Backmerge tag 'v4.14-rc7' into drm-next

Linux 4.14-rc7

Requested by Ben Skeggs for nouveau to avoid major conflicts,
and things were getting a bit conflicty already, esp around amdgpu
reverts.

28 files changed, 754 insertions, 71 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 43ab5c4..c174971 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -312,7 +312,7 @@ union bpf_attr {
  *     jump into another BPF program
  *     @ctx: context pointer passed to next program
  *     @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY
- *     @index: index inside array that selects specific program to run
+ *     @index: 32-bit index inside array that selects specific program to run
  *     Return: 0 on success or negative error
  *
  * int bpf_clone_redirect(skb, ifindex, flags)
@@ -569,9 +569,10 @@ union bpf_attr {
  *     @flags: reserved for future use
  *     Return: 0 on success or negative error code
  *
- * int bpf_sk_redirect_map(map, key, flags)
+ * int bpf_sk_redirect_map(skb, map, key, flags)
  *     Redirect skb to a sock in map using key as a lookup key for the
  *     sock in map.
+ *     @skb: pointer to skb
  *     @map: pointer to sockmap
  *     @key: key to lookup sock in map
  *     @flags: reserved for future use
@@ -786,8 +787,8 @@ struct xdp_md {
 };
 
 enum sk_action {
-	SK_ABORTED = 0,
-	SK_DROP,
+	SK_DROP = 0,
+	SK_PASS,
 	SK_REDIRECT,
 };
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index a0c518e..c0e26ad 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -267,12 +267,13 @@ static int decode_instructions(struct objtool_file *file)
 						      &insn->immediate,
 						      &insn->stack_op);
 			if (ret)
-				return ret;
+				goto err;
 
 			if (!insn->type || insn->type > INSN_LAST) {
 				WARN_FUNC("invalid instruction type %d",
 					  insn->sec, insn->offset, insn->type);
-				return -1;
+				ret = -1;
+				goto err;
 			}
 
 			hash_add(file->insn_hash, &insn->hash, insn->offset);
@@ -296,6 +297,10 @@ static int decode_instructions(struct objtool_file *file)
 	}
 
 	return 0;
+
+err:
+	free(insn);
+	return ret;
 }
 
 /*
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index e397453..63526f4 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -8,8 +8,8 @@ perf-record - Run a command and record its profile into perf.data
 SYNOPSIS
 --------
 [verse]
-'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] <command>
-'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] -- <command> [<options>]
+'perf record' [-e <EVENT> | --event=EVENT] [-a] <command>
+'perf record' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
 
 DESCRIPTION
 -----------
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 3d4c3b5..0c977b6 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -586,7 +586,7 @@ static void print_sample_brstack(struct perf_sample *sample,
 			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
 		}
 
-		printf("0x%"PRIx64, from);
+		printf(" 0x%"PRIx64, from);
 		if (PRINT_FIELD(DSO)) {
 			printf("(");
 			map__fprintf_dsoname(alf.map, stdout);
@@ -681,7 +681,7 @@ static void print_sample_brstackoff(struct perf_sample *sample,
 		if (alt.map && !alt.map->dso->adjust_symbols)
 			to = map__map_ip(alt.map, to);
 
-		printf("0x%"PRIx64, from);
+		printf(" 0x%"PRIx64, from);
 		if (PRINT_FIELD(DSO)) {
 			printf("(");
 			map__fprintf_dsoname(alf.map, stdout);
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
index 462fc75..7a84d73 100755
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
@@ -10,6 +10,9 @@
 
 . $(dirname $0)/lib/probe.sh
 
+ld=$(realpath /lib64/ld*.so.* | uniq)
+libc=$(echo $ld | sed 's/ld/libc/g')
+
 trace_libc_inet_pton_backtrace() {
 	idx=0
 	expected[0]="PING.*bytes"
@@ -18,8 +21,8 @@ trace_libc_inet_pton_backtrace() {
 	expected[3]=".*packets transmitted.*"
 	expected[4]="rtt min.*"
 	expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)"
-	expected[6]=".*inet_pton[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$"
-	expected[7]="getaddrinfo[[:space:]]\(/usr/lib.*/libc-[0-9]+\.[0-9]+\.so\)$"
+	expected[6]=".*inet_pton[[:space:]]\($libc\)$"
+	expected[7]="getaddrinfo[[:space:]]\($libc\)$"
 	expected[8]=".*\(.*/bin/ping.*\)$"
 
 	perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
@@ -35,7 +38,7 @@ trace_libc_inet_pton_backtrace() {
 }
 
 skip_if_no_perf_probe && \
-perf probe -q /lib64/libc-*.so inet_pton && \
+perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace
 err=$?
 rm -f ${file}
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index ddb2c6f..db79017 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -532,7 +532,7 @@ void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
 
