summaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/objtool/Documentation/stack-validation.txt38
-rw-r--r--tools/objtool/builtin-check.c97
-rw-r--r--tools/perf/util/intel-pt.c2
-rw-r--r--tools/power/x86/turbostat/turbostat.c117
-rw-r--r--tools/testing/selftests/net/.gitignore1
-rw-r--r--tools/testing/selftests/net/Makefile2
-rw-r--r--tools/testing/selftests/net/reuseport_dualstack.c208
-rw-r--r--tools/testing/selftests/seccomp/seccomp_bpf.c22
8 files changed, 430 insertions, 57 deletions
diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/stack-validation.txt
index 5a95896105bc..55a60d331f47 100644
--- a/tools/objtool/Documentation/stack-validation.txt
+++ b/tools/objtool/Documentation/stack-validation.txt
@@ -299,18 +299,38 @@ they mean, and suggestions for how to fix them.
Errors in .c files
------------------
-If you're getting an objtool error in a compiled .c file, chances are
-the file uses an asm() statement which has a "call" instruction. An
-asm() statement with a call instruction must declare the use of the
-stack pointer in its output operand. For example, on x86_64:
+1. c_file.o: warning: objtool: funcA() falls through to next function funcB()
- register void *__sp asm("rsp");
- asm volatile("call func" : "+r" (__sp));
+ This means that funcA() doesn't end with a return instruction or an
+ unconditional jump, and that objtool has determined that the function
+ can fall through into the next function. There could be different
+ reasons for this:
-Otherwise the stack frame may not get created before the call.
+ 1) funcA()'s last instruction is a call to a "noreturn" function like
+ panic(). In this case the noreturn function needs to be added to
+ objtool's hard-coded global_noreturns array. Feel free to bug the
+ objtool maintainer, or you can submit a patch.
-Another possible cause for errors in C code is if the Makefile removes
--fno-omit-frame-pointer or adds -fomit-frame-pointer to the gcc options.
+ 2) funcA() uses the unreachable() annotation in a section of code
+ that is actually reachable.
+
+ 3) If funcA() calls an inline function, the object code for funcA()
+ might be corrupt due to a gcc bug. For more details, see:
+ https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70646
+
+2. If you're getting any other objtool error in a compiled .c file, it
+ may be because the file uses an asm() statement which has a "call"
+ instruction. An asm() statement with a call instruction must declare
+ the use of the stack pointer in its output operand. For example, on
+ x86_64:
+
+ register void *__sp asm("rsp");
+ asm volatile("call func" : "+r" (__sp));
+
+ Otherwise the stack frame may not get created before the call.
+
+3. Another possible cause for errors in C code is if the Makefile removes
+ -fno-omit-frame-pointer or adds -fomit-frame-pointer to the gcc options.
Also see the above section for .S file errors for more information what
the individual error messages mean.
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 7515cb2e879a..e8a1e69eb92c 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -54,6 +54,7 @@ struct instruction {
struct symbol *call_dest;
struct instruction *jump_dest;
struct list_head alts;
+ struct symbol *func;
};
struct alternative {
@@ -66,6 +67,7 @@ struct objtool_file {
struct list_head insn_list;
DECLARE_HASHTABLE(insn_hash, 16);
struct section *rodata, *whitelist;
+ bool ignore_unreachables, c_file;
};
const char *objname;
@@ -228,7 +230,7 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
}
}
- if (insn->type == INSN_JUMP_DYNAMIC)
+ if (insn->type == INSN_JUMP_DYNAMIC && list_empty(&insn->alts))
/* sibling call */
return 0;
}
@@ -248,6 +250,7 @@ static int dead_end_function(struct objtool_file *file, struct symbol *func)
static int decode_instructions(struct objtool_file *file)
{
struct section *sec;
+ struct symbol *func;
unsigned long offset;
struct instruction *insn;
int ret;
@@ -281,6 +284,21 @@ static int decode_instructions(struct objtool_file *file)
hash_add(file->insn_hash, &insn->hash, insn->offset);
list_add_tail(&insn->list, &file->insn_list);
}
+
+ list_for_each_entry(func, &sec->symbol_list, list) {
+ if (func->type != STT_FUNC)
+ continue;
+
+ if (!find_insn(file, sec, func->offset)) {
+ WARN("%s(): can't find starting instruction",
+ func->name);
+ return -1;
+ }
+
+ func_for_each_insn(file, func, insn)
+ if (!insn->func)
+ insn->func = func;
+ }
}
return 0;
@@ -664,13 +682,40 @@ static int add_func_switch_tables(struct objtool_file *file,
text_rela->addend);
/*
- * TODO: Document where this is needed, or get rid of it.
