Merge branch 'x86/asm' into x86/apic, to resolve a conflict

Conflicts:
	arch/x86/kernel/apic/io_apic.c
	arch/x86/kernel/apic/vector.c

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

19 files changed, 269 insertions, 53 deletions

diff --git a/tools/hv/Makefile b/tools/hv/Makefile
index 99ffe61051a7..a8ab79556926 100644
--- a/tools/hv/Makefile
+++ b/tools/hv/Makefile
@@ -3,7 +3,7 @@
 CC = $(CROSS_COMPILE)gcc
 PTHREAD_LIBS = -lpthread
 WARNINGS = -Wall -Wextra
-CFLAGS = $(WARNINGS) -g $(PTHREAD_LIBS)
+CFLAGS = $(WARNINGS) -g $(PTHREAD_LIBS) $(shell getconf LFS_CFLAGS)
 
 all: hv_kvp_daemon hv_vss_daemon hv_fcopy_daemon
 %: %.c
diff --git a/tools/hv/hv_vss_daemon.c b/tools/hv/hv_vss_daemon.c
index 5e63f70bd956..506dd0148828 100644
--- a/tools/hv/hv_vss_daemon.c
+++ b/tools/hv/hv_vss_daemon.c
@@ -81,6 +81,7 @@ static int vss_operate(int operation)
 	char match[] = "/dev/";
 	FILE *mounts;
 	struct mntent *ent;
+	char errdir[1024] = {0};
 	unsigned int cmd;
 	int error = 0, root_seen = 0, save_errno = 0;
 
@@ -115,6 +116,8 @@ static int vss_operate(int operation)
 			goto err;
 	}
 
+	endmntent(mounts);
+
 	if (root_seen) {
 		error |= vss_do_freeze("/", cmd);
 		if (error && operation == VSS_OP_FREEZE)
@@ -124,16 +127,19 @@ static int vss_operate(int operation)
 	goto out;
 err:
 	save_errno = errno;
+	if (ent) {
+		strncpy(errdir, ent->mnt_dir, sizeof(errdir)-1);
+		endmntent(mounts);
+	}
 	vss_operate(VSS_OP_THAW);
 	/* Call syslog after we thaw all filesystems */
 	if (ent)
 		syslog(LOG_ERR, "FREEZE of %s failed; error:%d %s",
-		       ent->mnt_dir, save_errno, strerror(save_errno));
+		       errdir, save_errno, strerror(save_errno));
 	else
 		syslog(LOG_ERR, "FREEZE of / failed; error:%d %s", save_errno,
 		       strerror(save_errno));
 out:
-	endmntent(mounts);
 	return error;
 }
 
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index d8fe29fc19a4..8bd960658463 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -16,7 +16,7 @@ MAKEFLAGS += --no-print-directory
 LIBFILE = $(OUTPUT)libapi.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 
 RM = rm -f
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index e0917c0f5d9f..29f94f6f0d9e 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -3865,7 +3865,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			} else if (el_size == 4) {
 				trace_seq_printf(s, "%u", *(uint32_t *)num);
 			} else if (el_size == 8) {
-				trace_seq_printf(s, "%lu", *(uint64_t *)num);
+				trace_seq_printf(s, "%"PRIu64, *(uint64_t *)num);
 			} else {
 				trace_seq_printf(s, "BAD SIZE:%d 0x%x",
 						 el_size, *(uint8_t *)num);
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index bedff6b5b3cf..ad0d9b5342fb 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -132,6 +132,9 @@ int bench_futex_requeue(int argc, const char **argv,
 	if (!fshared)
 		futex_flag = FUTEX_PRIVATE_FLAG;
 
+	if (nrequeue > nthreads)
+		nrequeue = nthreads;
+
 	printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
 	       "%d at a time.\n\n",  getpid(), nthreads,
 	       fshared ? "shared":"private", &futex1, &futex2, nrequeue);
@@ -161,20 +164,18 @@ int bench_futex_requeue(int argc, const char **argv,
 
 		/* Ok, all threads are patiently blocked, start requeueing */
 		gettimeofday(&start, NULL);
-		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) {
+		while (nrequeued < nthreads) {
 			/*
 			 * Do not wakeup any tasks blocked on futex1, allowing
 			 * us to really measure futex_wait functionality.
 			 */
-			futex_cmp_requeue(&futex1, 0, &futex2, 0,
-					  nrequeue, futex_flag);
+			nrequeued += futex_cmp_requeue(&futex1, 0, &futex2, 0,
+						       nrequeue, futex_flag);
 		}
+
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 
-		if (nrequeued > nthreads)
-			nrequeued = nthreads;
-
 		update_stats(&requeued_stats, nrequeued);
 		update_stats(&requeuetime_stats, runtime.tv_usec);
 