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
-	list_del(&format->list);
+	list_del_init(&format->list);
 }
 
 void perf_hpp__cancel_cumulate(void)
@@ -606,6 +606,13 @@ next:
 
 static void fmt_free(struct perf_hpp_fmt *fmt)
 {
+	/*
+	 * At this point fmt should be completely
+	 * unhooked, if not it's a bug.
+	 */
+	BUG_ON(!list_empty(&fmt->list));
+	BUG_ON(!list_empty(&fmt->sort_list));
+
 	if (fmt->free)
 		fmt->free(fmt);
 }
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index be09d77..a971caf 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -685,6 +685,8 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 {
 	struct symbol *sym = node->sym;
 	u64 left, right;
+	struct dso *left_dso = NULL;
+	struct dso *right_dso = NULL;
 
 	if (callchain_param.key == CCKEY_SRCLINE) {
 		enum match_result match = match_chain_srcline(node, cnode);
@@ -696,12 +698,14 @@ static enum match_result match_chain(struct callchain_cursor_node *node,
 	if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
 		left = cnode->ms.sym->start;
 		right = sym->start;
+		left_dso = cnode->ms.map->dso;
+		right_dso = node->map->dso;
 	} else {
 		left = cnode->ip;
 		right = node->ip;
 	}
 
-	if (left == right) {
+	if (left == right && left_dso == right_dso) {
 		if (node->branch) {
 			cnode->branch_count++;
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f6257fb..39b1596 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -309,10 +309,11 @@ static char *get_config_name(struct list_head *head_terms)
 static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
 	    struct perf_event_attr *attr,
-	    char *name, struct cpu_map *cpus,
+	    char *name, struct perf_pmu *pmu,
 	    struct list_head *config_terms, bool auto_merge_stats)
 {
 	struct perf_evsel *evsel;
+	struct cpu_map *cpus = pmu ? pmu->cpus : NULL;
 
 	event_attr_init(attr);
 
@@ -323,7 +324,7 @@ __add_event(struct list_head *list, int *idx,
 	(*idx)++;
 	evsel->cpus        = cpu_map__get(cpus);
 	evsel->own_cpus    = cpu_map__get(cpus);
-	evsel->system_wide = !!cpus;
+	evsel->system_wide = pmu ? pmu->is_uncore : false;
 	evsel->auto_merge_stats = auto_merge_stats;
 
 	if (name)
@@ -1233,7 +1234,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu->cpus, NULL, auto_merge_stats);
+		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
 		return evsel ? 0 : -ENOMEM;
 	}
 
@@ -1254,7 +1255,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 		return -EINVAL;
 
 	evsel = __add_event(list, &parse_state->idx, &attr,
-			    get_config_name(head_config), pmu->cpus,
+			    get_config_name(head_config), pmu,
 			    &config_terms, auto_merge_stats);
 	if (evsel) {
 		evsel->unit = info.unit;
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index c42edea..dcfdafd 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -8,6 +8,9 @@
 
 %{
 #include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
 #include "../perf.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
@@ -53,9 +56,8 @@ static int str(yyscan_t scanner, int token)
 	return token;
 }
 
-static bool isbpf(yyscan_t scanner)
+static bool isbpf_suffix(char *text)
 {
-	char *text = parse_events_get_text(scanner);
 	int len = strlen(text);
 
 	if (len < 2)
@@ -68,6 +70,17 @@ static bool isbpf(yyscan_t scanner)
 	return false;
 }
 
+static bool isbpf(yyscan_t scanner)
+{
+	char *text = parse_events_get_text(scanner);
+	struct stat st;
+
+	if (!isbpf_suffix(text))
+		return false;
+
+	return stat(text, &st) == 0;
+}
+
 /*
  * This function is called when the parser gets two kind of input:
  *
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index ac16a9d..1c4d7b4 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -470,17 +470,36 @@ static void pmu_read_sysfs(void)
 	closedir(dir);
 }
 