- *
* rare case: jmpq *[addr](%rip)
+ *
+ * This check is for a rare gcc quirk, currently only seen in
+ * three driver functions in the kernel, only with certain
+ * obscure non-distro configs.
+ *
+ * As part of an optimization, gcc makes a copy of an existing
+ * switch jump table, modifies it, and then hard-codes the jump
+ * (albeit with an indirect jump) to use a single entry in the
+ * table. The rest of the jump table and some of its jump
+ * targets remain as dead code.
+ *
+ * In such a case we can just crudely ignore all unreachable
+ * instruction warnings for the entire object file. Ideally we
+ * would just ignore them for the function, but that would
+ * require redesigning the code quite a bit. And honestly
+ * that's just not worth doing: unreachable instruction
+ * warnings are of questionable value anyway, and this is such
+ * a rare issue.
+ *
+ * kbuild reports:
+ * - https://lkml.kernel.org/r/201603231906.LWcVUpxm%25fengguang.wu@intel.com
+ * - https://lkml.kernel.org/r/201603271114.K9i45biy%25fengguang.wu@intel.com
+ * - https://lkml.kernel.org/r/201603291058.zuJ6ben1%25fengguang.wu@intel.com
+ *
+ * gcc bug:
+ * - https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70604
*/
- if (!rodata_rela)
+ if (!rodata_rela) {
rodata_rela = find_rela_by_dest(file->rodata,
text_rela->addend + 4);
+ if (rodata_rela)
+ file->ignore_unreachables = true;
+ }
if (!rodata_rela)
continue;
@@ -732,9 +777,6 @@ static int decode_sections(struct objtool_file *file)
{
int ret;
- file->whitelist = find_section_by_name(file->elf, "__func_stack_frame_non_standard");
- file->rodata = find_section_by_name(file->elf, ".rodata");
-
ret = decode_instructions(file);
if (ret)
return ret;
@@ -799,6 +841,7 @@ static int validate_branch(struct objtool_file *file,
struct alternative *alt;
struct instruction *insn;
struct section *sec;
+ struct symbol *func = NULL;
unsigned char state;
int ret;
@@ -813,6 +856,16 @@ static int validate_branch(struct objtool_file *file,
}
while (1) {
+ if (file->c_file && insn->func) {
+ if (func && func != insn->func) {
+ WARN("%s() falls through to next function %s()",
+ func->name, insn->func->name);
+ return 1;
+ }
+
+ func = insn->func;
+ }
+
if (insn->visited) {
if (frame_state(insn->state) != frame_state(state)) {
WARN_FUNC("frame pointer state mismatch",
@@ -823,13 +876,6 @@ static int validate_branch(struct objtool_file *file,
return 0;
}
- /*
- * Catch a rare case where a noreturn function falls through to
- * the next function.
