[GIT pull] core fixes for 4.17

From: Thomas Gleixner
Date: Sun May 20 2018 - 03:25:56 EST

Linus,

please pull the latest core-urgent-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core-urgent-for-linus

The pull request provides:

- Unbreak the BPF compilation which got broken by the unconditional
requirement of asm-goto, which is not supported by clang.

- Prevent probing on exception masking instructions in uprobes and kprobes
to avoid the issues of the delayed exceptions instead of having an ugly
workaround.

- Prevent a double free_page() in the error path of do_kexec_load()

- A set of objtool updates addressing various issues mostly related to
switch tables and the noreturn detection for recursive sibling calls

- Header sync for tools.


Thanks,

tglx

------------------>
Alexei Starovoitov (1):
x86/cpufeature: Guard asm_volatile_goto usage for BPF compilation

Ingo Molnar (1):
objtool, kprobes/x86: Sync the latest <asm/insn.h> header with tools/objtool/arch/x86/include/asm/insn.h

Josh Poimboeuf (5):
objtool: Fix "noreturn" detection for recursive sibling calls
objtool: Support GCC 8's cold subfunctions
objtool: Support GCC 8 switch tables
objtool: Detect RIP-relative switch table references
objtool: Detect RIP-relative switch table references, part 2

Masami Hiramatsu (2):
kprobes/x86: Prohibit probing on exception masking instructions
uprobes/x86: Prohibit probing on MOV SS instruction

Tetsuo Handa (1):
x86/kexec: Avoid double free_page() upon do_kexec_load() failure


arch/x86/include/asm/cpufeature.h | 15 +++
arch/x86/include/asm/insn.h | 18 ++++
arch/x86/kernel/kprobes/core.c | 4 +
arch/x86/kernel/machine_kexec_32.c | 6 +-
arch/x86/kernel/machine_kexec_64.c | 5 +-
arch/x86/kernel/uprobes.c | 4 +
samples/bpf/Makefile | 2 +-
tools/objtool/arch/x86/include/asm/insn.h | 18 ++++
tools/objtool/check.c | 167 +++++++++++++++++-------------
tools/objtool/elf.c | 42 +++++++-
tools/objtool/elf.h | 2 +
11 files changed, 206 insertions(+), 77 deletions(-)

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index b27da9602a6d..aced6c9290d6 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -140,6 +140,20 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);

#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)

+#if defined(__clang__) && !defined(CC_HAVE_ASM_GOTO)
+
+/*
+ * Workaround for the sake of BPF compilation which utilizes kernel
+ * headers, but clang does not support ASM GOTO and fails the build.
+ */
+#ifndef __BPF_TRACING__
+#warning "Compiler lacks ASM_GOTO support. Add -D __BPF_TRACING__ to your compiler arguments"
+#endif
+
+#define static_cpu_has(bit) boot_cpu_has(bit)
+
+#else
+
/*
* Static testing of CPU features. Used the same as boot_cpu_has().
* These will statically patch the target code for additional
@@ -195,6 +209,7 @@ static __always_inline __pure bool _static_cpu_has(u16 bit)
boot_cpu_has(bit) : \
_static_cpu_has(bit) \
)
+#endif

#define cpu_has_bug(c, bit) cpu_has(c, (bit))
#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit))
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index b3e32b010ab1..c2c01f84df75 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn)
return insn_offset_displacement(insn) + insn->displacement.nbytes;
}

+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+ return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+ (insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+ X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
#endif /* _ASM_X86_INSN_H */
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 0715f827607c..6f4d42377fe5 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -370,6 +370,10 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
return 0;