+static struct cpu_map *__pmu_cpumask(const char *path)
+{
+	FILE *file;
+	struct cpu_map *cpus;
+
+	file = fopen(path, "r");
+	if (!file)
+		return NULL;
+
+	cpus = cpu_map__read(file);
+	fclose(file);
+	return cpus;
+}
+
+/*
+ * Uncore PMUs have a "cpumask" file under sysfs. CPU PMUs (e.g. on arm/arm64)
+ * may have a "cpus" file.
+ */
+#define CPUS_TEMPLATE_UNCORE	"%s/bus/event_source/devices/%s/cpumask"
+#define CPUS_TEMPLATE_CPU	"%s/bus/event_source/devices/%s/cpus"
+
 static struct cpu_map *pmu_cpumask(const char *name)
 {
-	struct stat st;
 	char path[PATH_MAX];
-	FILE *file;
 	struct cpu_map *cpus;
 	const char *sysfs = sysfs__mountpoint();
 	const char *templates[] = {
-		 "%s/bus/event_source/devices/%s/cpumask",
-		 "%s/bus/event_source/devices/%s/cpus",
-		 NULL
+		CPUS_TEMPLATE_UNCORE,
+		CPUS_TEMPLATE_CPU,
+		NULL
 	};
 	const char **template;
 
@@ -489,20 +508,25 @@ static struct cpu_map *pmu_cpumask(const char *name)
 
 	for (template = templates; *template; template++) {
 		snprintf(path, PATH_MAX, *template, sysfs, name);
-		if (stat(path, &st) == 0)
-			break;
+		cpus = __pmu_cpumask(path);
+		if (cpus)
+			return cpus;
 	}
 
-	if (!*template)
-		return NULL;
+	return NULL;
+}
 
-	file = fopen(path, "r");
-	if (!file)
-		return NULL;
+static bool pmu_is_uncore(const char *name)
+{
+	char path[PATH_MAX];
+	struct cpu_map *cpus;
+	const char *sysfs = sysfs__mountpoint();
 
-	cpus = cpu_map__read(file);
-	fclose(file);
-	return cpus;
+	snprintf(path, PATH_MAX, CPUS_TEMPLATE_UNCORE, sysfs, name);
+	cpus = __pmu_cpumask(path);
+	cpu_map__put(cpus);
+
+	return !!cpus;
 }
 
 /*
@@ -617,6 +641,8 @@ static struct perf_pmu *pmu_lookup(const char *name)
 
 	pmu->cpus = pmu_cpumask(name);
 
+	pmu->is_uncore = pmu_is_uncore(name);
+
 	INIT_LIST_HEAD(&pmu->format);
 	INIT_LIST_HEAD(&pmu->aliases);
 	list_splice(&format, &pmu->format);
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 389e972..fe0de05 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -22,6 +22,7 @@ struct perf_pmu {
 	char *name;
 	__u32 type;
 	bool selectable;
+	bool is_uncore;
 	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index a7ebd9f..76ab070 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -374,6 +374,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->mmap2 = process_event_stub;
 	if (tool->comm == NULL)
 		tool->comm = process_event_stub;
+	if (tool->namespaces == NULL)
+		tool->namespaces = process_event_stub;
 	if (tool->fork == NULL)
 		tool->fork = process_event_stub;
 	if (tool->exit == NULL)
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
index 4ba726c..54af6046 100644
--- a/tools/perf/util/xyarray.h
+++ b/tools/perf/util/xyarray.h
@@ -23,12 +23,12 @@ static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
 
 static inline int xyarray__max_y(struct xyarray *xy)
 {
-	return xy->max_x;
+	return xy->max_y;
 }
 
 static inline int xyarray__max_x(struct xyarray *xy)
 {
-	return xy->max_y;
+	return xy->max_x;
 }
 
 #endif /* _PERF_XYARRAY_H_ */
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index 4c5a481..d6e1c02 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -26,7 +26,7 @@ endif
 
 ifneq ($(OUTPUT),)
 # check that the output directory actually exists
-OUTDIR := $(realpath $(OUTPUT))
+OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
 $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
 endif
 
