.h> diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index 8b58d6975d5d..ea1d8eb644cb 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -11,6 +11,7 @@

#include <asm/nops.h> #include <asm/cpufeatures.h> +#include <asm/alternative.h>

/* "Raw" instruction opcodes */ #define __ASM_CLAC ".byte 0x0f,0x01,0xca" @@ -18,8 +19,6 @@

#ifdef __ASSEMBLY__

-#include <asm/alternative-asm.h> - #ifdef CONFIG_X86_SMAP

#define ASM_CLAC \ @@ -37,8 +36,6 @@

#else /* __ASSEMBLY__ */

-#include <asm/alternative.h> - #ifdef CONFIG_X86_SMAP

static __always_inline void clac(void) diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S index 3b6544111ac9..16bc9130e7a5 100644 --- a/arch/x86/lib/atomic64_386_32.S +++ b/arch/x86/lib/atomic64_386_32.S @@ -6,7 +6,7 @@ */

#include <linux/linkage.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h>

/* if you want SMP support, implement these with real spinlocks */ .macro LOCK reg diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index 1c5c81c16b06..ce6935690766 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -6,7 +6,7 @@ */

#include <linux/linkage.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h>

.macro read64 reg movl %ebx, %eax diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index 16ca196d349b..0751592089e9 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -3,7 +3,7 @@

#include <linux/linkage.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h>

/* diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 77b9b2a3b5c8..57b79c577496 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -11,7 +11,7 @@ #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/asm.h> #include <asm/smap.h> #include <asm/export.h> diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 1e299ac73c86..1cc9da6e29c7 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -4,7 +4,7 @@ #include <linux/linkage.h> #include <asm/errno.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h>

.pushsection .noinstr.text, "ax" diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 41902fe8b859..64801010d312 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -8,7 +8,7 @@ */ #include <linux/linkage.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h>

#undef memmove diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 0bfd26e4ca9e..9827ae267f96 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -3,7 +3,7 @@

#include <linux/linkage.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h>

/* diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index f6fb1d218dcc..6bb74b5c238c 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -4,7 +4,7 @@ #include <linux/linkage.h> #include <asm/dwarf2.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h> #include <asm/nospec-branch.h> #include <asm/unwind_hints.h>

From: Juergen Gross jgross@suse.com

stable inclusion from stable-v5.10.133 commit 341e6178c1cf6225e085de9eaba6216d624d641e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit e208b3c4a9748b2c17aa09ba663b5096ccf82dce upstream.

Add ALTERNATIVE_TERNARY support for replacing an initial instruction with either of two instructions depending on a feature:

ALTERNATIVE_TERNARY "default_instr", FEATURE_NR, "feature_on_instr", "feature_off_instr"

which will start with "default_instr" and at patch time will, depending on FEATURE_NR being set or not, patch that with either "feature_on_instr" or "feature_off_instr".

[ bp: Add comment ontop. ]

Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20210311142319.4723-7-jgross@suse.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/alternative.h | 13 +++++++++++++ 1 file changed, 13 insertions(+)

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index c6690d1e1de6..be29b927ff1e 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -179,6 +179,11 @@ static inline int alternatives_text_reserved(void *start, void *end) ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \ ".popsection\n"

+/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */ +#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \ + ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \ + newinstr_yes, feature) + #define ALTERNATIVE_3(oldinsn, newinsn1, feat1, newinsn2, feat2, newinsn3, feat3) \ OLDINSTR_3(oldinsn, 1, 2, 3) \ ".pushsection .altinstructions,"a"\n" \ @@ -210,6 +215,9 @@ static inline int alternatives_text_reserved(void *start, void *end) #define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \ asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory")

+#define alternative_ternary(oldinstr, feature, newinstr_yes, newinstr_no) \ + asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) ::: "memory") + /* * Alternative inline assembly with input. * @@ -380,6 +388,11 @@ static inline int alternatives_text_reserved(void *start, void *end) .popsection .endm

+/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */ +#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \ + ALTERNATIVE_2 oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \ + newinstr_yes, feature + #endif /* __ASSEMBLY__ */

#endif /* _ASM_X86_ALTERNATIVE_H */

From: Borislav Petkov bp@suse.de

stable inclusion from stable-v5.10.133 commit a3d96c74395e162e880515d711ab96f5959856ec category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 9e761296c52dcdb1aaa151b65bd39accb05740d9 upstream.

Rename insn_decode() to insn_decode_from_regs() to denote that it receives regs as param and uses registers from there during decoding. Free the former name for a more generic version of the function.

No functional changes.

Signed-off-by: Borislav Petkov bp@suse.de Link: https://lkml.kernel.org/r/20210304174237.31945-2-bp@alien8.de Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/insn-eval.h | 4 ++-- arch/x86/kernel/sev-es.c | 2 +- arch/x86/kernel/umip.c | 2 +- arch/x86/lib/insn-eval.c | 6 +++--- 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index c1438f9239e4..594ad2f57d23 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -26,7 +26,7 @@ int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE]); int insn_fetch_from_user_inatomic(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE]); -bool insn_decode(struct insn *insn, struct pt_regs *regs, - unsigned char buf[MAX_INSN_SIZE], int buf_size); +bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs, + unsigned char buf[MAX_INSN_SIZE], int buf_size);

#endif /* _ASM_X86_INSN_EVAL_H */ diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index c222fab112cb..f441002c2327 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -236,7 +236,7 @@ static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) return ES_EXCEPTION; }

- if (!insn_decode(&ctxt->insn, ctxt->regs, buffer, res)) + if (!insn_decode_from_regs(&ctxt->insn, ctxt->regs, buffer, res)) return ES_DECODE_FAILED; } else { res = vc_fetch_insn_kernel(ctxt, buffer); diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c index f6225bf22c02..8032f5f7eef9 100644 --- a/arch/x86/kernel/umip.c +++ b/arch/x86/kernel/umip.c @@ -356,7 +356,7 @@ bool fixup_umip_exception(struct pt_regs *regs) if (!nr_copied) return false;

- if (!insn_decode(&insn, regs, buf, nr_copied)) + if (!insn_decode_from_regs(&insn, regs, buf, nr_copied)) return false;

umip_inst = identify_insn(&insn); diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index c6a19c88af54..3a7e307d42aa 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -1492,7 +1492,7 @@ int insn_fetch_from_user_inatomic(struct pt_regs *regs, unsigned char buf[MAX_IN }

/** - * insn_decode() - Decode an instruction + * insn_decode_from_regs() - Decode an instruction * @insn: Structure to store decoded instruction * @regs: Structure with register values as seen when entering kernel mode * @buf: Buffer containing the instruction bytes @@ -1505,8 +1505,8 @@ int insn_fetch_from_user_inatomic(struct pt_regs *regs, unsigned char buf[MAX_IN * * True if instruction was decoded, False otherwise. */ -bool insn_decode(struct insn *insn, struct pt_regs *regs, - unsigned char buf[MAX_INSN_SIZE], int buf_size) +bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs, + unsigned char buf[MAX_INSN_SIZE], int buf_size) { int seg_defs;

From: Borislav Petkov bp@suse.de

stable inclusion from stable-v5.10.133 commit 6bc6875b82a0cb99212c4b78fe7606418888af30 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 93281c4a96572a34504244969b938e035204778d upstream.

Users of the instruction decoder should use this to decode instruction bytes. For that, have insn*() helpers return an int value to denote success/failure. When there's an error fetching the next insn byte and the insn falls short, return -ENODATA to denote that.

While at it, make insn_get_opcode() more stricter as to whether what has seen so far is a valid insn and if not.

Copy linux/kconfig.h for the tools-version of the decoder so that it can use IS_ENABLED().

Also, cast the INSN_MODE_KERN dummy define value to (enum insn_mode) for tools use of the decoder because perf tool builds with -Werror and errors out with -Werror=sign-compare otherwise.

Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Masami Hiramatsu mhiramat@kernel.org Link: https://lkml.kernel.org/r/20210304174237.31945-5-bp@alien8.de Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/insn.h | 24 +++- arch/x86/lib/insn.c | 216 +++++++++++++++++++++++------ tools/arch/x86/include/asm/insn.h | 24 +++- tools/arch/x86/lib/insn.c | 222 +++++++++++++++++++++++------- tools/include/linux/kconfig.h | 73 ++++++++++ 5 files changed, 452 insertions(+), 107 deletions(-) create mode 100644 tools/include/linux/kconfig.h

diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index 17c130f1ba57..546436b3c215 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -87,13 +87,23 @@ struct insn { #define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */

extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64); -extern void insn_get_prefixes(struct insn *insn); -extern void insn_get_opcode(struct insn *insn); -extern void insn_get_modrm(struct insn *insn); -extern void insn_get_sib(struct insn *insn); -extern void insn_get_displacement(struct insn *insn); -extern void insn_get_immediate(struct insn *insn); -extern void insn_get_length(struct insn *insn); +extern int insn_get_prefixes(struct insn *insn); +extern int insn_get_opcode(struct insn *insn); +extern int insn_get_modrm(struct insn *insn); +extern int insn_get_sib(struct insn *insn); +extern int insn_get_displacement(struct insn *insn); +extern int insn_get_immediate(struct insn *insn); +extern int insn_get_length(struct insn *insn); + +enum insn_mode { + INSN_MODE_32, + INSN_MODE_64, + /* Mode is determined by the current kernel build. */ + INSN_MODE_KERN, + INSN_NUM_MODES, +}; + +extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m);

/* Attribute will be determined after getting ModRM (for opcode groups) */ static inline void insn_get_attribute(struct insn *insn) diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index ce07af6ba5e9..24e89239dcca 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -13,6 +13,9 @@ #include <asm/inat.h> /*__ignore_sync_check__ */ #include <asm/insn.h> /* __ignore_sync_check__ */

+#include <linux/errno.h> +#include <linux/kconfig.h> + #include <asm/emulate_prefix.h> /* __ignore_sync_check__ */

/* Verify next sizeof(t) bytes can be on the same instruction */ @@ -97,8 +100,12 @@ static void insn_get_emulate_prefix(struct insn *insn) * Populates the @insn->prefixes bitmap, and updates @insn->next_byte * to point to the (first) opcode. No effect if @insn->prefixes.got * is already set. + * + * * Returns: + * 0: on success + * < 0: on error */ -void insn_get_prefixes(struct insn *insn) +int insn_get_prefixes(struct insn *insn) { struct insn_field *prefixes = &insn->prefixes; insn_attr_t attr; @@ -106,7 +113,7 @@ void insn_get_prefixes(struct insn *insn) int i, nb;

if (prefixes->got) - return; + return 0;

insn_get_emulate_prefix(insn);

@@ -217,8 +224,10 @@ void insn_get_prefixes(struct insn *insn)

prefixes->got = 1;

+ return 0; + err_out: - return; + return -ENODATA; }

/** @@ -230,16 +239,25 @@ void insn_get_prefixes(struct insn *insn) * If necessary, first collects any preceding (prefix) bytes. * Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got * is already 1. + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_opcode(struct insn *insn) +int insn_get_opcode(struct insn *insn) { struct insn_field *opcode = &insn->opcode; + int pfx_id, ret; insn_byte_t op; - int pfx_id; + if (opcode->got) - return; - if (!insn->prefixes.got) - insn_get_prefixes(insn); + return 0; + + if (!insn->prefixes.got) { + ret = insn_get_prefixes(insn); + if (ret) + return ret; + }

/* Get first opcode */ op = get_next(insn_byte_t, insn); @@ -254,9 +272,13 @@ void insn_get_opcode(struct insn *insn) insn->attr = inat_get_avx_attribute(op, m, p); if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || (!inat_accept_vex(insn->attr) && - !inat_is_group(insn->attr))) - insn->attr = 0; /* This instruction is bad */ - goto end; /* VEX has only 1 byte for opcode */ + !inat_is_group(insn->attr))) { + /* This instruction is bad */ + insn->attr = 0; + return -EINVAL; + } + /* VEX has only 1 byte for opcode */ + goto end; }

insn->attr = inat_get_opcode_attribute(op); @@ -267,13 +289,18 @@ void insn_get_opcode(struct insn *insn) pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr); } - if (inat_must_vex(insn->attr)) - insn->attr = 0; /* This instruction is bad */ + + if (inat_must_vex(insn->attr)) { + /* This instruction is bad */ + insn->attr = 0; + return -EINVAL; + } end: opcode->got = 1; + return 0;

err_out: - return; + return -ENODATA; }

/** @@ -283,15 +310,25 @@ void insn_get_opcode(struct insn *insn) * Populates @insn->modrm and updates @insn->next_byte to point past the * ModRM byte, if any. If necessary, first collects the preceding bytes * (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1. + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_modrm(struct insn *insn) +int insn_get_modrm(struct insn *insn) { struct insn_field *modrm = &insn->modrm; insn_byte_t pfx_id, mod; + int ret; + if (modrm->got) - return; - if (!insn->opcode.got) - insn_get_opcode(insn); + return 0; + + if (!insn->opcode.got) { + ret = insn_get_opcode(insn); + if (ret) + return ret; + }

if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); @@ -301,17 +338,22 @@ void insn_get_modrm(struct insn *insn) pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_group_attribute(mod, pfx_id, insn->attr); - if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) - insn->attr = 0; /* This is bad */ + if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) { + /* Bad insn */ + insn->attr = 0; + return -EINVAL; + } } }

if (insn->x86_64 && inat_is_force64(insn->attr)) insn->opnd_bytes = 8; + modrm->got = 1; + return 0;

err_out: - return; + return -ENODATA; }

@@ -325,11 +367,16 @@ void insn_get_modrm(struct insn *insn) int insn_rip_relative(struct insn *insn) { struct insn_field *modrm = &insn->modrm; + int ret;

if (!insn->x86_64) return 0; - if (!modrm->got) - insn_get_modrm(insn); + + if (!modrm->got) { + ret = insn_get_modrm(insn); + if (ret) + return 0; + } /* * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. @@ -343,15 +390,25 @@ int insn_rip_relative(struct insn *insn) * * If necessary, first collects the instruction up to and including the * ModRM byte. + * + * Returns: + * 0: if decoding succeeded + * < 0: otherwise. */ -void insn_get_sib(struct insn *insn) +int insn_get_sib(struct insn *insn) { insn_byte_t modrm; + int ret;

if (insn->sib.got) - return; - if (!insn->modrm.got) - insn_get_modrm(insn); + return 0; + + if (!insn->modrm.got) { + ret = insn_get_modrm(insn); + if (ret) + return ret; + } + if (insn->modrm.nbytes) { modrm = (insn_byte_t)insn->modrm.value; if (insn->addr_bytes != 2 && @@ -362,8 +419,10 @@ void insn_get_sib(struct insn *insn) } insn->sib.got = 1;

+ return 0; + err_out: - return; + return -ENODATA; }

@@ -374,15 +433,25 @@ void insn_get_sib(struct insn *insn) * If necessary, first collects the instruction up to and including the * SIB byte. * Displacement value is sign-expanded. + * + * * Returns: + * 0: if decoding succeeded + * < 0: otherwise. */ -void insn_get_displacement(struct insn *insn) +int insn_get_displacement(struct insn *insn) { insn_byte_t mod, rm, base; + int ret;

if (insn->displacement.got) - return; - if (!insn->sib.got) - insn_get_sib(insn); + return 0; + + if (!insn->sib.got) { + ret = insn_get_sib(insn); + if (ret) + return ret; + } + if (insn->modrm.nbytes) { /* * Interpreting the modrm byte: @@ -425,9 +494,10 @@ void insn_get_displacement(struct insn *insn) } out: insn->displacement.got = 1; + return 0;

err_out: - return; + return -ENODATA; }

/* Decode moffset16/32/64. Return 0 if failed */ @@ -538,20 +608,30 @@ static int __get_immptr(struct insn *insn) }

/** - * insn_get_immediate() - Get the immediates of instruction + * insn_get_immediate() - Get the immediate in an instruction * @insn: &struct insn containing instruction * * If necessary, first collects the instruction up to and including the * displacement bytes. * Basically, most of immediates are sign-expanded. Unsigned-value can be - * get by bit masking with ((1 << (nbytes * 8)) - 1) + * computed by bit masking with ((1 << (nbytes * 8)) - 1) + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_immediate(struct insn *insn) +int insn_get_immediate(struct insn *insn) { + int ret; + if (insn->immediate.got) - return; - if (!insn->displacement.got) - insn_get_displacement(insn); + return 0; + + if (!insn->displacement.got) { + ret = insn_get_displacement(insn); + if (ret) + return ret; + }

if (inat_has_moffset(insn->attr)) { if (!__get_moffset(insn)) @@ -604,9 +684,10 @@ void insn_get_immediate(struct insn *insn) } done: insn->immediate.got = 1; + return 0;

err_out: - return; + return -ENODATA; }

/** @@ -615,13 +696,58 @@ void insn_get_immediate(struct insn *insn) * * If necessary, first collects the instruction up to and including the * immediates bytes. - */ -void insn_get_length(struct insn *insn) + * + * Returns: + * - 0 on success + * - < 0 on error +*/ +int insn_get_length(struct insn *insn) { + int ret; + if (insn->length) - return; - if (!insn->immediate.got) - insn_get_immediate(insn); + return 0; + + if (!insn->immediate.got) { + ret = insn_get_immediate(insn); + if (ret) + return ret; + } + insn->length = (unsigned char)((unsigned long)insn->next_byte - (unsigned long)insn->kaddr); + + return 0; +} + +/** + * insn_decode() - Decode an x86 instruction + * @insn: &struct insn to be initialized + * @kaddr: address (in kernel memory) of instruction (or copy thereof) + * @buf_len: length of the insn buffer at @kaddr + * @m: insn mode, see enum insn_mode + * + * Returns: + * 0: if decoding succeeded + * < 0: otherwise. + */ +int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m) +{ + int ret; + +/* #define INSN_MODE_KERN -1 __ignore_sync_check__ mode is only valid in the kernel */ + + if (m == INSN_MODE_KERN) + insn_init(insn, kaddr, buf_len, IS_ENABLED(CONFIG_X86_64)); + else + insn_init(insn, kaddr, buf_len, m == INSN_MODE_64); + + ret = insn_get_length(insn); + if (ret) + return ret; + + if (insn_complete(insn)) + return 0; + + return -EINVAL; } diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h index 33d41982a5dd..621ab64a6d27 100644 --- a/tools/arch/x86/include/asm/insn.h +++ b/tools/arch/x86/include/asm/insn.h @@ -87,13 +87,23 @@ struct insn { #define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */

extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64); -extern void insn_get_prefixes(struct insn *insn); -extern void insn_get_opcode(struct insn *insn); -extern void insn_get_modrm(struct insn *insn); -extern void insn_get_sib(struct insn *insn); -extern void insn_get_displacement(struct insn *insn); -extern void insn_get_immediate(struct insn *insn); -extern void insn_get_length(struct insn *insn); +extern int insn_get_prefixes(struct insn *insn); +extern int insn_get_opcode(struct insn *insn); +extern int insn_get_modrm(struct insn *insn); +extern int insn_get_sib(struct insn *insn); +extern int insn_get_displacement(struct insn *insn); +extern int insn_get_immediate(struct insn *insn); +extern int insn_get_length(struct insn *insn); + +enum insn_mode { + INSN_MODE_32, + INSN_MODE_64, + /* Mode is determined by the current kernel build. */ + INSN_MODE_KERN, + INSN_NUM_MODES, +}; + +extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m);

/* Attribute will be determined after getting ModRM (for opcode groups) */ static inline void insn_get_attribute(struct insn *insn) diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c index 6c82e3526127..819c82529fe8 100644 --- a/tools/arch/x86/lib/insn.c +++ b/tools/arch/x86/lib/insn.c @@ -10,10 +10,13 @@ #else #include <string.h> #endif -#include "../include/asm/inat.h" /* __ignore_sync_check__ */ -#include "../include/asm/insn.h" /* __ignore_sync_check__ */ +#include <asm/inat.h> /* __ignore_sync_check__ */ +#include <asm/insn.h> /* __ignore_sync_check__ */

-#include "../include/asm/emulate_prefix.h" /* __ignore_sync_check__ */ +#include <linux/errno.h> +#include <linux/kconfig.h> + +#include <asm/emulate_prefix.h> /* __ignore_sync_check__ */

/* Verify next sizeof(t) bytes can be on the same instruction */ #define validate_next(t, insn, n) \ @@ -97,8 +100,12 @@ static void insn_get_emulate_prefix(struct insn *insn) * Populates the @insn->prefixes bitmap, and updates @insn->next_byte * to point to the (first) opcode. No effect if @insn->prefixes.got * is already set. + * + * * Returns: + * 0: on success + * < 0: on error */ -void insn_get_prefixes(struct insn *insn) +int insn_get_prefixes(struct insn *insn) { struct insn_field *prefixes = &insn->prefixes; insn_attr_t attr; @@ -106,7 +113,7 @@ void insn_get_prefixes(struct insn *insn) int i, nb;

if (prefixes->got) - return; + return 0;

insn_get_emulate_prefix(insn);

@@ -217,8 +224,10 @@ void insn_get_prefixes(struct insn *insn)

prefixes->got = 1;

+ return 0; + err_out: - return; + return -ENODATA; }

/** @@ -230,16 +239,25 @@ void insn_get_prefixes(struct insn *insn) * If necessary, first collects any preceding (prefix) bytes. * Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got * is already 1. + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_opcode(struct insn *insn) +int insn_get_opcode(struct insn *insn) { struct insn_field *opcode = &insn->opcode; + int pfx_id, ret; insn_byte_t op; - int pfx_id; + if (opcode->got) - return; - if (!insn->prefixes.got) - insn_get_prefixes(insn); + return 0; + + if (!insn->prefixes.got) { + ret = insn_get_prefixes(insn); + if (ret) + return ret; + }

/* Get first opcode */ op = get_next(insn_byte_t, insn); @@ -254,9 +272,13 @@ void insn_get_opcode(struct insn *insn) insn->attr = inat_get_avx_attribute(op, m, p); if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) || (!inat_accept_vex(insn->attr) && - !inat_is_group(insn->attr))) - insn->attr = 0; /* This instruction is bad */ - goto end; /* VEX has only 1 byte for opcode */ + !inat_is_group(insn->attr))) { + /* This instruction is bad */ + insn->attr = 0; + return -EINVAL; + } + /* VEX has only 1 byte for opcode */ + goto end; }

insn->attr = inat_get_opcode_attribute(op); @@ -267,13 +289,18 @@ void insn_get_opcode(struct insn *insn) pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr); } - if (inat_must_vex(insn->attr)) - insn->attr = 0; /* This instruction is bad */ + + if (inat_must_vex(insn->attr)) { + /* This instruction is bad */ + insn->attr = 0; + return -EINVAL; + } end: opcode->got = 1; + return 0;

err_out: - return; + return -ENODATA; }

/** @@ -283,15 +310,25 @@ void insn_get_opcode(struct insn *insn) * Populates @insn->modrm and updates @insn->next_byte to point past the * ModRM byte, if any. If necessary, first collects the preceding bytes * (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1. + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_modrm(struct insn *insn) +int insn_get_modrm(struct insn *insn) { struct insn_field *modrm = &insn->modrm; insn_byte_t pfx_id, mod; + int ret; + if (modrm->got) - return; - if (!insn->opcode.got) - insn_get_opcode(insn); + return 0; + + if (!insn->opcode.got) { + ret = insn_get_opcode(insn); + if (ret) + return ret; + }

if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); @@ -301,17 +338,22 @@ void insn_get_modrm(struct insn *insn) pfx_id = insn_last_prefix_id(insn); insn->attr = inat_get_group_attribute(mod, pfx_id, insn->attr); - if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) - insn->attr = 0; /* This is bad */ + if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) { + /* Bad insn */ + insn->attr = 0; + return -EINVAL; + } } }

if (insn->x86_64 && inat_is_force64(insn->attr)) insn->opnd_bytes = 8; + modrm->got = 1; + return 0;

err_out: - return; + return -ENODATA; }

@@ -325,11 +367,16 @@ void insn_get_modrm(struct insn *insn) int insn_rip_relative(struct insn *insn) { struct insn_field *modrm = &insn->modrm; + int ret;

if (!insn->x86_64) return 0; - if (!modrm->got) - insn_get_modrm(insn); + + if (!modrm->got) { + ret = insn_get_modrm(insn); + if (ret) + return 0; + } /* * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. @@ -343,15 +390,25 @@ int insn_rip_relative(struct insn *insn) * * If necessary, first collects the instruction up to and including the * ModRM byte. + * + * Returns: + * 0: if decoding succeeded + * < 0: otherwise. */ -void insn_get_sib(struct insn *insn) +int insn_get_sib(struct insn *insn) { insn_byte_t modrm; + int ret;

if (insn->sib.got) - return; - if (!insn->modrm.got) - insn_get_modrm(insn); + return 0; + + if (!insn->modrm.got) { + ret = insn_get_modrm(insn); + if (ret) + return ret; + } + if (insn->modrm.nbytes) { modrm = (insn_byte_t)insn->modrm.value; if (insn->addr_bytes != 2 && @@ -362,8 +419,10 @@ void insn_get_sib(struct insn *insn) } insn->sib.got = 1;

+ return 0; + err_out: - return; + return -ENODATA; }

@@ -374,15 +433,25 @@ void insn_get_sib(struct insn *insn) * If necessary, first collects the instruction up to and including the * SIB byte. * Displacement value is sign-expanded. + * + * * Returns: + * 0: if decoding succeeded + * < 0: otherwise. */ -void insn_get_displacement(struct insn *insn) +int insn_get_displacement(struct insn *insn) { insn_byte_t mod, rm, base; + int ret;

if (insn->displacement.got) - return; - if (!insn->sib.got) - insn_get_sib(insn); + return 0; + + if (!insn->sib.got) { + ret = insn_get_sib(insn); + if (ret) + return ret; + } + if (insn->modrm.nbytes) { /* * Interpreting the modrm byte: @@ -425,9 +494,10 @@ void insn_get_displacement(struct insn *insn) } out: insn->displacement.got = 1; + return 0;

err_out: - return; + return -ENODATA; }

/* Decode moffset16/32/64. Return 0 if failed */ @@ -538,20 +608,30 @@ static int __get_immptr(struct insn *insn) }

/** - * insn_get_immediate() - Get the immediates of instruction + * insn_get_immediate() - Get the immediate in an instruction * @insn: &struct insn containing instruction * * If necessary, first collects the instruction up to and including the * displacement bytes. * Basically, most of immediates are sign-expanded. Unsigned-value can be - * get by bit masking with ((1 << (nbytes * 8)) - 1) + * computed by bit masking with ((1 << (nbytes * 8)) - 1) + * + * Returns: + * 0: on success + * < 0: on error */ -void insn_get_immediate(struct insn *insn) +int insn_get_immediate(struct insn *insn) { + int ret; + if (insn->immediate.got) - return; - if (!insn->displacement.got) - insn_get_displacement(insn); + return 0; + + if (!insn->displacement.got) { + ret = insn_get_displacement(insn); + if (ret) + return ret; + }

if (inat_has_moffset(insn->attr)) { if (!__get_moffset(insn)) @@ -604,9 +684,10 @@ void insn_get_immediate(struct insn *insn) } done: insn->immediate.got = 1; + return 0;

err_out: - return; + return -ENODATA; }

/** @@ -615,13 +696,58 @@ void insn_get_immediate(struct insn *insn) * * If necessary, first collects the instruction up to and including the * immediates bytes. - */ -void insn_get_length(struct insn *insn) + * + * Returns: + * - 0 on success + * - < 0 on error +*/ +int insn_get_length(struct insn *insn) { + int ret; + if (insn->length) - return; - if (!insn->immediate.got) - insn_get_immediate(insn); + return 0; + + if (!insn->immediate.got) { + ret = insn_get_immediate(insn); + if (ret) + return ret; + } + insn->length = (unsigned char)((unsigned long)insn->next_byte - (unsigned long)insn->kaddr); + + return 0; +} + +/** + * insn_decode() - Decode an x86 instruction + * @insn: &struct insn to be initialized + * @kaddr: address (in kernel memory) of instruction (or copy thereof) + * @buf_len: length of the insn buffer at @kaddr + * @m: insn mode, see enum insn_mode + * + * Returns: + * 0: if decoding succeeded + * < 0: otherwise. + */ +int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m) +{ + int ret; + +#define INSN_MODE_KERN (enum insn_mode)-1 /* __ignore_sync_check__ mode is only valid in the kernel */ + + if (m == INSN_MODE_KERN) + insn_init(insn, kaddr, buf_len, IS_ENABLED(CONFIG_X86_64)); + else + insn_init(insn, kaddr, buf_len, m == INSN_MODE_64); + + ret = insn_get_length(insn); + if (ret) + return ret; + + if (insn_complete(insn)) + return 0; + + return -EINVAL; } diff --git a/tools/include/linux/kconfig.h b/tools/include/linux/kconfig.h new file mode 100644 index 000000000000..1555a0c4f345 --- /dev/null +++ b/tools/include/linux/kconfig.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _TOOLS_LINUX_KCONFIG_H +#define _TOOLS_LINUX_KCONFIG_H + +/* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */ + +#ifdef CONFIG_CPU_BIG_ENDIAN +#define __BIG_ENDIAN 4321 +#else +#define __LITTLE_ENDIAN 1234 +#endif + +#define __ARG_PLACEHOLDER_1 0, +#define __take_second_arg(__ignored, val, ...) val + +/* + * The use of "&&" / "||" is limited in certain expressions. + * The following enable to calculate "and" / "or" with macro expansion only. + */ +#define __and(x, y) ___and(x, y) +#define ___and(x, y) ____and(__ARG_PLACEHOLDER_##x, y) +#define ____and(arg1_or_junk, y) __take_second_arg(arg1_or_junk y, 0) + +#define __or(x, y) ___or(x, y) +#define ___or(x, y) ____or(__ARG_PLACEHOLDER_##x, y) +#define ____or(arg1_or_junk, y) __take_second_arg(arg1_or_junk 1, y) + +/* + * Helper macros to use CONFIG_ options in C/CPP expressions. Note that + * these only work with boolean and tristate options. + */ + +/* + * Getting something that works in C and CPP for an arg that may or may + * not be defined is tricky. Here, if we have "#define CONFIG_BOOGER 1" + * we match on the placeholder define, insert the "0," for arg1 and generate + * the triplet (0, 1, 0). Then the last step cherry picks the 2nd arg (a one). + * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when + * the last step cherry picks the 2nd arg, we get a zero. + */ +#define __is_defined(x) ___is_defined(x) +#define ___is_defined(val) ____is_defined(__ARG_PLACEHOLDER_##val) +#define ____is_defined(arg1_or_junk) __take_second_arg(arg1_or_junk 1, 0) + +/* + * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0 + * otherwise. For boolean options, this is equivalent to + * IS_ENABLED(CONFIG_FOO). + */ +#define IS_BUILTIN(option) __is_defined(option) + +/* + * IS_MODULE(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'm', 0 + * otherwise. + */ +#define IS_MODULE(option) __is_defined(option##_MODULE) + +/* + * IS_REACHABLE(CONFIG_FOO) evaluates to 1 if the currently compiled + * code can call a function defined in code compiled based on CONFIG_FOO. + * This is similar to IS_ENABLED(), but returns false when invoked from + * built-in code when CONFIG_FOO is set to 'm'. + */ +#define IS_REACHABLE(option) __or(IS_BUILTIN(option), \ + __and(IS_MODULE(option), __is_defined(MODULE))) + +/* + * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm', + * 0 otherwise. + */ +#define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option)) + +#endif /* _TOOLS_LINUX_KCONFIG_H */

From: Ben Hutchings ben@decadent.org.uk

stable inclusion from stable-v5.10.133 commit 9a6471666b7387ba0af70d504fe1602cc3d3e5b2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

This was done by commit 52fa82c21f64e900a72437269a5cc9e0034b424e upstream, but this backport avoids changing all callers of the old decoder API.

Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/insn.h | 2 ++ arch/x86/kernel/alternative.c | 2 +- tools/arch/x86/include/asm/insn.h | 2 ++ 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h index 546436b3c215..0da37756917a 100644 --- a/arch/x86/include/asm/insn.h +++ b/arch/x86/include/asm/insn.h @@ -105,6 +105,8 @@ enum insn_mode {

extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m);

+#define insn_decode_kernel(_insn, _ptr) insn_decode((_insn), (_ptr), MAX_INSN_SIZE, INSN_MODE_KERN) + /* Attribute will be determined after getting ModRM (for opcode groups) */ static inline void insn_get_attribute(struct insn *insn) { diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 2bc76137c4e7..198dfe0b8326 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1290,7 +1290,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, if (!emulate) emulate = opcode;

- ret = insn_decode(&insn, emulate, MAX_INSN_SIZE, INSN_MODE_KERN); + ret = insn_decode_kernel(&insn, emulate);

BUG_ON(ret < 0); BUG_ON(len != insn.length); diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h index 621ab64a6d27..636ec02793a7 100644 --- a/tools/arch/x86/include/asm/insn.h +++ b/tools/arch/x86/include/asm/insn.h @@ -105,6 +105,8 @@ enum insn_mode {

extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m);

+#define insn_decode_kernel(_insn, _ptr) insn_decode((_insn), (_ptr), MAX_INSN_SIZE, INSN_MODE_KERN) + /* Attribute will be determined after getting ModRM (for opcode groups) */ static inline void insn_get_attribute(struct insn *insn) {

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 28ca351296742a9e7506a548acaf7ea3bc9feef0 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 119251855f9adf9421cb5eb409933092141ab2c7 upstream.

Due to:

c9c324dc22aa ("objtool: Support stack layout changes in alternatives")

it is now possible to simplify the retpolines.

Currently our retpolines consist of 2 symbols:

- __x86_indirect_thunk_\reg: the compiler target - __x86_retpoline_\reg: the actual retpoline.

Both are consecutive in code and aligned such that for any one register they both live in the same cacheline:

0000000000000000 <__x86_indirect_thunk_rax>: 0: ff e0 jmpq *%rax 2: 90 nop 3: 90 nop 4: 90 nop

0000000000000005 <__x86_retpoline_rax>: 5: e8 07 00 00 00 callq 11 <__x86_retpoline_rax+0xc> a: f3 90 pause c: 0f ae e8 lfence f: eb f9 jmp a <__x86_retpoline_rax+0x5> 11: 48 89 04 24 mov %rax,(%rsp) 15: c3 retq 16: 66 2e 0f 1f 84 00 00 00 00 00 nopw %cs:0x0(%rax,%rax,1)

The thunk is an alternative_2, where one option is a JMP to the retpoline. This was done so that objtool didn't need to deal with alternatives with stack ops. But that problem has been solved, so now it is possible to fold the entire retpoline into the alternative to simplify and consolidate unused bytes:

0000000000000000 <__x86_indirect_thunk_rax>: 0: ff e0 jmpq *%rax 2: 90 nop 3: 90 nop 4: 90 nop 5: 90 nop 6: 90 nop 7: 90 nop 8: 90 nop 9: 90 nop a: 90 nop b: 90 nop c: 90 nop d: 90 nop e: 90 nop f: 90 nop 10: 90 nop 11: 66 66 2e 0f 1f 84 00 00 00 00 00 data16 nopw %cs:0x0(%rax,%rax,1) 1c: 0f 1f 40 00 nopl 0x0(%rax)

Notice that since the longest alternative sequence is now:

0: e8 07 00 00 00 callq c <.altinstr_replacement+0xc> 5: f3 90 pause 7: 0f ae e8 lfence a: eb f9 jmp 5 <.altinstr_replacement+0x5> c: 48 89 04 24 mov %rax,(%rsp) 10: c3 retq

17 bytes, we have 15 bytes NOP at the end of our 32 byte slot. (IOW, if we can shrink the retpoline by 1 byte we can pack it more densely).

[ bp: Massage commit message. ]

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Ingo Molnar mingo@kernel.org Link: https://lkml.kernel.org/r/20210326151259.506071949@infradead.org [bwh: Backported to 5.10: - Use X86_FEATRURE_RETPOLINE_LFENCE flag instead of X86_FEATURE_RETPOLINE_AMD, since the later renaming of this flag has already been applied - Adjust context] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/asm-prototypes.h | 7 ------ arch/x86/include/asm/nospec-branch.h | 6 ++--- arch/x86/lib/retpoline.S | 34 +++++++++++++-------------- tools/objtool/check.c | 3 +-- 4 files changed, 21 insertions(+), 29 deletions(-)

diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 51e2bf27cc9b..0545b07895a5 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -22,15 +22,8 @@ extern void cmpxchg8b_emu(void); #define DECL_INDIRECT_THUNK(reg) \ extern asmlinkage void __x86_indirect_thunk_ ## reg (void);

-#define DECL_RETPOLINE(reg) \ - extern asmlinkage void __x86_retpoline_ ## reg (void); - #undef GEN #define GEN(reg) DECL_INDIRECT_THUNK(reg) #include <asm/GEN-for-each-reg.h>

-#undef GEN -#define GEN(reg) DECL_RETPOLINE(reg) -#include <asm/GEN-for-each-reg.h> - #endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index c5820916cd4f..838c15e1b775 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -80,7 +80,7 @@ .macro JMP_NOSPEC reg:req #ifdef CONFIG_RETPOLINE ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ - __stringify(jmp __x86_retpoline_\reg), X86_FEATURE_RETPOLINE, \ + __stringify(jmp __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \ __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_LFENCE #else jmp *%\reg @@ -90,7 +90,7 @@ .macro CALL_NOSPEC reg:req #ifdef CONFIG_RETPOLINE ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \ - __stringify(call __x86_retpoline_\reg), X86_FEATURE_RETPOLINE, \ + __stringify(call __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \ __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_LFENCE #else call *%\reg @@ -128,7 +128,7 @@ ALTERNATIVE_2( \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ - "call __x86_retpoline_%V[thunk_target]\n", \ + "call __x86_indirect_thunk_%V[thunk_target]\n", \ X86_FEATURE_RETPOLINE, \ "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 6bb74b5c238c..b22075d6e38d 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -10,27 +10,31 @@ #include <asm/unwind_hints.h> #include <asm/frame.h>

-.macro THUNK reg - .section .text.__x86.indirect_thunk - - .align 32 -SYM_FUNC_START(__x86_indirect_thunk_\reg) - JMP_NOSPEC \reg -SYM_FUNC_END(__x86_indirect_thunk_\reg) - -SYM_FUNC_START_NOALIGN(__x86_retpoline_\reg) +.macro RETPOLINE reg ANNOTATE_INTRA_FUNCTION_CALL - call .Ldo_rop_@ + call .Ldo_rop_@ .Lspec_trap_@: UNWIND_HINT_EMPTY pause lfence - jmp .Lspec_trap_@ + jmp .Lspec_trap_@ .Ldo_rop_@: - mov %\reg, (%_ASM_SP) + mov %\reg, (%_ASM_SP) UNWIND_HINT_FUNC ret -SYM_FUNC_END(__x86_retpoline_\reg) +.endm + +.macro THUNK reg + .section .text.__x86.indirect_thunk + + .align 32 +SYM_FUNC_START(__x86_indirect_thunk_\reg) + + ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ + __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_LFENCE + +SYM_FUNC_END(__x86_indirect_thunk_\reg)

.endm

@@ -48,7 +52,6 @@ SYM_FUNC_END(__x86_retpoline_\reg)

#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym) #define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg) -#define EXPORT_RETPOLINE(reg) __EXPORT_THUNK(__x86_retpoline_ ## reg)

#undef GEN #define GEN(reg) THUNK reg @@ -58,6 +61,3 @@ SYM_FUNC_END(__x86_retpoline_\reg) #define GEN(reg) EXPORT_THUNK(reg) #include <asm/GEN-for-each-reg.h>

-#undef GEN -#define GEN(reg) EXPORT_RETPOLINE(reg) -#include <asm/GEN-for-each-reg.h> diff --git a/tools/objtool/check.c b/tools/objtool/check.c index ed5e4b04f508..334781ee60f1 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -800,8 +800,7 @@ static int add_jump_destinations(struct objtool_file *file) } else if (reloc->sym->type == STT_SECTION) { dest_sec = reloc->sym->sec; dest_off = arch_dest_reloc_offset(reloc->addend); - } else if (!strncmp(reloc->sym->name, "__x86_indirect_thunk_", 21) || - !strncmp(reloc->sym->name, "__x86_retpoline_", 16)) { + } else if (!strncmp(reloc->sym->name, "__x86_indirect_thunk_", 21)) { /* * Retpoline jumps are really dynamic jumps in * disguise, so convert them accordingly.

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit d42fa5bf19fc04833f3c27e9555051c428422248 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 530b4ddd9dd92b263081f5c7786d39a8129c8b2d upstream.

The __x86_indirect_ naming is obviously not generic. Shorten to allow matching some additional magic names later.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Ingo Molnar mingo@kernel.org Reviewed-by: Miroslav Benes mbenes@suse.cz Link: https://lkml.kernel.org/r/20210326151259.630296706@infradead.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/arch.h | 2 ++ tools/objtool/arch/x86/decode.c | 5 +++++ tools/objtool/check.c | 9 +++++++-- 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index 5e3f3ea8bb89..82896d7615f5 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -86,4 +86,6 @@ const char *arch_nop_insn(int len);

int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg);

+bool arch_is_retpoline(struct symbol *sym); + #endif /* _ARCH_H */ diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 6f5a45754ad8..a540c8cda8e1 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -620,3 +620,8 @@ int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg)

return 0; } + +bool arch_is_retpoline(struct symbol *sym) +{ + return !strncmp(sym->name, "__x86_indirect_", 15); +} diff --git a/tools/objtool/check.c b/tools/objtool/check.c index da78811ffda5..5e407ec95949 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -778,6 +778,11 @@ static int add_ignore_alternatives(struct objtool_file *file) return 0; }

+__weak bool arch_is_retpoline(struct symbol *sym) +{ + return false; +} + /* * Find the destination instructions for all jumps. */ @@ -800,7 +805,7 @@ static int add_jump_destinations(struct objtool_file *file) } else if (reloc->sym->type == STT_SECTION) { dest_sec = reloc->sym->sec; dest_off = arch_dest_reloc_offset(reloc->addend); - } else if (!strncmp(reloc->sym->name, "__x86_indirect_thunk_", 21)) { + } else if (arch_is_retpoline(reloc->sym)) { /* * Retpoline jumps are really dynamic jumps in * disguise, so convert them accordingly. @@ -954,7 +959,7 @@ static int add_call_destinations(struct objtool_file *file) return -1; }

- } else if (!strncmp(reloc->sym->name, "__x86_indirect_thunk_", 21)) { + } else if (arch_is_retpoline(reloc->sym)) { /* * Retpoline calls are really dynamic calls in * disguise, so convert them accordingly.

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit fcdb7926d399910ee847856b28d7bde5437f77f0 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit ef47cc01cb4abcd760d8ac66b9361d6ade4d0846 upstream.