+ /* We should not singlestep on the exception masking instructions */
+ if (insn_masking_exception(insn))
+ return 0;
+
#ifdef CONFIG_X86_64
/* Only x86_64 has RIP relative instructions */
if (insn_rip_relative(insn)) {
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 60cdec6628b0..d1ab07ec8c9a 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -57,12 +57,17 @@ static void load_segments(void)
static void machine_kexec_free_page_tables(struct kimage *image)
{
free_page((unsigned long)image->arch.pgd);
+ image->arch.pgd = NULL;
#ifdef CONFIG_X86_PAE
free_page((unsigned long)image->arch.pmd0);
+ image->arch.pmd0 = NULL;
free_page((unsigned long)image->arch.pmd1);
+ image->arch.pmd1 = NULL;
#endif
free_page((unsigned long)image->arch.pte0);
+ image->arch.pte0 = NULL;
free_page((unsigned long)image->arch.pte1);
+ image->arch.pte1 = NULL;
}

static int machine_kexec_alloc_page_tables(struct kimage *image)
@@ -79,7 +84,6 @@ static int machine_kexec_alloc_page_tables(struct kimage *image)
!image->arch.pmd0 || !image->arch.pmd1 ||
#endif
!image->arch.pte0 || !image->arch.pte1) {
- machine_kexec_free_page_tables(image);
return -ENOMEM;
}
return 0;
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index a5e55d832d0a..6010449ca6d2 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -39,9 +39,13 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
static void free_transition_pgtable(struct kimage *image)
{
free_page((unsigned long)image->arch.p4d);
+ image->arch.p4d = NULL;
free_page((unsigned long)image->arch.pud);
+ image->arch.pud = NULL;
free_page((unsigned long)image->arch.pmd);
+ image->arch.pmd = NULL;
free_page((unsigned long)image->arch.pte);
+ image->arch.pte = NULL;
}

static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
@@ -91,7 +95,6 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC));
return 0;
err:
- free_transition_pgtable(image);
return result;
}

diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 85c7ef23d99f..c84bb5396958 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -299,6 +299,10 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
if (is_prefix_bad(insn))
return -ENOTSUPP;

+ /* We should not singlestep on the exception masking instructions */
+ if (insn_masking_exception(insn))
+ return -ENOTSUPP;
+
if (x86_64)
good_insns = good_insns_64;
else
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 4d6a6edd4bf6..092947676143 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -255,7 +255,7 @@ $(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h
$(obj)/%.o: $(src)/%.c
$(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \
-I$(srctree)/tools/testing/selftests/bpf/ \
- -D__KERNEL__ -Wno-unused-value -Wno-pointer-sign \
+ -D__KERNEL__ -D__BPF_TRACING__ -Wno-unused-value -Wno-pointer-sign \
-D__TARGET_ARCH_$(ARCH) -Wno-compare-distinct-pointer-types \
-Wno-gnu-variable-sized-type-not-at-end \
-Wno-address-of-packed-member -Wno-tautological-compare \
diff --git a/tools/objtool/arch/x86/include/asm/insn.h b/tools/objtool/arch/x86/include/asm/insn.h
index b3e32b010ab1..c2c01f84df75 100644
--- a/tools/objtool/arch/x86/include/asm/insn.h
+++ b/tools/objtool/arch/x86/include/asm/insn.h
@@ -208,4 +208,22 @@ static inline int insn_offset_immediate(struct insn *insn)
return insn_offset_displacement(insn) + insn->displacement.nbytes;
}

+#define POP_SS_OPCODE 0x1f
+#define MOV_SREG_OPCODE 0x8e
+
+/*
+ * Intel SDM Vol.3A 6.8.3 states;
+ * "Any single-step trap that would be delivered following the MOV to SS
+ * instruction or POP to SS instruction (because EFLAGS.TF is 1) is
+ * suppressed."
+ * This function returns true if @insn is MOV SS or POP SS. On these
+ * instructions, single stepping is suppressed.
+ */
+static inline int insn_masking_exception(struct insn *insn)
+{
+ return insn->opcode.bytes[0] == POP_SS_OPCODE ||
+ (insn->opcode.bytes[0] == MOV_SREG_OPCODE &&
+ X86_MODRM_REG(insn->modrm.bytes[0]) == 2);
+}
+
#endif /* _ASM_X86_INSN_H */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 5409f6f6c48d..3a31b238f885 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -59,6 +59,31 @@ static struct instruction *next_insn_same_sec(struct objtool_file *file,
return next;
}