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 0dafba2..bd9c6b3 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -92,7 +92,6 @@ unsigned int do_ring_perf_limit_reasons;
 unsigned int crystal_hz;
 unsigned long long tsc_hz;
 int base_cpu;
-int do_migrate;
 double discover_bclk(unsigned int family, unsigned int model);
 unsigned int has_hwp;	/* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */
 			/* IA32_HWP_REQUEST, IA32_HWP_STATUS */
@@ -303,9 +302,6 @@ int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg
 
 int cpu_migrate(int cpu)
 {
-	if (!do_migrate)
-		return 0;
-
 	CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
 	CPU_SET_S(cpu, cpu_affinity_setsize, cpu_affinity_set);
 	if (sched_setaffinity(0, cpu_affinity_setsize, cpu_affinity_set) == -1)
@@ -5007,7 +5003,6 @@ void cmdline(int argc, char **argv)
 		{"hide",	required_argument,	0, 'H'},	// meh, -h taken by --help
 		{"Joules",	no_argument,		0, 'J'},
 		{"list",	no_argument,		0, 'l'},
-		{"migrate",	no_argument,		0, 'm'},
 		{"out",		required_argument,	0, 'o'},
 		{"quiet",	no_argument,		0, 'q'},
 		{"show",	required_argument,	0, 's'},
@@ -5019,7 +5014,7 @@ void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
-	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:Jmo:qST:v",
+	while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v",
 				long_options, &option_index)) != -1) {
 		switch (opt) {
 		case 'a':
@@ -5062,9 +5057,6 @@ void cmdline(int argc, char **argv)
 			list_header_only++;
 			quiet++;
 			break;
-		case 'm':
-			do_migrate = 1;
-			break;
 		case 'o':
 			outf = fopen_or_die(optarg, "w");
 			break;
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 9dc8f07..1e8b611 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -1,7 +1,7 @@
 ifneq ($(O),)
 ifeq ($(origin O), command line)
-	ABSOLUTE_O := $(realpath $(O))
-	dummy := $(if $(ABSOLUTE_O),,$(error O=$(O) does not exist))
+	dummy := $(if $(shell test -d $(O) || echo $(O)),$(error O=$(O) does not exist),)
+	ABSOLUTE_O := $(shell cd $(O) ; pwd)
 	OUTPUT := $(ABSOLUTE_O)/$(if $(subdir),$(subdir)/)
 	COMMAND_O := O=$(ABSOLUTE_O)
 ifeq ($(objtree),)
@@ -12,7 +12,7 @@ endif
 
 # check that the output directory actually exists
 ifneq ($(OUTPUT),)
-OUTDIR := $(realpath $(OUTPUT))
+OUTDIR := $(shell cd $(OUTPUT) && /bin/pwd)
 $(if $(OUTDIR),, $(error output directory "$(OUTPUT)" does not exist))
 endif
 
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 36fb916..b2e02bd 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -65,7 +65,7 @@ static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
 static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
 			     int optlen) =
 	(void *) BPF_FUNC_setsockopt;
-static int (*bpf_sk_redirect_map)(void *map, int key, int flags) =
+static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) =
 	(void *) BPF_FUNC_sk_redirect_map;
 static int (*bpf_sock_map_update)(void *map, void *key, void *value,
 				  unsigned long long flags) =
diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
index 9b99bd1..2cd2d55 100644
--- a/tools/testing/selftests/bpf/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/sockmap_verdict_prog.c
@@ -61,8 +61,8 @@ int bpf_prog2(struct __sk_buff *skb)
 	bpf_printk("verdict: data[0] = redir(%u:%u)\n", map, sk);
 
 	if (!map)
-		return bpf_sk_redirect_map(&sock_map_rx, sk, 0);
-	return bpf_sk_redirect_map(&sock_map_tx, sk, 0);
+		return bpf_sk_redirect_map(skb, &sock_map_rx, sk, 0);
+	return bpf_sk_redirect_map(skb, &sock_map_tx, sk, 0);
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index fe3a443..50ce52d 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -466,7 +466,7 @@ static void test_sockmap(int tasks, void *data)
 	int one = 1, map_fd_rx, map_fd_tx, map_fd_break, s, sc, rc;
 	struct bpf_map *bpf_map_rx, *bpf_map_tx, *bpf_map_break;
 	int ports[] = {50200, 50201, 50202, 50204};
-	int err, i, fd, sfd[6] = {0xdeadbeef};
+	int err, i, fd, udp, sfd[6] = {0xdeadbeef};
 	u8 buf[20] = {0x0, 0x5, 0x3, 0x2, 0x1, 0x0};
 	int parse_prog, verdict_prog;
 	struct sockaddr_in addr;
@@ -548,6 +548,16 @@ static void test_sockmap(int tasks, void *data)
 		goto out_sockmap;
 	}
 
