Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Fun set of conflict resolutions here...

For the mac80211 stuff, these were fortunately just parallel
adds.  Trivially resolved.

In drivers/net/phy/phy.c we had a bug fix in 'net' that moved the
function phy_disable_interrupts() earlier in the file, whilst in
'net-next' the phy_error() call from this function was removed.

In net/ipv4/xfrm4_policy.c, David Ahern's changes to remove the
'rt_table_id' member of rtable collided with a bug fix in 'net' that
added a new struct member "rt_mtu_locked" which needs to be copied
over here.

The mlxsw driver conflict consisted of net-next separating
the span code and definitions into separate files, whilst
a 'net' bug fix made some changes to that moved code.

The mlx5 infiniband conflict resolution was quite non-trivial,
the RDMA tree's merge commit was used as a guide here, and
here are their notes:

====================

    Due to bug fixes found by the syzkaller bot and taken into the for-rc
    branch after development for the 4.17 merge window had already started
    being taken into the for-next branch, there were fairly non-trivial
    merge issues that would need to be resolved between the for-rc branch
    and the for-next branch.  This merge resolves those conflicts and
    provides a unified base upon which ongoing development for 4.17 can
    be based.

    Conflicts:
            drivers/infiniband/hw/mlx5/main.c - Commit 42cea83f95
            (IB/mlx5: Fix cleanup order on unload) added to for-rc and
            commit b5ca15ad7e (IB/mlx5: Add proper representors support)
            add as part of the devel cycle both needed to modify the
            init/de-init functions used by mlx5.  To support the new
            representors, the new functions added by the cleanup patch
            needed to be made non-static, and the init/de-init list
            added by the representors patch needed to be modified to
            match the init/de-init list changes made by the cleanup
            patch.
    Updates:
            drivers/infiniband/hw/mlx5/mlx5_ib.h - Update function
            prototypes added by representors patch to reflect new function
            names as changed by cleanup patch
            drivers/infiniband/hw/mlx5/ib_rep.c - Update init/de-init
            stage list to match new order from cleanup patch
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

tools/arch/x86/include/asm/cpufeatures.h

@@ -213,6 +213,7 @@
 #define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
 
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
+#define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */

tools/bpf/bpftool/common.c

@@ -55,6 +55,10 @@
 
 #include "main.h"
 
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC		0xcafe4a11
+#endif
+
 void p_err(const char *fmt, ...)
 {
 	va_list ap;

tools/include/uapi/linux/kvm.h

@@ -761,6 +761,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
 #define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
 #define KVM_GET_EMULATED_CPUID	  _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
+#define KVM_GET_MSR_FEATURE_INDEX_LIST    _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
 
 /*
  * Extension capability list.
@@ -934,6 +935,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_AIS_MIGRATION 150
 #define KVM_CAP_PPC_GET_CPU_CHAR 151
 #define KVM_CAP_S390_BPB 152
+#define KVM_CAP_GET_MSR_FEATURES 153
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

tools/objtool/check.c

@@ -1116,42 +1116,29 @@ static int read_unwind_hints(struct objtool_file *file)
 
 static int read_retpoline_hints(struct objtool_file *file)
 {
-	struct section *sec, *relasec;
+	struct section *sec;
 	struct instruction *insn;
 	struct rela *rela;
-	int i;
 
-	sec = find_section_by_name(file->elf, ".discard.retpoline_safe");
+	sec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe");
 	if (!sec)
 		return 0;
 
-	relasec = sec->rela;
-	if (!relasec) {
-		WARN("missing .rela.discard.retpoline_safe section");
-		return -1;
-	}
-
-	if (sec->len % sizeof(unsigned long)) {
-		WARN("retpoline_safe size mismatch: %d %ld", sec->len, sizeof(unsigned long));
-		return -1;
-	}
-
-	for (i = 0; i < sec->len / sizeof(unsigned long); i++) {
-		rela = find_rela_by_dest(sec, i * sizeof(unsigned long));
-		if (!rela) {
-			WARN("can't find rela for retpoline_safe[%d]", i);
+	list_for_each_entry(rela, &sec->rela_list, list) {
+		if (rela->sym->type != STT_SECTION) {
+			WARN("unexpected relocation symbol type in %s", sec->name);
 			return -1;
 		}
 