+static struct instruction *next_insn_same_func(struct objtool_file *file,
+ struct instruction *insn)
+{
+ struct instruction *next = list_next_entry(insn, list);
+ struct symbol *func = insn->func;
+
+ if (!func)
+ return NULL;
+
+ if (&next->list != &file->insn_list && next->func == func)
+ return next;
+
+ /* Check if we're already in the subfunction: */
+ if (func == func->cfunc)
+ return NULL;
+
+ /* Move to the subfunction: */
+ return find_insn(file, func->cfunc->sec, func->cfunc->offset);
+}
+
+#define func_for_each_insn_all(file, func, insn) \
+ for (insn = find_insn(file, func->sec, func->offset); \
+ insn; \
+ insn = next_insn_same_func(file, insn))
+
#define func_for_each_insn(file, func, insn) \
for (insn = find_insn(file, func->sec, func->offset); \
insn && &insn->list != &file->insn_list && \
@@ -149,10 +174,14 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
if (!strcmp(func->name, global_noreturns[i]))
return 1;

- if (!func->sec)
+ if (!func->len)
return 0;

- func_for_each_insn(file, func, insn) {
+ insn = find_insn(file, func->sec, func->offset);
+ if (!insn->func)
+ return 0;
+
+ func_for_each_insn_all(file, func, insn) {
empty = false;

if (insn->type == INSN_RETURN)
@@ -167,35 +196,28 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
* case, the function's dead-end status depends on whether the target
* of the sibling call returns.
*/
- func_for_each_insn(file, func, insn) {
- if (insn->sec != func->sec ||
- insn->offset >= func->offset + func->len)
- break;
-
+ func_for_each_insn_all(file, func, insn) {
if (insn->type == INSN_JUMP_UNCONDITIONAL) {
struct instruction *dest = insn->jump_dest;
- struct symbol *dest_func;

if (!dest)
/* sibling call to another file */
return 0;

- if (dest->sec != func->sec ||
- dest->offset < func->offset ||
- dest->offset >= func->offset + func->len) {
- /* local sibling call */
- dest_func = find_symbol_by_offset(dest->sec,
- dest->offset);
- if (!dest_func)
- continue;
+ if (dest->func && dest->func->pfunc != insn->func->pfunc) {

+ /* local sibling call */
if (recursion == 5) {
- WARN_FUNC("infinite recursion (objtool bug!)",
- dest->sec, dest->offset);
- return -1;
+ /*
+ * Infinite recursion: two functions
+ * have sibling calls to each other.
+ * This is a very rare case. It means
+ * they aren't dead ends.
+ */
+ return 0;
}

- return __dead_end_function(file, dest_func,
+ return __dead_end_function(file, dest->func,
recursion + 1);
}
}
@@ -422,7 +444,7 @@ static void add_ignores(struct objtool_file *file)
if (!ignore_func(file, func))
continue;

- func_for_each_insn(file, func, insn)
+ func_for_each_insn_all(file, func, insn)
insn->ignore = true;
}
}
@@ -782,30 +804,35 @@ static int add_special_section_alts(struct objtool_file *file)
return ret;
}

-static int add_switch_table(struct objtool_file *file, struct symbol *func,
- struct instruction *insn, struct rela *table,
- struct rela *next_table)
+static int add_switch_table(struct objtool_file *file, struct instruction *insn,
+ struct rela *table, struct rela *next_table)
{
struct rela *rela = table;
struct instruction *alt_insn;
struct alternative *alt;
+ struct symbol *pfunc = insn->func->pfunc;
+ unsigned int prev_offset = 0;

list_for_each_entry_from(rela, &file->rodata->rela->rela_list, list) {
if (rela == next_table)
break;

- if (rela->sym->sec != insn->sec ||
- rela->addend <= func->offset ||
- rela->addend >= func->offset + func->len)
+ /* Make sure the switch table entries are consecutive: */
+ if (prev_offset && rela->offset != prev_offset + 8)
break;