+	/* Test update with unsupported UDP socket */
+	udp = socket(AF_INET, SOCK_DGRAM, 0);
+	i = 0;
+	err = bpf_map_update_elem(fd, &i, &udp, BPF_ANY);
+	if (!err) {
+		printf("Failed socket SOCK_DGRAM allowed '%i:%i'\n",
+		       i, udp);
+		goto out_sockmap;
+	}
+
 	/* Test update without programs */
 	for (i = 0; i < 6; i++) {
 		err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY);
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 26f3250..64ae21f 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -1130,15 +1130,27 @@ static struct bpf_test tests[] = {
 		.errstr = "invalid bpf_context access",
 	},
 	{
-		"check skb->mark is writeable by SK_SKB",
+		"invalid access of skb->mark for SK_SKB",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_EXIT_INSN(),
+		},
+		.result =  REJECT,
+		.prog_type = BPF_PROG_TYPE_SK_SKB,
+		.errstr = "invalid bpf_context access",
+	},
+	{
+		"check skb->mark is not writeable by SK_SKB",
 		.insns = {
 			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0,
 				    offsetof(struct __sk_buff, mark)),
 			BPF_EXIT_INSN(),
 		},
-		.result = ACCEPT,
+		.result =  REJECT,
 		.prog_type = BPF_PROG_TYPE_SK_SKB,
+		.errstr = "invalid bpf_context access",
 	},
 	{
 		"check skb->tc_index is writeable by SK_SKB",
@@ -6645,6 +6657,500 @@ static struct bpf_test tests[] = {
 		.errstr = "BPF_END uses reserved fields",
 		.result = REJECT,
 	},
+	{
+		"arithmetic ops make PTR_TO_CTX unusable",
+		.insns = {
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1,
+				      offsetof(struct __sk_buff, data) -
+				      offsetof(struct __sk_buff, mark)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+				    offsetof(struct __sk_buff, mark)),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "dereference of modified ctx ptr R1 off=68+8, ctx+const is allowed, ctx+const+const is not",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	},
+	{
+		"XDP pkt read, pkt_end mangling, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end mangling, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_ALU64_IMM(BPF_SUB, BPF_REG_3, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' > pkt_end, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' > pkt_end, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data' > pkt_end, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end > pkt_data', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_end > pkt_data', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end > pkt_data', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' < pkt_end, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data' < pkt_end, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' < pkt_end, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end < pkt_data', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end < pkt_data', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_end < pkt_data', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 0),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' >= pkt_end, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data' >= pkt_end, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' >= pkt_end, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_end >= pkt_data', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end >= pkt_data', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_end >= pkt_data', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' <= pkt_end, good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_data' <= pkt_end, bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -4),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_data' <= pkt_end, bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end <= pkt_data', good access",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
+	{
+		"XDP pkt read, pkt_end <= pkt_data', bad access 1",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+	},
+	{
+		"XDP pkt read, pkt_end <= pkt_data', bad access 2",
+		.insns = {
+			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+				    offsetof(struct xdp_md, data)),
+			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+				    offsetof(struct xdp_md, data_end)),
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+			BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 0),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, -5),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.errstr = "R1 offset is outside of the packet",
+		.result = REJECT,
+		.prog_type = BPF_PROG_TYPE_XDP,
+		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile
index 0f5e347..152823b 100644
--- a/tools/testing/selftests/mqueue/Makefile
+++ b/tools/testing/selftests/mqueue/Makefile
@@ -5,8 +5,8 @@ TEST_GEN_PROGS := mq_open_tests mq_perf_tests
 include ../lib.mk
 
 override define RUN_TESTS
-	$(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]"
-	$(OUTPUT)//mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
+	@$(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]"
+	@$(OUTPUT)/mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
 endef
 