@@ -184,7 +185,7 @@ int bench_futex_requeue(int argc, const char **argv,
 		}
 
 		/* everybody should be blocked on futex2, wake'em up */
-		nrequeued = futex_wake(&futex2, nthreads, futex_flag);
+		nrequeued = futex_wake(&futex2, nrequeued, futex_flag);
 		if (nthreads != nrequeued)
 			warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
 
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index ebfa163b80b5..ba5efa4710b5 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -180,7 +180,7 @@ static const struct option options[] = {
 	OPT_INTEGER('H', "thp"		, &p0.thp,		"MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"),
 	OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"),
 	OPT_BOOLEAN('m', "measure_convergence",	&p0.measure_convergence, "measure convergence latency"),
-	OPT_BOOLEAN('q', "quiet"	, &p0.show_quiet,	"bzero the initial allocations"),
+	OPT_BOOLEAN('q', "quiet"	, &p0.show_quiet,	"quiet mode"),
 	OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"),
 
 	/* Special option string parsing callbacks: */
@@ -828,6 +828,9 @@ static int count_process_nodes(int process_nr)
 		td = g->threads + task_nr;
 
 		node = numa_node_of_cpu(td->curr_cpu);
+		if (node < 0) /* curr_cpu was likely still -1 */
+			return 0;
+
 		node_present[node] = 1;
 	}
 
@@ -882,6 +885,11 @@ static void calc_convergence_compression(int *strong)
 	for (p = 0; p < g->p.nr_proc; p++) {
 		unsigned int nodes = count_process_nodes(p);
 
+		if (!nodes) {
+			*strong = 0;
+			return;
+		}
+
 		nodes_min = min(nodes, nodes_min);
 		nodes_max = max(nodes, nodes_max);
 	}
@@ -1395,7 +1403,7 @@ static void print_res(const char *name, double val,
 	if (!name)
 		name = "main,";
 
-	if (g->p.show_quiet)
+	if (!g->p.show_quiet)
 		printf(" %-30s %15.3f, %-15s %s\n", name, val, txt_unit, txt_short);
 	else
 		printf(" %14.3f %s\n", val, txt_long);
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 63ea01349b6e..1634186d537c 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -319,7 +319,7 @@ static int page_stat_cmp(struct page_stat *a, struct page_stat *b)
 	return 0;
 }
 
-static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool create)
+static struct page_stat *search_page_alloc_stat(struct page_stat *pstat, bool create)
 {
 	struct rb_node **node = &page_alloc_tree.rb_node;
 	struct rb_node *parent = NULL;
@@ -331,7 +331,7 @@ static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool cre
 		parent = *node;
 		data = rb_entry(*node, struct page_stat, node);
 
-		cmp = page_stat_cmp(data, stat);
+		cmp = page_stat_cmp(data, pstat);
 		if (cmp < 0)
 			node = &parent->rb_left;
 		else if (cmp > 0)
@@ -345,10 +345,10 @@ static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool cre
 
 	data = zalloc(sizeof(*data));
 	if (data != NULL) {
-		data->page = stat->page;
-		data->order = stat->order;
-		data->gfp_flags = stat->gfp_flags;
-		data->migrate_type = stat->migrate_type;
+		data->page = pstat->page;
+		data->order = pstat->order;
+		data->gfp_flags = pstat->gfp_flags;
+		data->migrate_type = pstat->migrate_type;
 
 		rb_link_node(&data->node, parent, node);
 		rb_insert_color(&data->node, &page_alloc_tree);
@@ -375,7 +375,7 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 	unsigned int migrate_type = perf_evsel__intval(evsel, sample,
 						       "migratetype");
 	u64 bytes = kmem_page_size << order;
-	struct page_stat *stat;
+	struct page_stat *pstat;
 	struct page_stat this = {
 		.order = order,
 		.gfp_flags = gfp_flags,
@@ -401,21 +401,21 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 	 * This is to find the current page (with correct gfp flags and
 	 * migrate type) at free event.
 	 */
-	stat = search_page(page, true);
-	if (stat == NULL)
+	pstat = search_page(page, true);
+	if (pstat == NULL)
 		return -ENOMEM;
 