We have 4 instances of adding a relocation. Create a common helper to avoid growing even more.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Ingo Molnar mingo@kernel.org Reviewed-by: Miroslav Benes mbenes@suse.cz Link: https://lkml.kernel.org/r/20210326151259.817438847@infradead.org [bwh: Backported to 5.10: drop changes in create_mcount_loc_sections()] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/check.c | 43 +++++---------------- tools/objtool/elf.c | 86 +++++++++++++++++++++++++++-------------- tools/objtool/elf.h | 10 +++-- tools/objtool/orc_gen.c | 30 +++----------- 4 files changed, 79 insertions(+), 90 deletions(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c index fb9be8ec893d..76a63294d64e 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -433,8 +433,7 @@ static int add_dead_ends(struct objtool_file *file)

static int create_static_call_sections(struct objtool_file *file) { - struct section *sec, *reloc_sec; - struct reloc *reloc; + struct section *sec; struct static_call_site *site; struct instruction *insn; struct symbol *key_sym; @@ -460,8 +459,7 @@ static int create_static_call_sections(struct objtool_file *file) if (!sec) return -1;

- reloc_sec = elf_create_reloc_section(file->elf, sec, SHT_RELA); - if (!reloc_sec) + if (!elf_create_reloc_section(file->elf, sec, SHT_RELA)) return -1;

idx = 0; @@ -471,25 +469,11 @@ static int create_static_call_sections(struct objtool_file *file) memset(site, 0, sizeof(struct static_call_site));

/* populate reloc for 'addr' */ - reloc = malloc(sizeof(*reloc)); - - if (!reloc) { - perror("malloc"); - return -1; - } - memset(reloc, 0, sizeof(*reloc)); - - insn_to_reloc_sym_addend(insn->sec, insn->offset, reloc); - if (!reloc->sym) { - WARN_FUNC("static call tramp: missing containing symbol", - insn->sec, insn->offset); + if (elf_add_reloc_to_insn(file->elf, sec, + idx * sizeof(struct static_call_site), + R_X86_64_PC32, + insn->sec, insn->offset)) return -1; - } - - reloc->type = R_X86_64_PC32; - reloc->offset = idx * sizeof(struct static_call_site); - reloc->sec = reloc_sec; - elf_add_reloc(file->elf, reloc);

/* find key symbol */ key_name = strdup(insn->call_dest->name); @@ -526,18 +510,11 @@ static int create_static_call_sections(struct objtool_file *file) free(key_name);

/* populate reloc for 'key' */ - reloc = malloc(sizeof(*reloc)); - if (!reloc) { - perror("malloc"); + if (elf_add_reloc(file->elf, sec, + idx * sizeof(struct static_call_site) + 4, + R_X86_64_PC32, key_sym, + is_sibling_call(insn) * STATIC_CALL_SITE_TAIL)) return -1; - } - memset(reloc, 0, sizeof(*reloc)); - reloc->sym = key_sym; - reloc->addend = is_sibling_call(insn) ? STATIC_CALL_SITE_TAIL : 0; - reloc->type = R_X86_64_PC32; - reloc->offset = idx * sizeof(struct static_call_site) + 4; - reloc->sec = reloc_sec; - elf_add_reloc(file->elf, reloc);

idx++; } diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index ce08aafa7da0..973f0c481bac 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -262,32 +262,6 @@ struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, uns return find_reloc_by_dest_range(elf, sec, offset, 1); }

-void insn_to_reloc_sym_addend(struct section *sec, unsigned long offset, - struct reloc *reloc) -{ - if (sec->sym) { - reloc->sym = sec->sym; - reloc->addend = offset; - return; - } - - /* - * The Clang assembler strips section symbols, so we have to reference - * the function symbol instead: - */ - reloc->sym = find_symbol_containing(sec, offset); - if (!reloc->sym) { - /* - * Hack alert. This happens when we need to reference the NOP - * pad insn immediately after the function. - */ - reloc->sym = find_symbol_containing(sec, offset - 1); - } - - if (reloc->sym) - reloc->addend = offset - reloc->sym->offset; -} - static int read_sections(struct elf *elf) { Elf_Scn *s = NULL; @@ -524,14 +498,66 @@ static int read_symbols(struct elf *elf) return -1; }

-void elf_add_reloc(struct elf *elf, struct reloc *reloc) +int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, + unsigned int type, struct symbol *sym, int addend) { - struct section *sec = reloc->sec; + struct reloc *reloc; + + reloc = malloc(sizeof(*reloc)); + if (!reloc) { + perror("malloc"); + return -1; + } + memset(reloc, 0, sizeof(*reloc));

- list_add_tail(&reloc->list, &sec->reloc_list); + reloc->sec = sec->reloc; + reloc->offset = offset; + reloc->type = type; + reloc->sym = sym; + reloc->addend = addend; + + list_add_tail(&reloc->list, &sec->reloc->reloc_list); elf_hash_add(elf->reloc_hash, &reloc->hash, reloc_hash(reloc));

- sec->changed = true; + sec->reloc->changed = true; + + return 0; +} + +int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, + unsigned long offset, unsigned int type, + struct section *insn_sec, unsigned long insn_off) +{ + struct symbol *sym; + int addend; + + if (insn_sec->sym) { + sym = insn_sec->sym; + addend = insn_off; + + } else { + /* + * The Clang assembler strips section symbols, so we have to + * reference the function symbol instead: + */ + sym = find_symbol_containing(insn_sec, insn_off); + if (!sym) { + /* + * Hack alert. This happens when we need to reference + * the NOP pad insn immediately after the function. + */ + sym = find_symbol_containing(insn_sec, insn_off - 1); + } + + if (!sym) { + WARN("can't find symbol containing %s+0x%lx", insn_sec->name, insn_off); + return -1; + } + + addend = insn_off - sym->offset; + } + + return elf_add_reloc(elf, sec, offset, type, sym, addend); }

static int read_rel_reloc(struct section *sec, int i, struct reloc *reloc, unsigned int *symndx) diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index fc576edacfc4..825ad326201d 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -123,7 +123,13 @@ static inline u32 reloc_hash(struct reloc *reloc) struct elf *elf_open_read(const char *name, int flags); struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr); struct section *elf_create_reloc_section(struct elf *elf, struct section *base, int reltype); -void elf_add_reloc(struct elf *elf, struct reloc *reloc); + +int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset, + unsigned int type, struct symbol *sym, int addend); +int elf_add_reloc_to_insn(struct elf *elf, struct section *sec, + unsigned long offset, unsigned int type, + struct section *insn_sec, unsigned long insn_off); + int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn); @@ -140,8 +146,6 @@ struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, uns struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec, unsigned long offset, unsigned int len); struct symbol *find_func_containing(struct section *sec, unsigned long offset); -void insn_to_reloc_sym_addend(struct section *sec, unsigned long offset, - struct reloc *reloc);

#define for_each_sec(file, sec) \ list_for_each_entry(sec, &file->elf->sections, list) diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 02e02fc49bbd..57de202c51b4 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -81,37 +81,20 @@ static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi) }

static int write_orc_entry(struct elf *elf, struct section *orc_sec, - struct section *ip_rsec, unsigned int idx, + struct section *ip_sec, unsigned int idx, struct section *insn_sec, unsigned long insn_off, struct orc_entry *o) { struct orc_entry *orc; - struct reloc *reloc;

/* populate ORC data */ orc = (struct orc_entry *)orc_sec->data->d_buf + idx; memcpy(orc, o, sizeof(*orc));

/* populate reloc for ip */ - reloc = malloc(sizeof(*reloc)); - if (!reloc) { - perror("malloc"); + if (elf_add_reloc_to_insn(elf, ip_sec, idx * sizeof(int), R_X86_64_PC32, + insn_sec, insn_off)) return -1; - } - memset(reloc, 0, sizeof(*reloc)); - - insn_to_reloc_sym_addend(insn_sec, insn_off, reloc); - if (!reloc->sym) { - WARN("missing symbol for insn at offset 0x%lx", - insn_off); - return -1; - } - - reloc->type = R_X86_64_PC32; - reloc->offset = idx * sizeof(int); - reloc->sec = ip_rsec; - - elf_add_reloc(elf, reloc);

return 0; } @@ -150,7 +133,7 @@ static unsigned long alt_group_len(struct alt_group *alt_group)

int orc_create(struct objtool_file *file) { - struct section *sec, *ip_rsec, *orc_sec; + struct section *sec, *orc_sec; unsigned int nr = 0, idx = 0; struct orc_list_entry *entry; struct list_head orc_list; @@ -239,13 +222,12 @@ int orc_create(struct objtool_file *file) sec = elf_create_section(file->elf, ".orc_unwind_ip", 0, sizeof(int), nr); if (!sec) return -1; - ip_rsec = elf_create_reloc_section(file->elf, sec, SHT_RELA); - if (!ip_rsec) + if (!elf_create_reloc_section(file->elf, sec, SHT_RELA)) return -1;

/* Write ORC entries to sections: */ list_for_each_entry(entry, &orc_list, list) { - if (write_orc_entry(file->elf, orc_sec, ip_rsec, idx++, + if (write_orc_entry(file->elf, orc_sec, sec, idx++, entry->insn_sec, entry->insn_off, &entry->orc)) return -1;

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit da962cd0a2fe2e2c29c75f425fb29fc09b4233cc category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 417a4dc91e559f92404c2544f785b02ce75784c3 upstream.

Create a common helper to append strings to a strtab.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Ingo Molnar mingo@kernel.org Reviewed-by: Miroslav Benes mbenes@suse.cz Link: https://lkml.kernel.org/r/20210326151259.941474004@infradead.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/elf.c | 60 ++++++++++++++++++++++++++++----------------- 1 file changed, 38 insertions(+), 22 deletions(-)

diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index b76d687bc962..07805b13abe0 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -724,13 +724,48 @@ struct elf *elf_open_read(const char *name, int flags) return NULL; }

+static int elf_add_string(struct elf *elf, struct section *strtab, char *str) +{ + Elf_Data *data; + Elf_Scn *s; + int len; + + if (!strtab) + strtab = find_section_by_name(elf, ".strtab"); + if (!strtab) { + WARN("can't find .strtab section"); + return -1; + } + + s = elf_getscn(elf->elf, strtab->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return -1; + } + + data = elf_newdata(s); + if (!data) { + WARN_ELF("elf_newdata"); + return -1; + } + + data->d_buf = str; + data->d_size = strlen(str) + 1; + data->d_align = 1; + + len = strtab->len; + strtab->len += data->d_size; + strtab->changed = true; + + return len; +} + struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr) { struct section *sec, *shstrtab; size_t size = entsize * nr; Elf_Scn *s; - Elf_Data *data;

sec = malloc(sizeof(*sec)); if (!sec) { @@ -787,7 +822,6 @@ struct section *elf_create_section(struct elf *elf, const char *name, sec->sh.sh_addralign = 1; sec->sh.sh_flags = SHF_ALLOC | sh_flags;

- /* Add section name to .shstrtab (or .strtab for Clang) */ shstrtab = find_section_by_name(elf, ".shstrtab"); if (!shstrtab) @@ -796,27 +830,9 @@ struct section *elf_create_section(struct elf *elf, const char *name, WARN("can't find .shstrtab or .strtab section"); return NULL; } - - s = elf_getscn(elf->elf, shstrtab->idx); - if (!s) { - WARN_ELF("elf_getscn"); + sec->sh.sh_name = elf_add_string(elf, shstrtab, sec->name); + if (sec->sh.sh_name == -1) return NULL; - } - - data = elf_newdata(s); - if (!data) { - WARN_ELF("elf_newdata"); - return NULL; - } - - data->d_buf = sec->name; - data->d_size = strlen(name) + 1; - data->d_align = 1; - - sec->sh.sh_name = shstrtab->len; - - shstrtab->len += strlen(name) + 1; - shstrtab->changed = true;

list_add_tail(&sec->list, &elf->sections); elf_hash_add(elf->section_hash, &sec->hash, sec->idx);

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 8a6d73f7db7f8486918d144e457e3b1d2cd22dba category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 2f2f7e47f0525cbaad5dd9675fd9d8aa8da12046 upstream.

Allow objtool to create undefined symbols; this allows creating relocations to symbols not currently in the symbol table.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Ingo Molnar mingo@kernel.org Reviewed-by: Miroslav Benes mbenes@suse.cz Link: https://lkml.kernel.org/r/20210326151300.064743095@infradead.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/elf.c | 60 +++++++++++++++++++++++++++++++++++++++++++++ tools/objtool/elf.h | 1 + 2 files changed, 61 insertions(+)

diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 74f4b3bb7961..fff4c5587e3e 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -766,6 +766,66 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str) return len; }

+struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) +{ + struct section *symtab; + struct symbol *sym; + Elf_Data *data; + Elf_Scn *s; + + sym = malloc(sizeof(*sym)); + if (!sym) { + perror("malloc"); + return NULL; + } + memset(sym, 0, sizeof(*sym)); + + sym->name = strdup(name); + + sym->sym.st_name = elf_add_string(elf, NULL, sym->name); + if (sym->sym.st_name == -1) + return NULL; + + sym->sym.st_info = GELF_ST_INFO(STB_GLOBAL, STT_NOTYPE); + // st_other 0 + // st_shndx 0 + // st_value 0 + // st_size 0 + + symtab = find_section_by_name(elf, ".symtab"); + if (!symtab) { + WARN("can't find .symtab"); + return NULL; + } + + s = elf_getscn(elf->elf, symtab->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return NULL; + } + + data = elf_newdata(s); + if (!data) { + WARN_ELF("elf_newdata"); + return NULL; + } + + data->d_buf = &sym->sym; + data->d_size = sizeof(sym->sym); + data->d_align = 1; + + sym->idx = symtab->len / sizeof(sym->sym); + + symtab->len += data->d_size; + symtab->changed = true; + + sym->sec = find_section_by_index(elf, 0); + + elf_add_symbol(elf, sym); + + return sym; +} + struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr) { diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index 463f329f1c66..45e5ede363b0 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -133,6 +133,7 @@ int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn); int elf_write_reloc(struct elf *elf, struct reloc *reloc); +struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name); int elf_write(struct elf *elf); void elf_close(struct elf *elf);

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit e87c18c4a951bba1d69c7acaf401d613cf9a828c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 7bd2a600f3e9d27286bbf23c83d599e9cc7cf245 upstream.

Track the reloc of instructions in the new instruction->reloc field to avoid having to look them up again later.

( Technically x86 instructions can have two relocations, but not jumps and calls, for which we're using this. )

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Ingo Molnar mingo@kernel.org Reviewed-by: Miroslav Benes mbenes@suse.cz Link: https://lkml.kernel.org/r/20210326151300.195441549@infradead.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/check.c | 28 ++++++++++++++++++++++------ tools/objtool/check.h | 1 + 2 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c index f87a8782c817..6d62ad940fce 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -754,6 +754,25 @@ __weak bool arch_is_retpoline(struct symbol *sym) return false; }

+#define NEGATIVE_RELOC ((void *)-1L) + +static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *insn) +{ + if (insn->reloc == NEGATIVE_RELOC) + return NULL; + + if (!insn->reloc) { + insn->reloc = find_reloc_by_dest_range(file->elf, insn->sec, + insn->offset, insn->len); + if (!insn->reloc) { + insn->reloc = NEGATIVE_RELOC; + return NULL; + } + } + + return insn->reloc; +} + /* * Find the destination instructions for all jumps. */ @@ -768,8 +787,7 @@ static int add_jump_destinations(struct objtool_file *file) if (!is_static_jump(insn)) continue;

- reloc = find_reloc_by_dest_range(file->elf, insn->sec, - insn->offset, insn->len); + reloc = insn_reloc(file, insn); if (!reloc) { dest_sec = insn->sec; dest_off = arch_jump_destination(insn); @@ -901,8 +919,7 @@ static int add_call_destinations(struct objtool_file *file) if (insn->type != INSN_CALL) continue;

- reloc = find_reloc_by_dest_range(file->elf, insn->sec, - insn->offset, insn->len); + reloc = insn_reloc(file, insn); if (!reloc) { dest_off = arch_jump_destination(insn); insn->call_dest = find_call_destination(insn->sec, dest_off); @@ -1085,8 +1102,7 @@ static int handle_group_alt(struct objtool_file *file, * alternatives code can adjust the relative offsets * accordingly. */ - alt_reloc = find_reloc_by_dest_range(file->elf, insn->sec, - insn->offset, insn->len); + alt_reloc = insn_reloc(file, insn); if (alt_reloc && !arch_support_alt_relocation(special_alt, insn, alt_reloc)) {

diff --git a/tools/objtool/check.h b/tools/objtool/check.h index e0ae2fc13e67..ca3259eebac8 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -55,6 +55,7 @@ struct instruction { struct instruction *jump_dest; struct instruction *first_jump_src; struct reloc *jump_table; + struct reloc *reloc; struct list_head alts; struct symbol *func; struct list_head stack_ops;

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 0b2c8bf4983bdefbb69337c7d68cbe7c2d47a61a category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 9bc0bb50727c8ac69fbb33fb937431cf3518ff37 upstream.

When the compiler emits: "CALL __x86_indirect_thunk_\reg" for an indirect call, have objtool rewrite it to:

ALTERNATIVE "call __x86_indirect_thunk_\reg", "call *%reg", ALT_NOT(X86_FEATURE_RETPOLINE)

Additionally, in order to not emit endless identical .altinst_replacement chunks, use a global symbol for them, see __x86_indirect_alt_*.

This also avoids objtool from having to do code generation.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Ingo Molnar mingo@kernel.org Reviewed-by: Miroslav Benes mbenes@suse.cz Link: https://lkml.kernel.org/r/20210326151300.320177914@infradead.org [bwh: Backported to 5.10: include "arch_elf.h" instead of "arch/elf.h"] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/asm-prototypes.h | 12 ++- arch/x86/lib/retpoline.S | 41 ++++++++- tools/objtool/arch/x86/decode.c | 117 ++++++++++++++++++++++++++ 3 files changed, 167 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 0545b07895a5..4cb726c71ed8 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -19,11 +19,19 @@ extern void cmpxchg8b_emu(void);

#ifdef CONFIG_RETPOLINE

-#define DECL_INDIRECT_THUNK(reg) \ +#undef GEN +#define GEN(reg) \ extern asmlinkage void __x86_indirect_thunk_ ## reg (void); +#include <asm/GEN-for-each-reg.h> + +#undef GEN +#define GEN(reg) \ + extern asmlinkage void __x86_indirect_alt_call_ ## reg (void); +#include <asm/GEN-for-each-reg.h>

#undef GEN -#define GEN(reg) DECL_INDIRECT_THUNK(reg) +#define GEN(reg) \ + extern asmlinkage void __x86_indirect_alt_jmp_ ## reg (void); #include <asm/GEN-for-each-reg.h>

#endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index b22075d6e38d..fa30f2326547 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -10,6 +10,8 @@ #include <asm/unwind_hints.h> #include <asm/frame.h>

+ .section .text.__x86.indirect_thunk + .macro RETPOLINE reg ANNOTATE_INTRA_FUNCTION_CALL call .Ldo_rop_@ @@ -25,9 +27,9 @@ .endm

.macro THUNK reg - .section .text.__x86.indirect_thunk

.align 32 + SYM_FUNC_START(__x86_indirect_thunk_\reg)

ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ @@ -38,6 +40,32 @@ SYM_FUNC_END(__x86_indirect_thunk_\reg)

.endm

+/* + * This generates .altinstr_replacement symbols for use by objtool. They, + * however, must not actually live in .altinstr_replacement since that will be + * discarded after init, but module alternatives will also reference these + * symbols. + * + * Their names matches the "__x86_indirect_" prefix to mark them as retpolines. + */ +.macro ALT_THUNK reg + + .align 1 + +SYM_FUNC_START_NOALIGN(__x86_indirect_alt_call_\reg) + ANNOTATE_RETPOLINE_SAFE +1: call *%\reg +2: .skip 5-(2b-1b), 0x90 +SYM_FUNC_END(__x86_indirect_alt_call_\reg) + +SYM_FUNC_START_NOALIGN(__x86_indirect_alt_jmp_\reg) + ANNOTATE_RETPOLINE_SAFE +1: jmp *%\reg +2: .skip 5-(2b-1b), 0x90 +SYM_FUNC_END(__x86_indirect_alt_jmp_\reg) + +.endm + /* * Despite being an assembler file we can't just use .irp here * because __KSYM_DEPS__ only uses the C preprocessor and would @@ -61,3 +89,14 @@ SYM_FUNC_END(__x86_indirect_thunk_\reg) #define GEN(reg) EXPORT_THUNK(reg) #include <asm/GEN-for-each-reg.h>

+#undef GEN +#define GEN(reg) ALT_THUNK reg +#include <asm/GEN-for-each-reg.h> + +#undef GEN +#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_call_ ## reg) +#include <asm/GEN-for-each-reg.h> + +#undef GEN +#define GEN(reg) __EXPORT_THUNK(__x86_indirect_alt_jmp_ ## reg) +#include <asm/GEN-for-each-reg.h> diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index a540c8cda8e1..4154921291d0 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -16,6 +16,7 @@ #include "../../arch.h" #include "../../warn.h" #include <asm/orc_types.h> +#include "arch_elf.h"

static unsigned char op_to_cfi_reg[][2] = { {CFI_AX, CFI_R8}, @@ -585,6 +586,122 @@ const char *arch_nop_insn(int len) return nops[len-1]; }

+/* asm/alternative.h ? */ + +#define ALTINSTR_FLAG_INV (1 << 15) +#define ALT_NOT(feat) ((feat) | ALTINSTR_FLAG_INV) + +struct alt_instr { + s32 instr_offset; /* original instruction */ + s32 repl_offset; /* offset to replacement instruction */ + u16 cpuid; /* cpuid bit set for replacement */ + u8 instrlen; /* length of original instruction */ + u8 replacementlen; /* length of new instruction */ +} __packed; + +static int elf_add_alternative(struct elf *elf, + struct instruction *orig, struct symbol *sym, + int cpuid, u8 orig_len, u8 repl_len) +{ + const int size = sizeof(struct alt_instr); + struct alt_instr *alt; + struct section *sec; + Elf_Scn *s; + + sec = find_section_by_name(elf, ".altinstructions"); + if (!sec) { + sec = elf_create_section(elf, ".altinstructions", + SHF_WRITE, size, 0); + + if (!sec) { + WARN_ELF("elf_create_section"); + return -1; + } + } + + s = elf_getscn(elf->elf, sec->idx); + if (!s) { + WARN_ELF("elf_getscn"); + return -1; + } + + sec->data = elf_newdata(s); + if (!sec->data) { + WARN_ELF("elf_newdata"); + return -1; + } + + sec->data->d_size = size; + sec->data->d_align = 1; + + alt = sec->data->d_buf = malloc(size); + if (!sec->data->d_buf) { + perror("malloc"); + return -1; + } + memset(sec->data->d_buf, 0, size); + + if (elf_add_reloc_to_insn(elf, sec, sec->sh.sh_size, + R_X86_64_PC32, orig->sec, orig->offset)) { + WARN("elf_create_reloc: alt_instr::instr_offset"); + return -1; + } + + if (elf_add_reloc(elf, sec, sec->sh.sh_size + 4, + R_X86_64_PC32, sym, 0)) { + WARN("elf_create_reloc: alt_instr::repl_offset"); + return -1; + } + + alt->cpuid = cpuid; + alt->instrlen = orig_len; + alt->replacementlen = repl_len; + + sec->sh.sh_size += size; + sec->changed = true; + + return 0; +} + +#define X86_FEATURE_RETPOLINE ( 7*32+12) + +int arch_rewrite_retpolines(struct objtool_file *file) +{ + struct instruction *insn; + struct reloc *reloc; + struct symbol *sym; + char name[32] = ""; + + list_for_each_entry(insn, &file->retpoline_call_list, call_node) { + + if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk")) + continue; + + reloc = insn->reloc; + + sprintf(name, "__x86_indirect_alt_%s_%s", + insn->type == INSN_JUMP_DYNAMIC ? "jmp" : "call", + reloc->sym->name + 21); + + sym = find_symbol_by_name(file->elf, name); + if (!sym) { + sym = elf_create_undef_symbol(file->elf, name); + if (!sym) { + WARN("elf_create_undef_symbol"); + return -1; + } + } + + if (elf_add_alternative(file->elf, insn, sym, + ALT_NOT(X86_FEATURE_RETPOLINE), 5, 5)) { + WARN("elf_add_alternative"); + return -1; + } + } + + return 0; +} + int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg) { struct cfi_reg *cfa = &insn->cfi.cfa;

From: Borislav Petkov bp@suse.de

stable inclusion from stable-v5.10.133 commit 76474a9dd34a7a33abc82952b82f7092750f3bdc category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 2b31e8ed96b260ce2c22bd62ecbb9458399e3b62 upstream.

Up until now the assumption was that an alternative patching site would have some instructions at the beginning and trailing single-byte NOPs (0x90) padding. Therefore, the patching machinery would go and optimize those single-byte NOPs into longer ones.

However, this assumption is broken on 32-bit when code like hv_do_hypercall() in hyperv_init() would use the ratpoline speculation killer CALL_NOSPEC. The 32-bit version of that macro would align certain insns to 16 bytes, leading to the compiler issuing a one or more single-byte NOPs, depending on the holes it needs to fill for alignment.

That would lead to the warning in optimize_nops() to fire:

------------[ cut here ]------------ Not a NOP at 0xc27fb598 WARNING: CPU: 0 PID: 0 at arch/x86/kernel/alternative.c:211 optimize_nops.isra.13

due to that function verifying whether all of the following bytes really are single-byte NOPs.

Therefore, carve out the NOP padding into a separate function and call it for each NOP range beginning with a single-byte NOP.

Fixes: 23c1ad538f4f ("x86/alternatives: Optimize optimize_nops()") Reported-by: Richard Narron richard@aaazen.com Signed-off-by: Borislav Petkov bp@suse.de Acked-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=213301 Link: https://lkml.kernel.org/r/20210601212125.17145-1-bp@alien8.de Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/kernel/alternative.c | 64 +++++++++++++++++++++++++---------- 1 file changed, 46 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 959916cf9461..5d43499562e0 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -337,42 +337,70 @@ recompute_jump(struct alt_instr *a, u8 *orig_insn, u8 *repl_insn, u8 *insn_buff) n_dspl, (unsigned long)orig_insn + n_dspl + repl_len); }

+/* + * optimize_nops_range() - Optimize a sequence of single byte NOPs (0x90) + * + * @instr: instruction byte stream + * @instrlen: length of the above + * @off: offset within @instr where the first NOP has been detected + * + * Return: number of NOPs found (and replaced). + */ +static __always_inline int optimize_nops_range(u8 *instr, u8 instrlen, int off) +{ + unsigned long flags; + int i = off, nnops; + + while (i < instrlen) { + if (instr[i] != 0x90) + break; + + i++; + } + + nnops = i - off; + + if (nnops <= 1) + return nnops; + + local_irq_save(flags); + add_nops(instr + off, nnops); + local_irq_restore(flags); + + DUMP_BYTES(instr, instrlen, "%px: [%d:%d) optimized NOPs: ", instr, off, i); + + return nnops; +} + /* * "noinline" to cause control flow change and thus invalidate I$ and * cause refetch after modification. */ static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr) { - unsigned long flags; struct insn insn; - int nop, i = 0; + int i = 0;

/* - * Jump over the non-NOP insns, the remaining bytes must be single-byte - * NOPs, optimize them. + * Jump over the non-NOP insns and optimize single-byte NOPs into bigger + * ones. */ for (;;) { if (insn_decode_kernel(&insn, &instr[i])) return;

+ /* + * See if this and any potentially following NOPs can be + * optimized. + */ if (insn.length == 1 && insn.opcode.bytes[0] == 0x90) - break; - - if ((i += insn.length) >= a->instrlen) - return; - } + i += optimize_nops_range(instr, a->instrlen, i); + else + i += insn.length;

- for (nop = i; i < a->instrlen; i++) { - if (WARN_ONCE(instr[i] != 0x90, "Not a NOP at 0x%px\n", &instr[i])) + if (i >= a->instrlen) return; } - - local_irq_save(flags); - add_nops(instr + nop, i - nop); - local_irq_restore(flags); - - DUMP_BYTES(instr, a->instrlen, "%px: [%d:%d) optimized NOPs: ", - instr, nop, a->instrlen); }

/*

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit e32542e9ed362bf8ea48941d965495e1593b5cef category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 2d49b721dc18c113d5221f4cf5a6104eb66cb7f2 upstream.

It turns out that the compilers generate conditional branches to the retpoline thunks like:

5d5: 0f 85 00 00 00 00 jne 5db <cpuidle_reflect+0x22> 5d7: R_X86_64_PLT32 __x86_indirect_thunk_r11-0x4

while the rewrite can only handle JMP/CALL to the thunks. The result is the alternative wrecking the code. Make sure to skip writing the alternatives for conditional branches.

Fixes: 9bc0bb50727c ("objtool/x86: Rewrite retpoline thunk calls") Reported-by: Lukasz Majczak lma@semihalf.com Reported-by: Nathan Chancellor nathan@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Tested-by: Nathan Chancellor nathan@kernel.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/arch/x86/decode.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 4154921291d0..09035e28f472 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -674,6 +674,10 @@ int arch_rewrite_retpolines(struct objtool_file *file)

list_for_each_entry(insn, &file->retpoline_call_list, call_node) {

+ if (insn->type != INSN_JUMP_DYNAMIC && + insn->type != INSN_CALL_DYNAMIC) + continue; + if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk")) continue;

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 7ea073195745a8db3cd561faba5cd9870a862045 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 24ff652573754fe4c03213ebd26b17e86842feb3 upstream.

Occasionally objtool encounters symbol (as opposed to section) relocations in .altinstructions. Typically they are the alternatives written by elf_add_alternative() as encountered on a noinstr validation run on vmlinux after having already ran objtool on the individual .o files.

Basically this is the counterpart of commit 44f6a7c0755d ("objtool: Fix seg fault with Clang non-section symbols"), because when these new assemblers (binutils now also does this) strip the section symbols, elf_add_reloc_to_insn() is forced to emit symbol based relocations.

As such, teach get_alt_entry() about different relocation types.

Fixes: 9bc0bb50727c ("objtool/x86: Rewrite retpoline thunk calls") Reported-by: Stephen Rothwell sfr@canb.auug.org.au Reported-by: Borislav Petkov bp@alien8.de Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Acked-by: Josh Poimboeuf jpoimboe@redhat.com Tested-by: Nathan Chancellor nathan@kernel.org Link: https://lore.kernel.org/r/YVWUvknIEVNkPvnP@hirez.programming.kicks-ass.net Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/special.c | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/tools/objtool/special.c b/tools/objtool/special.c index 272e29cf8a0c..81d501613389 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -55,6 +55,24 @@ void __weak arch_handle_alternative(unsigned short feature, struct special_alt * { }

+static bool reloc2sec_off(struct reloc *reloc, struct section **sec, unsigned long *off) +{ + switch (reloc->sym->type) { + case STT_FUNC: + *sec = reloc->sym->sec; + *off = reloc->sym->offset + reloc->addend; + return true; + + case STT_SECTION: + *sec = reloc->sym->sec; + *off = reloc->addend; + return true; + + default: + return false; + } +} + static int get_alt_entry(struct elf *elf, struct special_entry *entry, struct section *sec, int idx, struct special_alt *alt) @@ -87,15 +105,12 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); return -1; } - if (orig_reloc->sym->type != STT_SECTION) { - WARN_FUNC("don't know how to handle non-section reloc symbol %s", + if (!reloc2sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off)) { + WARN_FUNC("don't know how to handle reloc symbol type: %s", sec, offset + entry->orig, orig_reloc->sym->name); return -1; }

- alt->orig_sec = orig_reloc->sym->sec; - alt->orig_off = orig_reloc->addend; - if (!entry->group || alt->new_len) { new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); if (!new_reloc) { @@ -112,8 +127,11 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, if (arch_is_retpoline(new_reloc->sym)) return 1;

- alt->new_sec = new_reloc->sym->sec; - alt->new_off = (unsigned int)new_reloc->addend; + if (!reloc2sec_off(new_reloc, &alt->new_sec, &alt->new_off)) { + WARN_FUNC("don't know how to handle reloc symbol type: %s", + sec, offset + entry->new, new_reloc->sym->name); + return -1; + }

/* _ASM_EXTABLE_EX hack */ if (alt->new_off >= 0x7ffffff0)

From: Josh Poimboeuf jpoimboe@redhat.com

stable inclusion from stable-v5.10.133 commit 1afa44480b62ef3928cad4e7dea0fe076ae163c8 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 4d8b35968bbf9e42b6b202eedb510e2c82ad8b38 upstream.

Converting a special section's relocation reference to a symbol is straightforward. No need for objtool to complain that it doesn't know how to handle it. Just handle it.

This fixes the following warning:

arch/x86/kvm/emulate.o: warning: objtool: __ex_table+0x4: don't know how to handle reloc symbol type: kvm_fastop_exception

Fixes: 24ff65257375 ("objtool: Teach get_alt_entry() about more relocation types") Reported-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Link: https://lore.kernel.org/r/feadbc3dfb3440d973580fad8d3db873cbfe1694.163336724... Cc: Peter Zijlstra peterz@infradead.org Cc: x86@kernel.org Cc: Miroslav Benes mbenes@suse.cz Cc: linux-kernel@vger.kernel.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/special.c | 36 +++++++----------------------------- 1 file changed, 7 insertions(+), 29 deletions(-)

diff --git a/tools/objtool/special.c b/tools/objtool/special.c index 5f6205fa19d6..99a3a35772a5 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -55,22 +55,11 @@ void __weak arch_handle_alternative(unsigned short feature, struct special_alt * { }

-static bool reloc2sec_off(struct reloc *reloc, struct section **sec, unsigned long *off) +static void reloc_to_sec_off(struct reloc *reloc, struct section **sec, + unsigned long *off) { - switch (reloc->sym->type) { - case STT_FUNC: - *sec = reloc->sym->sec; - *off = reloc->sym->offset + reloc->addend; - return true; - - case STT_SECTION: - *sec = reloc->sym->sec; - *off = reloc->addend; - return true; - - default: - return false; - } + *sec = reloc->sym->sec; + *off = reloc->sym->offset + reloc->addend; }

static int get_alt_entry(struct elf *elf, struct special_entry *entry, @@ -105,13 +94,8 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, WARN_FUNC("can't find orig reloc", sec, offset + entry->orig); return -1; } - if (!reloc2sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off)) { - WARN_FUNC("don't know how to handle reloc symbol type %d: %s", - sec, offset + entry->orig, - orig_reloc->sym->type, - orig_reloc->sym->name); - return -1; - } + + reloc_to_sec_off(orig_reloc, &alt->orig_sec, &alt->orig_off);

if (!entry->group || alt->new_len) { new_reloc = find_reloc_by_dest(elf, sec, offset + entry->new); @@ -129,13 +113,7 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, if (arch_is_retpoline(new_reloc->sym)) return 1;

- if (!reloc2sec_off(new_reloc, &alt->new_sec, &alt->new_off)) { - WARN_FUNC("don't know how to handle reloc symbol type %d: %s", - sec, offset + entry->new, - new_reloc->sym->type, - new_reloc->sym->name); - return -1; - } + reloc_to_sec_off(new_reloc, &alt->new_sec, &alt->new_off);

/* _ASM_EXTABLE_EX hack */ if (alt->new_off >= 0x7ffffff0)

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 9d7ec2418a3a6669a69d96927bf9ce8f2efea444 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 8b946cc38e063f0f7bb67789478c38f6d7d457c9 upstream.

Andi reported that objtool on vmlinux.o consumes more memory than his system has, leading to horrific performance.

This is in part because we keep a struct instruction for every instruction in the file in-memory. Shrink struct instruction by removing the CFI state (which includes full register state) from it and demand allocating it.

Given most instructions don't actually change CFI state, there's lots of repetition there, so add a hash table to find previous CFI instances.

Reduces memory consumption (and runtime) for processing an x86_64-allyesconfig:

pre: 4:40.84 real, 143.99 user, 44.18 sys, 30624988 mem post: 2:14.61 real, 108.58 user, 25.04 sys, 16396184 mem

Suggested-by: Andi Kleen andi@firstfloor.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lore.kernel.org/r/20210624095147.756759107@infradead.org Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com [bwh: Backported to 5.10: - Don't use bswap_if_needed() since we don't have any of the other fixes for mixed-endian cross-compilation - Since we don't have "objtool: Rewrite hashtable sizing", make cfi_hash_alloc() set the number of bits similarly to elf_hash_bits() - objtool doesn't have any mcount handling - Adjust context] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/arch.h | 2 +- tools/objtool/arch/x86/decode.c | 20 ++--- tools/objtool/cfi.h | 2 + tools/objtool/check.c | 154 ++++++++++++++++++++++++++++---- tools/objtool/check.h | 2 +- tools/objtool/orc_gen.c | 15 +++- 6 files changed, 160 insertions(+), 35 deletions(-)

diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index 8918de4f8189..35e3f94413eb 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -84,7 +84,7 @@ unsigned long arch_dest_reloc_offset(int addend);

const char *arch_nop_insn(int len);

-int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg); +int arch_decode_hint_reg(u8 sp_reg, int *base);

bool arch_is_retpoline(struct symbol *sym);

diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 99b47720dce9..5005a4811157 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -706,34 +706,32 @@ int arch_rewrite_retpolines(struct objtool_file *file) return 0; }

-int arch_decode_hint_reg(struct instruction *insn, u8 sp_reg) +int arch_decode_hint_reg(u8 sp_reg, int *base) { - struct cfi_reg *cfa = &insn->cfi.cfa; - switch (sp_reg) { case ORC_REG_UNDEFINED: - cfa->base = CFI_UNDEFINED; + *base = CFI_UNDEFINED; break; case ORC_REG_SP: - cfa->base = CFI_SP; + *base = CFI_SP; break; case ORC_REG_BP: - cfa->base = CFI_BP; + *base = CFI_BP; break; case ORC_REG_SP_INDIRECT: - cfa->base = CFI_SP_INDIRECT; + *base = CFI_SP_INDIRECT; break; case ORC_REG_R10: - cfa->base = CFI_R10; + *base = CFI_R10; break; case ORC_REG_R13: - cfa->base = CFI_R13; + *base = CFI_R13; break; case ORC_REG_DI: - cfa->base = CFI_DI; + *base = CFI_DI; break; case ORC_REG_DX: - cfa->base = CFI_DX; + *base = CFI_DX; break; default: return -1; diff --git a/tools/objtool/cfi.h b/tools/objtool/cfi.h index c7c59c6a44ee..f579802d7ec2 100644 --- a/tools/objtool/cfi.h +++ b/tools/objtool/cfi.h @@ -7,6 +7,7 @@ #define _OBJTOOL_CFI_H

#include "cfi_regs.h" +#include <linux/list.h>

#define CFI_UNDEFINED -1 #define CFI_CFA -2 @@ -24,6 +25,7 @@ struct cfi_init_state { };

struct cfi_state { + struct hlist_node hash; /* must be first, cficmp() */ struct cfi_reg regs[CFI_NUM_REGS]; struct cfi_reg vals[CFI_NUM_REGS]; struct cfi_reg cfa; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index eb180c78f440..b6c56c7bb837 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -5,6 +5,7 @@

#include <string.h> #include <stdlib.h> +#include <sys/mman.h>

#include "builtin.h" #include "cfi.h" @@ -25,7 +26,11 @@ struct alternative { bool skip_orig; };

-struct cfi_init_state initial_func_cfi; +static unsigned long nr_cfi, nr_cfi_reused, nr_cfi_cache; + +static struct cfi_init_state initial_func_cfi; +static struct cfi_state init_cfi; +static struct cfi_state func_cfi;

struct instruction *find_insn(struct objtool_file *file, struct section *sec, unsigned long offset) @@ -265,6 +270,78 @@ static void init_insn_state(struct insn_state *state, struct section *sec) state->noinstr = sec->noinstr; }

+static struct cfi_state *cfi_alloc(void) +{ + struct cfi_state *cfi = calloc(sizeof(struct cfi_state), 1); + if (!cfi) { + WARN("calloc failed"); + exit(1); + } + nr_cfi++; + return cfi; +} + +static int cfi_bits; +static struct hlist_head *cfi_hash; + +static inline bool cficmp(struct cfi_state *cfi1, struct cfi_state *cfi2) +{ + return memcmp((void *)cfi1 + sizeof(cfi1->hash), + (void *)cfi2 + sizeof(cfi2->hash), + sizeof(struct cfi_state) - sizeof(struct hlist_node)); +} + +static inline u32 cfi_key(struct cfi_state *cfi) +{ + return jhash((void *)cfi + sizeof(cfi->hash), + sizeof(*cfi) - sizeof(cfi->hash), 0); +} + +static struct cfi_state *cfi_hash_find_or_add(struct cfi_state *cfi) +{ + struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)]; + struct cfi_state *obj; + + hlist_for_each_entry(obj, head, hash) { + if (!cficmp(cfi, obj)) { + nr_cfi_cache++; + return obj; + } + } + + obj = cfi_alloc(); + *obj = *cfi; + hlist_add_head(&obj->hash, head); + + return obj; +} + +static void cfi_hash_add(struct cfi_state *cfi) +{ + struct hlist_head *head = &cfi_hash[hash_min(cfi_key(cfi), cfi_bits)]; + + hlist_add_head(&cfi->hash, head); +} + +static void *cfi_hash_alloc(void) +{ + cfi_bits = vmlinux ? ELF_HASH_BITS - 3 : 13; + cfi_hash = mmap(NULL, sizeof(struct hlist_head) << cfi_bits, + PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANON, -1, 0); + if (cfi_hash == (void *)-1L) { + WARN("mmap fail cfi_hash"); + cfi_hash = NULL; + } else if (stats) { + printf("cfi_bits: %d\n", cfi_bits); + } + + return cfi_hash; +} + +static unsigned long nr_insns; +static unsigned long nr_insns_visited; + /* * Call the arch-specific instruction decoder for all the instructions and add * them to the global instruction list. @@ -275,7 +352,6 @@ static int decode_instructions(struct objtool_file *file) struct symbol *func; unsigned long offset; struct instruction *insn; - unsigned long nr_insns = 0; int ret;

for_each_sec(file, sec) { @@ -301,7 +377,6 @@ static int decode_instructions(struct objtool_file *file) memset(insn, 0, sizeof(*insn)); INIT_LIST_HEAD(&insn->alts); INIT_LIST_HEAD(&insn->stack_ops); - init_cfi_state(&insn->cfi);

insn->sec = sec; insn->offset = offset; @@ -1077,7 +1152,6 @@ static int handle_group_alt(struct objtool_file *file, memset(nop, 0, sizeof(*nop)); INIT_LIST_HEAD(&nop->alts); INIT_LIST_HEAD(&nop->stack_ops); - init_cfi_state(&nop->cfi);

nop->sec = special_alt->new_sec; nop->offset = special_alt->new_off + special_alt->new_len; @@ -1454,10 +1528,11 @@ static void set_func_state(struct cfi_state *state)

static int read_unwind_hints(struct objtool_file *file) { + struct cfi_state cfi = init_cfi; struct section *sec, *relocsec; - struct reloc *reloc; struct unwind_hint *hint; struct instruction *insn; + struct reloc *reloc; int i;

sec = find_section_by_name(file->elf, ".discard.unwind_hints"); @@ -1495,19 +1570,24 @@ static int read_unwind_hints(struct objtool_file *file) insn->hint = true;

if (hint->type == UNWIND_HINT_TYPE_FUNC) { - set_func_state(&insn->cfi); + insn->cfi = &func_cfi; continue; }

- if (arch_decode_hint_reg(insn, hint->sp_reg)) { + if (insn->cfi) + cfi = *(insn->cfi); + + if (arch_decode_hint_reg(hint->sp_reg, &cfi.cfa.base)) { WARN_FUNC("unsupported unwind_hint sp base reg %d", insn->sec, insn->offset, hint->sp_reg); return -1; }

- insn->cfi.cfa.offset = hint->sp_offset; - insn->cfi.type = hint->type; - insn->cfi.end = hint->end; + cfi.cfa.offset = hint->sp_offset; + cfi.type = hint->type; + cfi.end = hint->end; + + insn->cfi = cfi_hash_find_or_add(&cfi); }

return 0; @@ -2283,13 +2363,18 @@ static int propagate_alt_cfi(struct objtool_file *file, struct instruction *insn if (!insn->alt_group) return 0;

+ if (!insn->cfi) { + WARN("CFI missing"); + return -1; + } + alt_cfi = insn->alt_group->cfi; group_off = insn->offset - insn->alt_group->first_insn->offset;

if (!alt_cfi[group_off]) { - alt_cfi[group_off] = &insn->cfi; + alt_cfi[group_off] = insn->cfi; } else { - if (memcmp(alt_cfi[group_off], &insn->cfi, sizeof(struct cfi_state))) { + if (cficmp(alt_cfi[group_off], insn->cfi)) { WARN_FUNC("stack layout conflict in alternatives", insn->sec, insn->offset); return -1; @@ -2335,9 +2420,14 @@ static int handle_insn_ops(struct instruction *insn, struct insn_state *state)

static bool insn_cfi_match(struct instruction *insn, struct cfi_state *cfi2) { - struct cfi_state *cfi1 = &insn->cfi; + struct cfi_state *cfi1 = insn->cfi; int i;

+ if (!cfi1) { + WARN("CFI missing"); + return false; + } + if (memcmp(&cfi1->cfa, &cfi2->cfa, sizeof(cfi1->cfa))) {

WARN_FUNC("stack state mismatch: cfa1=%d%+d cfa2=%d%+d", @@ -2522,7 +2612,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, struct instruction *insn, struct insn_state state) { struct alternative *alt; - struct instruction *next_insn; + struct instruction *next_insn, *prev_insn = NULL; struct section *sec; u8 visited; int ret; @@ -2551,15 +2641,25 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,

if (insn->visited & visited) return 0; + } else { + nr_insns_visited++; }

if (state.noinstr) state.instr += insn->instr;

- if (insn->hint) - state.cfi = insn->cfi; - else - insn->cfi = state.cfi; + if (insn->hint) { + state.cfi = *insn->cfi; + } else { + /* XXX track if we actually changed state.cfi */ + + if (prev_insn && !cficmp(prev_insn->cfi, &state.cfi)) { + insn->cfi = prev_insn->cfi; + nr_cfi_reused++; + } else { + insn->cfi = cfi_hash_find_or_add(&state.cfi); + } + }

insn->visited |= visited;

@@ -2709,6 +2809,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 1; }

+ prev_insn = insn; insn = next_insn; }

@@ -2964,10 +3065,20 @@ int check(struct objtool_file *file) int ret, warnings = 0;

arch_initial_func_cfi_state(&initial_func_cfi); + init_cfi_state(&init_cfi); + init_cfi_state(&func_cfi); + set_func_state(&func_cfi); + + if (!cfi_hash_alloc()) + goto out; + + cfi_hash_add(&init_cfi); + cfi_hash_add(&func_cfi);

ret = decode_sections(file); if (ret < 0) goto out; + warnings += ret;

if (list_empty(&file->insn_list)) @@ -3011,6 +3122,13 @@ int check(struct objtool_file *file) goto out; warnings += ret;

+ if (stats) { + printf("nr_insns_visited: %ld\n", nr_insns_visited); + printf("nr_cfi: %ld\n", nr_cfi); + printf("nr_cfi_reused: %ld\n", nr_cfi_reused); + printf("nr_cfi_cache: %ld\n", nr_cfi_cache); + } + out: /* * For now, don't fail the kernel build on fatal warnings. These diff --git a/tools/objtool/check.h b/tools/objtool/check.h index ca3259eebac8..508f712deba1 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -59,7 +59,7 @@ struct instruction { struct list_head alts; struct symbol *func; struct list_head stack_ops; - struct cfi_state cfi; + struct cfi_state *cfi; };

static inline bool is_static_jump(struct instruction *insn) diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index 671f3b296c1a..812b33ed9f65 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -12,13 +12,19 @@ #include "check.h" #include "warn.h"

-static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi) +static int init_orc_entry(struct orc_entry *orc, struct cfi_state *cfi, + struct instruction *insn) { - struct instruction *insn = container_of(cfi, struct instruction, cfi); struct cfi_reg *bp = &cfi->regs[CFI_BP];

memset(orc, 0, sizeof(*orc));

+ if (!cfi) { + orc->end = 0; + orc->sp_reg = ORC_REG_UNDEFINED; + return 0; + } + orc->end = cfi->end;

if (cfi->cfa.base == CFI_UNDEFINED) { @@ -159,7 +165,7 @@ int orc_create(struct objtool_file *file) int i;

if (!alt_group) { - if (init_orc_entry(&orc, &insn->cfi)) + if (init_orc_entry(&orc, insn->cfi, insn)) return -1; if (!memcmp(&prev_orc, &orc, sizeof(orc))) continue; @@ -183,7 +189,8 @@ int orc_create(struct objtool_file *file) struct cfi_state *cfi = alt_group->cfi[i]; if (!cfi) continue; - if (init_orc_entry(&orc, cfi)) + /* errors are reported on the original insn */ + if (init_orc_entry(&orc, cfi, insn)) return -1; if (!memcmp(&prev_orc, &orc, sizeof(orc))) continue;

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 6e4676f438f8a454d85c12ffa2abf613f9a8f75c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 1739c66eb7bd5f27f1b69a5a26e10e8327d1e136 upstream.