 override define EMIT_TESTS
diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
index 00f2866..dd4162f 100644
--- a/tools/testing/selftests/networking/timestamping/rxtimestamp.c
+++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c
@@ -341,7 +341,7 @@ int main(int argc, char **argv)
 			return 0;
 		case 'n':
 			t = atoi(optarg);
-			if (t > ARRAY_SIZE(test_cases))
+			if (t >= ARRAY_SIZE(test_cases))
 				error(1, 0, "Invalid test case: %d", t);
 			all_tests = false;
 			test_cases[t].enabled = true;
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index c727b96..5fa02d8 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -17,5 +17,26 @@
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
         ]
+    },
+    {
+        "id": "d052",
+        "name": "Add 1M filters with the same action",
+        "category": [
+            "filter",
+            "flower"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV2 ingress",
+            "./tdc_batch.py $DEV2 $BATCH_FILE --share_action -n 1000000"
+        ],
+        "cmdUnderTest": "$TC -b $BATCH_FILE",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order 0: gact action drop.*index 1 ref 1000000 bind 1000000",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV2 ingress",
+            "/bin/rm $BATCH_FILE"
+        ]
     }
-]
\ No newline at end of file
+]
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index cd61b78..5f11f5d 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -88,7 +88,7 @@ def prepare_env(cmdlist):
             exit(1)
 
 
-def test_runner(filtered_tests):
+def test_runner(filtered_tests, args):
     """
     Driver function for the unit tests.
 
@@ -105,6 +105,8 @@ def test_runner(filtered_tests):
     for tidx in testlist:
         result = True
         tresult = ""
+        if "flower" in tidx["category"] and args.device == None:
+            continue
         print("Test " + tidx["id"] + ": " + tidx["name"])
         prepare_env(tidx["setup"])
         (p, procout) = exec_cmd(tidx["cmdUnderTest"])
@@ -152,6 +154,10 @@ def ns_create():
         exec_cmd(cmd, False)
         cmd = 'ip -s $NS link set $DEV1 up'
         exec_cmd(cmd, False)
+        cmd = 'ip link set $DEV2 netns $NS'
+        exec_cmd(cmd, False)
+        cmd = 'ip -s $NS link set $DEV2 up'
+        exec_cmd(cmd, False)
 
 
 def ns_destroy():
@@ -211,7 +217,8 @@ def set_args(parser):
                         help='Execute the single test case with specified ID')
     parser.add_argument('-i', '--id', action='store_true', dest='gen_id',
                         help='Generate ID numbers for new test cases')
-    return parser
+    parser.add_argument('-d', '--device',
+                        help='Execute the test case in flower category')
     return parser
 
 
@@ -225,6 +232,8 @@ def check_default_settings(args):
 
     if args.path != None:
          NAMES['TC'] = args.path
+    if args.device != None:
+         NAMES['DEV2'] = args.device
     if not os.path.isfile(NAMES['TC']):
         print("The specified tc path " + NAMES['TC'] + " does not exist.")
         exit(1)
@@ -381,14 +390,17 @@ def set_operation_mode(args):
             if (len(alltests) == 0):
                 print("Cannot find a test case with ID matching " + target_id)
                 exit(1)
-        catresults = test_runner(alltests)
+        catresults = test_runner(alltests, args)
         print("All test results: " + "\n\n" + catresults)
     elif (len(target_category) > 0):
+        if (target_category == "flower") and args.device == None:
+            print("Please specify a NIC device (-d) to run category flower")
+            exit(1)
         if (target_category not in ucat):
             print("Specified category is not present in this file.")
             exit(1)
         else:
-            catresults = test_runner(testcases[target_category])
+            catresults = test_runner(testcases[target_category], args)
             print("Category " + target_category + "\n\n" + catresults)
 