-	stat->order = order;
-	stat->gfp_flags = gfp_flags;
-	stat->migrate_type = migrate_type;
+	pstat->order = order;
+	pstat->gfp_flags = gfp_flags;
+	pstat->migrate_type = migrate_type;
 
 	this.page = page;
-	stat = search_page_alloc_stat(&this, true);
-	if (stat == NULL)
+	pstat = search_page_alloc_stat(&this, true);
+	if (pstat == NULL)
 		return -ENOMEM;
 
-	stat->nr_alloc++;
-	stat->alloc_bytes += bytes;
+	pstat->nr_alloc++;
+	pstat->alloc_bytes += bytes;
 
 	order_stats[order][migrate_type]++;
 
@@ -428,7 +428,7 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	u64 page;
 	unsigned int order = perf_evsel__intval(evsel, sample, "order");
 	u64 bytes = kmem_page_size << order;
-	struct page_stat *stat;
+	struct page_stat *pstat;
 	struct page_stat this = {
 		.order = order,
 	};
@@ -441,8 +441,8 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	nr_page_frees++;
 	total_page_free_bytes += bytes;
 
-	stat = search_page(page, false);
-	if (stat == NULL) {
+	pstat = search_page(page, false);
+	if (pstat == NULL) {
 		pr_debug2("missing free at page %"PRIx64" (order: %d)\n",
 			  page, order);
 
@@ -453,18 +453,18 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	}
 
 	this.page = page;
-	this.gfp_flags = stat->gfp_flags;
-	this.migrate_type = stat->migrate_type;
+	this.gfp_flags = pstat->gfp_flags;
+	this.migrate_type = pstat->migrate_type;
 
-	rb_erase(&stat->node, &page_tree);
-	free(stat);
+	rb_erase(&pstat->node, &page_tree);
+	free(pstat);
 
-	stat = search_page_alloc_stat(&this, false);
-	if (stat == NULL)
+	pstat = search_page_alloc_stat(&this, false);
+	if (pstat == NULL)
 		return -ENOENT;
 
-	stat->nr_free++;
-	stat->free_bytes += bytes;
+	pstat->nr_free++;
+	pstat->free_bytes += bytes;
 
 	return 0;
 }
@@ -640,9 +640,9 @@ static void print_page_summary(void)
 	       nr_page_frees, total_page_free_bytes / 1024);
 	printf("\n");
 
-	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total alloc+freed requests",
+	printf("%-30s: %'16"PRIu64"   [ %'16"PRIu64" KB ]\n", "Total alloc+freed requests",
 	       nr_alloc_freed, (total_alloc_freed_bytes) / 1024);
-	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total alloc-only requests",
+	printf("%-30s: %'16"PRIu64"   [ %'16"PRIu64" KB ]\n", "Total alloc-only requests",
 	       nr_page_allocs - nr_alloc_freed,
 	       (total_page_alloc_bytes - total_alloc_freed_bytes) / 1024);
 	printf("%-30s: %'16lu   [ %'16"PRIu64" KB ]\n", "Total free-only requests",
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 476cdf7afcca..b63aeda719be 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -329,7 +329,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 		fprintf(stdout, "\n\n");
 	}
 
-	if (sort_order == default_sort_order &&
+	if (sort_order == NULL &&
 	    parent_pattern == default_parent_pattern) {
 		fprintf(stdout, "#\n# (%s)\n#\n", help);
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1cb3436276d1..6a4d5d41c671 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -733,7 +733,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict.\n\n"
 "Kernel%s samples will not be resolved.\n",
-			  !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
+			  al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
 			  " modules" : "");
 		if (use_browser <= 0)
 			sleep(5);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e124741be187..e122970361f2 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2241,10 +2241,11 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	if (err < 0)
 		goto out_error_mmap;
 
+	if (!target__none(&trace->opts.target))
+		perf_evlist__enable(evlist);
+
 	if (forks)
 		perf_evlist__start_workload(evlist);
-	else
-		perf_evlist__enable(evlist);
 
 	trace->multiple_threads = evlist->threads->map[0] == -1 ||
 				  evlist->threads->nr > 1 ||
@@ -2272,6 +2273,11 @@ next_event:
 
 			if (interrupted)
 				goto out_disable;
+
+			if (done && !draining) {
+				perf_evlist__disable(evlist);
+				draining = true;
+			}
 		}
 	}
 