- alt_insn = find_insn(file, insn->sec, rela->addend);
- if (!alt_insn) {
- WARN("%s: can't find instruction at %s+0x%x",
- file->rodata->rela->name, insn->sec->name,
- rela->addend);
- return -1;
- }
+ /* Detect function pointers from contiguous objects: */
+ if (rela->sym->sec == pfunc->sec &&
+ rela->addend == pfunc->offset)
+ break;
+
+ alt_insn = find_insn(file, rela->sym->sec, rela->addend);
+ if (!alt_insn)
+ break;
+
+ /* Make sure the jmp dest is in the function or subfunction: */
+ if (alt_insn->func->pfunc != pfunc)
+ break;

alt = malloc(sizeof(*alt));
if (!alt) {
@@ -815,6 +842,13 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func,

alt->insn = alt_insn;
list_add_tail(&alt->list, &insn->alts);
+ prev_offset = rela->offset;
+ }
+
+ if (!prev_offset) {
+ WARN_FUNC("can't find switch jump table",
+ insn->sec, insn->offset);
+ return -1;
}

return 0;
@@ -869,40 +903,21 @@ static struct rela *find_switch_table(struct objtool_file *file,
{
struct rela *text_rela, *rodata_rela;
struct instruction *orig_insn = insn;
+ unsigned long table_offset;

- text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len);
- if (text_rela && text_rela->sym == file->rodata->sym) {
- /* case 1 */
- rodata_rela = find_rela_by_dest(file->rodata,
- text_rela->addend);
- if (rodata_rela)
- return rodata_rela;
-
- /* case 2 */
- rodata_rela = find_rela_by_dest(file->rodata,
- text_rela->addend + 4);
- if (!rodata_rela)
- return NULL;
-
- file->ignore_unreachables = true;
- return rodata_rela;
- }
-
- /* case 3 */
/*
* Backward search using the @first_jump_src links, these help avoid
* much of the 'in between' code. Which avoids us getting confused by
* it.
*/
- for (insn = list_prev_entry(insn, list);
-
+ for (;
&insn->list != &file->insn_list &&
insn->sec == func->sec &&
insn->offset >= func->offset;

insn = insn->first_jump_src ?: list_prev_entry(insn, list)) {

- if (insn->type == INSN_JUMP_DYNAMIC)
+ if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC)
break;

/* allow small jumps within the range */
@@ -918,18 +933,29 @@ static struct rela *find_switch_table(struct objtool_file *file,
if (!text_rela || text_rela->sym != file->rodata->sym)
continue;

+ table_offset = text_rela->addend;
+ if (text_rela->type == R_X86_64_PC32)
+ table_offset += 4;
+
/*
* Make sure the .rodata address isn't associated with a
* symbol. gcc jump tables are anonymous data.
*/
- if (find_symbol_containing(file->rodata, text_rela->addend))
+ if (find_symbol_containing(file->rodata, table_offset))
continue;

- rodata_rela = find_rela_by_dest(file->rodata, text_rela->addend);
- if (!rodata_rela)
- continue;
+ rodata_rela = find_rela_by_dest(file->rodata, table_offset);
+ if (rodata_rela) {
+ /*
+ * Use of RIP-relative switch jumps is quite rare, and
+ * indicates a rare GCC quirk/bug which can leave dead
+ * code behind.
+ */
+ if (text_rela->type == R_X86_64_PC32)
+ file->ignore_unreachables = true;

- return rodata_rela;
+ return rodata_rela;
+ }
}

return NULL;
@@ -943,7 +969,7 @@ static int add_func_switch_tables(struct objtool_file *file,
struct rela *rela, *prev_rela = NULL;
int ret;

- func_for_each_insn(file, func, insn) {
+ func_for_each_insn_all(file, func, insn) {
if (!last)
last = insn;

@@ -974,8 +1000,7 @@ static int add_func_switch_tables(struct objtool_file *file,
* the beginning of another switch table in the same function.
*/
if (prev_jump) {
- ret = add_switch_table(file, func, prev_jump, prev_rela,
- rela);
+ ret = add_switch_table(file, prev_jump, prev_rela, rela);
if (ret)
return ret;
}
@@ -985,7 +1010,7 @@ static int add_func_switch_tables(struct objtool_file *file,
}

if (prev_jump) {
- ret = add_switch_table(file, func, prev_jump, prev_rela, NULL);
+ ret = add_switch_table(file, prev_jump, prev_rela, NULL);
if (ret)
return ret;
}
@@ -1749,15 +1774,13 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
while (1) {
next_insn = next_insn_same_sec(file, insn);