- */
- if (is_fentry_call(insn) && (state & STATE_FENTRY))
- return 0;
-
insn->visited = true;
insn->state = state;
@@ -1035,12 +1081,8 @@ static int validate_functions(struct objtool_file *file)
continue;
insn = find_insn(file, sec, func->offset);
- if (!insn) {
- WARN("%s(): can't find starting instruction",
- func->name);
- warnings++;
+ if (!insn)
continue;
- }
ret = validate_branch(file, insn, 0);
warnings += ret;
@@ -1056,13 +1098,14 @@ static int validate_functions(struct objtool_file *file)
if (insn->visited)
continue;
- if (!ignore_unreachable_insn(func, insn) &&
- !warnings) {
- WARN_FUNC("function has unreachable instruction", insn->sec, insn->offset);
- warnings++;
- }
-
insn->visited = true;
+
+ if (file->ignore_unreachables || warnings ||
+ ignore_unreachable_insn(func, insn))
+ continue;
+
+ WARN_FUNC("function has unreachable instruction", insn->sec, insn->offset);
+ warnings++;
}
}
}
@@ -1133,6 +1176,10 @@ int cmd_check(int argc, const char **argv)
INIT_LIST_HEAD(&file.insn_list);
hash_init(file.insn_hash);
+ file.whitelist = find_section_by_name(file.elf, "__func_stack_frame_non_standard");
+ file.rodata = find_section_by_name(file.elf, ".rodata");
+ file.ignore_unreachables = false;
+ file.c_file = find_section_by_name(file.elf, ".comment");
ret = decode_sections(&file);
if (ret < 0)
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 407f11b97c8d..617578440989 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1130,7 +1130,7 @@ static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
pr_err("Intel Processor Trace: failed to deliver transaction event, error %d\n",
ret);
- if (pt->synth_opts.callchain)
+ if (pt->synth_opts.last_branch)
intel_pt_reset_last_branch_rb(ptq);
return ret;
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 20a257a12ea5..acbf7ff2ee6e 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -66,6 +66,8 @@ unsigned int do_slm_cstates;
unsigned int use_c1_residency_msr;
unsigned int has_aperf;
unsigned int has_epb;
+unsigned int do_irtl_snb;
+unsigned int do_irtl_hsw;
unsigned int units = 1000000; /* MHz etc */
unsigned int genuine_intel;
unsigned int has_invariant_tsc;
@@ -187,7 +189,7 @@ struct pkg_data {
unsigned long long pkg_any_core_c0;
unsigned long long pkg_any_gfxe_c0;
unsigned long long pkg_both_core_gfxe_c0;
- unsigned long long gfx_rc6_ms;
+ long long gfx_rc6_ms;
unsigned int gfx_mhz;
unsigned int package_id;
unsigned int energy_pkg; /* MSR_PKG_ENERGY_STATUS */
@@ -621,8 +623,14 @@ int format_counters(struct thread_data *t, struct core_data *c,
outp += sprintf(outp, "%8d", p->pkg_temp_c);
/* GFXrc6 */
- if (do_gfx_rc6_ms)
- outp += sprintf(outp, "%8.2f", 100.0 * p->gfx_rc6_ms / 1000.0 / interval_float);
+ if (do_gfx_rc6_ms) {
+ if (p->gfx_rc6_ms == -1) { /* detect counter reset */
+ outp += sprintf(outp, " ***.**");
+ } else {
+ outp += sprintf(outp, "%8.2f",
+ p->gfx_rc6_ms / 10.0 / interval_float);
+ }
+ }
/* GFXMHz */
if (do_gfx_mhz)
@@ -766,7 +774,12 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