In order to avoid calling str*cmp() on symbol names, over and over, do them all once upfront and store the result.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Borislav Petkov bp@suse.de Acked-by: Josh Poimboeuf jpoimboe@redhat.com Tested-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/r/20211026120309.658539311@infradead.org [cascardo: no pv_target on struct symbol, because of missing db2b0c5d7b6f19b3c2cab08c531b65342eb5252b] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com [bwh: Backported to 5.10: objtool doesn't have any mcount handling] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/check.c | 32 +++++++++++++++++++++----------- tools/objtool/elf.h | 7 +++++-- 2 files changed, 26 insertions(+), 13 deletions(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c index b397868aa6f2..01b064b6182d 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -889,8 +889,7 @@ static void add_call_dest(struct objtool_file *file, struct instruction *insn, * so they need a little help, NOP out any KCOV calls from noinstr * text. */ - if (insn->sec->noinstr && - !strncmp(insn->call_dest->name, "__sanitizer_cov_", 16)) { + if (insn->sec->noinstr && insn->call_dest->kcov) { if (reloc) { reloc->type = R_NONE; elf_write_reloc(file->elf, reloc); @@ -935,7 +934,7 @@ static int add_jump_destinations(struct objtool_file *file) } else if (reloc->sym->type == STT_SECTION) { dest_sec = reloc->sym->sec; dest_off = arch_dest_reloc_offset(reloc->addend); - } else if (arch_is_retpoline(reloc->sym)) { + } else if (reloc->sym->retpoline_thunk) { /* * Retpoline jumps are really dynamic jumps in * disguise, so convert them accordingly. @@ -1076,7 +1075,7 @@ static int add_call_destinations(struct objtool_file *file)

add_call_dest(file, insn, dest, false);

- } else if (arch_is_retpoline(reloc->sym)) { + } else if (reloc->sym->retpoline_thunk) { /* * Retpoline calls are really dynamic calls in * disguise, so convert them accordingly. @@ -1733,17 +1732,28 @@ static int read_intra_function_calls(struct objtool_file *file) return 0; }

-static int read_static_call_tramps(struct objtool_file *file) +static int classify_symbols(struct objtool_file *file) { struct section *sec; struct symbol *func;

for_each_sec(file, sec) { list_for_each_entry(func, &sec->symbol_list, list) { - if (func->bind == STB_GLOBAL && - !strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR, + if (func->bind != STB_GLOBAL) + continue; + + if (!strncmp(func->name, STATIC_CALL_TRAMP_PREFIX_STR, strlen(STATIC_CALL_TRAMP_PREFIX_STR))) func->static_call_tramp = true; + + if (arch_is_retpoline(func)) + func->retpoline_thunk = true; + + if (!strcmp(func->name, "__fentry__")) + func->fentry = true; + + if (!strncmp(func->name, "__sanitizer_cov_", 16)) + func->kcov = true; } }

@@ -1805,7 +1815,7 @@ static int decode_sections(struct objtool_file *file) /* * Must be before add_{jump_call}_destination. */ - ret = read_static_call_tramps(file); + ret = classify_symbols(file); if (ret) return ret;

@@ -1863,9 +1873,9 @@ static int decode_sections(struct objtool_file *file)

static bool is_fentry_call(struct instruction *insn) { - if (insn->type == INSN_CALL && insn->call_dest && - insn->call_dest->type == STT_NOTYPE && - !strcmp(insn->call_dest->name, "__fentry__")) + if (insn->type == INSN_CALL && + insn->call_dest && + insn->call_dest->fentry) return true;

return false; diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index 45e5ede363b0..b51e35825dad 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -55,8 +55,11 @@ struct symbol { unsigned long offset; unsigned int len; struct symbol *pfunc, *cfunc, *alias; - bool uaccess_safe; - bool static_call_tramp; + u8 uaccess_safe : 1; + u8 static_call_tramp : 1; + u8 retpoline_thunk : 1; + u8 fentry : 1; + u8 kcov : 1; };

struct reloc {

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 908bd980a80ea23ff834c3fff828c3d37ada6cc2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 134ab5bd1883312d7a4b3033b05c6b5a1bb8889b upstream.

Instead of writing complete alternatives, simply provide a list of all the retpoline thunk calls. Then the kernel is free to do with them as it pleases. Simpler code all-round.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Borislav Petkov bp@suse.de Acked-by: Josh Poimboeuf jpoimboe@redhat.com Tested-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/r/20211026120309.850007165@infradead.org [cascardo: fixed conflict because of missing 8b946cc38e063f0f7bb67789478c38f6d7d457c9] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com [bwh: Backported to 5.10: deleted functions had slightly different code] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/kernel/vmlinux.lds.S | 14 ++++ tools/objtool/arch/x86/decode.c | 120 ----------------------------- tools/objtool/check.c | 132 ++++++++++++++++++++++---------- tools/objtool/elf.c | 83 -------------------- tools/objtool/elf.h | 1 - tools/objtool/special.c | 8 -- 6 files changed, 107 insertions(+), 251 deletions(-)

diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index bf9e0adb5b7e..d7085a94cfed 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -272,6 +272,20 @@ SECTIONS __parainstructions_end = .; }

+#ifdef CONFIG_RETPOLINE + /* + * List of instructions that call/jmp/jcc to retpoline thunks + * __x86_indirect_thunk_*(). These instructions can be patched along + * with alternatives, after which the section can be freed. + */ + . = ALIGN(8); + .retpoline_sites : AT(ADDR(.retpoline_sites) - LOAD_OFFSET) { + __retpoline_sites = .; + *(.retpoline_sites) + __retpoline_sites_end = .; + } +#endif + /* * struct alt_inst entries. From the header (alternative.h): * "Alternative instructions for different CPU types or capabilities" diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 4fb50239b82a..32a810429306 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -606,126 +606,6 @@ const char *arch_ret_insn(int len) return ret[len-1]; }

-/* asm/alternative.h ? */ - -#define ALTINSTR_FLAG_INV (1 << 15) -#define ALT_NOT(feat) ((feat) | ALTINSTR_FLAG_INV) - -struct alt_instr { - s32 instr_offset; /* original instruction */ - s32 repl_offset; /* offset to replacement instruction */ - u16 cpuid; /* cpuid bit set for replacement */ - u8 instrlen; /* length of original instruction */ - u8 replacementlen; /* length of new instruction */ -} __packed; - -static int elf_add_alternative(struct elf *elf, - struct instruction *orig, struct symbol *sym, - int cpuid, u8 orig_len, u8 repl_len) -{ - const int size = sizeof(struct alt_instr); - struct alt_instr *alt; - struct section *sec; - Elf_Scn *s; - - sec = find_section_by_name(elf, ".altinstructions"); - if (!sec) { - sec = elf_create_section(elf, ".altinstructions", - SHF_ALLOC, 0, 0); - - if (!sec) { - WARN_ELF("elf_create_section"); - return -1; - } - } - - s = elf_getscn(elf->elf, sec->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return -1; - } - - sec->data = elf_newdata(s); - if (!sec->data) { - WARN_ELF("elf_newdata"); - return -1; - } - - sec->data->d_size = size; - sec->data->d_align = 1; - - alt = sec->data->d_buf = malloc(size); - if (!sec->data->d_buf) { - perror("malloc"); - return -1; - } - memset(sec->data->d_buf, 0, size); - - if (elf_add_reloc_to_insn(elf, sec, sec->sh.sh_size, - R_X86_64_PC32, orig->sec, orig->offset)) { - WARN("elf_create_reloc: alt_instr::instr_offset"); - return -1; - } - - if (elf_add_reloc(elf, sec, sec->sh.sh_size + 4, - R_X86_64_PC32, sym, 0)) { - WARN("elf_create_reloc: alt_instr::repl_offset"); - return -1; - } - - alt->cpuid = cpuid; - alt->instrlen = orig_len; - alt->replacementlen = repl_len; - - sec->sh.sh_size += size; - sec->changed = true; - - return 0; -} - -#define X86_FEATURE_RETPOLINE ( 7*32+12) - -int arch_rewrite_retpolines(struct objtool_file *file) -{ - struct instruction *insn; - struct reloc *reloc; - struct symbol *sym; - char name[32] = ""; - - list_for_each_entry(insn, &file->retpoline_call_list, call_node) { - - if (insn->type != INSN_JUMP_DYNAMIC && - insn->type != INSN_CALL_DYNAMIC) - continue; - - if (!strcmp(insn->sec->name, ".text.__x86.indirect_thunk")) - continue; - - reloc = insn->reloc; - - sprintf(name, "__x86_indirect_alt_%s_%s", - insn->type == INSN_JUMP_DYNAMIC ? "jmp" : "call", - reloc->sym->name + 21); - - sym = find_symbol_by_name(file->elf, name); - if (!sym) { - sym = elf_create_undef_symbol(file->elf, name); - if (!sym) { - WARN("elf_create_undef_symbol"); - return -1; - } - } - - if (elf_add_alternative(file->elf, insn, sym, - ALT_NOT(X86_FEATURE_RETPOLINE), 5, 5)) { - WARN("elf_add_alternative"); - return -1; - } - } - - return 0; -} - int arch_decode_hint_reg(u8 sp_reg, int *base) { switch (sp_reg) { diff --git a/tools/objtool/check.c b/tools/objtool/check.c index a70f3811918b..09e7807f83ee 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -606,6 +606,52 @@ static int create_static_call_sections(struct objtool_file *file) return 0; }

+static int create_retpoline_sites_sections(struct objtool_file *file) +{ + struct instruction *insn; + struct section *sec; + int idx; + + sec = find_section_by_name(file->elf, ".retpoline_sites"); + if (sec) { + WARN("file already has .retpoline_sites, skipping"); + return 0; + } + + idx = 0; + list_for_each_entry(insn, &file->retpoline_call_list, call_node) + idx++; + + if (!idx) + return 0; + + sec = elf_create_section(file->elf, ".retpoline_sites", 0, + sizeof(int), idx); + if (!sec) { + WARN("elf_create_section: .retpoline_sites"); + return -1; + } + + idx = 0; + list_for_each_entry(insn, &file->retpoline_call_list, call_node) { + + int *site = (int *)sec->data->d_buf + idx; + *site = 0; + + if (elf_add_reloc_to_insn(file->elf, sec, + idx * sizeof(int), + R_X86_64_PC32, + insn->sec, insn->offset)) { + WARN("elf_add_reloc_to_insn: .retpoline_sites"); + return -1; + } + + idx++; + } + + return 0; +} + /* * Warnings shouldn't be reported for ignored functions. */ @@ -893,6 +939,11 @@ static void annotate_call_site(struct objtool_file *file, return; }

+ if (sym->retpoline_thunk) { + list_add_tail(&insn->call_node, &file->retpoline_call_list); + return; + } + /* * Many compilers cannot disable KCOV with a function attribute * so they need a little help, NOP out any KCOV calls from noinstr @@ -933,6 +984,39 @@ static void add_call_dest(struct objtool_file *file, struct instruction *insn, annotate_call_site(file, insn, sibling); }

+static void add_retpoline_call(struct objtool_file *file, struct instruction *insn) +{ + /* + * Retpoline calls/jumps are really dynamic calls/jumps in disguise, + * so convert them accordingly. + */ + switch (insn->type) { + case INSN_CALL: + insn->type = INSN_CALL_DYNAMIC; + break; + case INSN_JUMP_UNCONDITIONAL: + insn->type = INSN_JUMP_DYNAMIC; + break; + case INSN_JUMP_CONDITIONAL: + insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL; + break; + default: + return; + } + + insn->retpoline_safe = true; + + /* + * Whatever stack impact regular CALLs have, should be undone + * by the RETURN of the called function. + * + * Annotated intra-function calls retain the stack_ops but + * are converted to JUMP, see read_intra_function_calls(). + */ + remove_insn_ops(insn); + + annotate_call_site(file, insn, false); +} /* * Find the destination instructions for all jumps. */ @@ -955,19 +1039,7 @@ static int add_jump_destinations(struct objtool_file *file) dest_sec = reloc->sym->sec; dest_off = arch_dest_reloc_offset(reloc->addend); } else if (reloc->sym->retpoline_thunk) { - /* - * Retpoline jumps are really dynamic jumps in - * disguise, so convert them accordingly. - */ - if (insn->type == INSN_JUMP_UNCONDITIONAL) - insn->type = INSN_JUMP_DYNAMIC; - else - insn->type = INSN_JUMP_DYNAMIC_CONDITIONAL; - - list_add_tail(&insn->call_node, - &file->retpoline_call_list); - - insn->retpoline_safe = true; + add_retpoline_call(file, insn); continue; } else if (insn->func) { /* internal or external sibling call (with reloc) */ @@ -1096,18 +1168,7 @@ static int add_call_destinations(struct objtool_file *file) add_call_dest(file, insn, dest, false);

} else if (reloc->sym->retpoline_thunk) { - /* - * Retpoline calls are really dynamic calls in - * disguise, so convert them accordingly. - */ - insn->type = INSN_CALL_DYNAMIC; - insn->retpoline_safe = true; - - list_add_tail(&insn->call_node, - &file->retpoline_call_list); - - remove_insn_ops(insn); - continue; + add_retpoline_call(file, insn);

} else add_call_dest(file, insn, reloc->sym, false); @@ -1806,11 +1867,6 @@ static void mark_rodata(struct objtool_file *file) file->rodata = found; }

-__weak int arch_rewrite_retpolines(struct objtool_file *file) -{ - return 0; -} - static int decode_sections(struct objtool_file *file) { int ret; @@ -1879,15 +1935,6 @@ static int decode_sections(struct objtool_file *file) if (ret) return ret;

- /* - * Must be after add_special_section_alts(), since this will emit - * alternatives. Must be after add_{jump,call}_destination(), since - * those create the call insn lists. - */ - ret = arch_rewrite_retpolines(file); - if (ret) - return ret; - return 0; }

@@ -3159,6 +3206,13 @@ int check(struct objtool_file *file) goto out; warnings += ret;

+ if (retpoline) { + ret = create_retpoline_sites_sections(file); + if (ret < 0) + goto out; + warnings += ret; + } + if (stats) { printf("nr_insns_visited: %ld\n", nr_insns_visited); printf("nr_cfi: %ld\n", nr_cfi); diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 9c7d395f0db1..74f4b3bb7961 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -766,89 +766,6 @@ static int elf_add_string(struct elf *elf, struct section *strtab, char *str) return len; }

-struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name) -{ - struct section *symtab, *symtab_shndx; - struct symbol *sym; - Elf_Data *data; - Elf_Scn *s; - - sym = malloc(sizeof(*sym)); - if (!sym) { - perror("malloc"); - return NULL; - } - memset(sym, 0, sizeof(*sym)); - - sym->name = strdup(name); - - sym->sym.st_name = elf_add_string(elf, NULL, sym->name); - if (sym->sym.st_name == -1) - return NULL; - - sym->sym.st_info = GELF_ST_INFO(STB_GLOBAL, STT_NOTYPE); - // st_other 0 - // st_shndx 0 - // st_value 0 - // st_size 0 - - symtab = find_section_by_name(elf, ".symtab"); - if (!symtab) { - WARN("can't find .symtab"); - return NULL; - } - - s = elf_getscn(elf->elf, symtab->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return NULL; - } - - data = elf_newdata(s); - if (!data) { - WARN_ELF("elf_newdata"); - return NULL; - } - - data->d_buf = &sym->sym; - data->d_size = sizeof(sym->sym); - data->d_align = 1; - - sym->idx = symtab->len / sizeof(sym->sym); - - symtab->len += data->d_size; - symtab->changed = true; - - symtab_shndx = find_section_by_name(elf, ".symtab_shndx"); - if (symtab_shndx) { - s = elf_getscn(elf->elf, symtab_shndx->idx); - if (!s) { - WARN_ELF("elf_getscn"); - return NULL; - } - - data = elf_newdata(s); - if (!data) { - WARN_ELF("elf_newdata"); - return NULL; - } - - data->d_buf = &sym->sym.st_size; /* conveniently 0 */ - data->d_size = sizeof(Elf32_Word); - data->d_align = 4; - data->d_type = ELF_T_WORD; - - symtab_shndx->len += 4; - symtab_shndx->changed = true; - } - - sym->sec = find_section_by_index(elf, 0); - - elf_add_symbol(elf, sym); - - return sym; -} - struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr) { diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index b51e35825dad..de00cac9aede 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -136,7 +136,6 @@ int elf_write_insn(struct elf *elf, struct section *sec, unsigned long offset, unsigned int len, const char *insn); int elf_write_reloc(struct elf *elf, struct reloc *reloc); -struct symbol *elf_create_undef_symbol(struct elf *elf, const char *name); int elf_write(struct elf *elf); void elf_close(struct elf *elf);

diff --git a/tools/objtool/special.c b/tools/objtool/special.c index 99a3a35772a5..aff0cee7bac1 100644 --- a/tools/objtool/special.c +++ b/tools/objtool/special.c @@ -105,14 +105,6 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry, return -1; }

- /* - * Skip retpoline .altinstr_replacement... we already rewrite the - * instructions for retpolines anyway, see arch_is_retpoline() - * usage in add_{call,jump}_destinations(). - */ - if (arch_is_retpoline(new_reloc->sym)) - return 1; - reloc_to_sec_off(new_reloc, &alt->new_sec, &alt->new_off);

/* _ASM_EXTABLE_EX hack */

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 8ef808b3f406ed920adea8ffc949f63c059bf3a7 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit a92ede2d584a2e070def59c7e47e6b6f6341c55c upstream.

Ensure the register order is correct; this allows for easy translation between register number and trampoline and vice-versa.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Borislav Petkov bp@suse.de Acked-by: Josh Poimboeuf jpoimboe@redhat.com Tested-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/r/20211026120309.978573921@infradead.org Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/GEN-for-each-reg.h | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/GEN-for-each-reg.h b/arch/x86/include/asm/GEN-for-each-reg.h index 1b07fb102c4e..07949102a08d 100644 --- a/arch/x86/include/asm/GEN-for-each-reg.h +++ b/arch/x86/include/asm/GEN-for-each-reg.h @@ -1,11 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * These are in machine order; things rely on that. + */ #ifdef CONFIG_64BIT GEN(rax) -GEN(rbx) GEN(rcx) GEN(rdx) +GEN(rbx) +GEN(rsp) +GEN(rbp) GEN(rsi) GEN(rdi) -GEN(rbp) GEN(r8) GEN(r9) GEN(r10) @@ -16,10 +21,11 @@ GEN(r14) GEN(r15) #else GEN(eax) -GEN(ebx) GEN(ecx) GEN(edx) +GEN(ebx) +GEN(esp) +GEN(ebp) GEN(esi) GEN(edi) -GEN(ebp) #endif

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 0de47ad5b9d57e52b81c3ce0faa91c8b7749affe category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 6fda8a38865607db739be3e567a2387376222dbd upstream.

Because it makes no sense to split the retpoline gunk over multiple headers.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Borislav Petkov bp@suse.de Acked-by: Josh Poimboeuf jpoimboe@redhat.com Tested-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/r/20211026120310.106290934@infradead.org Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/asm-prototypes.h | 8 -------- arch/x86/include/asm/nospec-branch.h | 7 +++++++ arch/x86/net/bpf_jit_comp.c | 1 - 3 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index a2bed09d3c11..8f80de627c60 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -17,11 +17,3 @@ extern void cmpxchg8b_emu(void); #endif

-#ifdef CONFIG_RETPOLINE - -#define GEN(reg) \ - extern asmlinkage void __x86_indirect_thunk_ ## reg (void); -#include <asm/GEN-for-each-reg.h> -#undef GEN - -#endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 838c15e1b775..08ea9888fb5b 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -5,6 +5,7 @@

#include <linux/static_key.h> #include <linux/objtool.h> +#include <linux/linkage.h>

#include <asm/alternative.h> #include <asm/cpufeatures.h> @@ -118,6 +119,12 @@ ".popsection\n\t"

#ifdef CONFIG_RETPOLINE + +#define GEN(reg) \ + extern asmlinkage void __x86_indirect_thunk_ ## reg (void); +#include <asm/GEN-for-each-reg.h> +#undef GEN + #ifdef CONFIG_X86_64

/* diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index a0a7ead52698..a3e453d20f00 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -15,7 +15,6 @@ #include <asm/set_memory.h> #include <asm/nospec-branch.h> #include <asm/text-patching.h> -#include <asm/asm-prototypes.h>

static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) {

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 381fd04c97b469106d83a48343512c5312347155 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 7508500900814d14e2e085cdc4e28142721abbdf upstream.

Rewrite retpoline thunk call sites to be indirect calls for spectre_v2=off. This ensures spectre_v2=off is as near to a RETPOLINE=n build as possible.

This is the replacement for objtool writing alternative entries to ensure the same and achieves feature-parity with the previous approach.

One noteworthy feature is that it relies on the thunks to be in machine order to compute the register index.

Specifically, this does not yet address the Jcc __x86_indirect_thunk_* calls generated by clang, a future patch will add this.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Borislav Petkov bp@suse.de Acked-by: Josh Poimboeuf jpoimboe@redhat.com Tested-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/r/20211026120310.232495794@infradead.org [cascardo: small conflict fixup at arch/x86/kernel/module.c] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com [bwh: Backported to 5.10: - Use hex literal instead of BYTES_NOP1 - Adjust context] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/um/kernel/um_arch.c | 4 + arch/x86/include/asm/alternative.h | 1 + arch/x86/kernel/alternative.c | 141 ++++++++++++++++++++++++++++- arch/x86/kernel/module.c | 9 +- 4 files changed, 150 insertions(+), 5 deletions(-)

diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 76b37297b7d4..2676ac322146 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -358,6 +358,10 @@ void __init check_bugs(void) os_check_bugs(); }

+void apply_retpolines(s32 *start, s32 *end) +{ +} + void apply_alternatives(struct alt_instr *start, struct alt_instr *end) { } diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 9965638d184f..3ac7460933af 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -75,6 +75,7 @@ extern int alternatives_patched;

extern void alternative_instructions(void); extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); +extern void apply_retpolines(s32 *start, s32 *end);

struct module;

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 5d43499562e0..fe466b8abf44 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -28,6 +28,7 @@ #include <asm/insn.h> #include <asm/io.h> #include <asm/fixmap.h> +#include <asm/asm-prototypes.h>

int __read_mostly alternatives_patched;

@@ -268,6 +269,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len) } }

+extern s32 __retpoline_sites[], __retpoline_sites_end[]; extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; void text_poke_early(void *addr, const void *opcode, size_t len); @@ -376,7 +378,7 @@ static __always_inline int optimize_nops_range(u8 *instr, u8 instrlen, int off) * "noinline" to cause control flow change and thus invalidate I$ and * cause refetch after modification. */ -static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr) +static void __init_or_module noinline optimize_nops(u8 *instr, size_t len) { struct insn insn; int i = 0; @@ -394,11 +396,11 @@ static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *ins * optimized. */ if (insn.length == 1 && insn.opcode.bytes[0] == 0x90) - i += optimize_nops_range(instr, a->instrlen, i); + i += optimize_nops_range(instr, len, i); else i += insn.length;

- if (i >= a->instrlen) + if (i >= len) return; } } @@ -486,10 +488,135 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, text_poke_early(instr, insn_buff, insn_buff_sz);

next: - optimize_nops(a, instr); + optimize_nops(instr, a->instrlen); } }

+#if defined(CONFIG_RETPOLINE) && defined(CONFIG_STACK_VALIDATION) + +/* + * CALL/JMP *%\reg + */ +static int emit_indirect(int op, int reg, u8 *bytes) +{ + int i = 0; + u8 modrm; + + switch (op) { + case CALL_INSN_OPCODE: + modrm = 0x10; /* Reg = 2; CALL r/m */ + break; + + case JMP32_INSN_OPCODE: + modrm = 0x20; /* Reg = 4; JMP r/m */ + break; + + default: + WARN_ON_ONCE(1); + return -1; + } + + if (reg >= 8) { + bytes[i++] = 0x41; /* REX.B prefix */ + reg -= 8; + } + + modrm |= 0xc0; /* Mod = 3 */ + modrm += reg; + + bytes[i++] = 0xff; /* opcode */ + bytes[i++] = modrm; + + return i; +} + +/* + * Rewrite the compiler generated retpoline thunk calls. + * + * For spectre_v2=off (!X86_FEATURE_RETPOLINE), rewrite them into immediate + * indirect instructions, avoiding the extra indirection. + * + * For example, convert: + * + * CALL __x86_indirect_thunk_\reg + * + * into: + * + * CALL *%\reg + * + */ +static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) +{ + retpoline_thunk_t *target; + int reg, i = 0; + + target = addr + insn->length + insn->immediate.value; + reg = target - __x86_indirect_thunk_array; + + if (WARN_ON_ONCE(reg & ~0xf)) + return -1; + + /* If anyone ever does: CALL/JMP *%rsp, we're in deep trouble. */ + BUG_ON(reg == 4); + + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) + return -1; + + i = emit_indirect(insn->opcode.bytes[0], reg, bytes); + if (i < 0) + return i; + + for (; i < insn->length;) + bytes[i++] = 0x90; + + return i; +} + +/* + * Generated by 'objtool --retpoline'. + */ +void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) +{ + s32 *s; + + for (s = start; s < end; s++) { + void *addr = (void *)s + *s; + struct insn insn; + int len, ret; + u8 bytes[16]; + u8 op1, op2; + + ret = insn_decode_kernel(&insn, addr); + if (WARN_ON_ONCE(ret < 0)) + continue; + + op1 = insn.opcode.bytes[0]; + op2 = insn.opcode.bytes[1]; + + switch (op1) { + case CALL_INSN_OPCODE: + case JMP32_INSN_OPCODE: + break; + + default: + WARN_ON_ONCE(1); + continue; + } + + len = patch_retpoline(addr, &insn, bytes); + if (len == insn.length) { + optimize_nops(bytes, len); + text_poke_early(addr, bytes, len); + } + } +} + +#else /* !RETPOLINES || !CONFIG_STACK_VALIDATION */ + +void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { } + +#endif /* CONFIG_RETPOLINE && CONFIG_STACK_VALIDATION */ + #ifdef CONFIG_SMP static void alternatives_smp_lock(const s32 *start, const s32 *end, u8 *text, u8 *text_end) @@ -774,6 +901,12 @@ void __init alternative_instructions(void) * patching. */

+ /* + * Rewrite the retpolines, must be done before alternatives since + * those can rewrite the retpoline thunks. + */ + apply_retpolines(__retpoline_sites, __retpoline_sites_end); + apply_alternatives(__alt_instructions, __alt_instructions_end);

#ifdef CONFIG_SMP diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index a1eadaa41a95..dd1d8378f255 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -251,7 +251,8 @@ int module_finalize(const Elf_Ehdr *hdr, struct module *me) { const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL, - *para = NULL, *orc = NULL, *orc_ip = NULL; + *para = NULL, *orc = NULL, *orc_ip = NULL, + *retpolines = NULL; char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;

for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { @@ -267,8 +268,14 @@ int module_finalize(const Elf_Ehdr *hdr, orc = s; if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name)) orc_ip = s; + if (!strcmp(".retpoline_sites", secstrings + s->sh_name)) + retpolines = s; }

+ if (retpolines) { + void *rseg = (void *)retpolines->sh_addr; + apply_retpolines(rseg, rseg + retpolines->sh_size); + } if (alt) { /* patch .altinstructions */ void *aseg = (void *)alt->sh_addr;

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit c2746d567dcda6df41b1c3c1e930f51429f5a364 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 87c87ecd00c54ecd677798cb49ef27329e0fab41 upstream.

Current BPF codegen doesn't respect X86_FEATURE_RETPOLINE* flags and unconditionally emits a thunk call, this is sub-optimal and doesn't match the regular, compiler generated, code.

Update the i386 JIT to emit code equal to what the compiler emits for the regular kernel text (IOW. a plain THUNK call).

Update the x86_64 JIT to emit code similar to the result of compiler and kernel rewrites as according to X86_FEATURE_RETPOLINE* flags. Inlining RETPOLINE_AMD (lfence; jmp *%reg) and !RETPOLINE (jmp *%reg), while doing a THUNK call for RETPOLINE.

This removes the hard-coded retpoline thunks and shrinks the generated code. Leaving a single retpoline thunk definition in the kernel.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Borislav Petkov bp@suse.de Acked-by: Alexei Starovoitov ast@kernel.org Acked-by: Josh Poimboeuf jpoimboe@redhat.com Tested-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/r/20211026120310.614772675@infradead.org [cascardo: RETPOLINE_AMD was renamed to RETPOLINE_LFENCE] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com [bwh: Backported to 5.10: add the necessary cnt variable to emit_indirect_jump()] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/nospec-branch.h | 59 ---------------------------- arch/x86/net/bpf_jit_comp.c | 49 +++++++++++------------ arch/x86/net/bpf_jit_comp32.c | 22 +++++++++-- 3 files changed, 42 insertions(+), 88 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 01ced200bcd9..e791fe7e9de5 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -325,63 +325,4 @@ static inline void mds_idle_clear_cpu_buffers(void)

#endif /* __ASSEMBLY__ */

-/* - * Below is used in the eBPF JIT compiler and emits the byte sequence - * for the following assembly: - * - * With retpolines configured: - * - * callq do_rop - * spec_trap: - * pause - * lfence - * jmp spec_trap - * do_rop: - * mov %rcx,(%rsp) for x86_64 - * mov %edx,(%esp) for x86_32 - * retq - * - * Without retpolines configured: - * - * jmp *%rcx for x86_64 - * jmp *%edx for x86_32 - */ -#ifdef CONFIG_RETPOLINE -# ifdef CONFIG_X86_64 -# define RETPOLINE_RCX_BPF_JIT_SIZE 17 -# define RETPOLINE_RCX_BPF_JIT() \ -do { \ - EMIT1_off32(0xE8, 7); /* callq do_rop */ \ - /* spec_trap: */ \ - EMIT2(0xF3, 0x90); /* pause */ \ - EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \ - EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \ - /* do_rop: */ \ - EMIT4(0x48, 0x89, 0x0C, 0x24); /* mov %rcx,(%rsp) */ \ - EMIT1(0xC3); /* retq */ \ -} while (0) -# else /* !CONFIG_X86_64 */ -# define RETPOLINE_EDX_BPF_JIT() \ -do { \ - EMIT1_off32(0xE8, 7); /* call do_rop */ \ - /* spec_trap: */ \ - EMIT2(0xF3, 0x90); /* pause */ \ - EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \ - EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \ - /* do_rop: */ \ - EMIT3(0x89, 0x14, 0x24); /* mov %edx,(%esp) */ \ - EMIT1(0xC3); /* ret */ \ -} while (0) -# endif -#else /* !CONFIG_RETPOLINE */ -# ifdef CONFIG_X86_64 -# define RETPOLINE_RCX_BPF_JIT_SIZE 2 -# define RETPOLINE_RCX_BPF_JIT() \ - EMIT2(0xFF, 0xE1); /* jmp *%rcx */ -# else /* !CONFIG_X86_64 */ -# define RETPOLINE_EDX_BPF_JIT() \ - EMIT2(0xFF, 0xE2) /* jmp *%edx */ -# endif -#endif - #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 4c539a41d2b0..75358b63d9e4 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -379,6 +379,26 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, return __bpf_arch_text_poke(ip, t, old_addr, new_addr, true); }

+#define EMIT_LFENCE() EMIT3(0x0F, 0xAE, 0xE8) + +static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) +{ + u8 *prog = *pprog; + int cnt = 0; + +#ifdef CONFIG_RETPOLINE + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { + EMIT_LFENCE(); + EMIT2(0xFF, 0xE0 + reg); + } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { + emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); + } else +#endif + EMIT2(0xFF, 0xE0 + reg); + + *pprog = prog; +} + /* * Generate the following code: * @@ -460,7 +480,7 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, * rdi == ctx (1st arg) * rcx == prog->bpf_func + X86_TAIL_CALL_OFFSET */ - RETPOLINE_RCX_BPF_JIT(); + emit_indirect_jump(&prog, 1 /* rcx */, ip + (prog - start));

/* out: */ ctx->tail_call_indirect_label = prog - start; @@ -1099,8 +1119,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, /* speculation barrier */ case BPF_ST | BPF_NOSPEC: if (boot_cpu_has(X86_FEATURE_XMM2)) - /* Emit 'lfence' */ - EMIT3(0x0F, 0xAE, 0xE8); + EMIT_LFENCE(); break;

/* ST: *(u8*)(dst_reg + off) = imm */ @@ -1877,26 +1896,6 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i return ret; }

-static int emit_fallback_jump(u8 **pprog) -{ - u8 *prog = *pprog; - int err = 0; - -#ifdef CONFIG_RETPOLINE - /* Note that this assumes the the compiler uses external - * thunks for indirect calls. Both clang and GCC use the same - * naming convention for external thunks. - */ - err = emit_jump(&prog, __x86_indirect_thunk_rdx, prog); -#else - int cnt = 0; - - EMIT2(0xFF, 0xE2); /* jmp rdx */ -#endif - *pprog = prog; - return err; -} - static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) { u8 *jg_reloc, *prog = *pprog; @@ -1918,9 +1917,7 @@ static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs) if (err) return err;

- err = emit_fallback_jump(&prog); /* jmp thunk/indirect */ - if (err) - return err; + emit_indirect_jump(&prog, 2 /* rdx */, prog);

*pprog = prog; return 0; diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 4bd0f98df700..622af951220c 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -15,6 +15,7 @@ #include <asm/cacheflush.h> #include <asm/set_memory.h> #include <asm/nospec-branch.h> +#include <asm/asm-prototypes.h> #include <linux/bpf.h>

/* @@ -1267,6 +1268,21 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth) *pprog = prog; }

+static int emit_jmp_edx(u8 **pprog, u8 *ip) +{ + u8 *prog = *pprog; + int cnt = 0; + +#ifdef CONFIG_RETPOLINE + EMIT1_off32(0xE9, (u8 *)__x86_indirect_thunk_edx - (ip + 5)); +#else + EMIT2(0xFF, 0xE2); +#endif + *pprog = prog; + + return cnt; +} + /* * Generate the following code: * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ... @@ -1280,7 +1296,7 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth) * goto *(prog->bpf_func + prologue_size); * out: */ -static void emit_bpf_tail_call(u8 **pprog) +static void emit_bpf_tail_call(u8 **pprog, u8 *ip) { u8 *prog = *pprog; int cnt = 0; @@ -1362,7 +1378,7 @@ static void emit_bpf_tail_call(u8 **pprog) * eax == ctx (1st arg) * edx == prog->bpf_func + prologue_size */ - RETPOLINE_EDX_BPF_JIT(); + cnt += emit_jmp_edx(&prog, ip + cnt);

if (jmp_label1 == -1) jmp_label1 = cnt; @@ -1929,7 +1945,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, break; } case BPF_JMP | BPF_TAIL_CALL: - emit_bpf_tail_call(&prog); + emit_bpf_tail_call(&prog, image + addrs[i - 1]); break;

/* cond jump */

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 3c91e2257622c169bf74d587e48b96923285ed74 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit f94909ceb1ed4bfdb2ada72f93236305e6d6951f upstream.