 		insn = find_insn(file, rela->sym->sec, rela->addend);
 		if (!insn) {
-			WARN("can't find insn for retpoline_safe[%d]", i);
+			WARN("bad .discard.retpoline_safe entry");
 			return -1;
 		}
 
 		if (insn->type != INSN_JUMP_DYNAMIC &&
 		    insn->type != INSN_CALL_DYNAMIC) {
-			WARN_FUNC("retpoline_safe hint not a indirect jump/call",
+			WARN_FUNC("retpoline_safe hint not an indirect jump/call",
 				  insn->sec, insn->offset);
 			return -1;
 		}

tools/perf/Documentation/perf-kallsyms.txt

@@ -8,7 +8,7 @@ perf-kallsyms - Searches running kernel for symbols
 SYNOPSIS
 --------
 [verse]
-'perf kallsyms <options> symbol_name[,symbol_name...]'
+'perf kallsyms' [<options>] symbol_name[,symbol_name...]
 
 DESCRIPTION
 -----------

tools/perf/builtin-record.c

@@ -881,6 +881,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		}
 	}
 
+	/*
+	 * If we have just single event and are sending data
+	 * through pipe, we need to force the ids allocation,
+	 * because we synthesize event name through the pipe
+	 * and need the id for that.
+	 */
+	if (data->is_pipe && rec->evlist->nr_entries == 1)
+		rec->opts.sample_id = true;
+
 	if (record__open(rec) != 0) {
 		err = -1;
 		goto out_child;

tools/perf/builtin-stat.c

@@ -917,7 +917,7 @@ static void print_metric_csv(void *ctx,
 	char buf[64], *vals, *ends;
 
 	if (unit == NULL || fmt == NULL) {
-		fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep);
+		fprintf(out, "%s%s", csv_sep, csv_sep);
 		return;
 	}
 	snprintf(buf, sizeof(buf), fmt, val);

tools/perf/builtin-top.c

@@ -991,7 +991,7 @@ static int perf_top_overwrite_fallback(struct perf_top *top,
 	evlist__for_each_entry(evlist, counter)
 		counter->attr.write_backward = false;
 	opts->overwrite = false;
-	ui__warning("fall back to non-overwrite mode\n");
+	pr_debug2("fall back to non-overwrite mode\n");
 	return 1;
 }
 

tools/perf/perf.h

@@ -61,6 +61,7 @@ struct record_opts {
 	bool	     tail_synthesize;
 	bool	     overwrite;
 	bool	     ignore_missing_thread;
+	bool	     sample_id;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int auxtrace_mmap_pages;

tools/perf/ui/browsers/annotate.c

@@ -327,7 +327,32 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 	if (!disasm_line__is_valid_jump(cursor, sym))
 		return;
 
+	/*
+	 * This first was seen with a gcc function, _cpp_lex_token, that
+	 * has the usual jumps:
+	 *
+	 *  │1159e6c: ↓ jne    115aa32 <_cpp_lex_token@@Base+0xf92>
+	 *
+	 * I.e. jumps to a label inside that function (_cpp_lex_token), and
+	 * those works, but also this kind:
+	 *
+	 *  │1159e8b: ↓ jne    c469be <cpp_named_operator2name@@Base+0xa72>
+	 *
+	 *  I.e. jumps to another function, outside _cpp_lex_token, which
+	 *  are not being correctly handled generating as a side effect references
+	 *  to ab->offset[] entries that are set to NULL, so to make this code
+	 *  more robust, check that here.
+	 *
+	 *  A proper fix for will be put in place, looking at the function
+	 *  name right after the '<' token and probably treating this like a
+	 *  'call' instruction.
+	 */
 	target = ab->offsets[cursor->ops.target.offset];
+	if (target == NULL) {
+		ui_helpline__printf("WARN: jump target inconsistency, press 'o', ab->offsets[%#x] = NULL\n",
+				    cursor->ops.target.offset);
+		return;
+	}
 
 	bcursor = browser_line(&cursor->al);
 	btarget = browser_line(target);

tools/perf/util/auxtrace.c

@@ -60,6 +60,12 @@
 #include "sane_ctype.h"
 #include "symbol/kallsyms.h"
 