old->pc10 = new->pc10 - old->pc10;
old->pkg_temp_c = new->pkg_temp_c;
- old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms;
+ /* flag an error when rc6 counter resets/wraps */
+ if (old->gfx_rc6_ms > new->gfx_rc6_ms)
+ old->gfx_rc6_ms = -1;
+ else
+ old->gfx_rc6_ms = new->gfx_rc6_ms - old->gfx_rc6_ms;
+
old->gfx_mhz = new->gfx_mhz;
DELTA_WRAP32(new->energy_pkg, old->energy_pkg);
@@ -1296,6 +1309,7 @@ int hsw_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL__3, PCL__6, PCL__7, PCL_7S,
int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
static void
@@ -1579,6 +1593,47 @@ dump_config_tdp(void)
fprintf(outf, " lock=%d", (unsigned int)(msr >> 31) & 1);
fprintf(outf, ")\n");
}
+
+unsigned int irtl_time_units[] = {1, 32, 1024, 32768, 1048576, 33554432, 0, 0 };
+
+void print_irtl(void)
+{
+ unsigned long long msr;
+
+ get_msr(base_cpu, MSR_PKGC3_IRTL, &msr);
+ fprintf(outf, "cpu%d: MSR_PKGC3_IRTL: 0x%08llx (", base_cpu, msr);
+ fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+ (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+
+ get_msr(base_cpu, MSR_PKGC6_IRTL, &msr);
+ fprintf(outf, "cpu%d: MSR_PKGC6_IRTL: 0x%08llx (", base_cpu, msr);
+ fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+ (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+
+ get_msr(base_cpu, MSR_PKGC7_IRTL, &msr);
+ fprintf(outf, "cpu%d: MSR_PKGC7_IRTL: 0x%08llx (", base_cpu, msr);
+ fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+ (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+
+ if (!do_irtl_hsw)
+ return;
+
+ get_msr(base_cpu, MSR_PKGC8_IRTL, &msr);
+ fprintf(outf, "cpu%d: MSR_PKGC8_IRTL: 0x%08llx (", base_cpu, msr);
+ fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+ (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+
+ get_msr(base_cpu, MSR_PKGC9_IRTL, &msr);
+ fprintf(outf, "cpu%d: MSR_PKGC9_IRTL: 0x%08llx (", base_cpu, msr);
+ fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+ (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+
+ get_msr(base_cpu, MSR_PKGC10_IRTL, &msr);
+ fprintf(outf, "cpu%d: MSR_PKGC10_IRTL: 0x%08llx (", base_cpu, msr);
+ fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT",
+ (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]);
+
+}
void free_fd_percpu(void)
{
int i;
@@ -2144,6 +2199,9 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
case 0x56: /* BDX-DE */
case 0x4E: /* SKL */
case 0x5E: /* SKL */
+ case 0x8E: /* KBL */
+ case 0x9E: /* KBL */
+ case 0x55: /* SKX */
pkg_cstate_limits = hsw_pkg_cstate_limits;
break;
case 0x37: /* BYT */
@@ -2156,6 +2214,9 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
case 0x57: /* PHI */
pkg_cstate_limits = phi_pkg_cstate_limits;
break;
+ case 0x5C: /* BXT */
+ pkg_cstate_limits = bxt_pkg_cstate_limits;
+ break;
default:
return 0;
}
@@ -2248,6 +2309,9 @@ int has_config_tdp(unsigned int family, unsigned int model)
case 0x56: /* BDX-DE */
case 0x4E: /* SKL */
case 0x5E: /* SKL */
+ case 0x8E: /* KBL */
+ case 0x9E: /* KBL */