Replace all ret/retq instructions with RET in preparation of making RET a macro. Since AS is case insensitive it's a big no-op without RET defined.

find arch/x86/ -name *.S | while read file do sed -i 's/<ret[q]*>/RET/' $file done

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Link: https://lore.kernel.org/r/20211204134907.905503893@infradead.org [bwh: Backported to 5.10: ran the above command] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

conflict: arch/x86/lib/copy_user_64.S

Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/boot/compressed/efi_thunk_64.S | 2 +- arch/x86/boot/compressed/head_64.S | 4 +- arch/x86/boot/compressed/mem_encrypt.S | 4 +- arch/x86/crypto/aegis128-aesni-asm.S | 48 +++++++++--------- arch/x86/crypto/aes_ctrby8_avx-x86_64.S | 2 +- arch/x86/crypto/aesni-intel_asm.S | 52 ++++++++++---------- arch/x86/crypto/aesni-intel_avx-x86_64.S | 40 +++++++-------- arch/x86/crypto/blake2s-core.S | 4 +- arch/x86/crypto/blowfish-x86_64-asm_64.S | 12 ++--- arch/x86/crypto/camellia-aesni-avx-asm_64.S | 18 +++---- arch/x86/crypto/camellia-aesni-avx2-asm_64.S | 18 +++---- arch/x86/crypto/camellia-x86_64-asm_64.S | 12 ++--- arch/x86/crypto/cast5-avx-x86_64-asm_64.S | 12 ++--- arch/x86/crypto/cast6-avx-x86_64-asm_64.S | 16 +++--- arch/x86/crypto/chacha-avx2-x86_64.S | 6 +-- arch/x86/crypto/chacha-avx512vl-x86_64.S | 6 +-- arch/x86/crypto/chacha-ssse3-x86_64.S | 8 +-- arch/x86/crypto/crc32-pclmul_asm.S | 2 +- arch/x86/crypto/crc32c-pcl-intel-asm_64.S | 2 +- arch/x86/crypto/crct10dif-pcl-asm_64.S | 2 +- arch/x86/crypto/des3_ede-asm_64.S | 4 +- arch/x86/crypto/ghash-clmulni-intel_asm.S | 6 +-- arch/x86/crypto/nh-avx2-x86_64.S | 2 +- arch/x86/crypto/nh-sse2-x86_64.S | 2 +- arch/x86/crypto/serpent-avx-x86_64-asm_64.S | 16 +++--- arch/x86/crypto/serpent-avx2-asm_64.S | 16 +++--- arch/x86/crypto/serpent-sse2-i586-asm_32.S | 6 +-- arch/x86/crypto/serpent-sse2-x86_64-asm_64.S | 6 +-- arch/x86/crypto/sha1_avx2_x86_64_asm.S | 2 +- arch/x86/crypto/sha1_ni_asm.S | 2 +- arch/x86/crypto/sha1_ssse3_asm.S | 2 +- arch/x86/crypto/sha256-avx-asm.S | 2 +- arch/x86/crypto/sha256-avx2-asm.S | 2 +- arch/x86/crypto/sha256-ssse3-asm.S | 2 +- arch/x86/crypto/sha256_ni_asm.S | 2 +- arch/x86/crypto/sha512-avx-asm.S | 2 +- arch/x86/crypto/sha512-avx2-asm.S | 2 +- arch/x86/crypto/sha512-ssse3-asm.S | 2 +- arch/x86/crypto/twofish-avx-x86_64-asm_64.S | 16 +++--- arch/x86/crypto/twofish-i586-asm_32.S | 4 +- arch/x86/crypto/twofish-x86_64-asm_64-3way.S | 6 +-- arch/x86/crypto/twofish-x86_64-asm_64.S | 4 +- arch/x86/entry/entry_32.S | 2 +- arch/x86/entry/entry_64.S | 12 ++--- arch/x86/entry/thunk_32.S | 2 +- arch/x86/entry/thunk_64.S | 2 +- arch/x86/entry/vdso/vdso32/system_call.S | 2 +- arch/x86/entry/vsyscall/vsyscall_emu_64.S | 6 +-- arch/x86/kernel/acpi/wakeup_32.S | 6 +-- arch/x86/kernel/ftrace_32.S | 6 +-- arch/x86/kernel/ftrace_64.S | 10 ++-- arch/x86/kernel/head_32.S | 2 +- arch/x86/kernel/irqflags.S | 4 +- arch/x86/kernel/relocate_kernel_32.S | 10 ++-- arch/x86/kernel/relocate_kernel_64.S | 10 ++-- arch/x86/kernel/sev_verify_cbit.S | 2 +- arch/x86/kernel/verify_cpu.S | 4 +- arch/x86/kvm/svm/vmenter.S | 2 +- arch/x86/kvm/vmx/vmenter.S | 14 +++--- arch/x86/lib/atomic64_386_32.S | 2 +- arch/x86/lib/atomic64_cx8_32.S | 16 +++--- arch/x86/lib/checksum_32.S | 8 +-- arch/x86/lib/clear_page_64.S | 6 +-- arch/x86/lib/cmpxchg16b_emu.S | 4 +- arch/x86/lib/cmpxchg8b_emu.S | 4 +- arch/x86/lib/copy_mc_64.S | 6 +-- arch/x86/lib/copy_page_64.S | 4 +- arch/x86/lib/copy_user_64.S | 12 ++--- arch/x86/lib/csum-copy_64.S | 2 +- arch/x86/lib/getuser.S | 22 ++++----- arch/x86/lib/hweight.S | 6 +-- arch/x86/lib/iomap_copy_64.S | 2 +- arch/x86/lib/memcpy_64.S | 12 ++--- arch/x86/lib/memmove_64.S | 4 +- arch/x86/lib/memset_64.S | 6 +-- arch/x86/lib/msr-reg.S | 4 +- arch/x86/lib/putuser.S | 6 +-- arch/x86/lib/retpoline.S | 2 +- arch/x86/math-emu/div_Xsig.S | 2 +- arch/x86/math-emu/div_small.S | 2 +- arch/x86/math-emu/mul_Xsig.S | 6 +-- arch/x86/math-emu/polynom_Xsig.S | 2 +- arch/x86/math-emu/reg_norm.S | 6 +-- arch/x86/math-emu/reg_round.S | 2 +- arch/x86/math-emu/reg_u_add.S | 2 +- arch/x86/math-emu/reg_u_div.S | 2 +- arch/x86/math-emu/reg_u_mul.S | 2 +- arch/x86/math-emu/reg_u_sub.S | 2 +- arch/x86/math-emu/round_Xsig.S | 4 +- arch/x86/math-emu/shr_Xsig.S | 8 +-- arch/x86/math-emu/wm_shrx.S | 16 +++--- arch/x86/mm/mem_encrypt_boot.S | 4 +- arch/x86/platform/efi/efi_stub_32.S | 2 +- arch/x86/platform/efi/efi_stub_64.S | 2 +- arch/x86/platform/efi/efi_thunk_64.S | 2 +- arch/x86/platform/olpc/xo1-wakeup.S | 6 +-- arch/x86/power/hibernate_asm_32.S | 4 +- arch/x86/power/hibernate_asm_64.S | 4 +- arch/x86/um/checksum_32.S | 4 +- arch/x86/um/setjmp_32.S | 2 +- arch/x86/um/setjmp_64.S | 2 +- arch/x86/xen/xen-asm.S | 14 +++--- arch/x86/xen/xen-head.S | 2 +- 103 files changed, 353 insertions(+), 353 deletions(-)

diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S index c4bb0f9363f5..c8052a141b08 100644 --- a/arch/x86/boot/compressed/efi_thunk_64.S +++ b/arch/x86/boot/compressed/efi_thunk_64.S @@ -89,7 +89,7 @@ SYM_FUNC_START(__efi64_thunk)

pop %rbx pop %rbp - ret + RET SYM_FUNC_END(__efi64_thunk)

.code32 diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 72f655c238cf..b55e2007b30c 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -786,7 +786,7 @@ SYM_FUNC_START(efi32_pe_entry) 2: popl %edi // restore callee-save registers popl %ebx leave - ret + RET SYM_FUNC_END(efi32_pe_entry)

.section ".rodata" @@ -868,7 +868,7 @@ SYM_FUNC_START(startup32_check_sev_cbit) popl %ebx popl %eax #endif - ret + RET SYM_FUNC_END(startup32_check_sev_cbit)

/* diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index a6dea4e8a082..484a9c06f41d 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -58,7 +58,7 @@ SYM_FUNC_START(get_sev_encryption_bit)

#endif /* CONFIG_AMD_MEM_ENCRYPT */

- ret + RET SYM_FUNC_END(get_sev_encryption_bit)

.code64 @@ -99,7 +99,7 @@ SYM_FUNC_START(set_sev_encryption_mask) #endif

xor %rax, %rax - ret + RET SYM_FUNC_END(set_sev_encryption_mask)

.data diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S index 51d46d93efbc..b48ddebb4748 100644 --- a/arch/x86/crypto/aegis128-aesni-asm.S +++ b/arch/x86/crypto/aegis128-aesni-asm.S @@ -122,7 +122,7 @@ SYM_FUNC_START_LOCAL(__load_partial) pxor T0, MSG

.Lld_partial_8: - ret + RET SYM_FUNC_END(__load_partial)

/* @@ -180,7 +180,7 @@ SYM_FUNC_START_LOCAL(__store_partial) mov %r10b, (%r9)

.Lst_partial_1: - ret + RET SYM_FUNC_END(__store_partial)

/* @@ -225,7 +225,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_init) movdqu STATE4, 0x40(STATEP)

FRAME_END - ret + RET SYM_FUNC_END(crypto_aegis128_aesni_init)

/* @@ -337,7 +337,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad) movdqu STATE3, 0x30(STATEP) movdqu STATE4, 0x40(STATEP) FRAME_END - ret + RET

.Lad_out_1: movdqu STATE4, 0x00(STATEP) @@ -346,7 +346,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad) movdqu STATE2, 0x30(STATEP) movdqu STATE3, 0x40(STATEP) FRAME_END - ret + RET

.Lad_out_2: movdqu STATE3, 0x00(STATEP) @@ -355,7 +355,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad) movdqu STATE1, 0x30(STATEP) movdqu STATE2, 0x40(STATEP) FRAME_END - ret + RET

.Lad_out_3: movdqu STATE2, 0x00(STATEP) @@ -364,7 +364,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad) movdqu STATE0, 0x30(STATEP) movdqu STATE1, 0x40(STATEP) FRAME_END - ret + RET

.Lad_out_4: movdqu STATE1, 0x00(STATEP) @@ -373,11 +373,11 @@ SYM_FUNC_START(crypto_aegis128_aesni_ad) movdqu STATE4, 0x30(STATEP) movdqu STATE0, 0x40(STATEP) FRAME_END - ret + RET

.Lad_out: FRAME_END - ret + RET SYM_FUNC_END(crypto_aegis128_aesni_ad)

.macro encrypt_block a s0 s1 s2 s3 s4 i @@ -452,7 +452,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc) movdqu STATE2, 0x30(STATEP) movdqu STATE3, 0x40(STATEP) FRAME_END - ret + RET

.Lenc_out_1: movdqu STATE3, 0x00(STATEP) @@ -461,7 +461,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc) movdqu STATE1, 0x30(STATEP) movdqu STATE2, 0x40(STATEP) FRAME_END - ret + RET

.Lenc_out_2: movdqu STATE2, 0x00(STATEP) @@ -470,7 +470,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc) movdqu STATE0, 0x30(STATEP) movdqu STATE1, 0x40(STATEP) FRAME_END - ret + RET

.Lenc_out_3: movdqu STATE1, 0x00(STATEP) @@ -479,7 +479,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc) movdqu STATE4, 0x30(STATEP) movdqu STATE0, 0x40(STATEP) FRAME_END - ret + RET

.Lenc_out_4: movdqu STATE0, 0x00(STATEP) @@ -488,11 +488,11 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc) movdqu STATE3, 0x30(STATEP) movdqu STATE4, 0x40(STATEP) FRAME_END - ret + RET

.Lenc_out: FRAME_END - ret + RET SYM_FUNC_END(crypto_aegis128_aesni_enc)

/* @@ -532,7 +532,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_enc_tail) movdqu STATE3, 0x40(STATEP)

FRAME_END - ret + RET SYM_FUNC_END(crypto_aegis128_aesni_enc_tail)

.macro decrypt_block a s0 s1 s2 s3 s4 i @@ -606,7 +606,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec) movdqu STATE2, 0x30(STATEP) movdqu STATE3, 0x40(STATEP) FRAME_END - ret + RET

.Ldec_out_1: movdqu STATE3, 0x00(STATEP) @@ -615,7 +615,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec) movdqu STATE1, 0x30(STATEP) movdqu STATE2, 0x40(STATEP) FRAME_END - ret + RET

.Ldec_out_2: movdqu STATE2, 0x00(STATEP) @@ -624,7 +624,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec) movdqu STATE0, 0x30(STATEP) movdqu STATE1, 0x40(STATEP) FRAME_END - ret + RET

.Ldec_out_3: movdqu STATE1, 0x00(STATEP) @@ -633,7 +633,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec) movdqu STATE4, 0x30(STATEP) movdqu STATE0, 0x40(STATEP) FRAME_END - ret + RET

.Ldec_out_4: movdqu STATE0, 0x00(STATEP) @@ -642,11 +642,11 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec) movdqu STATE3, 0x30(STATEP) movdqu STATE4, 0x40(STATEP) FRAME_END - ret + RET

.Ldec_out: FRAME_END - ret + RET SYM_FUNC_END(crypto_aegis128_aesni_dec)

/* @@ -696,7 +696,7 @@ SYM_FUNC_START(crypto_aegis128_aesni_dec_tail) movdqu STATE3, 0x40(STATEP)

FRAME_END - ret + RET SYM_FUNC_END(crypto_aegis128_aesni_dec_tail)

/* @@ -743,5 +743,5 @@ SYM_FUNC_START(crypto_aegis128_aesni_final) movdqu MSG, (%rsi)

FRAME_END - ret + RET SYM_FUNC_END(crypto_aegis128_aesni_final) diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S index 3f0fc7dd87d7..c799838242a6 100644 --- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S +++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S @@ -525,7 +525,7 @@ ddq_add_8: /* return updated IV */ vpshufb xbyteswap, xcounter, xcounter vmovdqu xcounter, (p_iv) - ret + RET .endm

/* diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 57aef3f5a81e..69c7c0dc22ea 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -1598,7 +1598,7 @@ SYM_FUNC_START(aesni_gcm_dec) GCM_ENC_DEC dec GCM_COMPLETE arg10, arg11 FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_dec)

@@ -1687,7 +1687,7 @@ SYM_FUNC_START(aesni_gcm_enc)

GCM_COMPLETE arg10, arg11 FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_enc)

/***************************************************************************** @@ -1705,7 +1705,7 @@ SYM_FUNC_START(aesni_gcm_init) FUNC_SAVE GCM_INIT %arg3, %arg4,%arg5, %arg6 FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_init)

/***************************************************************************** @@ -1720,7 +1720,7 @@ SYM_FUNC_START(aesni_gcm_enc_update) FUNC_SAVE GCM_ENC_DEC enc FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_enc_update)

/***************************************************************************** @@ -1735,7 +1735,7 @@ SYM_FUNC_START(aesni_gcm_dec_update) FUNC_SAVE GCM_ENC_DEC dec FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_dec_update)

/***************************************************************************** @@ -1750,7 +1750,7 @@ SYM_FUNC_START(aesni_gcm_finalize) FUNC_SAVE GCM_COMPLETE %arg3 %arg4 FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_finalize)

#endif @@ -1766,7 +1766,7 @@ SYM_FUNC_START_LOCAL(_key_expansion_256a) pxor %xmm1, %xmm0 movaps %xmm0, (TKEYP) add $0x10, TKEYP - ret + RET SYM_FUNC_END(_key_expansion_256a) SYM_FUNC_END_ALIAS(_key_expansion_128)

@@ -1791,7 +1791,7 @@ SYM_FUNC_START_LOCAL(_key_expansion_192a) shufps $0b01001110, %xmm2, %xmm1 movaps %xmm1, 0x10(TKEYP) add $0x20, TKEYP - ret + RET SYM_FUNC_END(_key_expansion_192a)

SYM_FUNC_START_LOCAL(_key_expansion_192b) @@ -1810,7 +1810,7 @@ SYM_FUNC_START_LOCAL(_key_expansion_192b)

movaps %xmm0, (TKEYP) add $0x10, TKEYP - ret + RET SYM_FUNC_END(_key_expansion_192b)

SYM_FUNC_START_LOCAL(_key_expansion_256b) @@ -1822,7 +1822,7 @@ SYM_FUNC_START_LOCAL(_key_expansion_256b) pxor %xmm1, %xmm2 movaps %xmm2, (TKEYP) add $0x10, TKEYP - ret + RET SYM_FUNC_END(_key_expansion_256b)

/* @@ -1937,7 +1937,7 @@ SYM_FUNC_START(aesni_set_key) popl KEYP #endif FRAME_END - ret + RET SYM_FUNC_END(aesni_set_key)

/* @@ -1961,7 +1961,7 @@ SYM_FUNC_START(aesni_enc) popl KEYP #endif FRAME_END - ret + RET SYM_FUNC_END(aesni_enc)

/* @@ -2018,7 +2018,7 @@ SYM_FUNC_START_LOCAL(_aesni_enc1) aesenc KEY, STATE movaps 0x70(TKEYP), KEY aesenclast KEY, STATE - ret + RET SYM_FUNC_END(_aesni_enc1)

/* @@ -2126,7 +2126,7 @@ SYM_FUNC_START_LOCAL(_aesni_enc4) aesenclast KEY, STATE2 aesenclast KEY, STATE3 aesenclast KEY, STATE4 - ret + RET SYM_FUNC_END(_aesni_enc4)

/* @@ -2151,7 +2151,7 @@ SYM_FUNC_START(aesni_dec) popl KEYP #endif FRAME_END - ret + RET SYM_FUNC_END(aesni_dec)

/* @@ -2208,7 +2208,7 @@ SYM_FUNC_START_LOCAL(_aesni_dec1) aesdec KEY, STATE movaps 0x70(TKEYP), KEY aesdeclast KEY, STATE - ret + RET SYM_FUNC_END(_aesni_dec1)

/* @@ -2316,7 +2316,7 @@ SYM_FUNC_START_LOCAL(_aesni_dec4) aesdeclast KEY, STATE2 aesdeclast KEY, STATE3 aesdeclast KEY, STATE4 - ret + RET SYM_FUNC_END(_aesni_dec4)

/* @@ -2376,7 +2376,7 @@ SYM_FUNC_START(aesni_ecb_enc) popl LEN #endif FRAME_END - ret + RET SYM_FUNC_END(aesni_ecb_enc)

/* @@ -2437,7 +2437,7 @@ SYM_FUNC_START(aesni_ecb_dec) popl LEN #endif FRAME_END - ret + RET SYM_FUNC_END(aesni_ecb_dec)

/* @@ -2481,7 +2481,7 @@ SYM_FUNC_START(aesni_cbc_enc) popl IVP #endif FRAME_END - ret + RET SYM_FUNC_END(aesni_cbc_enc)

/* @@ -2574,7 +2574,7 @@ SYM_FUNC_START(aesni_cbc_dec) popl IVP #endif FRAME_END - ret + RET SYM_FUNC_END(aesni_cbc_dec)

#ifdef __x86_64__ @@ -2602,7 +2602,7 @@ SYM_FUNC_START_LOCAL(_aesni_inc_init) mov $1, TCTR_LOW movq TCTR_LOW, INC movq CTR, TCTR_LOW - ret + RET SYM_FUNC_END(_aesni_inc_init)

/* @@ -2630,7 +2630,7 @@ SYM_FUNC_START_LOCAL(_aesni_inc) .Linc_low: movaps CTR, IV pshufb BSWAP_MASK, IV - ret + RET SYM_FUNC_END(_aesni_inc)

/* @@ -2693,7 +2693,7 @@ SYM_FUNC_START(aesni_ctr_enc) movups IV, (IVP) .Lctr_enc_just_ret: FRAME_END - ret + RET SYM_FUNC_END(aesni_ctr_enc)

/* @@ -2778,7 +2778,7 @@ SYM_FUNC_START(aesni_xts_encrypt) movups IV, (IVP)

FRAME_END - ret + RET SYM_FUNC_END(aesni_xts_encrypt)

/* @@ -2846,7 +2846,7 @@ SYM_FUNC_START(aesni_xts_decrypt) movups IV, (IVP)

FRAME_END - ret + RET SYM_FUNC_END(aesni_xts_decrypt)

#endif diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index 2cf8e94d986a..4d9b2f887064 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -1777,7 +1777,7 @@ SYM_FUNC_START(aesni_gcm_init_avx_gen2) FUNC_SAVE INIT GHASH_MUL_AVX, PRECOMPUTE_AVX FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_init_avx_gen2)

############################################################################### @@ -1798,15 +1798,15 @@ SYM_FUNC_START(aesni_gcm_enc_update_avx_gen2) # must be 192 GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 11 FUNC_RESTORE - ret + RET key_128_enc_update: GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 9 FUNC_RESTORE - ret + RET key_256_enc_update: GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, ENC, 13 FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_enc_update_avx_gen2)

############################################################################### @@ -1827,15 +1827,15 @@ SYM_FUNC_START(aesni_gcm_dec_update_avx_gen2) # must be 192 GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 11 FUNC_RESTORE - ret + RET key_128_dec_update: GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 9 FUNC_RESTORE - ret + RET key_256_dec_update: GCM_ENC_DEC INITIAL_BLOCKS_AVX, GHASH_8_ENCRYPT_8_PARALLEL_AVX, GHASH_LAST_8_AVX, GHASH_MUL_AVX, DEC, 13 FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_dec_update_avx_gen2)

############################################################################### @@ -1856,15 +1856,15 @@ SYM_FUNC_START(aesni_gcm_finalize_avx_gen2) # must be 192 GCM_COMPLETE GHASH_MUL_AVX, 11, arg3, arg4 FUNC_RESTORE - ret + RET key_128_finalize: GCM_COMPLETE GHASH_MUL_AVX, 9, arg3, arg4 FUNC_RESTORE - ret + RET key_256_finalize: GCM_COMPLETE GHASH_MUL_AVX, 13, arg3, arg4 FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_finalize_avx_gen2)

############################################################################### @@ -2745,7 +2745,7 @@ SYM_FUNC_START(aesni_gcm_init_avx_gen4) FUNC_SAVE INIT GHASH_MUL_AVX2, PRECOMPUTE_AVX2 FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_init_avx_gen4)

############################################################################### @@ -2766,15 +2766,15 @@ SYM_FUNC_START(aesni_gcm_enc_update_avx_gen4) # must be 192 GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 11 FUNC_RESTORE - ret + RET key_128_enc_update4: GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 9 FUNC_RESTORE - ret + RET key_256_enc_update4: GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, ENC, 13 FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_enc_update_avx_gen4)

############################################################################### @@ -2795,15 +2795,15 @@ SYM_FUNC_START(aesni_gcm_dec_update_avx_gen4) # must be 192 GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 11 FUNC_RESTORE - ret + RET key_128_dec_update4: GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 9 FUNC_RESTORE - ret + RET key_256_dec_update4: GCM_ENC_DEC INITIAL_BLOCKS_AVX2, GHASH_8_ENCRYPT_8_PARALLEL_AVX2, GHASH_LAST_8_AVX2, GHASH_MUL_AVX2, DEC, 13 FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_dec_update_avx_gen4)

############################################################################### @@ -2824,13 +2824,13 @@ SYM_FUNC_START(aesni_gcm_finalize_avx_gen4) # must be 192 GCM_COMPLETE GHASH_MUL_AVX2, 11, arg3, arg4 FUNC_RESTORE - ret + RET key_128_finalize4: GCM_COMPLETE GHASH_MUL_AVX2, 9, arg3, arg4 FUNC_RESTORE - ret + RET key_256_finalize4: GCM_COMPLETE GHASH_MUL_AVX2, 13, arg3, arg4 FUNC_RESTORE - ret + RET SYM_FUNC_END(aesni_gcm_finalize_avx_gen4) diff --git a/arch/x86/crypto/blake2s-core.S b/arch/x86/crypto/blake2s-core.S index 2ca79974f819..b50b35ff1fdb 100644 --- a/arch/x86/crypto/blake2s-core.S +++ b/arch/x86/crypto/blake2s-core.S @@ -171,7 +171,7 @@ SYM_FUNC_START(blake2s_compress_ssse3) movdqu %xmm1,0x10(%rdi) movdqu %xmm14,0x20(%rdi) .Lendofloop: - ret + RET SYM_FUNC_END(blake2s_compress_ssse3)

#ifdef CONFIG_AS_AVX512 @@ -251,6 +251,6 @@ SYM_FUNC_START(blake2s_compress_avx512) vmovdqu %xmm1,0x10(%rdi) vmovdqu %xmm4,0x20(%rdi) vzeroupper - retq + RET SYM_FUNC_END(blake2s_compress_avx512) #endif /* CONFIG_AS_AVX512 */ diff --git a/arch/x86/crypto/blowfish-x86_64-asm_64.S b/arch/x86/crypto/blowfish-x86_64-asm_64.S index 4222ac6d6584..802d71582689 100644 --- a/arch/x86/crypto/blowfish-x86_64-asm_64.S +++ b/arch/x86/crypto/blowfish-x86_64-asm_64.S @@ -135,10 +135,10 @@ SYM_FUNC_START(__blowfish_enc_blk) jnz .L__enc_xor;

write_block(); - ret; + RET; .L__enc_xor: xor_block(); - ret; + RET; SYM_FUNC_END(__blowfish_enc_blk)

SYM_FUNC_START(blowfish_dec_blk) @@ -170,7 +170,7 @@ SYM_FUNC_START(blowfish_dec_blk)

movq %r11, %r12;

- ret; + RET; SYM_FUNC_END(blowfish_dec_blk)

/********************************************************************** @@ -322,14 +322,14 @@ SYM_FUNC_START(__blowfish_enc_blk_4way)

popq %rbx; popq %r12; - ret; + RET;

.L__enc_xor4: xor_block4();

popq %rbx; popq %r12; - ret; + RET; SYM_FUNC_END(__blowfish_enc_blk_4way)

SYM_FUNC_START(blowfish_dec_blk_4way) @@ -364,5 +364,5 @@ SYM_FUNC_START(blowfish_dec_blk_4way) popq %rbx; popq %r12;

- ret; + RET; SYM_FUNC_END(blowfish_dec_blk_4way) diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S index ecc0a9a905c4..297b1a7ed2bc 100644 --- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S @@ -193,7 +193,7 @@ SYM_FUNC_START_LOCAL(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_c roundsm16(%xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, %xmm15, %rcx, (%r9)); - ret; + RET; SYM_FUNC_END(roundsm16_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)

.align 8 @@ -201,7 +201,7 @@ SYM_FUNC_START_LOCAL(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_a roundsm16(%xmm4, %xmm5, %xmm6, %xmm7, %xmm0, %xmm1, %xmm2, %xmm3, %xmm12, %xmm13, %xmm14, %xmm15, %xmm8, %xmm9, %xmm10, %xmm11, %rax, (%r9)); - ret; + RET; SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)

/* @@ -787,7 +787,7 @@ SYM_FUNC_START_LOCAL(__camellia_enc_blk16) %xmm15, (key_table)(CTX, %r8, 8), (%rax), 1 * 16(%rax));

FRAME_END - ret; + RET;

.align 8 .Lenc_max32: @@ -874,7 +874,7 @@ SYM_FUNC_START_LOCAL(__camellia_dec_blk16) %xmm15, (key_table)(CTX), (%rax), 1 * 16(%rax));

FRAME_END - ret; + RET;

.align 8 .Ldec_max32: @@ -915,7 +915,7 @@ SYM_FUNC_START(camellia_ecb_enc_16way) %xmm8, %rsi);

FRAME_END - ret; + RET; SYM_FUNC_END(camellia_ecb_enc_16way)

SYM_FUNC_START(camellia_ecb_dec_16way) @@ -945,7 +945,7 @@ SYM_FUNC_START(camellia_ecb_dec_16way) %xmm8, %rsi);

FRAME_END - ret; + RET; SYM_FUNC_END(camellia_ecb_dec_16way)

SYM_FUNC_START(camellia_cbc_dec_16way) @@ -996,7 +996,7 @@ SYM_FUNC_START(camellia_cbc_dec_16way) %xmm8, %rsi);

FRAME_END - ret; + RET; SYM_FUNC_END(camellia_cbc_dec_16way)

#define inc_le128(x, minus_one, tmp) \ @@ -1109,7 +1109,7 @@ SYM_FUNC_START(camellia_ctr_16way) %xmm8, %rsi);

FRAME_END - ret; + RET; SYM_FUNC_END(camellia_ctr_16way)

#define gf128mul_x_ble(iv, mask, tmp) \ @@ -1253,7 +1253,7 @@ SYM_FUNC_START_LOCAL(camellia_xts_crypt_16way) %xmm8, %rsi);

FRAME_END - ret; + RET; SYM_FUNC_END(camellia_xts_crypt_16way)

SYM_FUNC_START(camellia_xts_enc_16way) diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S index 0907243c501c..288cd246da20 100644 --- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S @@ -227,7 +227,7 @@ SYM_FUNC_START_LOCAL(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_c roundsm32(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, %rcx, (%r9)); - ret; + RET; SYM_FUNC_END(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd)

.align 8 @@ -235,7 +235,7 @@ SYM_FUNC_START_LOCAL(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_a roundsm32(%ymm4, %ymm5, %ymm6, %ymm7, %ymm0, %ymm1, %ymm2, %ymm3, %ymm12, %ymm13, %ymm14, %ymm15, %ymm8, %ymm9, %ymm10, %ymm11, %rax, (%r9)); - ret; + RET; SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab)

/* @@ -825,7 +825,7 @@ SYM_FUNC_START_LOCAL(__camellia_enc_blk32) %ymm15, (key_table)(CTX, %r8, 8), (%rax), 1 * 32(%rax));

FRAME_END - ret; + RET;

.align 8 .Lenc_max32: @@ -912,7 +912,7 @@ SYM_FUNC_START_LOCAL(__camellia_dec_blk32) %ymm15, (key_table)(CTX), (%rax), 1 * 32(%rax));

FRAME_END - ret; + RET;

.align 8 .Ldec_max32: @@ -957,7 +957,7 @@ SYM_FUNC_START(camellia_ecb_enc_32way) vzeroupper;

FRAME_END - ret; + RET; SYM_FUNC_END(camellia_ecb_enc_32way)

SYM_FUNC_START(camellia_ecb_dec_32way) @@ -991,7 +991,7 @@ SYM_FUNC_START(camellia_ecb_dec_32way) vzeroupper;

FRAME_END - ret; + RET; SYM_FUNC_END(camellia_ecb_dec_32way)

SYM_FUNC_START(camellia_cbc_dec_32way) @@ -1059,7 +1059,7 @@ SYM_FUNC_START(camellia_cbc_dec_32way) vzeroupper;

FRAME_END - ret; + RET; SYM_FUNC_END(camellia_cbc_dec_32way)

#define inc_le128(x, minus_one, tmp) \ @@ -1199,7 +1199,7 @@ SYM_FUNC_START(camellia_ctr_32way) vzeroupper;

FRAME_END - ret; + RET; SYM_FUNC_END(camellia_ctr_32way)

#define gf128mul_x_ble(iv, mask, tmp) \ @@ -1366,7 +1366,7 @@ SYM_FUNC_START_LOCAL(camellia_xts_crypt_32way) vzeroupper;

FRAME_END - ret; + RET; SYM_FUNC_END(camellia_xts_crypt_32way)

SYM_FUNC_START(camellia_xts_enc_32way) diff --git a/arch/x86/crypto/camellia-x86_64-asm_64.S b/arch/x86/crypto/camellia-x86_64-asm_64.S index 1372e6408850..347c059f5940 100644 --- a/arch/x86/crypto/camellia-x86_64-asm_64.S +++ b/arch/x86/crypto/camellia-x86_64-asm_64.S @@ -213,13 +213,13 @@ SYM_FUNC_START(__camellia_enc_blk) enc_outunpack(mov, RT1);

movq RR12, %r12; - ret; + RET;

.L__enc_xor: enc_outunpack(xor, RT1);

movq RR12, %r12; - ret; + RET; SYM_FUNC_END(__camellia_enc_blk)

SYM_FUNC_START(camellia_dec_blk) @@ -257,7 +257,7 @@ SYM_FUNC_START(camellia_dec_blk) dec_outunpack();

movq RR12, %r12; - ret; + RET; SYM_FUNC_END(camellia_dec_blk)

/********************************************************************** @@ -448,14 +448,14 @@ SYM_FUNC_START(__camellia_enc_blk_2way)

movq RR12, %r12; popq %rbx; - ret; + RET;

.L__enc2_xor: enc_outunpack2(xor, RT2);

movq RR12, %r12; popq %rbx; - ret; + RET; SYM_FUNC_END(__camellia_enc_blk_2way)

SYM_FUNC_START(camellia_dec_blk_2way) @@ -495,5 +495,5 @@ SYM_FUNC_START(camellia_dec_blk_2way)

movq RR12, %r12; movq RXOR, %rbx; - ret; + RET; SYM_FUNC_END(camellia_dec_blk_2way) diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S index 8a6181b08b59..b258af420c92 100644 --- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S @@ -279,7 +279,7 @@ SYM_FUNC_START_LOCAL(__cast5_enc_blk16) outunpack_blocks(RR3, RL3, RTMP, RX, RKM); outunpack_blocks(RR4, RL4, RTMP, RX, RKM);

- ret; + RET; SYM_FUNC_END(__cast5_enc_blk16)

.align 16 @@ -352,7 +352,7 @@ SYM_FUNC_START_LOCAL(__cast5_dec_blk16) outunpack_blocks(RR3, RL3, RTMP, RX, RKM); outunpack_blocks(RR4, RL4, RTMP, RX, RKM);

- ret; + RET;

.L__skip_dec: vpsrldq $4, RKR, RKR; @@ -393,7 +393,7 @@ SYM_FUNC_START(cast5_ecb_enc_16way)

popq %r15; FRAME_END - ret; + RET; SYM_FUNC_END(cast5_ecb_enc_16way)

SYM_FUNC_START(cast5_ecb_dec_16way) @@ -431,7 +431,7 @@ SYM_FUNC_START(cast5_ecb_dec_16way)

popq %r15; FRAME_END - ret; + RET; SYM_FUNC_END(cast5_ecb_dec_16way)

SYM_FUNC_START(cast5_cbc_dec_16way) @@ -483,7 +483,7 @@ SYM_FUNC_START(cast5_cbc_dec_16way) popq %r15; popq %r12; FRAME_END - ret; + RET; SYM_FUNC_END(cast5_cbc_dec_16way)

SYM_FUNC_START(cast5_ctr_16way) @@ -559,5 +559,5 @@ SYM_FUNC_START(cast5_ctr_16way) popq %r15; popq %r12; FRAME_END - ret; + RET; SYM_FUNC_END(cast5_ctr_16way) diff --git a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S index 932a3ce32a88..6eccaf1fb4c6 100644 --- a/arch/x86/crypto/cast6-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast6-avx-x86_64-asm_64.S @@ -291,7 +291,7 @@ SYM_FUNC_START_LOCAL(__cast6_enc_blk8) outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM); outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);

- ret; + RET; SYM_FUNC_END(__cast6_enc_blk8)

.align 8 @@ -338,7 +338,7 @@ SYM_FUNC_START_LOCAL(__cast6_dec_blk8) outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM); outunpack_blocks(RA2, RB2, RC2, RD2, RTMP, RX, RKRF, RKM);

- ret; + RET; SYM_FUNC_END(__cast6_dec_blk8)

SYM_FUNC_START(cast6_ecb_enc_8way) @@ -361,7 +361,7 @@ SYM_FUNC_START(cast6_ecb_enc_8way)

popq %r15; FRAME_END - ret; + RET; SYM_FUNC_END(cast6_ecb_enc_8way)

SYM_FUNC_START(cast6_ecb_dec_8way) @@ -384,7 +384,7 @@ SYM_FUNC_START(cast6_ecb_dec_8way)

popq %r15; FRAME_END - ret; + RET; SYM_FUNC_END(cast6_ecb_dec_8way)

SYM_FUNC_START(cast6_cbc_dec_8way) @@ -410,7 +410,7 @@ SYM_FUNC_START(cast6_cbc_dec_8way) popq %r15; popq %r12; FRAME_END - ret; + RET; SYM_FUNC_END(cast6_cbc_dec_8way)

SYM_FUNC_START(cast6_ctr_8way) @@ -438,7 +438,7 @@ SYM_FUNC_START(cast6_ctr_8way) popq %r15; popq %r12; FRAME_END - ret; + RET; SYM_FUNC_END(cast6_ctr_8way)

SYM_FUNC_START(cast6_xts_enc_8way) @@ -465,7 +465,7 @@ SYM_FUNC_START(cast6_xts_enc_8way)

popq %r15; FRAME_END - ret; + RET; SYM_FUNC_END(cast6_xts_enc_8way)

SYM_FUNC_START(cast6_xts_dec_8way) @@ -492,5 +492,5 @@ SYM_FUNC_START(cast6_xts_dec_8way)

popq %r15; FRAME_END - ret; + RET; SYM_FUNC_END(cast6_xts_dec_8way) diff --git a/arch/x86/crypto/chacha-avx2-x86_64.S b/arch/x86/crypto/chacha-avx2-x86_64.S index ee9a40ab4109..f3d8fc018249 100644 --- a/arch/x86/crypto/chacha-avx2-x86_64.S +++ b/arch/x86/crypto/chacha-avx2-x86_64.S @@ -193,7 +193,7 @@ SYM_FUNC_START(chacha_2block_xor_avx2)

.Ldone2: vzeroupper - ret + RET

.Lxorpart2: # xor remaining bytes from partial register into output @@ -498,7 +498,7 @@ SYM_FUNC_START(chacha_4block_xor_avx2)

.Ldone4: vzeroupper - ret + RET

.Lxorpart4: # xor remaining bytes from partial register into output @@ -992,7 +992,7 @@ SYM_FUNC_START(chacha_8block_xor_avx2) .Ldone8: vzeroupper lea -8(%r10),%rsp - ret + RET

.Lxorpart8: # xor remaining bytes from partial register into output diff --git a/arch/x86/crypto/chacha-avx512vl-x86_64.S b/arch/x86/crypto/chacha-avx512vl-x86_64.S index 8713c16c2501..259383e1ad44 100644 --- a/arch/x86/crypto/chacha-avx512vl-x86_64.S +++ b/arch/x86/crypto/chacha-avx512vl-x86_64.S @@ -166,7 +166,7 @@ SYM_FUNC_START(chacha_2block_xor_avx512vl)

.Ldone2: vzeroupper - ret + RET

.Lxorpart2: # xor remaining bytes from partial register into output @@ -432,7 +432,7 @@ SYM_FUNC_START(chacha_4block_xor_avx512vl)

.Ldone4: vzeroupper - ret + RET

.Lxorpart4: # xor remaining bytes from partial register into output @@ -812,7 +812,7 @@ SYM_FUNC_START(chacha_8block_xor_avx512vl)

.Ldone8: vzeroupper - ret + RET

.Lxorpart8: # xor remaining bytes from partial register into output diff --git a/arch/x86/crypto/chacha-ssse3-x86_64.S b/arch/x86/crypto/chacha-ssse3-x86_64.S index ca1788bfee16..7111949cd5b9 100644 --- a/arch/x86/crypto/chacha-ssse3-x86_64.S +++ b/arch/x86/crypto/chacha-ssse3-x86_64.S @@ -108,7 +108,7 @@ SYM_FUNC_START_LOCAL(chacha_permute) sub $2,%r8d jnz .Ldoubleround

- ret + RET SYM_FUNC_END(chacha_permute)

SYM_FUNC_START(chacha_block_xor_ssse3) @@ -166,7 +166,7 @@ SYM_FUNC_START(chacha_block_xor_ssse3)

.Ldone: FRAME_END - ret + RET

.Lxorpart: # xor remaining bytes from partial register into output @@ -217,7 +217,7 @@ SYM_FUNC_START(hchacha_block_ssse3) movdqu %xmm3,0x10(%rsi)

FRAME_END - ret + RET SYM_FUNC_END(hchacha_block_ssse3)

SYM_FUNC_START(chacha_4block_xor_ssse3) @@ -762,7 +762,7 @@ SYM_FUNC_START(chacha_4block_xor_ssse3)

.Ldone4: lea -8(%r10),%rsp - ret + RET

.Lxorpart4: # xor remaining bytes from partial register into output diff --git a/arch/x86/crypto/crc32-pclmul_asm.S b/arch/x86/crypto/crc32-pclmul_asm.S index 6e7d4c4d3208..c392a6edbfff 100644 --- a/arch/x86/crypto/crc32-pclmul_asm.S +++ b/arch/x86/crypto/crc32-pclmul_asm.S @@ -236,5 +236,5 @@ fold_64: pxor %xmm2, %xmm1 pextrd $0x01, %xmm1, %eax

- ret + RET SYM_FUNC_END(crc32_pclmul_le_16) diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index 884dc767b051..f6e3568fbd63 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -309,7 +309,7 @@ do_return: popq %rsi popq %rdi popq %rbx - ret + RET SYM_FUNC_END(crc_pcl)

.section .rodata, "a", @progbits diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/crypto/crct10dif-pcl-asm_64.S index b2533d63030e..721474abfb71 100644 --- a/arch/x86/crypto/crct10dif-pcl-asm_64.S +++ b/arch/x86/crypto/crct10dif-pcl-asm_64.S @@ -257,7 +257,7 @@ SYM_FUNC_START(crc_t10dif_pcl) # Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of xmm0.

pextrw $0, %xmm0, %eax - ret + RET

.align 16 .Lless_than_256_bytes: diff --git a/arch/x86/crypto/des3_ede-asm_64.S b/arch/x86/crypto/des3_ede-asm_64.S index fac0fdc3f25d..f4c760f4cade 100644 --- a/arch/x86/crypto/des3_ede-asm_64.S +++ b/arch/x86/crypto/des3_ede-asm_64.S @@ -243,7 +243,7 @@ SYM_FUNC_START(des3_ede_x86_64_crypt_blk) popq %r12; popq %rbx;

- ret; + RET; SYM_FUNC_END(des3_ede_x86_64_crypt_blk)

/*********************************************************************** @@ -528,7 +528,7 @@ SYM_FUNC_START(des3_ede_x86_64_crypt_blk_3way) popq %r12; popq %rbx;

- ret; + RET; SYM_FUNC_END(des3_ede_x86_64_crypt_blk_3way)

.section .rodata, "a", @progbits diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S index 99ac25e18e09..2bf871899920 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_asm.S +++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S @@ -85,7 +85,7 @@ SYM_FUNC_START_LOCAL(__clmul_gf128mul_ble) psrlq $1, T2 pxor T2, T1 pxor T1, DATA - ret + RET SYM_FUNC_END(__clmul_gf128mul_ble)

/* void clmul_ghash_mul(char *dst, const u128 *shash) */ @@ -99,7 +99,7 @@ SYM_FUNC_START(clmul_ghash_mul) pshufb BSWAP, DATA movups DATA, (%rdi) FRAME_END - ret + RET SYM_FUNC_END(clmul_ghash_mul)

/* @@ -128,5 +128,5 @@ SYM_FUNC_START(clmul_ghash_update) movups DATA, (%rdi) .Lupdate_just_ret: FRAME_END - ret + RET SYM_FUNC_END(clmul_ghash_update) diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S index b22c7b936272..6a0b15e7196a 100644 --- a/arch/x86/crypto/nh-avx2-x86_64.S +++ b/arch/x86/crypto/nh-avx2-x86_64.S @@ -153,5 +153,5 @@ SYM_FUNC_START(nh_avx2) vpaddq T1, T0, T0 vpaddq T4, T0, T0 vmovdqu T0, (HASH) - ret + RET SYM_FUNC_END(nh_avx2) diff --git a/arch/x86/crypto/nh-sse2-x86_64.S b/arch/x86/crypto/nh-sse2-x86_64.S index d7ae22dd6683..34c567bbcb4f 100644 --- a/arch/x86/crypto/nh-sse2-x86_64.S +++ b/arch/x86/crypto/nh-sse2-x86_64.S @@ -119,5 +119,5 @@ SYM_FUNC_START(nh_sse2) paddq PASS2_SUMS, T1 movdqu T0, 0x00(HASH) movdqu T1, 0x10(HASH) - ret + RET SYM_FUNC_END(nh_sse2) diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S index ba9e4c1e7f5c..c985bc15304b 100644 --- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S @@ -605,7 +605,7 @@ SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx) write_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2); write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);

- ret; + RET; SYM_FUNC_END(__serpent_enc_blk8_avx)

.align 8 @@ -659,7 +659,7 @@ SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx) write_blocks(RC1, RD1, RB1, RE1, RK0, RK1, RK2); write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);

- ret; + RET; SYM_FUNC_END(__serpent_dec_blk8_avx)

SYM_FUNC_START(serpent_ecb_enc_8way_avx) @@ -677,7 +677,7 @@ SYM_FUNC_START(serpent_ecb_enc_8way_avx) store_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);

FRAME_END - ret; + RET; SYM_FUNC_END(serpent_ecb_enc_8way_avx)

SYM_FUNC_START(serpent_ecb_dec_8way_avx) @@ -695,7 +695,7 @@ SYM_FUNC_START(serpent_ecb_dec_8way_avx) store_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);

FRAME_END - ret; + RET; SYM_FUNC_END(serpent_ecb_dec_8way_avx)

SYM_FUNC_START(serpent_cbc_dec_8way_avx) @@ -713,7 +713,7 @@ SYM_FUNC_START(serpent_cbc_dec_8way_avx) store_cbc_8way(%rdx, %rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);

FRAME_END - ret; + RET; SYM_FUNC_END(serpent_cbc_dec_8way_avx)

SYM_FUNC_START(serpent_ctr_8way_avx) @@ -733,7 +733,7 @@ SYM_FUNC_START(serpent_ctr_8way_avx) store_ctr_8way(%rdx, %rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);

FRAME_END - ret; + RET; SYM_FUNC_END(serpent_ctr_8way_avx)

SYM_FUNC_START(serpent_xts_enc_8way_avx) @@ -755,7 +755,7 @@ SYM_FUNC_START(serpent_xts_enc_8way_avx) store_xts_8way(%rsi, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);

FRAME_END - ret; + RET; SYM_FUNC_END(serpent_xts_enc_8way_avx)

SYM_FUNC_START(serpent_xts_dec_8way_avx) @@ -777,5 +777,5 @@ SYM_FUNC_START(serpent_xts_dec_8way_avx) store_xts_8way(%rsi, RC1, RD1, RB1, RE1, RC2, RD2, RB2, RE2);

FRAME_END - ret; + RET; SYM_FUNC_END(serpent_xts_dec_8way_avx) diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S index c9648aeae705..ca18948964f4 100644 --- a/arch/x86/crypto/serpent-avx2-asm_64.S +++ b/arch/x86/crypto/serpent-avx2-asm_64.S @@ -611,7 +611,7 @@ SYM_FUNC_START_LOCAL(__serpent_enc_blk16) write_blocks(RA1, RB1, RC1, RD1, RK0, RK1, RK2); write_blocks(RA2, RB2, RC2, RD2, RK0, RK1, RK2);

- ret; + RET; SYM_FUNC_END(__serpent_enc_blk16)