-
- if (file->c_file && func && insn->func && func != insn->func) {
+ if (file->c_file && func && insn->func && func != insn->func->pfunc) {
WARN("%s() falls through to next function %s()",
func->name, insn->func->name);
return 1;
}

- if (insn->func)
- func = insn->func;
+ func = insn->func ? insn->func->pfunc : NULL;

if (func && insn->ignore) {
WARN_FUNC("BUG: why am I validating an ignored function?",
@@ -1778,7 +1801,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,

i = insn;
save_insn = NULL;
- func_for_each_insn_continue_reverse(file, func, i) {
+ func_for_each_insn_continue_reverse(file, insn->func, i) {
if (i->save) {
save_insn = i;
break;
@@ -1865,7 +1888,7 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
case INSN_JUMP_UNCONDITIONAL:
if (insn->jump_dest &&
(!func || !insn->jump_dest->func ||
- func == insn->jump_dest->func)) {
+ insn->jump_dest->func->pfunc == func)) {
ret = validate_branch(file, insn->jump_dest,
state);
if (ret)
@@ -2060,7 +2083,7 @@ static int validate_functions(struct objtool_file *file)

for_each_sec(file, sec) {
list_for_each_entry(func, &sec->symbol_list, list) {
- if (func->type != STT_FUNC)
+ if (func->type != STT_FUNC || func->pfunc != func)
continue;

insn = find_insn(file, sec, func->offset);
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index c1c338661699..4e60e105583e 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -79,6 +79,19 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
return NULL;
}

+struct symbol *find_symbol_by_name(struct elf *elf, const char *name)
+{
+ struct section *sec;
+ struct symbol *sym;
+
+ list_for_each_entry(sec, &elf->sections, list)
+ list_for_each_entry(sym, &sec->symbol_list, list)
+ if (!strcmp(sym->name, name))
+ return sym;
+
+ return NULL;
+}
+
struct symbol *find_symbol_containing(struct section *sec, unsigned long offset)
{
struct symbol *sym;
@@ -203,10 +216,11 @@ static int read_sections(struct elf *elf)

static int read_symbols(struct elf *elf)
{
- struct section *symtab;
- struct symbol *sym;
+ struct section *symtab, *sec;
+ struct symbol *sym, *pfunc;
struct list_head *entry, *tmp;
int symbols_nr, i;
+ char *coldstr;

symtab = find_section_by_name(elf, ".symtab");
if (!symtab) {
@@ -281,6 +295,30 @@ static int read_symbols(struct elf *elf)
hash_add(sym->sec->symbol_hash, &sym->hash, sym->idx);
}

+ /* Create parent/child links for any cold subfunctions */
+ list_for_each_entry(sec, &elf->sections, list) {
+ list_for_each_entry(sym, &sec->symbol_list, list) {
+ if (sym->type != STT_FUNC)
+ continue;
+ sym->pfunc = sym->cfunc = sym;
+ coldstr = strstr(sym->name, ".cold.");
+ if (coldstr) {
+ coldstr[0] = '\0';
+ pfunc = find_symbol_by_name(elf, sym->name);
+ coldstr[0] = '.';
+
+ if (!pfunc) {
+ WARN("%s(): can't find parent function",
+ sym->name);
+ goto err;
+ }
+
+ sym->pfunc = pfunc;
+ pfunc->cfunc = sym;
+ }
+ }
+ }
+
return 0;

err:
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index d86e2ff14466..de5cd2ddded9 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -61,6 +61,7 @@ struct symbol {
unsigned char bind, type;
unsigned long offset;
unsigned int len;
+ struct symbol *pfunc, *cfunc;
};

struct rela {
@@ -86,6 +87,7 @@ struct elf {
struct elf *elf_open(const char *name, int flags);
struct section *find_section_by_name(struct elf *elf, const char *name);
struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
+struct symbol *find_symbol_by_name(struct elf *elf, const char *name);
struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,