+ case 0x55: /* SKX */
case 0x57: /* Knights Landing */
return 1;
@@ -2585,13 +2649,19 @@ void rapl_probe(unsigned int family, unsigned int model)
case 0x47: /* BDW */
do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO;
break;
+ case 0x5C: /* BXT */
+ do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO;
+ break;
case 0x4E: /* SKL */
case 0x5E: /* SKL */
+ case 0x8E: /* KBL */
+ case 0x9E: /* KBL */
do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
break;
case 0x3F: /* HSX */
case 0x4F: /* BDX */
case 0x56: /* BDX-DE */
+ case 0x55: /* SKX */
case 0x57: /* KNL */
do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO;
break;
@@ -2871,6 +2941,10 @@ int has_snb_msrs(unsigned int family, unsigned int model)
case 0x56: /* BDX-DE */
case 0x4E: /* SKL */
case 0x5E: /* SKL */
+ case 0x8E: /* KBL */
+ case 0x9E: /* KBL */
+ case 0x55: /* SKX */
+ case 0x5C: /* BXT */
return 1;
}
return 0;
@@ -2879,9 +2953,14 @@ int has_snb_msrs(unsigned int family, unsigned int model)
/*
* HSW adds support for additional MSRs:
*
- * MSR_PKG_C8_RESIDENCY 0x00000630
- * MSR_PKG_C9_RESIDENCY 0x00000631
- * MSR_PKG_C10_RESIDENCY 0x00000632
+ * MSR_PKG_C8_RESIDENCY 0x00000630
+ * MSR_PKG_C9_RESIDENCY 0x00000631
+ * MSR_PKG_C10_RESIDENCY 0x00000632
+ *
+ * MSR_PKGC8_IRTL 0x00000633
+ * MSR_PKGC9_IRTL 0x00000634
+ * MSR_PKGC10_IRTL 0x00000635
+ *
*/
int has_hsw_msrs(unsigned int family, unsigned int model)
{
@@ -2893,6 +2972,9 @@ int has_hsw_msrs(unsigned int family, unsigned int model)
case 0x3D: /* BDW */
case 0x4E: /* SKL */
case 0x5E: /* SKL */
+ case 0x8E: /* KBL */
+ case 0x9E: /* KBL */
+ case 0x5C: /* BXT */
return 1;
}
return 0;
@@ -2914,6 +2996,8 @@ int has_skl_msrs(unsigned int family, unsigned int model)
switch (model) {
case 0x4E: /* SKL */
case 0x5E: /* SKL */
+ case 0x8E: /* KBL */
+ case 0x9E: /* KBL */
return 1;
}
return 0;
@@ -3187,7 +3271,7 @@ void process_cpuid()
if (debug)
decode_misc_enable_msr();
- if (max_level >= 0x7) {
+ if (max_level >= 0x7 && debug) {
int has_sgx;
ecx = 0;
@@ -3221,7 +3305,15 @@ void process_cpuid()
switch(model) {
case 0x4E: /* SKL */
case 0x5E: /* SKL */
- crystal_hz = 24000000; /* 24 MHz */
+ case 0x8E: /* KBL */
+ case 0x9E: /* KBL */
+ crystal_hz = 24000000; /* 24.0 MHz */
+ break;
+ case 0x55: /* SKX */
+ crystal_hz = 25000000; /* 25.0 MHz */
+ break;
+ case 0x5C: /* BXT */
+ crystal_hz = 19200000; /* 19.2 MHz */
break;
default:
crystal_hz = 0;
@@ -3254,11 +3346,13 @@ void process_cpuid()
do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model);
do_snb_cstates = has_snb_msrs(family, model);
+ do_irtl_snb = has_snb_msrs(family, model);
do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2);
do_pc3 = (pkg_cstate_limit >= PCL__3);
do_pc6 = (pkg_cstate_limit >= PCL__6);
do_pc7 = do_snb_cstates && (pkg_cstate_limit >= PCL__7);
do_c8_c9_c10 = has_hsw_msrs(family, model);
+ do_irtl_hsw = has_hsw_msrs(family, model);
do_skl_residency = has_skl_msrs(family, model);
do_slm_cstates = is_slm(family, model);