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d8bb616ff57c..d05b77cf35f7 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1084,6 +1084,8 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 	 *
 	 * TODO:Group name support
 	 */
+	if (!arg)
+		return -EINVAL;
 
 	ptr = strpbrk(arg, ";=@+%");
 	if (ptr && *ptr == '=') {	/* Event name */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index b5bf9d5efeaf..2a76e14db732 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -578,10 +578,12 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 	/* Search child die for local variables and parameters. */
 	if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) {
 		/* Search again in global variables */
-		if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die))
+		if (!die_find_variable_at(&pf->cu_die, pf->pvar->var,
+						0, &vr_die)) {
 			pr_warning("Failed to find '%s' in this function.\n",
 				   pf->pvar->var);
 			ret = -ENOENT;
+		}
 	}
 	if (ret >= 0)
 		ret = convert_variable(&vr_die, pf);
diff --git a/tools/power/cpupower/utils/helpers/pci.c b/tools/power/cpupower/utils/helpers/pci.c
index 9690798e6446..8b278983cfc5 100644
--- a/tools/power/cpupower/utils/helpers/pci.c
+++ b/tools/power/cpupower/utils/helpers/pci.c
@@ -25,14 +25,21 @@
 struct pci_dev *pci_acc_init(struct pci_access **pacc, int domain, int bus,
 			     int slot, int func, int vendor, int dev)
 {
-	struct pci_filter filter_nb_link = { domain, bus, slot, func,
-					     vendor, dev };
+	struct pci_filter filter_nb_link;
 	struct pci_dev *device;
 
 	*pacc = pci_alloc();
 	if (*pacc == NULL)
 		return NULL;
 
+	pci_filter_init(*pacc, &filter_nb_link);
+	filter_nb_link.domain	= domain;
+	filter_nb_link.bus	= bus;
+	filter_nb_link.slot	= slot;
+	filter_nb_link.func	= func;
+	filter_nb_link.vendor	= vendor;
+	filter_nb_link.device	= dev;
+
 	pci_init(*pacc);
 	pci_scan_bus(*pacc);
 
diff --git a/tools/testing/selftests/powerpc/pmu/Makefile b/tools/testing/selftests/powerpc/pmu/Makefile
index 5a161175bbd4..a9099d9f8f39 100644
--- a/tools/testing/selftests/powerpc/pmu/Makefile
+++ b/tools/testing/selftests/powerpc/pmu/Makefile
@@ -26,7 +26,7 @@ override define EMIT_TESTS
 	$(MAKE) -s -C ebb emit_tests
 endef
 
-DEFAULT_INSTALL := $(INSTALL_RULE)
+DEFAULT_INSTALL_RULE := $(INSTALL_RULE)
 override define INSTALL_RULE
 	$(DEFAULT_INSTALL_RULE)
 	$(MAKE) -C ebb install
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index 1b616fa79e93..6bff955e1d55 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -1,4 +1,4 @@
-TEST_PROGS := tm-resched-dscr tm-syscall
+TEST_PROGS := tm-resched-dscr
 
 all: $(TEST_PROGS)
 
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index ddf63569df5a..9309097f58e8 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -1,6 +1,6 @@
 .PHONY: all all_32 all_64 check_build32 clean run_tests
 
-TARGETS_C_BOTHBITS := sigreturn single_step_syscall
+TARGETS_C_BOTHBITS := sigreturn single_step_syscall sysret_ss_attrs
 
 BINARIES_32 := $(TARGETS_C_BOTHBITS:%=%_32)
 BINARIES_64 := $(TARGETS_C_BOTHBITS:%=%_64)
@@ -46,3 +46,6 @@ check_build32:
 	  echo "  yum install glibc-devel.*i686";			\
 	  exit 1;							\
 	fi
+
+# Some tests have additional dependencies.
+sysret_ss_attrs_64: thunks.S
diff --git a/tools/testing/selftests/x86/run_x86_tests.sh b/tools/testing/selftests/x86/run_x86_tests.sh
index 3fc19b376812..d25034280dd5 100644
--- a/tools/testing/selftests/x86/run_x86_tests.sh
+++ b/tools/testing/selftests/x86/run_x86_tests.sh
@@ -4,10 +4,12 @@
 # script here.
 ./sigreturn_32 || exit 1
 ./single_step_syscall_32 || exit 1
+./sysret_ss_attrs_32 || exit 1
 
 if [[ "$uname -p" -eq "x86_64" ]]; then
     ./sigreturn_64 || exit 1
     ./single_step_syscall_64 || exit 1
+    ./sysret_ss_attrs_64 || exit 1
 fi
 