+static bool auxtrace__dont_decode(struct perf_session *session)
+{
+	return !session->itrace_synth_opts ||
+	       session->itrace_synth_opts->dont_decode;
+}
+
 int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 			struct auxtrace_mmap_params *mp,
 			void *userpg, int fd)
@@ -762,6 +768,9 @@ int auxtrace_queues__process_index(struct auxtrace_queues *queues,
 	size_t i;
 	int err;
 
+	if (auxtrace__dont_decode(session))
+		return 0;
+
 	list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
 		for (i = 0; i < auxtrace_index->nr; i++) {
 			ent = &auxtrace_index->entries[i];
@@ -892,12 +901,6 @@ out_free:
 	return err;
 }
 
-static bool auxtrace__dont_decode(struct perf_session *session)
-{
-	return !session->itrace_synth_opts ||
-	       session->itrace_synth_opts->dont_decode;
-}
-
 int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
 				      union perf_event *event,
 				      struct perf_session *session)

tools/perf/util/record.c

@@ -137,6 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
 	struct perf_evsel *evsel;
 	bool use_sample_identifier = false;
 	bool use_comm_exec;
+	bool sample_id = opts->sample_id;
 
 	/*
 	 * Set the evsel leader links before we configure attributes,
@@ -163,8 +164,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
 		 * match the id.
 		 */
 		use_sample_identifier = perf_can_sample_identifier();
-		evlist__for_each_entry(evlist, evsel)
-			perf_evsel__set_sample_id(evsel, use_sample_identifier);
+		sample_id = true;
 	} else if (evlist->nr_entries > 1) {
 		struct perf_evsel *first = perf_evlist__first(evlist);
 
@@ -174,6 +174,10 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
 			use_sample_identifier = perf_can_sample_identifier();
 			break;
 		}
+		sample_id = true;
+	}
+
+	if (sample_id) {
 		evlist__for_each_entry(evlist, evsel)
 			perf_evsel__set_sample_id(evsel, use_sample_identifier);
 	}

tools/perf/util/trigger.h

@@ -12,7 +12,7 @@
  * States and transits:
  *
  *
- *  OFF--(on)--> READY --(hit)--> HIT
+ *  OFF--> ON --> READY --(hit)--> HIT
  *                 ^               |
  *                 |            (ready)
  *                 |               |
@@ -27,8 +27,9 @@ struct trigger {
 	volatile enum {
 		TRIGGER_ERROR		= -2,
 		TRIGGER_OFF		= -1,
-		TRIGGER_READY		= 0,
-		TRIGGER_HIT		= 1,
+		TRIGGER_ON		= 0,
+		TRIGGER_READY		= 1,
+		TRIGGER_HIT		= 2,
 	} state;
 	const char *name;
 };
@@ -50,7 +51,7 @@ static inline bool trigger_is_error(struct trigger *t)
 static inline void trigger_on(struct trigger *t)
 {
 	TRIGGER_WARN_ONCE(t, TRIGGER_OFF);
-	t->state = TRIGGER_READY;
+	t->state = TRIGGER_ON;
 }
 
 static inline void trigger_ready(struct trigger *t)

tools/testing/selftests/powerpc/mm/subpage_prot.c

@@ -135,6 +135,16 @@ static int run_test(void *addr, unsigned long size)
 	return 0;
 }
 
+static int syscall_available(void)
+{
+	int rc;
+
+	errno = 0;
+	rc = syscall(__NR_subpage_prot, 0, 0, 0);
+
+	return rc == 0 || (errno != ENOENT && errno != ENOSYS);
+}
+
 int test_anon(void)
 {
 	unsigned long align;
@@ -145,6 +155,8 @@ int test_anon(void)
 	void *mallocblock;
 	unsigned long mallocsize;
 
+	SKIP_IF(!syscall_available());
+
 	if (getpagesize() != 0x10000) {
 		fprintf(stderr, "Kernel page size must be 64K!\n");
 		return 1;
@@ -180,6 +192,8 @@ int test_file(void)
 	off_t filesize;
 	int fd;
 