.align 8 @@ -665,7 +665,7 @@ SYM_FUNC_START_LOCAL(__serpent_dec_blk16) write_blocks(RC1, RD1, RB1, RE1, RK0, RK1, RK2); write_blocks(RC2, RD2, RB2, RE2, RK0, RK1, RK2);

- ret; + RET; SYM_FUNC_END(__serpent_dec_blk16)

SYM_FUNC_START(serpent_ecb_enc_16way) @@ -687,7 +687,7 @@ SYM_FUNC_START(serpent_ecb_enc_16way) vzeroupper;

FRAME_END - ret; + RET; SYM_FUNC_END(serpent_ecb_enc_16way)

SYM_FUNC_START(serpent_ecb_dec_16way) @@ -709,7 +709,7 @@ SYM_FUNC_START(serpent_ecb_dec_16way) vzeroupper;

FRAME_END - ret; + RET; SYM_FUNC_END(serpent_ecb_dec_16way)

SYM_FUNC_START(serpent_cbc_dec_16way) @@ -732,7 +732,7 @@ SYM_FUNC_START(serpent_cbc_dec_16way) vzeroupper;

FRAME_END - ret; + RET; SYM_FUNC_END(serpent_cbc_dec_16way)

SYM_FUNC_START(serpent_ctr_16way) @@ -757,7 +757,7 @@ SYM_FUNC_START(serpent_ctr_16way) vzeroupper;

FRAME_END - ret; + RET; SYM_FUNC_END(serpent_ctr_16way)

SYM_FUNC_START(serpent_xts_enc_16way) @@ -783,7 +783,7 @@ SYM_FUNC_START(serpent_xts_enc_16way) vzeroupper;

FRAME_END - ret; + RET; SYM_FUNC_END(serpent_xts_enc_16way)

SYM_FUNC_START(serpent_xts_dec_16way) @@ -809,5 +809,5 @@ SYM_FUNC_START(serpent_xts_dec_16way) vzeroupper;

FRAME_END - ret; + RET; SYM_FUNC_END(serpent_xts_dec_16way) diff --git a/arch/x86/crypto/serpent-sse2-i586-asm_32.S b/arch/x86/crypto/serpent-sse2-i586-asm_32.S index 6379b99cb722..8ccb03ad7cef 100644 --- a/arch/x86/crypto/serpent-sse2-i586-asm_32.S +++ b/arch/x86/crypto/serpent-sse2-i586-asm_32.S @@ -553,12 +553,12 @@ SYM_FUNC_START(__serpent_enc_blk_4way)

write_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);

- ret; + RET;

.L__enc_xor4: xor_blocks(%eax, RA, RB, RC, RD, RT0, RT1, RE);

- ret; + RET; SYM_FUNC_END(__serpent_enc_blk_4way)

SYM_FUNC_START(serpent_dec_blk_4way) @@ -612,5 +612,5 @@ SYM_FUNC_START(serpent_dec_blk_4way) movl arg_dst(%esp), %eax; write_blocks(%eax, RC, RD, RB, RE, RT0, RT1, RA);

- ret; + RET; SYM_FUNC_END(serpent_dec_blk_4way) diff --git a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S index efb6dc17dc90..e0998a011d1d 100644 --- a/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S +++ b/arch/x86/crypto/serpent-sse2-x86_64-asm_64.S @@ -675,13 +675,13 @@ SYM_FUNC_START(__serpent_enc_blk_8way) write_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2); write_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);

- ret; + RET;

.L__enc_xor8: xor_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2); xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);

- ret; + RET; SYM_FUNC_END(__serpent_enc_blk_8way)

SYM_FUNC_START(serpent_dec_blk_8way) @@ -735,5 +735,5 @@ SYM_FUNC_START(serpent_dec_blk_8way) write_blocks(%rsi, RC1, RD1, RB1, RE1, RK0, RK1, RK2); write_blocks(%rax, RC2, RD2, RB2, RE2, RK0, RK1, RK2);

- ret; + RET; SYM_FUNC_END(serpent_dec_blk_8way) diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S index 1e594d60afa5..6fa622652bfc 100644 --- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S +++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S @@ -674,7 +674,7 @@ _loop3: pop %r12 pop %rbx

- ret + RET

SYM_FUNC_END(\name) .endm diff --git a/arch/x86/crypto/sha1_ni_asm.S b/arch/x86/crypto/sha1_ni_asm.S index 11efe3a45a1f..b59f3ca62837 100644 --- a/arch/x86/crypto/sha1_ni_asm.S +++ b/arch/x86/crypto/sha1_ni_asm.S @@ -290,7 +290,7 @@ SYM_FUNC_START(sha1_ni_transform) .Ldone_hash: mov RSPSAVE, %rsp

- ret + RET SYM_FUNC_END(sha1_ni_transform)

.section .rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16 diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S index d25668d2a1e9..263f916362e0 100644 --- a/arch/x86/crypto/sha1_ssse3_asm.S +++ b/arch/x86/crypto/sha1_ssse3_asm.S @@ -99,7 +99,7 @@ pop %rbp pop %r12 pop %rbx - ret + RET

SYM_FUNC_END(\name) .endm diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S index 4739cd31b9db..3baa1ec39097 100644 --- a/arch/x86/crypto/sha256-avx-asm.S +++ b/arch/x86/crypto/sha256-avx-asm.S @@ -458,7 +458,7 @@ done_hash: popq %r13 popq %r12 popq %rbx - ret + RET SYM_FUNC_END(sha256_transform_avx)

.section .rodata.cst256.K256, "aM", @progbits, 256 diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 11ff60c29c8b..3439aaf4295d 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -711,7 +711,7 @@ done_hash: popq %r13 popq %r12 popq %rbx - ret + RET SYM_FUNC_END(sha256_transform_rorx)

.section .rodata.cst512.K256, "aM", @progbits, 512 diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S index ddfa863b4ee3..c4a5db612c32 100644 --- a/arch/x86/crypto/sha256-ssse3-asm.S +++ b/arch/x86/crypto/sha256-ssse3-asm.S @@ -472,7 +472,7 @@ done_hash: popq %r12 popq %rbx

- ret + RET SYM_FUNC_END(sha256_transform_ssse3)

.section .rodata.cst256.K256, "aM", @progbits, 256 diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S index 7abade04a3a3..94d50dd27cb5 100644 --- a/arch/x86/crypto/sha256_ni_asm.S +++ b/arch/x86/crypto/sha256_ni_asm.S @@ -326,7 +326,7 @@ SYM_FUNC_START(sha256_ni_transform)

.Ldone_hash:

- ret + RET SYM_FUNC_END(sha256_ni_transform)

.section .rodata.cst256.K256, "aM", @progbits, 256 diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S index 63470fd6ae32..34fc71c3524e 100644 --- a/arch/x86/crypto/sha512-avx-asm.S +++ b/arch/x86/crypto/sha512-avx-asm.S @@ -364,7 +364,7 @@ updateblock: mov frame_RSPSAVE(%rsp), %rsp

nowork: - ret + RET SYM_FUNC_END(sha512_transform_avx)

######################################################################## diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index 3a44bdcfd583..399fa74ab3d3 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -681,7 +681,7 @@ done_hash:

# Restore Stack Pointer mov frame_RSPSAVE(%rsp), %rsp - ret + RET SYM_FUNC_END(sha512_transform_rorx)

######################################################################## diff --git a/arch/x86/crypto/sha512-ssse3-asm.S b/arch/x86/crypto/sha512-ssse3-asm.S index 7946a1bee85b..e9b460a54503 100644 --- a/arch/x86/crypto/sha512-ssse3-asm.S +++ b/arch/x86/crypto/sha512-ssse3-asm.S @@ -366,7 +366,7 @@ updateblock: mov frame_RSPSAVE(%rsp), %rsp

nowork: - ret + RET SYM_FUNC_END(sha512_transform_ssse3)

######################################################################## diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S index a5151393bb2f..c3707a71ef72 100644 --- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S @@ -272,7 +272,7 @@ SYM_FUNC_START_LOCAL(__twofish_enc_blk8) outunpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2); outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);

- ret; + RET; SYM_FUNC_END(__twofish_enc_blk8)

.align 8 @@ -312,7 +312,7 @@ SYM_FUNC_START_LOCAL(__twofish_dec_blk8) outunpack_blocks(RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2); outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);

- ret; + RET; SYM_FUNC_END(__twofish_dec_blk8)

SYM_FUNC_START(twofish_ecb_enc_8way) @@ -332,7 +332,7 @@ SYM_FUNC_START(twofish_ecb_enc_8way) store_8way(%r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);

FRAME_END - ret; + RET; SYM_FUNC_END(twofish_ecb_enc_8way)

SYM_FUNC_START(twofish_ecb_dec_8way) @@ -352,7 +352,7 @@ SYM_FUNC_START(twofish_ecb_dec_8way) store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);

FRAME_END - ret; + RET; SYM_FUNC_END(twofish_ecb_dec_8way)

SYM_FUNC_START(twofish_cbc_dec_8way) @@ -377,7 +377,7 @@ SYM_FUNC_START(twofish_cbc_dec_8way) popq %r12;

FRAME_END - ret; + RET; SYM_FUNC_END(twofish_cbc_dec_8way)

SYM_FUNC_START(twofish_ctr_8way) @@ -404,7 +404,7 @@ SYM_FUNC_START(twofish_ctr_8way) popq %r12;

FRAME_END - ret; + RET; SYM_FUNC_END(twofish_ctr_8way)

SYM_FUNC_START(twofish_xts_enc_8way) @@ -428,7 +428,7 @@ SYM_FUNC_START(twofish_xts_enc_8way) store_xts_8way(%r11, RC1, RD1, RA1, RB1, RC2, RD2, RA2, RB2);

FRAME_END - ret; + RET; SYM_FUNC_END(twofish_xts_enc_8way)

SYM_FUNC_START(twofish_xts_dec_8way) @@ -452,5 +452,5 @@ SYM_FUNC_START(twofish_xts_dec_8way) store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);

FRAME_END - ret; + RET; SYM_FUNC_END(twofish_xts_dec_8way) diff --git a/arch/x86/crypto/twofish-i586-asm_32.S b/arch/x86/crypto/twofish-i586-asm_32.S index a6f09e4f2e46..3abcad661884 100644 --- a/arch/x86/crypto/twofish-i586-asm_32.S +++ b/arch/x86/crypto/twofish-i586-asm_32.S @@ -260,7 +260,7 @@ SYM_FUNC_START(twofish_enc_blk) pop %ebx pop %ebp mov $1, %eax - ret + RET SYM_FUNC_END(twofish_enc_blk)

SYM_FUNC_START(twofish_dec_blk) @@ -317,5 +317,5 @@ SYM_FUNC_START(twofish_dec_blk) pop %ebx pop %ebp mov $1, %eax - ret + RET SYM_FUNC_END(twofish_dec_blk) diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S index fc23552afe37..b12d916f08d6 100644 --- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S +++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S @@ -258,7 +258,7 @@ SYM_FUNC_START(__twofish_enc_blk_3way) popq %rbx; popq %r12; popq %r13; - ret; + RET;

.L__enc_xor3: outunpack_enc3(xor); @@ -266,7 +266,7 @@ SYM_FUNC_START(__twofish_enc_blk_3way) popq %rbx; popq %r12; popq %r13; - ret; + RET; SYM_FUNC_END(__twofish_enc_blk_3way)

SYM_FUNC_START(twofish_dec_blk_3way) @@ -301,5 +301,5 @@ SYM_FUNC_START(twofish_dec_blk_3way) popq %rbx; popq %r12; popq %r13; - ret; + RET; SYM_FUNC_END(twofish_dec_blk_3way) diff --git a/arch/x86/crypto/twofish-x86_64-asm_64.S b/arch/x86/crypto/twofish-x86_64-asm_64.S index d2e56232494a..775af290cd19 100644 --- a/arch/x86/crypto/twofish-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-x86_64-asm_64.S @@ -252,7 +252,7 @@ SYM_FUNC_START(twofish_enc_blk)

popq R1 movl $1,%eax - ret + RET SYM_FUNC_END(twofish_enc_blk)

SYM_FUNC_START(twofish_dec_blk) @@ -304,5 +304,5 @@ SYM_FUNC_START(twofish_dec_blk)

popq R1 movl $1,%eax - ret + RET SYM_FUNC_END(twofish_dec_blk) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 4e079f250962..4a4896ba4db3 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -821,7 +821,7 @@ SYM_FUNC_START(schedule_tail_wrapper) popl %eax

FRAME_END - ret + RET SYM_FUNC_END(schedule_tail_wrapper) .popsection

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a24ce5905ab8..cb9f63b5ba77 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -739,7 +739,7 @@ SYM_FUNC_START(asm_load_gs_index) 2: ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE swapgs FRAME_END - ret + RET SYM_FUNC_END(asm_load_gs_index) EXPORT_SYMBOL(asm_load_gs_index)

@@ -798,7 +798,7 @@ SYM_INNER_LABEL(asm_call_irq_on_stack, SYM_L_GLOBAL)

/* Restore the previous stack pointer from RBP. */ leaveq - ret + RET SYM_FUNC_END(asm_call_on_stack)

#ifdef CONFIG_XEN_PV @@ -931,7 +931,7 @@ SYM_CODE_START_LOCAL(paranoid_entry) * is needed here. */ SAVE_AND_SET_GSBASE scratch_reg=%rax save_reg=%rbx - ret + RET

.Lparanoid_entry_checkgs: /* EBX = 1 -> kernel GSBASE active, no restore required */ @@ -952,7 +952,7 @@ SYM_CODE_START_LOCAL(paranoid_entry) .Lparanoid_kernel_gsbase:

FENCE_SWAPGS_KERNEL_ENTRY - ret + RET SYM_CODE_END(paranoid_entry)

/* @@ -1031,7 +1031,7 @@ SYM_CODE_START_LOCAL(error_entry) movq %rax, %rsp /* switch stack */ ENCODE_FRAME_POINTER pushq %r12 - ret + RET

/* * There are two places in the kernel that can potentially fault with @@ -1062,7 +1062,7 @@ SYM_CODE_START_LOCAL(error_entry) */ .Lerror_entry_done_lfence: FENCE_SWAPGS_KERNEL_ENTRY - ret + RET

.Lbstep_iret: /* Fix truncated RIP */ diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S index f1f96d4d8cd6..7591bab060f7 100644 --- a/arch/x86/entry/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -24,7 +24,7 @@ SYM_CODE_START_NOALIGN(\name) popl %edx popl %ecx popl %eax - ret + RET _ASM_NOKPROBE(\name) SYM_CODE_END(\name) .endm diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index c9a9fbf1655f..1b5044ad8cd0 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -55,7 +55,7 @@ SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore) popq %rsi popq %rdi popq %rbp - ret + RET _ASM_NOKPROBE(__thunk_restore) SYM_CODE_END(__thunk_restore) #endif diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S index d6a6080bade0..c92a8fef2ed2 100644 --- a/arch/x86/entry/vdso/vdso32/system_call.S +++ b/arch/x86/entry/vdso/vdso32/system_call.S @@ -78,7 +78,7 @@ SYM_INNER_LABEL(int80_landing_pad, SYM_L_GLOBAL) popl %ecx CFI_RESTORE ecx CFI_ADJUST_CFA_OFFSET -4 - ret + RET CFI_ENDPROC

.size __kernel_vsyscall,.-__kernel_vsyscall diff --git a/arch/x86/entry/vsyscall/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S index 2e203f3a25a7..15e35159ebb6 100644 --- a/arch/x86/entry/vsyscall/vsyscall_emu_64.S +++ b/arch/x86/entry/vsyscall/vsyscall_emu_64.S @@ -19,17 +19,17 @@ __vsyscall_page:

mov $__NR_gettimeofday, %rax syscall - ret + RET

.balign 1024, 0xcc mov $__NR_time, %rax syscall - ret + RET

.balign 1024, 0xcc mov $__NR_getcpu, %rax syscall - ret + RET

.balign 4096, 0xcc

diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index daf88f8143c5..cf69081073b5 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -60,7 +60,7 @@ save_registers: popl saved_context_eflags

movl $ret_point, saved_eip - ret + RET

restore_registers: @@ -70,7 +70,7 @@ restore_registers: movl saved_context_edi, %edi pushl saved_context_eflags popfl - ret + RET

SYM_CODE_START(do_suspend_lowlevel) call save_processor_state @@ -86,7 +86,7 @@ SYM_CODE_START(do_suspend_lowlevel) ret_point: call restore_registers call restore_processor_state - ret + RET SYM_CODE_END(do_suspend_lowlevel)

.data diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index e405fe1a8bf4..a0ed0e4a2c0c 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -19,7 +19,7 @@ #endif

SYM_FUNC_START(__fentry__) - ret + RET SYM_FUNC_END(__fentry__) EXPORT_SYMBOL(__fentry__)

@@ -84,7 +84,7 @@ ftrace_graph_call:

/* This is weak to keep gas from relaxing the jumps */ SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) - ret + RET SYM_CODE_END(ftrace_caller)

SYM_CODE_START(ftrace_regs_caller) @@ -177,7 +177,7 @@ SYM_CODE_START(ftrace_graph_caller) popl %edx popl %ecx popl %eax - ret + RET SYM_CODE_END(ftrace_graph_caller)

.globl return_to_handler diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index ad1da5e85aeb..b656c11521a1 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -132,7 +132,7 @@ #ifdef CONFIG_DYNAMIC_FTRACE

SYM_FUNC_START(__fentry__) - retq + RET SYM_FUNC_END(__fentry__) EXPORT_SYMBOL(__fentry__)

@@ -170,10 +170,10 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)

/* * This is weak to keep gas from relaxing the jumps. - * It is also used to copy the retq for trampolines. + * It is also used to copy the RET for trampolines. */ SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK) - retq + RET SYM_FUNC_END(ftrace_epilogue)

SYM_FUNC_START(ftrace_regs_caller) @@ -287,7 +287,7 @@ fgraph_trace: #endif

SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL) - retq + RET

trace: /* save_mcount_regs fills in first two parameters */ @@ -319,7 +319,7 @@ SYM_FUNC_START(ftrace_graph_caller)

restore_mcount_regs

- retq + RET SYM_FUNC_END(ftrace_graph_caller)

SYM_CODE_START(return_to_handler) diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 7ed84c282233..9b2b1ac7e8c9 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -354,7 +354,7 @@ setup_once: #endif

andl $0,setup_once_ref /* Once is enough, thanks */ - ret + RET

SYM_FUNC_START(early_idt_handler_array) # 36(%esp) %eflags diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S index 0db0375235b4..a9c36400bdf8 100644 --- a/arch/x86/kernel/irqflags.S +++ b/arch/x86/kernel/irqflags.S @@ -10,7 +10,7 @@ SYM_FUNC_START(native_save_fl) pushf pop %_ASM_AX - ret + RET SYM_FUNC_END(native_save_fl) EXPORT_SYMBOL(native_save_fl)

@@ -21,6 +21,6 @@ EXPORT_SYMBOL(native_save_fl) SYM_FUNC_START(native_restore_fl) push %_ASM_ARG1 popf - ret + RET SYM_FUNC_END(native_restore_fl) EXPORT_SYMBOL(native_restore_fl) diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index 94b33885f8d2..8190136cc63a 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -91,7 +91,7 @@ SYM_CODE_START_NOALIGN(relocate_kernel) movl %edi, %eax addl $(identity_mapped - relocate_kernel), %eax pushl %eax - ret + RET SYM_CODE_END(relocate_kernel)

SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) @@ -159,7 +159,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) xorl %edx, %edx xorl %esi, %esi xorl %ebp, %ebp - ret + RET 1: popl %edx movl CP_PA_SWAP_PAGE(%edi), %esp @@ -190,7 +190,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) movl %edi, %eax addl $(virtual_mapped - relocate_kernel), %eax pushl %eax - ret + RET SYM_CODE_END(identity_mapped)

SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) @@ -208,7 +208,7 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) popl %edi popl %esi popl %ebx - ret + RET SYM_CODE_END(virtual_mapped)

/* Do the copies */ @@ -271,7 +271,7 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) popl %edi popl %ebx popl %ebp - ret + RET SYM_CODE_END(swap_pages)

.globl kexec_control_code_size diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index a4d9a261425b..a0ae167b1aeb 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -104,7 +104,7 @@ SYM_CODE_START_NOALIGN(relocate_kernel) /* jump to identity mapped page */ addq $(identity_mapped - relocate_kernel), %r8 pushq %r8 - ret + RET SYM_CODE_END(relocate_kernel)

SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) @@ -191,7 +191,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) xorl %r14d, %r14d xorl %r15d, %r15d

- ret + RET

1: popq %rdx @@ -210,7 +210,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) call swap_pages movq $virtual_mapped, %rax pushq %rax - ret + RET SYM_CODE_END(identity_mapped)

SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) @@ -231,7 +231,7 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) popq %r12 popq %rbp popq %rbx - ret + RET SYM_CODE_END(virtual_mapped)

/* Do the copies */ @@ -288,7 +288,7 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) lea PAGE_SIZE(%rax), %rsi jmp 0b 3: - ret + RET SYM_CODE_END(swap_pages)

.globl kexec_control_code_size diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S index ee04941a6546..3355e27c69eb 100644 --- a/arch/x86/kernel/sev_verify_cbit.S +++ b/arch/x86/kernel/sev_verify_cbit.S @@ -85,5 +85,5 @@ SYM_FUNC_START(sev_verify_cbit) #endif /* Return page-table pointer */ movq %rdi, %rax - ret + RET SYM_FUNC_END(sev_verify_cbit) diff --git a/arch/x86/kernel/verify_cpu.S b/arch/x86/kernel/verify_cpu.S index 641f0fe1e5b4..1258a5872d12 100644 --- a/arch/x86/kernel/verify_cpu.S +++ b/arch/x86/kernel/verify_cpu.S @@ -132,9 +132,9 @@ SYM_FUNC_START_LOCAL(verify_cpu) .Lverify_cpu_no_longmode: popf # Restore caller passed flags movl $1,%eax - ret + RET .Lverify_cpu_sse_ok: popf # Restore caller passed flags xorl %eax, %eax - ret + RET SYM_FUNC_END(verify_cpu) diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 1ec1ac40e328..6df5950d6967 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -166,5 +166,5 @@ SYM_FUNC_START(__svm_vcpu_run) pop %edi #endif pop %_ASM_BP - ret + RET SYM_FUNC_END(__svm_vcpu_run) diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 3a6461694fc2..435c187927c4 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -49,14 +49,14 @@ SYM_FUNC_START_LOCAL(vmx_vmenter) je 2f

1: vmresume - ret + RET

2: vmlaunch - ret + RET

3: cmpb $0, kvm_rebooting je 4f - ret + RET 4: ud2

_ASM_EXTABLE(1b, 3b) @@ -89,7 +89,7 @@ SYM_FUNC_START(vmx_vmexit) pop %_ASM_AX .Lvmexit_skip_rsb: #endif - ret + RET SYM_FUNC_END(vmx_vmexit)

/** @@ -228,7 +228,7 @@ SYM_FUNC_START(__vmx_vcpu_run) pop %edi #endif pop %_ASM_BP - ret + RET

/* VM-Fail. Out-of-line to avoid a taken Jcc after VM-Exit. */ 2: mov $1, %eax @@ -293,7 +293,7 @@ SYM_FUNC_START(vmread_error_trampoline) pop %_ASM_AX pop %_ASM_BP

- ret + RET SYM_FUNC_END(vmread_error_trampoline)

SYM_FUNC_START(vmx_do_interrupt_nmi_irqoff) @@ -326,5 +326,5 @@ SYM_FUNC_START(vmx_do_interrupt_nmi_irqoff) */ mov %_ASM_BP, %_ASM_SP pop %_ASM_BP - ret + RET SYM_FUNC_END(vmx_do_interrupt_nmi_irqoff) diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S index 4ad6b97fdb6f..e768815e58ae 100644 --- a/arch/x86/lib/atomic64_386_32.S +++ b/arch/x86/lib/atomic64_386_32.S @@ -30,7 +30,7 @@ SYM_FUNC_START(atomic64_##op##_386); \

#define RET_IRQ_RESTORE \ IRQ_RESTORE v; \ - ret + RET

#define v %ecx BEGIN_IRQ_SAVE(read) diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index ce6935690766..90afb488b396 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -18,7 +18,7 @@

SYM_FUNC_START(atomic64_read_cx8) read64 %ecx - ret + RET SYM_FUNC_END(atomic64_read_cx8)

SYM_FUNC_START(atomic64_set_cx8) @@ -28,7 +28,7 @@ SYM_FUNC_START(atomic64_set_cx8) cmpxchg8b (%esi) jne 1b

- ret + RET SYM_FUNC_END(atomic64_set_cx8)

SYM_FUNC_START(atomic64_xchg_cx8) @@ -37,7 +37,7 @@ SYM_FUNC_START(atomic64_xchg_cx8) cmpxchg8b (%esi) jne 1b

- ret + RET SYM_FUNC_END(atomic64_xchg_cx8)

.macro addsub_return func ins insc @@ -68,7 +68,7 @@ SYM_FUNC_START(atomic64_\func()_return_cx8) popl %esi popl %ebx popl %ebp - ret + RET SYM_FUNC_END(atomic64_\func()_return_cx8) .endm

@@ -93,7 +93,7 @@ SYM_FUNC_START(atomic64_\func()_return_cx8) movl %ebx, %eax movl %ecx, %edx popl %ebx - ret + RET SYM_FUNC_END(atomic64_\func()_return_cx8) .endm

@@ -118,7 +118,7 @@ SYM_FUNC_START(atomic64_dec_if_positive_cx8) movl %ebx, %eax movl %ecx, %edx popl %ebx - ret + RET SYM_FUNC_END(atomic64_dec_if_positive_cx8)

SYM_FUNC_START(atomic64_add_unless_cx8) @@ -149,7 +149,7 @@ SYM_FUNC_START(atomic64_add_unless_cx8) addl $8, %esp popl %ebx popl %ebp - ret + RET 4: cmpl %edx, 4(%esp) jne 2b @@ -176,5 +176,5 @@ SYM_FUNC_START(atomic64_inc_not_zero_cx8) movl $1, %eax 3: popl %ebx - ret + RET SYM_FUNC_END(atomic64_inc_not_zero_cx8) diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 4304320e51f4..929ad1747dea 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -127,7 +127,7 @@ SYM_FUNC_START(csum_partial) 8: popl %ebx popl %esi - ret + RET SYM_FUNC_END(csum_partial)

#else @@ -245,7 +245,7 @@ SYM_FUNC_START(csum_partial) 90: popl %ebx popl %esi - ret + RET SYM_FUNC_END(csum_partial) #endif @@ -371,7 +371,7 @@ EXC( movb %cl, (%edi) ) popl %esi popl %edi popl %ecx # equivalent to addl $4,%esp - ret + RET SYM_FUNC_END(csum_partial_copy_generic)

#else @@ -447,7 +447,7 @@ EXC( movb %dl, (%edi) ) popl %esi popl %edi popl %ebx - ret + RET SYM_FUNC_END(csum_partial_copy_generic) #undef ROUND diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index c4c7dd115953..fe59b8ac4fcc 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -17,7 +17,7 @@ SYM_FUNC_START(clear_page_rep) movl $4096/8,%ecx xorl %eax,%eax rep stosq - ret + RET SYM_FUNC_END(clear_page_rep) EXPORT_SYMBOL_GPL(clear_page_rep)

@@ -39,7 +39,7 @@ SYM_FUNC_START(clear_page_orig) leaq 64(%rdi),%rdi jnz .Lloop nop - ret + RET SYM_FUNC_END(clear_page_orig) EXPORT_SYMBOL_GPL(clear_page_orig)

@@ -47,6 +47,6 @@ SYM_FUNC_START(clear_page_erms) movl $4096,%ecx xorl %eax,%eax rep stosb - ret + RET SYM_FUNC_END(clear_page_erms) EXPORT_SYMBOL_GPL(clear_page_erms) diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S index 3542502faa3b..33c70c0160ea 100644 --- a/arch/x86/lib/cmpxchg16b_emu.S +++ b/arch/x86/lib/cmpxchg16b_emu.S @@ -37,11 +37,11 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu)

popfq mov $1, %al - ret + RET

.Lnot_same: popfq xor %al,%al - ret + RET

SYM_FUNC_END(this_cpu_cmpxchg16b_emu) diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S index ca01ed6029f4..6a912d58fecc 100644 --- a/arch/x86/lib/cmpxchg8b_emu.S +++ b/arch/x86/lib/cmpxchg8b_emu.S @@ -32,7 +32,7 @@ SYM_FUNC_START(cmpxchg8b_emu) movl %ecx, 4(%esi)

popfl - ret + RET

.Lnot_same: movl (%esi), %eax @@ -40,7 +40,7 @@ SYM_FUNC_START(cmpxchg8b_emu) movl 4(%esi), %edx

popfl - ret + RET

SYM_FUNC_END(cmpxchg8b_emu) EXPORT_SYMBOL(cmpxchg8b_emu) diff --git a/arch/x86/lib/copy_mc_64.S b/arch/x86/lib/copy_mc_64.S index 892d8915f609..fdd1929b1f9d 100644 --- a/arch/x86/lib/copy_mc_64.S +++ b/arch/x86/lib/copy_mc_64.S @@ -86,7 +86,7 @@ SYM_FUNC_START(copy_mc_fragile) .L_done_memcpy_trap: xorl %eax, %eax .L_done: - ret + RET SYM_FUNC_END(copy_mc_fragile) EXPORT_SYMBOL_GPL(copy_mc_fragile)

@@ -142,7 +142,7 @@ SYM_FUNC_START(copy_mc_enhanced_fast_string) rep movsb /* Copy successful. Return zero */ xorl %eax, %eax - ret + RET SYM_FUNC_END(copy_mc_enhanced_fast_string)

.section .fixup, "ax" @@ -155,7 +155,7 @@ SYM_FUNC_END(copy_mc_enhanced_fast_string) * user-copy routines. */ movq %rcx, %rax - ret + RET

.previous

diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index 0751592089e9..c31a9a79b18e 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -17,7 +17,7 @@ SYM_FUNC_START(copy_page) ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD movl $4096/8, %ecx rep movsq - ret + RET SYM_FUNC_END(copy_page) EXPORT_SYMBOL(copy_page)

@@ -85,7 +85,7 @@ SYM_FUNC_START_LOCAL(copy_page_regs) movq (%rsp), %rbx movq 1*8(%rsp), %r12 addq $2*8, %rsp - ret + RET SYM_FUNC_END(copy_page_regs)

SYM_FUNC_START(copy_page_nocache) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 57b79c577496..84cee84fc658 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -105,7 +105,7 @@ SYM_FUNC_START(copy_user_generic_unrolled) jnz 21b 23: xor %eax,%eax ASM_CLAC - ret + RET

.section .fixup,"ax" 30: shll $6,%ecx @@ -173,7 +173,7 @@ SYM_FUNC_START(copy_user_generic_string) movsb xorl %eax,%eax ASM_CLAC - ret + RET

.section .fixup,"ax" 11: leal (%rdx,%rcx,8),%ecx @@ -207,7 +207,7 @@ SYM_FUNC_START(copy_user_enhanced_fast_string) movsb xorl %eax,%eax ASM_CLAC - ret + RET

.section .fixup,"ax" 12: movl %ecx,%edx /* ecx is zerorest also */ @@ -239,7 +239,7 @@ SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail) 1: rep movsb 2: mov %ecx,%eax ASM_CLAC - ret + RET

/* * Return zero to pretend that this copy succeeded. This @@ -250,7 +250,7 @@ SYM_CODE_START_LOCAL(.Lcopy_user_handle_tail) */ 3: xorl %eax,%eax ASM_CLAC - ret + RET

_ASM_EXTABLE_CPY(1b, 2b) SYM_CODE_END(.Lcopy_user_handle_tail) @@ -361,7 +361,7 @@ SYM_FUNC_START(__copy_user_nocache) xorl %eax,%eax ASM_CLAC sfence - ret + RET

.section .fixup,"ax" .L_fixup_4x8b_copy: diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S index 1fbd8ee9642d..d9e16a2cf285 100644 --- a/arch/x86/lib/csum-copy_64.S +++ b/arch/x86/lib/csum-copy_64.S @@ -201,7 +201,7 @@ SYM_FUNC_START(csum_partial_copy_generic) movq 3*8(%rsp), %r13 movq 4*8(%rsp), %r15 addq $5*8, %rsp - ret + RET .Lshort: movl %ecx, %r10d jmp .L1 diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index fa1bc2104b32..b70d98d79a9d 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -57,7 +57,7 @@ SYM_FUNC_START(__get_user_1) 1: movzbl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_1) EXPORT_SYMBOL(__get_user_1)

@@ -71,7 +71,7 @@ SYM_FUNC_START(__get_user_2) 2: movzwl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_2) EXPORT_SYMBOL(__get_user_2)

@@ -85,7 +85,7 @@ SYM_FUNC_START(__get_user_4) 3: movl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_4) EXPORT_SYMBOL(__get_user_4)

@@ -100,7 +100,7 @@ SYM_FUNC_START(__get_user_8) 4: movq (%_ASM_AX),%rdx xor %eax,%eax ASM_CLAC - ret + RET #else LOAD_TASK_SIZE_MINUS_N(7) cmp %_ASM_DX,%_ASM_AX @@ -112,7 +112,7 @@ SYM_FUNC_START(__get_user_8) 5: movl 4(%_ASM_AX),%ecx xor %eax,%eax ASM_CLAC - ret + RET #endif SYM_FUNC_END(__get_user_8) EXPORT_SYMBOL(__get_user_8) @@ -124,7 +124,7 @@ SYM_FUNC_START(__get_user_nocheck_1) 6: movzbl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_nocheck_1) EXPORT_SYMBOL(__get_user_nocheck_1)

@@ -134,7 +134,7 @@ SYM_FUNC_START(__get_user_nocheck_2) 7: movzwl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_nocheck_2) EXPORT_SYMBOL(__get_user_nocheck_2)

@@ -144,7 +144,7 @@ SYM_FUNC_START(__get_user_nocheck_4) 8: movl (%_ASM_AX),%edx xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_nocheck_4) EXPORT_SYMBOL(__get_user_nocheck_4)

@@ -159,7 +159,7 @@ SYM_FUNC_START(__get_user_nocheck_8) #endif xor %eax,%eax ASM_CLAC - ret + RET SYM_FUNC_END(__get_user_nocheck_8) EXPORT_SYMBOL(__get_user_nocheck_8)

@@ -169,7 +169,7 @@ SYM_CODE_START_LOCAL(.Lbad_get_user_clac) bad_get_user: xor %edx,%edx mov $(-EFAULT),%_ASM_AX - ret + RET SYM_CODE_END(.Lbad_get_user_clac)

#ifdef CONFIG_X86_32 @@ -179,7 +179,7 @@ bad_get_user_8: xor %edx,%edx xor %ecx,%ecx mov $(-EFAULT),%_ASM_AX - ret + RET SYM_CODE_END(.Lbad_get_user_8_clac) #endif

diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S index dbf8cc97b7f5..12c16c6aa44a 100644 --- a/arch/x86/lib/hweight.S +++ b/arch/x86/lib/hweight.S @@ -32,7 +32,7 @@ SYM_FUNC_START(__sw_hweight32) imull $0x01010101, %eax, %eax # w_tmp *= 0x01010101 shrl $24, %eax # w = w_tmp >> 24 __ASM_SIZE(pop,) %__ASM_REG(dx) - ret + RET SYM_FUNC_END(__sw_hweight32) EXPORT_SYMBOL(__sw_hweight32)

@@ -65,7 +65,7 @@ SYM_FUNC_START(__sw_hweight64)

popq %rdx popq %rdi - ret + RET #else /* CONFIG_X86_32 */ /* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */ pushl %ecx @@ -77,7 +77,7 @@ SYM_FUNC_START(__sw_hweight64) addl %ecx, %eax # result

popl %ecx - ret + RET #endif SYM_FUNC_END(__sw_hweight64) EXPORT_SYMBOL(__sw_hweight64) diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S index cb5a1964506b..a1f9416bf67a 100644 --- a/arch/x86/lib/iomap_copy_64.S +++ b/arch/x86/lib/iomap_copy_64.S @@ -11,5 +11,5 @@ SYM_FUNC_START(__iowrite32_copy) movl %edx,%ecx rep movsd - ret + RET SYM_FUNC_END(__iowrite32_copy) diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 1cc9da6e29c7..59cf2343f3d9 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -39,7 +39,7 @@ SYM_FUNC_START_WEAK(memcpy) rep movsq movl %edx, %ecx rep movsb - ret + RET SYM_FUNC_END(memcpy) SYM_FUNC_END_ALIAS(__memcpy) EXPORT_SYMBOL(memcpy) @@ -53,7 +53,7 @@ SYM_FUNC_START_LOCAL(memcpy_erms) movq %rdi, %rax movq %rdx, %rcx rep movsb - ret + RET SYM_FUNC_END(memcpy_erms)

SYM_FUNC_START_LOCAL(memcpy_orig) @@ -137,7 +137,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movq %r9, 1*8(%rdi) movq %r10, -2*8(%rdi, %rdx) movq %r11, -1*8(%rdi, %rdx) - retq + RET .p2align 4 .Lless_16bytes: cmpl $8, %edx @@ -149,7 +149,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movq -1*8(%rsi, %rdx), %r9 movq %r8, 0*8(%rdi) movq %r9, -1*8(%rdi, %rdx) - retq + RET .p2align 4 .Lless_8bytes: cmpl $4, %edx @@ -162,7 +162,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movl -4(%rsi, %rdx), %r8d movl %ecx, (%rdi) movl %r8d, -4(%rdi, %rdx) - retq + RET .p2align 4 .Lless_3bytes: subl $1, %edx @@ -180,7 +180,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movb %cl, (%rdi)

.Lend: - retq + RET SYM_FUNC_END(memcpy_orig)

.popsection diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 64801010d312..e84d649620c4 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -40,7 +40,7 @@ SYM_FUNC_START(__memmove) /* FSRM implies ERMS => no length checks, do the copy directly */ .Lmemmove_begin_forward: ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM - ALTERNATIVE "", "movq %rdx, %rcx; rep movsb; retq", X86_FEATURE_ERMS + ALTERNATIVE "", "movq %rdx, %rcx; rep movsb; RET", X86_FEATURE_ERMS

/* * movsq instruction have many startup latency @@ -205,7 +205,7 @@ SYM_FUNC_START(__memmove) movb (%rsi), %r11b movb %r11b, (%rdi) 13: - retq + RET SYM_FUNC_END(__memmove) SYM_FUNC_END_ALIAS(memmove) EXPORT_SYMBOL(__memmove) diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 9827ae267f96..d624f2bc42f1 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -40,7 +40,7 @@ SYM_FUNC_START(__memset) movl %edx,%ecx rep stosb movq %r9,%rax - ret + RET SYM_FUNC_END(__memset) SYM_FUNC_END_ALIAS(memset) EXPORT_SYMBOL(memset) @@ -63,7 +63,7 @@ SYM_FUNC_START_LOCAL(memset_erms) movq %rdx,%rcx rep stosb movq %r9,%rax - ret + RET SYM_FUNC_END(memset_erms)

SYM_FUNC_START_LOCAL(memset_orig) @@ -125,7 +125,7 @@ SYM_FUNC_START_LOCAL(memset_orig)

.Lende: movq %r10,%rax - ret + RET

.Lbad_alignment: cmpq $7,%rdx diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S index a2b9caa5274c..ebd259f31496 100644 --- a/arch/x86/lib/msr-reg.S +++ b/arch/x86/lib/msr-reg.S @@ -35,7 +35,7 @@ SYM_FUNC_START(\op()_safe_regs) movl %edi, 28(%r10) popq %r12 popq %rbx - ret + RET 3: movl $-EIO, %r11d jmp 2b @@ -77,7 +77,7 @@ SYM_FUNC_START(\op()_safe_regs) popl %esi popl %ebp popl %ebx - ret + RET 3: movl $-EIO, 4(%esp) jmp 2b diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index 0ea344c5ea43..ecb2049c1273 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -52,7 +52,7 @@ SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL) 1: movb %al,(%_ASM_CX) xor %ecx,%ecx ASM_CLAC - ret + RET SYM_FUNC_END(__put_user_1) EXPORT_SYMBOL(__put_user_1) EXPORT_SYMBOL(__put_user_nocheck_1) @@ -66,7 +66,7 @@ SYM_INNER_LABEL(__put_user_nocheck_2, SYM_L_GLOBAL) 2: movw %ax,(%_ASM_CX) xor %ecx,%ecx ASM_CLAC - ret + RET SYM_FUNC_END(__put_user_2) EXPORT_SYMBOL(__put_user_2) EXPORT_SYMBOL(__put_user_nocheck_2) @@ -80,7 +80,7 @@ SYM_INNER_LABEL(__put_user_nocheck_4, SYM_L_GLOBAL) 3: movl %eax,(%_ASM_CX) xor %ecx,%ecx ASM_CLAC - ret + RET SYM_FUNC_END(__put_user_4) EXPORT_SYMBOL(__put_user_4) EXPORT_SYMBOL(__put_user_nocheck_4) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 6565c6f86160..8904c076a1df 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -23,7 +23,7 @@ .Ldo_rop_@: mov %\reg, (%_ASM_SP) UNWIND_HINT_FUNC - ret + RET .endm

.macro THUNK reg diff --git a/arch/x86/math-emu/div_Xsig.S b/arch/x86/math-emu/div_Xsig.S index 951da2ad54bb..8c270ab415be 100644 --- a/arch/x86/math-emu/div_Xsig.S +++ b/arch/x86/math-emu/div_Xsig.S @@ -341,7 +341,7 @@ L_exit: popl %esi

leave - ret + RET

#ifdef PARANOID diff --git a/arch/x86/math-emu/div_small.S b/arch/x86/math-emu/div_small.S index d047d1816abe..637439bfefa4 100644 --- a/arch/x86/math-emu/div_small.S +++ b/arch/x86/math-emu/div_small.S @@ -44,5 +44,5 @@ SYM_FUNC_START(FPU_div_small) popl %esi

leave - ret + RET SYM_FUNC_END(FPU_div_small) diff --git a/arch/x86/math-emu/mul_Xsig.S b/arch/x86/math-emu/mul_Xsig.S index 4afc7b1fa6e9..54a031b66142 100644 --- a/arch/x86/math-emu/mul_Xsig.S +++ b/arch/x86/math-emu/mul_Xsig.S @@ -62,7 +62,7 @@ SYM_FUNC_START(mul32_Xsig)

popl %esi leave - ret + RET SYM_FUNC_END(mul32_Xsig)

@@ -115,7 +115,7 @@ SYM_FUNC_START(mul64_Xsig)

popl %esi leave - ret + RET SYM_FUNC_END(mul64_Xsig)

@@ -175,5 +175,5 @@ SYM_FUNC_START(mul_Xsig_Xsig)

popl %esi leave - ret + RET SYM_FUNC_END(mul_Xsig_Xsig) diff --git a/arch/x86/math-emu/polynom_Xsig.S b/arch/x86/math-emu/polynom_Xsig.S index 702315eecb86..35fd723fc0df 100644 --- a/arch/x86/math-emu/polynom_Xsig.S +++ b/arch/x86/math-emu/polynom_Xsig.S @@ -133,5 +133,5 @@ L_accum_done: popl %edi popl %esi leave - ret + RET SYM_FUNC_END(polynomial_Xsig) diff --git a/arch/x86/math-emu/reg_norm.S b/arch/x86/math-emu/reg_norm.S index cad1d60b1e84..594936eeed67 100644 --- a/arch/x86/math-emu/reg_norm.S +++ b/arch/x86/math-emu/reg_norm.S @@ -72,7 +72,7 @@ L_exit_valid: L_exit: popl %ebx leave - ret + RET