 exit 0
diff --git a/tools/testing/selftests/x86/sysret_ss_attrs.c b/tools/testing/selftests/x86/sysret_ss_attrs.c
new file mode 100644
index 000000000000..ce42d5a64009
--- /dev/null
+++ b/tools/testing/selftests/x86/sysret_ss_attrs.c
@@ -0,0 +1,112 @@
+/*
+ * sysret_ss_attrs.c - test that syscalls return valid hidden SS attributes
+ * Copyright (c) 2015 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * On AMD CPUs, SYSRET can return with a valid SS descriptor with with
+ * the hidden attributes set to an unusable state.  Make sure the kernel
+ * doesn't let this happen.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <err.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <pthread.h>
+
+static void *threadproc(void *ctx)
+{
+	/*
+	 * Do our best to cause sleeps on this CPU to exit the kernel and
+	 * re-enter with SS = 0.
+	 */
+	while (true)
+		;
+
+	return NULL;
+}
+
+#ifdef __x86_64__
+extern unsigned long call32_from_64(void *stack, void (*function)(void));
+
+asm (".pushsection .text\n\t"
+     ".code32\n\t"
+     "test_ss:\n\t"
+     "pushl $0\n\t"
+     "popl %eax\n\t"
+     "ret\n\t"
+     ".code64");
+extern void test_ss(void);
+#endif
+
+int main()
+{
+	/*
+	 * Start a busy-looping thread on the same CPU we're on.
+	 * For simplicity, just stick everything to CPU 0.  This will
+	 * fail in some containers, but that's probably okay.
+	 */
+	cpu_set_t cpuset;
+	CPU_ZERO(&cpuset);
+	CPU_SET(0, &cpuset);
+	if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0)
+		printf("[WARN]\tsched_setaffinity failed\n");
+
+	pthread_t thread;
+	if (pthread_create(&thread, 0, threadproc, 0) != 0)
+		err(1, "pthread_create");
+
+#ifdef __x86_64__
+	unsigned char *stack32 = mmap(NULL, 4096, PROT_READ | PROT_WRITE,
+				      MAP_32BIT | MAP_ANONYMOUS | MAP_PRIVATE,
+				      -1, 0);
+	if (stack32 == MAP_FAILED)
+		err(1, "mmap");
+#endif
+
+	printf("[RUN]\tSyscalls followed by SS validation\n");
+
+	for (int i = 0; i < 1000; i++) {
+		/*
+		 * Go to sleep and return using sysret (if we're 64-bit
+		 * or we're 32-bit on AMD on a 64-bit kernel).  On AMD CPUs,
+		 * SYSRET doesn't fix up the cached SS descriptor, so the
+		 * kernel needs some kind of workaround to make sure that we
+		 * end the system call with a valid stack segment.  This
+		 * can be a confusing failure because the SS *selector*
+		 * is the same regardless.
+		 */
+		usleep(2);
+
+#ifdef __x86_64__
+		/*
+		 * On 32-bit, just doing a syscall through glibc is enough
+		 * to cause a crash if our cached SS descriptor is invalid.
+		 * On 64-bit, it's not, so try extra hard.
+		 */
+		call32_from_64(stack32 + 4088, test_ss);
+#endif
+	}
+
+	printf("[OK]\tWe survived\n");
+
+#ifdef __x86_64__
+	munmap(stack32, 4096);
+#endif
+
+	return 0;
+}
diff --git a/tools/testing/selftests/x86/thunks.S b/tools/testing/selftests/x86/thunks.S
new file mode 100644
index 000000000000..ce8a995bbb17
--- /dev/null
+++ b/tools/testing/selftests/x86/thunks.S
@@ -0,0 +1,67 @@
+/*
+ * thunks.S - assembly helpers for mixed-bitness code
+ * Copyright (c) 2015 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * These are little helpers that make it easier to switch bitness on
+ * the fly.
+ */
+
+	.text
+
+	.global call32_from_64
+	.type call32_from_64, @function
+call32_from_64:
+	// rdi: stack to use
+	// esi: function to call
+
+	// Save registers
+	pushq %rbx
+	pushq %rbp
+	pushq %r12
+	pushq %r13
+	pushq %r14
+	pushq %r15
+	pushfq
+
+	// Switch stacks
+	mov %rsp,(%rdi)
+	mov %rdi,%rsp
+
+	// Switch to compatibility mode
+	pushq $0x23  /* USER32_CS */
+	pushq $1f
+	lretq
+
+1:
+	.code32
+	// Call the function
+	call *%esi
+	// Switch back to long mode
+	jmp $0x33,$1f
+	.code64
+
+1:
+	// Restore the stack
+	mov (%rsp),%rsp
+
+	// Restore registers
+	popfq
+	popq %r15
+	popq %r14
+	popq %r13
+	popq %r12
+	popq %rbp
+	popq %rbx
+
+	ret
+
+.size call32_from_64, .-call32_from_64