     ns_destroy()
diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py
new file mode 100755
index 0000000..707c6bf
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tdc_batch.py
@@ -0,0 +1,62 @@
+#!/usr/bin/python3
+
+"""
+tdc_batch.py - a script to generate TC batch file
+
+Copyright (C) 2017 Chris Mi <chrism@mellanox.com>
+"""
+
+import argparse
+
+parser = argparse.ArgumentParser(description='TC batch file generator')
+parser.add_argument("device", help="device name")
+parser.add_argument("file", help="batch file name")
+parser.add_argument("-n", "--number", type=int,
+                    help="how many lines in batch file")
+parser.add_argument("-o", "--skip_sw",
+                    help="skip_sw (offload), by default skip_hw",
+                    action="store_true")
+parser.add_argument("-s", "--share_action",
+                    help="all filters share the same action",
+                    action="store_true")
+parser.add_argument("-p", "--prio",
+                    help="all filters have different prio",
+                    action="store_true")
+args = parser.parse_args()
+
+device = args.device
+file = open(args.file, 'w')
+
+number = 1
+if args.number:
+    number = args.number
+
+skip = "skip_hw"
+if args.skip_sw:
+    skip = "skip_sw"
+
+share_action = ""
+if args.share_action:
+    share_action = "index 1"
+
+prio = "prio 1"
+if args.prio:
+    prio = ""
+    if number > 0x4000:
+        number = 0x4000
+
+index = 0
+for i in range(0x100):
+    for j in range(0x100):
+        for k in range(0x100):
+            mac = ("%02x:%02x:%02x" % (i, j, k))
+            src_mac = "e4:11:00:" + mac
+            dst_mac = "e4:12:00:" + mac
+            cmd = ("filter add dev %s %s protocol ip parent ffff: flower %s "
+                   "src_mac %s dst_mac %s action drop %s" %
+                   (device, prio, skip, src_mac, dst_mac, share_action))
+            file.write("%s\n" % cmd)
+            index += 1
+            if index >= number:
+                file.close()
+                exit(0)
diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index 0108737..b635251 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -12,6 +12,8 @@ NAMES = {
           # Name of veth devices to be created for the namespace
           'DEV0': 'v0p0',
           'DEV1': 'v0p1',
+          'DEV2': '',
+          'BATCH_FILE': './batch.txt',
           # Name of the namespace to use
           'NS': 'tcut'
         }
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index a2c53a3..de2f9ec 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -397,7 +397,7 @@ static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy,
 	}
 }
 
-static int copy_page(int ufd, unsigned long offset)
+static int __copy_page(int ufd, unsigned long offset, bool retry)
 {
 	struct uffdio_copy uffdio_copy;
 
@@ -418,7 +418,7 @@ static int copy_page(int ufd, unsigned long offset)
 		fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n",
 			uffdio_copy.copy), exit(1);
 	} else {
-		if (test_uffdio_copy_eexist) {
+		if (test_uffdio_copy_eexist && retry) {
 			test_uffdio_copy_eexist = false;
 			retry_copy_page(ufd, &uffdio_copy, offset);
 		}
@@ -427,6 +427,16 @@ static int copy_page(int ufd, unsigned long offset)
 	return 0;
 }
 
+static int copy_page_retry(int ufd, unsigned long offset)
+{
+	return __copy_page(ufd, offset, true);
+}
+
+static int copy_page(int ufd, unsigned long offset)
+{
+	return __copy_page(ufd, offset, false);
+}
+
 static void *uffd_poll_thread(void *arg)
 {
 	unsigned long cpu = (unsigned long) arg;
@@ -544,7 +554,7 @@ static void *background_thread(void *arg)
 	for (page_nr = cpu * nr_pages_per_cpu;
 	     page_nr < (cpu+1) * nr_pages_per_cpu;
 	     page_nr++)
-		copy_page(uffd, page_nr * page_size);
+		copy_page_retry(uffd, page_nr * page_size);
 
 	return NULL;
 }
@@ -779,7 +789,7 @@ static void retry_uffdio_zeropage(int ufd,
 	}
 }
 
-static int uffdio_zeropage(int ufd, unsigned long offset)
+static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
 {
 	struct uffdio_zeropage uffdio_zeropage;
 	int ret;
@@ -814,7 +824,7 @@ static int uffdio_zeropage(int ufd, unsigned long offset)
 			fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n",
 				uffdio_zeropage.zeropage), exit(1);
 		} else {
-			if (test_uffdio_zeropage_eexist) {
+			if (test_uffdio_zeropage_eexist && retry) {
 				test_uffdio_zeropage_eexist = false;
 				retry_uffdio_zeropage(ufd, &uffdio_zeropage,
 						      offset);
@@ -830,6 +840,11 @@ static int uffdio_zeropage(int ufd, unsigned long offset)
 	return 0;
 }
 
+static int uffdio_zeropage(int ufd, unsigned long offset)
+{
+	return __uffdio_zeropage(ufd, offset, false);
+}
+
 /* exercise UFFDIO_ZEROPAGE */
 static int userfaultfd_zeropage_test(void)
 {
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 97f187e..0a74a20 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -20,7 +20,7 @@ BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64)
 BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
 BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
 
-CFLAGS := -O2 -g -std=gnu99 -pthread -Wall
+CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -no-pie
 
 UNAME_M := $(shell uname -m)
 CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)