do_knl_cstates = is_knl(family, model);
@@ -3564,6 +3658,9 @@ void turbostat_init()
if (debug)
for_all_cpus(print_thermal, ODD_COUNTERS);
+
+ if (debug && do_irtl_snb)
+ print_irtl();
}
int fork_it(char **argv)
@@ -3629,7 +3726,7 @@ int get_and_dump_counters(void)
}
void print_version() {
- fprintf(outf, "turbostat version 4.11 27 Feb 2016"
+ fprintf(outf, "turbostat version 4.12 5 Apr 2016"
" - Len Brown <lenb@kernel.org>\n");
}
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 69bb3fc38fb2..0840684deb7d 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -3,3 +3,4 @@ psock_fanout
psock_tpacket
reuseport_bpf
reuseport_bpf_cpu
+reuseport_dualstack
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index c658792d47b4..0e5340742620 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -4,7 +4,7 @@ CFLAGS = -Wall -O2 -g
CFLAGS += -I../../../../usr/include/
-NET_PROGS = socket psock_fanout psock_tpacket reuseport_bpf reuseport_bpf_cpu
+NET_PROGS = socket psock_fanout psock_tpacket reuseport_bpf reuseport_bpf_cpu reuseport_dualstack
all: $(NET_PROGS)
%: %.c
diff --git a/tools/testing/selftests/net/reuseport_dualstack.c b/tools/testing/selftests/net/reuseport_dualstack.c
new file mode 100644
index 000000000000..90958aaaafb9
--- /dev/null
+++ b/tools/testing/selftests/net/reuseport_dualstack.c
@@ -0,0 +1,208 @@
+/*
+ * It is possible to use SO_REUSEPORT to open multiple sockets bound to
+ * equivalent local addresses using AF_INET and AF_INET6 at the same time. If
+ * the AF_INET6 socket has IPV6_V6ONLY set, it's clear which socket should
+ * receive a given incoming packet. However, when it is not set, incoming v4
+ * packets should prefer the AF_INET socket(s). This behavior was defined with
+ * the original SO_REUSEPORT implementation, but broke with
+ * e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection")
+ * This test creates these mixed AF_INET/AF_INET6 sockets and asserts the
+ * AF_INET preference for v4 packets.
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <linux/in.h>
+#include <linux/unistd.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/epoll.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+static const int PORT = 8888;
+
+static void build_rcv_fd(int family, int proto, int *rcv_fds, int count)
+{
+ struct sockaddr_storage addr;
+ struct sockaddr_in *addr4;
+ struct sockaddr_in6 *addr6;
+ int opt, i;
+
+ switch (family) {
+ case AF_INET:
+ addr4 = (struct sockaddr_in *)&addr;
+ addr4->sin_family = AF_INET;
+ addr4->sin_addr.s_addr = htonl(INADDR_ANY);
+ addr4->sin_port = htons(PORT);
+ break;
+ case AF_INET6:
+ addr6 = (struct sockaddr_in6 *)&addr;
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_addr = in6addr_any;
+ addr6->sin6_port = htons(PORT);
+ break;
+ default:
+ error(1, 0, "Unsupported family %d", family);
+ }
+
+ for (i = 0; i < count; ++i) {
+ rcv_fds[i] = socket(family, proto, 0);
+ if (rcv_fds[i] < 0)
+ error(1, errno, "failed to create receive socket");
+
+ opt = 1;
+ if (setsockopt(rcv_fds[i], SOL_SOCKET, SO_REUSEPORT, &opt,