+	SKIP_IF(!syscall_available());
+
 	fd = open(file_name, O_RDWR);
 	if (fd == -1) {
 		perror("failed to open file");

tools/testing/selftests/powerpc/tm/Makefile

@@ -16,7 +16,7 @@ $(OUTPUT)/tm-syscall: tm-syscall-asm.S
 $(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include
 $(OUTPUT)/tm-tmspr: CFLAGS += -pthread
 $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64
-$(OUTPUT)/tm-resched-dscr: ../pmu/lib.o
+$(OUTPUT)/tm-resched-dscr: ../pmu/lib.c
 $(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx
 $(OUTPUT)/tm-trap: CFLAGS += -O0 -pthread -m64
 

tools/testing/selftests/powerpc/tm/tm-trap.c

@@ -255,6 +255,8 @@ int tm_trap_test(void)
 
 	struct sigaction trap_sa;
 
+	SKIP_IF(!have_htm());
+
 	trap_sa.sa_flags = SA_SIGINFO;
 	trap_sa.sa_sigaction = trap_signal_handler;
 	sigaction(SIGTRAP, &trap_sa, NULL);

tools/testing/selftests/vm/run_vmtests

@@ -2,25 +2,33 @@
 # SPDX-License-Identifier: GPL-2.0
 #please run as root
 
-#we need 256M, below is the size in kB
-needmem=262144
 mnt=./huge
 exitcode=0
 
-#get pagesize and freepages from /proc/meminfo
+#get huge pagesize and freepages from /proc/meminfo
 while read name size unit; do
 	if [ "$name" = "HugePages_Free:" ]; then
 		freepgs=$size
 	fi
 	if [ "$name" = "Hugepagesize:" ]; then
-		pgsize=$size
+		hpgsize_KB=$size
 	fi
 done < /proc/meminfo
 
+# Simple hugetlbfs tests have a hardcoded minimum requirement of
+# huge pages totaling 256MB (262144KB) in size.  The userfaultfd
+# hugetlb test requires a minimum of 2 * nr_cpus huge pages.  Take
+# both of these requirements into account and attempt to increase
+# number of huge pages available.
+nr_cpus=$(nproc)
+hpgsize_MB=$((hpgsize_KB / 1024))
+half_ufd_size_MB=$((((nr_cpus * hpgsize_MB + 127) / 128) * 128))
+needmem_KB=$((half_ufd_size_MB * 2 * 1024))
+
 #set proper nr_hugepages
-if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then
+if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then
 	nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
-	needpgs=`expr $needmem / $pgsize`
+	needpgs=$((needmem_KB / hpgsize_KB))
 	tries=2
 	while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do
 		lackpgs=$(( $needpgs - $freepgs ))
@@ -107,8 +115,9 @@ fi
 echo "---------------------------"
 echo "running userfaultfd_hugetlb"
 echo "---------------------------"
-# 256MB total huge pages == 128MB src and 128MB dst
-./userfaultfd hugetlb 128 32 $mnt/ufd_test_file
+# Test requires source and destination huge pages.  Size of source
+# (half_ufd_size_MB) is passed as argument to test.
+./userfaultfd hugetlb $half_ufd_size_MB 32 $mnt/ufd_test_file
 if [ $? -ne 0 ]; then
 	echo "[FAIL]"
 	exitcode=1

tools/testing/selftests/x86/entry_from_vm86.c

@@ -95,6 +95,10 @@ asm (
 	"int3\n\t"
 	"vmcode_int80:\n\t"
 	"int $0x80\n\t"
+	"vmcode_popf_hlt:\n\t"
+	"push %ax\n\t"
+	"popf\n\t"
+	"hlt\n\t"
 	"vmcode_umip:\n\t"
 	/* addressing via displacements */
 	"smsw (2052)\n\t"
@@ -124,8 +128,8 @@ asm (
 
 extern unsigned char vmcode[], end_vmcode[];
 extern unsigned char vmcode_bound[], vmcode_sysenter[], vmcode_syscall[],
-	vmcode_sti[], vmcode_int3[], vmcode_int80[], vmcode_umip[],
-	vmcode_umip_str[], vmcode_umip_sldt[];
+	vmcode_sti[], vmcode_int3[], vmcode_int80[], vmcode_popf_hlt[],
+	vmcode_umip[], vmcode_umip_str[], vmcode_umip_sldt[];
 