L_zero: @@ -138,7 +138,7 @@ L_exit_nuo_valid:

popl %ebx leave - ret + RET

L_exit_nuo_zero: movl TAG_Zero,%eax @@ -146,5 +146,5 @@ L_exit_nuo_zero:

popl %ebx leave - ret + RET SYM_FUNC_END(FPU_normalize_nuo) diff --git a/arch/x86/math-emu/reg_round.S b/arch/x86/math-emu/reg_round.S index 11a1f798451b..8bdbdcee7456 100644 --- a/arch/x86/math-emu/reg_round.S +++ b/arch/x86/math-emu/reg_round.S @@ -437,7 +437,7 @@ fpu_Arith_exit: popl %edi popl %esi leave - ret + RET

/* diff --git a/arch/x86/math-emu/reg_u_add.S b/arch/x86/math-emu/reg_u_add.S index 9c9e2c810afe..07247287a3af 100644 --- a/arch/x86/math-emu/reg_u_add.S +++ b/arch/x86/math-emu/reg_u_add.S @@ -164,6 +164,6 @@ L_exit: popl %edi popl %esi leave - ret + RET #endif /* PARANOID */ SYM_FUNC_END(FPU_u_add) diff --git a/arch/x86/math-emu/reg_u_div.S b/arch/x86/math-emu/reg_u_div.S index e2fb5c2644c5..b5a41e2fc484 100644 --- a/arch/x86/math-emu/reg_u_div.S +++ b/arch/x86/math-emu/reg_u_div.S @@ -468,7 +468,7 @@ L_exit: popl %esi

leave - ret + RET #endif /* PARANOID */

SYM_FUNC_END(FPU_u_div) diff --git a/arch/x86/math-emu/reg_u_mul.S b/arch/x86/math-emu/reg_u_mul.S index 0c779c87ac5b..e2588b24b8c2 100644 --- a/arch/x86/math-emu/reg_u_mul.S +++ b/arch/x86/math-emu/reg_u_mul.S @@ -144,7 +144,7 @@ L_exit: popl %edi popl %esi leave - ret + RET #endif /* PARANOID */

SYM_FUNC_END(FPU_u_mul) diff --git a/arch/x86/math-emu/reg_u_sub.S b/arch/x86/math-emu/reg_u_sub.S index e9bb7c248649..4c900c29e4ff 100644 --- a/arch/x86/math-emu/reg_u_sub.S +++ b/arch/x86/math-emu/reg_u_sub.S @@ -270,5 +270,5 @@ L_exit: popl %edi popl %esi leave - ret + RET SYM_FUNC_END(FPU_u_sub) diff --git a/arch/x86/math-emu/round_Xsig.S b/arch/x86/math-emu/round_Xsig.S index d9d7de8dbd7b..126c40473bad 100644 --- a/arch/x86/math-emu/round_Xsig.S +++ b/arch/x86/math-emu/round_Xsig.S @@ -78,7 +78,7 @@ L_exit: popl %esi popl %ebx leave - ret + RET SYM_FUNC_END(round_Xsig)

@@ -138,5 +138,5 @@ L_n_exit: popl %esi popl %ebx leave - ret + RET SYM_FUNC_END(norm_Xsig) diff --git a/arch/x86/math-emu/shr_Xsig.S b/arch/x86/math-emu/shr_Xsig.S index 726af985f758..f726bf6f6396 100644 --- a/arch/x86/math-emu/shr_Xsig.S +++ b/arch/x86/math-emu/shr_Xsig.S @@ -45,7 +45,7 @@ SYM_FUNC_START(shr_Xsig) popl %ebx popl %esi leave - ret + RET

L_more_than_31: cmpl $64,%ecx @@ -61,7 +61,7 @@ L_more_than_31: movl $0,8(%esi) popl %esi leave - ret + RET

L_more_than_63: cmpl $96,%ecx @@ -76,7 +76,7 @@ L_more_than_63: movl %edx,8(%esi) popl %esi leave - ret + RET

L_more_than_95: xorl %eax,%eax @@ -85,5 +85,5 @@ L_more_than_95: movl %eax,8(%esi) popl %esi leave - ret + RET SYM_FUNC_END(shr_Xsig) diff --git a/arch/x86/math-emu/wm_shrx.S b/arch/x86/math-emu/wm_shrx.S index 4fc89174caf0..f608a28a4c43 100644 --- a/arch/x86/math-emu/wm_shrx.S +++ b/arch/x86/math-emu/wm_shrx.S @@ -55,7 +55,7 @@ SYM_FUNC_START(FPU_shrx) popl %ebx popl %esi leave - ret + RET

L_more_than_31: cmpl $64,%ecx @@ -70,7 +70,7 @@ L_more_than_31: movl $0,4(%esi) popl %esi leave - ret + RET

L_more_than_63: cmpl $96,%ecx @@ -84,7 +84,7 @@ L_more_than_63: movl %edx,4(%esi) popl %esi leave - ret + RET

L_more_than_95: xorl %eax,%eax @@ -92,7 +92,7 @@ L_more_than_95: movl %eax,4(%esi) popl %esi leave - ret + RET SYM_FUNC_END(FPU_shrx)

@@ -146,7 +146,7 @@ SYM_FUNC_START(FPU_shrxs) popl %ebx popl %esi leave - ret + RET

/* Shift by [0..31] bits */ Ls_less_than_32: @@ -163,7 +163,7 @@ Ls_less_than_32: popl %ebx popl %esi leave - ret + RET

/* Shift by [64..95] bits */ Ls_more_than_63: @@ -189,7 +189,7 @@ Ls_more_than_63: popl %ebx popl %esi leave - ret + RET

Ls_more_than_95: /* Shift by [96..inf) bits */ @@ -203,5 +203,5 @@ Ls_more_than_95: popl %ebx popl %esi leave - ret + RET SYM_FUNC_END(FPU_shrxs) diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 7a84fc8bc5c3..3c2bc5562fc2 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -65,7 +65,7 @@ SYM_FUNC_START(sme_encrypt_execute) movq %rbp, %rsp /* Restore original stack pointer */ pop %rbp

- ret + RET SYM_FUNC_END(sme_encrypt_execute)

SYM_FUNC_START(__enc_copy) @@ -151,6 +151,6 @@ SYM_FUNC_START(__enc_copy) pop %r12 pop %r15

- ret + RET .L__enc_copy_end: SYM_FUNC_END(__enc_copy) diff --git a/arch/x86/platform/efi/efi_stub_32.S b/arch/x86/platform/efi/efi_stub_32.S index 09ec84f6ef51..f3cfdb1c9a35 100644 --- a/arch/x86/platform/efi/efi_stub_32.S +++ b/arch/x86/platform/efi/efi_stub_32.S @@ -56,5 +56,5 @@ SYM_FUNC_START(efi_call_svam)

movl 16(%esp), %ebx leave - ret + RET SYM_FUNC_END(efi_call_svam) diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index 90380a17ab23..2206b8bc47b8 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -23,5 +23,5 @@ SYM_FUNC_START(__efi_call) mov %rsi, %rcx CALL_NOSPEC rdi leave - ret + RET SYM_FUNC_END(__efi_call) diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S index 26f0da238c1c..063eb27c0a12 100644 --- a/arch/x86/platform/efi/efi_thunk_64.S +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -63,7 +63,7 @@ SYM_CODE_START(__efi64_thunk) 1: movq 24(%rsp), %rsp pop %rbx pop %rbp - retq + RET

.code32 2: pushl $__KERNEL_CS diff --git a/arch/x86/platform/olpc/xo1-wakeup.S b/arch/x86/platform/olpc/xo1-wakeup.S index 75f4faff8468..3a5abffe5660 100644 --- a/arch/x86/platform/olpc/xo1-wakeup.S +++ b/arch/x86/platform/olpc/xo1-wakeup.S @@ -77,7 +77,7 @@ save_registers: pushfl popl saved_context_eflags

- ret + RET

restore_registers: movl saved_context_ebp, %ebp @@ -88,7 +88,7 @@ restore_registers: pushl saved_context_eflags popfl

- ret + RET

SYM_CODE_START(do_olpc_suspend_lowlevel) call save_processor_state @@ -109,7 +109,7 @@ ret_point:

call restore_registers call restore_processor_state - ret + RET SYM_CODE_END(do_olpc_suspend_lowlevel)

.data diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S index 8786653ad3c0..5606a15cf9a1 100644 --- a/arch/x86/power/hibernate_asm_32.S +++ b/arch/x86/power/hibernate_asm_32.S @@ -32,7 +32,7 @@ SYM_FUNC_START(swsusp_arch_suspend) FRAME_BEGIN call swsusp_save FRAME_END - ret + RET SYM_FUNC_END(swsusp_arch_suspend)

SYM_CODE_START(restore_image) @@ -108,5 +108,5 @@ SYM_FUNC_START(restore_registers) /* tell the hibernation core that we've just restored the memory */ movl %eax, in_suspend

- ret + RET SYM_FUNC_END(restore_registers) diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 7918b8415f13..3ae7a3d7d61e 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -49,7 +49,7 @@ SYM_FUNC_START(swsusp_arch_suspend) FRAME_BEGIN call swsusp_save FRAME_END - ret + RET SYM_FUNC_END(swsusp_arch_suspend)

SYM_CODE_START(restore_image) @@ -143,5 +143,5 @@ SYM_FUNC_START(restore_registers) /* tell the hibernation core that we've just restored the memory */ movq %rax, in_suspend(%rip)

- ret + RET SYM_FUNC_END(restore_registers) diff --git a/arch/x86/um/checksum_32.S b/arch/x86/um/checksum_32.S index 13f118dec74f..aed782ab7721 100644 --- a/arch/x86/um/checksum_32.S +++ b/arch/x86/um/checksum_32.S @@ -110,7 +110,7 @@ csum_partial: 7: popl %ebx popl %esi - ret + RET

#else

@@ -208,7 +208,7 @@ csum_partial: 80: popl %ebx popl %esi - ret + RET #endif EXPORT_SYMBOL(csum_partial) diff --git a/arch/x86/um/setjmp_32.S b/arch/x86/um/setjmp_32.S index 62eaf8c80e04..2d991ddbcca5 100644 --- a/arch/x86/um/setjmp_32.S +++ b/arch/x86/um/setjmp_32.S @@ -34,7 +34,7 @@ kernel_setjmp: movl %esi,12(%edx) movl %edi,16(%edx) movl %ecx,20(%edx) # Return address - ret + RET

.size kernel_setjmp,.-kernel_setjmp

diff --git a/arch/x86/um/setjmp_64.S b/arch/x86/um/setjmp_64.S index 1b5d40d4ff46..b46acb6a8ebd 100644 --- a/arch/x86/um/setjmp_64.S +++ b/arch/x86/um/setjmp_64.S @@ -33,7 +33,7 @@ kernel_setjmp: movq %r14,40(%rdi) movq %r15,48(%rdi) movq %rsi,56(%rdi) # Return address - ret + RET

.size kernel_setjmp,.-kernel_setjmp

diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index e75f60a06056..e8854f3b9a9f 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -45,7 +45,7 @@ SYM_FUNC_START(xen_irq_enable_direct) call check_events 1: FRAME_END - ret + RET SYM_FUNC_END(xen_irq_enable_direct)

@@ -55,7 +55,7 @@ SYM_FUNC_END(xen_irq_enable_direct) */ SYM_FUNC_START(xen_irq_disable_direct) movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask - ret + RET SYM_FUNC_END(xen_irq_disable_direct)

/* @@ -71,7 +71,7 @@ SYM_FUNC_START(xen_save_fl_direct) testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask setz %ah addb %ah, %ah - ret + RET SYM_FUNC_END(xen_save_fl_direct)

@@ -98,7 +98,7 @@ SYM_FUNC_START(xen_restore_fl_direct) call check_events 1: FRAME_END - ret + RET SYM_FUNC_END(xen_restore_fl_direct)

@@ -128,7 +128,7 @@ SYM_FUNC_START(check_events) pop %rcx pop %rax FRAME_END - ret + RET SYM_FUNC_END(check_events)

SYM_FUNC_START(xen_read_cr2) @@ -136,14 +136,14 @@ SYM_FUNC_START(xen_read_cr2) _ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX _ASM_MOV XEN_vcpu_info_arch_cr2(%_ASM_AX), %_ASM_AX FRAME_END - ret + RET SYM_FUNC_END(xen_read_cr2);

SYM_FUNC_START(xen_read_cr2_direct) FRAME_BEGIN _ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX FRAME_END - ret + RET SYM_FUNC_END(xen_read_cr2_direct);

.macro xen_pv_trap name diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index cb6538ae2fe0..565062932ef1 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -70,7 +70,7 @@ SYM_CODE_START(hypercall_page) .rept (PAGE_SIZE / 32) UNWIND_HINT_FUNC .skip 31, 0x90 - ret + RET .endr

#define HYPERCALL(n) \

From: Lin Yujun linyujun809@huawei.com

Offering: HULK hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

--------------------------------

fix these build warning arch/x86/lib/copy_page_64.o: warning: objtool: copy_page_nocache()+0xdf: 'naked' return found in RETHUNK build arch/x86/lib/copy_page_64.o: warning: objtool: copy_page_nocache_barrir()+0x3: 'naked' return found in RETHUNK build

The reference 5.10-stable branch patches are as follows: 3c91e2257622 x86: Prepare asm files for straight-line-speculation

Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/lib/copy_page_64.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index c31a9a79b18e..71c9c91e20b2 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -153,10 +153,10 @@ SYM_FUNC_START(copy_page_nocache) movq (%rsp), %rbx movq 1*8(%rsp), %r12 addq $2*8, %rsp - ret + RET SYM_FUNC_END(copy_page_nocache)

SYM_FUNC_START(copy_page_nocache_barrir) ALTERNATIVE "", "sfence", X86_FEATURE_XMM2 - ret + RET SYM_FUNC_END(copy_page_nocache_barrir)

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 0f8532c2837793acdaa07c6b47fda0bf1fa61f40 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 1cc1e4c8aab4213bd4e6353dec2620476a233d6d upstream.

Teach objtool to validate the straight-line-speculation constraints:

- speculation trap after indirect calls - speculation trap after RET

Notable: when an instruction is annotated RETPOLINE_SAFE, indicating speculation isn't a problem, also don't care about sls for that instruction.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Link: https://lore.kernel.org/r/20211204134908.023037659@infradead.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org [bwh: Backported to 5.10: adjust filenames, context] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/arch.h | 1 + tools/objtool/arch/x86/decode.c | 13 +++++++++---- tools/objtool/builtin-check.c | 4 +++- tools/objtool/builtin.h | 3 ++- tools/objtool/check.c | 14 ++++++++++++++ 5 files changed, 29 insertions(+), 6 deletions(-)

diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index 0031a27b6ad0..e15f6e932b4f 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -26,6 +26,7 @@ enum insn_type { INSN_CLAC, INSN_STD, INSN_CLD, + INSN_TRAP, INSN_OTHER, };

diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 32a810429306..f7154241a2a5 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -456,6 +456,11 @@ int arch_decode_instruction(const struct elf *elf, const struct section *sec,

break;

+ case 0xcc: + /* int3 */ + *type = INSN_TRAP; + break; + case 0xe3: /* jecxz/jrcxz */ *type = INSN_JUMP_CONDITIONAL; @@ -592,10 +597,10 @@ const char *arch_ret_insn(int len) { static const char ret[5][5] = { { BYTE_RET }, - { BYTE_RET, 0x90 }, - { BYTE_RET, 0x66, 0x90 }, - { BYTE_RET, 0x0f, 0x1f, 0x00 }, - { BYTE_RET, 0x0f, 0x1f, 0x40, 0x00 }, + { BYTE_RET, 0xcc }, + { BYTE_RET, 0xcc, 0x90 }, + { BYTE_RET, 0xcc, 0x66, 0x90 }, + { BYTE_RET, 0xcc, 0x0f, 0x1f, 0x00 }, };

if (len < 1 || len > 5) { diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index c6d199bfd0ae..758baf918d83 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -18,7 +18,8 @@ #include "builtin.h" #include "objtool.h"

-bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, validate_dup, vmlinux; +bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, + validate_dup, vmlinux, sls;

static const char * const check_usage[] = { "objtool check [<options>] file.o", @@ -35,6 +36,7 @@ const struct option check_options[] = { OPT_BOOLEAN('s', "stats", &stats, "print statistics"), OPT_BOOLEAN('d', "duplicate", &validate_dup, "duplicate validation for vmlinux.o"), OPT_BOOLEAN('l', "vmlinux", &vmlinux, "vmlinux.o validation"), + OPT_BOOLEAN('S', "sls", &sls, "validate straight-line-speculation"), OPT_END(), };

diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h index 85c979caa367..33043fcb16db 100644 --- a/tools/objtool/builtin.h +++ b/tools/objtool/builtin.h @@ -8,7 +8,8 @@ #include <subcmd/parse-options.h>

extern const struct option check_options[]; -extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, validate_dup, vmlinux; +extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, + validate_dup, vmlinux, sls;

extern int cmd_check(int argc, const char **argv); extern int cmd_orc(int argc, const char **argv); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 09e7807f83ee..9943987b24a9 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2775,6 +2775,12 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, switch (insn->type) {

case INSN_RETURN: + if (next_insn && next_insn->type == INSN_TRAP) { + next_insn->ignore = true; + } else if (sls && !insn->retpoline_safe) { + WARN_FUNC("missing int3 after ret", + insn->sec, insn->offset); + } return validate_return(func, insn, &state);

case INSN_CALL: @@ -2818,6 +2824,14 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, break;

case INSN_JUMP_DYNAMIC: + if (next_insn && next_insn->type == INSN_TRAP) { + next_insn->ignore = true; + } else if (sls && !insn->retpoline_safe) { + WARN_FUNC("missing int3 after indirect jump", + insn->sec, insn->offset); + } + + /* fallthrough */ case INSN_JUMP_DYNAMIC_CONDITIONAL: if (is_sibling_call(insn)) { ret = validate_sibling_call(insn, &state);

From: Arnaldo Carvalho de Melo acme@redhat.com

stable inclusion from stable-v5.10.133 commit 494ed76c1446b67621b1c55b8b2dceb5c6dfee64 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 35cb8c713a496e8c114eed5e2a5a30b359876df2 upstream.

To bring in the change made in this cset:

f94909ceb1ed4bfd ("x86: Prepare asm files for straight-line-speculation")

It silences these perf tools build warnings, no change in the tools:

Warning: Kernel ABI header at 'tools/arch/x86/lib/memcpy_64.S' differs from latest version at 'arch/x86/lib/memcpy_64.S' diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S Warning: Kernel ABI header at 'tools/arch/x86/lib/memset_64.S' differs from latest version at 'arch/x86/lib/memset_64.S' diff -u tools/arch/x86/lib/memset_64.S arch/x86/lib/memset_64.S

The code generated was checked before and after using 'objdump -d /tmp/build/perf/bench/mem-memcpy-x86-64-asm.o', no changes.

Cc: Borislav Petkov bp@suse.de Cc: Peter Zijlstra peterz@infradead.org Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/arch/x86/lib/memcpy_64.S | 12 ++++++------ tools/arch/x86/lib/memset_64.S | 6 +++--- 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 1e299ac73c86..644da05e5e71 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -39,7 +39,7 @@ SYM_FUNC_START_WEAK(memcpy) rep movsq movl %edx, %ecx rep movsb - ret + RET SYM_FUNC_END(memcpy) SYM_FUNC_END_ALIAS(__memcpy) EXPORT_SYMBOL(memcpy) @@ -53,7 +53,7 @@ SYM_FUNC_START_LOCAL(memcpy_erms) movq %rdi, %rax movq %rdx, %rcx rep movsb - ret + RET SYM_FUNC_END(memcpy_erms)

SYM_FUNC_START_LOCAL(memcpy_orig) @@ -137,7 +137,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movq %r9, 1*8(%rdi) movq %r10, -2*8(%rdi, %rdx) movq %r11, -1*8(%rdi, %rdx) - retq + RET .p2align 4 .Lless_16bytes: cmpl $8, %edx @@ -149,7 +149,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movq -1*8(%rsi, %rdx), %r9 movq %r8, 0*8(%rdi) movq %r9, -1*8(%rdi, %rdx) - retq + RET .p2align 4 .Lless_8bytes: cmpl $4, %edx @@ -162,7 +162,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movl -4(%rsi, %rdx), %r8d movl %ecx, (%rdi) movl %r8d, -4(%rdi, %rdx) - retq + RET .p2align 4 .Lless_3bytes: subl $1, %edx @@ -180,7 +180,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig) movb %cl, (%rdi)

.Lend: - retq + RET SYM_FUNC_END(memcpy_orig)

.popsection diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S index 0bfd26e4ca9e..4d793ff820e2 100644 --- a/tools/arch/x86/lib/memset_64.S +++ b/tools/arch/x86/lib/memset_64.S @@ -40,7 +40,7 @@ SYM_FUNC_START(__memset) movl %edx,%ecx rep stosb movq %r9,%rax - ret + RET SYM_FUNC_END(__memset) SYM_FUNC_END_ALIAS(memset) EXPORT_SYMBOL(memset) @@ -63,7 +63,7 @@ SYM_FUNC_START_LOCAL(memset_erms) movq %rdx,%rcx rep stosb movq %r9,%rax - ret + RET SYM_FUNC_END(memset_erms)

SYM_FUNC_START_LOCAL(memset_orig) @@ -125,7 +125,7 @@ SYM_FUNC_START_LOCAL(memset_orig)

.Lende: movq %r10,%rax - ret + RET

.Lbad_alignment: cmpq $7,%rdx

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 03c5c33e043e77a1a848c52f37c512efb412f2c3 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 1ffbe4e935f9b7308615c75be990aec07464d1e7 upstream.

Ignore all INT3 instructions for unreachable code warnings, similar to NOP. This allows using INT3 for various paddings instead of NOPs.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Acked-by: Josh Poimboeuf jpoimboe@redhat.com Link: https://lore.kernel.org/r/20220308154317.343312938@infradead.org Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/check.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 9943987b24a9..fdf96eef6e00 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2775,9 +2775,8 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, switch (insn->type) {

case INSN_RETURN: - if (next_insn && next_insn->type == INSN_TRAP) { - next_insn->ignore = true; - } else if (sls && !insn->retpoline_safe) { + if (sls && !insn->retpoline_safe && + next_insn && next_insn->type != INSN_TRAP) { WARN_FUNC("missing int3 after ret", insn->sec, insn->offset); } @@ -2824,9 +2823,8 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, break;

case INSN_JUMP_DYNAMIC: - if (next_insn && next_insn->type == INSN_TRAP) { - next_insn->ignore = true; - } else if (sls && !insn->retpoline_safe) { + if (sls && !insn->retpoline_safe && + next_insn && next_insn->type != INSN_TRAP) { WARN_FUNC("missing int3 after indirect jump", insn->sec, insn->offset); } @@ -2997,7 +2995,7 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio int i; struct instruction *prev_insn;

- if (insn->ignore || insn->type == INSN_NOP) + if (insn->ignore || insn->type == INSN_NOP || insn->type == INSN_TRAP) return true;

/*

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 831d5c07b7e7c6eab9df64ae328bacb5a6a0313a category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 7a53f408902d913cd541b4f8ad7dbcd4961f5b82 upstream.

Since not all compilers have a function attribute to disable KCOV instrumentation, objtool can rewrite KCOV instrumentation in noinstr functions as per commit:

f56dae88a81f ("objtool: Handle __sanitize_cov*() tail calls")

However, this has subtle interaction with the SLS validation from commit:

1cc1e4c8aab4 ("objtool: Add straight-line-speculation validation")

In that when a tail-call instrucion is replaced with a RET an additional INT3 instruction is also written, but is not represented in the decoded instruction stream.

This then leads to false positive missing INT3 objtool warnings in noinstr code.

Instead of adding additional struct instruction objects, mark the RET instruction with retpoline_safe to suppress the warning (since we know there really is an INT3).

Fixes: 1cc1e4c8aab4 ("objtool: Add straight-line-speculation validation") Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20220323230712.GA8939@worktop.programming.kicks-as... Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/check.c | 11 +++++++++++ 1 file changed, 11 insertions(+)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c index fdf96eef6e00..0ca4a3c2d86b 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -961,6 +961,17 @@ static void annotate_call_site(struct objtool_file *file, : arch_nop_insn(insn->len));

insn->type = sibling ? INSN_RETURN : INSN_NOP; + + if (sibling) { + /* + * We've replaced the tail-call JMP insn by two new + * insn: RET; INT3, except we only have a single struct + * insn here. Mark it retpoline_safe to avoid the SLS + * warning, instead of adding another insn. + */ + insn->retpoline_safe = true; + } + return; } }

From: Thadeu Lima de Souza Cascardo cascardo@canonical.com

stable inclusion from stable-v5.10.133 commit accb8cfd506da1e218a0cd56a11f37885dc32adf category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

Commit 156ff4a544ae ("x86/ibt: Base IBT bits") added this option when building realmode in order to disable IBT there. This is also needed in order to disable return thunks.

Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 05f5d28b75eb..1f796050c6dd 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -31,7 +31,7 @@ endif CODE16GCC_CFLAGS := -m32 -Wa,$(srctree)/arch/x86/boot/code16gcc.h M16_CFLAGS := $(call cc-option, -m16, $(CODE16GCC_CFLAGS))

-REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -DDISABLE_BRANCH_PROFILING \ +REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -DDISABLE_BRANCH_PROFILING -D__DISABLE_EXPORTS \ -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none)

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit feec5277d5aa9780d4814084262b98af2b1a2242 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit a883d624aed463c84c22596006e5a96f5b44db31 upstream.

In order to extend the RETPOLINE features to 4, move them to word 11 where there is still room. This mostly keeps DISABLE_RETPOLINE simple.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com [bwh: Backported to 5.10: bits 8 and 9 of word 11 are also free here, so comment them accordingly] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

conflict: arch/x86/include/asm/cpufeatures.h

Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/cpufeatures.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 4da419226377..59d7a2ef64cb 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -203,8 +203,8 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ +/* FREE! ( 7*32+12) */ +/* FREE! ( 7*32+13) */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ @@ -291,6 +291,10 @@ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ #define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ #define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ +/* FREE! (11*32+10) */ +/* FREE! (11*32+11) */ +#define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */

/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 3e519ed8d509f5f2e1c67984f3cdf079b725e724 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 00e1533325fd1fb5459229fe37f235462649f668 upstream.

Put the actual retpoline thunk as the original code so that it can become more complicated. Specifically, it allows RET to be a JMP, which can't be .altinstr_replacement since that doesn't do relocations (except for the very first instruction).

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/lib/retpoline.S | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index afbdda539b80..c013241d9188 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -32,9 +32,9 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) UNWIND_HINT_EMPTY

- ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ - __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE + ALTERNATIVE_2 __stringify(RETPOLINE \reg), \ + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE, \ + __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), ALT_NOT(X86_FEATURE_RETPOLINE)

.endm

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 270de63cf4a380fe9942d3e0da599c0e966fad78 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 0b53c374b9eff2255a386f1f1cfb9a928e52a5ae upstream.

Utilize -mfunction-return=thunk-extern when available to have the compiler replace RET instructions with direct JMPs to the symbol __x86_return_thunk. This does not affect assembler (.S) sources, only C sources.

-mfunction-return=thunk-extern has been available since gcc 7.3 and clang 15.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Nick Desaulniers ndesaulniers@google.com Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Tested-by: Nick Desaulniers ndesaulniers@google.com Signed-off-by: Borislav Petkov bp@suse.de [cascardo: RETPOLINE_CFLAGS is at Makefile] [cascardo: remove ANNOTATE_NOENDBR from __x86_return_thunk] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- Makefile | 2 ++ arch/x86/include/asm/nospec-branch.h | 2 ++ arch/x86/lib/retpoline.S | 12 ++++++++++++ 3 files changed, 16 insertions(+)

diff --git a/Makefile b/Makefile index ebb503a59db2..963734589fe6 100644 --- a/Makefile +++ b/Makefile @@ -672,11 +672,13 @@ endif

ifdef CONFIG_CC_IS_GCC RETPOLINE_CFLAGS := $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) +RETPOLINE_CFLAGS += $(call cc-option,-mfunction-return=thunk-extern) RETPOLINE_VDSO_CFLAGS := $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register) endif ifdef CONFIG_CC_IS_CLANG RETPOLINE_CFLAGS := -mretpoline-external-thunk RETPOLINE_VDSO_CFLAGS := -mretpoline +RETPOLINE_CFLAGS += $(call cc-option,-mfunction-return=thunk-extern) endif export RETPOLINE_CFLAGS export RETPOLINE_VDSO_CFLAGS diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index e791fe7e9de5..6eedd835613c 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -120,6 +120,8 @@ _ASM_PTR " 999b\n\t" \ ".popsection\n\t"

+extern void __x86_return_thunk(void); + #ifdef CONFIG_RETPOLINE

typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index c013241d9188..01667ea9da02 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -66,3 +66,15 @@ SYM_CODE_END(__x86_indirect_thunk_array) #define GEN(reg) EXPORT_THUNK(reg) #include <asm/GEN-for-each-reg.h> #undef GEN + +/* + * This function name is magical and is used by -mfunction-return=thunk-extern + * for the compiler to generate JMPs to it. + */ +SYM_CODE_START(__x86_return_thunk) + UNWIND_HINT_EMPTY + ret + int3 +SYM_CODE_END(__x86_return_thunk) + +__EXPORT_THUNK(__x86_return_thunk)

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 8bdb25f7aee312450e9c9ac21ae209d9cf0602e5 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit d9e9d2300681d68a775c28de6aa6e5290ae17796 upstream.

Find all the return-thunk sites and record them in a .return_sites section such that the kernel can undo this.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de [cascardo: conflict fixup because of functions added to support IBT] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com [bwh: Backported to 5.10: adjust context] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com

[Backport] objtool: skip non-text sections when adding return-thunk sites

stable inclusion from stable-v5.10.133 commit 446eb6f08936e6f87bea9f35be05556a7211df9b category: bugfix bugzilla: 187378

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

The .discard.text section is added in order to reserve BRK, with a temporary function just so it can give it a size. This adds a relocation to the return thunk, which objtool will add to the .return_sites section. Linking will then fail as there are references to the .discard.text section.

Do not add instructions from non-text sections to the list of return thunk calls, avoiding the reference to .discard.text.

Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Acked-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/arch.h | 1 + tools/objtool/arch/x86/decode.c | 5 +++ tools/objtool/check.c | 77 +++++++++++++++++++++++++++++++++ tools/objtool/elf.h | 1 + tools/objtool/objtool.c | 1 + tools/objtool/objtool.h | 1 + 6 files changed, 86 insertions(+)

diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h index e15f6e932b4f..580ce1857585 100644 --- a/tools/objtool/arch.h +++ b/tools/objtool/arch.h @@ -89,6 +89,7 @@ const char *arch_ret_insn(int len); int arch_decode_hint_reg(u8 sp_reg, int *base);

bool arch_is_retpoline(struct symbol *sym); +bool arch_is_rethunk(struct symbol *sym);

int arch_rewrite_retpolines(struct objtool_file *file);

diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index f7154241a2a5..d8f47704fd85 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -649,3 +649,8 @@ bool arch_is_retpoline(struct symbol *sym) { return !strncmp(sym->name, "__x86_indirect_", 15); } + +bool arch_is_rethunk(struct symbol *sym) +{ + return !strcmp(sym->name, "__x86_return_thunk"); +} diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 0ca4a3c2d86b..4d9057e50b1b 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -652,6 +652,52 @@ static int create_retpoline_sites_sections(struct objtool_file *file) return 0; }

+static int create_return_sites_sections(struct objtool_file *file) +{ + struct instruction *insn; + struct section *sec; + int idx; + + sec = find_section_by_name(file->elf, ".return_sites"); + if (sec) { + WARN("file already has .return_sites, skipping"); + return 0; + } + + idx = 0; + list_for_each_entry(insn, &file->return_thunk_list, call_node) + idx++; + + if (!idx) + return 0; + + sec = elf_create_section(file->elf, ".return_sites", 0, + sizeof(int), idx); + if (!sec) { + WARN("elf_create_section: .return_sites"); + return -1; + } + + idx = 0; + list_for_each_entry(insn, &file->return_thunk_list, call_node) { + + int *site = (int *)sec->data->d_buf + idx; + *site = 0; + + if (elf_add_reloc_to_insn(file->elf, sec, + idx * sizeof(int), + R_X86_64_PC32, + insn->sec, insn->offset)) { + WARN("elf_add_reloc_to_insn: .return_sites"); + return -1; + } + + idx++; + } + + return 0; +} + /* * Warnings shouldn't be reported for ignored functions. */ @@ -887,6 +933,11 @@ __weak bool arch_is_retpoline(struct symbol *sym) return false; }

+__weak bool arch_is_rethunk(struct symbol *sym) +{ + return false; +} + #define NEGATIVE_RELOC ((void *)-1L)

static struct reloc *insn_reloc(struct objtool_file *file, struct instruction *insn) @@ -1028,6 +1079,21 @@ static void add_retpoline_call(struct objtool_file *file, struct instruction *in

annotate_call_site(file, insn, false); } + +static void add_return_call(struct objtool_file *file, struct instruction *insn) +{ + /* + * Return thunk tail calls are really just returns in disguise, + * so convert them accordingly. + */ + insn->type = INSN_RETURN; + insn->retpoline_safe = true; + + /* Skip the non-text sections, specially .discard ones */ + if (insn->sec->text) + list_add_tail(&insn->call_node, &file->return_thunk_list); +} + /* * Find the destination instructions for all jumps. */ @@ -1052,6 +1118,9 @@ static int add_jump_destinations(struct objtool_file *file) } else if (reloc->sym->retpoline_thunk) { add_retpoline_call(file, insn); continue; + } else if (reloc->sym->return_thunk) { + add_return_call(file, insn); + continue; } else if (insn->func) { /* internal or external sibling call (with reloc) */ add_call_dest(file, insn, reloc->sym, true); @@ -1841,6 +1910,9 @@ static int classify_symbols(struct objtool_file *file) if (arch_is_retpoline(func)) func->retpoline_thunk = true;

+ if (arch_is_rethunk(func)) + func->return_thunk = true; + if (!strcmp(func->name, "__fentry__")) func->fentry = true;

@@ -3234,6 +3306,11 @@ int check(struct objtool_file *file) if (ret < 0) goto out; warnings += ret; + + ret = create_return_sites_sections(file); + if (ret < 0) + goto out; + warnings += ret; }

if (stats) { diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index de00cac9aede..c68f11b71562 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -58,6 +58,7 @@ struct symbol { u8 uaccess_safe : 1; u8 static_call_tramp : 1; u8 retpoline_thunk : 1; + u8 return_thunk : 1; u8 fentry : 1; u8 kcov : 1; }; diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c index c0b1f5a99df9..cb2c6acd9667 100644 --- a/tools/objtool/objtool.c +++ b/tools/objtool/objtool.c @@ -62,6 +62,7 @@ struct objtool_file *objtool_open_read(const char *_objname) INIT_LIST_HEAD(&file.insn_list); hash_init(file.insn_hash); INIT_LIST_HEAD(&file.retpoline_call_list); + INIT_LIST_HEAD(&file.return_thunk_list); INIT_LIST_HEAD(&file.static_call_list); file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment"); file.ignore_unreachables = no_unreachable; diff --git a/tools/objtool/objtool.h b/tools/objtool/objtool.h index 0b57150ea0fe..bf64946e749b 100644 --- a/tools/objtool/objtool.h +++ b/tools/objtool/objtool.h @@ -19,6 +19,7 @@ struct objtool_file { struct list_head insn_list; DECLARE_HASHTABLE(insn_hash, 20); struct list_head retpoline_call_list; + struct list_head return_thunk_list; struct list_head static_call_list; bool ignore_unreachables, c_file, hints, rodata; };

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 00b136bb6254e0abf6aaafe62c4da5f6c4fea4cb category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 1f001e9da6bbf482311e45e48f53c2bd2179e59c upstream.

Use the return thunk in ftrace trampolines, if needed.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de [cascardo: still copy return from ftrace_stub] [cascardo: use memcpy(text_gen_insn) as there is no __text_gen_insn] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/kernel/ftrace.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index fbcd144260ac..dca5cf82144c 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -308,7 +308,7 @@ union ftrace_op_code_union { } __attribute__((packed)); };

-#define RET_SIZE 1 + IS_ENABLED(CONFIG_SLS) +#define RET_SIZE (IS_ENABLED(CONFIG_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_SLS))

static unsigned long create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) @@ -367,7 +367,10 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)

/* The trampoline ends with ret(q) */ retq = (unsigned long)ftrace_stub; - ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE); + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + memcpy(ip, text_gen_insn(JMP32_INSN_OPCODE, ip, &__x86_return_thunk), JMP32_INSN_SIZE); + else + ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE); if (WARN_ON(ret < 0)) goto fail;

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit ee4996f07d868ee6cc7e76151dfab9a2344cdeb0 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit af2e140f34208a5dfb6b7a8ad2d56bda88f0524d upstream.

Prepare the SETcc fastop stuff for when RET can be larger still.

The tricky bit here is that the expressions should not only be constant C expressions, but also absolute GAS expressions. This means no ?: and 'true' is ~0.

Also ensure em_setcc() has the same alignment as the actual FOP_SETCC() ops, this ensures there cannot be an alignment hole between em_setcc() and the first op.

Additionally, add a .skip directive to the FOP_SETCC() macro to fill any remaining space with INT3 traps; however the primary purpose of this directive is to generate AS warnings when the remaining space goes negative. Which is a very good indication the alignment magic went side-ways.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de [cascardo: ignore ENDBR when computing SETCC_LENGTH] [cascardo: conflict fixup] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/kvm/emulate.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index bdcbf23b8b1e..1f953f230ad5 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -322,13 +322,15 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); #define FOP_RET(name) \ __FOP_RET(#name)

-#define FOP_START(op) \ +#define __FOP_START(op, align) \ extern void em_##op(struct fastop *fake); \ asm(".pushsection .text, "ax" \n\t" \ ".global em_" #op " \n\t" \ - ".align " __stringify(FASTOP_SIZE) " \n\t" \ + ".align " __stringify(align) " \n\t" \ "em_" #op ":\n\t"

+#define FOP_START(op) __FOP_START(op, FASTOP_SIZE) + #define FOP_END \ ".popsection")

@@ -432,15 +434,14 @@ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); /* * Depending on .config the SETcc functions look like: * - * SETcc %al [3 bytes] - * RET [1 byte] - * INT3 [1 byte; CONFIG_SLS] - * - * Which gives possible sizes 4 or 5. When rounded up to the - * next power-of-two alignment they become 4 or 8. + * SETcc %al [3 bytes] + * RET | JMP __x86_return_thunk [1,5 bytes; CONFIG_RETPOLINE] + * INT3 [1 byte; CONFIG_SLS] */ -#define SETCC_LENGTH (4 + IS_ENABLED(CONFIG_SLS)) -#define SETCC_ALIGN (4 << IS_ENABLED(CONFIG_SLS)) +#define RET_LENGTH (1 + (4 * IS_ENABLED(CONFIG_RETPOLINE)) + \ + IS_ENABLED(CONFIG_SLS)) +#define SETCC_LENGTH (3 + RET_LENGTH) +#define SETCC_ALIGN (4 << ((SETCC_LENGTH > 4) & 1) << ((SETCC_LENGTH > 8) & 1)) static_assert(SETCC_LENGTH <= SETCC_ALIGN);

#define FOP_SETCC(op) \ @@ -448,14 +449,15 @@ static_assert(SETCC_LENGTH <= SETCC_ALIGN); ".type " #op ", @function \n\t" \ #op ": \n\t" \ #op " %al \n\t" \ - __FOP_RET(#op) + __FOP_RET(#op) \ + ".skip " __stringify(SETCC_ALIGN) " - (.-" #op "), 0xcc \n\t"

asm(".pushsection .fixup, "ax"\n" ".global kvm_fastop_exception \n" "kvm_fastop_exception: xor %esi, %esi; " ASM_RET ".popsection");

-FOP_START(setcc) +__FOP_START(setcc, SETCC_ALIGN) FOP_SETCC(seto) FOP_SETCC(setno) FOP_SETCC(setc)

From: Kim Phillips kim.phillips@amd.com

stable inclusion from stable-v5.10.133 commit 5b2edaf709b50c81b3c6ddb745c8a76ab6632645 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 0ee9073000e8791f8b134a8ded31bcc767f7f232 upstream.

Specifically, it's because __enc_copy() encrypts the kernel after being relocated outside the kernel in sme_encrypt_execute(), and the RET macro's jmp offset isn't amended prior to execution.

Signed-off-by: Kim Phillips kim.phillips@amd.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/mm/mem_encrypt_boot.S | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 3c2bc5562fc2..a186007a50d3 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -65,7 +65,9 @@ SYM_FUNC_START(sme_encrypt_execute) movq %rbp, %rsp /* Restore original stack pointer */ pop %rbp

- RET + /* Offset to __x86_return_thunk would be wrong here */ + ret + int3 SYM_FUNC_END(sme_encrypt_execute)

SYM_FUNC_START(__enc_copy) @@ -151,6 +153,8 @@ SYM_FUNC_START(__enc_copy) pop %r12 pop %r15

- RET + /* Offset to __x86_return_thunk would be wrong here */ + ret + int3 .L__enc_copy_end: SYM_FUNC_END(__enc_copy)

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit c70d6f82141b89db6c076b0cbf9a7a2edc29e46d category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 951ddecf435659553ed15a9214e153a3af43a9a1 upstream.

Needed because zen_untrain_ret() will be called from noinstr code.

Also makes sense since the thunks MUST NOT contain instrumentation nor be poked with dynamic instrumentation.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- tools/objtool/check.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4d9057e50b1b..082059654322 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -365,7 +365,8 @@ static int decode_instructions(struct objtool_file *file) sec->text = true;

if (!strcmp(sec->name, ".noinstr.text") || - !strcmp(sec->name, ".entry.text")) + !strcmp(sec->name, ".entry.text") || + !strncmp(sec->name, ".text.__x86.", 12)) sec->noinstr = true;

for (offset = 0; offset < sec->len; offset += insn->len) {

From: Alexandre Chartre alexandre.chartre@oracle.com

stable inclusion from stable-v5.10.133 commit 876750cca4f043bd626a3ac760ce887dda3b6ec7 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 6b80b59b3555706508008f1f127b5412c89c7fd8 upstream.

Report that AMD x86 CPUs are vulnerable to the RETBleed (Arbitrary Speculative Code Execution with Return Instructions) attack.