+ sizeof(opt)))
+ error(1, errno, "failed to set SO_REUSEPORT");
+
+ if (bind(rcv_fds[i], (struct sockaddr *)&addr, sizeof(addr)))
+ error(1, errno, "failed to bind receive socket");
+
+ if (proto == SOCK_STREAM && listen(rcv_fds[i], 10))
+ error(1, errno, "failed to listen on receive port");
+ }
+}
+
+static void send_from_v4(int proto)
+{
+ struct sockaddr_in saddr, daddr;
+ int fd;
+
+ saddr.sin_family = AF_INET;
+ saddr.sin_addr.s_addr = htonl(INADDR_ANY);
+ saddr.sin_port = 0;
+
+ daddr.sin_family = AF_INET;
+ daddr.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+ daddr.sin_port = htons(PORT);
+
+ fd = socket(AF_INET, proto, 0);
+ if (fd < 0)
+ error(1, errno, "failed to create send socket");
+
+ if (bind(fd, (struct sockaddr *)&saddr, sizeof(saddr)))
+ error(1, errno, "failed to bind send socket");
+
+ if (connect(fd, (struct sockaddr *)&daddr, sizeof(daddr)))
+ error(1, errno, "failed to connect send socket");
+
+ if (send(fd, "a", 1, 0) < 0)
+ error(1, errno, "failed to send message");
+
+ close(fd);
+}
+
+static int receive_once(int epfd, int proto)
+{
+ struct epoll_event ev;
+ int i, fd;
+ char buf[8];
+
+ i = epoll_wait(epfd, &ev, 1, -1);
+ if (i < 0)
+ error(1, errno, "epoll_wait failed");
+
+ if (proto == SOCK_STREAM) {
+ fd = accept(ev.data.fd, NULL, NULL);
+ if (fd < 0)
+ error(1, errno, "failed to accept");
+ i = recv(fd, buf, sizeof(buf), 0);
+ close(fd);
+ } else {
+ i = recv(ev.data.fd, buf, sizeof(buf), 0);
+ }
+
+ if (i < 0)
+ error(1, errno, "failed to recv");
+
+ return ev.data.fd;
+}
+
+static void test(int *rcv_fds, int count, int proto)
+{
+ struct epoll_event ev;
+ int epfd, i, test_fd;
+ uint16_t test_family;
+ socklen_t len;
+
+ epfd = epoll_create(1);
+ if (epfd < 0)
+ error(1, errno, "failed to create epoll");
+
+ ev.events = EPOLLIN;
+ for (i = 0; i < count; ++i) {
+ ev.data.fd = rcv_fds[i];
+ if (epoll_ctl(epfd, EPOLL_CTL_ADD, rcv_fds[i], &ev))
+ error(1, errno, "failed to register sock epoll");
+ }
+
+ send_from_v4(proto);
+
+ test_fd = receive_once(epfd, proto);
+ if (getsockopt(test_fd, SOL_SOCKET, SO_DOMAIN, &test_family, &len))
+ error(1, errno, "failed to read socket domain");
+ if (test_family != AF_INET)
+ error(1, 0, "expected to receive on v4 socket but got v6 (%d)",
+ test_family);
+
+ close(epfd);
+}
+
+int main(void)
+{
+ int rcv_fds[32], i;
+
+ fprintf(stderr, "---- UDP IPv4 created before IPv6 ----\n");
+ build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 5);
+ build_rcv_fd(AF_INET6, SOCK_DGRAM, &(rcv_fds[5]), 5);
+ test(rcv_fds, 10, SOCK_DGRAM);
+ for (i = 0; i < 10; ++i)
+ close(rcv_fds[i]);
+
+ fprintf(stderr, "---- UDP IPv6 created before IPv4 ----\n");
+ build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds, 5);
+ build_rcv_fd(AF_INET, SOCK_DGRAM, &(rcv_fds[5]), 5);
+ test(rcv_fds, 10, SOCK_DGRAM);
+ for (i = 0; i < 10; ++i)
+ close(rcv_fds[i]);
+
+ /* NOTE: UDP socket lookups traverse a different code path when there
+ * are > 10 sockets in a group.
