Merge branch 'perf/urgent' into perf/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

5 files changed, 311 insertions, 35 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/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;
+}