[peterz: add hygon] [kim: invert parity; fam15h]

Co-developed-by: Kim Phillips kim.phillips@amd.com Signed-off-by: Kim Phillips kim.phillips@amd.com Signed-off-by: Alexandre Chartre alexandre.chartre@oracle.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/bugs.c | 13 +++++++++++++ arch/x86/kernel/cpu/common.c | 19 +++++++++++++++++++ drivers/base/cpu.c | 8 ++++++++ include/linux/cpu.h | 2 ++ 5 files changed, 43 insertions(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6bc0e28c9232..3f92cb3768b7 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -426,5 +426,6 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ +#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */

#endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 2a21046846b6..56757e1b7301 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1917,6 +1917,11 @@ static ssize_t srbds_show_state(char *buf) return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); }

+static ssize_t retbleed_show_state(char *buf) +{ + return sprintf(buf, "Vulnerable\n"); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -1962,6 +1967,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_MMIO_STALE_DATA: return mmio_stale_data_show_state(buf);

+ case X86_BUG_RETBLEED: + return retbleed_show_state(buf); + default: break; } @@ -2018,4 +2026,9 @@ ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *at { return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); } + +ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED); +} #endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 4917c2698ac1..5214c4bba33b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1092,16 +1092,27 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { {} };

+#define VULNBL(vendor, family, model, blacklist) \ + X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, blacklist) + #define VULNBL_INTEL_STEPPINGS(model, steppings, issues) \ X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, \ INTEL_FAM6_##model, steppings, \ X86_FEATURE_ANY, issues)

+#define VULNBL_AMD(family, blacklist) \ + VULNBL(AMD, family, X86_MODEL_ANY, blacklist) + +#define VULNBL_HYGON(family, blacklist) \ + VULNBL(HYGON, family, X86_MODEL_ANY, blacklist) + #define SRBDS BIT(0) /* CPU is affected by X86_BUG_MMIO_STALE_DATA */ #define MMIO BIT(1) /* CPU is affected by Shared Buffers Data Sampling (SBDS), a variant of X86_BUG_MMIO_STALE_DATA */ #define MMIO_SBDS BIT(2) +/* CPU is affected by RETbleed, speculating where you would not expect it */ +#define RETBLEED BIT(3)

static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1134,6 +1145,11 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPINGS(0x0, 0x0), MMIO | MMIO_SBDS), + + VULNBL_AMD(0x15, RETBLEED), + VULNBL_AMD(0x16, RETBLEED), + VULNBL_AMD(0x17, RETBLEED), + VULNBL_HYGON(0x18, RETBLEED), {} };

@@ -1235,6 +1251,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !arch_cap_mmio_immune(ia32_cap)) setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);

+ if (cpu_matches(cpu_vuln_blacklist, RETBLEED)) + setup_force_cpu_bug(X86_BUG_RETBLEED); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return;

diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 8ecb9f90f467..24dd532c8e5e 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -572,6 +572,12 @@ ssize_t __weak cpu_show_mmio_stale_data(struct device *dev, return sysfs_emit(buf, "Not affected\n"); }

+ssize_t __weak cpu_show_retbleed(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "Not affected\n"); +} + static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); @@ -582,6 +588,7 @@ static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL); static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL); static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL); static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL); +static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL);

static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -594,6 +601,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_itlb_multihit.attr, &dev_attr_srbds.attr, &dev_attr_mmio_stale_data.attr, + &dev_attr_retbleed.attr, NULL };

diff --git a/include/linux/cpu.h b/include/linux/cpu.h index d63b8f70d123..24e5f237244d 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -68,6 +68,8 @@ extern ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, extern ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_retbleed(struct device *dev, + struct device_attribute *attr, char *buf);

extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata,

From: Kim Phillips kim.phillips@amd.com

stable inclusion from stable-v5.10.133 commit a989e75136192036d47e4dc4fe87ff9c961d6b46 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit e8ec1b6e08a2102d8755ccb06fa26d540f26a2fa upstream.

For untrained return thunks to be fully effective, STIBP must be enabled or SMT disabled.

Co-developed-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Josh Poimboeuf jpoimboe@redhat.com Signed-off-by: Kim Phillips kim.phillips@amd.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- .../admin-guide/kernel-parameters.txt | 16 +++-- arch/x86/kernel/cpu/bugs.c | 58 +++++++++++++++---- 2 files changed, 57 insertions(+), 17 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 7ce6137be034..d312bc5a7a49 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4822,11 +4822,17 @@ Speculative Code Execution with Return Instructions) vulnerability.

- off - unconditionally disable - auto - automatically select a migitation - unret - force enable untrained return thunks, - only effective on AMD Zen {1,2} - based systems. + off - no mitigation + auto - automatically select a migitation + auto,nosmt - automatically select a mitigation, + disabling SMT if necessary for + the full mitigation (only on Zen1 + and older without STIBP). + unret - force enable untrained return thunks, + only effective on AMD f15h-f17h + based systems. + unret,nosmt - like unret, will disable SMT when STIBP + is not available.

Selecting 'auto' will choose a mitigation method at run time according to the CPU. diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 7cf0f1d2bcb0..619565986048 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -739,19 +739,34 @@ static enum retbleed_mitigation retbleed_mitigation __ro_after_init = static enum retbleed_mitigation_cmd retbleed_cmd __ro_after_init = RETBLEED_CMD_AUTO;

+static int __ro_after_init retbleed_nosmt = false; + static int __init retbleed_parse_cmdline(char *str) { if (!str) return -EINVAL;

- if (!strcmp(str, "off")) - retbleed_cmd = RETBLEED_CMD_OFF; - else if (!strcmp(str, "auto")) - retbleed_cmd = RETBLEED_CMD_AUTO; - else if (!strcmp(str, "unret")) - retbleed_cmd = RETBLEED_CMD_UNRET; - else - pr_err("Unknown retbleed option (%s). Defaulting to 'auto'\n", str); + while (str) { + char *next = strchr(str, ','); + if (next) { + *next = 0; + next++; + } + + if (!strcmp(str, "off")) { + retbleed_cmd = RETBLEED_CMD_OFF; + } else if (!strcmp(str, "auto")) { + retbleed_cmd = RETBLEED_CMD_AUTO; + } else if (!strcmp(str, "unret")) { + retbleed_cmd = RETBLEED_CMD_UNRET; + } else if (!strcmp(str, "nosmt")) { + retbleed_nosmt = true; + } else { + pr_err("Ignoring unknown retbleed option (%s).", str); + } + + str = next; + }

return 0; } @@ -797,6 +812,10 @@ static void __init retbleed_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET);

+ if (!boot_cpu_has(X86_FEATURE_STIBP) && + (retbleed_nosmt || cpu_mitigations_auto_nosmt())) + cpu_smt_disable(false); + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) pr_err(RETBLEED_UNTRAIN_MSG); @@ -1043,6 +1062,13 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON)) mode = SPECTRE_V2_USER_STRICT_PREFERRED;

+ if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET) { + if (mode != SPECTRE_V2_USER_STRICT && + mode != SPECTRE_V2_USER_STRICT_PREFERRED) + pr_info("Selecting STIBP always-on mode to complement retbleed mitigation'\n"); + mode = SPECTRE_V2_USER_STRICT_PREFERRED; + } + spectre_v2_user_stibp = mode;

set_mode: @@ -2020,10 +2046,18 @@ static ssize_t srbds_show_state(char *buf)

static ssize_t retbleed_show_state(char *buf) { - if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET && - (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && - boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)) - return sprintf(buf, "Vulnerable: untrained return thunk on non-Zen uarch\n"); + if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + return sprintf(buf, "Vulnerable: untrained return thunk on non-Zen uarch\n"); + + return sprintf(buf, "%s; SMT %s\n", + retbleed_strings[retbleed_mitigation], + !sched_smt_active() ? "disabled" : + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? + "enabled with STIBP protection" : "vulnerable"); + }

return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]); }

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 3dddacf8c3cc29b9b37d8c4353f746e510ad1371 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 2dbb887e875b1de3ca8f40ddf26bcfe55798c609 upstream.

Implement Kernel IBRS - currently the only known option to mitigate RSB underflow speculation issues on Skylake hardware.

Note: since IBRS_ENTER requires fuller context established than UNTRAIN_RET, it must be placed after it. However, since UNTRAIN_RET itself implies a RET, it must come after IBRS_ENTER. This means IBRS_ENTER needs to also move UNTRAIN_RET.

Note 2: KERNEL_IBRS is sub-optimal for XenPV.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de [cascardo: conflict at arch/x86/entry/entry_64.S, skip_r11rcx] [cascardo: conflict at arch/x86/entry/entry_64_compat.S] [cascardo: conflict fixups, no ANNOTATE_NOENDBR] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com [bwh: Backported to 5.10: adjust context] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/entry/calling.h | 58 ++++++++++++++++++++++++++++++ arch/x86/entry/entry_64.S | 44 ++++++++++++++++++++--- arch/x86/entry/entry_64_compat.S | 17 ++++++--- arch/x86/include/asm/cpufeatures.h | 2 +- 4 files changed, 111 insertions(+), 10 deletions(-)

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 2be2595e4458..c3c68e97a404 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -6,6 +6,8 @@ #include <asm/percpu.h> #include <asm/asm-offsets.h> #include <asm/processor-flags.h> +#include <asm/msr.h> +#include <asm/nospec-branch.h>

/*

@@ -308,6 +310,62 @@ For 32-bit we have the following conventions - kernel is built with

#endif

+/* + * IBRS kernel mitigation for Spectre_v2. + * + * Assumes full context is established (PUSH_REGS, CR3 and GS) and it clobbers + * the regs it uses (AX, CX, DX). Must be called before the first RET + * instruction (NOTE! UNTRAIN_RET includes a RET instruction) + * + * The optional argument is used to save/restore the current value, + * which is used on the paranoid paths. + * + * Assumes x86_spec_ctrl_{base,current} to have SPEC_CTRL_IBRS set. + */ +.macro IBRS_ENTER save_reg + ALTERNATIVE "jmp .Lend_@", "", X86_FEATURE_KERNEL_IBRS + movl $MSR_IA32_SPEC_CTRL, %ecx + +.ifnb \save_reg + rdmsr + shl $32, %rdx + or %rdx, %rax + mov %rax, \save_reg + test $SPEC_CTRL_IBRS, %eax + jz .Ldo_wrmsr_@ + lfence + jmp .Lend_@ +.Ldo_wrmsr_@: +.endif + + movq PER_CPU_VAR(x86_spec_ctrl_current), %rdx + movl %edx, %eax + shr $32, %rdx + wrmsr +.Lend_@: +.endm + +/* + * Similar to IBRS_ENTER, requires KERNEL GS,CR3 and clobbers (AX, CX, DX) + * regs. Must be called after the last RET. + */ +.macro IBRS_EXIT save_reg + ALTERNATIVE "jmp .Lend_@", "", X86_FEATURE_KERNEL_IBRS + movl $MSR_IA32_SPEC_CTRL, %ecx + +.ifnb \save_reg + mov \save_reg, %rdx +.else + movq PER_CPU_VAR(x86_spec_ctrl_current), %rdx + andl $(~SPEC_CTRL_IBRS), %edx +.endif + + movl %edx, %eax + shr $32, %rdx + wrmsr +.Lend_@: +.endm + /* * Mitigate Spectre v1 for conditional swapgs code paths. * diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index be5558c82ea7..ca616ee71dfb 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -102,7 +102,6 @@ SYM_CODE_START(entry_SYSCALL_64) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp

SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL) - UNTRAIN_RET

/* Construct struct pt_regs on stack */ pushq $__USER_DS /* pt_regs->ss */ @@ -118,6 +117,11 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) /* IRQs are off. */ movq %rax, %rdi movq %rsp, %rsi + + /* clobbers %rax, make sure it is after saving the syscall nr */ + IBRS_ENTER + UNTRAIN_RET + call do_syscall_64 /* returns with IRQs disabled */

/* @@ -192,6 +196,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) * perf profiles. Nothing jumps here. */ syscall_return_via_sysret: + IBRS_EXIT POP_REGS pop_rdi=0

/* @@ -568,6 +573,7 @@ __irqentry_text_end:

SYM_CODE_START_LOCAL(common_interrupt_return) SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) + IBRS_EXIT #ifdef CONFIG_DEBUG_ENTRY /* Assert that pt_regs indicates user mode. */ testb $3, CS(%rsp) @@ -888,6 +894,9 @@ SYM_CODE_END(xen_failsafe_callback) * 1 -> no SWAPGS on exit * * Y GSBASE value at entry, must be restored in paranoid_exit + * + * R14 - old CR3 + * R15 - old SPEC_CTRL */ SYM_CODE_START_LOCAL(paranoid_entry) UNWIND_HINT_FUNC @@ -911,7 +920,6 @@ SYM_CODE_START_LOCAL(paranoid_entry) * be retrieved from a kernel internal table. */ SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14 - UNTRAIN_RET

/* * Handling GSBASE depends on the availability of FSGSBASE. @@ -933,7 +941,7 @@ SYM_CODE_START_LOCAL(paranoid_entry) * is needed here. */ SAVE_AND_SET_GSBASE scratch_reg=%rax save_reg=%rbx - RET + jmp .Lparanoid_gsbase_done

.Lparanoid_entry_checkgs: /* EBX = 1 -> kernel GSBASE active, no restore required */ @@ -952,8 +960,16 @@ SYM_CODE_START_LOCAL(paranoid_entry) xorl %ebx, %ebx swapgs .Lparanoid_kernel_gsbase: - FENCE_SWAPGS_KERNEL_ENTRY +.Lparanoid_gsbase_done: + + /* + * Once we have CR3 and %GS setup save and set SPEC_CTRL. Just like + * CR3 above, keep the old value in a callee saved register. + */ + IBRS_ENTER save_reg=%r15 + UNTRAIN_RET + RET SYM_CODE_END(paranoid_entry)

@@ -975,9 +991,19 @@ SYM_CODE_END(paranoid_entry) * 1 -> no SWAPGS on exit * * Y User space GSBASE, must be restored unconditionally + * + * R14 - old CR3 + * R15 - old SPEC_CTRL */ SYM_CODE_START_LOCAL(paranoid_exit) UNWIND_HINT_REGS + + /* + * Must restore IBRS state before both CR3 and %GS since we need access + * to the per-CPU x86_spec_ctrl_shadow variable. + */ + IBRS_EXIT save_reg=%r15 + /* * The order of operations is important. RESTORE_CR3 requires * kernel GSBASE. @@ -1024,9 +1050,11 @@ SYM_CODE_START_LOCAL(error_entry) FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + IBRS_ENTER UNTRAIN_RET

.Lerror_entry_from_usermode_after_swapgs: + /* Put us onto the real thread stack. */ popq %r12 /* save return addr in %12 */ movq %rsp, %rdi /* arg0 = pt_regs pointer */ @@ -1080,6 +1108,7 @@ SYM_CODE_START_LOCAL(error_entry) SWAPGS FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + IBRS_ENTER UNTRAIN_RET

/* @@ -1175,7 +1204,6 @@ SYM_CODE_START(asm_exc_nmi) movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp UNWIND_HINT_IRET_REGS base=%rdx offset=8 - UNTRAIN_RET pushq 5*8(%rdx) /* pt_regs->ss */ pushq 4*8(%rdx) /* pt_regs->rsp */ pushq 3*8(%rdx) /* pt_regs->flags */ @@ -1186,6 +1214,9 @@ SYM_CODE_START(asm_exc_nmi) PUSH_AND_CLEAR_REGS rdx=(%rdx) ENCODE_FRAME_POINTER

+ IBRS_ENTER + UNTRAIN_RET + /* * At this point we no longer need to worry about stack damage * due to nesting -- we're on the normal thread stack and we're @@ -1408,6 +1439,9 @@ end_repeat_nmi: movq $-1, %rsi call exc_nmi

+ /* Always restore stashed SPEC_CTRL value (see paranoid_entry) */ + IBRS_EXIT save_reg=%r15 + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%r15 save_reg=%r14

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 007f3a1fbf1a..e2f25403ec30 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -4,7 +4,6 @@ * * Copyright 2000-2002 Andi Kleen, SuSE Labs. */ -#include "calling.h" #include <asm/asm-offsets.h> #include <asm/current.h> #include <asm/errno.h> @@ -18,6 +17,8 @@ #include <linux/linkage.h> #include <linux/err.h>

+#include "calling.h" + .section .entry.text, "ax"

/* @@ -72,7 +73,6 @@ SYM_CODE_START(entry_SYSENTER_compat) pushq $__USER32_CS /* pt_regs->cs */ pushq $0 /* pt_regs->ip = 0 (placeholder) */ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) - UNTRAIN_RET

/* * User tracing code (ptrace or signal handlers) might assume that @@ -114,6 +114,9 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)

cld

+ IBRS_ENTER + UNTRAIN_RET + /* * SYSENTER doesn't filter flags, so we need to clear NT and AC * ourselves. To save a few cycles, we can check whether @@ -213,7 +216,6 @@ SYM_CODE_START(entry_SYSCALL_compat) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp

SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL) - UNTRAIN_RET

/* Construct struct pt_regs on stack */ pushq $__USER32_DS /* pt_regs->ss */ @@ -255,6 +257,9 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)

UNWIND_HINT_REGS

+ IBRS_ENTER + UNTRAIN_RET + movq %rsp, %rdi call do_fast_syscall_32 /* XEN PV guests always use IRET path */ @@ -269,6 +274,8 @@ sysret32_from_system_call: */ STACKLEAK_ERASE

+ IBRS_EXIT + movq RBX(%rsp), %rbx /* pt_regs->rbx */ movq RBP(%rsp), %rbp /* pt_regs->rbp */ movq EFLAGS(%rsp), %r11 /* pt_regs->flags (in r11) */ @@ -380,7 +387,6 @@ SYM_CODE_START(entry_INT80_compat) pushq (%rdi) /* pt_regs->di */ .Lint80_keep_stack:

- UNTRAIN_RET pushq %rsi /* pt_regs->si */ xorl %esi, %esi /* nospec si */ pushq %rdx /* pt_regs->dx */ @@ -413,6 +419,9 @@ SYM_CODE_START(entry_INT80_compat)

cld

+ IBRS_ENTER + UNTRAIN_RET + movq %rsp, %rdi call do_int80_syscall_32 jmp swapgs_restore_regs_and_return_to_usermode diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 3f92cb3768b7..83c85ee0edab 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -203,7 +203,7 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -/* FREE! ( 7*32+12) */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ /* FREE! ( 7*32+13) */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */

From: Pawan Gupta pawan.kumar.gupta@linux.intel.com

stable inclusion from stable-v5.10.133 commit dabc2a1b406ae0ff5286c91f7519b3e20ec2aa63 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 7c693f54c873691a4b7da05c7e0f74e67745d144 upstream.

Extend spectre_v2= boot option with Kernel IBRS.

[jpoimboe: no STIBP with IBRS]

Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- .../admin-guide/kernel-parameters.txt | 1 + arch/x86/include/asm/nospec-branch.h | 1 + arch/x86/kernel/cpu/bugs.c | 66 +++++++++++++++---- 3 files changed, 54 insertions(+), 14 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index d312bc5a7a49..fc65fe7797e9 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5188,6 +5188,7 @@ eibrs - enhanced IBRS eibrs,retpoline - enhanced IBRS + Retpolines eibrs,lfence - enhanced IBRS + LFENCE + ibrs - use IBRS to protect kernel

Not specifying this option is equivalent to spectre_v2=auto. diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 1a044c65e484..152ca4372e06 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -219,6 +219,7 @@ enum spectre_v2_mitigation { SPECTRE_V2_EIBRS, SPECTRE_V2_EIBRS_RETPOLINE, SPECTRE_V2_EIBRS_LFENCE, + SPECTRE_V2_IBRS, };

/* The indirect branch speculation control variants */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 8572cac3ca98..483c5d5afc9f 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -928,6 +928,7 @@ enum spectre_v2_mitigation_cmd { SPECTRE_V2_CMD_EIBRS, SPECTRE_V2_CMD_EIBRS_RETPOLINE, SPECTRE_V2_CMD_EIBRS_LFENCE, + SPECTRE_V2_CMD_IBRS, };

enum spectre_v2_user_cmd { @@ -1000,11 +1001,12 @@ spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd) return SPECTRE_V2_USER_CMD_AUTO; }

-static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) +static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) { - return (mode == SPECTRE_V2_EIBRS || - mode == SPECTRE_V2_EIBRS_RETPOLINE || - mode == SPECTRE_V2_EIBRS_LFENCE); + return mode == SPECTRE_V2_IBRS || + mode == SPECTRE_V2_EIBRS || + mode == SPECTRE_V2_EIBRS_RETPOLINE || + mode == SPECTRE_V2_EIBRS_LFENCE; }

static void __init @@ -1069,12 +1071,12 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) }

/* - * If no STIBP, enhanced IBRS is enabled or SMT impossible, STIBP is not - * required. + * If no STIBP, IBRS or enhanced IBRS is enabled, or SMT impossible, + * STIBP is not required. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + spectre_v2_in_ibrs_mode(spectre_v2_enabled)) return;

/* @@ -1106,6 +1108,7 @@ static const char * const spectre_v2_strings[] = { [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS", [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE", [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines", + [SPECTRE_V2_IBRS] = "Mitigation: IBRS", };

static const struct { @@ -1123,6 +1126,7 @@ static const struct { { "eibrs,lfence", SPECTRE_V2_CMD_EIBRS_LFENCE, false }, { "eibrs,retpoline", SPECTRE_V2_CMD_EIBRS_RETPOLINE, false }, { "auto", SPECTRE_V2_CMD_AUTO, false }, + { "ibrs", SPECTRE_V2_CMD_IBRS, false }, };

static void __init spec_v2_print_cond(const char *reason, bool secure) @@ -1185,6 +1189,24 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return SPECTRE_V2_CMD_AUTO; }

+ if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { + pr_err("%s selected but not Intel CPU. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_IBRS && !boot_cpu_has(X86_FEATURE_IBRS)) { + pr_err("%s selected but CPU doesn't have IBRS. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_has(X86_FEATURE_XENPV)) { + pr_err("%s selected but running as XenPV guest. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + spec_v2_print_cond(mitigation_options[i].option, mitigation_options[i].secure); return cmd; @@ -1224,6 +1246,14 @@ static void __init spectre_v2_select_mitigation(void) break; }

+ if (boot_cpu_has_bug(X86_BUG_RETBLEED) && + retbleed_cmd != RETBLEED_CMD_OFF && + boot_cpu_has(X86_FEATURE_IBRS) && + boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { + mode = SPECTRE_V2_IBRS; + break; + } + mode = spectre_v2_select_retpoline(); break;

@@ -1240,6 +1270,10 @@ static void __init spectre_v2_select_mitigation(void) mode = spectre_v2_select_retpoline(); break;

+ case SPECTRE_V2_CMD_IBRS: + mode = SPECTRE_V2_IBRS; + break; + case SPECTRE_V2_CMD_EIBRS: mode = SPECTRE_V2_EIBRS; break; @@ -1256,7 +1290,7 @@ static void __init spectre_v2_select_mitigation(void) if (mode == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) pr_err(SPECTRE_V2_EIBRS_EBPF_MSG);

- if (spectre_v2_in_eibrs_mode(mode)) { + if (spectre_v2_in_ibrs_mode(mode)) { /* Force it so VMEXIT will restore correctly */ x86_spec_ctrl_base |= SPEC_CTRL_IBRS; write_spec_ctrl_current(x86_spec_ctrl_base, true); @@ -1267,6 +1301,10 @@ static void __init spectre_v2_select_mitigation(void) case SPECTRE_V2_EIBRS: break;

+ case SPECTRE_V2_IBRS: + setup_force_cpu_cap(X86_FEATURE_KERNEL_IBRS); + break; + case SPECTRE_V2_LFENCE: case SPECTRE_V2_EIBRS_LFENCE: setup_force_cpu_cap(X86_FEATURE_RETPOLINE_LFENCE); @@ -1293,17 +1331,17 @@ static void __init spectre_v2_select_mitigation(void) pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");

/* - * Retpoline means the kernel is safe because it has no indirect - * branches. Enhanced IBRS protects firmware too, so, enable restricted - * speculation around firmware calls only when Enhanced IBRS isn't - * supported. + * Retpoline protects the kernel, but doesn't protect firmware. IBRS + * and Enhanced IBRS protect firmware too, so enable IBRS around + * firmware calls only when IBRS / Enhanced IBRS aren't otherwise + * enabled. * * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because * the user might select retpoline on the kernel command line and if * the CPU supports Enhanced IBRS, kernel might un-intentionally not * enable IBRS around firmware calls. */ - if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_eibrs_mode(mode)) { + if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) { setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } @@ -2012,7 +2050,7 @@ static ssize_t mmio_stale_data_show_state(char *buf)

static char *stibp_state(void) { - if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_ibrs_mode(spectre_v2_enabled)) return "";

switch (spectre_v2_user_stibp) {

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit e8142e2d6cb6b39fdd78bc17199429f79bcd051c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 6ad0ad2bf8a67e27d1f9d006a1dabb0e1c360cc3 upstream.

Skylake suffers from RSB underflow speculation issues; report this vulnerability and it's mitigation (spectre_v2=ibrs).

[jpoimboe: cleanups, eibrs]

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/msr-index.h | 1 + arch/x86/kernel/cpu/bugs.c | 39 +++++++++++++++++++++++++++----- arch/x86/kernel/cpu/common.c | 24 ++++++++++---------- 3 files changed, 46 insertions(+), 18 deletions(-)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 2b0af5eb5131..4291f840ef51 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -91,6 +91,7 @@ #define MSR_IA32_ARCH_CAPABILITIES 0x0000010a #define ARCH_CAP_RDCL_NO BIT(0) /* Not susceptible to Meltdown */ #define ARCH_CAP_IBRS_ALL BIT(1) /* Enhanced IBRS support */ +#define ARCH_CAP_RSBA BIT(2) /* RET may use alternative branch predictors */ #define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH BIT(3) /* Skip L1D flush on vmentry */ #define ARCH_CAP_SSB_NO BIT(4) /* * Not susceptible to Speculative Store Bypass diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 58f48f93e8cc..a2423d4ed293 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -746,12 +746,17 @@ static int __init nospectre_v1_cmdline(char *str) } early_param("nospectre_v1", nospectre_v1_cmdline);

+static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = + SPECTRE_V2_NONE; + #undef pr_fmt #define pr_fmt(fmt) "RETBleed: " fmt

enum retbleed_mitigation { RETBLEED_MITIGATION_NONE, RETBLEED_MITIGATION_UNRET, + RETBLEED_MITIGATION_IBRS, + RETBLEED_MITIGATION_EIBRS, };

enum retbleed_mitigation_cmd { @@ -763,6 +768,8 @@ enum retbleed_mitigation_cmd { const char * const retbleed_strings[] = { [RETBLEED_MITIGATION_NONE] = "Vulnerable", [RETBLEED_MITIGATION_UNRET] = "Mitigation: untrained return thunk", + [RETBLEED_MITIGATION_IBRS] = "Mitigation: IBRS", + [RETBLEED_MITIGATION_EIBRS] = "Mitigation: Enhanced IBRS", };

static enum retbleed_mitigation retbleed_mitigation __ro_after_init = @@ -805,6 +812,7 @@ early_param("retbleed", retbleed_parse_cmdline);

#define RETBLEED_UNTRAIN_MSG "WARNING: BTB untrained return thunk mitigation is only effective on AMD/Hygon!\n" #define RETBLEED_COMPILER_MSG "WARNING: kernel not compiled with RETPOLINE or -mfunction-return capable compiler!\n" +#define RETBLEED_INTEL_MSG "WARNING: Spectre v2 mitigation leaves CPU vulnerable to RETBleed attacks, data leaks possible!\n"

static void __init retbleed_select_mitigation(void) { @@ -821,12 +829,15 @@ static void __init retbleed_select_mitigation(void)

case RETBLEED_CMD_AUTO: default: - if (!boot_cpu_has_bug(X86_BUG_RETBLEED)) - break; - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) retbleed_mitigation = RETBLEED_MITIGATION_UNRET; + + /* + * The Intel mitigation (IBRS) was already selected in + * spectre_v2_select_mitigation(). + */ + break; }

@@ -856,15 +867,31 @@ static void __init retbleed_select_mitigation(void) break; }

+ /* + * Let IBRS trump all on Intel without affecting the effects of the + * retbleed= cmdline option. + */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { + switch (spectre_v2_enabled) { + case SPECTRE_V2_IBRS: + retbleed_mitigation = RETBLEED_MITIGATION_IBRS; + break; + case SPECTRE_V2_EIBRS: + case SPECTRE_V2_EIBRS_RETPOLINE: + case SPECTRE_V2_EIBRS_LFENCE: + retbleed_mitigation = RETBLEED_MITIGATION_EIBRS; + break; + default: + pr_err(RETBLEED_INTEL_MSG); + } + } + pr_info("%s\n", retbleed_strings[retbleed_mitigation]); }

#undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt

-static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = - SPECTRE_V2_NONE; - static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = SPECTRE_V2_USER_NONE; static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init = diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 5214c4bba33b..ab68595e217e 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1124,24 +1124,24 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO), + VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(SKYLAKE_X, BIT(3) | BIT(4) | BIT(6) | - BIT(7) | BIT(0xB), MMIO), - VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO), + BIT(7) | BIT(0xB), MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x9, 0xC), SRBDS | MMIO), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x9, 0xC), SRBDS | MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x0, 0x8), SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x9, 0xD), SRBDS | MMIO), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x9, 0xD), SRBDS | MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x0, 0x8), SRBDS), - VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPINGS(0x5, 0x5), MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPINGS(0x5, 0x5), MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPINGS(0x1, 0x1), MMIO), VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPINGS(0x4, 0x6), MMIO), - VULNBL_INTEL_STEPPINGS(COMETLAKE, BIT(2) | BIT(3) | BIT(5), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO), - VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPINGS(0x1, 0x1), MMIO), + VULNBL_INTEL_STEPPINGS(COMETLAKE, BIT(2) | BIT(3) | BIT(5), MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPINGS(0x1, 0x1), MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPINGS(0x0, 0x0), MMIO | MMIO_SBDS), @@ -1251,7 +1251,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !arch_cap_mmio_immune(ia32_cap)) setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);

- if (cpu_matches(cpu_vuln_blacklist, RETBLEED)) + if ((cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA))) setup_force_cpu_bug(X86_BUG_RETBLEED);

if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 28aa3fa0b2c9d0cd7bdac42d9eb7fe3d5f6c79e8 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 9bb2ec608a209018080ca262f771e6a9ff203b6f upstream.

Update retpoline validation with the new CONFIG_RETPOLINE requirement of not having bare naked RET instructions.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de [cascardo: conflict fixup at arch/x86/xen/xen-head.S] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/nospec-branch.h | 6 ++++++ arch/x86/mm/mem_encrypt_boot.S | 2 ++ arch/x86/xen/xen-head.S | 1 + tools/objtool/check.c | 19 +++++++++++++------ 4 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index fd8ab72d826b..719b5dd95037 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -75,6 +75,12 @@ .popsection .endm

+/* + * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions + * vs RETBleed validation. + */ +#define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE + /* * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple * indirect jmp/call which may be susceptible to the Spectre variant 2 diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index a186007a50d3..145b67299ab6 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -66,6 +66,7 @@ SYM_FUNC_START(sme_encrypt_execute) pop %rbp

/* Offset to __x86_return_thunk would be wrong here */ + ANNOTATE_UNRET_SAFE ret int3 SYM_FUNC_END(sme_encrypt_execute) @@ -154,6 +155,7 @@ SYM_FUNC_START(__enc_copy) pop %r15

/* Offset to __x86_return_thunk would be wrong here */ + ANNOTATE_UNRET_SAFE ret int3 .L__enc_copy_end: diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 565062932ef1..38b73e7e54ba 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -70,6 +70,7 @@ SYM_CODE_START(hypercall_page) .rept (PAGE_SIZE / 32) UNWIND_HINT_FUNC .skip 31, 0x90 + ANNOTATE_UNRET_SAFE RET .endr

diff --git a/tools/objtool/check.c b/tools/objtool/check.c index a484df42255f..fff2e7bcd091 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1798,8 +1798,9 @@ static int read_retpoline_hints(struct objtool_file *file) }

if (insn->type != INSN_JUMP_DYNAMIC && - insn->type != INSN_CALL_DYNAMIC) { - WARN_FUNC("retpoline_safe hint not an indirect jump/call", + insn->type != INSN_CALL_DYNAMIC && + insn->type != INSN_RETURN) { + WARN_FUNC("retpoline_safe hint not an indirect jump/call/ret", insn->sec, insn->offset); return -1; } @@ -3050,7 +3051,8 @@ static int validate_retpoline(struct objtool_file *file)

for_each_insn(file, insn) { if (insn->type != INSN_JUMP_DYNAMIC && - insn->type != INSN_CALL_DYNAMIC) + insn->type != INSN_CALL_DYNAMIC && + insn->type != INSN_RETURN) continue;

if (insn->retpoline_safe) @@ -3065,9 +3067,14 @@ static int validate_retpoline(struct objtool_file *file) if (!strcmp(insn->sec->name, ".init.text") && !module) continue;

- WARN_FUNC("indirect %s found in RETPOLINE build", - insn->sec, insn->offset, - insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); + if (insn->type == INSN_RETURN) { + WARN_FUNC("'naked' return found in RETPOLINE build", + insn->sec, insn->offset); + } else { + WARN_FUNC("indirect %s found in RETPOLINE build", + insn->sec, insn->offset, + insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call"); + }

warnings++; }

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit c8845b875437b8ea9cd023f15b44c436c9c5b62d category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 3ebc170068885b6fc7bedda6c667bb2c4d533159 upstream.

jmp2ret mitigates the easy-to-attack case at relatively low overhead. It mitigates the long speculation windows after a mispredicted RET, but it does not mitigate the short speculation window from arbitrary instruction boundaries.

On Zen2, there is a chicken bit which needs setting, which mitigates "arbitrary instruction boundaries" down to just "basic block boundaries".

But there is no fix for the short speculation window on basic block boundaries, other than to flush the entire BTB to evict all attacker predictions.

On the spectrum of "fast & blurry" -> "safe", there is (on top of STIBP or no-SMT):

1) Nothing System wide open 2) jmp2ret May stop a script kiddy 3) jmp2ret+chickenbit Raises the bar rather further 4) IBPB Only thing which can count as "safe".

Tentative numbers put IBPB-on-entry at a 2.5x hit on Zen2, and a 10x hit on Zen1 according to lmbench.

[ bp: Fixup feature bit comments, document option, 32-bit build fix. ]

Suggested-by: Andrew Cooper Andrew.Cooper3@citrix.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com [bwh: Backported to 5.10: adjust context] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

conflict: arch/x86/include/asm/cpufeatures.h

Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- .../admin-guide/kernel-parameters.txt | 3 ++ arch/x86/entry/Makefile | 2 +- arch/x86/entry/entry.S | 22 ++++++++++ arch/x86/include/asm/cpufeatures.h | 2 +- arch/x86/include/asm/nospec-branch.h | 8 +++- arch/x86/kernel/cpu/bugs.c | 43 +++++++++++++++---- 6 files changed, 67 insertions(+), 13 deletions(-) create mode 100644 arch/x86/entry/entry.S

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index fc65fe7797e9..54c30c5bb244 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4828,6 +4828,9 @@ disabling SMT if necessary for the full mitigation (only on Zen1 and older without STIBP). + ibpb - mitigate short speculation windows on + basic block boundaries too. Safe, highest + perf impact. unret - force enable untrained return thunks, only effective on AMD f15h-f17h based systems. diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index 08bf95dbc911..58533752efab 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -21,7 +21,7 @@ CFLAGS_syscall_64.o += $(call cc-option,-Wno-override-init,) CFLAGS_syscall_32.o += $(call cc-option,-Wno-override-init,) CFLAGS_syscall_x32.o += $(call cc-option,-Wno-override-init,)

-obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o +obj-y := entry.o entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o obj-y += common.o

obj-y += vdso/ diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S new file mode 100644 index 000000000000..bfb7bcb362bc --- /dev/null +++ b/arch/x86/entry/entry.S @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common place for both 32- and 64-bit entry routines. + */ + +#include <linux/linkage.h> +#include <asm/export.h> +#include <asm/msr-index.h> + +.pushsection .noinstr.text, "ax" + +SYM_FUNC_START(entry_ibpb) + movl $MSR_IA32_PRED_CMD, %ecx + movl $PRED_CMD_IBPB, %eax + xorl %edx, %edx + wrmsr + RET +SYM_FUNC_END(entry_ibpb) +/* For KVM */ +EXPORT_SYMBOL_GPL(entry_ibpb); + +.popsection diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 83c85ee0edab..4cba3c1d8b79 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -291,7 +291,7 @@ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ #define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ #define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ -/* FREE! (11*32+10) */ +#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* "" Issue an IBPB on kernel entry */ /* FREE! (11*32+11) */ #define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 719b5dd95037..554d03cb11d1 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -123,14 +123,17 @@ * return thunk isn't mapped into the userspace tables (then again, AMD * typically has NO_MELTDOWN). * - * Doesn't clobber any registers but does require a stable stack. + * While zen_untrain_ret() doesn't clobber anything but requires stack, + * entry_ibpb() will clobber AX, CX, DX. * * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point * where we have a stack but before any RET instruction. */ .macro UNTRAIN_RET #ifdef CONFIG_RETPOLINE - ALTERNATIVE "", "call zen_untrain_ret", X86_FEATURE_UNRET + ALTERNATIVE_2 "", \ + "call zen_untrain_ret", X86_FEATURE_UNRET, \ + "call entry_ibpb", X86_FEATURE_ENTRY_IBPB #endif .endm

@@ -144,6 +147,7 @@

extern void __x86_return_thunk(void); extern void zen_untrain_ret(void); +extern void entry_ibpb(void);

#ifdef CONFIG_RETPOLINE

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1d16d194f6ab..0e25b0a66621 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -761,6 +761,7 @@ static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = enum retbleed_mitigation { RETBLEED_MITIGATION_NONE, RETBLEED_MITIGATION_UNRET, + RETBLEED_MITIGATION_IBPB, RETBLEED_MITIGATION_IBRS, RETBLEED_MITIGATION_EIBRS, }; @@ -769,11 +770,13 @@ enum retbleed_mitigation_cmd { RETBLEED_CMD_OFF, RETBLEED_CMD_AUTO, RETBLEED_CMD_UNRET, + RETBLEED_CMD_IBPB, };

const char * const retbleed_strings[] = { [RETBLEED_MITIGATION_NONE] = "Vulnerable", [RETBLEED_MITIGATION_UNRET] = "Mitigation: untrained return thunk", + [RETBLEED_MITIGATION_IBPB] = "Mitigation: IBPB", [RETBLEED_MITIGATION_IBRS] = "Mitigation: IBRS", [RETBLEED_MITIGATION_EIBRS] = "Mitigation: Enhanced IBRS", }; @@ -803,6 +806,8 @@ static int __init retbleed_parse_cmdline(char *str) retbleed_cmd = RETBLEED_CMD_AUTO; } else if (!strcmp(str, "unret")) { retbleed_cmd = RETBLEED_CMD_UNRET; + } else if (!strcmp(str, "ibpb")) { + retbleed_cmd = RETBLEED_CMD_IBPB; } else if (!strcmp(str, "nosmt")) { retbleed_nosmt = true; } else { @@ -817,11 +822,13 @@ static int __init retbleed_parse_cmdline(char *str) early_param("retbleed", retbleed_parse_cmdline);

#define RETBLEED_UNTRAIN_MSG "WARNING: BTB untrained return thunk mitigation is only effective on AMD/Hygon!\n" -#define RETBLEED_COMPILER_MSG "WARNING: kernel not compiled with RETPOLINE or -mfunction-return capable compiler!\n" +#define RETBLEED_COMPILER_MSG "WARNING: kernel not compiled with RETPOLINE or -mfunction-return capable compiler; falling back to IBPB!\n" #define RETBLEED_INTEL_MSG "WARNING: Spectre v2 mitigation leaves CPU vulnerable to RETBleed attacks, data leaks possible!\n"

static void __init retbleed_select_mitigation(void) { + bool mitigate_smt = false; + if (!boot_cpu_has_bug(X86_BUG_RETBLEED) || cpu_mitigations_off()) return;

@@ -833,11 +840,21 @@ static void __init retbleed_select_mitigation(void) retbleed_mitigation = RETBLEED_MITIGATION_UNRET; break;

+ case RETBLEED_CMD_IBPB: + retbleed_mitigation = RETBLEED_MITIGATION_IBPB; + break; + case RETBLEED_CMD_AUTO: default: if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || - boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) - retbleed_mitigation = RETBLEED_MITIGATION_UNRET; + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { + + if (IS_ENABLED(CONFIG_RETPOLINE) && + IS_ENABLED(CONFIG_CC_HAS_RETURN_THUNK)) + retbleed_mitigation = RETBLEED_MITIGATION_UNRET; + else + retbleed_mitigation = RETBLEED_MITIGATION_IBPB; + }

/* * The Intel mitigation (IBRS) was already selected in @@ -853,26 +870,34 @@ static void __init retbleed_select_mitigation(void) if (!IS_ENABLED(CONFIG_RETPOLINE) || !IS_ENABLED(CONFIG_CC_HAS_RETURN_THUNK)) { pr_err(RETBLEED_COMPILER_MSG); - retbleed_mitigation = RETBLEED_MITIGATION_NONE; - break; + retbleed_mitigation = RETBLEED_MITIGATION_IBPB; + goto retbleed_force_ibpb; }

setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET);

- if (!boot_cpu_has(X86_FEATURE_STIBP) && - (retbleed_nosmt || cpu_mitigations_auto_nosmt())) - cpu_smt_disable(false); - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) pr_err(RETBLEED_UNTRAIN_MSG); + + mitigate_smt = true; + break; + + case RETBLEED_MITIGATION_IBPB: +retbleed_force_ibpb: + setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + mitigate_smt = true; break;

default: break; }

+ if (mitigate_smt && !boot_cpu_has(X86_FEATURE_STIBP) && + (retbleed_nosmt || cpu_mitigations_auto_nosmt())) + cpu_smt_disable(false); + /* * Let IBRS trump all on Intel without affecting the effects of the * retbleed= cmdline option.

From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-v5.10.133 commit 0d1a8a16e62c8048f2ff7f9c6f448bf595d2a2a8 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit a09a6e2399ba0595c3042b3164f3ca68a3cff33e upstream.

Since entry asm is tricky, add a validation pass that ensures the retbleed mitigation has been done before the first actual RET instruction.

Entry points are those that either have UNWIND_HINT_ENTRY, which acts as UNWIND_HINT_EMPTY but marks the instruction as an entry point, or those that have UWIND_HINT_IRET_REGS at +0.

This is basically a variant of validate_branch() that is intra-function and it will simply follow all branches from marked entry points and ensures that all paths lead to ANNOTATE_UNRET_END.

If a path hits RET or an indirection the path is a fail and will be reported.