+ */
+ fprintf(stderr, "---- UDP IPv4 created before IPv6 (large) ----\n");
+ build_rcv_fd(AF_INET, SOCK_DGRAM, rcv_fds, 16);
+ build_rcv_fd(AF_INET6, SOCK_DGRAM, &(rcv_fds[16]), 16);
+ test(rcv_fds, 32, SOCK_DGRAM);
+ for (i = 0; i < 32; ++i)
+ close(rcv_fds[i]);
+
+ fprintf(stderr, "---- UDP IPv6 created before IPv4 (large) ----\n");
+ build_rcv_fd(AF_INET6, SOCK_DGRAM, rcv_fds, 16);
+ build_rcv_fd(AF_INET, SOCK_DGRAM, &(rcv_fds[16]), 16);
+ test(rcv_fds, 32, SOCK_DGRAM);
+ for (i = 0; i < 32; ++i)
+ close(rcv_fds[i]);
+
+ fprintf(stderr, "---- TCP IPv4 created before IPv6 ----\n");
+ build_rcv_fd(AF_INET, SOCK_STREAM, rcv_fds, 5);
+ build_rcv_fd(AF_INET6, SOCK_STREAM, &(rcv_fds[5]), 5);
+ test(rcv_fds, 10, SOCK_STREAM);
+ for (i = 0; i < 10; ++i)
+ close(rcv_fds[i]);
+
+ fprintf(stderr, "---- TCP IPv6 created before IPv4 ----\n");
+ build_rcv_fd(AF_INET6, SOCK_STREAM, rcv_fds, 5);
+ build_rcv_fd(AF_INET, SOCK_STREAM, &(rcv_fds[5]), 5);
+ test(rcv_fds, 10, SOCK_STREAM);
+ for (i = 0; i < 10; ++i)
+ close(rcv_fds[i]);
+
+ fprintf(stderr, "SUCCESS\n");
+ return 0;
+}
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index b9453b838162..150829dd7998 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1497,15 +1497,15 @@ TEST_F(TRACE_syscall, syscall_dropped)
#define SECCOMP_SET_MODE_FILTER 1
#endif
-#ifndef SECCOMP_FLAG_FILTER_TSYNC
-#define SECCOMP_FLAG_FILTER_TSYNC 1
+#ifndef SECCOMP_FILTER_FLAG_TSYNC
+#define SECCOMP_FILTER_FLAG_TSYNC 1
#endif
#ifndef seccomp
-int seccomp(unsigned int op, unsigned int flags, struct sock_fprog *filter)
+int seccomp(unsigned int op, unsigned int flags, void *args)
{
errno = 0;
- return syscall(__NR_seccomp, op, flags, filter);
+ return syscall(__NR_seccomp, op, flags, args);
}
#endif
@@ -1613,7 +1613,7 @@ TEST(TSYNC_first)
TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
}
- ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
&prog);
ASSERT_NE(ENOSYS, errno) {
TH_LOG("Kernel does not support seccomp syscall!");
@@ -1831,7 +1831,7 @@ TEST_F(TSYNC, two_siblings_with_ancestor)
self->sibling_count++;
}
- ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
&self->apply_prog);
ASSERT_EQ(0, ret) {
TH_LOG("Could install filter on all threads!");
@@ -1892,7 +1892,7 @@ TEST_F(TSYNC, two_siblings_with_no_filter)
TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
}
- ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
&self->apply_prog);
ASSERT_NE(ENOSYS, errno) {
TH_LOG("Kernel does not support seccomp syscall!");
@@ -1940,7 +1940,7 @@ TEST_F(TSYNC, two_siblings_with_one_divergence)
self->sibling_count++;
}
- ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
&self->apply_prog);
ASSERT_EQ(self->sibling[0].system_tid, ret) {
TH_LOG("Did not fail on diverged sibling.");
@@ -1992,7 +1992,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter)
TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!");
}
- ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
&self->apply_prog);
ASSERT_EQ(ret, self->sibling[0].system_tid) {
TH_LOG("Did not fail on diverged sibling.");
@@ -2021,7 +2021,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter)
/* Switch to the remaining sibling */
sib = !sib;
- ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
&self->apply_prog);
ASSERT_EQ(0, ret) {
TH_LOG("Expected the remaining sibling to sync");
@@ -2044,7 +2044,7 @@ TEST_F(TSYNC, two_siblings_not_under_filter)
while (!kill(self->sibling[sib].system_tid, 0))
sleep(0.1);
- ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_TSYNC,
&self->apply_prog);
ASSERT_EQ(0, ret); /* just us chickens */
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-22 08:37:50 +0000