 /* Returns false if the test was skipped. */
 static bool do_test(struct vm86plus_struct *v86, unsigned long eip,
@@ -175,7 +179,7 @@ static bool do_test(struct vm86plus_struct *v86, unsigned long eip,
 	    (VM86_TYPE(ret) == rettype && VM86_ARG(ret) == retarg)) {
 		printf("[OK]\tReturned correctly\n");
 	} else {
-		printf("[FAIL]\tIncorrect return reason\n");
+		printf("[FAIL]\tIncorrect return reason (started at eip = 0x%lx, ended at eip = 0x%lx)\n", eip, v86->regs.eip);
 		nerrs++;
 	}
 
@@ -264,6 +268,9 @@ int main(void)
 	v86.regs.ds = load_addr / 16;
 	v86.regs.es = load_addr / 16;
 
+	/* Use the end of the page as our stack. */
+	v86.regs.esp = 4096;
+
 	assert((v86.regs.cs & 3) == 0);	/* Looks like RPL = 0 */
 
 	/* #BR -- should deliver SIG??? */
@@ -295,6 +302,23 @@ int main(void)
 	v86.regs.eflags &= ~X86_EFLAGS_IF;
 	do_test(&v86, vmcode_sti - vmcode, VM86_STI, 0, "STI with VIP set");
 
+	/* POPF with VIP set but IF clear: should not trap */
+	v86.regs.eflags = X86_EFLAGS_VIP;
+	v86.regs.eax = 0;
+	do_test(&v86, vmcode_popf_hlt - vmcode, VM86_UNKNOWN, 0, "POPF with VIP set and IF clear");
+
+	/* POPF with VIP set and IF set: should trap */
+	v86.regs.eflags = X86_EFLAGS_VIP;
+	v86.regs.eax = X86_EFLAGS_IF;
+	do_test(&v86, vmcode_popf_hlt - vmcode, VM86_STI, 0, "POPF with VIP and IF set");
+
+	/* POPF with VIP clear and IF set: should not trap */
+	v86.regs.eflags = 0;
+	v86.regs.eax = X86_EFLAGS_IF;
+	do_test(&v86, vmcode_popf_hlt - vmcode, VM86_UNKNOWN, 0, "POPF with VIP clear and IF set");
+
+	v86.regs.eflags = 0;
+
 	/* INT3 -- should cause #BP */
 	do_test(&v86, vmcode_int3 - vmcode, VM86_TRAP, 3, "INT3");
 
@@ -318,7 +342,7 @@ int main(void)
 	clearhandler(SIGSEGV);
 
 	/* Make sure nothing explodes if we fork. */
-	if (fork() > 0)
+	if (fork() == 0)
 		return 0;
 
 	return (nerrs == 0 ? 0 : 1);

tools/testing/selftests/x86/test_vsyscall.c

@@ -450,7 +450,7 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
 		num_vsyscall_traps++;
 }
 
-static int test_native_vsyscall(void)
+static int test_emulation(void)
 {
 	time_t tmp;
 	bool is_native;
@@ -458,7 +458,7 @@ static int test_native_vsyscall(void)
 	if (!vtime)
 		return 0;
 
-	printf("[RUN]\tchecking for native vsyscall\n");
+	printf("[RUN]\tchecking that vsyscalls are emulated\n");
 	sethandler(SIGTRAP, sigtrap, 0);
 	set_eflags(get_eflags() | X86_EFLAGS_TF);
 	vtime(&tmp);
@@ -474,11 +474,12 @@ static int test_native_vsyscall(void)
 	 */
 	is_native = (num_vsyscall_traps > 1);
 
-	printf("\tvsyscalls are %s (%d instructions in vsyscall page)\n",
+	printf("[%s]\tvsyscalls are %s (%d instructions in vsyscall page)\n",
+	       (is_native ? "FAIL" : "OK"),
 	       (is_native ? "native" : "emulated"),
 	       (int)num_vsyscall_traps);
 
-	return 0;
+	return is_native;
 }
 #endif
 
@@ -498,7 +499,7 @@ int main(int argc, char **argv)
 	nerrs += test_vsys_r();
 
 #ifdef __x86_64__
-	nerrs += test_native_vsyscall();
+	nerrs += test_emulation();
 #endif
 
 	return nerrs ? 1 : 0;