There are 3 ANNOTATE_UNRET_END instances:

- UNTRAIN_RET itself - exception from-kernel; this path doesn't need UNTRAIN_RET - all early exceptions; these also don't need UNTRAIN_RET

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de [cascardo: arch/x86/entry/entry_64.S no pt_regs return at .Lerror_entry_done_lfence] [cascardo: tools/objtool/builtin-check.c no link option validation] [cascardo: tools/objtool/check.c opts.ibt is ibt] [cascardo: tools/objtool/include/objtool/builtin.h leave unret option as bool, no struct opts] [cascardo: objtool is still called from scripts/link-vmlinux.sh] [cascardo: no IBT support] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com [bwh: Backported to 5.10: - In scripts/link-vmlinux.sh, use "test -n" instead of is_enabled - Adjust context] Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/entry/entry_64.S | 3 +- arch/x86/entry/entry_64_compat.S | 6 +- arch/x86/include/asm/nospec-branch.h | 12 ++ arch/x86/include/asm/unwind_hints.h | 4 + arch/x86/kernel/head_64.S | 5 + arch/x86/xen/xen-asm.S | 10 +- include/linux/objtool.h | 3 + scripts/link-vmlinux.sh | 3 + tools/include/linux/objtool.h | 3 + tools/objtool/builtin-check.c | 3 +- tools/objtool/builtin.h | 2 +- tools/objtool/check.c | 172 ++++++++++++++++++++++++++- tools/objtool/check.h | 6 + 13 files changed, 217 insertions(+), 15 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index ca616ee71dfb..639a6495a321 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -93,7 +93,7 @@ SYM_CODE_END(native_usergs_sysret64) */

SYM_CODE_START(entry_SYSCALL_64) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY

swapgs /* tss.sp2 is scratch space. */ @@ -1093,6 +1093,7 @@ SYM_CODE_START_LOCAL(error_entry) */ .Lerror_entry_done_lfence: FENCE_SWAPGS_KERNEL_ENTRY + ANNOTATE_UNRET_END RET

.Lbstep_iret: diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index e2f25403ec30..4d637a965efb 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -49,7 +49,7 @@ * 0(%ebp) arg6 */ SYM_CODE_START(entry_SYSENTER_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY /* Interrupts are off on entry. */ SWAPGS

@@ -202,7 +202,7 @@ SYM_CODE_END(entry_SYSENTER_compat) * 0(%esp) arg6 */ SYM_CODE_START(entry_SYSCALL_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY /* Interrupts are off on entry. */ swapgs

@@ -349,7 +349,7 @@ SYM_CODE_END(entry_SYSCALL_compat) * ebp arg6 */ SYM_CODE_START(entry_INT80_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY /* * Interrupts are off on entry. */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 554d03cb11d1..c1cd0b5ca038 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -81,6 +81,17 @@ */ #define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE

+/* + * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should + * eventually turn into it's own annotation. + */ +.macro ANNOTATE_UNRET_END +#ifdef CONFIG_DEBUG_ENTRY + ANNOTATE_RETPOLINE_SAFE + nop +#endif +.endm + /* * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple * indirect jmp/call which may be susceptible to the Spectre variant 2 @@ -131,6 +142,7 @@ */ .macro UNTRAIN_RET #ifdef CONFIG_RETPOLINE + ANNOTATE_UNRET_END ALTERNATIVE_2 "", \ "call zen_untrain_ret", X86_FEATURE_UNRET, \ "call entry_ibpb", X86_FEATURE_ENTRY_IBPB diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h index 8e574c0afef8..9cd8214175b5 100644 --- a/arch/x86/include/asm/unwind_hints.h +++ b/arch/x86/include/asm/unwind_hints.h @@ -11,6 +11,10 @@ UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_CALL end=1 .endm

+.macro UNWIND_HINT_ENTRY + UNWIND_HINT sp_reg=ORC_REG_UNDEFINED type=UNWIND_HINT_TYPE_ENTRY end=1 +.endm + .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 .if \base == %rsp .if \indirect diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 3c417734790f..0424c2a6c15b 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -321,6 +321,8 @@ SYM_CODE_END(start_cpu0) SYM_CODE_START_NOALIGN(vc_boot_ghcb) UNWIND_HINT_IRET_REGS offset=8

+ ANNOTATE_UNRET_END + /* Build pt_regs */ PUSH_AND_CLEAR_REGS

@@ -378,6 +380,7 @@ SYM_CODE_START(early_idt_handler_array) SYM_CODE_END(early_idt_handler_array)

SYM_CODE_START_LOCAL(early_idt_handler_common) + ANNOTATE_UNRET_END /* * The stack is the hardware frame, an error code or zero, and the * vector number. @@ -424,6 +427,8 @@ SYM_CODE_END(early_idt_handler_common) SYM_CODE_START_NOALIGN(vc_no_ghcb) UNWIND_HINT_IRET_REGS offset=8

+ ANNOTATE_UNRET_END + /* Build pt_regs */ PUSH_AND_CLEAR_REGS

diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 70d3b21008e5..e3031afcb103 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -148,7 +148,7 @@ SYM_FUNC_END(xen_read_cr2_direct);

.macro xen_pv_trap name SYM_CODE_START(xen_\name) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY pop %rcx pop %r11 jmp \name @@ -277,7 +277,7 @@ SYM_CODE_END(xenpv_restore_regs_and_return_to_usermode)

/* Normal 64-bit system call target */ SYM_CODE_START(xen_entry_SYSCALL_64) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY popq %rcx popq %r11

@@ -296,7 +296,7 @@ SYM_CODE_END(xen_entry_SYSCALL_64)

/* 32-bit compat syscall target */ SYM_CODE_START(xen_entry_SYSCALL_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY popq %rcx popq %r11

@@ -313,7 +313,7 @@ SYM_CODE_END(xen_entry_SYSCALL_compat)

/* 32-bit compat sysenter target */ SYM_CODE_START(xen_entry_SYSENTER_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY /* * NB: Xen is polite and clears TF from EFLAGS for us. This means * that we don't need to guard against single step exceptions here. @@ -336,7 +336,7 @@ SYM_CODE_END(xen_entry_SYSENTER_compat)

SYM_CODE_START(xen_entry_SYSCALL_compat) SYM_CODE_START(xen_entry_SYSENTER_compat) - UNWIND_HINT_EMPTY + UNWIND_HINT_ENTRY lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax pushq $0 diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 8ed079c52c47..b2855f7fce53 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -32,11 +32,14 @@ struct unwind_hint { * * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4

#ifdef CONFIG_STACK_VALIDATION

diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index b184d94b9052..a7c72eb5a624 100755 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -65,6 +65,9 @@ objtool_link()

if [ -n "${CONFIG_VMLINUX_VALIDATION}" ]; then objtoolopt="check" + if [ -n "${CONFIG_RETPOLINE}" ]; then + objtoolopt="${objtoolopt} --unret" + fi if [ -z "${CONFIG_FRAME_POINTER}" ]; then objtoolopt="${objtoolopt} --no-fp" fi diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index 8ed079c52c47..b2855f7fce53 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -32,11 +32,14 @@ struct unwind_hint { * * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. */ #define UNWIND_HINT_TYPE_CALL 0 #define UNWIND_HINT_TYPE_REGS 1 #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 +#define UNWIND_HINT_TYPE_ENTRY 4

#ifdef CONFIG_STACK_VALIDATION

diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c index 758baf918d83..d04eab7e77ae 100644 --- a/tools/objtool/builtin-check.c +++ b/tools/objtool/builtin-check.c @@ -19,7 +19,7 @@ #include "objtool.h"

bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, - validate_dup, vmlinux, sls; + validate_dup, vmlinux, sls, unret;

static const char * const check_usage[] = { "objtool check [<options>] file.o", @@ -30,6 +30,7 @@ const struct option check_options[] = { OPT_BOOLEAN('f', "no-fp", &no_fp, "Skip frame pointer validation"), OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"), OPT_BOOLEAN('r', "retpoline", &retpoline, "Validate retpoline assumptions"), + OPT_BOOLEAN(0, "unret", &unret, "validate entry unret placement"), OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"), OPT_BOOLEAN('b', "backtrace", &backtrace, "unwind on error"), OPT_BOOLEAN('a', "uaccess", &uaccess, "enable uaccess checking"), diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h index 33043fcb16db..b6b486e28d54 100644 --- a/tools/objtool/builtin.h +++ b/tools/objtool/builtin.h @@ -9,7 +9,7 @@

extern const struct option check_options[]; extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats, - validate_dup, vmlinux, sls; + validate_dup, vmlinux, sls, unret;

extern int cmd_check(int argc, const char **argv); extern int cmd_orc(int argc, const char **argv); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index fff2e7bcd091..2075a1617887 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -1751,6 +1751,19 @@ static int read_unwind_hints(struct objtool_file *file)

insn->hint = true;

+ if (hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) { + struct symbol *sym = find_symbol_by_offset(insn->sec, insn->offset); + + if (sym && sym->bind == STB_GLOBAL) { + insn->entry = 1; + } + } + + if (hint->type == UNWIND_HINT_TYPE_ENTRY) { + hint->type = UNWIND_HINT_TYPE_CALL; + insn->entry = 1; + } + if (hint->type == UNWIND_HINT_TYPE_FUNC) { insn->cfi = &func_cfi; continue; @@ -1799,8 +1812,9 @@ static int read_retpoline_hints(struct objtool_file *file)

if (insn->type != INSN_JUMP_DYNAMIC && insn->type != INSN_CALL_DYNAMIC && - insn->type != INSN_RETURN) { - WARN_FUNC("retpoline_safe hint not an indirect jump/call/ret", + insn->type != INSN_RETURN && + insn->type != INSN_NOP) { + WARN_FUNC("retpoline_safe hint not an indirect jump/call/ret/nop", insn->sec, insn->offset); return -1; } @@ -2817,8 +2831,8 @@ static int validate_branch(struct objtool_file *file, struct symbol *func, return 1; }

- visited = 1 << state.uaccess; - if (insn->visited) { + visited = VISITED_BRANCH << state.uaccess; + if (insn->visited & VISITED_BRANCH_MASK) { if (!insn->hint && !insn_cfi_match(insn, &state.cfi)) return 1;

@@ -3044,6 +3058,145 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec) return warnings; }

+/* + * Validate rethunk entry constraint: must untrain RET before the first RET. + * + * Follow every branch (intra-function) and ensure ANNOTATE_UNRET_END comes + * before an actual RET instruction. + */ +static int validate_entry(struct objtool_file *file, struct instruction *insn) +{ + struct instruction *next, *dest; + int ret, warnings = 0; + + for (;;) { + next = next_insn_to_validate(file, insn); + + if (insn->visited & VISITED_ENTRY) + return 0; + + insn->visited |= VISITED_ENTRY; + + if (!insn->ignore_alts && !list_empty(&insn->alts)) { + struct alternative *alt; + bool skip_orig = false; + + list_for_each_entry(alt, &insn->alts, list) { + if (alt->skip_orig) + skip_orig = true; + + ret = validate_entry(file, alt->insn); + if (ret) { + if (backtrace) + BT_FUNC("(alt)", insn); + return ret; + } + } + + if (skip_orig) + return 0; + } + + switch (insn->type) { + + case INSN_CALL_DYNAMIC: + case INSN_JUMP_DYNAMIC: + case INSN_JUMP_DYNAMIC_CONDITIONAL: + WARN_FUNC("early indirect call", insn->sec, insn->offset); + return 1; + + case INSN_JUMP_UNCONDITIONAL: + case INSN_JUMP_CONDITIONAL: + if (!is_sibling_call(insn)) { + if (!insn->jump_dest) { + WARN_FUNC("unresolved jump target after linking?!?", + insn->sec, insn->offset); + return -1; + } + ret = validate_entry(file, insn->jump_dest); + if (ret) { + if (backtrace) { + BT_FUNC("(branch%s)", insn, + insn->type == INSN_JUMP_CONDITIONAL ? "-cond" : ""); + } + return ret; + } + + if (insn->type == INSN_JUMP_UNCONDITIONAL) + return 0; + + break; + } + + /* fallthrough */ + case INSN_CALL: + dest = find_insn(file, insn->call_dest->sec, + insn->call_dest->offset); + if (!dest) { + WARN("Unresolved function after linking!?: %s", + insn->call_dest->name); + return -1; + } + + ret = validate_entry(file, dest); + if (ret) { + if (backtrace) + BT_FUNC("(call)", insn); + return ret; + } + /* + * If a call returns without error, it must have seen UNTRAIN_RET. + * Therefore any non-error return is a success. + */ + return 0; + + case INSN_RETURN: + WARN_FUNC("RET before UNTRAIN", insn->sec, insn->offset); + return 1; + + case INSN_NOP: + if (insn->retpoline_safe) + return 0; + break; + + default: + break; + } + + if (!next) { + WARN_FUNC("teh end!", insn->sec, insn->offset); + return -1; + } + insn = next; + } + + return warnings; +} + +/* + * Validate that all branches starting at 'insn->entry' encounter UNRET_END + * before RET. + */ +static int validate_unret(struct objtool_file *file) +{ + struct instruction *insn; + int ret, warnings = 0; + + for_each_insn(file, insn) { + if (!insn->entry) + continue; + + ret = validate_entry(file, insn); + if (ret < 0) { + WARN_FUNC("Failed UNRET validation", insn->sec, insn->offset); + return ret; + } + warnings += ret; + } + + return warnings; +} + static int validate_retpoline(struct objtool_file *file) { struct instruction *insn; @@ -3311,6 +3464,17 @@ int check(struct objtool_file *file) goto out; warnings += ret;

+ if (unret) { + /* + * Must be after validate_branch() and friends, it plays + * further games with insn->visited. + */ + ret = validate_unret(file); + if (ret < 0) + return ret; + warnings += ret; + } + if (!warnings) { ret = validate_reachable_instructions(file); if (ret < 0) diff --git a/tools/objtool/check.h b/tools/objtool/check.h index 508f712deba1..e8fa948c053f 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -48,6 +48,7 @@ struct instruction { bool dead_end, ignore, ignore_alts; bool hint; bool retpoline_safe; + bool entry; s8 instr; u8 visited; struct alt_group *alt_group; @@ -62,6 +63,11 @@ struct instruction { struct cfi_state *cfi; };

+#define VISITED_BRANCH 0x01 +#define VISITED_BRANCH_UACCESS 0x02 +#define VISITED_BRANCH_MASK 0x03 +#define VISITED_ENTRY 0x04 + static inline bool is_static_jump(struct instruction *insn) { return insn->type == INSN_JUMP_CONDITIONAL ||

From: Josh Poimboeuf jpoimboe@kernel.org

stable inclusion from stable-v5.10.133 commit f1b01ace814b0a8318041e3aea5fd36cc74f09b0 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit b2620facef4889fefcbf2e87284f34dcd4189bce upstream.

If a kernel is built with CONFIG_RETPOLINE=n, but the user still wants to mitigate Spectre v2 using IBRS or eIBRS, the RSB filling will be silently disabled.

There's nothing retpoline-specific about RSB buffer filling. Remove the CONFIG_RETPOLINE guards around it.

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/entry/entry_32.S | 2 -- arch/x86/entry/entry_64.S | 2 -- arch/x86/include/asm/nospec-branch.h | 2 -- 3 files changed, 6 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 4a4896ba4db3..8fcd6a42b3a1 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -782,7 +782,6 @@ SYM_CODE_START(__switch_to_asm) movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset #endif

-#ifdef CONFIG_RETPOLINE /* * When switching from a shallower to a deeper call stack * the RSB may either underflow or use entries populated @@ -791,7 +790,6 @@ SYM_CODE_START(__switch_to_asm) * speculative execution to prevent attack. */ FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW -#endif

/* Restore flags or the incoming task to restore AC state. */ popfl diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 639a6495a321..bf0cf5760906 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -249,7 +249,6 @@ SYM_FUNC_START(__switch_to_asm) movq %rbx, PER_CPU_VAR(fixed_percpu_data) + stack_canary_offset #endif

-#ifdef CONFIG_RETPOLINE /* * When switching from a shallower to a deeper call stack * the RSB may either underflow or use entries populated @@ -258,7 +257,6 @@ SYM_FUNC_START(__switch_to_asm) * speculative execution to prevent attack. */ FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW -#endif

/* restore callee-saved registers */ popq %r15 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index c1cd0b5ca038..b42f8d7fd52b 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -122,11 +122,9 @@ * monstrosity above, manually. */ .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req -#ifdef CONFIG_RETPOLINE ALTERNATIVE "jmp .Lskip_rsb_@", "", \ftr __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP) .Lskip_rsb_@: -#endif .endm

/*

From: Josh Poimboeuf jpoimboe@kernel.org

stable inclusion from stable-v5.10.133 commit aad83db22e9950577b5b827f57ed7108b3ca5553 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 56aa4d221f1ee2c3a49b45b800778ec6e0ab73c5 upstream.

If the SMT state changes, SSBD might get accidentally disabled. Fix that.

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/kernel/cpu/bugs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 8205834dd11e..33af6f9ab241 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1414,7 +1414,8 @@ static void __init spectre_v2_select_mitigation(void)

static void update_stibp_msr(void * __unused) { - write_spec_ctrl_current(x86_spec_ctrl_base, true); + u64 val = spec_ctrl_current() | (x86_spec_ctrl_base & SPEC_CTRL_STIBP); + write_spec_ctrl_current(val, true); }

/* Update x86_spec_ctrl_base in case SMT state changed. */

From: Josh Poimboeuf jpoimboe@kernel.org

stable inclusion from stable-v5.10.133 commit 1dbefa57725204be0348351ea4756c52b10b3504 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit acac5e98ef8d638a411cfa2ee676c87e1973f126 upstream.

This mask has been made redundant by kvm_spec_ctrl_test_value(). And it doesn't even work when MSR interception is disabled, as the guest can just write to SPEC_CTRL directly.

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/kernel/cpu/bugs.c | 31 +------------------------------ 1 file changed, 1 insertion(+), 30 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 6af379b69b82..8fe701ffee31 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -84,12 +84,6 @@ u64 spec_ctrl_current(void) } EXPORT_SYMBOL_GPL(spec_ctrl_current);

-/* - * The vendor and possibly platform specific bits which can be modified in - * x86_spec_ctrl_base. - */ -static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS; - /* * AMD specific MSR info for Speculative Store Bypass control. * x86_amd_ls_cfg_ssbd_mask is initialized in identify_boot_cpu(). @@ -138,10 +132,6 @@ void __init check_bugs(void) if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);

- /* Allow STIBP in MSR_SPEC_CTRL if supported */ - if (boot_cpu_has(X86_FEATURE_STIBP)) - x86_spec_ctrl_mask |= SPEC_CTRL_STIBP; - /* Select the proper CPU mitigations before patching alternatives: */ spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); @@ -199,19 +189,10 @@ void __init check_bugs(void) void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) { - u64 msrval, guestval, hostval = spec_ctrl_current(); + u64 msrval, guestval = guest_spec_ctrl, hostval = spec_ctrl_current(); struct thread_info *ti = current_thread_info();

- /* Is MSR_SPEC_CTRL implemented ? */ if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) { - /* - * Restrict guest_spec_ctrl to supported values. Clear the - * modifiable bits in the host base value and or the - * modifiable bits from the guest value. - */ - guestval = hostval & ~x86_spec_ctrl_mask; - guestval |= guest_spec_ctrl & x86_spec_ctrl_mask; - if (hostval != guestval) { msrval = setguest ? guestval : hostval; wrmsrl(MSR_IA32_SPEC_CTRL, msrval); @@ -1621,16 +1602,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) break; }

- /* - * If SSBD is controlled by the SPEC_CTRL MSR, then set the proper - * bit in the mask to allow guests to use the mitigation even in the - * case where the host does not enable it. - */ - if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - static_cpu_has(X86_FEATURE_AMD_SSBD)) { - x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; - } - /* * We have three CPU feature flags that are in play here: * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.

From: Josh Poimboeuf jpoimboe@kernel.org

stable inclusion from stable-v5.10.133 commit 07401c2311f6fddd3c49a392eafc2c28a899f768 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 8bd200d23ec42d66ccd517a72dd0b9cc6132d2fd upstream.

Move the vmx_vm{enter,exit}() functionality into __vmx_vcpu_run(). This will make it easier to do the spec_ctrl handling before the first RET.

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de [cascardo: remove ENDBR] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/kvm/vmx/vmenter.S | 118 ++++++++++++++----------------------- 1 file changed, 45 insertions(+), 73 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 435c187927c4..cd1cd516ec3d 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -30,68 +30,6 @@

.section .noinstr.text, "ax"

-/** - * vmx_vmenter - VM-Enter the current loaded VMCS - * - * %RFLAGS.ZF: !VMCS.LAUNCHED, i.e. controls VMLAUNCH vs. VMRESUME - * - * Returns: - * %RFLAGS.CF is set on VM-Fail Invalid - * %RFLAGS.ZF is set on VM-Fail Valid - * %RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit - * - * Note that VMRESUME/VMLAUNCH fall-through and return directly if - * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump - * to vmx_vmexit. - */ -SYM_FUNC_START_LOCAL(vmx_vmenter) - /* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */ - je 2f - -1: vmresume - RET - -2: vmlaunch - RET - -3: cmpb $0, kvm_rebooting - je 4f - RET -4: ud2 - - _ASM_EXTABLE(1b, 3b) - _ASM_EXTABLE(2b, 3b) - -SYM_FUNC_END(vmx_vmenter) - -/** - * vmx_vmexit - Handle a VMX VM-Exit - * - * Returns: - * %RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit - * - * This is vmx_vmenter's partner in crime. On a VM-Exit, control will jump - * here after hardware loads the host's state, i.e. this is the destination - * referred to by VMCS.HOST_RIP. - */ -SYM_FUNC_START(vmx_vmexit) -#ifdef CONFIG_RETPOLINE - ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE - /* Preserve guest's RAX, it's used to stuff the RSB. */ - push %_ASM_AX - - /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE - - /* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */ - or $1, %_ASM_AX - - pop %_ASM_AX -.Lvmexit_skip_rsb: -#endif - RET -SYM_FUNC_END(vmx_vmexit) - /** * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode * @vmx: struct vcpu_vmx * (forwarded to vmx_update_host_rsp) @@ -124,8 +62,7 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Copy @launched to BL, _ASM_ARG3 is volatile. */ mov %_ASM_ARG3B, %bl

- /* Adjust RSP to account for the CALL to vmx_vmenter(). */ - lea -WORD_SIZE(%_ASM_SP), %_ASM_ARG2 + lea (%_ASM_SP), %_ASM_ARG2 call vmx_update_host_rsp

/* Load @regs to RAX. */ @@ -154,11 +91,36 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX

- /* Enter guest mode */ - call vmx_vmenter + /* Check EFLAGS.ZF from 'testb' above */ + je .Lvmlaunch + + /* + * After a successful VMRESUME/VMLAUNCH, control flow "magically" + * resumes below at 'vmx_vmexit' due to the VMCS HOST_RIP setting. + * So this isn't a typical function and objtool needs to be told to + * save the unwind state here and restore it below. + */ + UNWIND_HINT_SAVE + +/* + * If VMRESUME/VMLAUNCH and corresponding vmexit succeed, execution resumes at + * the 'vmx_vmexit' label below. + */ +.Lvmresume: + vmresume + jmp .Lvmfail + +.Lvmlaunch: + vmlaunch + jmp .Lvmfail + + _ASM_EXTABLE(.Lvmresume, .Lfixup) + _ASM_EXTABLE(.Lvmlaunch, .Lfixup)

- /* Jump on VM-Fail. */ - jbe 2f +SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) + + /* Restore unwind state from before the VMRESUME/VMLAUNCH. */ + UNWIND_HINT_RESTORE

/* Temporarily save guest's RAX. */ push %_ASM_AX @@ -185,9 +147,13 @@ SYM_FUNC_START(__vmx_vcpu_run) mov %r15, VCPU_R15(%_ASM_AX) #endif

+ /* IMPORTANT: RSB must be stuffed before the first return. */ + FILL_RETURN_BUFFER %_ASM_BX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + /* Clear RAX to indicate VM-Exit (as opposed to VM-Fail). */ xor %eax, %eax

+.Lclear_regs: /* * Clear all general purpose registers except RSP and RAX to prevent * speculative use of the guest's values, even those that are reloaded @@ -197,7 +163,7 @@ SYM_FUNC_START(__vmx_vcpu_run) * free. RSP and RAX are exempt as RSP is restored by hardware during * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail. */ -1: xor %ecx, %ecx + xor %ecx, %ecx xor %edx, %edx xor %ebx, %ebx xor %ebp, %ebp @@ -216,8 +182,8 @@ SYM_FUNC_START(__vmx_vcpu_run)

/* "POP" @regs. */ add $WORD_SIZE, %_ASM_SP - pop %_ASM_BX

+ pop %_ASM_BX #ifdef CONFIG_X86_64 pop %r12 pop %r13 @@ -230,9 +196,15 @@ SYM_FUNC_START(__vmx_vcpu_run) pop %_ASM_BP RET

- /* VM-Fail. Out-of-line to avoid a taken Jcc after VM-Exit. */ -2: mov $1, %eax - jmp 1b +.Lfixup: + cmpb $0, kvm_rebooting + jne .Lvmfail + ud2 +.Lvmfail: + /* VM-Fail: set return value to 1 */ + mov $1, %eax + jmp .Lclear_regs + SYM_FUNC_END(__vmx_vcpu_run)

From: Josh Poimboeuf jpoimboe@kernel.org

stable inclusion from stable-v5.10.133 commit 5269be9111e2b66572e78647f2e8948f7fc96466 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit fc02735b14fff8c6678b521d324ade27b1a3d4cf upstream.

On eIBRS systems, the returns in the vmexit return path from __vmx_vcpu_run() to vmx_vcpu_run() are exposed to RSB poisoning attacks.

Fix that by moving the post-vmexit spec_ctrl handling to immediately after the vmexit.

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

conflict: arch/x86/kvm/vmx/vmx.h

Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/nospec-branch.h | 1 + arch/x86/kernel/cpu/bugs.c | 4 +++ arch/x86/kvm/vmx/run_flags.h | 1 + arch/x86/kvm/vmx/vmenter.S | 49 +++++++++++++++++++++------- arch/x86/kvm/vmx/vmx.c | 48 +++++++++++++++------------ arch/x86/kvm/vmx/vmx.h | 1 + 6 files changed, 73 insertions(+), 31 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index bb419c5b4867..530e8ca4f74c 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -282,6 +282,7 @@ static inline void indirect_branch_prediction_barrier(void)

/* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; +extern u64 x86_spec_ctrl_current; extern void write_spec_ctrl_current(u64 val, bool force); extern u64 spec_ctrl_current(void);

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 8fe701ffee31..4157991053d1 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -186,6 +186,10 @@ void __init check_bugs(void) #endif }

+/* + * NOTE: For VMX, this function is not called in the vmexit path. + * It uses vmx_spec_ctrl_restore_host() instead. + */ void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) { diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h index 57f4c664ea9c..edc3f16cc189 100644 --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -3,5 +3,6 @@ #define __KVM_X86_VMX_RUN_FLAGS_H

#define VMX_RUN_VMRESUME (1 << 0) +#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1)

#endif /* __KVM_X86_VMX_RUN_FLAGS_H */ diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 95d3a47b157d..1c1a3d6c2af2 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -33,9 +33,10 @@

/** * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode - * @vmx: struct vcpu_vmx * (forwarded to vmx_update_host_rsp) + * @vmx: struct vcpu_vmx * * @regs: unsigned long * (to guest registers) - * @flags: VMX_RUN_VMRESUME: use VMRESUME instead of VMLAUNCH + * @flags: VMX_RUN_VMRESUME: use VMRESUME instead of VMLAUNCH + * VMX_RUN_SAVE_SPEC_CTRL: save guest SPEC_CTRL into vmx->spec_ctrl * * Returns: * 0 on VM-Exit, 1 on VM-Fail @@ -54,6 +55,12 @@ SYM_FUNC_START(__vmx_vcpu_run) #endif push %_ASM_BX

+ /* Save @vmx for SPEC_CTRL handling */ + push %_ASM_ARG1 + + /* Save @flags for SPEC_CTRL handling */ + push %_ASM_ARG3 + /* * Save @regs, _ASM_ARG2 may be modified by vmx_update_host_rsp() and * @regs is needed after VM-Exit to save the guest's register values. @@ -148,25 +155,23 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) mov %r15, VCPU_R15(%_ASM_AX) #endif

- /* IMPORTANT: RSB must be stuffed before the first return. */ - FILL_RETURN_BUFFER %_ASM_BX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE - - /* Clear RAX to indicate VM-Exit (as opposed to VM-Fail). */ - xor %eax, %eax + /* Clear return value to indicate VM-Exit (as opposed to VM-Fail). */ + xor %ebx, %ebx

.Lclear_regs: /* - * Clear all general purpose registers except RSP and RAX to prevent + * Clear all general purpose registers except RSP and RBX to prevent * speculative use of the guest's values, even those that are reloaded * via the stack. In theory, an L1 cache miss when restoring registers * could lead to speculative execution with the guest's values. * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially * free. RSP and RAX are exempt as RSP is restored by hardware during - * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail. + * VM-Exit and RBX is explicitly loaded with 0 or 1 to hold the return + * value. */ + xor %eax, %eax xor %ecx, %ecx xor %edx, %edx - xor %ebx, %ebx xor %ebp, %ebp xor %esi, %esi xor %edi, %edi @@ -184,6 +189,28 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) /* "POP" @regs. */ add $WORD_SIZE, %_ASM_SP

+ /* + * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before + * the first unbalanced RET after vmexit! + * + * For retpoline, RSB filling is needed to prevent poisoned RSB entries + * and (in some cases) RSB underflow. + * + * eIBRS has its own protection against poisoned RSB, so it doesn't + * need the RSB filling sequence. But it does need to be enabled + * before the first unbalanced RET. + */ + + FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + + pop %_ASM_ARG2 /* @flags */ + pop %_ASM_ARG1 /* @vmx */ + + call vmx_spec_ctrl_restore_host + + /* Put return value in AX */ + mov %_ASM_BX, %_ASM_AX + pop %_ASM_BX #ifdef CONFIG_X86_64 pop %r12 @@ -203,7 +230,7 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) ud2 .Lvmfail: /* VM-Fail: set return value to 1 */ - mov $1, %eax + mov $1, %_ASM_BX jmp .Lclear_regs

SYM_FUNC_END(__vmx_vcpu_run) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 8300e3181bd0..b6ed6f98cdc2 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -951,6 +951,14 @@ unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) if (vmx->loaded_vmcs->launched) flags |= VMX_RUN_VMRESUME;

+ /* + * If writes to the SPEC_CTRL MSR aren't intercepted, the guest is free + * to change it directly without causing a vmexit. In that case read + * it after vmexit and store it in vmx->spec_ctrl. + */ + if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) + flags |= VMX_RUN_SAVE_SPEC_CTRL; + return flags; }

@@ -6739,6 +6747,26 @@ void noinstr vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp) } }

+void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, + unsigned int flags) +{ + u64 hostval = this_cpu_read(x86_spec_ctrl_current); + + if (!cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) + return; + + if (flags & VMX_RUN_SAVE_SPEC_CTRL) + vmx->spec_ctrl = __rdmsr(MSR_IA32_SPEC_CTRL); + + /* + * If the guest/host SPEC_CTRL values differ, restore the host value. + */ + if (vmx->spec_ctrl != hostval) + native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval); + + barrier_nospec(); +} + static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { switch (to_vmx(vcpu)->exit_reason.basic) { @@ -6895,26 +6923,6 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) /* The actual VMENTER/EXIT is in the .noinstr.text section. */ vmx_vcpu_enter_exit(vcpu, vmx, __vmx_vcpu_run_flags(vmx));

- /* - * We do not use IBRS in the kernel. If this vCPU has used the - * SPEC_CTRL MSR it may have left it on; save the value and - * turn it off. This is much more efficient than blindly adding - * it to the atomic save/restore list. Especially as the former - * (Saving guest MSRs on vmexit) doesn't even exist in KVM. - * - * For non-nested case: - * If the L01 MSR bitmap does not intercept the MSR, then we need to - * save it. - * - * For nested case: - * If the L02 MSR bitmap does not intercept the MSR, then we need to - * save it. - */ - if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) - vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - - x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); - /* All fields are clean at this point */ if (static_branch_unlikely(&enable_evmcs)) current_evmcs->hv_clean_fields |= diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index f3c06ba881a5..70dfee0dd9ef 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -392,6 +392,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr); void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu); void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp); +void vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, unsigned int flags); unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx); bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, unsigned int flags);

From: Josh Poimboeuf jpoimboe@kernel.org

stable inclusion from stable-v5.10.133 commit 4d7f72b6e1bc630bec7e4cd51814bc2b092bf153 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 9756bba28470722dacb79ffce554336dd1f6a6cd upstream.

Prevent RSB underflow/poisoning attacks with RSB. While at it, add a bunch of comments to attempt to document the current state of tribal knowledge about RSB attacks and what exactly is being mitigated.

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/cpufeatures.h | 2 +- arch/x86/kernel/cpu/bugs.c | 63 +++++++++++++++++++++++++++--- arch/x86/kvm/vmx/vmenter.S | 6 +-- 3 files changed, 62 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 4cba3c1d8b79..0e97fc744d61 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -204,7 +204,7 @@ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ -/* FREE! ( 7*32+13) */ +#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 4157991053d1..5e88663591bb 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1357,16 +1357,69 @@ static void __init spectre_v2_select_mitigation(void) pr_info("%s\n", spectre_v2_strings[mode]);

/* - * If spectre v2 protection has been enabled, unconditionally fill - * RSB during a context switch; this protects against two independent - * issues: + * If Spectre v2 protection has been enabled, fill the RSB during a + * context switch. In general there are two types of RSB attacks + * across context switches, for which the CALLs/RETs may be unbalanced. * - * - RSB underflow (and switch to BTB) on Skylake+ - * - SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs + * 1) RSB underflow + * + * Some Intel parts have "bottomless RSB". When the RSB is empty, + * speculated return targets may come from the branch predictor, + * which could have a user-poisoned BTB or BHB entry. + * + * AMD has it even worse: *all* returns are speculated from the BTB, + * regardless of the state of the RSB. + * + * When IBRS or eIBRS is enabled, the "user -> kernel" attack + * scenario is mitigated by the IBRS branch prediction isolation + * properties, so the RSB buffer filling wouldn't be necessary to + * protect against this type of attack. + * + * The "user -> user" attack scenario is mitigated by RSB filling. + * + * 2) Poisoned RSB entry + * + * If the 'next' in-kernel return stack is shorter than 'prev', + * 'next' could be tricked into speculating with a user-poisoned RSB + * entry. + * + * The "user -> kernel" attack scenario is mitigated by SMEP and + * eIBRS. + * + * The "user -> user" scenario, also known as SpectreBHB, requires + * RSB clearing. + * + * So to mitigate all cases, unconditionally fill RSB on context + * switches. + * + * FIXME: Is this pointless for retbleed-affected AMD? */ setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");

+ /* + * Similar to context switches, there are two types of RSB attacks + * after vmexit: + * + * 1) RSB underflow + * + * 2) Poisoned RSB entry + * + * When retpoline is enabled, both are mitigated by filling/clearing + * the RSB. + * + * When IBRS is enabled, while #1 would be mitigated by the IBRS branch + * prediction isolation protections, RSB still needs to be cleared + * because of #2. Note that SMEP provides no protection here, unlike + * user-space-poisoned RSB entries. + * + * eIBRS, on the other hand, has RSB-poisoning protections, so it + * doesn't need RSB clearing after vmexit. + */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) || + boot_cpu_has(X86_FEATURE_KERNEL_IBRS)) + setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); + /* * Retpoline protects the kernel, but doesn't protect firmware. IBRS * and Enhanced IBRS protect firmware too, so enable IBRS around diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 1c1a3d6c2af2..857fa0fc49fa 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -193,15 +193,15 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before * the first unbalanced RET after vmexit! * - * For retpoline, RSB filling is needed to prevent poisoned RSB entries - * and (in some cases) RSB underflow. + * For retpoline or IBRS, RSB filling is needed to prevent poisoned RSB + * entries and (in some cases) RSB underflow. * * eIBRS has its own protection against poisoned RSB, so it doesn't * need the RSB filling sequence. But it does need to be enabled * before the first unbalanced RET. */

- FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT

pop %_ASM_ARG2 /* @flags */ pop %_ASM_ARG1 /* @vmx */

From: Andrew Cooper andrew.cooper3@citrix.com

stable inclusion from stable-v5.10.133 commit f7851ed697be2ce86bd8baf29111762b7b3ff6cc category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 26aae8ccbc1972233afd08fb3f368947c0314265 upstream.

BTC_NO indicates that hardware is not susceptible to Branch Type Confusion.

Zen3 CPUs don't suffer BTC.

Hypervisors are expected to synthesise BTC_NO when it is appropriate given the migration pool, to prevent kernels using heuristics.

[ bp: Massage. ]

Signed-off-by: Andrew Cooper andrew.cooper3@citrix.com Signed-off-by: Borislav Petkov bp@suse.de [cascardo: no X86_FEATURE_BRS] [cascardo: no X86_FEATURE_CPPC] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/amd.c | 21 +++++++++++++++------ arch/x86/kernel/cpu/common.c | 6 ++++-- 3 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 0e97fc744d61..ca4895c69654 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -315,6 +315,7 @@ #define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ +#define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */

/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f1f52e67e361..a2a7f0275e36 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -942,12 +942,21 @@ static void init_amd_zn(struct cpuinfo_x86 *c) node_reclaim_distance = 32; #endif

- /* - * Fix erratum 1076: CPB feature bit not being set in CPUID. - * Always set it, except when running under a hypervisor. - */ - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_CPB)) - set_cpu_cap(c, X86_FEATURE_CPB); + /* Fix up CPUID bits, but only if not virtualised. */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { + + /* Erratum 1076: CPB feature bit not being set in CPUID. */ + if (!cpu_has(c, X86_FEATURE_CPB)) + set_cpu_cap(c, X86_FEATURE_CPB); + + /* + * Zen3 (Fam19 model < 0x10) parts are not susceptible to + * Branch Type Confusion, but predate the allocation of the + * BTC_NO bit. + */ + if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO)) + set_cpu_cap(c, X86_FEATURE_BTC_NO); + } }

static void init_amd(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a1051a036833..3364498f5537 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1246,8 +1246,10 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) !arch_cap_mmio_immune(ia32_cap)) setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);

- if ((cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA))) - setup_force_cpu_bug(X86_BUG_RETBLEED); + if (!cpu_has(c, X86_FEATURE_BTC_NO)) { + if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA)) + setup_force_cpu_bug(X86_BUG_RETBLEED); + }

if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return;

From: Pawan Gupta pawan.kumar.gupta@linux.intel.com

stable inclusion from stable-v5.10.133 commit 609336351d08699395be24860902e6e0b7860e2b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit f54d45372c6ac9c993451de5e51312485f7d10bc upstream.

Cannon lake is also affected by RETBleed, add it to the list.

Fixes: 6ad0ad2bf8a6 ("x86/bugs: Report Intel retbleed vulnerability") Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/kernel/cpu/common.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 3364498f5537..901352bd3b42 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1129,6 +1129,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO),

From: Konrad Rzeszutek Wilk konrad.wilk@oracle.com

stable inclusion from stable-v5.10.133 commit c2ca992144281917cfae19d231b1195c02906a4e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit 697977d8415d61f3acbc4ee6d564c9dcf0309507 upstream.

All the invocations unroll to __x86_return_thunk and this file must be PIC independent.

This fixes kexec on 64-bit AMD boxes.

[ bp: Fix 32-bit build. ]

Reported-by: Edward Tran edward.tran@oracle.com Reported-by: Awais Tanveer awais.tanveer@oracle.com Suggested-by: Ankur Arora ankur.a.arora@oracle.com Signed-off-by: Konrad Rzeszutek Wilk konrad.wilk@oracle.com Signed-off-by: Alexandre Chartre alexandre.chartre@oracle.com Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/kernel/relocate_kernel_32.S | 25 +++++++++++++++++++------ arch/x86/kernel/relocate_kernel_64.S | 23 +++++++++++++++++------ 2 files changed, 36 insertions(+), 12 deletions(-)

diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index 8190136cc63a..82a839885a3c 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -7,10 +7,12 @@ #include <linux/linkage.h> #include <asm/page_types.h> #include <asm/kexec.h> +#include <asm/nospec-branch.h> #include <asm/processor-flags.h>

/* - * Must be relocatable PIC code callable as a C function + * Must be relocatable PIC code callable as a C function, in particular + * there must be a plain RET and not jump to return thunk. */

#define PTR(x) (x << 2) @@ -91,7 +93,9 @@ SYM_CODE_START_NOALIGN(relocate_kernel) movl %edi, %eax addl $(identity_mapped - relocate_kernel), %eax pushl %eax - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(relocate_kernel)

SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) @@ -159,12 +163,15 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) xorl %edx, %edx xorl %esi, %esi xorl %ebp, %ebp - RET + ANNOTATE_UNRET_SAFE + ret + int3 1: popl %edx movl CP_PA_SWAP_PAGE(%edi), %esp addl $PAGE_SIZE, %esp 2: + ANNOTATE_RETPOLINE_SAFE call *%edx

/* get the re-entry point of the peer system */ @@ -190,7 +197,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) movl %edi, %eax addl $(virtual_mapped - relocate_kernel), %eax pushl %eax - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(identity_mapped)

SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) @@ -208,7 +217,9 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) popl %edi popl %esi popl %ebx - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(virtual_mapped)

/* Do the copies */ @@ -271,7 +282,9 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) popl %edi popl %ebx popl %ebp - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(swap_pages)

.globl kexec_control_code_size diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index a0ae167b1aeb..d2b7d212caa4 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -13,7 +13,8 @@ #include <asm/unwind_hints.h>

/* - * Must be relocatable PIC code callable as a C function + * Must be relocatable PIC code callable as a C function, in particular + * there must be a plain RET and not jump to return thunk. */

#define PTR(x) (x << 3) @@ -104,7 +105,9 @@ SYM_CODE_START_NOALIGN(relocate_kernel) /* jump to identity mapped page */ addq $(identity_mapped - relocate_kernel), %r8 pushq %r8 - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(relocate_kernel)

SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) @@ -191,7 +194,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) xorl %r14d, %r14d xorl %r15d, %r15d

- RET + ANNOTATE_UNRET_SAFE + ret + int3

1: popq %rdx @@ -210,7 +215,9 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) call swap_pages movq $virtual_mapped, %rax pushq %rax - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(identity_mapped)

SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) @@ -231,7 +238,9 @@ SYM_CODE_START_LOCAL_NOALIGN(virtual_mapped) popq %r12 popq %rbp popq %rbx - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(virtual_mapped)

/* Do the copies */ @@ -288,7 +297,9 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) lea PAGE_SIZE(%rax), %rsi jmp 0b 3: - RET + ANNOTATE_UNRET_SAFE + ret + int3 SYM_CODE_END(swap_pages)

.globl kexec_control_code_size

From: Thomas Gleixner tglx@linutronix.de

stable inclusion from stable-v5.10.133 commit c035ca88b0742952150b1671bb5d26b96f921245 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit c27c753ea6fd1237f4f96abf8b623d7bab505513 upstream.

__static_call_fixup() invokes __static_call_transform() without holding text_mutex, which causes lockdep to complain in text_poke_bp().

Adding the proper locking cures that, but as this is either used during early boot or during module finalizing, it's not required to use text_poke_bp(). Add an argument to __static_call_transform() which tells it to use text_poke_early() for it.

Fixes: ee88d363d156 ("x86,static_call: Use alternative RET encoding") Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

conflict: arch/x86/kernel/static_call.c

Signed-off-by: Lin Yujun linyujun809@huawei.com Reviewed-by: Zhang Jianhua chris.zjh@huawei.com --- arch/x86/kernel/static_call.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 9e5cc3cb6524..9339130112ec 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -26,7 +26,8 @@ static const u8 tramp_ud[] = { 0x0f, 0xb9, 0xcc };

static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };

-static void __ref __static_call_transform(void *insn, enum insn_type type, void *func) +static void __ref __static_call_transform(void *insn, enum insn_type type, + void *func, bool modinit) { const void *emulate = NULL; int size = CALL_INSN_SIZE; @@ -61,7 +62,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void if (memcmp(insn, code, size) == 0) return;

- if (unlikely(system_state == SYSTEM_BOOTING)) + if (system_state == SYSTEM_BOOTING || modinit) return text_poke_early(insn, code, size);

text_poke_bp(insn, code, size, emulate); @@ -109,12 +110,12 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)

if (tramp) { __static_call_validate(tramp, true); - __static_call_transform(tramp, __sc_insn(!func, true), func); + __static_call_transform(tramp, __sc_insn(!func, true), func, false); }

if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site) { __static_call_validate(site, tail); - __static_call_transform(site, __sc_insn(!func, tail), func); + __static_call_transform(site, __sc_insn(!func, tail), func, false); }

mutex_unlock(&text_mutex); @@ -140,8 +141,10 @@ bool __static_call_fixup(void *tramp, u8 op, void *dest) return false; }

+ mutex_lock(&text_mutex); if (op == RET_INSN_OPCODE || dest == &__x86_return_thunk) - __static_call_transform(tramp, RET, NULL); + __static_call_transform(tramp, RET, NULL, true); + mutex_unlock(&text_mutex);

return true; }